20053 lines
596 KiB
JSON
20053 lines
596 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.09643201542912247,
|
|
"eval_steps": 50000,
|
|
"global_step": 100000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 4.8216007714561236e-05,
|
|
"grad_norm": 1.1467028856277466,
|
|
"learning_rate": 1.9200000000000003e-05,
|
|
"loss": 1.567644805908203,
|
|
"num_input_tokens_seen": 121648,
|
|
"step": 50,
|
|
"train_runtime": 159.5452,
|
|
"train_tokens_per_second": 762.467
|
|
},
|
|
{
|
|
"epoch": 9.643201542912247e-05,
|
|
"grad_norm": 2.018777847290039,
|
|
"learning_rate": 3.9200000000000004e-05,
|
|
"loss": 1.3859580993652343,
|
|
"num_input_tokens_seen": 245824,
|
|
"step": 100,
|
|
"train_runtime": 314.357,
|
|
"train_tokens_per_second": 781.99
|
|
},
|
|
{
|
|
"epoch": 0.0001446480231436837,
|
|
"grad_norm": 1.3833121061325073,
|
|
"learning_rate": 5.88e-05,
|
|
"loss": 1.2797930145263672,
|
|
"num_input_tokens_seen": 379360,
|
|
"step": 150,
|
|
"train_runtime": 481.3337,
|
|
"train_tokens_per_second": 788.143
|
|
},
|
|
{
|
|
"epoch": 0.00019286403085824494,
|
|
"grad_norm": 1.5318325757980347,
|
|
"learning_rate": 7.88e-05,
|
|
"loss": 1.2482891082763672,
|
|
"num_input_tokens_seen": 503512,
|
|
"step": 200,
|
|
"train_runtime": 637.514,
|
|
"train_tokens_per_second": 789.805
|
|
},
|
|
{
|
|
"epoch": 0.00024108003857280618,
|
|
"grad_norm": 1.6061843633651733,
|
|
"learning_rate": 9.88e-05,
|
|
"loss": 1.1814483642578124,
|
|
"num_input_tokens_seen": 639096,
|
|
"step": 250,
|
|
"train_runtime": 808.837,
|
|
"train_tokens_per_second": 790.142
|
|
},
|
|
{
|
|
"epoch": 0.0002892960462873674,
|
|
"grad_norm": 1.2636164426803589,
|
|
"learning_rate": 0.0001188,
|
|
"loss": 1.3041719055175782,
|
|
"num_input_tokens_seen": 756672,
|
|
"step": 300,
|
|
"train_runtime": 955.5215,
|
|
"train_tokens_per_second": 791.894
|
|
},
|
|
{
|
|
"epoch": 0.0003375120540019286,
|
|
"grad_norm": 1.7266672849655151,
|
|
"learning_rate": 0.00013879999999999999,
|
|
"loss": 1.1771054077148437,
|
|
"num_input_tokens_seen": 890968,
|
|
"step": 350,
|
|
"train_runtime": 1124.2301,
|
|
"train_tokens_per_second": 792.514
|
|
},
|
|
{
|
|
"epoch": 0.0003857280617164899,
|
|
"grad_norm": 1.5519499778747559,
|
|
"learning_rate": 0.0001588,
|
|
"loss": 1.162370376586914,
|
|
"num_input_tokens_seen": 1021888,
|
|
"step": 400,
|
|
"train_runtime": 1288.6553,
|
|
"train_tokens_per_second": 792.988
|
|
},
|
|
{
|
|
"epoch": 0.0004339440694310511,
|
|
"grad_norm": 1.27588951587677,
|
|
"learning_rate": 0.0001788,
|
|
"loss": 1.2086297607421874,
|
|
"num_input_tokens_seen": 1146344,
|
|
"step": 450,
|
|
"train_runtime": 1443.6451,
|
|
"train_tokens_per_second": 794.062
|
|
},
|
|
{
|
|
"epoch": 0.00048216007714561236,
|
|
"grad_norm": 1.7894173860549927,
|
|
"learning_rate": 0.0001988,
|
|
"loss": 1.18284423828125,
|
|
"num_input_tokens_seen": 1275416,
|
|
"step": 500,
|
|
"train_runtime": 1605.4424,
|
|
"train_tokens_per_second": 794.433
|
|
},
|
|
{
|
|
"epoch": 0.0005303760848601736,
|
|
"grad_norm": 3.2783801555633545,
|
|
"learning_rate": 0.00019999999898532526,
|
|
"loss": 1.1667653656005859,
|
|
"num_input_tokens_seen": 1409448,
|
|
"step": 550,
|
|
"train_runtime": 1773.337,
|
|
"train_tokens_per_second": 794.8
|
|
},
|
|
{
|
|
"epoch": 0.0005785920925747348,
|
|
"grad_norm": 1.5383628606796265,
|
|
"learning_rate": 0.00019999999567810113,
|
|
"loss": 1.2064752960205078,
|
|
"num_input_tokens_seen": 1538544,
|
|
"step": 600,
|
|
"train_runtime": 1935.8516,
|
|
"train_tokens_per_second": 794.763
|
|
},
|
|
{
|
|
"epoch": 0.000626808100289296,
|
|
"grad_norm": 1.818877935409546,
|
|
"learning_rate": 0.00019999999007419363,
|
|
"loss": 1.14654541015625,
|
|
"num_input_tokens_seen": 1669568,
|
|
"step": 650,
|
|
"train_runtime": 2100.2304,
|
|
"train_tokens_per_second": 794.945
|
|
},
|
|
{
|
|
"epoch": 0.0006750241080038572,
|
|
"grad_norm": 2.485257863998413,
|
|
"learning_rate": 0.0001999999821736029,
|
|
"loss": 1.1787911224365235,
|
|
"num_input_tokens_seen": 1796080,
|
|
"step": 700,
|
|
"train_runtime": 2258.815,
|
|
"train_tokens_per_second": 795.143
|
|
},
|
|
{
|
|
"epoch": 0.0007232401157184186,
|
|
"grad_norm": 2.3129396438598633,
|
|
"learning_rate": 0.00019999997197632917,
|
|
"loss": 1.1223541259765626,
|
|
"num_input_tokens_seen": 1923744,
|
|
"step": 750,
|
|
"train_runtime": 2419.9521,
|
|
"train_tokens_per_second": 794.951
|
|
},
|
|
{
|
|
"epoch": 0.0007714561234329798,
|
|
"grad_norm": 2.276571035385132,
|
|
"learning_rate": 0.00019999995948237262,
|
|
"loss": 1.0881556701660156,
|
|
"num_input_tokens_seen": 2058920,
|
|
"step": 800,
|
|
"train_runtime": 2589.1745,
|
|
"train_tokens_per_second": 795.203
|
|
},
|
|
{
|
|
"epoch": 0.000819672131147541,
|
|
"grad_norm": 2.6064651012420654,
|
|
"learning_rate": 0.00019999994469173355,
|
|
"loss": 1.10181884765625,
|
|
"num_input_tokens_seen": 2191112,
|
|
"step": 850,
|
|
"train_runtime": 2754.4133,
|
|
"train_tokens_per_second": 795.491
|
|
},
|
|
{
|
|
"epoch": 0.0008678881388621022,
|
|
"grad_norm": 2.005110263824463,
|
|
"learning_rate": 0.0001999999276044123,
|
|
"loss": 1.1037062072753907,
|
|
"num_input_tokens_seen": 2330168,
|
|
"step": 900,
|
|
"train_runtime": 2928.4577,
|
|
"train_tokens_per_second": 795.698
|
|
},
|
|
{
|
|
"epoch": 0.0009161041465766634,
|
|
"grad_norm": 2.1018550395965576,
|
|
"learning_rate": 0.00019999990822040927,
|
|
"loss": 1.108128662109375,
|
|
"num_input_tokens_seen": 2466872,
|
|
"step": 950,
|
|
"train_runtime": 3100.46,
|
|
"train_tokens_per_second": 795.647
|
|
},
|
|
{
|
|
"epoch": 0.0009643201542912247,
|
|
"grad_norm": 2.00207781791687,
|
|
"learning_rate": 0.00019999988653972493,
|
|
"loss": 1.1243585968017578,
|
|
"num_input_tokens_seen": 2595888,
|
|
"step": 1000,
|
|
"train_runtime": 3262.8102,
|
|
"train_tokens_per_second": 795.599
|
|
},
|
|
{
|
|
"epoch": 0.0010125361620057858,
|
|
"grad_norm": 2.1752774715423584,
|
|
"learning_rate": 0.00019999986256235972,
|
|
"loss": 1.0777310180664061,
|
|
"num_input_tokens_seen": 2735152,
|
|
"step": 1050,
|
|
"train_runtime": 3437.1954,
|
|
"train_tokens_per_second": 795.751
|
|
},
|
|
{
|
|
"epoch": 0.0010607521697203472,
|
|
"grad_norm": 2.0019516944885254,
|
|
"learning_rate": 0.0001999998362883142,
|
|
"loss": 1.0495980072021485,
|
|
"num_input_tokens_seen": 2873496,
|
|
"step": 1100,
|
|
"train_runtime": 3610.3623,
|
|
"train_tokens_per_second": 795.902
|
|
},
|
|
{
|
|
"epoch": 0.0011089681774349085,
|
|
"grad_norm": 1.7995004653930664,
|
|
"learning_rate": 0.00019999980771758901,
|
|
"loss": 1.0169412231445312,
|
|
"num_input_tokens_seen": 3010528,
|
|
"step": 1150,
|
|
"train_runtime": 3782.6356,
|
|
"train_tokens_per_second": 795.881
|
|
},
|
|
{
|
|
"epoch": 0.0011571841851494697,
|
|
"grad_norm": 2.1871795654296875,
|
|
"learning_rate": 0.00019999977685018481,
|
|
"loss": 1.0633456420898437,
|
|
"num_input_tokens_seen": 3148024,
|
|
"step": 1200,
|
|
"train_runtime": 3954.516,
|
|
"train_tokens_per_second": 796.058
|
|
},
|
|
{
|
|
"epoch": 0.0012054001928640309,
|
|
"grad_norm": 2.981612205505371,
|
|
"learning_rate": 0.00019999974368610225,
|
|
"loss": 1.0944416046142578,
|
|
"num_input_tokens_seen": 3288184,
|
|
"step": 1250,
|
|
"train_runtime": 4130.9363,
|
|
"train_tokens_per_second": 795.99
|
|
},
|
|
{
|
|
"epoch": 0.001253616200578592,
|
|
"grad_norm": 2.3446383476257324,
|
|
"learning_rate": 0.00019999970822534216,
|
|
"loss": 1.0464827728271484,
|
|
"num_input_tokens_seen": 3430920,
|
|
"step": 1300,
|
|
"train_runtime": 4310.4336,
|
|
"train_tokens_per_second": 795.957
|
|
},
|
|
{
|
|
"epoch": 0.0013018322082931533,
|
|
"grad_norm": 1.6762936115264893,
|
|
"learning_rate": 0.0001999996704679053,
|
|
"loss": 1.0589771270751953,
|
|
"num_input_tokens_seen": 3578608,
|
|
"step": 1350,
|
|
"train_runtime": 4495.8528,
|
|
"train_tokens_per_second": 795.98
|
|
},
|
|
{
|
|
"epoch": 0.0013500482160077145,
|
|
"grad_norm": 2.360914945602417,
|
|
"learning_rate": 0.0001999996304137926,
|
|
"loss": 1.0319899749755859,
|
|
"num_input_tokens_seen": 3719152,
|
|
"step": 1400,
|
|
"train_runtime": 4672.3792,
|
|
"train_tokens_per_second": 795.987
|
|
},
|
|
{
|
|
"epoch": 0.0013982642237222757,
|
|
"grad_norm": 2.213979959487915,
|
|
"learning_rate": 0.0001999995880630049,
|
|
"loss": 1.0147222137451173,
|
|
"num_input_tokens_seen": 3857072,
|
|
"step": 1450,
|
|
"train_runtime": 4844.9114,
|
|
"train_tokens_per_second": 796.108
|
|
},
|
|
{
|
|
"epoch": 0.0014464802314368371,
|
|
"grad_norm": 2.4567244052886963,
|
|
"learning_rate": 0.00019999954341554324,
|
|
"loss": 1.0593975830078124,
|
|
"num_input_tokens_seen": 3995344,
|
|
"step": 1500,
|
|
"train_runtime": 5018.9364,
|
|
"train_tokens_per_second": 796.054
|
|
},
|
|
{
|
|
"epoch": 0.0014946962391513983,
|
|
"grad_norm": 1.8086879253387451,
|
|
"learning_rate": 0.00019999949647140857,
|
|
"loss": 1.061892318725586,
|
|
"num_input_tokens_seen": 4132240,
|
|
"step": 1550,
|
|
"train_runtime": 5190.4107,
|
|
"train_tokens_per_second": 796.13
|
|
},
|
|
{
|
|
"epoch": 0.0015429122468659595,
|
|
"grad_norm": 1.9579216241836548,
|
|
"learning_rate": 0.00019999944723060207,
|
|
"loss": 1.036820755004883,
|
|
"num_input_tokens_seen": 4268936,
|
|
"step": 1600,
|
|
"train_runtime": 5361.6689,
|
|
"train_tokens_per_second": 796.195
|
|
},
|
|
{
|
|
"epoch": 0.0015911282545805208,
|
|
"grad_norm": 3.109316349029541,
|
|
"learning_rate": 0.0001999993956931248,
|
|
"loss": 1.0769754791259765,
|
|
"num_input_tokens_seen": 4402416,
|
|
"step": 1650,
|
|
"train_runtime": 5529.0053,
|
|
"train_tokens_per_second": 796.24
|
|
},
|
|
{
|
|
"epoch": 0.001639344262295082,
|
|
"grad_norm": 1.9769625663757324,
|
|
"learning_rate": 0.00019999934185897797,
|
|
"loss": 1.0342123413085937,
|
|
"num_input_tokens_seen": 4546648,
|
|
"step": 1700,
|
|
"train_runtime": 5709.4666,
|
|
"train_tokens_per_second": 796.335
|
|
},
|
|
{
|
|
"epoch": 0.0016875602700096432,
|
|
"grad_norm": 3.1573781967163086,
|
|
"learning_rate": 0.00019999928572816278,
|
|
"loss": 0.9480636596679688,
|
|
"num_input_tokens_seen": 4688384,
|
|
"step": 1750,
|
|
"train_runtime": 5888.2485,
|
|
"train_tokens_per_second": 796.227
|
|
},
|
|
{
|
|
"epoch": 0.0017357762777242044,
|
|
"grad_norm": 4.794156074523926,
|
|
"learning_rate": 0.0001999992273006806,
|
|
"loss": 1.0099034118652344,
|
|
"num_input_tokens_seen": 4826296,
|
|
"step": 1800,
|
|
"train_runtime": 6060.8592,
|
|
"train_tokens_per_second": 796.306
|
|
},
|
|
{
|
|
"epoch": 0.0017839922854387656,
|
|
"grad_norm": 3.4145448207855225,
|
|
"learning_rate": 0.00019999916657653267,
|
|
"loss": 1.0405985260009765,
|
|
"num_input_tokens_seen": 4958328,
|
|
"step": 1850,
|
|
"train_runtime": 6227.3456,
|
|
"train_tokens_per_second": 796.219
|
|
},
|
|
{
|
|
"epoch": 0.0018322082931533268,
|
|
"grad_norm": 2.1898574829101562,
|
|
"learning_rate": 0.00019999910355572044,
|
|
"loss": 1.083897476196289,
|
|
"num_input_tokens_seen": 5095688,
|
|
"step": 1900,
|
|
"train_runtime": 6399.1132,
|
|
"train_tokens_per_second": 796.312
|
|
},
|
|
{
|
|
"epoch": 0.0018804243008678882,
|
|
"grad_norm": 2.188990831375122,
|
|
"learning_rate": 0.00019999903823824538,
|
|
"loss": 1.0715613555908203,
|
|
"num_input_tokens_seen": 5233680,
|
|
"step": 1950,
|
|
"train_runtime": 6572.0563,
|
|
"train_tokens_per_second": 796.353
|
|
},
|
|
{
|
|
"epoch": 0.0019286403085824494,
|
|
"grad_norm": 2.812885046005249,
|
|
"learning_rate": 0.00019999897062410892,
|
|
"loss": 1.0710340118408204,
|
|
"num_input_tokens_seen": 5374568,
|
|
"step": 2000,
|
|
"train_runtime": 6750.4919,
|
|
"train_tokens_per_second": 796.174
|
|
},
|
|
{
|
|
"epoch": 0.0019768563162970106,
|
|
"grad_norm": 2.197707414627075,
|
|
"learning_rate": 0.0001999989007133127,
|
|
"loss": 1.0418057250976562,
|
|
"num_input_tokens_seen": 5513520,
|
|
"step": 2050,
|
|
"train_runtime": 6925.322,
|
|
"train_tokens_per_second": 796.139
|
|
},
|
|
{
|
|
"epoch": 0.0020250723240115716,
|
|
"grad_norm": 4.356228351593018,
|
|
"learning_rate": 0.00019999882850585822,
|
|
"loss": 1.0257611083984375,
|
|
"num_input_tokens_seen": 5655128,
|
|
"step": 2100,
|
|
"train_runtime": 7103.6333,
|
|
"train_tokens_per_second": 796.09
|
|
},
|
|
{
|
|
"epoch": 0.002073288331726133,
|
|
"grad_norm": 3.790513038635254,
|
|
"learning_rate": 0.0001999987555143367,
|
|
"loss": 1.0556934356689454,
|
|
"num_input_tokens_seen": 5797136,
|
|
"step": 2150,
|
|
"train_runtime": 7282.3924,
|
|
"train_tokens_per_second": 796.048
|
|
},
|
|
{
|
|
"epoch": 0.0021215043394406945,
|
|
"grad_norm": 3.3590099811553955,
|
|
"learning_rate": 0.00019999867875950398,
|
|
"loss": 1.0168655395507813,
|
|
"num_input_tokens_seen": 5938112,
|
|
"step": 2200,
|
|
"train_runtime": 7459.1088,
|
|
"train_tokens_per_second": 796.089
|
|
},
|
|
{
|
|
"epoch": 0.0021697203471552555,
|
|
"grad_norm": 3.356379985809326,
|
|
"learning_rate": 0.00019999859970801814,
|
|
"loss": 1.0564580535888672,
|
|
"num_input_tokens_seen": 6080208,
|
|
"step": 2250,
|
|
"train_runtime": 7637.7497,
|
|
"train_tokens_per_second": 796.073
|
|
},
|
|
{
|
|
"epoch": 0.002217936354869817,
|
|
"grad_norm": 2.7345423698425293,
|
|
"learning_rate": 0.00019999851835988098,
|
|
"loss": 1.0112544250488282,
|
|
"num_input_tokens_seen": 6217376,
|
|
"step": 2300,
|
|
"train_runtime": 7810.3295,
|
|
"train_tokens_per_second": 796.045
|
|
},
|
|
{
|
|
"epoch": 0.002266152362584378,
|
|
"grad_norm": 3.1642043590545654,
|
|
"learning_rate": 0.00019999843471509444,
|
|
"loss": 0.9988410949707032,
|
|
"num_input_tokens_seen": 6354616,
|
|
"step": 2350,
|
|
"train_runtime": 7983.2194,
|
|
"train_tokens_per_second": 795.997
|
|
},
|
|
{
|
|
"epoch": 0.0023143683702989393,
|
|
"grad_norm": 2.2759008407592773,
|
|
"learning_rate": 0.0001999983487736604,
|
|
"loss": 1.0875826263427735,
|
|
"num_input_tokens_seen": 6498608,
|
|
"step": 2400,
|
|
"train_runtime": 8164.9154,
|
|
"train_tokens_per_second": 795.919
|
|
},
|
|
{
|
|
"epoch": 0.0023625843780135003,
|
|
"grad_norm": 3.780980348587036,
|
|
"learning_rate": 0.00019999826053558083,
|
|
"loss": 1.0278046417236328,
|
|
"num_input_tokens_seen": 6649552,
|
|
"step": 2450,
|
|
"train_runtime": 8354.0003,
|
|
"train_tokens_per_second": 795.972
|
|
},
|
|
{
|
|
"epoch": 0.0024108003857280617,
|
|
"grad_norm": 3.0308001041412354,
|
|
"learning_rate": 0.0001999981700008578,
|
|
"loss": 1.106314697265625,
|
|
"num_input_tokens_seen": 6795280,
|
|
"step": 2500,
|
|
"train_runtime": 8537.2379,
|
|
"train_tokens_per_second": 795.958
|
|
},
|
|
{
|
|
"epoch": 0.002459016393442623,
|
|
"grad_norm": 2.569699764251709,
|
|
"learning_rate": 0.0001999980771694933,
|
|
"loss": 1.0307982635498047,
|
|
"num_input_tokens_seen": 6941704,
|
|
"step": 2550,
|
|
"train_runtime": 8720.9885,
|
|
"train_tokens_per_second": 795.977
|
|
},
|
|
{
|
|
"epoch": 0.002507232401157184,
|
|
"grad_norm": 4.719316005706787,
|
|
"learning_rate": 0.00019999798204148954,
|
|
"loss": 1.0396181488037108,
|
|
"num_input_tokens_seen": 7089976,
|
|
"step": 2600,
|
|
"train_runtime": 8907.3694,
|
|
"train_tokens_per_second": 795.967
|
|
},
|
|
{
|
|
"epoch": 0.0025554484088717456,
|
|
"grad_norm": 4.289868354797363,
|
|
"learning_rate": 0.00019999788461684865,
|
|
"loss": 1.0601388549804687,
|
|
"num_input_tokens_seen": 7237232,
|
|
"step": 2650,
|
|
"train_runtime": 9092.8326,
|
|
"train_tokens_per_second": 795.927
|
|
},
|
|
{
|
|
"epoch": 0.0026036644165863066,
|
|
"grad_norm": 3.532341957092285,
|
|
"learning_rate": 0.00019999778489557292,
|
|
"loss": 1.0399396514892578,
|
|
"num_input_tokens_seen": 7382336,
|
|
"step": 2700,
|
|
"train_runtime": 9275.2918,
|
|
"train_tokens_per_second": 795.914
|
|
},
|
|
{
|
|
"epoch": 0.002651880424300868,
|
|
"grad_norm": 3.3046586513519287,
|
|
"learning_rate": 0.00019999768287766462,
|
|
"loss": 0.9850960540771484,
|
|
"num_input_tokens_seen": 7525072,
|
|
"step": 2750,
|
|
"train_runtime": 9454.8624,
|
|
"train_tokens_per_second": 795.894
|
|
},
|
|
{
|
|
"epoch": 0.002700096432015429,
|
|
"grad_norm": 4.225088596343994,
|
|
"learning_rate": 0.00019999757856312608,
|
|
"loss": 1.0748612976074219,
|
|
"num_input_tokens_seen": 7677864,
|
|
"step": 2800,
|
|
"train_runtime": 9647.049,
|
|
"train_tokens_per_second": 795.877
|
|
},
|
|
{
|
|
"epoch": 0.0027483124397299904,
|
|
"grad_norm": 4.497129440307617,
|
|
"learning_rate": 0.00019999747410668999,
|
|
"loss": 1.0839518737792968,
|
|
"num_input_tokens_seen": 7832576,
|
|
"step": 2850,
|
|
"train_runtime": 9841.4458,
|
|
"train_tokens_per_second": 795.877
|
|
},
|
|
{
|
|
"epoch": 0.0027965284474445514,
|
|
"grad_norm": 1.8247474431991577,
|
|
"learning_rate": 0.0001999973652448307,
|
|
"loss": 1.0246115875244142,
|
|
"num_input_tokens_seen": 7974768,
|
|
"step": 2900,
|
|
"train_runtime": 10020.0572,
|
|
"train_tokens_per_second": 795.88
|
|
},
|
|
{
|
|
"epoch": 0.002844744455159113,
|
|
"grad_norm": 4.121457576751709,
|
|
"learning_rate": 0.0001999972540863485,
|
|
"loss": 1.0360467529296875,
|
|
"num_input_tokens_seen": 8122360,
|
|
"step": 2950,
|
|
"train_runtime": 10204.9984,
|
|
"train_tokens_per_second": 795.92
|
|
},
|
|
{
|
|
"epoch": 0.0028929604628736743,
|
|
"grad_norm": 4.441408157348633,
|
|
"learning_rate": 0.0001999971406312459,
|
|
"loss": 1.1134804534912108,
|
|
"num_input_tokens_seen": 8274368,
|
|
"step": 3000,
|
|
"train_runtime": 10396.968,
|
|
"train_tokens_per_second": 795.844
|
|
},
|
|
{
|
|
"epoch": 0.0029411764705882353,
|
|
"grad_norm": 4.148735523223877,
|
|
"learning_rate": 0.00019999702487952554,
|
|
"loss": 1.0241043853759766,
|
|
"num_input_tokens_seen": 8425784,
|
|
"step": 3050,
|
|
"train_runtime": 10587.6873,
|
|
"train_tokens_per_second": 795.81
|
|
},
|
|
{
|
|
"epoch": 0.0029893924783027967,
|
|
"grad_norm": 2.8046419620513916,
|
|
"learning_rate": 0.00019999690683119003,
|
|
"loss": 1.0935558319091796,
|
|
"num_input_tokens_seen": 8574056,
|
|
"step": 3100,
|
|
"train_runtime": 10773.5494,
|
|
"train_tokens_per_second": 795.843
|
|
},
|
|
{
|
|
"epoch": 0.0030376084860173577,
|
|
"grad_norm": 4.267324447631836,
|
|
"learning_rate": 0.00019999678648624215,
|
|
"loss": 1.0696584320068359,
|
|
"num_input_tokens_seen": 8732672,
|
|
"step": 3150,
|
|
"train_runtime": 10972.5148,
|
|
"train_tokens_per_second": 795.868
|
|
},
|
|
{
|
|
"epoch": 0.003085824493731919,
|
|
"grad_norm": 9.066252708435059,
|
|
"learning_rate": 0.0001999966638446846,
|
|
"loss": 1.0606288146972656,
|
|
"num_input_tokens_seen": 8881024,
|
|
"step": 3200,
|
|
"train_runtime": 11158.7514,
|
|
"train_tokens_per_second": 795.88
|
|
},
|
|
{
|
|
"epoch": 0.00313404050144648,
|
|
"grad_norm": 3.977785110473633,
|
|
"learning_rate": 0.00019999653890652024,
|
|
"loss": 1.0722166442871093,
|
|
"num_input_tokens_seen": 9017936,
|
|
"step": 3250,
|
|
"train_runtime": 11331.4147,
|
|
"train_tokens_per_second": 795.835
|
|
},
|
|
{
|
|
"epoch": 0.0031822565091610415,
|
|
"grad_norm": 4.629640579223633,
|
|
"learning_rate": 0.00019999641423895398,
|
|
"loss": 1.037092819213867,
|
|
"num_input_tokens_seen": 9169216,
|
|
"step": 3300,
|
|
"train_runtime": 11521.4641,
|
|
"train_tokens_per_second": 795.838
|
|
},
|
|
{
|
|
"epoch": 0.0032304725168756025,
|
|
"grad_norm": 4.690183639526367,
|
|
"learning_rate": 0.0001999962847535166,
|
|
"loss": 1.090658950805664,
|
|
"num_input_tokens_seen": 9314280,
|
|
"step": 3350,
|
|
"train_runtime": 11702.6062,
|
|
"train_tokens_per_second": 795.915
|
|
},
|
|
{
|
|
"epoch": 0.003278688524590164,
|
|
"grad_norm": 2.5034019947052,
|
|
"learning_rate": 0.00019999615297148116,
|
|
"loss": 1.1002796936035155,
|
|
"num_input_tokens_seen": 9460840,
|
|
"step": 3400,
|
|
"train_runtime": 11887.0294,
|
|
"train_tokens_per_second": 795.896
|
|
},
|
|
{
|
|
"epoch": 0.0033269045323047254,
|
|
"grad_norm": 5.8251190185546875,
|
|
"learning_rate": 0.00019999601889285056,
|
|
"loss": 1.0577523040771484,
|
|
"num_input_tokens_seen": 9610960,
|
|
"step": 3450,
|
|
"train_runtime": 12075.9678,
|
|
"train_tokens_per_second": 795.875
|
|
},
|
|
{
|
|
"epoch": 0.0033751205400192863,
|
|
"grad_norm": 4.045161247253418,
|
|
"learning_rate": 0.00019999588251762797,
|
|
"loss": 1.0499482727050782,
|
|
"num_input_tokens_seen": 9761736,
|
|
"step": 3500,
|
|
"train_runtime": 12266.4351,
|
|
"train_tokens_per_second": 795.809
|
|
},
|
|
{
|
|
"epoch": 0.0034233365477338478,
|
|
"grad_norm": 2.586531639099121,
|
|
"learning_rate": 0.00019999574384581652,
|
|
"loss": 1.0542233276367188,
|
|
"num_input_tokens_seen": 9912120,
|
|
"step": 3550,
|
|
"train_runtime": 12454.714,
|
|
"train_tokens_per_second": 795.853
|
|
},
|
|
{
|
|
"epoch": 0.0034715525554484088,
|
|
"grad_norm": 6.992589950561523,
|
|
"learning_rate": 0.00019999560287741933,
|
|
"loss": 1.0482408905029297,
|
|
"num_input_tokens_seen": 10059504,
|
|
"step": 3600,
|
|
"train_runtime": 12640.3589,
|
|
"train_tokens_per_second": 795.824
|
|
},
|
|
{
|
|
"epoch": 0.00351976856316297,
|
|
"grad_norm": 2.839594841003418,
|
|
"learning_rate": 0.0001999954596124397,
|
|
"loss": 1.1219342041015625,
|
|
"num_input_tokens_seen": 10211104,
|
|
"step": 3650,
|
|
"train_runtime": 12831.2366,
|
|
"train_tokens_per_second": 795.8
|
|
},
|
|
{
|
|
"epoch": 0.003567984570877531,
|
|
"grad_norm": 2.0528125762939453,
|
|
"learning_rate": 0.00019999531405088093,
|
|
"loss": 1.0370172882080078,
|
|
"num_input_tokens_seen": 10364096,
|
|
"step": 3700,
|
|
"train_runtime": 13023.5321,
|
|
"train_tokens_per_second": 795.798
|
|
},
|
|
{
|
|
"epoch": 0.0036162005785920926,
|
|
"grad_norm": 3.435650110244751,
|
|
"learning_rate": 0.0001999951661927463,
|
|
"loss": 1.0972762298583985,
|
|
"num_input_tokens_seen": 10510112,
|
|
"step": 3750,
|
|
"train_runtime": 13208.3551,
|
|
"train_tokens_per_second": 795.717
|
|
},
|
|
{
|
|
"epoch": 0.0036644165863066536,
|
|
"grad_norm": 3.062394857406616,
|
|
"learning_rate": 0.00019999501603803924,
|
|
"loss": 1.041371078491211,
|
|
"num_input_tokens_seen": 10657216,
|
|
"step": 3800,
|
|
"train_runtime": 13392.2991,
|
|
"train_tokens_per_second": 795.772
|
|
},
|
|
{
|
|
"epoch": 0.003712632594021215,
|
|
"grad_norm": 4.545124053955078,
|
|
"learning_rate": 0.00019999486358676319,
|
|
"loss": 1.0906889343261719,
|
|
"num_input_tokens_seen": 10808560,
|
|
"step": 3850,
|
|
"train_runtime": 13582.0739,
|
|
"train_tokens_per_second": 795.796
|
|
},
|
|
{
|
|
"epoch": 0.0037608486017357765,
|
|
"grad_norm": 3.202695608139038,
|
|
"learning_rate": 0.00019999471195638485,
|
|
"loss": 1.1333637237548828,
|
|
"num_input_tokens_seen": 10962424,
|
|
"step": 3900,
|
|
"train_runtime": 13775.1658,
|
|
"train_tokens_per_second": 795.811
|
|
},
|
|
{
|
|
"epoch": 0.0038090646094503374,
|
|
"grad_norm": 2.6042728424072266,
|
|
"learning_rate": 0.00019999455495791257,
|
|
"loss": 1.0578984832763672,
|
|
"num_input_tokens_seen": 11105944,
|
|
"step": 3950,
|
|
"train_runtime": 13954.4149,
|
|
"train_tokens_per_second": 795.873
|
|
},
|
|
{
|
|
"epoch": 0.003857280617164899,
|
|
"grad_norm": 2.198012113571167,
|
|
"learning_rate": 0.00019999439566288193,
|
|
"loss": 1.07780517578125,
|
|
"num_input_tokens_seen": 11252312,
|
|
"step": 4000,
|
|
"train_runtime": 14138.6823,
|
|
"train_tokens_per_second": 795.853
|
|
},
|
|
{
|
|
"epoch": 0.00390549662487946,
|
|
"grad_norm": 5.016533851623535,
|
|
"learning_rate": 0.00019999423407129658,
|
|
"loss": 1.0923271179199219,
|
|
"num_input_tokens_seen": 11399064,
|
|
"step": 4050,
|
|
"train_runtime": 14322.6892,
|
|
"train_tokens_per_second": 795.875
|
|
},
|
|
{
|
|
"epoch": 0.003953712632594021,
|
|
"grad_norm": 3.4136438369750977,
|
|
"learning_rate": 0.0001999940701831602,
|
|
"loss": 1.1117418670654298,
|
|
"num_input_tokens_seen": 11553784,
|
|
"step": 4100,
|
|
"train_runtime": 14518.0025,
|
|
"train_tokens_per_second": 795.825
|
|
},
|
|
{
|
|
"epoch": 0.004001928640308582,
|
|
"grad_norm": 2.8393211364746094,
|
|
"learning_rate": 0.00019999390399847656,
|
|
"loss": 1.1267523956298828,
|
|
"num_input_tokens_seen": 11705872,
|
|
"step": 4150,
|
|
"train_runtime": 14709.1994,
|
|
"train_tokens_per_second": 795.82
|
|
},
|
|
{
|
|
"epoch": 0.004050144648023143,
|
|
"grad_norm": 6.878384590148926,
|
|
"learning_rate": 0.00019999373551724946,
|
|
"loss": 1.1205565643310547,
|
|
"num_input_tokens_seen": 11863656,
|
|
"step": 4200,
|
|
"train_runtime": 14907.0157,
|
|
"train_tokens_per_second": 795.844
|
|
},
|
|
{
|
|
"epoch": 0.004098360655737705,
|
|
"grad_norm": 2.8326218128204346,
|
|
"learning_rate": 0.00019999356473948283,
|
|
"loss": 1.1009073638916016,
|
|
"num_input_tokens_seen": 12014224,
|
|
"step": 4250,
|
|
"train_runtime": 15097.5848,
|
|
"train_tokens_per_second": 795.771
|
|
},
|
|
{
|
|
"epoch": 0.004146576663452266,
|
|
"grad_norm": 4.335818767547607,
|
|
"learning_rate": 0.00019999339166518052,
|
|
"loss": 1.1056046295166015,
|
|
"num_input_tokens_seen": 12166256,
|
|
"step": 4300,
|
|
"train_runtime": 15289.0363,
|
|
"train_tokens_per_second": 795.75
|
|
},
|
|
{
|
|
"epoch": 0.004194792671166827,
|
|
"grad_norm": 3.1774818897247314,
|
|
"learning_rate": 0.00019999321629434654,
|
|
"loss": 1.0616819763183594,
|
|
"num_input_tokens_seen": 12316760,
|
|
"step": 4350,
|
|
"train_runtime": 15477.8691,
|
|
"train_tokens_per_second": 795.766
|
|
},
|
|
{
|
|
"epoch": 0.004243008678881389,
|
|
"grad_norm": 3.8473222255706787,
|
|
"learning_rate": 0.00019999303862698492,
|
|
"loss": 1.1155247497558594,
|
|
"num_input_tokens_seen": 12464888,
|
|
"step": 4400,
|
|
"train_runtime": 15664.3004,
|
|
"train_tokens_per_second": 795.751
|
|
},
|
|
{
|
|
"epoch": 0.00429122468659595,
|
|
"grad_norm": 5.138124465942383,
|
|
"learning_rate": 0.00019999285866309968,
|
|
"loss": 1.1778498840332032,
|
|
"num_input_tokens_seen": 12615696,
|
|
"step": 4450,
|
|
"train_runtime": 15854.2308,
|
|
"train_tokens_per_second": 795.731
|
|
},
|
|
{
|
|
"epoch": 0.004339440694310511,
|
|
"grad_norm": 6.003262519836426,
|
|
"learning_rate": 0.00019999267640269505,
|
|
"loss": 1.118102035522461,
|
|
"num_input_tokens_seen": 12773392,
|
|
"step": 4500,
|
|
"train_runtime": 16052.9596,
|
|
"train_tokens_per_second": 795.703
|
|
},
|
|
{
|
|
"epoch": 0.004387656702025072,
|
|
"grad_norm": 2.8125507831573486,
|
|
"learning_rate": 0.00019999249184577517,
|
|
"loss": 1.1140543365478515,
|
|
"num_input_tokens_seen": 12932088,
|
|
"step": 4550,
|
|
"train_runtime": 16252.5556,
|
|
"train_tokens_per_second": 795.696
|
|
},
|
|
{
|
|
"epoch": 0.004435872709739634,
|
|
"grad_norm": 3.1060242652893066,
|
|
"learning_rate": 0.0001999923049923443,
|
|
"loss": 1.185906219482422,
|
|
"num_input_tokens_seen": 13083280,
|
|
"step": 4600,
|
|
"train_runtime": 16442.1343,
|
|
"train_tokens_per_second": 795.717
|
|
},
|
|
{
|
|
"epoch": 0.004484088717454195,
|
|
"grad_norm": 3.123857021331787,
|
|
"learning_rate": 0.0001999921158424067,
|
|
"loss": 1.1313037109375,
|
|
"num_input_tokens_seen": 13239104,
|
|
"step": 4650,
|
|
"train_runtime": 16636.9628,
|
|
"train_tokens_per_second": 795.764
|
|
},
|
|
{
|
|
"epoch": 0.004532304725168756,
|
|
"grad_norm": 2.839475154876709,
|
|
"learning_rate": 0.00019999192439596673,
|
|
"loss": 1.1406651306152344,
|
|
"num_input_tokens_seen": 13387880,
|
|
"step": 4700,
|
|
"train_runtime": 16823.114,
|
|
"train_tokens_per_second": 795.803
|
|
},
|
|
{
|
|
"epoch": 0.004580520732883318,
|
|
"grad_norm": 3.619978666305542,
|
|
"learning_rate": 0.00019999173065302875,
|
|
"loss": 1.1547109985351562,
|
|
"num_input_tokens_seen": 13543744,
|
|
"step": 4750,
|
|
"train_runtime": 17020.4981,
|
|
"train_tokens_per_second": 795.731
|
|
},
|
|
{
|
|
"epoch": 0.004628736740597879,
|
|
"grad_norm": 3.4848074913024902,
|
|
"learning_rate": 0.0001999915346135973,
|
|
"loss": 1.1152828216552735,
|
|
"num_input_tokens_seen": 13699368,
|
|
"step": 4800,
|
|
"train_runtime": 17215.4656,
|
|
"train_tokens_per_second": 795.759
|
|
},
|
|
{
|
|
"epoch": 0.00467695274831244,
|
|
"grad_norm": 3.8960952758789062,
|
|
"learning_rate": 0.00019999134026690073,
|
|
"loss": 1.1547984313964843,
|
|
"num_input_tokens_seen": 13855808,
|
|
"step": 4850,
|
|
"train_runtime": 17411.6007,
|
|
"train_tokens_per_second": 795.78
|
|
},
|
|
{
|
|
"epoch": 0.004725168756027001,
|
|
"grad_norm": 4.826817989349365,
|
|
"learning_rate": 0.00019999113968042543,
|
|
"loss": 1.1312454223632813,
|
|
"num_input_tokens_seen": 14014352,
|
|
"step": 4900,
|
|
"train_runtime": 17610.7092,
|
|
"train_tokens_per_second": 795.786
|
|
},
|
|
{
|
|
"epoch": 0.0047733847637415625,
|
|
"grad_norm": 3.4434866905212402,
|
|
"learning_rate": 0.00019999093679747015,
|
|
"loss": 1.1138098907470704,
|
|
"num_input_tokens_seen": 14164928,
|
|
"step": 4950,
|
|
"train_runtime": 17799.712,
|
|
"train_tokens_per_second": 795.795
|
|
},
|
|
{
|
|
"epoch": 0.0048216007714561235,
|
|
"grad_norm": 3.3920693397521973,
|
|
"learning_rate": 0.00019999073161803955,
|
|
"loss": 1.1798188018798828,
|
|
"num_input_tokens_seen": 14314088,
|
|
"step": 5000,
|
|
"train_runtime": 17987.5383,
|
|
"train_tokens_per_second": 795.778
|
|
},
|
|
{
|
|
"epoch": 0.0048698167791706845,
|
|
"grad_norm": 3.5327558517456055,
|
|
"learning_rate": 0.0001999905241421384,
|
|
"loss": 1.1625843811035157,
|
|
"num_input_tokens_seen": 14472008,
|
|
"step": 5050,
|
|
"train_runtime": 18185.4819,
|
|
"train_tokens_per_second": 795.8
|
|
},
|
|
{
|
|
"epoch": 0.004918032786885246,
|
|
"grad_norm": 5.099838733673096,
|
|
"learning_rate": 0.0001999903143697714,
|
|
"loss": 1.1304238891601563,
|
|
"num_input_tokens_seen": 14625408,
|
|
"step": 5100,
|
|
"train_runtime": 18378.2561,
|
|
"train_tokens_per_second": 795.8
|
|
},
|
|
{
|
|
"epoch": 0.004966248794599807,
|
|
"grad_norm": 3.662264585494995,
|
|
"learning_rate": 0.00019999010230094345,
|
|
"loss": 1.1159452056884767,
|
|
"num_input_tokens_seen": 14778040,
|
|
"step": 5150,
|
|
"train_runtime": 18570.4012,
|
|
"train_tokens_per_second": 795.785
|
|
},
|
|
{
|
|
"epoch": 0.005014464802314368,
|
|
"grad_norm": 2.3775951862335205,
|
|
"learning_rate": 0.00019998988793565932,
|
|
"loss": 1.1117388916015625,
|
|
"num_input_tokens_seen": 14932976,
|
|
"step": 5200,
|
|
"train_runtime": 18764.8163,
|
|
"train_tokens_per_second": 795.797
|
|
},
|
|
{
|
|
"epoch": 0.005062680810028929,
|
|
"grad_norm": 7.036044597625732,
|
|
"learning_rate": 0.00019998967127392403,
|
|
"loss": 1.130252685546875,
|
|
"num_input_tokens_seen": 15086720,
|
|
"step": 5250,
|
|
"train_runtime": 18958.9074,
|
|
"train_tokens_per_second": 795.759
|
|
},
|
|
{
|
|
"epoch": 0.005110896817743491,
|
|
"grad_norm": 2.0267012119293213,
|
|
"learning_rate": 0.00019998945231574248,
|
|
"loss": 1.158425521850586,
|
|
"num_input_tokens_seen": 15240632,
|
|
"step": 5300,
|
|
"train_runtime": 19152.1593,
|
|
"train_tokens_per_second": 795.766
|
|
},
|
|
{
|
|
"epoch": 0.005159112825458052,
|
|
"grad_norm": 4.748377323150635,
|
|
"learning_rate": 0.00019998923106111978,
|
|
"loss": 1.1527466583251953,
|
|
"num_input_tokens_seen": 15388280,
|
|
"step": 5350,
|
|
"train_runtime": 19336.8501,
|
|
"train_tokens_per_second": 795.801
|
|
},
|
|
{
|
|
"epoch": 0.005207328833172613,
|
|
"grad_norm": 3.067131757736206,
|
|
"learning_rate": 0.0001999890075100609,
|
|
"loss": 1.1722109985351563,
|
|
"num_input_tokens_seen": 15546176,
|
|
"step": 5400,
|
|
"train_runtime": 19535.1983,
|
|
"train_tokens_per_second": 795.803
|
|
},
|
|
{
|
|
"epoch": 0.005255544840887174,
|
|
"grad_norm": 4.21209192276001,
|
|
"learning_rate": 0.00019998878166257108,
|
|
"loss": 1.1618234252929687,
|
|
"num_input_tokens_seen": 15702288,
|
|
"step": 5450,
|
|
"train_runtime": 19730.6351,
|
|
"train_tokens_per_second": 795.833
|
|
},
|
|
{
|
|
"epoch": 0.005303760848601736,
|
|
"grad_norm": 2.549159288406372,
|
|
"learning_rate": 0.00019998855351865543,
|
|
"loss": 1.1408056640625,
|
|
"num_input_tokens_seen": 15856728,
|
|
"step": 5500,
|
|
"train_runtime": 19926.0676,
|
|
"train_tokens_per_second": 795.778
|
|
},
|
|
{
|
|
"epoch": 0.005351976856316297,
|
|
"grad_norm": 6.4924235343933105,
|
|
"learning_rate": 0.00019998832307831923,
|
|
"loss": 1.1636355590820313,
|
|
"num_input_tokens_seen": 16006352,
|
|
"step": 5550,
|
|
"train_runtime": 20114.2809,
|
|
"train_tokens_per_second": 795.771
|
|
},
|
|
{
|
|
"epoch": 0.005400192864030858,
|
|
"grad_norm": 4.103078842163086,
|
|
"learning_rate": 0.00019998809034156776,
|
|
"loss": 1.1499610137939453,
|
|
"num_input_tokens_seen": 16166456,
|
|
"step": 5600,
|
|
"train_runtime": 20315.5294,
|
|
"train_tokens_per_second": 795.768
|
|
},
|
|
{
|
|
"epoch": 0.00544840887174542,
|
|
"grad_norm": 4.165494441986084,
|
|
"learning_rate": 0.00019998785530840637,
|
|
"loss": 1.1941165161132812,
|
|
"num_input_tokens_seen": 16321344,
|
|
"step": 5650,
|
|
"train_runtime": 20510.1754,
|
|
"train_tokens_per_second": 795.768
|
|
},
|
|
{
|
|
"epoch": 0.005496624879459981,
|
|
"grad_norm": 2.699083089828491,
|
|
"learning_rate": 0.00019998761797884046,
|
|
"loss": 1.1624859619140624,
|
|
"num_input_tokens_seen": 16477032,
|
|
"step": 5700,
|
|
"train_runtime": 20705.4766,
|
|
"train_tokens_per_second": 795.781
|
|
},
|
|
{
|
|
"epoch": 0.005544840887174542,
|
|
"grad_norm": 4.698432922363281,
|
|
"learning_rate": 0.0001999873783528755,
|
|
"loss": 1.1533927154541015,
|
|
"num_input_tokens_seen": 16632344,
|
|
"step": 5750,
|
|
"train_runtime": 20901.0057,
|
|
"train_tokens_per_second": 795.768
|
|
},
|
|
{
|
|
"epoch": 0.005593056894889103,
|
|
"grad_norm": 2.5076868534088135,
|
|
"learning_rate": 0.00019998713643051694,
|
|
"loss": 1.231993408203125,
|
|
"num_input_tokens_seen": 16790312,
|
|
"step": 5800,
|
|
"train_runtime": 21099.1474,
|
|
"train_tokens_per_second": 795.782
|
|
},
|
|
{
|
|
"epoch": 0.005641272902603665,
|
|
"grad_norm": 3.50299072265625,
|
|
"learning_rate": 0.00019998689221177037,
|
|
"loss": 1.1662635040283202,
|
|
"num_input_tokens_seen": 16949232,
|
|
"step": 5850,
|
|
"train_runtime": 21298.6664,
|
|
"train_tokens_per_second": 795.788
|
|
},
|
|
{
|
|
"epoch": 0.005689488910318226,
|
|
"grad_norm": 3.424320936203003,
|
|
"learning_rate": 0.00019998664569664142,
|
|
"loss": 1.2123499298095703,
|
|
"num_input_tokens_seen": 17107680,
|
|
"step": 5900,
|
|
"train_runtime": 21496.9927,
|
|
"train_tokens_per_second": 795.817
|
|
},
|
|
{
|
|
"epoch": 0.005737704918032787,
|
|
"grad_norm": 3.0827279090881348,
|
|
"learning_rate": 0.00019998639688513574,
|
|
"loss": 1.0921006774902344,
|
|
"num_input_tokens_seen": 17263232,
|
|
"step": 5950,
|
|
"train_runtime": 21692.3833,
|
|
"train_tokens_per_second": 795.82
|
|
},
|
|
{
|
|
"epoch": 0.0057859209257473485,
|
|
"grad_norm": 6.457613945007324,
|
|
"learning_rate": 0.000199986145777259,
|
|
"loss": 1.1960066986083984,
|
|
"num_input_tokens_seen": 17411072,
|
|
"step": 6000,
|
|
"train_runtime": 21878.4706,
|
|
"train_tokens_per_second": 795.808
|
|
},
|
|
{
|
|
"epoch": 0.0058341369334619095,
|
|
"grad_norm": 7.048415660858154,
|
|
"learning_rate": 0.00019998589237301702,
|
|
"loss": 1.1289830017089844,
|
|
"num_input_tokens_seen": 17562464,
|
|
"step": 6050,
|
|
"train_runtime": 22068.4972,
|
|
"train_tokens_per_second": 795.816
|
|
},
|
|
{
|
|
"epoch": 0.0058823529411764705,
|
|
"grad_norm": 4.861032485961914,
|
|
"learning_rate": 0.0001999856366724156,
|
|
"loss": 1.1921009063720702,
|
|
"num_input_tokens_seen": 17715496,
|
|
"step": 6100,
|
|
"train_runtime": 22260.5987,
|
|
"train_tokens_per_second": 795.823
|
|
},
|
|
{
|
|
"epoch": 0.0059305689488910315,
|
|
"grad_norm": 6.195998191833496,
|
|
"learning_rate": 0.00019998537867546058,
|
|
"loss": 1.1586724090576173,
|
|
"num_input_tokens_seen": 17879176,
|
|
"step": 6150,
|
|
"train_runtime": 22466.4688,
|
|
"train_tokens_per_second": 795.816
|
|
},
|
|
{
|
|
"epoch": 0.005978784956605593,
|
|
"grad_norm": 4.569608688354492,
|
|
"learning_rate": 0.00019998511838215793,
|
|
"loss": 1.1442041778564453,
|
|
"num_input_tokens_seen": 18036520,
|
|
"step": 6200,
|
|
"train_runtime": 22664.5393,
|
|
"train_tokens_per_second": 795.804
|
|
},
|
|
{
|
|
"epoch": 0.006027000964320154,
|
|
"grad_norm": 3.2505431175231934,
|
|
"learning_rate": 0.00019998485579251365,
|
|
"loss": 1.2148939514160155,
|
|
"num_input_tokens_seen": 18193920,
|
|
"step": 6250,
|
|
"train_runtime": 22862.6649,
|
|
"train_tokens_per_second": 795.792
|
|
},
|
|
{
|
|
"epoch": 0.006075216972034715,
|
|
"grad_norm": 2.278432846069336,
|
|
"learning_rate": 0.00019998459090653372,
|
|
"loss": 1.1565365600585937,
|
|
"num_input_tokens_seen": 18350440,
|
|
"step": 6300,
|
|
"train_runtime": 23058.7124,
|
|
"train_tokens_per_second": 795.814
|
|
},
|
|
{
|
|
"epoch": 0.006123432979749276,
|
|
"grad_norm": 4.003475189208984,
|
|
"learning_rate": 0.00019998432372422421,
|
|
"loss": 1.1289629364013671,
|
|
"num_input_tokens_seen": 18515168,
|
|
"step": 6350,
|
|
"train_runtime": 23265.8318,
|
|
"train_tokens_per_second": 795.809
|
|
},
|
|
{
|
|
"epoch": 0.006171648987463838,
|
|
"grad_norm": 2.540540933609009,
|
|
"learning_rate": 0.00019998405424559134,
|
|
"loss": 1.1765531158447267,
|
|
"num_input_tokens_seen": 18670704,
|
|
"step": 6400,
|
|
"train_runtime": 23460.4439,
|
|
"train_tokens_per_second": 795.838
|
|
},
|
|
{
|
|
"epoch": 0.006219864995178399,
|
|
"grad_norm": 2.6466386318206787,
|
|
"learning_rate": 0.0001999837824706412,
|
|
"loss": 1.1730777740478515,
|
|
"num_input_tokens_seen": 18829176,
|
|
"step": 6450,
|
|
"train_runtime": 23659.4024,
|
|
"train_tokens_per_second": 795.843
|
|
},
|
|
{
|
|
"epoch": 0.00626808100289296,
|
|
"grad_norm": 5.367827892303467,
|
|
"learning_rate": 0.00019998350839938012,
|
|
"loss": 1.1038116455078124,
|
|
"num_input_tokens_seen": 18991264,
|
|
"step": 6500,
|
|
"train_runtime": 23863.7446,
|
|
"train_tokens_per_second": 795.821
|
|
},
|
|
{
|
|
"epoch": 0.006316297010607522,
|
|
"grad_norm": 3.977985143661499,
|
|
"learning_rate": 0.00019998323203181432,
|
|
"loss": 1.1874691009521485,
|
|
"num_input_tokens_seen": 19153384,
|
|
"step": 6550,
|
|
"train_runtime": 24067.1514,
|
|
"train_tokens_per_second": 795.831
|
|
},
|
|
{
|
|
"epoch": 0.006364513018322083,
|
|
"grad_norm": 2.446540117263794,
|
|
"learning_rate": 0.0001999829533679502,
|
|
"loss": 1.1465693664550782,
|
|
"num_input_tokens_seen": 19319968,
|
|
"step": 6600,
|
|
"train_runtime": 24276.0217,
|
|
"train_tokens_per_second": 795.846
|
|
},
|
|
{
|
|
"epoch": 0.006412729026036644,
|
|
"grad_norm": 2.9619059562683105,
|
|
"learning_rate": 0.00019998267240779413,
|
|
"loss": 1.1802974700927735,
|
|
"num_input_tokens_seen": 19476488,
|
|
"step": 6650,
|
|
"train_runtime": 24472.576,
|
|
"train_tokens_per_second": 795.85
|
|
},
|
|
{
|
|
"epoch": 0.006460945033751205,
|
|
"grad_norm": 2.731968402862549,
|
|
"learning_rate": 0.00019998238915135258,
|
|
"loss": 1.1878755950927735,
|
|
"num_input_tokens_seen": 19628312,
|
|
"step": 6700,
|
|
"train_runtime": 24663.6145,
|
|
"train_tokens_per_second": 795.841
|
|
},
|
|
{
|
|
"epoch": 0.006509161041465767,
|
|
"grad_norm": 2.8332622051239014,
|
|
"learning_rate": 0.00019998210359863203,
|
|
"loss": 1.1881317138671874,
|
|
"num_input_tokens_seen": 19790872,
|
|
"step": 6750,
|
|
"train_runtime": 24869.0583,
|
|
"train_tokens_per_second": 795.803
|
|
},
|
|
{
|
|
"epoch": 0.006557377049180328,
|
|
"grad_norm": 4.0377278327941895,
|
|
"learning_rate": 0.00019998181574963904,
|
|
"loss": 1.179229736328125,
|
|
"num_input_tokens_seen": 19954024,
|
|
"step": 6800,
|
|
"train_runtime": 25073.8367,
|
|
"train_tokens_per_second": 795.811
|
|
},
|
|
{
|
|
"epoch": 0.006605593056894889,
|
|
"grad_norm": 3.5912861824035645,
|
|
"learning_rate": 0.0001999815256043803,
|
|
"loss": 1.1840432739257813,
|
|
"num_input_tokens_seen": 20110400,
|
|
"step": 6850,
|
|
"train_runtime": 25270.0728,
|
|
"train_tokens_per_second": 795.819
|
|
},
|
|
{
|
|
"epoch": 0.006653809064609451,
|
|
"grad_norm": 2.37129807472229,
|
|
"learning_rate": 0.00019998123316286237,
|
|
"loss": 1.1889665222167969,
|
|
"num_input_tokens_seen": 20258680,
|
|
"step": 6900,
|
|
"train_runtime": 25457.421,
|
|
"train_tokens_per_second": 795.787
|
|
},
|
|
{
|
|
"epoch": 0.006702025072324012,
|
|
"grad_norm": 3.144788980484009,
|
|
"learning_rate": 0.000199980938425092,
|
|
"loss": 1.2078351593017578,
|
|
"num_input_tokens_seen": 20409824,
|
|
"step": 6950,
|
|
"train_runtime": 25648.3298,
|
|
"train_tokens_per_second": 795.756
|
|
},
|
|
{
|
|
"epoch": 0.006750241080038573,
|
|
"grad_norm": 5.027791976928711,
|
|
"learning_rate": 0.00019998064139107599,
|
|
"loss": 1.1785513305664062,
|
|
"num_input_tokens_seen": 20562552,
|
|
"step": 7000,
|
|
"train_runtime": 25841.7539,
|
|
"train_tokens_per_second": 795.71
|
|
},
|
|
{
|
|
"epoch": 0.006798457087753134,
|
|
"grad_norm": 2.696073293685913,
|
|
"learning_rate": 0.00019998034206082112,
|
|
"loss": 1.235442123413086,
|
|
"num_input_tokens_seen": 20710712,
|
|
"step": 7050,
|
|
"train_runtime": 26028.7455,
|
|
"train_tokens_per_second": 795.686
|
|
},
|
|
{
|
|
"epoch": 0.0068466730954676955,
|
|
"grad_norm": 2.935499668121338,
|
|
"learning_rate": 0.00019998004043433429,
|
|
"loss": 1.1891513061523438,
|
|
"num_input_tokens_seen": 20863768,
|
|
"step": 7100,
|
|
"train_runtime": 26220.8126,
|
|
"train_tokens_per_second": 795.695
|
|
},
|
|
{
|
|
"epoch": 0.0068948891031822565,
|
|
"grad_norm": 2.755754232406616,
|
|
"learning_rate": 0.00019997973651162242,
|
|
"loss": 1.2316454315185548,
|
|
"num_input_tokens_seen": 21011952,
|
|
"step": 7150,
|
|
"train_runtime": 26407.8843,
|
|
"train_tokens_per_second": 795.67
|
|
},
|
|
{
|
|
"epoch": 0.0069431051108968175,
|
|
"grad_norm": 5.369665145874023,
|
|
"learning_rate": 0.0001999794302926925,
|
|
"loss": 1.1947048950195311,
|
|
"num_input_tokens_seen": 21148904,
|
|
"step": 7200,
|
|
"train_runtime": 26581.8273,
|
|
"train_tokens_per_second": 795.615
|
|
},
|
|
{
|
|
"epoch": 0.006991321118611379,
|
|
"grad_norm": 5.293364524841309,
|
|
"learning_rate": 0.00019997912177755156,
|
|
"loss": 1.2115525817871093,
|
|
"num_input_tokens_seen": 21301600,
|
|
"step": 7250,
|
|
"train_runtime": 26776.1996,
|
|
"train_tokens_per_second": 795.542
|
|
},
|
|
{
|
|
"epoch": 0.00703953712632594,
|
|
"grad_norm": 5.501073360443115,
|
|
"learning_rate": 0.00019997881096620667,
|
|
"loss": 1.1865999603271484,
|
|
"num_input_tokens_seen": 21441496,
|
|
"step": 7300,
|
|
"train_runtime": 26953.3477,
|
|
"train_tokens_per_second": 795.504
|
|
},
|
|
{
|
|
"epoch": 0.007087753134040501,
|
|
"grad_norm": 3.4206905364990234,
|
|
"learning_rate": 0.00019997849785866495,
|
|
"loss": 1.1712677764892578,
|
|
"num_input_tokens_seen": 21576512,
|
|
"step": 7350,
|
|
"train_runtime": 27125.0132,
|
|
"train_tokens_per_second": 795.447
|
|
},
|
|
{
|
|
"epoch": 0.007135969141755062,
|
|
"grad_norm": 4.537284851074219,
|
|
"learning_rate": 0.00019997818245493364,
|
|
"loss": 1.2076505279541017,
|
|
"num_input_tokens_seen": 21713400,
|
|
"step": 7400,
|
|
"train_runtime": 27299.2154,
|
|
"train_tokens_per_second": 795.385
|
|
},
|
|
{
|
|
"epoch": 0.007184185149469624,
|
|
"grad_norm": 3.7432072162628174,
|
|
"learning_rate": 0.00019997786475501998,
|
|
"loss": 1.1811279296875,
|
|
"num_input_tokens_seen": 21849328,
|
|
"step": 7450,
|
|
"train_runtime": 27471.9807,
|
|
"train_tokens_per_second": 795.331
|
|
},
|
|
{
|
|
"epoch": 0.007232401157184185,
|
|
"grad_norm": 6.112918853759766,
|
|
"learning_rate": 0.00019997754475893124,
|
|
"loss": 1.1437189483642578,
|
|
"num_input_tokens_seen": 21988816,
|
|
"step": 7500,
|
|
"train_runtime": 27649.4766,
|
|
"train_tokens_per_second": 795.271
|
|
},
|
|
{
|
|
"epoch": 0.007280617164898746,
|
|
"grad_norm": 5.329083442687988,
|
|
"learning_rate": 0.00019997722246667477,
|
|
"loss": 1.1954824066162109,
|
|
"num_input_tokens_seen": 22127024,
|
|
"step": 7550,
|
|
"train_runtime": 27825.0639,
|
|
"train_tokens_per_second": 795.219
|
|
},
|
|
{
|
|
"epoch": 0.007328833172613307,
|
|
"grad_norm": 6.663646221160889,
|
|
"learning_rate": 0.00019997689787825797,
|
|
"loss": 1.1545868682861329,
|
|
"num_input_tokens_seen": 22269128,
|
|
"step": 7600,
|
|
"train_runtime": 28005.6784,
|
|
"train_tokens_per_second": 795.165
|
|
},
|
|
{
|
|
"epoch": 0.007377049180327869,
|
|
"grad_norm": 4.986312389373779,
|
|
"learning_rate": 0.00019997657099368832,
|
|
"loss": 1.1702413177490234,
|
|
"num_input_tokens_seen": 22406200,
|
|
"step": 7650,
|
|
"train_runtime": 28180.2354,
|
|
"train_tokens_per_second": 795.103
|
|
},
|
|
{
|
|
"epoch": 0.00742526518804243,
|
|
"grad_norm": 4.00105094909668,
|
|
"learning_rate": 0.00019997624181297333,
|
|
"loss": 1.2036454772949219,
|
|
"num_input_tokens_seen": 22534896,
|
|
"step": 7700,
|
|
"train_runtime": 28344.4788,
|
|
"train_tokens_per_second": 795.037
|
|
},
|
|
{
|
|
"epoch": 0.007473481195756991,
|
|
"grad_norm": 2.9974911212921143,
|
|
"learning_rate": 0.0001999759103361205,
|
|
"loss": 1.175606918334961,
|
|
"num_input_tokens_seen": 22665128,
|
|
"step": 7750,
|
|
"train_runtime": 28512.1323,
|
|
"train_tokens_per_second": 794.929
|
|
},
|
|
{
|
|
"epoch": 0.007521697203471553,
|
|
"grad_norm": 3.8016157150268555,
|
|
"learning_rate": 0.00019997557656313753,
|
|
"loss": 1.1993572998046875,
|
|
"num_input_tokens_seen": 22796072,
|
|
"step": 7800,
|
|
"train_runtime": 28679.0931,
|
|
"train_tokens_per_second": 794.867
|
|
},
|
|
{
|
|
"epoch": 0.007569913211186114,
|
|
"grad_norm": 4.761569023132324,
|
|
"learning_rate": 0.000199975240494032,
|
|
"loss": 1.1410749816894532,
|
|
"num_input_tokens_seen": 22929320,
|
|
"step": 7850,
|
|
"train_runtime": 28849.0285,
|
|
"train_tokens_per_second": 794.804
|
|
},
|
|
{
|
|
"epoch": 0.007618129218900675,
|
|
"grad_norm": 2.9353902339935303,
|
|
"learning_rate": 0.0001999749021288117,
|
|
"loss": 1.1333987426757812,
|
|
"num_input_tokens_seen": 23050016,
|
|
"step": 7900,
|
|
"train_runtime": 29003.6981,
|
|
"train_tokens_per_second": 794.727
|
|
},
|
|
{
|
|
"epoch": 0.007666345226615236,
|
|
"grad_norm": 5.670568943023682,
|
|
"learning_rate": 0.00019997456146748436,
|
|
"loss": 1.1472447967529298,
|
|
"num_input_tokens_seen": 23175464,
|
|
"step": 7950,
|
|
"train_runtime": 29163.5915,
|
|
"train_tokens_per_second": 794.671
|
|
},
|
|
{
|
|
"epoch": 0.007714561234329798,
|
|
"grad_norm": 4.669622898101807,
|
|
"learning_rate": 0.00019997422539170807,
|
|
"loss": 1.1778974151611328,
|
|
"num_input_tokens_seen": 23307864,
|
|
"step": 8000,
|
|
"train_runtime": 29333.6128,
|
|
"train_tokens_per_second": 794.579
|
|
},
|
|
{
|
|
"epoch": 0.007762777242044359,
|
|
"grad_norm": 4.8720927238464355,
|
|
"learning_rate": 0.00019997388018411197,
|
|
"loss": 1.1580985260009766,
|
|
"num_input_tokens_seen": 23436896,
|
|
"step": 8050,
|
|
"train_runtime": 29499.1023,
|
|
"train_tokens_per_second": 794.495
|
|
},
|
|
{
|
|
"epoch": 0.00781099324975892,
|
|
"grad_norm": 6.199527263641357,
|
|
"learning_rate": 0.00019997353268043225,
|
|
"loss": 1.1472965240478517,
|
|
"num_input_tokens_seen": 23556616,
|
|
"step": 8100,
|
|
"train_runtime": 29653.7659,
|
|
"train_tokens_per_second": 794.389
|
|
},
|
|
{
|
|
"epoch": 0.00785920925747348,
|
|
"grad_norm": 3.105149269104004,
|
|
"learning_rate": 0.000199973182880677,
|
|
"loss": 1.1754726409912108,
|
|
"num_input_tokens_seen": 23677200,
|
|
"step": 8150,
|
|
"train_runtime": 29809.1433,
|
|
"train_tokens_per_second": 794.293
|
|
},
|
|
{
|
|
"epoch": 0.007907425265188043,
|
|
"grad_norm": 3.3506765365600586,
|
|
"learning_rate": 0.00019997283078485422,
|
|
"loss": 1.208150405883789,
|
|
"num_input_tokens_seen": 23798968,
|
|
"step": 8200,
|
|
"train_runtime": 29966.4533,
|
|
"train_tokens_per_second": 794.187
|
|
},
|
|
{
|
|
"epoch": 0.007955641272902604,
|
|
"grad_norm": 4.884840965270996,
|
|
"learning_rate": 0.00019997247639297198,
|
|
"loss": 1.2178065490722656,
|
|
"num_input_tokens_seen": 23921056,
|
|
"step": 8250,
|
|
"train_runtime": 30124.882,
|
|
"train_tokens_per_second": 794.063
|
|
},
|
|
{
|
|
"epoch": 0.008003857280617165,
|
|
"grad_norm": 3.883300542831421,
|
|
"learning_rate": 0.0001999721197050384,
|
|
"loss": 1.0957367706298828,
|
|
"num_input_tokens_seen": 24040888,
|
|
"step": 8300,
|
|
"train_runtime": 30280.3191,
|
|
"train_tokens_per_second": 793.944
|
|
},
|
|
{
|
|
"epoch": 0.008052073288331726,
|
|
"grad_norm": 4.704105854034424,
|
|
"learning_rate": 0.0001999717607210617,
|
|
"loss": 1.1460076904296874,
|
|
"num_input_tokens_seen": 24164152,
|
|
"step": 8350,
|
|
"train_runtime": 30438.7063,
|
|
"train_tokens_per_second": 793.863
|
|
},
|
|
{
|
|
"epoch": 0.008100289296046287,
|
|
"grad_norm": 5.256917476654053,
|
|
"learning_rate": 0.00019997139944105013,
|
|
"loss": 1.1680290222167968,
|
|
"num_input_tokens_seen": 24282072,
|
|
"step": 8400,
|
|
"train_runtime": 30591.6363,
|
|
"train_tokens_per_second": 793.749
|
|
},
|
|
{
|
|
"epoch": 0.008148505303760848,
|
|
"grad_norm": 5.063985347747803,
|
|
"learning_rate": 0.00019997103586501196,
|
|
"loss": 1.0963511657714844,
|
|
"num_input_tokens_seen": 24401064,
|
|
"step": 8450,
|
|
"train_runtime": 30745.4022,
|
|
"train_tokens_per_second": 793.649
|
|
},
|
|
{
|
|
"epoch": 0.00819672131147541,
|
|
"grad_norm": 5.49263858795166,
|
|
"learning_rate": 0.00019997066999295556,
|
|
"loss": 1.1810964965820312,
|
|
"num_input_tokens_seen": 24524768,
|
|
"step": 8500,
|
|
"train_runtime": 30906.4278,
|
|
"train_tokens_per_second": 793.517
|
|
},
|
|
{
|
|
"epoch": 0.00824493731918997,
|
|
"grad_norm": 2.9982590675354004,
|
|
"learning_rate": 0.00019997030182488933,
|
|
"loss": 1.2054883575439452,
|
|
"num_input_tokens_seen": 24637672,
|
|
"step": 8550,
|
|
"train_runtime": 31052.5504,
|
|
"train_tokens_per_second": 793.419
|
|
},
|
|
{
|
|
"epoch": 0.008293153326904532,
|
|
"grad_norm": 6.170753002166748,
|
|
"learning_rate": 0.00019996993136082173,
|
|
"loss": 1.0873966217041016,
|
|
"num_input_tokens_seen": 24754984,
|
|
"step": 8600,
|
|
"train_runtime": 31205.2559,
|
|
"train_tokens_per_second": 793.295
|
|
},
|
|
{
|
|
"epoch": 0.008341369334619094,
|
|
"grad_norm": 7.152240753173828,
|
|
"learning_rate": 0.00019996955860076128,
|
|
"loss": 1.1540665435791015,
|
|
"num_input_tokens_seen": 24873312,
|
|
"step": 8650,
|
|
"train_runtime": 31357.955,
|
|
"train_tokens_per_second": 793.206
|
|
},
|
|
{
|
|
"epoch": 0.008389585342333654,
|
|
"grad_norm": 6.077364444732666,
|
|
"learning_rate": 0.00019996918354471652,
|
|
"loss": 1.1511080169677734,
|
|
"num_input_tokens_seen": 24985776,
|
|
"step": 8700,
|
|
"train_runtime": 31505.0803,
|
|
"train_tokens_per_second": 793.071
|
|
},
|
|
{
|
|
"epoch": 0.008437801350048216,
|
|
"grad_norm": 9.377755165100098,
|
|
"learning_rate": 0.00019996880619269604,
|
|
"loss": 1.1163874053955078,
|
|
"num_input_tokens_seen": 25100360,
|
|
"step": 8750,
|
|
"train_runtime": 31654.7654,
|
|
"train_tokens_per_second": 792.941
|
|
},
|
|
{
|
|
"epoch": 0.008486017357762778,
|
|
"grad_norm": 8.531953811645508,
|
|
"learning_rate": 0.00019996842654470856,
|
|
"loss": 1.1187710571289062,
|
|
"num_input_tokens_seen": 25216712,
|
|
"step": 8800,
|
|
"train_runtime": 31806.0485,
|
|
"train_tokens_per_second": 792.828
|
|
},
|
|
{
|
|
"epoch": 0.008534233365477338,
|
|
"grad_norm": 6.532482147216797,
|
|
"learning_rate": 0.00019996804460076277,
|
|
"loss": 1.1475318145751954,
|
|
"num_input_tokens_seen": 25339720,
|
|
"step": 8850,
|
|
"train_runtime": 31964.4259,
|
|
"train_tokens_per_second": 792.748
|
|
},
|
|
{
|
|
"epoch": 0.0085824493731919,
|
|
"grad_norm": 5.10507345199585,
|
|
"learning_rate": 0.00019996766036086745,
|
|
"loss": 1.1399880981445312,
|
|
"num_input_tokens_seen": 25451856,
|
|
"step": 8900,
|
|
"train_runtime": 32111.6484,
|
|
"train_tokens_per_second": 792.605
|
|
},
|
|
{
|
|
"epoch": 0.008630665380906462,
|
|
"grad_norm": 5.002315521240234,
|
|
"learning_rate": 0.00019996727382503142,
|
|
"loss": 1.1110499572753907,
|
|
"num_input_tokens_seen": 25568072,
|
|
"step": 8950,
|
|
"train_runtime": 32262.912,
|
|
"train_tokens_per_second": 792.491
|
|
},
|
|
{
|
|
"epoch": 0.008678881388621022,
|
|
"grad_norm": 8.789694786071777,
|
|
"learning_rate": 0.00019996688499326356,
|
|
"loss": 1.074218978881836,
|
|
"num_input_tokens_seen": 25685760,
|
|
"step": 9000,
|
|
"train_runtime": 32416.2674,
|
|
"train_tokens_per_second": 792.373
|
|
},
|
|
{
|
|
"epoch": 0.008727097396335584,
|
|
"grad_norm": 3.3695337772369385,
|
|
"learning_rate": 0.0001999664938655728,
|
|
"loss": 1.1087096405029297,
|
|
"num_input_tokens_seen": 25794088,
|
|
"step": 9050,
|
|
"train_runtime": 32558.5471,
|
|
"train_tokens_per_second": 792.237
|
|
},
|
|
{
|
|
"epoch": 0.008775313404050144,
|
|
"grad_norm": 6.290781497955322,
|
|
"learning_rate": 0.00019996610044196813,
|
|
"loss": 1.1723241424560547,
|
|
"num_input_tokens_seen": 25897888,
|
|
"step": 9100,
|
|
"train_runtime": 32694.6338,
|
|
"train_tokens_per_second": 792.114
|
|
},
|
|
{
|
|
"epoch": 0.008823529411764706,
|
|
"grad_norm": 4.498072624206543,
|
|
"learning_rate": 0.00019996570472245856,
|
|
"loss": 1.0763970947265624,
|
|
"num_input_tokens_seen": 26004232,
|
|
"step": 9150,
|
|
"train_runtime": 32834.2402,
|
|
"train_tokens_per_second": 791.985
|
|
},
|
|
{
|
|
"epoch": 0.008871745419479268,
|
|
"grad_norm": 4.953782558441162,
|
|
"learning_rate": 0.0001999653067070532,
|
|
"loss": 1.151754150390625,
|
|
"num_input_tokens_seen": 26105344,
|
|
"step": 9200,
|
|
"train_runtime": 32966.8266,
|
|
"train_tokens_per_second": 791.867
|
|
},
|
|
{
|
|
"epoch": 0.008919961427193828,
|
|
"grad_norm": 5.382718086242676,
|
|
"learning_rate": 0.0001999649063957612,
|
|
"loss": 1.0906046295166016,
|
|
"num_input_tokens_seen": 26215952,
|
|
"step": 9250,
|
|
"train_runtime": 33112.1005,
|
|
"train_tokens_per_second": 791.733
|
|
},
|
|
{
|
|
"epoch": 0.00896817743490839,
|
|
"grad_norm": 4.603332042694092,
|
|
"learning_rate": 0.00019996450378859172,
|
|
"loss": 1.1330809020996093,
|
|
"num_input_tokens_seen": 26320752,
|
|
"step": 9300,
|
|
"train_runtime": 33249.591,
|
|
"train_tokens_per_second": 791.611
|
|
},
|
|
{
|
|
"epoch": 0.009016393442622951,
|
|
"grad_norm": 2.934601306915283,
|
|
"learning_rate": 0.00019996409888555405,
|
|
"loss": 1.1839237213134766,
|
|
"num_input_tokens_seen": 26422048,
|
|
"step": 9350,
|
|
"train_runtime": 33382.6413,
|
|
"train_tokens_per_second": 791.491
|
|
},
|
|
{
|
|
"epoch": 0.009064609450337512,
|
|
"grad_norm": 3.29888916015625,
|
|
"learning_rate": 0.00019996369168665746,
|
|
"loss": 1.1689480590820311,
|
|
"num_input_tokens_seen": 26533192,
|
|
"step": 9400,
|
|
"train_runtime": 33527.8757,
|
|
"train_tokens_per_second": 791.377
|
|
},
|
|
{
|
|
"epoch": 0.009112825458052073,
|
|
"grad_norm": 3.8537471294403076,
|
|
"learning_rate": 0.0001999632821919113,
|
|
"loss": 1.1217078399658202,
|
|
"num_input_tokens_seen": 26640064,
|
|
"step": 9450,
|
|
"train_runtime": 33667.7838,
|
|
"train_tokens_per_second": 791.263
|
|
},
|
|
{
|
|
"epoch": 0.009161041465766635,
|
|
"grad_norm": 3.612938404083252,
|
|
"learning_rate": 0.000199962870401325,
|
|
"loss": 1.1206032562255859,
|
|
"num_input_tokens_seen": 26743848,
|
|
"step": 9500,
|
|
"train_runtime": 33804.5929,
|
|
"train_tokens_per_second": 791.131
|
|
},
|
|
{
|
|
"epoch": 0.009209257473481195,
|
|
"grad_norm": 7.649857521057129,
|
|
"learning_rate": 0.00019996245631490799,
|
|
"loss": 1.1162215423583985,
|
|
"num_input_tokens_seen": 26841928,
|
|
"step": 9550,
|
|
"train_runtime": 33933.873,
|
|
"train_tokens_per_second": 791.007
|
|
},
|
|
{
|
|
"epoch": 0.009257473481195757,
|
|
"grad_norm": 4.809179782867432,
|
|
"learning_rate": 0.0001999620399326698,
|
|
"loss": 1.1184545135498047,
|
|
"num_input_tokens_seen": 26940808,
|
|
"step": 9600,
|
|
"train_runtime": 34064.1302,
|
|
"train_tokens_per_second": 790.885
|
|
},
|
|
{
|
|
"epoch": 0.009305689488910317,
|
|
"grad_norm": 5.56284761428833,
|
|
"learning_rate": 0.00019996162125461998,
|
|
"loss": 1.0712617492675782,
|
|
"num_input_tokens_seen": 27047104,
|
|
"step": 9650,
|
|
"train_runtime": 34203.3828,
|
|
"train_tokens_per_second": 790.773
|
|
},
|
|
{
|
|
"epoch": 0.00935390549662488,
|
|
"grad_norm": 5.159473896026611,
|
|
"learning_rate": 0.00019996120028076817,
|
|
"loss": 1.0962361907958984,
|
|
"num_input_tokens_seen": 27150168,
|
|
"step": 9700,
|
|
"train_runtime": 34338.9244,
|
|
"train_tokens_per_second": 790.653
|
|
},
|
|
{
|
|
"epoch": 0.009402121504339441,
|
|
"grad_norm": 6.817291736602783,
|
|
"learning_rate": 0.00019996077701112398,
|
|
"loss": 1.0742768096923827,
|
|
"num_input_tokens_seen": 27237024,
|
|
"step": 9750,
|
|
"train_runtime": 34456.0854,
|
|
"train_tokens_per_second": 790.485
|
|
},
|
|
{
|
|
"epoch": 0.009450337512054001,
|
|
"grad_norm": 5.779628753662109,
|
|
"learning_rate": 0.00019996035144569723,
|
|
"loss": 1.195142822265625,
|
|
"num_input_tokens_seen": 27339616,
|
|
"step": 9800,
|
|
"train_runtime": 34591.6998,
|
|
"train_tokens_per_second": 790.352
|
|
},
|
|
{
|
|
"epoch": 0.009498553519768563,
|
|
"grad_norm": 4.896306037902832,
|
|
"learning_rate": 0.0001999599235844976,
|
|
"loss": 1.0772993469238281,
|
|
"num_input_tokens_seen": 27428856,
|
|
"step": 9850,
|
|
"train_runtime": 34711.4175,
|
|
"train_tokens_per_second": 790.197
|
|
},
|
|
{
|
|
"epoch": 0.009546769527483125,
|
|
"grad_norm": 5.35271692276001,
|
|
"learning_rate": 0.00019995949342753493,
|
|
"loss": 1.1659256744384765,
|
|
"num_input_tokens_seen": 27535208,
|
|
"step": 9900,
|
|
"train_runtime": 34850.9623,
|
|
"train_tokens_per_second": 790.085
|
|
},
|
|
{
|
|
"epoch": 0.009594985535197685,
|
|
"grad_norm": 5.407012939453125,
|
|
"learning_rate": 0.00019995906097481915,
|
|
"loss": 1.0661520385742187,
|
|
"num_input_tokens_seen": 27627896,
|
|
"step": 9950,
|
|
"train_runtime": 34975.3405,
|
|
"train_tokens_per_second": 789.925
|
|
},
|
|
{
|
|
"epoch": 0.009643201542912247,
|
|
"grad_norm": 7.471088409423828,
|
|
"learning_rate": 0.00019995862622636015,
|
|
"loss": 1.152157974243164,
|
|
"num_input_tokens_seen": 27721912,
|
|
"step": 10000,
|
|
"train_runtime": 35101.487,
|
|
"train_tokens_per_second": 789.765
|
|
},
|
|
{
|
|
"epoch": 0.009691417550626809,
|
|
"grad_norm": 5.9994354248046875,
|
|
"learning_rate": 0.00019995818918216792,
|
|
"loss": 1.085326156616211,
|
|
"num_input_tokens_seen": 27812696,
|
|
"step": 10050,
|
|
"train_runtime": 35223.8848,
|
|
"train_tokens_per_second": 789.598
|
|
},
|
|
{
|
|
"epoch": 0.009739633558341369,
|
|
"grad_norm": 5.3652663230896,
|
|
"learning_rate": 0.00019995774984225254,
|
|
"loss": 1.0752402496337892,
|
|
"num_input_tokens_seen": 27902064,
|
|
"step": 10100,
|
|
"train_runtime": 35344.1839,
|
|
"train_tokens_per_second": 789.439
|
|
},
|
|
{
|
|
"epoch": 0.00978784956605593,
|
|
"grad_norm": 5.273618698120117,
|
|
"learning_rate": 0.00019995730820662405,
|
|
"loss": 1.0374341583251954,
|
|
"num_input_tokens_seen": 27985552,
|
|
"step": 10150,
|
|
"train_runtime": 35457.5642,
|
|
"train_tokens_per_second": 789.269
|
|
},
|
|
{
|
|
"epoch": 0.009836065573770493,
|
|
"grad_norm": 7.261931896209717,
|
|
"learning_rate": 0.00019995686427529258,
|
|
"loss": 1.1244140625,
|
|
"num_input_tokens_seen": 28069312,
|
|
"step": 10200,
|
|
"train_runtime": 35570.2307,
|
|
"train_tokens_per_second": 789.124
|
|
},
|
|
{
|
|
"epoch": 0.009884281581485053,
|
|
"grad_norm": 5.944073677062988,
|
|
"learning_rate": 0.00019995641804826836,
|
|
"loss": 1.063521270751953,
|
|
"num_input_tokens_seen": 28156440,
|
|
"step": 10250,
|
|
"train_runtime": 35688.9783,
|
|
"train_tokens_per_second": 788.939
|
|
},
|
|
{
|
|
"epoch": 0.009932497589199615,
|
|
"grad_norm": 6.0135626792907715,
|
|
"learning_rate": 0.00019995596952556165,
|
|
"loss": 1.1152246856689454,
|
|
"num_input_tokens_seen": 28253072,
|
|
"step": 10300,
|
|
"train_runtime": 35817.612,
|
|
"train_tokens_per_second": 788.804
|
|
},
|
|
{
|
|
"epoch": 0.009980713596914175,
|
|
"grad_norm": 6.880923748016357,
|
|
"learning_rate": 0.00019995551870718273,
|
|
"loss": 1.0702508544921876,
|
|
"num_input_tokens_seen": 28336120,
|
|
"step": 10350,
|
|
"train_runtime": 35928.9424,
|
|
"train_tokens_per_second": 788.671
|
|
},
|
|
{
|
|
"epoch": 0.010028929604628737,
|
|
"grad_norm": 5.20412015914917,
|
|
"learning_rate": 0.00019995506559314195,
|
|
"loss": 1.1398055267333984,
|
|
"num_input_tokens_seen": 28428520,
|
|
"step": 10400,
|
|
"train_runtime": 36052.1942,
|
|
"train_tokens_per_second": 788.538
|
|
},
|
|
{
|
|
"epoch": 0.010077145612343298,
|
|
"grad_norm": 4.039947509765625,
|
|
"learning_rate": 0.00019995461018344974,
|
|
"loss": 1.0773772430419921,
|
|
"num_input_tokens_seen": 28514336,
|
|
"step": 10450,
|
|
"train_runtime": 36168.5311,
|
|
"train_tokens_per_second": 788.374
|
|
},
|
|
{
|
|
"epoch": 0.010125361620057859,
|
|
"grad_norm": 5.706058025360107,
|
|
"learning_rate": 0.0001999541524781165,
|
|
"loss": 1.1047949981689453,
|
|
"num_input_tokens_seen": 28604552,
|
|
"step": 10500,
|
|
"train_runtime": 36289.2274,
|
|
"train_tokens_per_second": 788.238
|
|
},
|
|
{
|
|
"epoch": 0.01017357762777242,
|
|
"grad_norm": 6.099785327911377,
|
|
"learning_rate": 0.00019995369247715282,
|
|
"loss": 1.0220722198486327,
|
|
"num_input_tokens_seen": 28687344,
|
|
"step": 10550,
|
|
"train_runtime": 36402.9314,
|
|
"train_tokens_per_second": 788.05
|
|
},
|
|
{
|
|
"epoch": 0.010221793635486982,
|
|
"grad_norm": 6.2141828536987305,
|
|
"learning_rate": 0.00019995323018056924,
|
|
"loss": 1.0777069854736328,
|
|
"num_input_tokens_seen": 28768208,
|
|
"step": 10600,
|
|
"train_runtime": 36512.827,
|
|
"train_tokens_per_second": 787.893
|
|
},
|
|
{
|
|
"epoch": 0.010270009643201542,
|
|
"grad_norm": 3.5498392581939697,
|
|
"learning_rate": 0.00019995276558837634,
|
|
"loss": 1.0752593994140625,
|
|
"num_input_tokens_seen": 28857336,
|
|
"step": 10650,
|
|
"train_runtime": 36632.1167,
|
|
"train_tokens_per_second": 787.761
|
|
},
|
|
{
|
|
"epoch": 0.010318225650916104,
|
|
"grad_norm": 6.541693210601807,
|
|
"learning_rate": 0.00019995229870058484,
|
|
"loss": 1.10650146484375,
|
|
"num_input_tokens_seen": 28944176,
|
|
"step": 10700,
|
|
"train_runtime": 36749.9541,
|
|
"train_tokens_per_second": 787.598
|
|
},
|
|
{
|
|
"epoch": 0.010366441658630666,
|
|
"grad_norm": 5.62925910949707,
|
|
"learning_rate": 0.00019995182951720544,
|
|
"loss": 1.0278012084960937,
|
|
"num_input_tokens_seen": 29029296,
|
|
"step": 10750,
|
|
"train_runtime": 36865.8019,
|
|
"train_tokens_per_second": 787.432
|
|
},
|
|
{
|
|
"epoch": 0.010414657666345226,
|
|
"grad_norm": 3.4583253860473633,
|
|
"learning_rate": 0.00019995135803824892,
|
|
"loss": 1.1106737518310548,
|
|
"num_input_tokens_seen": 29115152,
|
|
"step": 10800,
|
|
"train_runtime": 36981.6085,
|
|
"train_tokens_per_second": 787.287
|
|
},
|
|
{
|
|
"epoch": 0.010462873674059788,
|
|
"grad_norm": 7.843570232391357,
|
|
"learning_rate": 0.00019995088426372608,
|
|
"loss": 1.1421663665771484,
|
|
"num_input_tokens_seen": 29202056,
|
|
"step": 10850,
|
|
"train_runtime": 37100.1773,
|
|
"train_tokens_per_second": 787.114
|
|
},
|
|
{
|
|
"epoch": 0.010511089681774348,
|
|
"grad_norm": 5.792357444763184,
|
|
"learning_rate": 0.00019995040819364784,
|
|
"loss": 1.0975267791748047,
|
|
"num_input_tokens_seen": 29289880,
|
|
"step": 10900,
|
|
"train_runtime": 37219.0447,
|
|
"train_tokens_per_second": 786.959
|
|
},
|
|
{
|
|
"epoch": 0.01055930568948891,
|
|
"grad_norm": 5.456055164337158,
|
|
"learning_rate": 0.00019994992982802512,
|
|
"loss": 1.0455081939697266,
|
|
"num_input_tokens_seen": 29368256,
|
|
"step": 10950,
|
|
"train_runtime": 37326.9013,
|
|
"train_tokens_per_second": 786.785
|
|
},
|
|
{
|
|
"epoch": 0.010607521697203472,
|
|
"grad_norm": 3.598719596862793,
|
|
"learning_rate": 0.0001999494491668689,
|
|
"loss": 1.0606918334960938,
|
|
"num_input_tokens_seen": 29447184,
|
|
"step": 11000,
|
|
"train_runtime": 37435.8349,
|
|
"train_tokens_per_second": 786.604
|
|
},
|
|
{
|
|
"epoch": 0.010655737704918032,
|
|
"grad_norm": 7.621616363525391,
|
|
"learning_rate": 0.00019994896621019023,
|
|
"loss": 1.0255219268798828,
|
|
"num_input_tokens_seen": 29526144,
|
|
"step": 11050,
|
|
"train_runtime": 37543.2664,
|
|
"train_tokens_per_second": 786.456
|
|
},
|
|
{
|
|
"epoch": 0.010703953712632594,
|
|
"grad_norm": 5.114947319030762,
|
|
"learning_rate": 0.00019994848095800018,
|
|
"loss": 1.0241009521484374,
|
|
"num_input_tokens_seen": 29608304,
|
|
"step": 11100,
|
|
"train_runtime": 37654.3143,
|
|
"train_tokens_per_second": 786.319
|
|
},
|
|
{
|
|
"epoch": 0.010752169720347156,
|
|
"grad_norm": 6.3999714851379395,
|
|
"learning_rate": 0.00019994799341030995,
|
|
"loss": 1.0756417846679687,
|
|
"num_input_tokens_seen": 29693112,
|
|
"step": 11150,
|
|
"train_runtime": 37769.6186,
|
|
"train_tokens_per_second": 786.164
|
|
},
|
|
{
|
|
"epoch": 0.010800385728061716,
|
|
"grad_norm": 6.839094161987305,
|
|
"learning_rate": 0.0001999475035671307,
|
|
"loss": 1.1073701477050781,
|
|
"num_input_tokens_seen": 29772520,
|
|
"step": 11200,
|
|
"train_runtime": 37878.6692,
|
|
"train_tokens_per_second": 785.997
|
|
},
|
|
{
|
|
"epoch": 0.010848601735776278,
|
|
"grad_norm": 3.916412353515625,
|
|
"learning_rate": 0.0001999470114284736,
|
|
"loss": 1.0509242248535156,
|
|
"num_input_tokens_seen": 29853200,
|
|
"step": 11250,
|
|
"train_runtime": 37989.7481,
|
|
"train_tokens_per_second": 785.823
|
|
},
|
|
{
|
|
"epoch": 0.01089681774349084,
|
|
"grad_norm": 11.404187202453613,
|
|
"learning_rate": 0.0001999465169943501,
|
|
"loss": 1.147591781616211,
|
|
"num_input_tokens_seen": 29942168,
|
|
"step": 11300,
|
|
"train_runtime": 38108.2342,
|
|
"train_tokens_per_second": 785.714
|
|
},
|
|
{
|
|
"epoch": 0.0109450337512054,
|
|
"grad_norm": 7.116096496582031,
|
|
"learning_rate": 0.00019994602026477147,
|
|
"loss": 1.0990084075927735,
|
|
"num_input_tokens_seen": 30027088,
|
|
"step": 11350,
|
|
"train_runtime": 38223.6313,
|
|
"train_tokens_per_second": 785.563
|
|
},
|
|
{
|
|
"epoch": 0.010993249758919962,
|
|
"grad_norm": 11.571887969970703,
|
|
"learning_rate": 0.00019994552123974915,
|
|
"loss": 1.0086239624023436,
|
|
"num_input_tokens_seen": 30102104,
|
|
"step": 11400,
|
|
"train_runtime": 38326.9155,
|
|
"train_tokens_per_second": 785.404
|
|
},
|
|
{
|
|
"epoch": 0.011041465766634522,
|
|
"grad_norm": 4.962576389312744,
|
|
"learning_rate": 0.00019994501991929458,
|
|
"loss": 1.0577239990234375,
|
|
"num_input_tokens_seen": 30182712,
|
|
"step": 11450,
|
|
"train_runtime": 38437.1002,
|
|
"train_tokens_per_second": 785.249
|
|
},
|
|
{
|
|
"epoch": 0.011089681774349084,
|
|
"grad_norm": 5.854893207550049,
|
|
"learning_rate": 0.0001999445163034193,
|
|
"loss": 1.0812836456298829,
|
|
"num_input_tokens_seen": 30258056,
|
|
"step": 11500,
|
|
"train_runtime": 38542.0459,
|
|
"train_tokens_per_second": 785.066
|
|
},
|
|
{
|
|
"epoch": 0.011137897782063646,
|
|
"grad_norm": 13.878477096557617,
|
|
"learning_rate": 0.00019994401039213485,
|
|
"loss": 1.04399658203125,
|
|
"num_input_tokens_seen": 30337128,
|
|
"step": 11550,
|
|
"train_runtime": 38649.027,
|
|
"train_tokens_per_second": 784.939
|
|
},
|
|
{
|
|
"epoch": 0.011186113789778206,
|
|
"grad_norm": 8.209726333618164,
|
|
"learning_rate": 0.00019994350218545282,
|
|
"loss": 1.0652425384521484,
|
|
"num_input_tokens_seen": 30412960,
|
|
"step": 11600,
|
|
"train_runtime": 38753.528,
|
|
"train_tokens_per_second": 784.779
|
|
},
|
|
{
|
|
"epoch": 0.011234329797492767,
|
|
"grad_norm": 7.537613868713379,
|
|
"learning_rate": 0.00019994299168338495,
|
|
"loss": 1.0378002166748046,
|
|
"num_input_tokens_seen": 30485104,
|
|
"step": 11650,
|
|
"train_runtime": 38853.4061,
|
|
"train_tokens_per_second": 784.619
|
|
},
|
|
{
|
|
"epoch": 0.01128254580520733,
|
|
"grad_norm": 5.9705047607421875,
|
|
"learning_rate": 0.00019994247888594294,
|
|
"loss": 1.0322565460205078,
|
|
"num_input_tokens_seen": 30557240,
|
|
"step": 11700,
|
|
"train_runtime": 38954.2213,
|
|
"train_tokens_per_second": 784.44
|
|
},
|
|
{
|
|
"epoch": 0.01133076181292189,
|
|
"grad_norm": 7.224442958831787,
|
|
"learning_rate": 0.0001999419637931385,
|
|
"loss": 0.9655182647705078,
|
|
"num_input_tokens_seen": 30625592,
|
|
"step": 11750,
|
|
"train_runtime": 39051.5298,
|
|
"train_tokens_per_second": 784.235
|
|
},
|
|
{
|
|
"epoch": 0.011378977820636451,
|
|
"grad_norm": 4.8540358543396,
|
|
"learning_rate": 0.0001999414464049836,
|
|
"loss": 1.0744315338134767,
|
|
"num_input_tokens_seen": 30700152,
|
|
"step": 11800,
|
|
"train_runtime": 39155.2401,
|
|
"train_tokens_per_second": 784.062
|
|
},
|
|
{
|
|
"epoch": 0.011427193828351013,
|
|
"grad_norm": 7.286028861999512,
|
|
"learning_rate": 0.00019994092672149,
|
|
"loss": 0.9426592254638672,
|
|
"num_input_tokens_seen": 30772032,
|
|
"step": 11850,
|
|
"train_runtime": 39256.9727,
|
|
"train_tokens_per_second": 783.862
|
|
},
|
|
{
|
|
"epoch": 0.011475409836065573,
|
|
"grad_norm": 4.2551727294921875,
|
|
"learning_rate": 0.0001999404047426697,
|
|
"loss": 1.0968148040771484,
|
|
"num_input_tokens_seen": 30843784,
|
|
"step": 11900,
|
|
"train_runtime": 39357.3535,
|
|
"train_tokens_per_second": 783.685
|
|
},
|
|
{
|
|
"epoch": 0.011523625843780135,
|
|
"grad_norm": 5.724776744842529,
|
|
"learning_rate": 0.00019993988046853467,
|
|
"loss": 0.9910453796386719,
|
|
"num_input_tokens_seen": 30914600,
|
|
"step": 11950,
|
|
"train_runtime": 39456.5088,
|
|
"train_tokens_per_second": 783.511
|
|
},
|
|
{
|
|
"epoch": 0.011571841851494697,
|
|
"grad_norm": 5.14203405380249,
|
|
"learning_rate": 0.00019993935389909693,
|
|
"loss": 0.9566682434082031,
|
|
"num_input_tokens_seen": 30983384,
|
|
"step": 12000,
|
|
"train_runtime": 39553.8205,
|
|
"train_tokens_per_second": 783.322
|
|
},
|
|
{
|
|
"epoch": 0.011620057859209257,
|
|
"grad_norm": 6.975264072418213,
|
|
"learning_rate": 0.00019993883563415693,
|
|
"loss": 1.01316650390625,
|
|
"num_input_tokens_seen": 31060032,
|
|
"step": 12050,
|
|
"train_runtime": 39659.4899,
|
|
"train_tokens_per_second": 783.168
|
|
},
|
|
{
|
|
"epoch": 0.011668273866923819,
|
|
"grad_norm": 6.3460540771484375,
|
|
"learning_rate": 0.00019993830452005558,
|
|
"loss": 1.0095925903320313,
|
|
"num_input_tokens_seen": 31138536,
|
|
"step": 12100,
|
|
"train_runtime": 39767.5679,
|
|
"train_tokens_per_second": 783.013
|
|
},
|
|
{
|
|
"epoch": 0.01171648987463838,
|
|
"grad_norm": 6.367609977722168,
|
|
"learning_rate": 0.00019993777111068775,
|
|
"loss": 1.006901397705078,
|
|
"num_input_tokens_seen": 31214976,
|
|
"step": 12150,
|
|
"train_runtime": 39873.2979,
|
|
"train_tokens_per_second": 782.854
|
|
},
|
|
{
|
|
"epoch": 0.011764705882352941,
|
|
"grad_norm": 4.465271949768066,
|
|
"learning_rate": 0.00019993723540606567,
|
|
"loss": 1.0493619537353516,
|
|
"num_input_tokens_seen": 31289248,
|
|
"step": 12200,
|
|
"train_runtime": 39977.0327,
|
|
"train_tokens_per_second": 782.681
|
|
},
|
|
{
|
|
"epoch": 0.011812921890067503,
|
|
"grad_norm": 3.7483248710632324,
|
|
"learning_rate": 0.00019993669740620167,
|
|
"loss": 1.0423163604736327,
|
|
"num_input_tokens_seen": 31362064,
|
|
"step": 12250,
|
|
"train_runtime": 40078.38,
|
|
"train_tokens_per_second": 782.518
|
|
},
|
|
{
|
|
"epoch": 0.011861137897782063,
|
|
"grad_norm": 6.975680828094482,
|
|
"learning_rate": 0.00019993615711110804,
|
|
"loss": 1.0152625274658202,
|
|
"num_input_tokens_seen": 31440496,
|
|
"step": 12300,
|
|
"train_runtime": 40186.2124,
|
|
"train_tokens_per_second": 782.37
|
|
},
|
|
{
|
|
"epoch": 0.011909353905496625,
|
|
"grad_norm": 4.797680854797363,
|
|
"learning_rate": 0.00019993561452079725,
|
|
"loss": 0.959788818359375,
|
|
"num_input_tokens_seen": 31504704,
|
|
"step": 12350,
|
|
"train_runtime": 40277.1809,
|
|
"train_tokens_per_second": 782.197
|
|
},
|
|
{
|
|
"epoch": 0.011957569913211187,
|
|
"grad_norm": 7.189600944519043,
|
|
"learning_rate": 0.00019993506963528174,
|
|
"loss": 1.0216622924804688,
|
|
"num_input_tokens_seen": 31583280,
|
|
"step": 12400,
|
|
"train_runtime": 40384.3177,
|
|
"train_tokens_per_second": 782.068
|
|
},
|
|
{
|
|
"epoch": 0.012005785920925747,
|
|
"grad_norm": 5.82935094833374,
|
|
"learning_rate": 0.00019993452245457404,
|
|
"loss": 0.9680135345458984,
|
|
"num_input_tokens_seen": 31649464,
|
|
"step": 12450,
|
|
"train_runtime": 40477.7531,
|
|
"train_tokens_per_second": 781.898
|
|
},
|
|
{
|
|
"epoch": 0.012054001928640309,
|
|
"grad_norm": 6.691218852996826,
|
|
"learning_rate": 0.0001999339729786867,
|
|
"loss": 1.018744659423828,
|
|
"num_input_tokens_seen": 31724944,
|
|
"step": 12500,
|
|
"train_runtime": 40583.4771,
|
|
"train_tokens_per_second": 781.721
|
|
},
|
|
{
|
|
"epoch": 0.01210221793635487,
|
|
"grad_norm": 5.762418746948242,
|
|
"learning_rate": 0.00019993342120763234,
|
|
"loss": 0.9619303131103516,
|
|
"num_input_tokens_seen": 31790360,
|
|
"step": 12550,
|
|
"train_runtime": 40676.0043,
|
|
"train_tokens_per_second": 781.551
|
|
},
|
|
{
|
|
"epoch": 0.01215043394406943,
|
|
"grad_norm": 6.976195812225342,
|
|
"learning_rate": 0.00019993286714142366,
|
|
"loss": 1.0836136627197266,
|
|
"num_input_tokens_seen": 31867104,
|
|
"step": 12600,
|
|
"train_runtime": 40781.6539,
|
|
"train_tokens_per_second": 781.408
|
|
},
|
|
{
|
|
"epoch": 0.012198649951783993,
|
|
"grad_norm": 8.34317398071289,
|
|
"learning_rate": 0.00019993231078007333,
|
|
"loss": 1.0244537353515626,
|
|
"num_input_tokens_seen": 31939632,
|
|
"step": 12650,
|
|
"train_runtime": 40882.5947,
|
|
"train_tokens_per_second": 781.253
|
|
},
|
|
{
|
|
"epoch": 0.012246865959498553,
|
|
"grad_norm": 4.709578514099121,
|
|
"learning_rate": 0.00019993175212359415,
|
|
"loss": 1.012821044921875,
|
|
"num_input_tokens_seen": 32007640,
|
|
"step": 12700,
|
|
"train_runtime": 40977.0016,
|
|
"train_tokens_per_second": 781.112
|
|
},
|
|
{
|
|
"epoch": 0.012295081967213115,
|
|
"grad_norm": 8.546862602233887,
|
|
"learning_rate": 0.000199931191171999,
|
|
"loss": 1.0059098815917968,
|
|
"num_input_tokens_seen": 32075880,
|
|
"step": 12750,
|
|
"train_runtime": 41073.3054,
|
|
"train_tokens_per_second": 780.942
|
|
},
|
|
{
|
|
"epoch": 0.012343297974927676,
|
|
"grad_norm": 6.723101615905762,
|
|
"learning_rate": 0.0001999306279253007,
|
|
"loss": 1.0138204193115234,
|
|
"num_input_tokens_seen": 32142792,
|
|
"step": 12800,
|
|
"train_runtime": 41166.8553,
|
|
"train_tokens_per_second": 780.793
|
|
},
|
|
{
|
|
"epoch": 0.012391513982642237,
|
|
"grad_norm": 3.5829508304595947,
|
|
"learning_rate": 0.00019993006238351222,
|
|
"loss": 0.9846931457519531,
|
|
"num_input_tokens_seen": 32205400,
|
|
"step": 12850,
|
|
"train_runtime": 41255.9261,
|
|
"train_tokens_per_second": 780.625
|
|
},
|
|
{
|
|
"epoch": 0.012439729990356798,
|
|
"grad_norm": 6.7176923751831055,
|
|
"learning_rate": 0.0001999294945466465,
|
|
"loss": 0.9547106170654297,
|
|
"num_input_tokens_seen": 32274712,
|
|
"step": 12900,
|
|
"train_runtime": 41353.5387,
|
|
"train_tokens_per_second": 780.458
|
|
},
|
|
{
|
|
"epoch": 0.01248794599807136,
|
|
"grad_norm": 2.911025047302246,
|
|
"learning_rate": 0.00019992892441471666,
|
|
"loss": 0.9932091522216797,
|
|
"num_input_tokens_seen": 32339256,
|
|
"step": 12950,
|
|
"train_runtime": 41444.3041,
|
|
"train_tokens_per_second": 780.306
|
|
},
|
|
{
|
|
"epoch": 0.01253616200578592,
|
|
"grad_norm": 6.4254560470581055,
|
|
"learning_rate": 0.00019992835198773577,
|
|
"loss": 0.9772125244140625,
|
|
"num_input_tokens_seen": 32401464,
|
|
"step": 13000,
|
|
"train_runtime": 41532.5936,
|
|
"train_tokens_per_second": 780.145
|
|
},
|
|
{
|
|
"epoch": 0.012584378013500482,
|
|
"grad_norm": 5.812196254730225,
|
|
"learning_rate": 0.00019992777726571693,
|
|
"loss": 0.97468505859375,
|
|
"num_input_tokens_seen": 32466504,
|
|
"step": 13050,
|
|
"train_runtime": 41625.236,
|
|
"train_tokens_per_second": 779.972
|
|
},
|
|
{
|
|
"epoch": 0.012632594021215044,
|
|
"grad_norm": 6.525760173797607,
|
|
"learning_rate": 0.00019992720024867338,
|
|
"loss": 1.079323272705078,
|
|
"num_input_tokens_seen": 32542120,
|
|
"step": 13100,
|
|
"train_runtime": 41729.6508,
|
|
"train_tokens_per_second": 779.832
|
|
},
|
|
{
|
|
"epoch": 0.012680810028929604,
|
|
"grad_norm": 5.462522983551025,
|
|
"learning_rate": 0.00019992662093661835,
|
|
"loss": 1.0251593780517578,
|
|
"num_input_tokens_seen": 32608360,
|
|
"step": 13150,
|
|
"train_runtime": 41822.9693,
|
|
"train_tokens_per_second": 779.676
|
|
},
|
|
{
|
|
"epoch": 0.012729026036644166,
|
|
"grad_norm": 4.808300018310547,
|
|
"learning_rate": 0.00019992603932956517,
|
|
"loss": 0.927762680053711,
|
|
"num_input_tokens_seen": 32675560,
|
|
"step": 13200,
|
|
"train_runtime": 41918.3562,
|
|
"train_tokens_per_second": 779.505
|
|
},
|
|
{
|
|
"epoch": 0.012777242044358728,
|
|
"grad_norm": 5.823526382446289,
|
|
"learning_rate": 0.00019992545542752717,
|
|
"loss": 1.0020172119140625,
|
|
"num_input_tokens_seen": 32746320,
|
|
"step": 13250,
|
|
"train_runtime": 42017.4716,
|
|
"train_tokens_per_second": 779.35
|
|
},
|
|
{
|
|
"epoch": 0.012825458052073288,
|
|
"grad_norm": 5.7537102699279785,
|
|
"learning_rate": 0.00019992486923051778,
|
|
"loss": 0.9378489685058594,
|
|
"num_input_tokens_seen": 32808184,
|
|
"step": 13300,
|
|
"train_runtime": 42105.9207,
|
|
"train_tokens_per_second": 779.182
|
|
},
|
|
{
|
|
"epoch": 0.01287367405978785,
|
|
"grad_norm": 10.35693359375,
|
|
"learning_rate": 0.00019992428073855047,
|
|
"loss": 1.0303922271728516,
|
|
"num_input_tokens_seen": 32882496,
|
|
"step": 13350,
|
|
"train_runtime": 42209.0023,
|
|
"train_tokens_per_second": 779.04
|
|
},
|
|
{
|
|
"epoch": 0.01292189006750241,
|
|
"grad_norm": 5.341796398162842,
|
|
"learning_rate": 0.00019992368995163875,
|
|
"loss": 0.9017025756835938,
|
|
"num_input_tokens_seen": 32945360,
|
|
"step": 13400,
|
|
"train_runtime": 42299.0494,
|
|
"train_tokens_per_second": 778.868
|
|
},
|
|
{
|
|
"epoch": 0.012970106075216972,
|
|
"grad_norm": 6.674615859985352,
|
|
"learning_rate": 0.0001999230968697962,
|
|
"loss": 1.052380599975586,
|
|
"num_input_tokens_seen": 33013536,
|
|
"step": 13450,
|
|
"train_runtime": 42394.2608,
|
|
"train_tokens_per_second": 778.727
|
|
},
|
|
{
|
|
"epoch": 0.013018322082931534,
|
|
"grad_norm": 7.3141770362854,
|
|
"learning_rate": 0.00019992250149303636,
|
|
"loss": 0.9685611724853516,
|
|
"num_input_tokens_seen": 33076096,
|
|
"step": 13500,
|
|
"train_runtime": 42484.171,
|
|
"train_tokens_per_second": 778.551
|
|
},
|
|
{
|
|
"epoch": 0.013066538090646094,
|
|
"grad_norm": 5.8429646492004395,
|
|
"learning_rate": 0.000199921903821373,
|
|
"loss": 1.0568414306640626,
|
|
"num_input_tokens_seen": 33137608,
|
|
"step": 13550,
|
|
"train_runtime": 42573.0689,
|
|
"train_tokens_per_second": 778.37
|
|
},
|
|
{
|
|
"epoch": 0.013114754098360656,
|
|
"grad_norm": 8.586183547973633,
|
|
"learning_rate": 0.00019992130385481982,
|
|
"loss": 0.9363051605224609,
|
|
"num_input_tokens_seen": 33200808,
|
|
"step": 13600,
|
|
"train_runtime": 42664.2723,
|
|
"train_tokens_per_second": 778.188
|
|
},
|
|
{
|
|
"epoch": 0.013162970106075218,
|
|
"grad_norm": 5.907812595367432,
|
|
"learning_rate": 0.0001999207015933906,
|
|
"loss": 1.0442145538330079,
|
|
"num_input_tokens_seen": 33273624,
|
|
"step": 13650,
|
|
"train_runtime": 42765.3316,
|
|
"train_tokens_per_second": 778.051
|
|
},
|
|
{
|
|
"epoch": 0.013211186113789778,
|
|
"grad_norm": 8.153900146484375,
|
|
"learning_rate": 0.00019992009703709916,
|
|
"loss": 0.9946853637695312,
|
|
"num_input_tokens_seen": 33339424,
|
|
"step": 13700,
|
|
"train_runtime": 42857.9695,
|
|
"train_tokens_per_second": 777.905
|
|
},
|
|
{
|
|
"epoch": 0.01325940212150434,
|
|
"grad_norm": 9.374747276306152,
|
|
"learning_rate": 0.0001999194901859594,
|
|
"loss": 1.0037115478515626,
|
|
"num_input_tokens_seen": 33402424,
|
|
"step": 13750,
|
|
"train_runtime": 42948.4614,
|
|
"train_tokens_per_second": 777.733
|
|
},
|
|
{
|
|
"epoch": 0.013307618129218901,
|
|
"grad_norm": 5.199647426605225,
|
|
"learning_rate": 0.00019991888103998524,
|
|
"loss": 0.9938618469238282,
|
|
"num_input_tokens_seen": 33472528,
|
|
"step": 13800,
|
|
"train_runtime": 43045.853,
|
|
"train_tokens_per_second": 777.602
|
|
},
|
|
{
|
|
"epoch": 0.013355834136933462,
|
|
"grad_norm": 7.809544086456299,
|
|
"learning_rate": 0.00019991826959919067,
|
|
"loss": 0.9265874481201172,
|
|
"num_input_tokens_seen": 33533960,
|
|
"step": 13850,
|
|
"train_runtime": 43135.2605,
|
|
"train_tokens_per_second": 777.414
|
|
},
|
|
{
|
|
"epoch": 0.013404050144648023,
|
|
"grad_norm": 10.14194107055664,
|
|
"learning_rate": 0.00019991765586358976,
|
|
"loss": 1.0077749633789062,
|
|
"num_input_tokens_seen": 33599832,
|
|
"step": 13900,
|
|
"train_runtime": 43229.3014,
|
|
"train_tokens_per_second": 777.247
|
|
},
|
|
{
|
|
"epoch": 0.013452266152362584,
|
|
"grad_norm": 6.500311851501465,
|
|
"learning_rate": 0.00019991703983319656,
|
|
"loss": 1.014174346923828,
|
|
"num_input_tokens_seen": 33660920,
|
|
"step": 13950,
|
|
"train_runtime": 43316.7771,
|
|
"train_tokens_per_second": 777.087
|
|
},
|
|
{
|
|
"epoch": 0.013500482160077145,
|
|
"grad_norm": 6.485054016113281,
|
|
"learning_rate": 0.00019991642150802525,
|
|
"loss": 0.9426477813720703,
|
|
"num_input_tokens_seen": 33720384,
|
|
"step": 14000,
|
|
"train_runtime": 43403.0225,
|
|
"train_tokens_per_second": 776.913
|
|
},
|
|
{
|
|
"epoch": 0.013548698167791707,
|
|
"grad_norm": 6.222419738769531,
|
|
"learning_rate": 0.00019991580088809006,
|
|
"loss": 0.9640670776367187,
|
|
"num_input_tokens_seen": 33783864,
|
|
"step": 14050,
|
|
"train_runtime": 43493.6376,
|
|
"train_tokens_per_second": 776.754
|
|
},
|
|
{
|
|
"epoch": 0.013596914175506267,
|
|
"grad_norm": 6.593068599700928,
|
|
"learning_rate": 0.00019991517797340516,
|
|
"loss": 1.0888720703125,
|
|
"num_input_tokens_seen": 33843960,
|
|
"step": 14100,
|
|
"train_runtime": 43580.684,
|
|
"train_tokens_per_second": 776.582
|
|
},
|
|
{
|
|
"epoch": 0.01364513018322083,
|
|
"grad_norm": 6.785283088684082,
|
|
"learning_rate": 0.00019991455276398493,
|
|
"loss": 0.9519427490234375,
|
|
"num_input_tokens_seen": 33905664,
|
|
"step": 14150,
|
|
"train_runtime": 43669.2624,
|
|
"train_tokens_per_second": 776.419
|
|
},
|
|
{
|
|
"epoch": 0.013693346190935391,
|
|
"grad_norm": 5.3056254386901855,
|
|
"learning_rate": 0.00019991392525984373,
|
|
"loss": 0.9714452362060547,
|
|
"num_input_tokens_seen": 33963664,
|
|
"step": 14200,
|
|
"train_runtime": 43753.3829,
|
|
"train_tokens_per_second": 776.252
|
|
},
|
|
{
|
|
"epoch": 0.013741562198649951,
|
|
"grad_norm": 5.280013561248779,
|
|
"learning_rate": 0.00019991329546099592,
|
|
"loss": 1.027360382080078,
|
|
"num_input_tokens_seen": 34026080,
|
|
"step": 14250,
|
|
"train_runtime": 43843.6401,
|
|
"train_tokens_per_second": 776.078
|
|
},
|
|
{
|
|
"epoch": 0.013789778206364513,
|
|
"grad_norm": 8.798730850219727,
|
|
"learning_rate": 0.00019991266336745597,
|
|
"loss": 1.0020081329345703,
|
|
"num_input_tokens_seen": 34090720,
|
|
"step": 14300,
|
|
"train_runtime": 43935.0005,
|
|
"train_tokens_per_second": 775.935
|
|
},
|
|
{
|
|
"epoch": 0.013837994214079075,
|
|
"grad_norm": 5.6939263343811035,
|
|
"learning_rate": 0.00019991202897923845,
|
|
"loss": 0.9928904724121094,
|
|
"num_input_tokens_seen": 34146480,
|
|
"step": 14350,
|
|
"train_runtime": 44015.7503,
|
|
"train_tokens_per_second": 775.779
|
|
},
|
|
{
|
|
"epoch": 0.013886210221793635,
|
|
"grad_norm": 5.718827247619629,
|
|
"learning_rate": 0.00019991139229635788,
|
|
"loss": 0.944555892944336,
|
|
"num_input_tokens_seen": 34209600,
|
|
"step": 14400,
|
|
"train_runtime": 44105.5066,
|
|
"train_tokens_per_second": 775.631
|
|
},
|
|
{
|
|
"epoch": 0.013934426229508197,
|
|
"grad_norm": 10.223149299621582,
|
|
"learning_rate": 0.00019991076612086697,
|
|
"loss": 0.9625386047363281,
|
|
"num_input_tokens_seen": 34265128,
|
|
"step": 14450,
|
|
"train_runtime": 44187.5061,
|
|
"train_tokens_per_second": 775.448
|
|
},
|
|
{
|
|
"epoch": 0.013982642237222759,
|
|
"grad_norm": 8.98515510559082,
|
|
"learning_rate": 0.00019991012489459678,
|
|
"loss": 0.9797266387939453,
|
|
"num_input_tokens_seen": 34322136,
|
|
"step": 14500,
|
|
"train_runtime": 44270.7839,
|
|
"train_tokens_per_second": 775.277
|
|
},
|
|
{
|
|
"epoch": 0.014030858244937319,
|
|
"grad_norm": 7.647890567779541,
|
|
"learning_rate": 0.00019990948137370732,
|
|
"loss": 1.020360794067383,
|
|
"num_input_tokens_seen": 34383096,
|
|
"step": 14550,
|
|
"train_runtime": 44358.1232,
|
|
"train_tokens_per_second": 775.125
|
|
},
|
|
{
|
|
"epoch": 0.01407907425265188,
|
|
"grad_norm": 7.268465995788574,
|
|
"learning_rate": 0.00019990883555821333,
|
|
"loss": 0.9346786499023437,
|
|
"num_input_tokens_seen": 34435376,
|
|
"step": 14600,
|
|
"train_runtime": 44436.5892,
|
|
"train_tokens_per_second": 774.933
|
|
},
|
|
{
|
|
"epoch": 0.014127290260366441,
|
|
"grad_norm": 5.207818984985352,
|
|
"learning_rate": 0.00019990818744812966,
|
|
"loss": 0.9905484008789063,
|
|
"num_input_tokens_seen": 34494504,
|
|
"step": 14650,
|
|
"train_runtime": 44522.2344,
|
|
"train_tokens_per_second": 774.77
|
|
},
|
|
{
|
|
"epoch": 0.014175506268081003,
|
|
"grad_norm": 8.16810131072998,
|
|
"learning_rate": 0.00019990753704347117,
|
|
"loss": 0.9376068115234375,
|
|
"num_input_tokens_seen": 34553560,
|
|
"step": 14700,
|
|
"train_runtime": 44607.46,
|
|
"train_tokens_per_second": 774.614
|
|
},
|
|
{
|
|
"epoch": 0.014223722275795565,
|
|
"grad_norm": 4.27252197265625,
|
|
"learning_rate": 0.00019990688434425282,
|
|
"loss": 1.035296173095703,
|
|
"num_input_tokens_seen": 34609816,
|
|
"step": 14750,
|
|
"train_runtime": 44690.0457,
|
|
"train_tokens_per_second": 774.441
|
|
},
|
|
{
|
|
"epoch": 0.014271938283510125,
|
|
"grad_norm": 10.213982582092285,
|
|
"learning_rate": 0.0001999062293504896,
|
|
"loss": 0.9761581420898438,
|
|
"num_input_tokens_seen": 34669520,
|
|
"step": 14800,
|
|
"train_runtime": 44776.3516,
|
|
"train_tokens_per_second": 774.282
|
|
},
|
|
{
|
|
"epoch": 0.014320154291224687,
|
|
"grad_norm": 6.690714359283447,
|
|
"learning_rate": 0.00019990557206219653,
|
|
"loss": 0.9186937713623047,
|
|
"num_input_tokens_seen": 34726128,
|
|
"step": 14850,
|
|
"train_runtime": 44858.2347,
|
|
"train_tokens_per_second": 774.131
|
|
},
|
|
{
|
|
"epoch": 0.014368370298939248,
|
|
"grad_norm": 6.133081436157227,
|
|
"learning_rate": 0.00019990491247938875,
|
|
"loss": 1.016747360229492,
|
|
"num_input_tokens_seen": 34789744,
|
|
"step": 14900,
|
|
"train_runtime": 44948.4303,
|
|
"train_tokens_per_second": 773.992
|
|
},
|
|
{
|
|
"epoch": 0.014416586306653809,
|
|
"grad_norm": 7.0184783935546875,
|
|
"learning_rate": 0.00019990425060208137,
|
|
"loss": 0.9253949737548828,
|
|
"num_input_tokens_seen": 34844712,
|
|
"step": 14950,
|
|
"train_runtime": 45029.3382,
|
|
"train_tokens_per_second": 773.822
|
|
},
|
|
{
|
|
"epoch": 0.01446480231436837,
|
|
"grad_norm": 7.4791083335876465,
|
|
"learning_rate": 0.00019990358643028958,
|
|
"loss": 1.0024604034423827,
|
|
"num_input_tokens_seen": 34901240,
|
|
"step": 15000,
|
|
"train_runtime": 45112.402,
|
|
"train_tokens_per_second": 773.651
|
|
},
|
|
{
|
|
"epoch": 0.014513018322082932,
|
|
"grad_norm": 5.102107048034668,
|
|
"learning_rate": 0.0001999029199640287,
|
|
"loss": 1.0305980682373046,
|
|
"num_input_tokens_seen": 34961176,
|
|
"step": 15050,
|
|
"train_runtime": 45198.1013,
|
|
"train_tokens_per_second": 773.51
|
|
},
|
|
{
|
|
"epoch": 0.014561234329797492,
|
|
"grad_norm": 8.383728981018066,
|
|
"learning_rate": 0.00019990225120331397,
|
|
"loss": 0.9804248046875,
|
|
"num_input_tokens_seen": 35021712,
|
|
"step": 15100,
|
|
"train_runtime": 45284.4523,
|
|
"train_tokens_per_second": 773.372
|
|
},
|
|
{
|
|
"epoch": 0.014609450337512054,
|
|
"grad_norm": 7.355087757110596,
|
|
"learning_rate": 0.00019990158014816076,
|
|
"loss": 1.0470338439941407,
|
|
"num_input_tokens_seen": 35083424,
|
|
"step": 15150,
|
|
"train_runtime": 45373.3426,
|
|
"train_tokens_per_second": 773.217
|
|
},
|
|
{
|
|
"epoch": 0.014657666345226614,
|
|
"grad_norm": 6.456941604614258,
|
|
"learning_rate": 0.0001999009067985845,
|
|
"loss": 1.014673080444336,
|
|
"num_input_tokens_seen": 35142984,
|
|
"step": 15200,
|
|
"train_runtime": 45458.2223,
|
|
"train_tokens_per_second": 773.083
|
|
},
|
|
{
|
|
"epoch": 0.014705882352941176,
|
|
"grad_norm": 10.15037727355957,
|
|
"learning_rate": 0.00019990023115460068,
|
|
"loss": 0.9284634399414062,
|
|
"num_input_tokens_seen": 35193464,
|
|
"step": 15250,
|
|
"train_runtime": 45533.492,
|
|
"train_tokens_per_second": 772.914
|
|
},
|
|
{
|
|
"epoch": 0.014754098360655738,
|
|
"grad_norm": 5.742589950561523,
|
|
"learning_rate": 0.00019989955321622475,
|
|
"loss": 0.9250184631347657,
|
|
"num_input_tokens_seen": 35246520,
|
|
"step": 15300,
|
|
"train_runtime": 45611.8448,
|
|
"train_tokens_per_second": 772.749
|
|
},
|
|
{
|
|
"epoch": 0.014802314368370298,
|
|
"grad_norm": 8.366775512695312,
|
|
"learning_rate": 0.00019989887298347235,
|
|
"loss": 0.9695088195800782,
|
|
"num_input_tokens_seen": 35310424,
|
|
"step": 15350,
|
|
"train_runtime": 45702.038,
|
|
"train_tokens_per_second": 772.623
|
|
},
|
|
{
|
|
"epoch": 0.01485053037608486,
|
|
"grad_norm": 8.185744285583496,
|
|
"learning_rate": 0.00019989819045635905,
|
|
"loss": 1.0129987335205077,
|
|
"num_input_tokens_seen": 35370696,
|
|
"step": 15400,
|
|
"train_runtime": 45789.2627,
|
|
"train_tokens_per_second": 772.467
|
|
},
|
|
{
|
|
"epoch": 0.014898746383799422,
|
|
"grad_norm": 5.2154083251953125,
|
|
"learning_rate": 0.00019989751935381417,
|
|
"loss": 1.0441301727294923,
|
|
"num_input_tokens_seen": 35429472,
|
|
"step": 15450,
|
|
"train_runtime": 45873.6701,
|
|
"train_tokens_per_second": 772.327
|
|
},
|
|
{
|
|
"epoch": 0.014946962391513982,
|
|
"grad_norm": 5.300354957580566,
|
|
"learning_rate": 0.00019989683228391266,
|
|
"loss": 0.9193112182617188,
|
|
"num_input_tokens_seen": 35484776,
|
|
"step": 15500,
|
|
"train_runtime": 45954.3762,
|
|
"train_tokens_per_second": 772.174
|
|
},
|
|
{
|
|
"epoch": 0.014995178399228544,
|
|
"grad_norm": 6.0389723777771,
|
|
"learning_rate": 0.0001998961429196971,
|
|
"loss": 0.9634468078613281,
|
|
"num_input_tokens_seen": 35539488,
|
|
"step": 15550,
|
|
"train_runtime": 46034.7441,
|
|
"train_tokens_per_second": 772.014
|
|
},
|
|
{
|
|
"epoch": 0.015043394406943106,
|
|
"grad_norm": 7.80370569229126,
|
|
"learning_rate": 0.00019989545126118335,
|
|
"loss": 1.0499915313720702,
|
|
"num_input_tokens_seen": 35599936,
|
|
"step": 15600,
|
|
"train_runtime": 46121.3383,
|
|
"train_tokens_per_second": 771.876
|
|
},
|
|
{
|
|
"epoch": 0.015091610414657666,
|
|
"grad_norm": 6.751246929168701,
|
|
"learning_rate": 0.00019989475730838733,
|
|
"loss": 0.9867279815673828,
|
|
"num_input_tokens_seen": 35658960,
|
|
"step": 15650,
|
|
"train_runtime": 46205.1563,
|
|
"train_tokens_per_second": 771.753
|
|
},
|
|
{
|
|
"epoch": 0.015139826422372228,
|
|
"grad_norm": 9.728730201721191,
|
|
"learning_rate": 0.00019989406106132496,
|
|
"loss": 0.9741952514648438,
|
|
"num_input_tokens_seen": 35716064,
|
|
"step": 15700,
|
|
"train_runtime": 46288.601,
|
|
"train_tokens_per_second": 771.595
|
|
},
|
|
{
|
|
"epoch": 0.01518804243008679,
|
|
"grad_norm": 7.22682523727417,
|
|
"learning_rate": 0.0001998933625200122,
|
|
"loss": 1.0305697631835937,
|
|
"num_input_tokens_seen": 35777128,
|
|
"step": 15750,
|
|
"train_runtime": 46376.1026,
|
|
"train_tokens_per_second": 771.456
|
|
},
|
|
{
|
|
"epoch": 0.01523625843780135,
|
|
"grad_norm": 8.590719223022461,
|
|
"learning_rate": 0.00019989266168446513,
|
|
"loss": 0.9551310729980469,
|
|
"num_input_tokens_seen": 35828016,
|
|
"step": 15800,
|
|
"train_runtime": 46452.4625,
|
|
"train_tokens_per_second": 771.283
|
|
},
|
|
{
|
|
"epoch": 0.015284474445515912,
|
|
"grad_norm": 6.330549716949463,
|
|
"learning_rate": 0.00019989195855469984,
|
|
"loss": 0.913033218383789,
|
|
"num_input_tokens_seen": 35884456,
|
|
"step": 15850,
|
|
"train_runtime": 46534.6476,
|
|
"train_tokens_per_second": 771.134
|
|
},
|
|
{
|
|
"epoch": 0.015332690453230472,
|
|
"grad_norm": 8.64586353302002,
|
|
"learning_rate": 0.00019989125313073247,
|
|
"loss": 1.0224980926513672,
|
|
"num_input_tokens_seen": 35937144,
|
|
"step": 15900,
|
|
"train_runtime": 46612.5596,
|
|
"train_tokens_per_second": 770.976
|
|
},
|
|
{
|
|
"epoch": 0.015380906460945034,
|
|
"grad_norm": 5.670004844665527,
|
|
"learning_rate": 0.00019989054541257923,
|
|
"loss": 0.9575067901611328,
|
|
"num_input_tokens_seen": 35995168,
|
|
"step": 15950,
|
|
"train_runtime": 46696.0533,
|
|
"train_tokens_per_second": 770.84
|
|
},
|
|
{
|
|
"epoch": 0.015429122468659595,
|
|
"grad_norm": 6.650516033172607,
|
|
"learning_rate": 0.00019988983540025635,
|
|
"loss": 0.941690673828125,
|
|
"num_input_tokens_seen": 36047656,
|
|
"step": 16000,
|
|
"train_runtime": 46774.82,
|
|
"train_tokens_per_second": 770.664
|
|
},
|
|
{
|
|
"epoch": 0.015477338476374156,
|
|
"grad_norm": 6.990214824676514,
|
|
"learning_rate": 0.00019988912309378017,
|
|
"loss": 0.9973748779296875,
|
|
"num_input_tokens_seen": 36098728,
|
|
"step": 16050,
|
|
"train_runtime": 46851.6049,
|
|
"train_tokens_per_second": 770.491
|
|
},
|
|
{
|
|
"epoch": 0.015525554484088717,
|
|
"grad_norm": 6.967688083648682,
|
|
"learning_rate": 0.000199888408493167,
|
|
"loss": 0.9471905517578125,
|
|
"num_input_tokens_seen": 36153136,
|
|
"step": 16100,
|
|
"train_runtime": 46932.5336,
|
|
"train_tokens_per_second": 770.321
|
|
},
|
|
{
|
|
"epoch": 0.01557377049180328,
|
|
"grad_norm": 6.735581398010254,
|
|
"learning_rate": 0.00019988769159843335,
|
|
"loss": 0.9542222595214844,
|
|
"num_input_tokens_seen": 36209328,
|
|
"step": 16150,
|
|
"train_runtime": 47014.3463,
|
|
"train_tokens_per_second": 770.176
|
|
},
|
|
{
|
|
"epoch": 0.01562198649951784,
|
|
"grad_norm": 6.302603244781494,
|
|
"learning_rate": 0.00019988697240959558,
|
|
"loss": 0.9631063842773437,
|
|
"num_input_tokens_seen": 36261152,
|
|
"step": 16200,
|
|
"train_runtime": 47092.3632,
|
|
"train_tokens_per_second": 770.001
|
|
},
|
|
{
|
|
"epoch": 0.0156702025072324,
|
|
"grad_norm": 6.198716640472412,
|
|
"learning_rate": 0.00019988625092667026,
|
|
"loss": 0.928399429321289,
|
|
"num_input_tokens_seen": 36322360,
|
|
"step": 16250,
|
|
"train_runtime": 47179.9708,
|
|
"train_tokens_per_second": 769.868
|
|
},
|
|
{
|
|
"epoch": 0.01571841851494696,
|
|
"grad_norm": 8.56251049041748,
|
|
"learning_rate": 0.00019988552714967392,
|
|
"loss": 0.9952062225341797,
|
|
"num_input_tokens_seen": 36380376,
|
|
"step": 16300,
|
|
"train_runtime": 47263.2299,
|
|
"train_tokens_per_second": 769.74
|
|
},
|
|
{
|
|
"epoch": 0.015766634522661523,
|
|
"grad_norm": 8.306207656860352,
|
|
"learning_rate": 0.00019988480107862325,
|
|
"loss": 0.9379901123046875,
|
|
"num_input_tokens_seen": 36435504,
|
|
"step": 16350,
|
|
"train_runtime": 47344.1483,
|
|
"train_tokens_per_second": 769.588
|
|
},
|
|
{
|
|
"epoch": 0.015814850530376085,
|
|
"grad_norm": 5.301617622375488,
|
|
"learning_rate": 0.00019988407271353487,
|
|
"loss": 0.9414238739013672,
|
|
"num_input_tokens_seen": 36485696,
|
|
"step": 16400,
|
|
"train_runtime": 47419.778,
|
|
"train_tokens_per_second": 769.419
|
|
},
|
|
{
|
|
"epoch": 0.015863066538090647,
|
|
"grad_norm": 5.427783012390137,
|
|
"learning_rate": 0.00019988334205442554,
|
|
"loss": 0.9604396820068359,
|
|
"num_input_tokens_seen": 36540392,
|
|
"step": 16450,
|
|
"train_runtime": 47500.6031,
|
|
"train_tokens_per_second": 769.262
|
|
},
|
|
{
|
|
"epoch": 0.01591128254580521,
|
|
"grad_norm": 5.731225490570068,
|
|
"learning_rate": 0.000199882609101312,
|
|
"loss": 0.9357376098632812,
|
|
"num_input_tokens_seen": 36594240,
|
|
"step": 16500,
|
|
"train_runtime": 47581.4619,
|
|
"train_tokens_per_second": 769.086
|
|
},
|
|
{
|
|
"epoch": 0.015959498553519767,
|
|
"grad_norm": 8.588957786560059,
|
|
"learning_rate": 0.0001998818738542111,
|
|
"loss": 0.9806840515136719,
|
|
"num_input_tokens_seen": 36651640,
|
|
"step": 16550,
|
|
"train_runtime": 47664.9503,
|
|
"train_tokens_per_second": 768.943
|
|
},
|
|
{
|
|
"epoch": 0.01600771456123433,
|
|
"grad_norm": 9.474140167236328,
|
|
"learning_rate": 0.0001998811363131398,
|
|
"loss": 0.9454917144775391,
|
|
"num_input_tokens_seen": 36707648,
|
|
"step": 16600,
|
|
"train_runtime": 47747.7063,
|
|
"train_tokens_per_second": 768.783
|
|
},
|
|
{
|
|
"epoch": 0.01605593056894889,
|
|
"grad_norm": 6.881364822387695,
|
|
"learning_rate": 0.00019988039647811492,
|
|
"loss": 0.9727147674560547,
|
|
"num_input_tokens_seen": 36766512,
|
|
"step": 16650,
|
|
"train_runtime": 47832.7521,
|
|
"train_tokens_per_second": 768.647
|
|
},
|
|
{
|
|
"epoch": 0.016104146576663453,
|
|
"grad_norm": 5.563490867614746,
|
|
"learning_rate": 0.00019987965434915353,
|
|
"loss": 0.9509459686279297,
|
|
"num_input_tokens_seen": 36818072,
|
|
"step": 16700,
|
|
"train_runtime": 47910.5615,
|
|
"train_tokens_per_second": 768.475
|
|
},
|
|
{
|
|
"epoch": 0.016152362584378015,
|
|
"grad_norm": 7.537481307983398,
|
|
"learning_rate": 0.00019987890992627263,
|
|
"loss": 0.981600341796875,
|
|
"num_input_tokens_seen": 36870144,
|
|
"step": 16750,
|
|
"train_runtime": 47988.5036,
|
|
"train_tokens_per_second": 768.312
|
|
},
|
|
{
|
|
"epoch": 0.016200578592092573,
|
|
"grad_norm": 7.261979579925537,
|
|
"learning_rate": 0.00019987816320948937,
|
|
"loss": 0.9038677215576172,
|
|
"num_input_tokens_seen": 36924480,
|
|
"step": 16800,
|
|
"train_runtime": 48067.6836,
|
|
"train_tokens_per_second": 768.177
|
|
},
|
|
{
|
|
"epoch": 0.016248794599807135,
|
|
"grad_norm": 6.556126117706299,
|
|
"learning_rate": 0.00019987741419882086,
|
|
"loss": 0.8860893249511719,
|
|
"num_input_tokens_seen": 36972256,
|
|
"step": 16850,
|
|
"train_runtime": 48140.7067,
|
|
"train_tokens_per_second": 768.004
|
|
},
|
|
{
|
|
"epoch": 0.016297010607521697,
|
|
"grad_norm": 4.881107330322266,
|
|
"learning_rate": 0.00019987666289428426,
|
|
"loss": 0.951117935180664,
|
|
"num_input_tokens_seen": 37026400,
|
|
"step": 16900,
|
|
"train_runtime": 48220.5691,
|
|
"train_tokens_per_second": 767.855
|
|
},
|
|
{
|
|
"epoch": 0.01634522661523626,
|
|
"grad_norm": 6.199646472930908,
|
|
"learning_rate": 0.00019987590929589693,
|
|
"loss": 0.9659663391113281,
|
|
"num_input_tokens_seen": 37077240,
|
|
"step": 16950,
|
|
"train_runtime": 48296.401,
|
|
"train_tokens_per_second": 767.702
|
|
},
|
|
{
|
|
"epoch": 0.01639344262295082,
|
|
"grad_norm": 4.940591812133789,
|
|
"learning_rate": 0.00019987515340367612,
|
|
"loss": 0.929069595336914,
|
|
"num_input_tokens_seen": 37127176,
|
|
"step": 17000,
|
|
"train_runtime": 48371.2502,
|
|
"train_tokens_per_second": 767.546
|
|
},
|
|
{
|
|
"epoch": 0.016441658630665382,
|
|
"grad_norm": 18.850107192993164,
|
|
"learning_rate": 0.00019987439521763916,
|
|
"loss": 0.9233118438720703,
|
|
"num_input_tokens_seen": 37184232,
|
|
"step": 17050,
|
|
"train_runtime": 48454.9712,
|
|
"train_tokens_per_second": 767.398
|
|
},
|
|
{
|
|
"epoch": 0.01648987463837994,
|
|
"grad_norm": 12.757966041564941,
|
|
"learning_rate": 0.00019987363473780354,
|
|
"loss": 0.9171466827392578,
|
|
"num_input_tokens_seen": 37237304,
|
|
"step": 17100,
|
|
"train_runtime": 48533.8616,
|
|
"train_tokens_per_second": 767.244
|
|
},
|
|
{
|
|
"epoch": 0.016538090646094503,
|
|
"grad_norm": 8.09614372253418,
|
|
"learning_rate": 0.00019987287196418665,
|
|
"loss": 0.8737010955810547,
|
|
"num_input_tokens_seen": 37289736,
|
|
"step": 17150,
|
|
"train_runtime": 48611.6001,
|
|
"train_tokens_per_second": 767.095
|
|
},
|
|
{
|
|
"epoch": 0.016586306653809064,
|
|
"grad_norm": 8.570305824279785,
|
|
"learning_rate": 0.00019987210689680605,
|
|
"loss": 0.9734009552001953,
|
|
"num_input_tokens_seen": 37339912,
|
|
"step": 17200,
|
|
"train_runtime": 48686.3809,
|
|
"train_tokens_per_second": 766.948
|
|
},
|
|
{
|
|
"epoch": 0.016634522661523626,
|
|
"grad_norm": 8.132840156555176,
|
|
"learning_rate": 0.00019987133953567931,
|
|
"loss": 0.9668477630615234,
|
|
"num_input_tokens_seen": 37392720,
|
|
"step": 17250,
|
|
"train_runtime": 48764.0465,
|
|
"train_tokens_per_second": 766.809
|
|
},
|
|
{
|
|
"epoch": 0.016682738669238188,
|
|
"grad_norm": 7.611454963684082,
|
|
"learning_rate": 0.00019987056988082403,
|
|
"loss": 0.8481081390380859,
|
|
"num_input_tokens_seen": 37443752,
|
|
"step": 17300,
|
|
"train_runtime": 48840.4058,
|
|
"train_tokens_per_second": 766.655
|
|
},
|
|
{
|
|
"epoch": 0.016730954676952747,
|
|
"grad_norm": 9.341901779174805,
|
|
"learning_rate": 0.00019986979793225793,
|
|
"loss": 0.922853012084961,
|
|
"num_input_tokens_seen": 37501208,
|
|
"step": 17350,
|
|
"train_runtime": 48923.1957,
|
|
"train_tokens_per_second": 766.532
|
|
},
|
|
{
|
|
"epoch": 0.01677917068466731,
|
|
"grad_norm": 6.233309268951416,
|
|
"learning_rate": 0.0001998690236899987,
|
|
"loss": 0.9147994232177734,
|
|
"num_input_tokens_seen": 37561024,
|
|
"step": 17400,
|
|
"train_runtime": 49008.7929,
|
|
"train_tokens_per_second": 766.414
|
|
},
|
|
{
|
|
"epoch": 0.01682738669238187,
|
|
"grad_norm": 8.314106941223145,
|
|
"learning_rate": 0.00019986824715406413,
|
|
"loss": 1.0152000427246093,
|
|
"num_input_tokens_seen": 37612392,
|
|
"step": 17450,
|
|
"train_runtime": 49084.9938,
|
|
"train_tokens_per_second": 766.271
|
|
},
|
|
{
|
|
"epoch": 0.016875602700096432,
|
|
"grad_norm": 7.745499610900879,
|
|
"learning_rate": 0.00019986746832447206,
|
|
"loss": 0.9322709655761718,
|
|
"num_input_tokens_seen": 37659216,
|
|
"step": 17500,
|
|
"train_runtime": 49157.8912,
|
|
"train_tokens_per_second": 766.087
|
|
},
|
|
{
|
|
"epoch": 0.016923818707810994,
|
|
"grad_norm": 5.748786926269531,
|
|
"learning_rate": 0.00019986668720124037,
|
|
"loss": 0.9013899230957031,
|
|
"num_input_tokens_seen": 37709656,
|
|
"step": 17550,
|
|
"train_runtime": 49233.2107,
|
|
"train_tokens_per_second": 765.939
|
|
},
|
|
{
|
|
"epoch": 0.016972034715525556,
|
|
"grad_norm": 9.423219680786133,
|
|
"learning_rate": 0.000199865903784387,
|
|
"loss": 0.9030335235595703,
|
|
"num_input_tokens_seen": 37761192,
|
|
"step": 17600,
|
|
"train_runtime": 49309.9627,
|
|
"train_tokens_per_second": 765.792
|
|
},
|
|
{
|
|
"epoch": 0.017020250723240114,
|
|
"grad_norm": 6.137840747833252,
|
|
"learning_rate": 0.00019986511807392994,
|
|
"loss": 0.9651508331298828,
|
|
"num_input_tokens_seen": 37814408,
|
|
"step": 17650,
|
|
"train_runtime": 49388.3229,
|
|
"train_tokens_per_second": 765.655
|
|
},
|
|
{
|
|
"epoch": 0.017068466730954676,
|
|
"grad_norm": 5.830076694488525,
|
|
"learning_rate": 0.00019986433006988728,
|
|
"loss": 0.9544180297851562,
|
|
"num_input_tokens_seen": 37864848,
|
|
"step": 17700,
|
|
"train_runtime": 49463.4512,
|
|
"train_tokens_per_second": 765.512
|
|
},
|
|
{
|
|
"epoch": 0.017116682738669238,
|
|
"grad_norm": 6.705332279205322,
|
|
"learning_rate": 0.00019986353977227705,
|
|
"loss": 0.8670779418945312,
|
|
"num_input_tokens_seen": 37914992,
|
|
"step": 17750,
|
|
"train_runtime": 49538.4949,
|
|
"train_tokens_per_second": 765.364
|
|
},
|
|
{
|
|
"epoch": 0.0171648987463838,
|
|
"grad_norm": 8.50774097442627,
|
|
"learning_rate": 0.00019986274718111747,
|
|
"loss": 0.9901067352294922,
|
|
"num_input_tokens_seen": 37968160,
|
|
"step": 17800,
|
|
"train_runtime": 49616.6094,
|
|
"train_tokens_per_second": 765.231
|
|
},
|
|
{
|
|
"epoch": 0.01721311475409836,
|
|
"grad_norm": 7.036761283874512,
|
|
"learning_rate": 0.00019986195229642668,
|
|
"loss": 0.9320948028564453,
|
|
"num_input_tokens_seen": 38012824,
|
|
"step": 17850,
|
|
"train_runtime": 49685.2229,
|
|
"train_tokens_per_second": 765.073
|
|
},
|
|
{
|
|
"epoch": 0.017261330761812924,
|
|
"grad_norm": 6.504554748535156,
|
|
"learning_rate": 0.00019986115511822297,
|
|
"loss": 0.9089884948730469,
|
|
"num_input_tokens_seen": 38064456,
|
|
"step": 17900,
|
|
"train_runtime": 49762.0727,
|
|
"train_tokens_per_second": 764.929
|
|
},
|
|
{
|
|
"epoch": 0.017309546769527482,
|
|
"grad_norm": 5.69332218170166,
|
|
"learning_rate": 0.0001998603556465246,
|
|
"loss": 0.8974175262451172,
|
|
"num_input_tokens_seen": 38113264,
|
|
"step": 17950,
|
|
"train_runtime": 49835.9254,
|
|
"train_tokens_per_second": 764.775
|
|
},
|
|
{
|
|
"epoch": 0.017357762777242044,
|
|
"grad_norm": 8.554183959960938,
|
|
"learning_rate": 0.00019985955388135003,
|
|
"loss": 0.9513985443115235,
|
|
"num_input_tokens_seen": 38163752,
|
|
"step": 18000,
|
|
"train_runtime": 49912.5596,
|
|
"train_tokens_per_second": 764.612
|
|
},
|
|
{
|
|
"epoch": 0.017405978784956606,
|
|
"grad_norm": 7.024445533752441,
|
|
"learning_rate": 0.00019985874982271758,
|
|
"loss": 0.9576093292236328,
|
|
"num_input_tokens_seen": 38210856,
|
|
"step": 18050,
|
|
"train_runtime": 49985.0212,
|
|
"train_tokens_per_second": 764.446
|
|
},
|
|
{
|
|
"epoch": 0.017454194792671168,
|
|
"grad_norm": 9.59158992767334,
|
|
"learning_rate": 0.00019985794347064575,
|
|
"loss": 0.9649050903320312,
|
|
"num_input_tokens_seen": 38261832,
|
|
"step": 18100,
|
|
"train_runtime": 50060.9406,
|
|
"train_tokens_per_second": 764.305
|
|
},
|
|
{
|
|
"epoch": 0.01750241080038573,
|
|
"grad_norm": 8.094367980957031,
|
|
"learning_rate": 0.00019985713482515308,
|
|
"loss": 0.9497956085205078,
|
|
"num_input_tokens_seen": 38318544,
|
|
"step": 18150,
|
|
"train_runtime": 50144.1559,
|
|
"train_tokens_per_second": 764.168
|
|
},
|
|
{
|
|
"epoch": 0.017550626808100288,
|
|
"grad_norm": 7.11672830581665,
|
|
"learning_rate": 0.0001998563238862581,
|
|
"loss": 0.8848564147949218,
|
|
"num_input_tokens_seen": 38367104,
|
|
"step": 18200,
|
|
"train_runtime": 50217.9407,
|
|
"train_tokens_per_second": 764.012
|
|
},
|
|
{
|
|
"epoch": 0.01759884281581485,
|
|
"grad_norm": 5.522322654724121,
|
|
"learning_rate": 0.0001998555106539795,
|
|
"loss": 0.8979723358154297,
|
|
"num_input_tokens_seen": 38417040,
|
|
"step": 18250,
|
|
"train_runtime": 50293.2353,
|
|
"train_tokens_per_second": 763.861
|
|
},
|
|
{
|
|
"epoch": 0.01764705882352941,
|
|
"grad_norm": 9.072237968444824,
|
|
"learning_rate": 0.0001998546951283359,
|
|
"loss": 0.9188253021240235,
|
|
"num_input_tokens_seen": 38464760,
|
|
"step": 18300,
|
|
"train_runtime": 50365.4165,
|
|
"train_tokens_per_second": 763.714
|
|
},
|
|
{
|
|
"epoch": 0.017695274831243973,
|
|
"grad_norm": 8.5104398727417,
|
|
"learning_rate": 0.00019985387730934602,
|
|
"loss": 0.9317515563964843,
|
|
"num_input_tokens_seen": 38511216,
|
|
"step": 18350,
|
|
"train_runtime": 50436.7586,
|
|
"train_tokens_per_second": 763.555
|
|
},
|
|
{
|
|
"epoch": 0.017743490838958535,
|
|
"grad_norm": 6.094876289367676,
|
|
"learning_rate": 0.0001998530571970287,
|
|
"loss": 0.9491600799560547,
|
|
"num_input_tokens_seen": 38562904,
|
|
"step": 18400,
|
|
"train_runtime": 50512.5914,
|
|
"train_tokens_per_second": 763.432
|
|
},
|
|
{
|
|
"epoch": 0.017791706846673097,
|
|
"grad_norm": 6.952563762664795,
|
|
"learning_rate": 0.00019985223479140272,
|
|
"loss": 1.0153215026855469,
|
|
"num_input_tokens_seen": 38615192,
|
|
"step": 18450,
|
|
"train_runtime": 50590.5886,
|
|
"train_tokens_per_second": 763.288
|
|
},
|
|
{
|
|
"epoch": 0.017839922854387655,
|
|
"grad_norm": 6.597976207733154,
|
|
"learning_rate": 0.000199851410092487,
|
|
"loss": 0.9445113372802735,
|
|
"num_input_tokens_seen": 38664616,
|
|
"step": 18500,
|
|
"train_runtime": 50665.0477,
|
|
"train_tokens_per_second": 763.142
|
|
},
|
|
{
|
|
"epoch": 0.017888138862102217,
|
|
"grad_norm": 5.053223609924316,
|
|
"learning_rate": 0.00019985058310030044,
|
|
"loss": 0.9296729278564453,
|
|
"num_input_tokens_seen": 38713904,
|
|
"step": 18550,
|
|
"train_runtime": 50739.0037,
|
|
"train_tokens_per_second": 763.001
|
|
},
|
|
{
|
|
"epoch": 0.01793635486981678,
|
|
"grad_norm": 9.550543785095215,
|
|
"learning_rate": 0.00019984975381486214,
|
|
"loss": 0.9493775177001953,
|
|
"num_input_tokens_seen": 38760304,
|
|
"step": 18600,
|
|
"train_runtime": 50809.4212,
|
|
"train_tokens_per_second": 762.857
|
|
},
|
|
{
|
|
"epoch": 0.01798457087753134,
|
|
"grad_norm": 6.740452766418457,
|
|
"learning_rate": 0.000199848922236191,
|
|
"loss": 0.8991613006591797,
|
|
"num_input_tokens_seen": 38809800,
|
|
"step": 18650,
|
|
"train_runtime": 50884.071,
|
|
"train_tokens_per_second": 762.71
|
|
},
|
|
{
|
|
"epoch": 0.018032786885245903,
|
|
"grad_norm": 10.679743766784668,
|
|
"learning_rate": 0.00019984808836430622,
|
|
"loss": 0.9129997253417969,
|
|
"num_input_tokens_seen": 38859000,
|
|
"step": 18700,
|
|
"train_runtime": 50958.8504,
|
|
"train_tokens_per_second": 762.556
|
|
},
|
|
{
|
|
"epoch": 0.01808100289296046,
|
|
"grad_norm": 4.517518520355225,
|
|
"learning_rate": 0.00019984725219922693,
|
|
"loss": 0.8991841125488281,
|
|
"num_input_tokens_seen": 38909272,
|
|
"step": 18750,
|
|
"train_runtime": 51033.8794,
|
|
"train_tokens_per_second": 762.42
|
|
},
|
|
{
|
|
"epoch": 0.018129218900675023,
|
|
"grad_norm": 10.947480201721191,
|
|
"learning_rate": 0.0001998464137409723,
|
|
"loss": 0.9492632293701172,
|
|
"num_input_tokens_seen": 38960752,
|
|
"step": 18800,
|
|
"train_runtime": 51110.6082,
|
|
"train_tokens_per_second": 762.283
|
|
},
|
|
{
|
|
"epoch": 0.018177434908389585,
|
|
"grad_norm": 8.860642433166504,
|
|
"learning_rate": 0.00019984557298956162,
|
|
"loss": 0.9313348388671875,
|
|
"num_input_tokens_seen": 39014048,
|
|
"step": 18850,
|
|
"train_runtime": 51189.3338,
|
|
"train_tokens_per_second": 762.152
|
|
},
|
|
{
|
|
"epoch": 0.018225650916104147,
|
|
"grad_norm": 6.976455211639404,
|
|
"learning_rate": 0.00019984472994501423,
|
|
"loss": 0.8758116912841797,
|
|
"num_input_tokens_seen": 39060416,
|
|
"step": 18900,
|
|
"train_runtime": 51258.6792,
|
|
"train_tokens_per_second": 762.025
|
|
},
|
|
{
|
|
"epoch": 0.01827386692381871,
|
|
"grad_norm": 4.859806537628174,
|
|
"learning_rate": 0.00019984388460734943,
|
|
"loss": 0.89221435546875,
|
|
"num_input_tokens_seen": 39104728,
|
|
"step": 18950,
|
|
"train_runtime": 51326.9425,
|
|
"train_tokens_per_second": 761.875
|
|
},
|
|
{
|
|
"epoch": 0.01832208293153327,
|
|
"grad_norm": 8.273653984069824,
|
|
"learning_rate": 0.00019984303697658665,
|
|
"loss": 0.9285385894775391,
|
|
"num_input_tokens_seen": 39151848,
|
|
"step": 19000,
|
|
"train_runtime": 51398.6921,
|
|
"train_tokens_per_second": 761.728
|
|
},
|
|
{
|
|
"epoch": 0.01837029893924783,
|
|
"grad_norm": 6.348496437072754,
|
|
"learning_rate": 0.00019984218705274538,
|
|
"loss": 0.9424622344970703,
|
|
"num_input_tokens_seen": 39200864,
|
|
"step": 19050,
|
|
"train_runtime": 51473.1507,
|
|
"train_tokens_per_second": 761.579
|
|
},
|
|
{
|
|
"epoch": 0.01841851494696239,
|
|
"grad_norm": 7.468011856079102,
|
|
"learning_rate": 0.00019984133483584514,
|
|
"loss": 0.9169634246826172,
|
|
"num_input_tokens_seen": 39248760,
|
|
"step": 19100,
|
|
"train_runtime": 51546.499,
|
|
"train_tokens_per_second": 761.424
|
|
},
|
|
{
|
|
"epoch": 0.018466730954676953,
|
|
"grad_norm": 8.517454147338867,
|
|
"learning_rate": 0.00019984048032590544,
|
|
"loss": 0.9655600738525391,
|
|
"num_input_tokens_seen": 39296680,
|
|
"step": 19150,
|
|
"train_runtime": 51618.4657,
|
|
"train_tokens_per_second": 761.291
|
|
},
|
|
{
|
|
"epoch": 0.018514946962391515,
|
|
"grad_norm": 10.671344757080078,
|
|
"learning_rate": 0.00019983962352294597,
|
|
"loss": 0.906551742553711,
|
|
"num_input_tokens_seen": 39345400,
|
|
"step": 19200,
|
|
"train_runtime": 51692.8916,
|
|
"train_tokens_per_second": 761.138
|
|
},
|
|
{
|
|
"epoch": 0.018563162970106076,
|
|
"grad_norm": 7.118502616882324,
|
|
"learning_rate": 0.00019983876442698643,
|
|
"loss": 0.8576236724853515,
|
|
"num_input_tokens_seen": 39395608,
|
|
"step": 19250,
|
|
"train_runtime": 51768.5697,
|
|
"train_tokens_per_second": 760.995
|
|
},
|
|
{
|
|
"epoch": 0.018611378977820635,
|
|
"grad_norm": 8.463969230651855,
|
|
"learning_rate": 0.00019983790303804649,
|
|
"loss": 0.9192215728759766,
|
|
"num_input_tokens_seen": 39445232,
|
|
"step": 19300,
|
|
"train_runtime": 51843.6428,
|
|
"train_tokens_per_second": 760.85
|
|
},
|
|
{
|
|
"epoch": 0.018659594985535197,
|
|
"grad_norm": 7.146262168884277,
|
|
"learning_rate": 0.00019983703935614594,
|
|
"loss": 0.8806719970703125,
|
|
"num_input_tokens_seen": 39494648,
|
|
"step": 19350,
|
|
"train_runtime": 51916.9852,
|
|
"train_tokens_per_second": 760.727
|
|
},
|
|
{
|
|
"epoch": 0.01870781099324976,
|
|
"grad_norm": 6.033990383148193,
|
|
"learning_rate": 0.00019983617338130465,
|
|
"loss": 0.9428286743164063,
|
|
"num_input_tokens_seen": 39544472,
|
|
"step": 19400,
|
|
"train_runtime": 51991.954,
|
|
"train_tokens_per_second": 760.588
|
|
},
|
|
{
|
|
"epoch": 0.01875602700096432,
|
|
"grad_norm": 8.452130317687988,
|
|
"learning_rate": 0.0001998353051135425,
|
|
"loss": 0.8758746337890625,
|
|
"num_input_tokens_seen": 39586912,
|
|
"step": 19450,
|
|
"train_runtime": 52059.2664,
|
|
"train_tokens_per_second": 760.42
|
|
},
|
|
{
|
|
"epoch": 0.018804243008678882,
|
|
"grad_norm": 7.411045074462891,
|
|
"learning_rate": 0.0001998344345528794,
|
|
"loss": 0.9001249694824218,
|
|
"num_input_tokens_seen": 39637008,
|
|
"step": 19500,
|
|
"train_runtime": 52135.1339,
|
|
"train_tokens_per_second": 760.274
|
|
},
|
|
{
|
|
"epoch": 0.018852459016393444,
|
|
"grad_norm": 9.736394882202148,
|
|
"learning_rate": 0.00019983356169933538,
|
|
"loss": 0.8886833953857421,
|
|
"num_input_tokens_seen": 39684112,
|
|
"step": 19550,
|
|
"train_runtime": 52206.5815,
|
|
"train_tokens_per_second": 760.136
|
|
},
|
|
{
|
|
"epoch": 0.018900675024108003,
|
|
"grad_norm": 7.254018306732178,
|
|
"learning_rate": 0.0001998326865529305,
|
|
"loss": 0.9050562286376953,
|
|
"num_input_tokens_seen": 39729488,
|
|
"step": 19600,
|
|
"train_runtime": 52276.587,
|
|
"train_tokens_per_second": 759.986
|
|
},
|
|
{
|
|
"epoch": 0.018948891031822564,
|
|
"grad_norm": 13.63679313659668,
|
|
"learning_rate": 0.00019983180911368478,
|
|
"loss": 0.8739277648925782,
|
|
"num_input_tokens_seen": 39777392,
|
|
"step": 19650,
|
|
"train_runtime": 52348.0596,
|
|
"train_tokens_per_second": 759.864
|
|
},
|
|
{
|
|
"epoch": 0.018997107039537126,
|
|
"grad_norm": 5.271658897399902,
|
|
"learning_rate": 0.00019983092938161845,
|
|
"loss": 0.9129212188720703,
|
|
"num_input_tokens_seen": 39824016,
|
|
"step": 19700,
|
|
"train_runtime": 52419.1049,
|
|
"train_tokens_per_second": 759.723
|
|
},
|
|
{
|
|
"epoch": 0.019045323047251688,
|
|
"grad_norm": 8.027909278869629,
|
|
"learning_rate": 0.00019983004735675167,
|
|
"loss": 0.8752159118652344,
|
|
"num_input_tokens_seen": 39871984,
|
|
"step": 19750,
|
|
"train_runtime": 52492.5221,
|
|
"train_tokens_per_second": 759.575
|
|
},
|
|
{
|
|
"epoch": 0.01909353905496625,
|
|
"grad_norm": 5.9601263999938965,
|
|
"learning_rate": 0.00019982916303910476,
|
|
"loss": 0.8881507110595703,
|
|
"num_input_tokens_seen": 39919560,
|
|
"step": 19800,
|
|
"train_runtime": 52565.1251,
|
|
"train_tokens_per_second": 759.431
|
|
},
|
|
{
|
|
"epoch": 0.01914175506268081,
|
|
"grad_norm": 5.056262493133545,
|
|
"learning_rate": 0.00019982827642869798,
|
|
"loss": 0.9665273284912109,
|
|
"num_input_tokens_seen": 39967120,
|
|
"step": 19850,
|
|
"train_runtime": 52636.9403,
|
|
"train_tokens_per_second": 759.298
|
|
},
|
|
{
|
|
"epoch": 0.01918997107039537,
|
|
"grad_norm": 7.605624198913574,
|
|
"learning_rate": 0.00019982738752555168,
|
|
"loss": 0.9909703063964844,
|
|
"num_input_tokens_seen": 40012592,
|
|
"step": 19900,
|
|
"train_runtime": 52706.5203,
|
|
"train_tokens_per_second": 759.158
|
|
},
|
|
{
|
|
"epoch": 0.019238187078109932,
|
|
"grad_norm": 6.138595104217529,
|
|
"learning_rate": 0.0001998264963296863,
|
|
"loss": 0.9316679382324219,
|
|
"num_input_tokens_seen": 40062640,
|
|
"step": 19950,
|
|
"train_runtime": 52780.5961,
|
|
"train_tokens_per_second": 759.041
|
|
},
|
|
{
|
|
"epoch": 0.019286403085824494,
|
|
"grad_norm": 7.419726371765137,
|
|
"learning_rate": 0.00019982560284112228,
|
|
"loss": 0.9176594543457032,
|
|
"num_input_tokens_seen": 40108880,
|
|
"step": 20000,
|
|
"train_runtime": 52852.1192,
|
|
"train_tokens_per_second": 758.889
|
|
},
|
|
{
|
|
"epoch": 0.019334619093539056,
|
|
"grad_norm": 8.551705360412598,
|
|
"learning_rate": 0.00019982470705988018,
|
|
"loss": 0.9541797637939453,
|
|
"num_input_tokens_seen": 40153192,
|
|
"step": 20050,
|
|
"train_runtime": 52923.0317,
|
|
"train_tokens_per_second": 758.709
|
|
},
|
|
{
|
|
"epoch": 0.019382835101253618,
|
|
"grad_norm": 11.433195114135742,
|
|
"learning_rate": 0.00019982380898598057,
|
|
"loss": 0.9312161254882813,
|
|
"num_input_tokens_seen": 40202264,
|
|
"step": 20100,
|
|
"train_runtime": 52997.5186,
|
|
"train_tokens_per_second": 758.569
|
|
},
|
|
{
|
|
"epoch": 0.019431051108968176,
|
|
"grad_norm": 8.248124122619629,
|
|
"learning_rate": 0.00019982290861944406,
|
|
"loss": 0.9611305236816406,
|
|
"num_input_tokens_seen": 40244128,
|
|
"step": 20150,
|
|
"train_runtime": 53063.9898,
|
|
"train_tokens_per_second": 758.408
|
|
},
|
|
{
|
|
"epoch": 0.019479267116682738,
|
|
"grad_norm": 7.669606685638428,
|
|
"learning_rate": 0.00019982200596029131,
|
|
"loss": 0.9843034362792968,
|
|
"num_input_tokens_seen": 40290840,
|
|
"step": 20200,
|
|
"train_runtime": 53134.635,
|
|
"train_tokens_per_second": 758.278
|
|
},
|
|
{
|
|
"epoch": 0.0195274831243973,
|
|
"grad_norm": 8.10736083984375,
|
|
"learning_rate": 0.0001998211010085431,
|
|
"loss": 0.9166609191894531,
|
|
"num_input_tokens_seen": 40340080,
|
|
"step": 20250,
|
|
"train_runtime": 53208.8212,
|
|
"train_tokens_per_second": 758.146
|
|
},
|
|
{
|
|
"epoch": 0.01957569913211186,
|
|
"grad_norm": 7.589653968811035,
|
|
"learning_rate": 0.00019982019376422016,
|
|
"loss": 0.9027670288085937,
|
|
"num_input_tokens_seen": 40386936,
|
|
"step": 20300,
|
|
"train_runtime": 53280.092,
|
|
"train_tokens_per_second": 758.012
|
|
},
|
|
{
|
|
"epoch": 0.019623915139826423,
|
|
"grad_norm": 12.363795280456543,
|
|
"learning_rate": 0.00019981928422734338,
|
|
"loss": 0.9284130096435547,
|
|
"num_input_tokens_seen": 40434088,
|
|
"step": 20350,
|
|
"train_runtime": 53350.2539,
|
|
"train_tokens_per_second": 757.899
|
|
},
|
|
{
|
|
"epoch": 0.019672131147540985,
|
|
"grad_norm": 7.132938861846924,
|
|
"learning_rate": 0.0001998183723979336,
|
|
"loss": 0.9204126739501953,
|
|
"num_input_tokens_seen": 40479984,
|
|
"step": 20400,
|
|
"train_runtime": 53420.8347,
|
|
"train_tokens_per_second": 757.756
|
|
},
|
|
{
|
|
"epoch": 0.019720347155255544,
|
|
"grad_norm": 6.81062650680542,
|
|
"learning_rate": 0.00019981745827601179,
|
|
"loss": 0.9094781494140625,
|
|
"num_input_tokens_seen": 40521624,
|
|
"step": 20450,
|
|
"train_runtime": 53487.4147,
|
|
"train_tokens_per_second": 757.592
|
|
},
|
|
{
|
|
"epoch": 0.019768563162970106,
|
|
"grad_norm": 6.6877031326293945,
|
|
"learning_rate": 0.00019981654186159892,
|
|
"loss": 0.8954215240478516,
|
|
"num_input_tokens_seen": 40567448,
|
|
"step": 20500,
|
|
"train_runtime": 53558.361,
|
|
"train_tokens_per_second": 757.444
|
|
},
|
|
{
|
|
"epoch": 0.019816779170684667,
|
|
"grad_norm": 7.634172439575195,
|
|
"learning_rate": 0.00019981562315471608,
|
|
"loss": 0.9335720825195313,
|
|
"num_input_tokens_seen": 40611840,
|
|
"step": 20550,
|
|
"train_runtime": 53627.3143,
|
|
"train_tokens_per_second": 757.298
|
|
},
|
|
{
|
|
"epoch": 0.01986499517839923,
|
|
"grad_norm": 8.012425422668457,
|
|
"learning_rate": 0.00019981470215538435,
|
|
"loss": 0.860129623413086,
|
|
"num_input_tokens_seen": 40659928,
|
|
"step": 20600,
|
|
"train_runtime": 53700.1808,
|
|
"train_tokens_per_second": 757.166
|
|
},
|
|
{
|
|
"epoch": 0.01991321118611379,
|
|
"grad_norm": 7.340192794799805,
|
|
"learning_rate": 0.00019981377886362487,
|
|
"loss": 0.9700403594970703,
|
|
"num_input_tokens_seen": 40711936,
|
|
"step": 20650,
|
|
"train_runtime": 53776.9999,
|
|
"train_tokens_per_second": 757.051
|
|
},
|
|
{
|
|
"epoch": 0.01996142719382835,
|
|
"grad_norm": 7.369932174682617,
|
|
"learning_rate": 0.00019981285327945884,
|
|
"loss": 0.9196085357666015,
|
|
"num_input_tokens_seen": 40757440,
|
|
"step": 20700,
|
|
"train_runtime": 53846.6001,
|
|
"train_tokens_per_second": 756.918
|
|
},
|
|
{
|
|
"epoch": 0.02000964320154291,
|
|
"grad_norm": 10.454463958740234,
|
|
"learning_rate": 0.00019981192540290756,
|
|
"loss": 0.8827559661865234,
|
|
"num_input_tokens_seen": 40803136,
|
|
"step": 20750,
|
|
"train_runtime": 53917.7039,
|
|
"train_tokens_per_second": 756.767
|
|
},
|
|
{
|
|
"epoch": 0.020057859209257473,
|
|
"grad_norm": 7.965270042419434,
|
|
"learning_rate": 0.0001998109952339923,
|
|
"loss": 0.9672048950195312,
|
|
"num_input_tokens_seen": 40847120,
|
|
"step": 20800,
|
|
"train_runtime": 53986.2041,
|
|
"train_tokens_per_second": 756.621
|
|
},
|
|
{
|
|
"epoch": 0.020106075216972035,
|
|
"grad_norm": 6.159726619720459,
|
|
"learning_rate": 0.00019981006277273438,
|
|
"loss": 0.9010369110107422,
|
|
"num_input_tokens_seen": 40891336,
|
|
"step": 20850,
|
|
"train_runtime": 54054.2251,
|
|
"train_tokens_per_second": 756.487
|
|
},
|
|
{
|
|
"epoch": 0.020154291224686597,
|
|
"grad_norm": 5.145337104797363,
|
|
"learning_rate": 0.00019980912801915535,
|
|
"loss": 0.9101256561279297,
|
|
"num_input_tokens_seen": 40941440,
|
|
"step": 20900,
|
|
"train_runtime": 54129.2498,
|
|
"train_tokens_per_second": 756.364
|
|
},
|
|
{
|
|
"epoch": 0.02020250723240116,
|
|
"grad_norm": 7.397220134735107,
|
|
"learning_rate": 0.00019980819097327658,
|
|
"loss": 0.955694808959961,
|
|
"num_input_tokens_seen": 40987704,
|
|
"step": 20950,
|
|
"train_runtime": 54199.9928,
|
|
"train_tokens_per_second": 756.231
|
|
},
|
|
{
|
|
"epoch": 0.020250723240115717,
|
|
"grad_norm": 7.794979095458984,
|
|
"learning_rate": 0.00019980725163511957,
|
|
"loss": 0.829678726196289,
|
|
"num_input_tokens_seen": 41033432,
|
|
"step": 21000,
|
|
"train_runtime": 54270.9857,
|
|
"train_tokens_per_second": 756.084
|
|
},
|
|
{
|
|
"epoch": 0.02029893924783028,
|
|
"grad_norm": 9.436833381652832,
|
|
"learning_rate": 0.00019980631000470592,
|
|
"loss": 1.0207832336425782,
|
|
"num_input_tokens_seen": 41079976,
|
|
"step": 21050,
|
|
"train_runtime": 54342.186,
|
|
"train_tokens_per_second": 755.95
|
|
},
|
|
{
|
|
"epoch": 0.02034715525554484,
|
|
"grad_norm": 5.300249099731445,
|
|
"learning_rate": 0.00019980536608205733,
|
|
"loss": 0.9641885375976562,
|
|
"num_input_tokens_seen": 41122760,
|
|
"step": 21100,
|
|
"train_runtime": 54408.5232,
|
|
"train_tokens_per_second": 755.815
|
|
},
|
|
{
|
|
"epoch": 0.020395371263259403,
|
|
"grad_norm": 7.468312740325928,
|
|
"learning_rate": 0.0001998044198671954,
|
|
"loss": 0.9504216766357422,
|
|
"num_input_tokens_seen": 41168760,
|
|
"step": 21150,
|
|
"train_runtime": 54478.6338,
|
|
"train_tokens_per_second": 755.686
|
|
},
|
|
{
|
|
"epoch": 0.020443587270973965,
|
|
"grad_norm": 5.195828914642334,
|
|
"learning_rate": 0.00019980347136014186,
|
|
"loss": 0.9234676361083984,
|
|
"num_input_tokens_seen": 41216464,
|
|
"step": 21200,
|
|
"train_runtime": 54550.4636,
|
|
"train_tokens_per_second": 755.566
|
|
},
|
|
{
|
|
"epoch": 0.020491803278688523,
|
|
"grad_norm": 9.310417175292969,
|
|
"learning_rate": 0.00019980252056091852,
|
|
"loss": 0.9304835510253906,
|
|
"num_input_tokens_seen": 41261320,
|
|
"step": 21250,
|
|
"train_runtime": 54619.9154,
|
|
"train_tokens_per_second": 755.426
|
|
},
|
|
{
|
|
"epoch": 0.020540019286403085,
|
|
"grad_norm": 7.659024715423584,
|
|
"learning_rate": 0.0001998015674695472,
|
|
"loss": 0.9654434204101563,
|
|
"num_input_tokens_seen": 41309632,
|
|
"step": 21300,
|
|
"train_runtime": 54692.955,
|
|
"train_tokens_per_second": 755.301
|
|
},
|
|
{
|
|
"epoch": 0.020588235294117647,
|
|
"grad_norm": 8.254072189331055,
|
|
"learning_rate": 0.00019980061208604985,
|
|
"loss": 0.946378173828125,
|
|
"num_input_tokens_seen": 41356696,
|
|
"step": 21350,
|
|
"train_runtime": 54764.3925,
|
|
"train_tokens_per_second": 755.175
|
|
},
|
|
{
|
|
"epoch": 0.02063645130183221,
|
|
"grad_norm": 7.080167293548584,
|
|
"learning_rate": 0.0001997996544104483,
|
|
"loss": 0.8566698455810546,
|
|
"num_input_tokens_seen": 41400840,
|
|
"step": 21400,
|
|
"train_runtime": 54833.0723,
|
|
"train_tokens_per_second": 755.034
|
|
},
|
|
{
|
|
"epoch": 0.02068466730954677,
|
|
"grad_norm": 8.228322982788086,
|
|
"learning_rate": 0.00019979869444276463,
|
|
"loss": 0.8824358367919922,
|
|
"num_input_tokens_seen": 41446224,
|
|
"step": 21450,
|
|
"train_runtime": 54903.7543,
|
|
"train_tokens_per_second": 754.889
|
|
},
|
|
{
|
|
"epoch": 0.020732883317261332,
|
|
"grad_norm": 6.597164154052734,
|
|
"learning_rate": 0.00019979773218302085,
|
|
"loss": 0.9035594177246093,
|
|
"num_input_tokens_seen": 41492304,
|
|
"step": 21500,
|
|
"train_runtime": 54975.7758,
|
|
"train_tokens_per_second": 754.738
|
|
},
|
|
{
|
|
"epoch": 0.02078109932497589,
|
|
"grad_norm": 6.127617835998535,
|
|
"learning_rate": 0.00019979676763123911,
|
|
"loss": 0.9752952575683593,
|
|
"num_input_tokens_seen": 41538352,
|
|
"step": 21550,
|
|
"train_runtime": 55046.329,
|
|
"train_tokens_per_second": 754.607
|
|
},
|
|
{
|
|
"epoch": 0.020829315332690453,
|
|
"grad_norm": 6.016520977020264,
|
|
"learning_rate": 0.00019979580078744152,
|
|
"loss": 0.8782232666015625,
|
|
"num_input_tokens_seen": 41584784,
|
|
"step": 21600,
|
|
"train_runtime": 55116.3241,
|
|
"train_tokens_per_second": 754.491
|
|
},
|
|
{
|
|
"epoch": 0.020877531340405014,
|
|
"grad_norm": 5.965268135070801,
|
|
"learning_rate": 0.00019979483165165026,
|
|
"loss": 0.9891378021240235,
|
|
"num_input_tokens_seen": 41633016,
|
|
"step": 21650,
|
|
"train_runtime": 55188.1547,
|
|
"train_tokens_per_second": 754.383
|
|
},
|
|
{
|
|
"epoch": 0.020925747348119576,
|
|
"grad_norm": 8.268887519836426,
|
|
"learning_rate": 0.00019979386022388762,
|
|
"loss": 0.84054931640625,
|
|
"num_input_tokens_seen": 41677224,
|
|
"step": 21700,
|
|
"train_runtime": 55257.2992,
|
|
"train_tokens_per_second": 754.239
|
|
},
|
|
{
|
|
"epoch": 0.020973963355834138,
|
|
"grad_norm": 6.487857818603516,
|
|
"learning_rate": 0.00019979288650417594,
|
|
"loss": 0.955909652709961,
|
|
"num_input_tokens_seen": 41725752,
|
|
"step": 21750,
|
|
"train_runtime": 55331.2588,
|
|
"train_tokens_per_second": 754.108
|
|
},
|
|
{
|
|
"epoch": 0.021022179363548697,
|
|
"grad_norm": 5.285030841827393,
|
|
"learning_rate": 0.00019979191049253756,
|
|
"loss": 0.9848507690429688,
|
|
"num_input_tokens_seen": 41775288,
|
|
"step": 21800,
|
|
"train_runtime": 55405.8774,
|
|
"train_tokens_per_second": 753.987
|
|
},
|
|
{
|
|
"epoch": 0.02107039537126326,
|
|
"grad_norm": 4.6729912757873535,
|
|
"learning_rate": 0.00019979093218899484,
|
|
"loss": 0.8383413696289063,
|
|
"num_input_tokens_seen": 41820184,
|
|
"step": 21850,
|
|
"train_runtime": 55473.7352,
|
|
"train_tokens_per_second": 753.874
|
|
},
|
|
{
|
|
"epoch": 0.02111861137897782,
|
|
"grad_norm": 5.168034553527832,
|
|
"learning_rate": 0.00019978995159357035,
|
|
"loss": 0.9230535888671875,
|
|
"num_input_tokens_seen": 41866696,
|
|
"step": 21900,
|
|
"train_runtime": 55544.5541,
|
|
"train_tokens_per_second": 753.75
|
|
},
|
|
{
|
|
"epoch": 0.021166827386692382,
|
|
"grad_norm": 8.513957977294922,
|
|
"learning_rate": 0.00019978896870628655,
|
|
"loss": 0.8888040161132813,
|
|
"num_input_tokens_seen": 41912920,
|
|
"step": 21950,
|
|
"train_runtime": 55614.7621,
|
|
"train_tokens_per_second": 753.629
|
|
},
|
|
{
|
|
"epoch": 0.021215043394406944,
|
|
"grad_norm": 8.520140647888184,
|
|
"learning_rate": 0.000199787983527166,
|
|
"loss": 0.8958989715576172,
|
|
"num_input_tokens_seen": 41958584,
|
|
"step": 22000,
|
|
"train_runtime": 55684.523,
|
|
"train_tokens_per_second": 753.505
|
|
},
|
|
{
|
|
"epoch": 0.021263259402121506,
|
|
"grad_norm": 6.832187175750732,
|
|
"learning_rate": 0.00019978699605623137,
|
|
"loss": 0.927935791015625,
|
|
"num_input_tokens_seen": 42004664,
|
|
"step": 22050,
|
|
"train_runtime": 55756.2893,
|
|
"train_tokens_per_second": 753.362
|
|
},
|
|
{
|
|
"epoch": 0.021311475409836064,
|
|
"grad_norm": 8.617132186889648,
|
|
"learning_rate": 0.0001997860062935053,
|
|
"loss": 0.9121678161621094,
|
|
"num_input_tokens_seen": 42051072,
|
|
"step": 22100,
|
|
"train_runtime": 55826.9734,
|
|
"train_tokens_per_second": 753.239
|
|
},
|
|
{
|
|
"epoch": 0.021359691417550626,
|
|
"grad_norm": 7.349531173706055,
|
|
"learning_rate": 0.00019978501423901056,
|
|
"loss": 0.9384589385986328,
|
|
"num_input_tokens_seen": 42095952,
|
|
"step": 22150,
|
|
"train_runtime": 55897.4308,
|
|
"train_tokens_per_second": 753.093
|
|
},
|
|
{
|
|
"epoch": 0.021407907425265188,
|
|
"grad_norm": 11.886220932006836,
|
|
"learning_rate": 0.0001997840198927699,
|
|
"loss": 0.8639747619628906,
|
|
"num_input_tokens_seen": 42140984,
|
|
"step": 22200,
|
|
"train_runtime": 55967.5748,
|
|
"train_tokens_per_second": 752.954
|
|
},
|
|
{
|
|
"epoch": 0.02145612343297975,
|
|
"grad_norm": 6.694061279296875,
|
|
"learning_rate": 0.00019978302325480618,
|
|
"loss": 0.9002442932128907,
|
|
"num_input_tokens_seen": 42189440,
|
|
"step": 22250,
|
|
"train_runtime": 56041.4367,
|
|
"train_tokens_per_second": 752.826
|
|
},
|
|
{
|
|
"epoch": 0.02150433944069431,
|
|
"grad_norm": 8.591554641723633,
|
|
"learning_rate": 0.00019978202432514232,
|
|
"loss": 0.8749357604980469,
|
|
"num_input_tokens_seen": 42237944,
|
|
"step": 22300,
|
|
"train_runtime": 56115.9502,
|
|
"train_tokens_per_second": 752.691
|
|
},
|
|
{
|
|
"epoch": 0.02155255544840887,
|
|
"grad_norm": 7.658833980560303,
|
|
"learning_rate": 0.00019978102310380116,
|
|
"loss": 0.8694376373291015,
|
|
"num_input_tokens_seen": 42284560,
|
|
"step": 22350,
|
|
"train_runtime": 56188.1941,
|
|
"train_tokens_per_second": 752.552
|
|
},
|
|
{
|
|
"epoch": 0.021600771456123432,
|
|
"grad_norm": 6.718590259552002,
|
|
"learning_rate": 0.00019978001959080577,
|
|
"loss": 0.8602400970458984,
|
|
"num_input_tokens_seen": 42326808,
|
|
"step": 22400,
|
|
"train_runtime": 56254.7374,
|
|
"train_tokens_per_second": 752.413
|
|
},
|
|
{
|
|
"epoch": 0.021648987463837994,
|
|
"grad_norm": 7.094481945037842,
|
|
"learning_rate": 0.0001997790137861792,
|
|
"loss": 0.9230850982666016,
|
|
"num_input_tokens_seen": 42375328,
|
|
"step": 22450,
|
|
"train_runtime": 56327.643,
|
|
"train_tokens_per_second": 752.301
|
|
},
|
|
{
|
|
"epoch": 0.021697203471552556,
|
|
"grad_norm": 4.90302848815918,
|
|
"learning_rate": 0.00019977800568994454,
|
|
"loss": 0.9822250366210937,
|
|
"num_input_tokens_seen": 42425176,
|
|
"step": 22500,
|
|
"train_runtime": 56402.7547,
|
|
"train_tokens_per_second": 752.183
|
|
},
|
|
{
|
|
"epoch": 0.021745419479267118,
|
|
"grad_norm": 9.070446014404297,
|
|
"learning_rate": 0.00019977699530212496,
|
|
"loss": 0.8875312805175781,
|
|
"num_input_tokens_seen": 42471320,
|
|
"step": 22550,
|
|
"train_runtime": 56472.7821,
|
|
"train_tokens_per_second": 752.067
|
|
},
|
|
{
|
|
"epoch": 0.02179363548698168,
|
|
"grad_norm": 7.69023323059082,
|
|
"learning_rate": 0.0001997759826227436,
|
|
"loss": 0.8835562133789062,
|
|
"num_input_tokens_seen": 42517616,
|
|
"step": 22600,
|
|
"train_runtime": 56543.2952,
|
|
"train_tokens_per_second": 751.948
|
|
},
|
|
{
|
|
"epoch": 0.021841851494696238,
|
|
"grad_norm": 6.927340984344482,
|
|
"learning_rate": 0.0001997749676518238,
|
|
"loss": 0.8482952117919922,
|
|
"num_input_tokens_seen": 42563760,
|
|
"step": 22650,
|
|
"train_runtime": 56613.2875,
|
|
"train_tokens_per_second": 751.833
|
|
},
|
|
{
|
|
"epoch": 0.0218900675024108,
|
|
"grad_norm": 7.275538921356201,
|
|
"learning_rate": 0.0001997739503893888,
|
|
"loss": 0.8850119018554687,
|
|
"num_input_tokens_seen": 42608192,
|
|
"step": 22700,
|
|
"train_runtime": 56681.5316,
|
|
"train_tokens_per_second": 751.712
|
|
},
|
|
{
|
|
"epoch": 0.02193828351012536,
|
|
"grad_norm": 7.42587947845459,
|
|
"learning_rate": 0.000199772930835462,
|
|
"loss": 0.9159330749511718,
|
|
"num_input_tokens_seen": 42655312,
|
|
"step": 22750,
|
|
"train_runtime": 56753.0927,
|
|
"train_tokens_per_second": 751.594
|
|
},
|
|
{
|
|
"epoch": 0.021986499517839923,
|
|
"grad_norm": 5.789289951324463,
|
|
"learning_rate": 0.00019977190899006685,
|
|
"loss": 0.871900405883789,
|
|
"num_input_tokens_seen": 42700280,
|
|
"step": 22800,
|
|
"train_runtime": 56821.5674,
|
|
"train_tokens_per_second": 751.48
|
|
},
|
|
{
|
|
"epoch": 0.022034715525554485,
|
|
"grad_norm": 7.885580062866211,
|
|
"learning_rate": 0.00019977088485322673,
|
|
"loss": 0.9240410614013672,
|
|
"num_input_tokens_seen": 42746976,
|
|
"step": 22850,
|
|
"train_runtime": 56892.5642,
|
|
"train_tokens_per_second": 751.363
|
|
},
|
|
{
|
|
"epoch": 0.022082931533269044,
|
|
"grad_norm": 5.821876525878906,
|
|
"learning_rate": 0.00019976985842496526,
|
|
"loss": 0.8724329376220703,
|
|
"num_input_tokens_seen": 42794696,
|
|
"step": 22900,
|
|
"train_runtime": 56963.7933,
|
|
"train_tokens_per_second": 751.261
|
|
},
|
|
{
|
|
"epoch": 0.022131147540983605,
|
|
"grad_norm": 7.791795253753662,
|
|
"learning_rate": 0.00019976882970530594,
|
|
"loss": 0.9541690826416016,
|
|
"num_input_tokens_seen": 42839904,
|
|
"step": 22950,
|
|
"train_runtime": 57034.1661,
|
|
"train_tokens_per_second": 751.127
|
|
},
|
|
{
|
|
"epoch": 0.022179363548698167,
|
|
"grad_norm": 9.200284004211426,
|
|
"learning_rate": 0.00019976779869427245,
|
|
"loss": 0.9156061553955078,
|
|
"num_input_tokens_seen": 42884664,
|
|
"step": 23000,
|
|
"train_runtime": 57104.3109,
|
|
"train_tokens_per_second": 750.988
|
|
},
|
|
{
|
|
"epoch": 0.02222757955641273,
|
|
"grad_norm": 7.05883264541626,
|
|
"learning_rate": 0.00019976676539188842,
|
|
"loss": 0.8539710235595703,
|
|
"num_input_tokens_seen": 42929192,
|
|
"step": 23050,
|
|
"train_runtime": 57172.4829,
|
|
"train_tokens_per_second": 750.872
|
|
},
|
|
{
|
|
"epoch": 0.02227579556412729,
|
|
"grad_norm": 7.184851169586182,
|
|
"learning_rate": 0.00019976572979817761,
|
|
"loss": 0.9217386627197266,
|
|
"num_input_tokens_seen": 42976504,
|
|
"step": 23100,
|
|
"train_runtime": 57243.345,
|
|
"train_tokens_per_second": 750.769
|
|
},
|
|
{
|
|
"epoch": 0.022324011571841853,
|
|
"grad_norm": 8.311331748962402,
|
|
"learning_rate": 0.00019976469191316376,
|
|
"loss": 0.8745499420166015,
|
|
"num_input_tokens_seen": 43021352,
|
|
"step": 23150,
|
|
"train_runtime": 57312.7029,
|
|
"train_tokens_per_second": 750.643
|
|
},
|
|
{
|
|
"epoch": 0.02237222757955641,
|
|
"grad_norm": 7.188688278198242,
|
|
"learning_rate": 0.0001997636517368708,
|
|
"loss": 0.9411102294921875,
|
|
"num_input_tokens_seen": 43066120,
|
|
"step": 23200,
|
|
"train_runtime": 57381.5887,
|
|
"train_tokens_per_second": 750.522
|
|
},
|
|
{
|
|
"epoch": 0.022420443587270973,
|
|
"grad_norm": 6.492039203643799,
|
|
"learning_rate": 0.00019976260926932252,
|
|
"loss": 0.8856814575195312,
|
|
"num_input_tokens_seen": 43112640,
|
|
"step": 23250,
|
|
"train_runtime": 57452.5706,
|
|
"train_tokens_per_second": 750.404
|
|
},
|
|
{
|
|
"epoch": 0.022468659594985535,
|
|
"grad_norm": 6.549287796020508,
|
|
"learning_rate": 0.00019976156451054293,
|
|
"loss": 0.9326125335693359,
|
|
"num_input_tokens_seen": 43158072,
|
|
"step": 23300,
|
|
"train_runtime": 57522.1043,
|
|
"train_tokens_per_second": 750.287
|
|
},
|
|
{
|
|
"epoch": 0.022516875602700097,
|
|
"grad_norm": 8.599569320678711,
|
|
"learning_rate": 0.00019976051746055598,
|
|
"loss": 0.9474910736083985,
|
|
"num_input_tokens_seen": 43200576,
|
|
"step": 23350,
|
|
"train_runtime": 57588.9743,
|
|
"train_tokens_per_second": 750.154
|
|
},
|
|
{
|
|
"epoch": 0.02256509161041466,
|
|
"grad_norm": 6.261628150939941,
|
|
"learning_rate": 0.00019975946811938577,
|
|
"loss": 0.8017835235595703,
|
|
"num_input_tokens_seen": 43244728,
|
|
"step": 23400,
|
|
"train_runtime": 57657.0079,
|
|
"train_tokens_per_second": 750.034
|
|
},
|
|
{
|
|
"epoch": 0.02261330761812922,
|
|
"grad_norm": 9.320496559143066,
|
|
"learning_rate": 0.00019975841648705634,
|
|
"loss": 0.9458789825439453,
|
|
"num_input_tokens_seen": 43289152,
|
|
"step": 23450,
|
|
"train_runtime": 57725.5394,
|
|
"train_tokens_per_second": 749.913
|
|
},
|
|
{
|
|
"epoch": 0.02266152362584378,
|
|
"grad_norm": 7.9135870933532715,
|
|
"learning_rate": 0.0001997573625635919,
|
|
"loss": 0.859818115234375,
|
|
"num_input_tokens_seen": 43336144,
|
|
"step": 23500,
|
|
"train_runtime": 57797.2645,
|
|
"train_tokens_per_second": 749.796
|
|
},
|
|
{
|
|
"epoch": 0.02270973963355834,
|
|
"grad_norm": 7.348023414611816,
|
|
"learning_rate": 0.00019975632749576086,
|
|
"loss": 0.9983107757568359,
|
|
"num_input_tokens_seen": 43387440,
|
|
"step": 23550,
|
|
"train_runtime": 57873.7602,
|
|
"train_tokens_per_second": 749.691
|
|
},
|
|
{
|
|
"epoch": 0.022757955641272903,
|
|
"grad_norm": 7.690008640289307,
|
|
"learning_rate": 0.00019975526903592047,
|
|
"loss": 0.9337245178222656,
|
|
"num_input_tokens_seen": 43432744,
|
|
"step": 23600,
|
|
"train_runtime": 57943.2612,
|
|
"train_tokens_per_second": 749.574
|
|
},
|
|
{
|
|
"epoch": 0.022806171648987465,
|
|
"grad_norm": 7.901937007904053,
|
|
"learning_rate": 0.00019975420828501737,
|
|
"loss": 0.9053121948242188,
|
|
"num_input_tokens_seen": 43479648,
|
|
"step": 23650,
|
|
"train_runtime": 58014.4301,
|
|
"train_tokens_per_second": 749.463
|
|
},
|
|
{
|
|
"epoch": 0.022854387656702026,
|
|
"grad_norm": 6.3564348220825195,
|
|
"learning_rate": 0.00019975314524307584,
|
|
"loss": 0.9143846893310547,
|
|
"num_input_tokens_seen": 43523280,
|
|
"step": 23700,
|
|
"train_runtime": 58082.9249,
|
|
"train_tokens_per_second": 749.33
|
|
},
|
|
{
|
|
"epoch": 0.022902603664416585,
|
|
"grad_norm": 6.551039218902588,
|
|
"learning_rate": 0.00019975207991012036,
|
|
"loss": 0.8526578521728516,
|
|
"num_input_tokens_seen": 43570072,
|
|
"step": 23750,
|
|
"train_runtime": 58154.2327,
|
|
"train_tokens_per_second": 749.216
|
|
},
|
|
{
|
|
"epoch": 0.022950819672131147,
|
|
"grad_norm": 8.326873779296875,
|
|
"learning_rate": 0.00019975101228617538,
|
|
"loss": 0.8984385681152344,
|
|
"num_input_tokens_seen": 43616040,
|
|
"step": 23800,
|
|
"train_runtime": 58224.4813,
|
|
"train_tokens_per_second": 749.101
|
|
},
|
|
{
|
|
"epoch": 0.02299903567984571,
|
|
"grad_norm": 10.732083320617676,
|
|
"learning_rate": 0.00019974994237126537,
|
|
"loss": 0.8916858673095703,
|
|
"num_input_tokens_seen": 43664296,
|
|
"step": 23850,
|
|
"train_runtime": 58297.0475,
|
|
"train_tokens_per_second": 748.997
|
|
},
|
|
{
|
|
"epoch": 0.02304725168756027,
|
|
"grad_norm": 4.699100017547607,
|
|
"learning_rate": 0.00019974887016541498,
|
|
"loss": 0.934093017578125,
|
|
"num_input_tokens_seen": 43709872,
|
|
"step": 23900,
|
|
"train_runtime": 58367.4935,
|
|
"train_tokens_per_second": 748.874
|
|
},
|
|
{
|
|
"epoch": 0.023095467695274832,
|
|
"grad_norm": 7.831923484802246,
|
|
"learning_rate": 0.0001997477956686488,
|
|
"loss": 0.8769267272949218,
|
|
"num_input_tokens_seen": 43755776,
|
|
"step": 23950,
|
|
"train_runtime": 58437.4262,
|
|
"train_tokens_per_second": 748.763
|
|
},
|
|
{
|
|
"epoch": 0.023143683702989394,
|
|
"grad_norm": 9.95285415649414,
|
|
"learning_rate": 0.00019974671888099149,
|
|
"loss": 0.827588882446289,
|
|
"num_input_tokens_seen": 43798520,
|
|
"step": 24000,
|
|
"train_runtime": 58505.1482,
|
|
"train_tokens_per_second": 748.627
|
|
},
|
|
{
|
|
"epoch": 0.023191899710703952,
|
|
"grad_norm": 11.578145980834961,
|
|
"learning_rate": 0.00019974563980246782,
|
|
"loss": 0.9358421325683594,
|
|
"num_input_tokens_seen": 43842984,
|
|
"step": 24050,
|
|
"train_runtime": 58573.6577,
|
|
"train_tokens_per_second": 748.51
|
|
},
|
|
{
|
|
"epoch": 0.023240115718418514,
|
|
"grad_norm": 4.729525089263916,
|
|
"learning_rate": 0.00019974455843310254,
|
|
"loss": 0.8868643951416015,
|
|
"num_input_tokens_seen": 43889064,
|
|
"step": 24100,
|
|
"train_runtime": 58643.288,
|
|
"train_tokens_per_second": 748.407
|
|
},
|
|
{
|
|
"epoch": 0.023288331726133076,
|
|
"grad_norm": 6.302151203155518,
|
|
"learning_rate": 0.00019974347477292047,
|
|
"loss": 0.8685957336425781,
|
|
"num_input_tokens_seen": 43934208,
|
|
"step": 24150,
|
|
"train_runtime": 58712.3018,
|
|
"train_tokens_per_second": 748.296
|
|
},
|
|
{
|
|
"epoch": 0.023336547733847638,
|
|
"grad_norm": 6.503923416137695,
|
|
"learning_rate": 0.00019974238882194655,
|
|
"loss": 0.9510240173339843,
|
|
"num_input_tokens_seen": 43982312,
|
|
"step": 24200,
|
|
"train_runtime": 58784.4366,
|
|
"train_tokens_per_second": 748.197
|
|
},
|
|
{
|
|
"epoch": 0.0233847637415622,
|
|
"grad_norm": 5.180490970611572,
|
|
"learning_rate": 0.00019974130058020572,
|
|
"loss": 0.8974213409423828,
|
|
"num_input_tokens_seen": 44025248,
|
|
"step": 24250,
|
|
"train_runtime": 58851.5624,
|
|
"train_tokens_per_second": 748.073
|
|
},
|
|
{
|
|
"epoch": 0.02343297974927676,
|
|
"grad_norm": 6.354820251464844,
|
|
"learning_rate": 0.00019974021004772293,
|
|
"loss": 0.9206002044677735,
|
|
"num_input_tokens_seen": 44073152,
|
|
"step": 24300,
|
|
"train_runtime": 58923.6178,
|
|
"train_tokens_per_second": 747.971
|
|
},
|
|
{
|
|
"epoch": 0.02348119575699132,
|
|
"grad_norm": 7.401444911956787,
|
|
"learning_rate": 0.00019973911722452324,
|
|
"loss": 0.9140322113037109,
|
|
"num_input_tokens_seen": 44116656,
|
|
"step": 24350,
|
|
"train_runtime": 58991.9641,
|
|
"train_tokens_per_second": 747.842
|
|
},
|
|
{
|
|
"epoch": 0.023529411764705882,
|
|
"grad_norm": 9.079787254333496,
|
|
"learning_rate": 0.00019973802211063174,
|
|
"loss": 0.8935973358154297,
|
|
"num_input_tokens_seen": 44161744,
|
|
"step": 24400,
|
|
"train_runtime": 59061.3185,
|
|
"train_tokens_per_second": 747.727
|
|
},
|
|
{
|
|
"epoch": 0.023577627772420444,
|
|
"grad_norm": 9.17170238494873,
|
|
"learning_rate": 0.00019973692470607362,
|
|
"loss": 0.8662525177001953,
|
|
"num_input_tokens_seen": 44204392,
|
|
"step": 24450,
|
|
"train_runtime": 59128.0082,
|
|
"train_tokens_per_second": 747.605
|
|
},
|
|
{
|
|
"epoch": 0.023625843780135006,
|
|
"grad_norm": 6.207198619842529,
|
|
"learning_rate": 0.00019973582501087405,
|
|
"loss": 0.9472468566894531,
|
|
"num_input_tokens_seen": 44247336,
|
|
"step": 24500,
|
|
"train_runtime": 59195.2969,
|
|
"train_tokens_per_second": 747.481
|
|
},
|
|
{
|
|
"epoch": 0.023674059787849568,
|
|
"grad_norm": 6.4733428955078125,
|
|
"learning_rate": 0.00019973472302505828,
|
|
"loss": 1.0022035217285157,
|
|
"num_input_tokens_seen": 44290184,
|
|
"step": 24550,
|
|
"train_runtime": 59261.9248,
|
|
"train_tokens_per_second": 747.363
|
|
},
|
|
{
|
|
"epoch": 0.023722275795564126,
|
|
"grad_norm": 5.754579067230225,
|
|
"learning_rate": 0.00019973361874865166,
|
|
"loss": 0.936693344116211,
|
|
"num_input_tokens_seen": 44336488,
|
|
"step": 24600,
|
|
"train_runtime": 59332.2947,
|
|
"train_tokens_per_second": 747.257
|
|
},
|
|
{
|
|
"epoch": 0.023770491803278688,
|
|
"grad_norm": 6.263538360595703,
|
|
"learning_rate": 0.00019973251218167952,
|
|
"loss": 0.9308546447753906,
|
|
"num_input_tokens_seen": 44383048,
|
|
"step": 24650,
|
|
"train_runtime": 59402.8457,
|
|
"train_tokens_per_second": 747.154
|
|
},
|
|
{
|
|
"epoch": 0.02381870781099325,
|
|
"grad_norm": 6.708986759185791,
|
|
"learning_rate": 0.00019973140332416728,
|
|
"loss": 0.8487769317626953,
|
|
"num_input_tokens_seen": 44431280,
|
|
"step": 24700,
|
|
"train_runtime": 59473.6149,
|
|
"train_tokens_per_second": 747.075
|
|
},
|
|
{
|
|
"epoch": 0.02386692381870781,
|
|
"grad_norm": 7.347559452056885,
|
|
"learning_rate": 0.00019973029217614042,
|
|
"loss": 0.9504742431640625,
|
|
"num_input_tokens_seen": 44477144,
|
|
"step": 24750,
|
|
"train_runtime": 59544.2567,
|
|
"train_tokens_per_second": 746.959
|
|
},
|
|
{
|
|
"epoch": 0.023915139826422373,
|
|
"grad_norm": 7.059614658355713,
|
|
"learning_rate": 0.00019972917873762442,
|
|
"loss": 0.8397139739990235,
|
|
"num_input_tokens_seen": 44524272,
|
|
"step": 24800,
|
|
"train_runtime": 59614.5255,
|
|
"train_tokens_per_second": 746.87
|
|
},
|
|
{
|
|
"epoch": 0.023963355834136932,
|
|
"grad_norm": 7.994228839874268,
|
|
"learning_rate": 0.0001997280630086449,
|
|
"loss": 0.8961300659179687,
|
|
"num_input_tokens_seen": 44569384,
|
|
"step": 24850,
|
|
"train_runtime": 59684.2766,
|
|
"train_tokens_per_second": 746.753
|
|
},
|
|
{
|
|
"epoch": 0.024011571841851494,
|
|
"grad_norm": 6.456995010375977,
|
|
"learning_rate": 0.00019972694498922747,
|
|
"loss": 0.9056488037109375,
|
|
"num_input_tokens_seen": 44613880,
|
|
"step": 24900,
|
|
"train_runtime": 59752.8239,
|
|
"train_tokens_per_second": 746.641
|
|
},
|
|
{
|
|
"epoch": 0.024059787849566056,
|
|
"grad_norm": 5.2822394371032715,
|
|
"learning_rate": 0.00019972582467939779,
|
|
"loss": 0.8734119415283204,
|
|
"num_input_tokens_seen": 44656896,
|
|
"step": 24950,
|
|
"train_runtime": 59819.7291,
|
|
"train_tokens_per_second": 746.525
|
|
},
|
|
{
|
|
"epoch": 0.024108003857280617,
|
|
"grad_norm": 6.367427825927734,
|
|
"learning_rate": 0.0001997247020791816,
|
|
"loss": 0.8544916534423828,
|
|
"num_input_tokens_seen": 44700712,
|
|
"step": 25000,
|
|
"train_runtime": 59887.1668,
|
|
"train_tokens_per_second": 746.416
|
|
},
|
|
{
|
|
"epoch": 0.02415621986499518,
|
|
"grad_norm": 9.466979026794434,
|
|
"learning_rate": 0.00019972357718860465,
|
|
"loss": 0.9411143493652344,
|
|
"num_input_tokens_seen": 44747040,
|
|
"step": 25050,
|
|
"train_runtime": 59957.8149,
|
|
"train_tokens_per_second": 746.309
|
|
},
|
|
{
|
|
"epoch": 0.02420443587270974,
|
|
"grad_norm": 7.906940460205078,
|
|
"learning_rate": 0.00019972245000769286,
|
|
"loss": 0.915389404296875,
|
|
"num_input_tokens_seen": 44793080,
|
|
"step": 25100,
|
|
"train_runtime": 60029.2044,
|
|
"train_tokens_per_second": 746.188
|
|
},
|
|
{
|
|
"epoch": 0.0242526518804243,
|
|
"grad_norm": 5.646145343780518,
|
|
"learning_rate": 0.00019972132053647207,
|
|
"loss": 0.9646265411376953,
|
|
"num_input_tokens_seen": 44837944,
|
|
"step": 25150,
|
|
"train_runtime": 60098.5848,
|
|
"train_tokens_per_second": 746.073
|
|
},
|
|
{
|
|
"epoch": 0.02430086788813886,
|
|
"grad_norm": 7.968454837799072,
|
|
"learning_rate": 0.0001997201887749682,
|
|
"loss": 0.9028688049316407,
|
|
"num_input_tokens_seen": 44883200,
|
|
"step": 25200,
|
|
"train_runtime": 60168.0258,
|
|
"train_tokens_per_second": 745.964
|
|
},
|
|
{
|
|
"epoch": 0.024349083895853423,
|
|
"grad_norm": 10.929859161376953,
|
|
"learning_rate": 0.00019971905472320728,
|
|
"loss": 0.8840025329589843,
|
|
"num_input_tokens_seen": 44928432,
|
|
"step": 25250,
|
|
"train_runtime": 60238.1465,
|
|
"train_tokens_per_second": 745.847
|
|
},
|
|
{
|
|
"epoch": 0.024397299903567985,
|
|
"grad_norm": 7.4895548820495605,
|
|
"learning_rate": 0.00019971791838121529,
|
|
"loss": 1.0117425537109375,
|
|
"num_input_tokens_seen": 44972048,
|
|
"step": 25300,
|
|
"train_runtime": 60305.8498,
|
|
"train_tokens_per_second": 745.733
|
|
},
|
|
{
|
|
"epoch": 0.024445515911282547,
|
|
"grad_norm": 9.662385940551758,
|
|
"learning_rate": 0.0001997167797490184,
|
|
"loss": 0.8374342346191406,
|
|
"num_input_tokens_seen": 45013752,
|
|
"step": 25350,
|
|
"train_runtime": 60371.439,
|
|
"train_tokens_per_second": 745.613
|
|
},
|
|
{
|
|
"epoch": 0.024493731918997105,
|
|
"grad_norm": 7.930041790008545,
|
|
"learning_rate": 0.00019971563882664276,
|
|
"loss": 0.9937860870361328,
|
|
"num_input_tokens_seen": 45060616,
|
|
"step": 25400,
|
|
"train_runtime": 60442.4169,
|
|
"train_tokens_per_second": 745.513
|
|
},
|
|
{
|
|
"epoch": 0.024541947926711667,
|
|
"grad_norm": 8.349189758300781,
|
|
"learning_rate": 0.0001997144956141145,
|
|
"loss": 0.9225363922119141,
|
|
"num_input_tokens_seen": 45105104,
|
|
"step": 25450,
|
|
"train_runtime": 60510.9851,
|
|
"train_tokens_per_second": 745.404
|
|
},
|
|
{
|
|
"epoch": 0.02459016393442623,
|
|
"grad_norm": 6.440289497375488,
|
|
"learning_rate": 0.00019971335011145997,
|
|
"loss": 0.8778396606445312,
|
|
"num_input_tokens_seen": 45148624,
|
|
"step": 25500,
|
|
"train_runtime": 60579.105,
|
|
"train_tokens_per_second": 745.284
|
|
},
|
|
{
|
|
"epoch": 0.02463837994214079,
|
|
"grad_norm": 8.332621574401855,
|
|
"learning_rate": 0.0001997122023187054,
|
|
"loss": 0.8841622924804687,
|
|
"num_input_tokens_seen": 45190808,
|
|
"step": 25550,
|
|
"train_runtime": 60645.7017,
|
|
"train_tokens_per_second": 745.161
|
|
},
|
|
{
|
|
"epoch": 0.024686595949855353,
|
|
"grad_norm": 8.78128719329834,
|
|
"learning_rate": 0.0001997110522358772,
|
|
"loss": 0.8782478332519531,
|
|
"num_input_tokens_seen": 45232232,
|
|
"step": 25600,
|
|
"train_runtime": 60711.1156,
|
|
"train_tokens_per_second": 745.04
|
|
},
|
|
{
|
|
"epoch": 0.024734811957569915,
|
|
"grad_norm": 6.348476886749268,
|
|
"learning_rate": 0.00019970992293290158,
|
|
"loss": 0.8897344207763672,
|
|
"num_input_tokens_seen": 45275440,
|
|
"step": 25650,
|
|
"train_runtime": 60778.1337,
|
|
"train_tokens_per_second": 744.93
|
|
},
|
|
{
|
|
"epoch": 0.024783027965284473,
|
|
"grad_norm": 11.39626407623291,
|
|
"learning_rate": 0.00019970876831580553,
|
|
"loss": 0.9116340637207031,
|
|
"num_input_tokens_seen": 45323040,
|
|
"step": 25700,
|
|
"train_runtime": 60849.8355,
|
|
"train_tokens_per_second": 744.834
|
|
},
|
|
{
|
|
"epoch": 0.024831243972999035,
|
|
"grad_norm": 7.323637008666992,
|
|
"learning_rate": 0.00019970761140871473,
|
|
"loss": 0.9201824188232421,
|
|
"num_input_tokens_seen": 45368232,
|
|
"step": 25750,
|
|
"train_runtime": 60918.6677,
|
|
"train_tokens_per_second": 744.734
|
|
},
|
|
{
|
|
"epoch": 0.024879459980713597,
|
|
"grad_norm": 8.688375473022461,
|
|
"learning_rate": 0.0001997064522116557,
|
|
"loss": 0.8604035186767578,
|
|
"num_input_tokens_seen": 45414472,
|
|
"step": 25800,
|
|
"train_runtime": 60988.9575,
|
|
"train_tokens_per_second": 744.634
|
|
},
|
|
{
|
|
"epoch": 0.02492767598842816,
|
|
"grad_norm": 6.65385103225708,
|
|
"learning_rate": 0.0001997052907246551,
|
|
"loss": 0.8989216613769532,
|
|
"num_input_tokens_seen": 45460064,
|
|
"step": 25850,
|
|
"train_runtime": 61058.7581,
|
|
"train_tokens_per_second": 744.53
|
|
},
|
|
{
|
|
"epoch": 0.02497589199614272,
|
|
"grad_norm": 6.864791393280029,
|
|
"learning_rate": 0.00019970412694773958,
|
|
"loss": 0.8454482269287109,
|
|
"num_input_tokens_seen": 45504144,
|
|
"step": 25900,
|
|
"train_runtime": 61126.3844,
|
|
"train_tokens_per_second": 744.427
|
|
},
|
|
{
|
|
"epoch": 0.025024108003857282,
|
|
"grad_norm": 9.69471263885498,
|
|
"learning_rate": 0.00019970296088093586,
|
|
"loss": 0.9220399475097656,
|
|
"num_input_tokens_seen": 45547752,
|
|
"step": 25950,
|
|
"train_runtime": 61194.097,
|
|
"train_tokens_per_second": 744.316
|
|
},
|
|
{
|
|
"epoch": 0.02507232401157184,
|
|
"grad_norm": 6.583077430725098,
|
|
"learning_rate": 0.00019970179252427078,
|
|
"loss": 0.8731085205078125,
|
|
"num_input_tokens_seen": 45592280,
|
|
"step": 26000,
|
|
"train_runtime": 61262.8929,
|
|
"train_tokens_per_second": 744.207
|
|
},
|
|
{
|
|
"epoch": 0.025120540019286403,
|
|
"grad_norm": 8.27088451385498,
|
|
"learning_rate": 0.0001997006218777711,
|
|
"loss": 0.8836900329589844,
|
|
"num_input_tokens_seen": 45633744,
|
|
"step": 26050,
|
|
"train_runtime": 61328.9167,
|
|
"train_tokens_per_second": 744.082
|
|
},
|
|
{
|
|
"epoch": 0.025168756027000964,
|
|
"grad_norm": 9.209531784057617,
|
|
"learning_rate": 0.00019969944894146377,
|
|
"loss": 0.8766096496582031,
|
|
"num_input_tokens_seen": 45676288,
|
|
"step": 26100,
|
|
"train_runtime": 61395.5712,
|
|
"train_tokens_per_second": 743.967
|
|
},
|
|
{
|
|
"epoch": 0.025216972034715526,
|
|
"grad_norm": 9.655044555664062,
|
|
"learning_rate": 0.0001996982737153757,
|
|
"loss": 0.8707710266113281,
|
|
"num_input_tokens_seen": 45718656,
|
|
"step": 26150,
|
|
"train_runtime": 61461.9686,
|
|
"train_tokens_per_second": 743.853
|
|
},
|
|
{
|
|
"epoch": 0.025265188042430088,
|
|
"grad_norm": 6.186187744140625,
|
|
"learning_rate": 0.00019969709619953384,
|
|
"loss": 0.8611100006103516,
|
|
"num_input_tokens_seen": 45763872,
|
|
"step": 26200,
|
|
"train_runtime": 61530.4326,
|
|
"train_tokens_per_second": 743.76
|
|
},
|
|
{
|
|
"epoch": 0.025313404050144647,
|
|
"grad_norm": 7.271822452545166,
|
|
"learning_rate": 0.0001996959163939653,
|
|
"loss": 0.8284069061279297,
|
|
"num_input_tokens_seen": 45809408,
|
|
"step": 26250,
|
|
"train_runtime": 61599.6044,
|
|
"train_tokens_per_second": 743.664
|
|
},
|
|
{
|
|
"epoch": 0.02536162005785921,
|
|
"grad_norm": 7.794938087463379,
|
|
"learning_rate": 0.00019969473429869714,
|
|
"loss": 0.8810490417480469,
|
|
"num_input_tokens_seen": 45853592,
|
|
"step": 26300,
|
|
"train_runtime": 61667.471,
|
|
"train_tokens_per_second": 743.562
|
|
},
|
|
{
|
|
"epoch": 0.02540983606557377,
|
|
"grad_norm": 5.849556922912598,
|
|
"learning_rate": 0.00019969354991375654,
|
|
"loss": 0.9096784210205078,
|
|
"num_input_tokens_seen": 45897920,
|
|
"step": 26350,
|
|
"train_runtime": 61736.1982,
|
|
"train_tokens_per_second": 743.452
|
|
},
|
|
{
|
|
"epoch": 0.025458052073288332,
|
|
"grad_norm": 7.43138313293457,
|
|
"learning_rate": 0.00019969236323917066,
|
|
"loss": 0.9812101745605468,
|
|
"num_input_tokens_seen": 45939320,
|
|
"step": 26400,
|
|
"train_runtime": 61801.8694,
|
|
"train_tokens_per_second": 743.332
|
|
},
|
|
{
|
|
"epoch": 0.025506268081002894,
|
|
"grad_norm": 10.801729202270508,
|
|
"learning_rate": 0.0001996911742749668,
|
|
"loss": 0.9410696411132813,
|
|
"num_input_tokens_seen": 45981424,
|
|
"step": 26450,
|
|
"train_runtime": 61867.826,
|
|
"train_tokens_per_second": 743.22
|
|
},
|
|
{
|
|
"epoch": 0.025554484088717456,
|
|
"grad_norm": 4.862583160400391,
|
|
"learning_rate": 0.0001996899830211722,
|
|
"loss": 0.9753996276855469,
|
|
"num_input_tokens_seen": 46026152,
|
|
"step": 26500,
|
|
"train_runtime": 61937.4129,
|
|
"train_tokens_per_second": 743.107
|
|
},
|
|
{
|
|
"epoch": 0.025602700096432014,
|
|
"grad_norm": 6.479689598083496,
|
|
"learning_rate": 0.00019968878947781434,
|
|
"loss": 0.9517256927490234,
|
|
"num_input_tokens_seen": 46070840,
|
|
"step": 26550,
|
|
"train_runtime": 62005.9288,
|
|
"train_tokens_per_second": 743.007
|
|
},
|
|
{
|
|
"epoch": 0.025650916104146576,
|
|
"grad_norm": 9.418253898620605,
|
|
"learning_rate": 0.00019968759364492048,
|
|
"loss": 0.9136795043945313,
|
|
"num_input_tokens_seen": 46115816,
|
|
"step": 26600,
|
|
"train_runtime": 62074.3312,
|
|
"train_tokens_per_second": 742.913
|
|
},
|
|
{
|
|
"epoch": 0.025699132111861138,
|
|
"grad_norm": 8.322517395019531,
|
|
"learning_rate": 0.00019968639552251816,
|
|
"loss": 0.874905014038086,
|
|
"num_input_tokens_seen": 46158568,
|
|
"step": 26650,
|
|
"train_runtime": 62141.9367,
|
|
"train_tokens_per_second": 742.793
|
|
},
|
|
{
|
|
"epoch": 0.0257473481195757,
|
|
"grad_norm": 7.869823455810547,
|
|
"learning_rate": 0.00019968519511063493,
|
|
"loss": 0.9214023590087891,
|
|
"num_input_tokens_seen": 46201536,
|
|
"step": 26700,
|
|
"train_runtime": 62208.5523,
|
|
"train_tokens_per_second": 742.688
|
|
},
|
|
{
|
|
"epoch": 0.02579556412729026,
|
|
"grad_norm": 6.752661228179932,
|
|
"learning_rate": 0.00019968399240929833,
|
|
"loss": 0.9920529174804688,
|
|
"num_input_tokens_seen": 46246416,
|
|
"step": 26750,
|
|
"train_runtime": 62276.679,
|
|
"train_tokens_per_second": 742.596
|
|
},
|
|
{
|
|
"epoch": 0.02584378013500482,
|
|
"grad_norm": 6.820393085479736,
|
|
"learning_rate": 0.00019968278741853594,
|
|
"loss": 0.9001280212402344,
|
|
"num_input_tokens_seen": 46290680,
|
|
"step": 26800,
|
|
"train_runtime": 62345.4679,
|
|
"train_tokens_per_second": 742.487
|
|
},
|
|
{
|
|
"epoch": 0.025891996142719382,
|
|
"grad_norm": 6.507169246673584,
|
|
"learning_rate": 0.0001996815801383755,
|
|
"loss": 0.9143851470947265,
|
|
"num_input_tokens_seen": 46333728,
|
|
"step": 26850,
|
|
"train_runtime": 62412.9838,
|
|
"train_tokens_per_second": 742.373
|
|
},
|
|
{
|
|
"epoch": 0.025940212150433944,
|
|
"grad_norm": 11.446792602539062,
|
|
"learning_rate": 0.00019968037056884467,
|
|
"loss": 0.9095830535888672,
|
|
"num_input_tokens_seen": 46379144,
|
|
"step": 26900,
|
|
"train_runtime": 62482.3193,
|
|
"train_tokens_per_second": 742.276
|
|
},
|
|
{
|
|
"epoch": 0.025988428158148506,
|
|
"grad_norm": 9.129182815551758,
|
|
"learning_rate": 0.0001996791587099713,
|
|
"loss": 1.0024927520751954,
|
|
"num_input_tokens_seen": 46423680,
|
|
"step": 26950,
|
|
"train_runtime": 62551.3914,
|
|
"train_tokens_per_second": 742.169
|
|
},
|
|
{
|
|
"epoch": 0.026036644165863067,
|
|
"grad_norm": 7.5577287673950195,
|
|
"learning_rate": 0.0001996779445617832,
|
|
"loss": 0.8830995178222656,
|
|
"num_input_tokens_seen": 46468192,
|
|
"step": 27000,
|
|
"train_runtime": 62619.9901,
|
|
"train_tokens_per_second": 742.066
|
|
},
|
|
{
|
|
"epoch": 0.02608486017357763,
|
|
"grad_norm": 8.247727394104004,
|
|
"learning_rate": 0.00019967672812430825,
|
|
"loss": 0.9312055206298828,
|
|
"num_input_tokens_seen": 46510624,
|
|
"step": 27050,
|
|
"train_runtime": 62686.0628,
|
|
"train_tokens_per_second": 741.961
|
|
},
|
|
{
|
|
"epoch": 0.026133076181292188,
|
|
"grad_norm": 6.944680213928223,
|
|
"learning_rate": 0.00019967550939757435,
|
|
"loss": 0.8939981079101562,
|
|
"num_input_tokens_seen": 46552416,
|
|
"step": 27100,
|
|
"train_runtime": 62751.6343,
|
|
"train_tokens_per_second": 741.852
|
|
},
|
|
{
|
|
"epoch": 0.02618129218900675,
|
|
"grad_norm": 8.280030250549316,
|
|
"learning_rate": 0.00019967428838160953,
|
|
"loss": 0.8804694366455078,
|
|
"num_input_tokens_seen": 46595160,
|
|
"step": 27150,
|
|
"train_runtime": 62818.7943,
|
|
"train_tokens_per_second": 741.739
|
|
},
|
|
{
|
|
"epoch": 0.02622950819672131,
|
|
"grad_norm": 6.5499267578125,
|
|
"learning_rate": 0.00019967306507644183,
|
|
"loss": 0.9179539489746094,
|
|
"num_input_tokens_seen": 46639240,
|
|
"step": 27200,
|
|
"train_runtime": 62886.8434,
|
|
"train_tokens_per_second": 741.637
|
|
},
|
|
{
|
|
"epoch": 0.026277724204435873,
|
|
"grad_norm": 4.838313102722168,
|
|
"learning_rate": 0.00019967183948209937,
|
|
"loss": 0.9282080841064453,
|
|
"num_input_tokens_seen": 46680800,
|
|
"step": 27250,
|
|
"train_runtime": 62953.0535,
|
|
"train_tokens_per_second": 741.518
|
|
},
|
|
{
|
|
"epoch": 0.026325940212150435,
|
|
"grad_norm": 8.34467887878418,
|
|
"learning_rate": 0.00019967061159861026,
|
|
"loss": 0.9697669219970703,
|
|
"num_input_tokens_seen": 46726456,
|
|
"step": 27300,
|
|
"train_runtime": 63022.4468,
|
|
"train_tokens_per_second": 741.426
|
|
},
|
|
{
|
|
"epoch": 0.026374156219864994,
|
|
"grad_norm": 9.048149108886719,
|
|
"learning_rate": 0.0001996693814260027,
|
|
"loss": 0.8345952606201172,
|
|
"num_input_tokens_seen": 46770512,
|
|
"step": 27350,
|
|
"train_runtime": 63091.0585,
|
|
"train_tokens_per_second": 741.318
|
|
},
|
|
{
|
|
"epoch": 0.026422372227579555,
|
|
"grad_norm": 9.035296440124512,
|
|
"learning_rate": 0.00019966814896430493,
|
|
"loss": 0.898397216796875,
|
|
"num_input_tokens_seen": 46816096,
|
|
"step": 27400,
|
|
"train_runtime": 63160.146,
|
|
"train_tokens_per_second": 741.228
|
|
},
|
|
{
|
|
"epoch": 0.026470588235294117,
|
|
"grad_norm": 10.21893310546875,
|
|
"learning_rate": 0.00019966691421354534,
|
|
"loss": 0.8628170776367188,
|
|
"num_input_tokens_seen": 46858752,
|
|
"step": 27450,
|
|
"train_runtime": 63227.0128,
|
|
"train_tokens_per_second": 741.119
|
|
},
|
|
{
|
|
"epoch": 0.02651880424300868,
|
|
"grad_norm": 7.458657264709473,
|
|
"learning_rate": 0.0001996656771737522,
|
|
"loss": 0.906025161743164,
|
|
"num_input_tokens_seen": 46900016,
|
|
"step": 27500,
|
|
"train_runtime": 63292.8132,
|
|
"train_tokens_per_second": 741.001
|
|
},
|
|
{
|
|
"epoch": 0.02656702025072324,
|
|
"grad_norm": 8.572747230529785,
|
|
"learning_rate": 0.00019966443784495396,
|
|
"loss": 0.8603483581542969,
|
|
"num_input_tokens_seen": 46941336,
|
|
"step": 27550,
|
|
"train_runtime": 63357.889,
|
|
"train_tokens_per_second": 740.892
|
|
},
|
|
{
|
|
"epoch": 0.026615236258437803,
|
|
"grad_norm": 7.083976745605469,
|
|
"learning_rate": 0.00019966319622717905,
|
|
"loss": 0.8540023803710938,
|
|
"num_input_tokens_seen": 46984800,
|
|
"step": 27600,
|
|
"train_runtime": 63424.4794,
|
|
"train_tokens_per_second": 740.799
|
|
},
|
|
{
|
|
"epoch": 0.02666345226615236,
|
|
"grad_norm": 12.23661994934082,
|
|
"learning_rate": 0.000199661952320456,
|
|
"loss": 0.8476334381103515,
|
|
"num_input_tokens_seen": 47028464,
|
|
"step": 27650,
|
|
"train_runtime": 63491.5981,
|
|
"train_tokens_per_second": 740.704
|
|
},
|
|
{
|
|
"epoch": 0.026711668273866923,
|
|
"grad_norm": 7.170474052429199,
|
|
"learning_rate": 0.0001996607310711575,
|
|
"loss": 0.9707311248779297,
|
|
"num_input_tokens_seen": 47071088,
|
|
"step": 27700,
|
|
"train_runtime": 63559.0914,
|
|
"train_tokens_per_second": 740.588
|
|
},
|
|
{
|
|
"epoch": 0.026759884281581485,
|
|
"grad_norm": 6.078575611114502,
|
|
"learning_rate": 0.0001996594826324015,
|
|
"loss": 0.95171875,
|
|
"num_input_tokens_seen": 47113680,
|
|
"step": 27750,
|
|
"train_runtime": 63626.1202,
|
|
"train_tokens_per_second": 740.477
|
|
},
|
|
{
|
|
"epoch": 0.026808100289296047,
|
|
"grad_norm": 6.8849358558654785,
|
|
"learning_rate": 0.00019965823190478267,
|
|
"loss": 0.8575485992431641,
|
|
"num_input_tokens_seen": 47158000,
|
|
"step": 27800,
|
|
"train_runtime": 63694.3466,
|
|
"train_tokens_per_second": 740.38
|
|
},
|
|
{
|
|
"epoch": 0.02685631629701061,
|
|
"grad_norm": 7.59286642074585,
|
|
"learning_rate": 0.0001996569788883297,
|
|
"loss": 0.8650318908691407,
|
|
"num_input_tokens_seen": 47201600,
|
|
"step": 27850,
|
|
"train_runtime": 63761.6071,
|
|
"train_tokens_per_second": 740.282
|
|
},
|
|
{
|
|
"epoch": 0.026904532304725167,
|
|
"grad_norm": 8.292630195617676,
|
|
"learning_rate": 0.00019965572358307144,
|
|
"loss": 0.8780065155029297,
|
|
"num_input_tokens_seen": 47244480,
|
|
"step": 27900,
|
|
"train_runtime": 63828.8996,
|
|
"train_tokens_per_second": 740.174
|
|
},
|
|
{
|
|
"epoch": 0.02695274831243973,
|
|
"grad_norm": 8.101641654968262,
|
|
"learning_rate": 0.00019965446598903662,
|
|
"loss": 0.9298429870605469,
|
|
"num_input_tokens_seen": 47289032,
|
|
"step": 27950,
|
|
"train_runtime": 63896.9233,
|
|
"train_tokens_per_second": 740.083
|
|
},
|
|
{
|
|
"epoch": 0.02700096432015429,
|
|
"grad_norm": 5.394447326660156,
|
|
"learning_rate": 0.0001996532061062542,
|
|
"loss": 0.8655193328857422,
|
|
"num_input_tokens_seen": 47331824,
|
|
"step": 28000,
|
|
"train_runtime": 63963.7357,
|
|
"train_tokens_per_second": 739.979
|
|
},
|
|
{
|
|
"epoch": 0.027049180327868853,
|
|
"grad_norm": 6.043957710266113,
|
|
"learning_rate": 0.0001996519439347531,
|
|
"loss": 0.8999359130859375,
|
|
"num_input_tokens_seen": 47376704,
|
|
"step": 28050,
|
|
"train_runtime": 64032.561,
|
|
"train_tokens_per_second": 739.885
|
|
},
|
|
{
|
|
"epoch": 0.027097396335583415,
|
|
"grad_norm": 7.3538818359375,
|
|
"learning_rate": 0.00019965067947456228,
|
|
"loss": 0.9095426177978516,
|
|
"num_input_tokens_seen": 47420504,
|
|
"step": 28100,
|
|
"train_runtime": 64100.4162,
|
|
"train_tokens_per_second": 739.785
|
|
},
|
|
{
|
|
"epoch": 0.027145612343297976,
|
|
"grad_norm": 4.4149580001831055,
|
|
"learning_rate": 0.0001996494127257108,
|
|
"loss": 0.9418747711181641,
|
|
"num_input_tokens_seen": 47464216,
|
|
"step": 28150,
|
|
"train_runtime": 64168.447,
|
|
"train_tokens_per_second": 739.682
|
|
},
|
|
{
|
|
"epoch": 0.027193828351012535,
|
|
"grad_norm": 5.947253227233887,
|
|
"learning_rate": 0.00019964814368822776,
|
|
"loss": 0.9599003601074219,
|
|
"num_input_tokens_seen": 47510432,
|
|
"step": 28200,
|
|
"train_runtime": 64238.722,
|
|
"train_tokens_per_second": 739.592
|
|
},
|
|
{
|
|
"epoch": 0.027242044358727097,
|
|
"grad_norm": 6.608746528625488,
|
|
"learning_rate": 0.00019964687236214231,
|
|
"loss": 0.8464434051513672,
|
|
"num_input_tokens_seen": 47551608,
|
|
"step": 28250,
|
|
"train_runtime": 64304.9263,
|
|
"train_tokens_per_second": 739.471
|
|
},
|
|
{
|
|
"epoch": 0.02729026036644166,
|
|
"grad_norm": 6.951412677764893,
|
|
"learning_rate": 0.00019964559874748362,
|
|
"loss": 0.8910402679443359,
|
|
"num_input_tokens_seen": 47596936,
|
|
"step": 28300,
|
|
"train_runtime": 64374.1387,
|
|
"train_tokens_per_second": 739.38
|
|
},
|
|
{
|
|
"epoch": 0.02733847637415622,
|
|
"grad_norm": 5.626654148101807,
|
|
"learning_rate": 0.00019964432284428095,
|
|
"loss": 0.9667503356933593,
|
|
"num_input_tokens_seen": 47641024,
|
|
"step": 28350,
|
|
"train_runtime": 64442.0258,
|
|
"train_tokens_per_second": 739.285
|
|
},
|
|
{
|
|
"epoch": 0.027386692381870782,
|
|
"grad_norm": 7.303611755371094,
|
|
"learning_rate": 0.00019964304465256363,
|
|
"loss": 0.9217509460449219,
|
|
"num_input_tokens_seen": 47684544,
|
|
"step": 28400,
|
|
"train_runtime": 64510.7597,
|
|
"train_tokens_per_second": 739.172
|
|
},
|
|
{
|
|
"epoch": 0.027434908389585344,
|
|
"grad_norm": 6.957376003265381,
|
|
"learning_rate": 0.000199641764172361,
|
|
"loss": 0.9425634002685547,
|
|
"num_input_tokens_seen": 47728784,
|
|
"step": 28450,
|
|
"train_runtime": 64578.6213,
|
|
"train_tokens_per_second": 739.08
|
|
},
|
|
{
|
|
"epoch": 0.027483124397299902,
|
|
"grad_norm": 4.9594902992248535,
|
|
"learning_rate": 0.00019964048140370244,
|
|
"loss": 0.8780956268310547,
|
|
"num_input_tokens_seen": 47772256,
|
|
"step": 28500,
|
|
"train_runtime": 64646.8022,
|
|
"train_tokens_per_second": 738.973
|
|
},
|
|
{
|
|
"epoch": 0.027531340405014464,
|
|
"grad_norm": 6.387382507324219,
|
|
"learning_rate": 0.00019963919634661745,
|
|
"loss": 0.900042724609375,
|
|
"num_input_tokens_seen": 47816280,
|
|
"step": 28550,
|
|
"train_runtime": 64714.8899,
|
|
"train_tokens_per_second": 738.876
|
|
},
|
|
{
|
|
"epoch": 0.027579556412729026,
|
|
"grad_norm": 5.046144485473633,
|
|
"learning_rate": 0.00019963790900113553,
|
|
"loss": 0.9321941375732422,
|
|
"num_input_tokens_seen": 47860480,
|
|
"step": 28600,
|
|
"train_runtime": 64784.0828,
|
|
"train_tokens_per_second": 738.769
|
|
},
|
|
{
|
|
"epoch": 0.027627772420443588,
|
|
"grad_norm": 10.389116287231445,
|
|
"learning_rate": 0.00019963661936728624,
|
|
"loss": 0.863303451538086,
|
|
"num_input_tokens_seen": 47906176,
|
|
"step": 28650,
|
|
"train_runtime": 64853.7541,
|
|
"train_tokens_per_second": 738.68
|
|
},
|
|
{
|
|
"epoch": 0.02767598842815815,
|
|
"grad_norm": 6.589110374450684,
|
|
"learning_rate": 0.00019963532744509923,
|
|
"loss": 0.907293701171875,
|
|
"num_input_tokens_seen": 47951904,
|
|
"step": 28700,
|
|
"train_runtime": 64923.216,
|
|
"train_tokens_per_second": 738.594
|
|
},
|
|
{
|
|
"epoch": 0.02772420443587271,
|
|
"grad_norm": 6.820734024047852,
|
|
"learning_rate": 0.00019963403323460414,
|
|
"loss": 0.8876425170898438,
|
|
"num_input_tokens_seen": 47994920,
|
|
"step": 28750,
|
|
"train_runtime": 64991.1324,
|
|
"train_tokens_per_second": 738.484
|
|
},
|
|
{
|
|
"epoch": 0.02777242044358727,
|
|
"grad_norm": 7.777144908905029,
|
|
"learning_rate": 0.00019963273673583067,
|
|
"loss": 0.9258315277099609,
|
|
"num_input_tokens_seen": 48037536,
|
|
"step": 28800,
|
|
"train_runtime": 65057.7137,
|
|
"train_tokens_per_second": 738.383
|
|
},
|
|
{
|
|
"epoch": 0.027820636451301832,
|
|
"grad_norm": 9.277643203735352,
|
|
"learning_rate": 0.00019963143794880865,
|
|
"loss": 0.9660711669921875,
|
|
"num_input_tokens_seen": 48080368,
|
|
"step": 28850,
|
|
"train_runtime": 65124.8992,
|
|
"train_tokens_per_second": 738.279
|
|
},
|
|
{
|
|
"epoch": 0.027868852459016394,
|
|
"grad_norm": 6.068514823913574,
|
|
"learning_rate": 0.00019963013687356788,
|
|
"loss": 0.9194924926757813,
|
|
"num_input_tokens_seen": 48121384,
|
|
"step": 28900,
|
|
"train_runtime": 65190.1685,
|
|
"train_tokens_per_second": 738.169
|
|
},
|
|
{
|
|
"epoch": 0.027917068466730956,
|
|
"grad_norm": 6.087042331695557,
|
|
"learning_rate": 0.00019962883351013825,
|
|
"loss": 0.8702348327636719,
|
|
"num_input_tokens_seen": 48164600,
|
|
"step": 28950,
|
|
"train_runtime": 65257.9394,
|
|
"train_tokens_per_second": 738.065
|
|
},
|
|
{
|
|
"epoch": 0.027965284474445518,
|
|
"grad_norm": 8.25111198425293,
|
|
"learning_rate": 0.0001996275278585497,
|
|
"loss": 0.91801025390625,
|
|
"num_input_tokens_seen": 48205360,
|
|
"step": 29000,
|
|
"train_runtime": 65323.0284,
|
|
"train_tokens_per_second": 737.954
|
|
},
|
|
{
|
|
"epoch": 0.028013500482160076,
|
|
"grad_norm": 8.016019821166992,
|
|
"learning_rate": 0.00019962621991883223,
|
|
"loss": 0.9433171844482422,
|
|
"num_input_tokens_seen": 48249240,
|
|
"step": 29050,
|
|
"train_runtime": 65390.6515,
|
|
"train_tokens_per_second": 737.861
|
|
},
|
|
{
|
|
"epoch": 0.028061716489874638,
|
|
"grad_norm": 7.289408206939697,
|
|
"learning_rate": 0.0001996249096910158,
|
|
"loss": 0.8592924499511718,
|
|
"num_input_tokens_seen": 48291768,
|
|
"step": 29100,
|
|
"train_runtime": 65457.2126,
|
|
"train_tokens_per_second": 737.761
|
|
},
|
|
{
|
|
"epoch": 0.0281099324975892,
|
|
"grad_norm": 8.102060317993164,
|
|
"learning_rate": 0.0001996235971751306,
|
|
"loss": 0.8535352325439454,
|
|
"num_input_tokens_seen": 48336664,
|
|
"step": 29150,
|
|
"train_runtime": 65526.3728,
|
|
"train_tokens_per_second": 737.667
|
|
},
|
|
{
|
|
"epoch": 0.02815814850530376,
|
|
"grad_norm": 7.3597588539123535,
|
|
"learning_rate": 0.0001996222823712067,
|
|
"loss": 0.9102005767822265,
|
|
"num_input_tokens_seen": 48381688,
|
|
"step": 29200,
|
|
"train_runtime": 65595.1128,
|
|
"train_tokens_per_second": 737.581
|
|
},
|
|
{
|
|
"epoch": 0.028206364513018323,
|
|
"grad_norm": 6.189422130584717,
|
|
"learning_rate": 0.0001996209652792744,
|
|
"loss": 0.8632147216796875,
|
|
"num_input_tokens_seen": 48426272,
|
|
"step": 29250,
|
|
"train_runtime": 65663.7744,
|
|
"train_tokens_per_second": 737.488
|
|
},
|
|
{
|
|
"epoch": 0.028254580520732882,
|
|
"grad_norm": 4.78323221206665,
|
|
"learning_rate": 0.0001996196458993638,
|
|
"loss": 0.8999051666259765,
|
|
"num_input_tokens_seen": 48470048,
|
|
"step": 29300,
|
|
"train_runtime": 65731.4664,
|
|
"train_tokens_per_second": 737.395
|
|
},
|
|
{
|
|
"epoch": 0.028302796528447444,
|
|
"grad_norm": 6.1891679763793945,
|
|
"learning_rate": 0.00019961832423150532,
|
|
"loss": 0.9630337524414062,
|
|
"num_input_tokens_seen": 48515208,
|
|
"step": 29350,
|
|
"train_runtime": 65801.71,
|
|
"train_tokens_per_second": 737.294
|
|
},
|
|
{
|
|
"epoch": 0.028351012536162006,
|
|
"grad_norm": 8.466527938842773,
|
|
"learning_rate": 0.0001996170002757293,
|
|
"loss": 0.9195822143554687,
|
|
"num_input_tokens_seen": 48558592,
|
|
"step": 29400,
|
|
"train_runtime": 65868.8218,
|
|
"train_tokens_per_second": 737.201
|
|
},
|
|
{
|
|
"epoch": 0.028399228543876567,
|
|
"grad_norm": 7.1532392501831055,
|
|
"learning_rate": 0.0001996156740320661,
|
|
"loss": 0.9529933929443359,
|
|
"num_input_tokens_seen": 48602568,
|
|
"step": 29450,
|
|
"train_runtime": 65936.4799,
|
|
"train_tokens_per_second": 737.112
|
|
},
|
|
{
|
|
"epoch": 0.02844744455159113,
|
|
"grad_norm": 6.581423759460449,
|
|
"learning_rate": 0.00019961434550054617,
|
|
"loss": 0.9135526275634765,
|
|
"num_input_tokens_seen": 48645256,
|
|
"step": 29500,
|
|
"train_runtime": 66003.6079,
|
|
"train_tokens_per_second": 737.009
|
|
},
|
|
{
|
|
"epoch": 0.02849566055930569,
|
|
"grad_norm": 10.923973083496094,
|
|
"learning_rate": 0.00019961301468120012,
|
|
"loss": 0.8842635345458985,
|
|
"num_input_tokens_seen": 48688504,
|
|
"step": 29550,
|
|
"train_runtime": 66070.4242,
|
|
"train_tokens_per_second": 736.918
|
|
},
|
|
{
|
|
"epoch": 0.02854387656702025,
|
|
"grad_norm": 7.7251877784729,
|
|
"learning_rate": 0.00019961168157405838,
|
|
"loss": 0.9014034271240234,
|
|
"num_input_tokens_seen": 48730992,
|
|
"step": 29600,
|
|
"train_runtime": 66136.9752,
|
|
"train_tokens_per_second": 736.819
|
|
},
|
|
{
|
|
"epoch": 0.02859209257473481,
|
|
"grad_norm": 11.049542427062988,
|
|
"learning_rate": 0.0001996103461791517,
|
|
"loss": 0.8520740509033203,
|
|
"num_input_tokens_seen": 48772592,
|
|
"step": 29650,
|
|
"train_runtime": 66202.6838,
|
|
"train_tokens_per_second": 736.716
|
|
},
|
|
{
|
|
"epoch": 0.028640308582449373,
|
|
"grad_norm": 10.51123046875,
|
|
"learning_rate": 0.00019960900849651066,
|
|
"loss": 0.8557865905761719,
|
|
"num_input_tokens_seen": 48816600,
|
|
"step": 29700,
|
|
"train_runtime": 66271.0253,
|
|
"train_tokens_per_second": 736.621
|
|
},
|
|
{
|
|
"epoch": 0.028688524590163935,
|
|
"grad_norm": 7.8692169189453125,
|
|
"learning_rate": 0.00019960766852616601,
|
|
"loss": 0.8878466033935547,
|
|
"num_input_tokens_seen": 48860432,
|
|
"step": 29750,
|
|
"train_runtime": 66339.7905,
|
|
"train_tokens_per_second": 736.518
|
|
},
|
|
{
|
|
"epoch": 0.028736740597878497,
|
|
"grad_norm": 4.820232391357422,
|
|
"learning_rate": 0.00019960632626814852,
|
|
"loss": 0.8655707550048828,
|
|
"num_input_tokens_seen": 48903080,
|
|
"step": 29800,
|
|
"train_runtime": 66406.1874,
|
|
"train_tokens_per_second": 736.424
|
|
},
|
|
{
|
|
"epoch": 0.028784956605593055,
|
|
"grad_norm": 7.193519115447998,
|
|
"learning_rate": 0.00019960498172248904,
|
|
"loss": 0.9292384338378906,
|
|
"num_input_tokens_seen": 48945504,
|
|
"step": 29850,
|
|
"train_runtime": 66473.8108,
|
|
"train_tokens_per_second": 736.313
|
|
},
|
|
{
|
|
"epoch": 0.028833172613307617,
|
|
"grad_norm": 5.8456621170043945,
|
|
"learning_rate": 0.00019960363488921842,
|
|
"loss": 0.928531265258789,
|
|
"num_input_tokens_seen": 48990184,
|
|
"step": 29900,
|
|
"train_runtime": 66542.1688,
|
|
"train_tokens_per_second": 736.228
|
|
},
|
|
{
|
|
"epoch": 0.02888138862102218,
|
|
"grad_norm": 8.62232780456543,
|
|
"learning_rate": 0.0001996022857683676,
|
|
"loss": 0.8761190032958984,
|
|
"num_input_tokens_seen": 49032896,
|
|
"step": 29950,
|
|
"train_runtime": 66609.5274,
|
|
"train_tokens_per_second": 736.124
|
|
},
|
|
{
|
|
"epoch": 0.02892960462873674,
|
|
"grad_norm": 10.214818954467773,
|
|
"learning_rate": 0.00019960093435996757,
|
|
"loss": 0.9675480651855469,
|
|
"num_input_tokens_seen": 49074176,
|
|
"step": 30000,
|
|
"train_runtime": 66675.703,
|
|
"train_tokens_per_second": 736.013
|
|
},
|
|
{
|
|
"epoch": 0.028977820636451303,
|
|
"grad_norm": 6.897599220275879,
|
|
"learning_rate": 0.00019959958066404938,
|
|
"loss": 0.9794612121582031,
|
|
"num_input_tokens_seen": 49116864,
|
|
"step": 30050,
|
|
"train_runtime": 66743.7257,
|
|
"train_tokens_per_second": 735.902
|
|
},
|
|
{
|
|
"epoch": 0.029026036644165865,
|
|
"grad_norm": 6.0572733879089355,
|
|
"learning_rate": 0.00019959822468064412,
|
|
"loss": 1.084517135620117,
|
|
"num_input_tokens_seen": 49162744,
|
|
"step": 30100,
|
|
"train_runtime": 66814.5283,
|
|
"train_tokens_per_second": 735.809
|
|
},
|
|
{
|
|
"epoch": 0.029074252651880423,
|
|
"grad_norm": 6.695127010345459,
|
|
"learning_rate": 0.00019959686640978288,
|
|
"loss": 1.0553150177001953,
|
|
"num_input_tokens_seen": 49207568,
|
|
"step": 30150,
|
|
"train_runtime": 66883.0818,
|
|
"train_tokens_per_second": 735.725
|
|
},
|
|
{
|
|
"epoch": 0.029122468659594985,
|
|
"grad_norm": 6.773244857788086,
|
|
"learning_rate": 0.00019959550585149692,
|
|
"loss": 0.9828330230712891,
|
|
"num_input_tokens_seen": 49252472,
|
|
"step": 30200,
|
|
"train_runtime": 66952.7733,
|
|
"train_tokens_per_second": 735.63
|
|
},
|
|
{
|
|
"epoch": 0.029170684667309547,
|
|
"grad_norm": 11.200570106506348,
|
|
"learning_rate": 0.00019959414300581746,
|
|
"loss": 1.0416008758544921,
|
|
"num_input_tokens_seen": 49296776,
|
|
"step": 30250,
|
|
"train_runtime": 67021.6585,
|
|
"train_tokens_per_second": 735.535
|
|
},
|
|
{
|
|
"epoch": 0.02921890067502411,
|
|
"grad_norm": 8.189773559570312,
|
|
"learning_rate": 0.0001995927778727758,
|
|
"loss": 0.9748827362060547,
|
|
"num_input_tokens_seen": 49338288,
|
|
"step": 30300,
|
|
"train_runtime": 67087.312,
|
|
"train_tokens_per_second": 735.434
|
|
},
|
|
{
|
|
"epoch": 0.02926711668273867,
|
|
"grad_norm": 5.6725358963012695,
|
|
"learning_rate": 0.00019959141045240331,
|
|
"loss": 0.9572772216796875,
|
|
"num_input_tokens_seen": 49384688,
|
|
"step": 30350,
|
|
"train_runtime": 67157.5076,
|
|
"train_tokens_per_second": 735.356
|
|
},
|
|
{
|
|
"epoch": 0.02931533269045323,
|
|
"grad_norm": 7.45173978805542,
|
|
"learning_rate": 0.00019959004074473135,
|
|
"loss": 0.9491313934326172,
|
|
"num_input_tokens_seen": 49427440,
|
|
"step": 30400,
|
|
"train_runtime": 67224.4203,
|
|
"train_tokens_per_second": 735.26
|
|
},
|
|
{
|
|
"epoch": 0.02936354869816779,
|
|
"grad_norm": 7.993218421936035,
|
|
"learning_rate": 0.00019958866874979144,
|
|
"loss": 1.0455535125732422,
|
|
"num_input_tokens_seen": 49470672,
|
|
"step": 30450,
|
|
"train_runtime": 67291.9985,
|
|
"train_tokens_per_second": 735.164
|
|
},
|
|
{
|
|
"epoch": 0.029411764705882353,
|
|
"grad_norm": 6.677618503570557,
|
|
"learning_rate": 0.00019958729446761504,
|
|
"loss": 1.0117230987548829,
|
|
"num_input_tokens_seen": 49515632,
|
|
"step": 30500,
|
|
"train_runtime": 67361.6808,
|
|
"train_tokens_per_second": 735.071
|
|
},
|
|
{
|
|
"epoch": 0.029459980713596914,
|
|
"grad_norm": 8.109087944030762,
|
|
"learning_rate": 0.00019958591789823372,
|
|
"loss": 0.8726683044433594,
|
|
"num_input_tokens_seen": 49559360,
|
|
"step": 30550,
|
|
"train_runtime": 67429.6373,
|
|
"train_tokens_per_second": 734.979
|
|
},
|
|
{
|
|
"epoch": 0.029508196721311476,
|
|
"grad_norm": 6.541062831878662,
|
|
"learning_rate": 0.00019958456664122433,
|
|
"loss": 1.0697627258300781,
|
|
"num_input_tokens_seen": 49605168,
|
|
"step": 30600,
|
|
"train_runtime": 67499.3177,
|
|
"train_tokens_per_second": 734.899
|
|
},
|
|
{
|
|
"epoch": 0.029556412729026038,
|
|
"grad_norm": 7.244748115539551,
|
|
"learning_rate": 0.00019958318554327064,
|
|
"loss": 0.9828516387939453,
|
|
"num_input_tokens_seen": 49652712,
|
|
"step": 30650,
|
|
"train_runtime": 67570.2355,
|
|
"train_tokens_per_second": 734.831
|
|
},
|
|
{
|
|
"epoch": 0.029604628736740597,
|
|
"grad_norm": 8.073100090026855,
|
|
"learning_rate": 0.00019958180215820642,
|
|
"loss": 0.9045378875732422,
|
|
"num_input_tokens_seen": 49697696,
|
|
"step": 30700,
|
|
"train_runtime": 67639.5908,
|
|
"train_tokens_per_second": 734.743
|
|
},
|
|
{
|
|
"epoch": 0.02965284474445516,
|
|
"grad_norm": 6.397795677185059,
|
|
"learning_rate": 0.0001995804442219194,
|
|
"loss": 1.04176025390625,
|
|
"num_input_tokens_seen": 49744880,
|
|
"step": 30750,
|
|
"train_runtime": 67711.5472,
|
|
"train_tokens_per_second": 734.659
|
|
},
|
|
{
|
|
"epoch": 0.02970106075216972,
|
|
"grad_norm": 6.2678937911987305,
|
|
"learning_rate": 0.00019957905630847012,
|
|
"loss": 0.9161843872070312,
|
|
"num_input_tokens_seen": 49789208,
|
|
"step": 30800,
|
|
"train_runtime": 67780.8591,
|
|
"train_tokens_per_second": 734.561
|
|
},
|
|
{
|
|
"epoch": 0.029749276759884282,
|
|
"grad_norm": 10.180242538452148,
|
|
"learning_rate": 0.0001995776661080051,
|
|
"loss": 0.8746125793457031,
|
|
"num_input_tokens_seen": 49833872,
|
|
"step": 30850,
|
|
"train_runtime": 67850.6977,
|
|
"train_tokens_per_second": 734.464
|
|
},
|
|
{
|
|
"epoch": 0.029797492767598844,
|
|
"grad_norm": 6.190165996551514,
|
|
"learning_rate": 0.00019957627362055628,
|
|
"loss": 0.9756806945800781,
|
|
"num_input_tokens_seen": 49880232,
|
|
"step": 30900,
|
|
"train_runtime": 67920.4659,
|
|
"train_tokens_per_second": 734.392
|
|
},
|
|
{
|
|
"epoch": 0.029845708775313402,
|
|
"grad_norm": 6.197800636291504,
|
|
"learning_rate": 0.00019957487884615568,
|
|
"loss": 0.8631037139892578,
|
|
"num_input_tokens_seen": 49923392,
|
|
"step": 30950,
|
|
"train_runtime": 67987.5431,
|
|
"train_tokens_per_second": 734.302
|
|
},
|
|
{
|
|
"epoch": 0.029893924783027964,
|
|
"grad_norm": 11.594888687133789,
|
|
"learning_rate": 0.00019957348178483534,
|
|
"loss": 0.8737953948974609,
|
|
"num_input_tokens_seen": 49967536,
|
|
"step": 31000,
|
|
"train_runtime": 68056.0799,
|
|
"train_tokens_per_second": 734.211
|
|
},
|
|
{
|
|
"epoch": 0.029942140790742526,
|
|
"grad_norm": 4.624935150146484,
|
|
"learning_rate": 0.00019957208243662734,
|
|
"loss": 0.883858642578125,
|
|
"num_input_tokens_seen": 50013336,
|
|
"step": 31050,
|
|
"train_runtime": 68126.608,
|
|
"train_tokens_per_second": 734.123
|
|
},
|
|
{
|
|
"epoch": 0.029990356798457088,
|
|
"grad_norm": 7.1981329917907715,
|
|
"learning_rate": 0.0001995706808015638,
|
|
"loss": 0.8532677459716796,
|
|
"num_input_tokens_seen": 50059304,
|
|
"step": 31100,
|
|
"train_runtime": 68196.0336,
|
|
"train_tokens_per_second": 734.05
|
|
},
|
|
{
|
|
"epoch": 0.03003857280617165,
|
|
"grad_norm": 7.8624467849731445,
|
|
"learning_rate": 0.00019956927687967685,
|
|
"loss": 0.8965191650390625,
|
|
"num_input_tokens_seen": 50107408,
|
|
"step": 31150,
|
|
"train_runtime": 68268.3454,
|
|
"train_tokens_per_second": 733.977
|
|
},
|
|
{
|
|
"epoch": 0.03008678881388621,
|
|
"grad_norm": 12.917635917663574,
|
|
"learning_rate": 0.00019956787067099886,
|
|
"loss": 0.9234679412841796,
|
|
"num_input_tokens_seen": 50153936,
|
|
"step": 31200,
|
|
"train_runtime": 68338.4679,
|
|
"train_tokens_per_second": 733.905
|
|
},
|
|
{
|
|
"epoch": 0.03013500482160077,
|
|
"grad_norm": 5.439303874969482,
|
|
"learning_rate": 0.00019956646217556204,
|
|
"loss": 0.87079833984375,
|
|
"num_input_tokens_seen": 50201360,
|
|
"step": 31250,
|
|
"train_runtime": 68410.1847,
|
|
"train_tokens_per_second": 733.829
|
|
},
|
|
{
|
|
"epoch": 0.030183220829315332,
|
|
"grad_norm": 12.652541160583496,
|
|
"learning_rate": 0.00019956505139339878,
|
|
"loss": 0.8618885040283203,
|
|
"num_input_tokens_seen": 50248088,
|
|
"step": 31300,
|
|
"train_runtime": 68481.0984,
|
|
"train_tokens_per_second": 733.751
|
|
},
|
|
{
|
|
"epoch": 0.030231436837029894,
|
|
"grad_norm": 7.053194999694824,
|
|
"learning_rate": 0.00019956363832454149,
|
|
"loss": 0.8750392150878906,
|
|
"num_input_tokens_seen": 50296256,
|
|
"step": 31350,
|
|
"train_runtime": 68554.299,
|
|
"train_tokens_per_second": 733.67
|
|
},
|
|
{
|
|
"epoch": 0.030279652844744456,
|
|
"grad_norm": 7.43891716003418,
|
|
"learning_rate": 0.00019956222296902256,
|
|
"loss": 0.9851769256591797,
|
|
"num_input_tokens_seen": 50342248,
|
|
"step": 31400,
|
|
"train_runtime": 68624.0004,
|
|
"train_tokens_per_second": 733.595
|
|
},
|
|
{
|
|
"epoch": 0.030327868852459017,
|
|
"grad_norm": 7.558279037475586,
|
|
"learning_rate": 0.00019956080532687454,
|
|
"loss": 0.8798101043701172,
|
|
"num_input_tokens_seen": 50389824,
|
|
"step": 31450,
|
|
"train_runtime": 68696.0331,
|
|
"train_tokens_per_second": 733.519
|
|
},
|
|
{
|
|
"epoch": 0.03037608486017358,
|
|
"grad_norm": 8.292657852172852,
|
|
"learning_rate": 0.00019955938539813,
|
|
"loss": 0.8526065826416016,
|
|
"num_input_tokens_seen": 50438000,
|
|
"step": 31500,
|
|
"train_runtime": 68768.2962,
|
|
"train_tokens_per_second": 733.448
|
|
},
|
|
{
|
|
"epoch": 0.030424300867888138,
|
|
"grad_norm": 11.766907691955566,
|
|
"learning_rate": 0.0001995579631828215,
|
|
"loss": 0.9604615783691406,
|
|
"num_input_tokens_seen": 50481736,
|
|
"step": 31550,
|
|
"train_runtime": 68836.7316,
|
|
"train_tokens_per_second": 733.355
|
|
},
|
|
{
|
|
"epoch": 0.0304725168756027,
|
|
"grad_norm": 7.310155868530273,
|
|
"learning_rate": 0.00019955653868098178,
|
|
"loss": 0.7611132049560547,
|
|
"num_input_tokens_seen": 50525752,
|
|
"step": 31600,
|
|
"train_runtime": 68904.5032,
|
|
"train_tokens_per_second": 733.272
|
|
},
|
|
{
|
|
"epoch": 0.03052073288331726,
|
|
"grad_norm": 8.486549377441406,
|
|
"learning_rate": 0.00019955511189264348,
|
|
"loss": 0.8584770965576172,
|
|
"num_input_tokens_seen": 50571064,
|
|
"step": 31650,
|
|
"train_runtime": 68973.3905,
|
|
"train_tokens_per_second": 733.197
|
|
},
|
|
{
|
|
"epoch": 0.030568948891031823,
|
|
"grad_norm": 5.7536444664001465,
|
|
"learning_rate": 0.00019955368281783943,
|
|
"loss": 0.8708917999267578,
|
|
"num_input_tokens_seen": 50619392,
|
|
"step": 31700,
|
|
"train_runtime": 69046.4234,
|
|
"train_tokens_per_second": 733.121
|
|
},
|
|
{
|
|
"epoch": 0.030617164898746385,
|
|
"grad_norm": 7.436832427978516,
|
|
"learning_rate": 0.00019955225145660242,
|
|
"loss": 0.9074885559082031,
|
|
"num_input_tokens_seen": 50668400,
|
|
"step": 31750,
|
|
"train_runtime": 69120.0506,
|
|
"train_tokens_per_second": 733.049
|
|
},
|
|
{
|
|
"epoch": 0.030665380906460944,
|
|
"grad_norm": 5.5813751220703125,
|
|
"learning_rate": 0.00019955081780896532,
|
|
"loss": 0.7580270385742187,
|
|
"num_input_tokens_seen": 50716696,
|
|
"step": 31800,
|
|
"train_runtime": 69192.5415,
|
|
"train_tokens_per_second": 732.979
|
|
},
|
|
{
|
|
"epoch": 0.030713596914175505,
|
|
"grad_norm": 14.789217948913574,
|
|
"learning_rate": 0.00019954938187496105,
|
|
"loss": 0.8388276672363282,
|
|
"num_input_tokens_seen": 50765784,
|
|
"step": 31850,
|
|
"train_runtime": 69265.5428,
|
|
"train_tokens_per_second": 732.915
|
|
},
|
|
{
|
|
"epoch": 0.030761812921890067,
|
|
"grad_norm": 10.416450500488281,
|
|
"learning_rate": 0.00019954794365462263,
|
|
"loss": 0.7596660614013672,
|
|
"num_input_tokens_seen": 50814864,
|
|
"step": 31900,
|
|
"train_runtime": 69338.0426,
|
|
"train_tokens_per_second": 732.857
|
|
},
|
|
{
|
|
"epoch": 0.03081002892960463,
|
|
"grad_norm": 6.031883239746094,
|
|
"learning_rate": 0.0001995465031479831,
|
|
"loss": 0.8369689178466797,
|
|
"num_input_tokens_seen": 50861632,
|
|
"step": 31950,
|
|
"train_runtime": 69409.3029,
|
|
"train_tokens_per_second": 732.778
|
|
},
|
|
{
|
|
"epoch": 0.03085824493731919,
|
|
"grad_norm": 6.86395263671875,
|
|
"learning_rate": 0.00019954506035507549,
|
|
"loss": 0.7961445617675781,
|
|
"num_input_tokens_seen": 50907792,
|
|
"step": 32000,
|
|
"train_runtime": 69479.9493,
|
|
"train_tokens_per_second": 732.698
|
|
},
|
|
{
|
|
"epoch": 0.030906460945033753,
|
|
"grad_norm": 7.525618076324463,
|
|
"learning_rate": 0.0001995436152759329,
|
|
"loss": 0.8980144500732422,
|
|
"num_input_tokens_seen": 50951408,
|
|
"step": 32050,
|
|
"train_runtime": 69548.3004,
|
|
"train_tokens_per_second": 732.605
|
|
},
|
|
{
|
|
"epoch": 0.03095467695274831,
|
|
"grad_norm": 5.709936141967773,
|
|
"learning_rate": 0.00019954216791058863,
|
|
"loss": 0.7946480560302734,
|
|
"num_input_tokens_seen": 50997184,
|
|
"step": 32100,
|
|
"train_runtime": 69618.0329,
|
|
"train_tokens_per_second": 732.528
|
|
},
|
|
{
|
|
"epoch": 0.031002892960462873,
|
|
"grad_norm": 10.820000648498535,
|
|
"learning_rate": 0.00019954071825907584,
|
|
"loss": 0.7499545288085937,
|
|
"num_input_tokens_seen": 51042624,
|
|
"step": 32150,
|
|
"train_runtime": 69687.3611,
|
|
"train_tokens_per_second": 732.452
|
|
},
|
|
{
|
|
"epoch": 0.031051108968177435,
|
|
"grad_norm": 11.399004936218262,
|
|
"learning_rate": 0.00019953926632142784,
|
|
"loss": 0.7571890258789062,
|
|
"num_input_tokens_seen": 51089816,
|
|
"step": 32200,
|
|
"train_runtime": 69758.8159,
|
|
"train_tokens_per_second": 732.378
|
|
},
|
|
{
|
|
"epoch": 0.031099324975891997,
|
|
"grad_norm": 10.855454444885254,
|
|
"learning_rate": 0.00019953781209767804,
|
|
"loss": 0.7944773864746094,
|
|
"num_input_tokens_seen": 51133856,
|
|
"step": 32250,
|
|
"train_runtime": 69828.4784,
|
|
"train_tokens_per_second": 732.278
|
|
},
|
|
{
|
|
"epoch": 0.03114754098360656,
|
|
"grad_norm": 10.548445701599121,
|
|
"learning_rate": 0.00019953635558785974,
|
|
"loss": 0.8420456695556641,
|
|
"num_input_tokens_seen": 51177864,
|
|
"step": 32300,
|
|
"train_runtime": 69897.666,
|
|
"train_tokens_per_second": 732.183
|
|
},
|
|
{
|
|
"epoch": 0.031195756991321117,
|
|
"grad_norm": 12.899710655212402,
|
|
"learning_rate": 0.00019953489679200645,
|
|
"loss": 0.9103004455566406,
|
|
"num_input_tokens_seen": 51223376,
|
|
"step": 32350,
|
|
"train_runtime": 69966.2133,
|
|
"train_tokens_per_second": 732.116
|
|
},
|
|
{
|
|
"epoch": 0.03124397299903568,
|
|
"grad_norm": 10.619632720947266,
|
|
"learning_rate": 0.00019953343571015166,
|
|
"loss": 0.8466280364990234,
|
|
"num_input_tokens_seen": 51272400,
|
|
"step": 32400,
|
|
"train_runtime": 70039.1575,
|
|
"train_tokens_per_second": 732.053
|
|
},
|
|
{
|
|
"epoch": 0.031292189006750244,
|
|
"grad_norm": 10.311902046203613,
|
|
"learning_rate": 0.00019953197234232894,
|
|
"loss": 0.8465247344970703,
|
|
"num_input_tokens_seen": 51317416,
|
|
"step": 32450,
|
|
"train_runtime": 70108.7557,
|
|
"train_tokens_per_second": 731.969
|
|
},
|
|
{
|
|
"epoch": 0.0313404050144648,
|
|
"grad_norm": 9.822750091552734,
|
|
"learning_rate": 0.00019953050668857186,
|
|
"loss": 0.773394775390625,
|
|
"num_input_tokens_seen": 51365760,
|
|
"step": 32500,
|
|
"train_runtime": 70181.2069,
|
|
"train_tokens_per_second": 731.902
|
|
},
|
|
{
|
|
"epoch": 0.03138862102217936,
|
|
"grad_norm": 6.678475379943848,
|
|
"learning_rate": 0.00019952903874891415,
|
|
"loss": 0.8095280456542969,
|
|
"num_input_tokens_seen": 51410656,
|
|
"step": 32550,
|
|
"train_runtime": 70250.3306,
|
|
"train_tokens_per_second": 731.821
|
|
},
|
|
{
|
|
"epoch": 0.03143683702989392,
|
|
"grad_norm": 10.345113754272461,
|
|
"learning_rate": 0.00019952756852338946,
|
|
"loss": 0.8103610229492187,
|
|
"num_input_tokens_seen": 51455624,
|
|
"step": 32600,
|
|
"train_runtime": 70320.1883,
|
|
"train_tokens_per_second": 731.733
|
|
},
|
|
{
|
|
"epoch": 0.031485053037608485,
|
|
"grad_norm": 10.966005325317383,
|
|
"learning_rate": 0.00019952609601203155,
|
|
"loss": 0.7727910614013672,
|
|
"num_input_tokens_seen": 51497536,
|
|
"step": 32650,
|
|
"train_runtime": 70387.1271,
|
|
"train_tokens_per_second": 731.633
|
|
},
|
|
{
|
|
"epoch": 0.03153326904532305,
|
|
"grad_norm": 7.840993881225586,
|
|
"learning_rate": 0.0001995246212148743,
|
|
"loss": 0.7581089782714844,
|
|
"num_input_tokens_seen": 51545336,
|
|
"step": 32700,
|
|
"train_runtime": 70460.4721,
|
|
"train_tokens_per_second": 731.55
|
|
},
|
|
{
|
|
"epoch": 0.03158148505303761,
|
|
"grad_norm": 7.049962520599365,
|
|
"learning_rate": 0.00019952314413195153,
|
|
"loss": 0.843936538696289,
|
|
"num_input_tokens_seen": 51589928,
|
|
"step": 32750,
|
|
"train_runtime": 70530.5688,
|
|
"train_tokens_per_second": 731.455
|
|
},
|
|
{
|
|
"epoch": 0.03162970106075217,
|
|
"grad_norm": 4.574373245239258,
|
|
"learning_rate": 0.0001995216647632972,
|
|
"loss": 0.80212158203125,
|
|
"num_input_tokens_seen": 51635592,
|
|
"step": 32800,
|
|
"train_runtime": 70601.2471,
|
|
"train_tokens_per_second": 731.369
|
|
},
|
|
{
|
|
"epoch": 0.03167791706846673,
|
|
"grad_norm": 17.428335189819336,
|
|
"learning_rate": 0.00019952018310894526,
|
|
"loss": 0.8247758483886719,
|
|
"num_input_tokens_seen": 51679944,
|
|
"step": 32850,
|
|
"train_runtime": 70670.1411,
|
|
"train_tokens_per_second": 731.284
|
|
},
|
|
{
|
|
"epoch": 0.031726133076181294,
|
|
"grad_norm": 8.19315242767334,
|
|
"learning_rate": 0.00019951869916892974,
|
|
"loss": 0.7693586730957032,
|
|
"num_input_tokens_seen": 51728096,
|
|
"step": 32900,
|
|
"train_runtime": 70743.3804,
|
|
"train_tokens_per_second": 731.208
|
|
},
|
|
{
|
|
"epoch": 0.031774349083895856,
|
|
"grad_norm": 6.906826972961426,
|
|
"learning_rate": 0.00019951721294328474,
|
|
"loss": 0.7810629272460937,
|
|
"num_input_tokens_seen": 51772904,
|
|
"step": 32950,
|
|
"train_runtime": 70813.3992,
|
|
"train_tokens_per_second": 731.117
|
|
},
|
|
{
|
|
"epoch": 0.03182256509161042,
|
|
"grad_norm": 10.231990814208984,
|
|
"learning_rate": 0.00019951572443204437,
|
|
"loss": 0.8511717224121094,
|
|
"num_input_tokens_seen": 51816616,
|
|
"step": 33000,
|
|
"train_runtime": 70882.1385,
|
|
"train_tokens_per_second": 731.025
|
|
},
|
|
{
|
|
"epoch": 0.03187078109932497,
|
|
"grad_norm": 7.27070426940918,
|
|
"learning_rate": 0.00019951423363524285,
|
|
"loss": 0.7103465270996093,
|
|
"num_input_tokens_seen": 51861512,
|
|
"step": 33050,
|
|
"train_runtime": 70951.9122,
|
|
"train_tokens_per_second": 730.939
|
|
},
|
|
{
|
|
"epoch": 0.031918997107039535,
|
|
"grad_norm": 11.29908275604248,
|
|
"learning_rate": 0.00019951274055291437,
|
|
"loss": 0.763965835571289,
|
|
"num_input_tokens_seen": 51905136,
|
|
"step": 33100,
|
|
"train_runtime": 71021.0071,
|
|
"train_tokens_per_second": 730.842
|
|
},
|
|
{
|
|
"epoch": 0.031967213114754096,
|
|
"grad_norm": 5.140653133392334,
|
|
"learning_rate": 0.0001995112451850933,
|
|
"loss": 0.7487338256835937,
|
|
"num_input_tokens_seen": 51948608,
|
|
"step": 33150,
|
|
"train_runtime": 71089.6756,
|
|
"train_tokens_per_second": 730.748
|
|
},
|
|
{
|
|
"epoch": 0.03201542912246866,
|
|
"grad_norm": 6.394457817077637,
|
|
"learning_rate": 0.00019950974753181388,
|
|
"loss": 0.799521713256836,
|
|
"num_input_tokens_seen": 51991832,
|
|
"step": 33200,
|
|
"train_runtime": 71158.3424,
|
|
"train_tokens_per_second": 730.65
|
|
},
|
|
{
|
|
"epoch": 0.03206364513018322,
|
|
"grad_norm": 5.851606369018555,
|
|
"learning_rate": 0.00019950824759311058,
|
|
"loss": 0.8536869049072265,
|
|
"num_input_tokens_seen": 52038616,
|
|
"step": 33250,
|
|
"train_runtime": 71229.916,
|
|
"train_tokens_per_second": 730.572
|
|
},
|
|
{
|
|
"epoch": 0.03211186113789778,
|
|
"grad_norm": 10.5271635055542,
|
|
"learning_rate": 0.00019950674536901782,
|
|
"loss": 0.8119235229492188,
|
|
"num_input_tokens_seen": 52083848,
|
|
"step": 33300,
|
|
"train_runtime": 71299.7676,
|
|
"train_tokens_per_second": 730.491
|
|
},
|
|
{
|
|
"epoch": 0.032160077145612344,
|
|
"grad_norm": 10.081520080566406,
|
|
"learning_rate": 0.00019950524085957013,
|
|
"loss": 0.7506763458251953,
|
|
"num_input_tokens_seen": 52128384,
|
|
"step": 33350,
|
|
"train_runtime": 71370.2245,
|
|
"train_tokens_per_second": 730.394
|
|
},
|
|
{
|
|
"epoch": 0.032208293153326906,
|
|
"grad_norm": 9.206167221069336,
|
|
"learning_rate": 0.00019950373406480204,
|
|
"loss": 0.831438217163086,
|
|
"num_input_tokens_seen": 52173336,
|
|
"step": 33400,
|
|
"train_runtime": 71440.6842,
|
|
"train_tokens_per_second": 730.303
|
|
},
|
|
{
|
|
"epoch": 0.03225650916104147,
|
|
"grad_norm": 17.003467559814453,
|
|
"learning_rate": 0.00019950222498474815,
|
|
"loss": 0.8617337799072265,
|
|
"num_input_tokens_seen": 52214576,
|
|
"step": 33450,
|
|
"train_runtime": 71507.7728,
|
|
"train_tokens_per_second": 730.194
|
|
},
|
|
{
|
|
"epoch": 0.03230472516875603,
|
|
"grad_norm": 13.451969146728516,
|
|
"learning_rate": 0.00019950071361944313,
|
|
"loss": 0.8533307647705078,
|
|
"num_input_tokens_seen": 52259424,
|
|
"step": 33500,
|
|
"train_runtime": 71578.5944,
|
|
"train_tokens_per_second": 730.098
|
|
},
|
|
{
|
|
"epoch": 0.03235294117647059,
|
|
"grad_norm": 9.072508811950684,
|
|
"learning_rate": 0.0001994991999689217,
|
|
"loss": 0.7468711090087891,
|
|
"num_input_tokens_seen": 52302528,
|
|
"step": 33550,
|
|
"train_runtime": 71648.0287,
|
|
"train_tokens_per_second": 729.993
|
|
},
|
|
{
|
|
"epoch": 0.032401157184185146,
|
|
"grad_norm": 11.486859321594238,
|
|
"learning_rate": 0.0001994976840332186,
|
|
"loss": 0.7341663360595703,
|
|
"num_input_tokens_seen": 52345376,
|
|
"step": 33600,
|
|
"train_runtime": 71718.2344,
|
|
"train_tokens_per_second": 729.875
|
|
},
|
|
{
|
|
"epoch": 0.03244937319189971,
|
|
"grad_norm": 11.670675277709961,
|
|
"learning_rate": 0.00019949616581236868,
|
|
"loss": 0.6607723999023437,
|
|
"num_input_tokens_seen": 52392392,
|
|
"step": 33650,
|
|
"train_runtime": 71791.452,
|
|
"train_tokens_per_second": 729.786
|
|
},
|
|
{
|
|
"epoch": 0.03249758919961427,
|
|
"grad_norm": 7.706065654754639,
|
|
"learning_rate": 0.0001994946453064068,
|
|
"loss": 0.8130783081054688,
|
|
"num_input_tokens_seen": 52437736,
|
|
"step": 33700,
|
|
"train_runtime": 71861.5846,
|
|
"train_tokens_per_second": 729.705
|
|
},
|
|
{
|
|
"epoch": 0.03254580520732883,
|
|
"grad_norm": 11.388274192810059,
|
|
"learning_rate": 0.00019949312251536783,
|
|
"loss": 0.7494591522216797,
|
|
"num_input_tokens_seen": 52485352,
|
|
"step": 33750,
|
|
"train_runtime": 71935.6314,
|
|
"train_tokens_per_second": 729.616
|
|
},
|
|
{
|
|
"epoch": 0.032594021215043394,
|
|
"grad_norm": 8.938033103942871,
|
|
"learning_rate": 0.0001994915974392868,
|
|
"loss": 0.687170639038086,
|
|
"num_input_tokens_seen": 52528872,
|
|
"step": 33800,
|
|
"train_runtime": 72005.3717,
|
|
"train_tokens_per_second": 729.513
|
|
},
|
|
{
|
|
"epoch": 0.032642237222757955,
|
|
"grad_norm": 7.732115745544434,
|
|
"learning_rate": 0.0001994900700781987,
|
|
"loss": 0.7417778778076172,
|
|
"num_input_tokens_seen": 52574528,
|
|
"step": 33850,
|
|
"train_runtime": 72076.3211,
|
|
"train_tokens_per_second": 729.429
|
|
},
|
|
{
|
|
"epoch": 0.03269045323047252,
|
|
"grad_norm": 12.362086296081543,
|
|
"learning_rate": 0.00019948854043213868,
|
|
"loss": 0.6744145965576172,
|
|
"num_input_tokens_seen": 52620792,
|
|
"step": 33900,
|
|
"train_runtime": 72148.9711,
|
|
"train_tokens_per_second": 729.335
|
|
},
|
|
{
|
|
"epoch": 0.03273866923818708,
|
|
"grad_norm": 8.031180381774902,
|
|
"learning_rate": 0.00019948700850114178,
|
|
"loss": 0.8399528503417969,
|
|
"num_input_tokens_seen": 52663360,
|
|
"step": 33950,
|
|
"train_runtime": 72218.1305,
|
|
"train_tokens_per_second": 729.226
|
|
},
|
|
{
|
|
"epoch": 0.03278688524590164,
|
|
"grad_norm": 10.704548835754395,
|
|
"learning_rate": 0.00019948547428524322,
|
|
"loss": 0.7734897613525391,
|
|
"num_input_tokens_seen": 52705664,
|
|
"step": 34000,
|
|
"train_runtime": 72287.0721,
|
|
"train_tokens_per_second": 729.116
|
|
},
|
|
{
|
|
"epoch": 0.0328351012536162,
|
|
"grad_norm": 6.97188138961792,
|
|
"learning_rate": 0.00019948393778447825,
|
|
"loss": 0.7026171112060546,
|
|
"num_input_tokens_seen": 52749744,
|
|
"step": 34050,
|
|
"train_runtime": 72356.459,
|
|
"train_tokens_per_second": 729.026
|
|
},
|
|
{
|
|
"epoch": 0.032883317261330765,
|
|
"grad_norm": 16.199106216430664,
|
|
"learning_rate": 0.00019948239899888215,
|
|
"loss": 0.7143807220458984,
|
|
"num_input_tokens_seen": 52793544,
|
|
"step": 34100,
|
|
"train_runtime": 72426.4396,
|
|
"train_tokens_per_second": 728.926
|
|
},
|
|
{
|
|
"epoch": 0.03293153326904532,
|
|
"grad_norm": 12.12110424041748,
|
|
"learning_rate": 0.00019948085792849027,
|
|
"loss": 0.7816483306884766,
|
|
"num_input_tokens_seen": 52838928,
|
|
"step": 34150,
|
|
"train_runtime": 72498.3456,
|
|
"train_tokens_per_second": 728.829
|
|
},
|
|
{
|
|
"epoch": 0.03297974927675988,
|
|
"grad_norm": 10.907366752624512,
|
|
"learning_rate": 0.00019947931457333797,
|
|
"loss": 0.7564363861083985,
|
|
"num_input_tokens_seen": 52880256,
|
|
"step": 34200,
|
|
"train_runtime": 72567.072,
|
|
"train_tokens_per_second": 728.709
|
|
},
|
|
{
|
|
"epoch": 0.03302796528447444,
|
|
"grad_norm": 12.279559135437012,
|
|
"learning_rate": 0.00019947776893346073,
|
|
"loss": 0.7922947692871094,
|
|
"num_input_tokens_seen": 52923416,
|
|
"step": 34250,
|
|
"train_runtime": 72636.8244,
|
|
"train_tokens_per_second": 728.603
|
|
},
|
|
{
|
|
"epoch": 0.033076181292189005,
|
|
"grad_norm": 9.32922077178955,
|
|
"learning_rate": 0.00019947622100889405,
|
|
"loss": 0.6778532409667969,
|
|
"num_input_tokens_seen": 52966224,
|
|
"step": 34300,
|
|
"train_runtime": 72706.3301,
|
|
"train_tokens_per_second": 728.495
|
|
},
|
|
{
|
|
"epoch": 0.03312439729990357,
|
|
"grad_norm": 8.128923416137695,
|
|
"learning_rate": 0.00019947467079967345,
|
|
"loss": 0.7276709747314453,
|
|
"num_input_tokens_seen": 53013280,
|
|
"step": 34350,
|
|
"train_runtime": 72780.4114,
|
|
"train_tokens_per_second": 728.4
|
|
},
|
|
{
|
|
"epoch": 0.03317261330761813,
|
|
"grad_norm": 7.321900367736816,
|
|
"learning_rate": 0.00019947311830583456,
|
|
"loss": 0.8039102935791016,
|
|
"num_input_tokens_seen": 53057432,
|
|
"step": 34400,
|
|
"train_runtime": 72850.9795,
|
|
"train_tokens_per_second": 728.301
|
|
},
|
|
{
|
|
"epoch": 0.03322082931533269,
|
|
"grad_norm": 12.749677658081055,
|
|
"learning_rate": 0.00019947156352741302,
|
|
"loss": 0.8883670806884766,
|
|
"num_input_tokens_seen": 53099048,
|
|
"step": 34450,
|
|
"train_runtime": 72918.9653,
|
|
"train_tokens_per_second": 728.193
|
|
},
|
|
{
|
|
"epoch": 0.03326904532304725,
|
|
"grad_norm": 12.180193901062012,
|
|
"learning_rate": 0.00019947000646444455,
|
|
"loss": 0.85135498046875,
|
|
"num_input_tokens_seen": 53140608,
|
|
"step": 34500,
|
|
"train_runtime": 72987.7556,
|
|
"train_tokens_per_second": 728.076
|
|
},
|
|
{
|
|
"epoch": 0.033317261330761815,
|
|
"grad_norm": 6.905839443206787,
|
|
"learning_rate": 0.0001994684471169649,
|
|
"loss": 0.9269057464599609,
|
|
"num_input_tokens_seen": 53182656,
|
|
"step": 34550,
|
|
"train_runtime": 73055.3287,
|
|
"train_tokens_per_second": 727.978
|
|
},
|
|
{
|
|
"epoch": 0.033365477338476376,
|
|
"grad_norm": 9.220721244812012,
|
|
"learning_rate": 0.00019946691674003664,
|
|
"loss": 0.8545632934570313,
|
|
"num_input_tokens_seen": 53224576,
|
|
"step": 34600,
|
|
"train_runtime": 73123.9278,
|
|
"train_tokens_per_second": 727.868
|
|
},
|
|
{
|
|
"epoch": 0.03341369334619094,
|
|
"grad_norm": 10.116294860839844,
|
|
"learning_rate": 0.00019946535286933056,
|
|
"loss": 0.7449246215820312,
|
|
"num_input_tokens_seen": 53267144,
|
|
"step": 34650,
|
|
"train_runtime": 73193.0484,
|
|
"train_tokens_per_second": 727.762
|
|
},
|
|
{
|
|
"epoch": 0.03346190935390549,
|
|
"grad_norm": 9.078619956970215,
|
|
"learning_rate": 0.0001994637867142202,
|
|
"loss": 0.8918234252929688,
|
|
"num_input_tokens_seen": 53306944,
|
|
"step": 34700,
|
|
"train_runtime": 73260.54,
|
|
"train_tokens_per_second": 727.635
|
|
},
|
|
{
|
|
"epoch": 0.033510125361620055,
|
|
"grad_norm": 10.744024276733398,
|
|
"learning_rate": 0.00019946221827474154,
|
|
"loss": 0.9490418243408203,
|
|
"num_input_tokens_seen": 53349456,
|
|
"step": 34750,
|
|
"train_runtime": 73329.5782,
|
|
"train_tokens_per_second": 727.53
|
|
},
|
|
{
|
|
"epoch": 0.03355834136933462,
|
|
"grad_norm": 12.48787784576416,
|
|
"learning_rate": 0.00019946064755093054,
|
|
"loss": 0.8914393615722657,
|
|
"num_input_tokens_seen": 53390352,
|
|
"step": 34800,
|
|
"train_runtime": 73397.4872,
|
|
"train_tokens_per_second": 727.414
|
|
},
|
|
{
|
|
"epoch": 0.03360655737704918,
|
|
"grad_norm": 4.956608295440674,
|
|
"learning_rate": 0.00019945907454282336,
|
|
"loss": 0.9437688446044922,
|
|
"num_input_tokens_seen": 53432584,
|
|
"step": 34850,
|
|
"train_runtime": 73466.9178,
|
|
"train_tokens_per_second": 727.301
|
|
},
|
|
{
|
|
"epoch": 0.03365477338476374,
|
|
"grad_norm": 8.336073875427246,
|
|
"learning_rate": 0.00019945749925045602,
|
|
"loss": 0.8311309051513672,
|
|
"num_input_tokens_seen": 53474368,
|
|
"step": 34900,
|
|
"train_runtime": 73535.908,
|
|
"train_tokens_per_second": 727.187
|
|
},
|
|
{
|
|
"epoch": 0.0337029893924783,
|
|
"grad_norm": 8.402314186096191,
|
|
"learning_rate": 0.0001994559216738648,
|
|
"loss": 0.9286373901367188,
|
|
"num_input_tokens_seen": 53514560,
|
|
"step": 34950,
|
|
"train_runtime": 73602.7061,
|
|
"train_tokens_per_second": 727.073
|
|
},
|
|
{
|
|
"epoch": 0.033751205400192864,
|
|
"grad_norm": 8.095053672790527,
|
|
"learning_rate": 0.00019945434181308587,
|
|
"loss": 1.0004069519042968,
|
|
"num_input_tokens_seen": 53556504,
|
|
"step": 35000,
|
|
"train_runtime": 73671.331,
|
|
"train_tokens_per_second": 726.965
|
|
},
|
|
{
|
|
"epoch": 0.033799421407907426,
|
|
"grad_norm": 7.826098918914795,
|
|
"learning_rate": 0.00019945275966815553,
|
|
"loss": 0.8564818572998046,
|
|
"num_input_tokens_seen": 53598120,
|
|
"step": 35050,
|
|
"train_runtime": 73739.7884,
|
|
"train_tokens_per_second": 726.855
|
|
},
|
|
{
|
|
"epoch": 0.03384763741562199,
|
|
"grad_norm": 8.090561866760254,
|
|
"learning_rate": 0.00019945117523911013,
|
|
"loss": 0.9408039855957031,
|
|
"num_input_tokens_seen": 53640328,
|
|
"step": 35100,
|
|
"train_runtime": 73808.8963,
|
|
"train_tokens_per_second": 726.746
|
|
},
|
|
{
|
|
"epoch": 0.03389585342333655,
|
|
"grad_norm": 8.881847381591797,
|
|
"learning_rate": 0.00019944958852598604,
|
|
"loss": 0.9128131866455078,
|
|
"num_input_tokens_seen": 53682704,
|
|
"step": 35150,
|
|
"train_runtime": 73878.1143,
|
|
"train_tokens_per_second": 726.639
|
|
},
|
|
{
|
|
"epoch": 0.03394406943105111,
|
|
"grad_norm": 11.952282905578613,
|
|
"learning_rate": 0.00019944799952881974,
|
|
"loss": 0.9303724670410156,
|
|
"num_input_tokens_seen": 53723232,
|
|
"step": 35200,
|
|
"train_runtime": 73945.4266,
|
|
"train_tokens_per_second": 726.525
|
|
},
|
|
{
|
|
"epoch": 0.033992285438765674,
|
|
"grad_norm": 5.894869804382324,
|
|
"learning_rate": 0.00019944640824764767,
|
|
"loss": 0.926352767944336,
|
|
"num_input_tokens_seen": 53764608,
|
|
"step": 35250,
|
|
"train_runtime": 74013.2209,
|
|
"train_tokens_per_second": 726.419
|
|
},
|
|
{
|
|
"epoch": 0.03404050144648023,
|
|
"grad_norm": 9.668693542480469,
|
|
"learning_rate": 0.0001994448146825064,
|
|
"loss": 0.8727204895019531,
|
|
"num_input_tokens_seen": 53806704,
|
|
"step": 35300,
|
|
"train_runtime": 74081.2164,
|
|
"train_tokens_per_second": 726.32
|
|
},
|
|
{
|
|
"epoch": 0.03408871745419479,
|
|
"grad_norm": 7.759515762329102,
|
|
"learning_rate": 0.00019944321883343254,
|
|
"loss": 0.9483051300048828,
|
|
"num_input_tokens_seen": 53848288,
|
|
"step": 35350,
|
|
"train_runtime": 74149.2379,
|
|
"train_tokens_per_second": 726.215
|
|
},
|
|
{
|
|
"epoch": 0.03413693346190935,
|
|
"grad_norm": 8.525580406188965,
|
|
"learning_rate": 0.00019944162070046272,
|
|
"loss": 0.8966922760009766,
|
|
"num_input_tokens_seen": 53889272,
|
|
"step": 35400,
|
|
"train_runtime": 74216.7047,
|
|
"train_tokens_per_second": 726.107
|
|
},
|
|
{
|
|
"epoch": 0.034185149469623914,
|
|
"grad_norm": 10.19591236114502,
|
|
"learning_rate": 0.0001994400202836337,
|
|
"loss": 0.8870204162597656,
|
|
"num_input_tokens_seen": 53928544,
|
|
"step": 35450,
|
|
"train_runtime": 74283.3063,
|
|
"train_tokens_per_second": 725.985
|
|
},
|
|
{
|
|
"epoch": 0.034233365477338476,
|
|
"grad_norm": 7.595946311950684,
|
|
"learning_rate": 0.00019943841758298213,
|
|
"loss": 0.9557320404052735,
|
|
"num_input_tokens_seen": 53969464,
|
|
"step": 35500,
|
|
"train_runtime": 74352.2,
|
|
"train_tokens_per_second": 725.862
|
|
},
|
|
{
|
|
"epoch": 0.03428158148505304,
|
|
"grad_norm": 10.300763130187988,
|
|
"learning_rate": 0.00019943681259854495,
|
|
"loss": 0.8614457702636719,
|
|
"num_input_tokens_seen": 54010968,
|
|
"step": 35550,
|
|
"train_runtime": 74420.945,
|
|
"train_tokens_per_second": 725.75
|
|
},
|
|
{
|
|
"epoch": 0.0343297974927676,
|
|
"grad_norm": 4.792901992797852,
|
|
"learning_rate": 0.0001994352053303589,
|
|
"loss": 0.9125040435791015,
|
|
"num_input_tokens_seen": 54053224,
|
|
"step": 35600,
|
|
"train_runtime": 74490.5992,
|
|
"train_tokens_per_second": 725.638
|
|
},
|
|
{
|
|
"epoch": 0.03437801350048216,
|
|
"grad_norm": 7.145506381988525,
|
|
"learning_rate": 0.00019943359577846096,
|
|
"loss": 0.9157393646240234,
|
|
"num_input_tokens_seen": 54095184,
|
|
"step": 35650,
|
|
"train_runtime": 74558.954,
|
|
"train_tokens_per_second": 725.536
|
|
},
|
|
{
|
|
"epoch": 0.03442622950819672,
|
|
"grad_norm": 5.266066074371338,
|
|
"learning_rate": 0.0001994319839428881,
|
|
"loss": 0.9737381744384765,
|
|
"num_input_tokens_seen": 54133520,
|
|
"step": 35700,
|
|
"train_runtime": 74624.0527,
|
|
"train_tokens_per_second": 725.417
|
|
},
|
|
{
|
|
"epoch": 0.034474445515911285,
|
|
"grad_norm": 6.260465145111084,
|
|
"learning_rate": 0.00019943036982367733,
|
|
"loss": 0.9106201171875,
|
|
"num_input_tokens_seen": 54175344,
|
|
"step": 35750,
|
|
"train_runtime": 74692.6319,
|
|
"train_tokens_per_second": 725.31
|
|
},
|
|
{
|
|
"epoch": 0.03452266152362585,
|
|
"grad_norm": 9.11707878112793,
|
|
"learning_rate": 0.00019942875342086568,
|
|
"loss": 0.9642995452880859,
|
|
"num_input_tokens_seen": 54216408,
|
|
"step": 35800,
|
|
"train_runtime": 74760.6469,
|
|
"train_tokens_per_second": 725.2
|
|
},
|
|
{
|
|
"epoch": 0.0345708775313404,
|
|
"grad_norm": 9.21313190460205,
|
|
"learning_rate": 0.00019942713473449034,
|
|
"loss": 1.018548583984375,
|
|
"num_input_tokens_seen": 54256328,
|
|
"step": 35850,
|
|
"train_runtime": 74826.4722,
|
|
"train_tokens_per_second": 725.095
|
|
},
|
|
{
|
|
"epoch": 0.034619093539054964,
|
|
"grad_norm": 4.38690710067749,
|
|
"learning_rate": 0.00019942551376458844,
|
|
"loss": 0.9565045928955078,
|
|
"num_input_tokens_seen": 54296240,
|
|
"step": 35900,
|
|
"train_runtime": 74892.4434,
|
|
"train_tokens_per_second": 724.99
|
|
},
|
|
{
|
|
"epoch": 0.034667309546769526,
|
|
"grad_norm": 8.213319778442383,
|
|
"learning_rate": 0.00019942389051119723,
|
|
"loss": 0.8856273651123047,
|
|
"num_input_tokens_seen": 54335248,
|
|
"step": 35950,
|
|
"train_runtime": 74958.301,
|
|
"train_tokens_per_second": 724.873
|
|
},
|
|
{
|
|
"epoch": 0.03471552555448409,
|
|
"grad_norm": 9.584681510925293,
|
|
"learning_rate": 0.00019942226497435403,
|
|
"loss": 0.9058517456054688,
|
|
"num_input_tokens_seen": 54378528,
|
|
"step": 36000,
|
|
"train_runtime": 75028.1543,
|
|
"train_tokens_per_second": 724.775
|
|
},
|
|
{
|
|
"epoch": 0.03476374156219865,
|
|
"grad_norm": 8.43655776977539,
|
|
"learning_rate": 0.00019942063715409604,
|
|
"loss": 0.9448054504394531,
|
|
"num_input_tokens_seen": 54420272,
|
|
"step": 36050,
|
|
"train_runtime": 75097.0494,
|
|
"train_tokens_per_second": 724.666
|
|
},
|
|
{
|
|
"epoch": 0.03481195756991321,
|
|
"grad_norm": 8.715587615966797,
|
|
"learning_rate": 0.00019941900705046077,
|
|
"loss": 0.9265594482421875,
|
|
"num_input_tokens_seen": 54460704,
|
|
"step": 36100,
|
|
"train_runtime": 75164.3354,
|
|
"train_tokens_per_second": 724.555
|
|
},
|
|
{
|
|
"epoch": 0.03486017357762777,
|
|
"grad_norm": 8.541111946105957,
|
|
"learning_rate": 0.0001994173746634856,
|
|
"loss": 0.9859822082519532,
|
|
"num_input_tokens_seen": 54499784,
|
|
"step": 36150,
|
|
"train_runtime": 75229.9541,
|
|
"train_tokens_per_second": 724.443
|
|
},
|
|
{
|
|
"epoch": 0.034908389585342335,
|
|
"grad_norm": 9.216029167175293,
|
|
"learning_rate": 0.0001994157399932081,
|
|
"loss": 0.9301145935058593,
|
|
"num_input_tokens_seen": 54540368,
|
|
"step": 36200,
|
|
"train_runtime": 75297.4956,
|
|
"train_tokens_per_second": 724.332
|
|
},
|
|
{
|
|
"epoch": 0.0349566055930569,
|
|
"grad_norm": 6.6781182289123535,
|
|
"learning_rate": 0.00019941410303966572,
|
|
"loss": 0.95708251953125,
|
|
"num_input_tokens_seen": 54581176,
|
|
"step": 36250,
|
|
"train_runtime": 75365.1386,
|
|
"train_tokens_per_second": 724.223
|
|
},
|
|
{
|
|
"epoch": 0.03500482160077146,
|
|
"grad_norm": 5.705411911010742,
|
|
"learning_rate": 0.00019941246380289612,
|
|
"loss": 0.9129982757568359,
|
|
"num_input_tokens_seen": 54621584,
|
|
"step": 36300,
|
|
"train_runtime": 75432.0746,
|
|
"train_tokens_per_second": 724.116
|
|
},
|
|
{
|
|
"epoch": 0.03505303760848602,
|
|
"grad_norm": 8.1051607131958,
|
|
"learning_rate": 0.00019941082228293685,
|
|
"loss": 1.025516891479492,
|
|
"num_input_tokens_seen": 54663600,
|
|
"step": 36350,
|
|
"train_runtime": 75499.1175,
|
|
"train_tokens_per_second": 724.03
|
|
},
|
|
{
|
|
"epoch": 0.035101253616200576,
|
|
"grad_norm": 9.990412712097168,
|
|
"learning_rate": 0.00019940917847982575,
|
|
"loss": 1.007061767578125,
|
|
"num_input_tokens_seen": 54702592,
|
|
"step": 36400,
|
|
"train_runtime": 75565.0724,
|
|
"train_tokens_per_second": 723.914
|
|
},
|
|
{
|
|
"epoch": 0.03514946962391514,
|
|
"grad_norm": 9.880223274230957,
|
|
"learning_rate": 0.00019940753239360047,
|
|
"loss": 0.9705640411376953,
|
|
"num_input_tokens_seen": 54742664,
|
|
"step": 36450,
|
|
"train_runtime": 75632.1304,
|
|
"train_tokens_per_second": 723.802
|
|
},
|
|
{
|
|
"epoch": 0.0351976856316297,
|
|
"grad_norm": 5.5787763595581055,
|
|
"learning_rate": 0.00019940588402429885,
|
|
"loss": 0.8898609924316406,
|
|
"num_input_tokens_seen": 54782168,
|
|
"step": 36500,
|
|
"train_runtime": 75699.5488,
|
|
"train_tokens_per_second": 723.679
|
|
},
|
|
{
|
|
"epoch": 0.03524590163934426,
|
|
"grad_norm": 11.467040061950684,
|
|
"learning_rate": 0.00019940423337195875,
|
|
"loss": 1.0300125885009765,
|
|
"num_input_tokens_seen": 54822152,
|
|
"step": 36550,
|
|
"train_runtime": 75765.7233,
|
|
"train_tokens_per_second": 723.575
|
|
},
|
|
{
|
|
"epoch": 0.03529411764705882,
|
|
"grad_norm": 7.9614667892456055,
|
|
"learning_rate": 0.00019940258043661807,
|
|
"loss": 1.0063140869140625,
|
|
"num_input_tokens_seen": 54861920,
|
|
"step": 36600,
|
|
"train_runtime": 75831.6794,
|
|
"train_tokens_per_second": 723.47
|
|
},
|
|
{
|
|
"epoch": 0.035342333654773385,
|
|
"grad_norm": 9.615310668945312,
|
|
"learning_rate": 0.0001994009252183148,
|
|
"loss": 0.9622119140625,
|
|
"num_input_tokens_seen": 54904480,
|
|
"step": 36650,
|
|
"train_runtime": 75900.6294,
|
|
"train_tokens_per_second": 723.373
|
|
},
|
|
{
|
|
"epoch": 0.03539054966248795,
|
|
"grad_norm": 8.228496551513672,
|
|
"learning_rate": 0.00019939930088948388,
|
|
"loss": 1.0318068695068359,
|
|
"num_input_tokens_seen": 54944424,
|
|
"step": 36700,
|
|
"train_runtime": 75966.7371,
|
|
"train_tokens_per_second": 723.27
|
|
},
|
|
{
|
|
"epoch": 0.03543876567020251,
|
|
"grad_norm": 9.001383781433105,
|
|
"learning_rate": 0.0001993976411510268,
|
|
"loss": 1.0507315826416015,
|
|
"num_input_tokens_seen": 54984760,
|
|
"step": 36750,
|
|
"train_runtime": 76034.4815,
|
|
"train_tokens_per_second": 723.156
|
|
},
|
|
{
|
|
"epoch": 0.03548698167791707,
|
|
"grad_norm": 7.743107318878174,
|
|
"learning_rate": 0.00019939597912972058,
|
|
"loss": 1.0455783081054688,
|
|
"num_input_tokens_seen": 55022960,
|
|
"step": 36800,
|
|
"train_runtime": 76100.195,
|
|
"train_tokens_per_second": 723.033
|
|
},
|
|
{
|
|
"epoch": 0.03553519768563163,
|
|
"grad_norm": 8.275322914123535,
|
|
"learning_rate": 0.00019939431482560337,
|
|
"loss": 1.0082305908203124,
|
|
"num_input_tokens_seen": 55064064,
|
|
"step": 36850,
|
|
"train_runtime": 76167.941,
|
|
"train_tokens_per_second": 722.93
|
|
},
|
|
{
|
|
"epoch": 0.035583413693346194,
|
|
"grad_norm": 5.54196834564209,
|
|
"learning_rate": 0.00019939264823871336,
|
|
"loss": 1.0395406341552735,
|
|
"num_input_tokens_seen": 55105368,
|
|
"step": 36900,
|
|
"train_runtime": 76235.1097,
|
|
"train_tokens_per_second": 722.835
|
|
},
|
|
{
|
|
"epoch": 0.03563162970106075,
|
|
"grad_norm": 5.599912643432617,
|
|
"learning_rate": 0.00019939097936908887,
|
|
"loss": 1.0073377990722656,
|
|
"num_input_tokens_seen": 55145976,
|
|
"step": 36950,
|
|
"train_runtime": 76301.675,
|
|
"train_tokens_per_second": 722.736
|
|
},
|
|
{
|
|
"epoch": 0.03567984570877531,
|
|
"grad_norm": 10.389533042907715,
|
|
"learning_rate": 0.0001993893082167682,
|
|
"loss": 1.0671810913085937,
|
|
"num_input_tokens_seen": 55184344,
|
|
"step": 37000,
|
|
"train_runtime": 76367.6072,
|
|
"train_tokens_per_second": 722.615
|
|
},
|
|
{
|
|
"epoch": 0.03572806171648987,
|
|
"grad_norm": 7.913829326629639,
|
|
"learning_rate": 0.00019938763478178975,
|
|
"loss": 1.070023193359375,
|
|
"num_input_tokens_seen": 55229232,
|
|
"step": 37050,
|
|
"train_runtime": 76438.6415,
|
|
"train_tokens_per_second": 722.53
|
|
},
|
|
{
|
|
"epoch": 0.035776277724204435,
|
|
"grad_norm": 5.575628280639648,
|
|
"learning_rate": 0.00019938595906419192,
|
|
"loss": 1.0720234680175782,
|
|
"num_input_tokens_seen": 55268712,
|
|
"step": 37100,
|
|
"train_runtime": 76503.6322,
|
|
"train_tokens_per_second": 722.433
|
|
},
|
|
{
|
|
"epoch": 0.035824493731919,
|
|
"grad_norm": 5.454362869262695,
|
|
"learning_rate": 0.00019938428106401322,
|
|
"loss": 1.1096266937255859,
|
|
"num_input_tokens_seen": 55307936,
|
|
"step": 37150,
|
|
"train_runtime": 76568.3625,
|
|
"train_tokens_per_second": 722.334
|
|
},
|
|
{
|
|
"epoch": 0.03587270973963356,
|
|
"grad_norm": 7.8070549964904785,
|
|
"learning_rate": 0.0001993826007812922,
|
|
"loss": 1.005312957763672,
|
|
"num_input_tokens_seen": 55347304,
|
|
"step": 37200,
|
|
"train_runtime": 76634.4814,
|
|
"train_tokens_per_second": 722.225
|
|
},
|
|
{
|
|
"epoch": 0.03592092574734812,
|
|
"grad_norm": 9.02029037475586,
|
|
"learning_rate": 0.00019938091821606745,
|
|
"loss": 1.0370655822753907,
|
|
"num_input_tokens_seen": 55386184,
|
|
"step": 37250,
|
|
"train_runtime": 76700.5161,
|
|
"train_tokens_per_second": 722.11
|
|
},
|
|
{
|
|
"epoch": 0.03596914175506268,
|
|
"grad_norm": 6.197319507598877,
|
|
"learning_rate": 0.0001993792333683776,
|
|
"loss": 1.027272720336914,
|
|
"num_input_tokens_seen": 55425984,
|
|
"step": 37300,
|
|
"train_runtime": 76766.4943,
|
|
"train_tokens_per_second": 722.007
|
|
},
|
|
{
|
|
"epoch": 0.036017357762777244,
|
|
"grad_norm": 6.124377727508545,
|
|
"learning_rate": 0.00019937754623826131,
|
|
"loss": 1.094661102294922,
|
|
"num_input_tokens_seen": 55466592,
|
|
"step": 37350,
|
|
"train_runtime": 76832.3118,
|
|
"train_tokens_per_second": 721.918
|
|
},
|
|
{
|
|
"epoch": 0.036065573770491806,
|
|
"grad_norm": 10.094806671142578,
|
|
"learning_rate": 0.00019937585682575738,
|
|
"loss": 1.1740863037109375,
|
|
"num_input_tokens_seen": 55503544,
|
|
"step": 37400,
|
|
"train_runtime": 76895.4812,
|
|
"train_tokens_per_second": 721.805
|
|
},
|
|
{
|
|
"epoch": 0.03611378977820637,
|
|
"grad_norm": 9.017782211303711,
|
|
"learning_rate": 0.00019937416513090463,
|
|
"loss": 0.9961177062988281,
|
|
"num_input_tokens_seen": 55543672,
|
|
"step": 37450,
|
|
"train_runtime": 76961.6144,
|
|
"train_tokens_per_second": 721.706
|
|
},
|
|
{
|
|
"epoch": 0.03616200578592092,
|
|
"grad_norm": 7.70034646987915,
|
|
"learning_rate": 0.00019937247115374185,
|
|
"loss": 1.0070616912841797,
|
|
"num_input_tokens_seen": 55583992,
|
|
"step": 37500,
|
|
"train_runtime": 77027.7262,
|
|
"train_tokens_per_second": 721.61
|
|
},
|
|
{
|
|
"epoch": 0.036210221793635484,
|
|
"grad_norm": 8.149955749511719,
|
|
"learning_rate": 0.00019937077489430796,
|
|
"loss": 1.0534967041015626,
|
|
"num_input_tokens_seen": 55624256,
|
|
"step": 37550,
|
|
"train_runtime": 77092.8922,
|
|
"train_tokens_per_second": 721.522
|
|
},
|
|
{
|
|
"epoch": 0.036258437801350046,
|
|
"grad_norm": 6.136117458343506,
|
|
"learning_rate": 0.00019936907635264195,
|
|
"loss": 1.0918058776855468,
|
|
"num_input_tokens_seen": 55662304,
|
|
"step": 37600,
|
|
"train_runtime": 77156.9747,
|
|
"train_tokens_per_second": 721.416
|
|
},
|
|
{
|
|
"epoch": 0.03630665380906461,
|
|
"grad_norm": 10.87959098815918,
|
|
"learning_rate": 0.0001993673755287828,
|
|
"loss": 1.0540807342529297,
|
|
"num_input_tokens_seen": 55701784,
|
|
"step": 37650,
|
|
"train_runtime": 77221.5895,
|
|
"train_tokens_per_second": 721.324
|
|
},
|
|
{
|
|
"epoch": 0.03635486981677917,
|
|
"grad_norm": 7.6970672607421875,
|
|
"learning_rate": 0.00019936567242276963,
|
|
"loss": 1.0389712524414063,
|
|
"num_input_tokens_seen": 55741640,
|
|
"step": 37700,
|
|
"train_runtime": 77287.033,
|
|
"train_tokens_per_second": 721.229
|
|
},
|
|
{
|
|
"epoch": 0.03640308582449373,
|
|
"grad_norm": 6.479321479797363,
|
|
"learning_rate": 0.00019936396703464145,
|
|
"loss": 0.9916974639892578,
|
|
"num_input_tokens_seen": 55780552,
|
|
"step": 37750,
|
|
"train_runtime": 77352.7304,
|
|
"train_tokens_per_second": 721.119
|
|
},
|
|
{
|
|
"epoch": 0.036451301832208294,
|
|
"grad_norm": 8.730469703674316,
|
|
"learning_rate": 0.00019936225936443753,
|
|
"loss": 1.1416515350341796,
|
|
"num_input_tokens_seen": 55821864,
|
|
"step": 37800,
|
|
"train_runtime": 77420.0544,
|
|
"train_tokens_per_second": 721.026
|
|
},
|
|
{
|
|
"epoch": 0.036499517839922856,
|
|
"grad_norm": 7.20620059967041,
|
|
"learning_rate": 0.00019936054941219701,
|
|
"loss": 1.118257064819336,
|
|
"num_input_tokens_seen": 55860296,
|
|
"step": 37850,
|
|
"train_runtime": 77484.7507,
|
|
"train_tokens_per_second": 720.92
|
|
},
|
|
{
|
|
"epoch": 0.03654773384763742,
|
|
"grad_norm": 6.608085632324219,
|
|
"learning_rate": 0.0001993588371779592,
|
|
"loss": 1.0373649597167969,
|
|
"num_input_tokens_seen": 55899376,
|
|
"step": 37900,
|
|
"train_runtime": 77549.6021,
|
|
"train_tokens_per_second": 720.821
|
|
},
|
|
{
|
|
"epoch": 0.03659594985535198,
|
|
"grad_norm": 5.752274513244629,
|
|
"learning_rate": 0.00019935712266176345,
|
|
"loss": 1.0205484008789063,
|
|
"num_input_tokens_seen": 55941040,
|
|
"step": 37950,
|
|
"train_runtime": 77617.8577,
|
|
"train_tokens_per_second": 720.724
|
|
},
|
|
{
|
|
"epoch": 0.03664416586306654,
|
|
"grad_norm": 4.523128509521484,
|
|
"learning_rate": 0.0001993554058636491,
|
|
"loss": 1.082652587890625,
|
|
"num_input_tokens_seen": 55981256,
|
|
"step": 38000,
|
|
"train_runtime": 77685.7806,
|
|
"train_tokens_per_second": 720.611
|
|
},
|
|
{
|
|
"epoch": 0.036692381870781096,
|
|
"grad_norm": 5.4479169845581055,
|
|
"learning_rate": 0.00019935368678365557,
|
|
"loss": 1.0458312225341797,
|
|
"num_input_tokens_seen": 56022312,
|
|
"step": 38050,
|
|
"train_runtime": 77753.1095,
|
|
"train_tokens_per_second": 720.515
|
|
},
|
|
{
|
|
"epoch": 0.03674059787849566,
|
|
"grad_norm": 7.85593318939209,
|
|
"learning_rate": 0.00019935196542182238,
|
|
"loss": 1.0541954803466798,
|
|
"num_input_tokens_seen": 56063544,
|
|
"step": 38100,
|
|
"train_runtime": 77820.7908,
|
|
"train_tokens_per_second": 720.419
|
|
},
|
|
{
|
|
"epoch": 0.03678881388621022,
|
|
"grad_norm": 8.603913307189941,
|
|
"learning_rate": 0.00019935024177818907,
|
|
"loss": 1.0316373443603515,
|
|
"num_input_tokens_seen": 56103376,
|
|
"step": 38150,
|
|
"train_runtime": 77887.4833,
|
|
"train_tokens_per_second": 720.313
|
|
},
|
|
{
|
|
"epoch": 0.03683702989392478,
|
|
"grad_norm": 8.455739974975586,
|
|
"learning_rate": 0.00019934851585279518,
|
|
"loss": 1.0971241760253907,
|
|
"num_input_tokens_seen": 56141944,
|
|
"step": 38200,
|
|
"train_runtime": 77952.0418,
|
|
"train_tokens_per_second": 720.211
|
|
},
|
|
{
|
|
"epoch": 0.036885245901639344,
|
|
"grad_norm": 8.330069541931152,
|
|
"learning_rate": 0.00019934678764568035,
|
|
"loss": 1.0572106170654296,
|
|
"num_input_tokens_seen": 56181096,
|
|
"step": 38250,
|
|
"train_runtime": 78017.4355,
|
|
"train_tokens_per_second": 720.109
|
|
},
|
|
{
|
|
"epoch": 0.036933461909353905,
|
|
"grad_norm": 7.127686023712158,
|
|
"learning_rate": 0.0001993450571568843,
|
|
"loss": 0.9877079010009766,
|
|
"num_input_tokens_seen": 56221240,
|
|
"step": 38300,
|
|
"train_runtime": 78084.1365,
|
|
"train_tokens_per_second": 720.008
|
|
},
|
|
{
|
|
"epoch": 0.03698167791706847,
|
|
"grad_norm": 5.290924549102783,
|
|
"learning_rate": 0.0001993433243864468,
|
|
"loss": 1.1101638793945312,
|
|
"num_input_tokens_seen": 56261200,
|
|
"step": 38350,
|
|
"train_runtime": 78149.6973,
|
|
"train_tokens_per_second": 719.916
|
|
},
|
|
{
|
|
"epoch": 0.03702989392478303,
|
|
"grad_norm": 7.5111775398254395,
|
|
"learning_rate": 0.0001993415893344076,
|
|
"loss": 1.1674281311035157,
|
|
"num_input_tokens_seen": 56300016,
|
|
"step": 38400,
|
|
"train_runtime": 78214.8873,
|
|
"train_tokens_per_second": 719.812
|
|
},
|
|
{
|
|
"epoch": 0.03707810993249759,
|
|
"grad_norm": 8.958099365234375,
|
|
"learning_rate": 0.00019933985200080653,
|
|
"loss": 1.068874282836914,
|
|
"num_input_tokens_seen": 56340496,
|
|
"step": 38450,
|
|
"train_runtime": 78281.1426,
|
|
"train_tokens_per_second": 719.72
|
|
},
|
|
{
|
|
"epoch": 0.03712632594021215,
|
|
"grad_norm": 9.725455284118652,
|
|
"learning_rate": 0.00019933811238568354,
|
|
"loss": 1.0631390380859376,
|
|
"num_input_tokens_seen": 56378512,
|
|
"step": 38500,
|
|
"train_runtime": 78345.6067,
|
|
"train_tokens_per_second": 719.613
|
|
},
|
|
{
|
|
"epoch": 0.037174541947926715,
|
|
"grad_norm": 8.61083984375,
|
|
"learning_rate": 0.0001993363704890786,
|
|
"loss": 1.0482708740234374,
|
|
"num_input_tokens_seen": 56416384,
|
|
"step": 38550,
|
|
"train_runtime": 78409.8785,
|
|
"train_tokens_per_second": 719.506
|
|
},
|
|
{
|
|
"epoch": 0.03722275795564127,
|
|
"grad_norm": 8.267424583435059,
|
|
"learning_rate": 0.00019933462631103161,
|
|
"loss": 1.158176803588867,
|
|
"num_input_tokens_seen": 56453784,
|
|
"step": 38600,
|
|
"train_runtime": 78473.57,
|
|
"train_tokens_per_second": 719.399
|
|
},
|
|
{
|
|
"epoch": 0.03727097396335583,
|
|
"grad_norm": 6.331938743591309,
|
|
"learning_rate": 0.00019933287985158277,
|
|
"loss": 1.1777459716796874,
|
|
"num_input_tokens_seen": 56492576,
|
|
"step": 38650,
|
|
"train_runtime": 78538.998,
|
|
"train_tokens_per_second": 719.293
|
|
},
|
|
{
|
|
"epoch": 0.03731918997107039,
|
|
"grad_norm": 6.392196178436279,
|
|
"learning_rate": 0.00019933113111077208,
|
|
"loss": 1.06009765625,
|
|
"num_input_tokens_seen": 56530600,
|
|
"step": 38700,
|
|
"train_runtime": 78603.4803,
|
|
"train_tokens_per_second": 719.187
|
|
},
|
|
{
|
|
"epoch": 0.037367405978784955,
|
|
"grad_norm": 8.4070463180542,
|
|
"learning_rate": 0.00019932938008863978,
|
|
"loss": 1.0497118377685546,
|
|
"num_input_tokens_seen": 56568584,
|
|
"step": 38750,
|
|
"train_runtime": 78667.4708,
|
|
"train_tokens_per_second": 719.085
|
|
},
|
|
{
|
|
"epoch": 0.03741562198649952,
|
|
"grad_norm": 7.420001983642578,
|
|
"learning_rate": 0.00019932762678522597,
|
|
"loss": 1.1027589416503907,
|
|
"num_input_tokens_seen": 56606728,
|
|
"step": 38800,
|
|
"train_runtime": 78730.3661,
|
|
"train_tokens_per_second": 718.995
|
|
},
|
|
{
|
|
"epoch": 0.03746383799421408,
|
|
"grad_norm": 8.371572494506836,
|
|
"learning_rate": 0.0001993259063346201,
|
|
"loss": 1.1156404876708985,
|
|
"num_input_tokens_seen": 56645888,
|
|
"step": 38850,
|
|
"train_runtime": 78795.6758,
|
|
"train_tokens_per_second": 718.896
|
|
},
|
|
{
|
|
"epoch": 0.03751205400192864,
|
|
"grad_norm": 8.0657377243042,
|
|
"learning_rate": 0.00019932414851438795,
|
|
"loss": 0.9725601959228516,
|
|
"num_input_tokens_seen": 56686016,
|
|
"step": 38900,
|
|
"train_runtime": 78861.9359,
|
|
"train_tokens_per_second": 718.801
|
|
},
|
|
{
|
|
"epoch": 0.0375602700096432,
|
|
"grad_norm": 6.979188919067383,
|
|
"learning_rate": 0.00019932238841299454,
|
|
"loss": 1.1209898376464844,
|
|
"num_input_tokens_seen": 56723656,
|
|
"step": 38950,
|
|
"train_runtime": 78925.771,
|
|
"train_tokens_per_second": 718.696
|
|
},
|
|
{
|
|
"epoch": 0.037608486017357765,
|
|
"grad_norm": 6.895879745483398,
|
|
"learning_rate": 0.00019932062603048026,
|
|
"loss": 1.1033724975585937,
|
|
"num_input_tokens_seen": 56761520,
|
|
"step": 39000,
|
|
"train_runtime": 78989.8103,
|
|
"train_tokens_per_second": 718.593
|
|
},
|
|
{
|
|
"epoch": 0.037656702025072326,
|
|
"grad_norm": 11.55008316040039,
|
|
"learning_rate": 0.0001993188613668856,
|
|
"loss": 1.0701551055908203,
|
|
"num_input_tokens_seen": 56802056,
|
|
"step": 39050,
|
|
"train_runtime": 79056.2392,
|
|
"train_tokens_per_second": 718.502
|
|
},
|
|
{
|
|
"epoch": 0.03770491803278689,
|
|
"grad_norm": 7.036686897277832,
|
|
"learning_rate": 0.0001993170944222511,
|
|
"loss": 1.159585189819336,
|
|
"num_input_tokens_seen": 56840784,
|
|
"step": 39100,
|
|
"train_runtime": 79120.3112,
|
|
"train_tokens_per_second": 718.41
|
|
},
|
|
{
|
|
"epoch": 0.03775313404050144,
|
|
"grad_norm": 7.056464195251465,
|
|
"learning_rate": 0.00019931532519661734,
|
|
"loss": 1.06703369140625,
|
|
"num_input_tokens_seen": 56880552,
|
|
"step": 39150,
|
|
"train_runtime": 79185.5259,
|
|
"train_tokens_per_second": 718.32
|
|
},
|
|
{
|
|
"epoch": 0.037801350048216005,
|
|
"grad_norm": 9.791584968566895,
|
|
"learning_rate": 0.00019931355369002493,
|
|
"loss": 1.0790948486328125,
|
|
"num_input_tokens_seen": 56919576,
|
|
"step": 39200,
|
|
"train_runtime": 79250.2337,
|
|
"train_tokens_per_second": 718.226
|
|
},
|
|
{
|
|
"epoch": 0.03784956605593057,
|
|
"grad_norm": 9.282594680786133,
|
|
"learning_rate": 0.0001993117799025146,
|
|
"loss": 1.0481141662597657,
|
|
"num_input_tokens_seen": 56957568,
|
|
"step": 39250,
|
|
"train_runtime": 79314.7788,
|
|
"train_tokens_per_second": 718.12
|
|
},
|
|
{
|
|
"epoch": 0.03789778206364513,
|
|
"grad_norm": 7.512643814086914,
|
|
"learning_rate": 0.00019931000383412704,
|
|
"loss": 1.0943451690673829,
|
|
"num_input_tokens_seen": 56996192,
|
|
"step": 39300,
|
|
"train_runtime": 79379.9566,
|
|
"train_tokens_per_second": 718.017
|
|
},
|
|
{
|
|
"epoch": 0.03794599807135969,
|
|
"grad_norm": 6.22097635269165,
|
|
"learning_rate": 0.00019930822548490303,
|
|
"loss": 1.0360592651367186,
|
|
"num_input_tokens_seen": 57035752,
|
|
"step": 39350,
|
|
"train_runtime": 79446.0538,
|
|
"train_tokens_per_second": 717.918
|
|
},
|
|
{
|
|
"epoch": 0.03799421407907425,
|
|
"grad_norm": 7.684467315673828,
|
|
"learning_rate": 0.00019930644485488349,
|
|
"loss": 1.0928297424316407,
|
|
"num_input_tokens_seen": 57075232,
|
|
"step": 39400,
|
|
"train_runtime": 79510.5423,
|
|
"train_tokens_per_second": 717.832
|
|
},
|
|
{
|
|
"epoch": 0.038042430086788814,
|
|
"grad_norm": 6.879452228546143,
|
|
"learning_rate": 0.00019930466194410923,
|
|
"loss": 1.0757313537597657,
|
|
"num_input_tokens_seen": 57114928,
|
|
"step": 39450,
|
|
"train_runtime": 79576.0524,
|
|
"train_tokens_per_second": 717.74
|
|
},
|
|
{
|
|
"epoch": 0.038090646094503376,
|
|
"grad_norm": 7.190834045410156,
|
|
"learning_rate": 0.00019930287675262127,
|
|
"loss": 1.1118821716308593,
|
|
"num_input_tokens_seen": 57153344,
|
|
"step": 39500,
|
|
"train_runtime": 79640.8262,
|
|
"train_tokens_per_second": 717.639
|
|
},
|
|
{
|
|
"epoch": 0.03813886210221794,
|
|
"grad_norm": 6.4658894538879395,
|
|
"learning_rate": 0.00019930108928046058,
|
|
"loss": 1.099799270629883,
|
|
"num_input_tokens_seen": 57192712,
|
|
"step": 39550,
|
|
"train_runtime": 79706.5674,
|
|
"train_tokens_per_second": 717.541
|
|
},
|
|
{
|
|
"epoch": 0.0381870781099325,
|
|
"grad_norm": 5.987537384033203,
|
|
"learning_rate": 0.00019929929952766816,
|
|
"loss": 1.0889903259277345,
|
|
"num_input_tokens_seen": 57231136,
|
|
"step": 39600,
|
|
"train_runtime": 79769.6721,
|
|
"train_tokens_per_second": 717.455
|
|
},
|
|
{
|
|
"epoch": 0.03823529411764706,
|
|
"grad_norm": 5.608473777770996,
|
|
"learning_rate": 0.00019929750749428523,
|
|
"loss": 1.1137923431396484,
|
|
"num_input_tokens_seen": 57269048,
|
|
"step": 39650,
|
|
"train_runtime": 79833.0772,
|
|
"train_tokens_per_second": 717.36
|
|
},
|
|
{
|
|
"epoch": 0.03828351012536162,
|
|
"grad_norm": 7.051680564880371,
|
|
"learning_rate": 0.00019929571318035282,
|
|
"loss": 1.128105697631836,
|
|
"num_input_tokens_seen": 57306056,
|
|
"step": 39700,
|
|
"train_runtime": 79895.6542,
|
|
"train_tokens_per_second": 717.261
|
|
},
|
|
{
|
|
"epoch": 0.03833172613307618,
|
|
"grad_norm": 9.6116943359375,
|
|
"learning_rate": 0.00019929391658591225,
|
|
"loss": 1.0777400207519532,
|
|
"num_input_tokens_seen": 57343120,
|
|
"step": 39750,
|
|
"train_runtime": 79958.4021,
|
|
"train_tokens_per_second": 717.162
|
|
},
|
|
{
|
|
"epoch": 0.03837994214079074,
|
|
"grad_norm": 8.40839672088623,
|
|
"learning_rate": 0.0001992921177110047,
|
|
"loss": 1.087022476196289,
|
|
"num_input_tokens_seen": 57381296,
|
|
"step": 39800,
|
|
"train_runtime": 80022.0653,
|
|
"train_tokens_per_second": 717.068
|
|
},
|
|
{
|
|
"epoch": 0.0384281581485053,
|
|
"grad_norm": 7.665341377258301,
|
|
"learning_rate": 0.00019929031655567157,
|
|
"loss": 1.1043975830078125,
|
|
"num_input_tokens_seen": 57418712,
|
|
"step": 39850,
|
|
"train_runtime": 80086.2917,
|
|
"train_tokens_per_second": 716.961
|
|
},
|
|
{
|
|
"epoch": 0.038476374156219864,
|
|
"grad_norm": 6.155496597290039,
|
|
"learning_rate": 0.00019928851311995413,
|
|
"loss": 1.1553018188476563,
|
|
"num_input_tokens_seen": 57457616,
|
|
"step": 39900,
|
|
"train_runtime": 80150.7733,
|
|
"train_tokens_per_second": 716.869
|
|
},
|
|
{
|
|
"epoch": 0.038524590163934426,
|
|
"grad_norm": 8.420520782470703,
|
|
"learning_rate": 0.00019928670740389386,
|
|
"loss": 1.1018820953369142,
|
|
"num_input_tokens_seen": 57496520,
|
|
"step": 39950,
|
|
"train_runtime": 80214.8797,
|
|
"train_tokens_per_second": 716.781
|
|
},
|
|
{
|
|
"epoch": 0.03857280617164899,
|
|
"grad_norm": 7.6095170974731445,
|
|
"learning_rate": 0.00019928489940753221,
|
|
"loss": 1.1415931701660156,
|
|
"num_input_tokens_seen": 57534296,
|
|
"step": 40000,
|
|
"train_runtime": 80278.7126,
|
|
"train_tokens_per_second": 716.682
|
|
},
|
|
{
|
|
"epoch": 0.03862102217936355,
|
|
"grad_norm": 6.42004919052124,
|
|
"learning_rate": 0.00019928308913091068,
|
|
"loss": 1.0603173828125,
|
|
"num_input_tokens_seen": 57574304,
|
|
"step": 40050,
|
|
"train_runtime": 80344.0848,
|
|
"train_tokens_per_second": 716.597
|
|
},
|
|
{
|
|
"epoch": 0.03866923818707811,
|
|
"grad_norm": 8.565956115722656,
|
|
"learning_rate": 0.00019928127657407093,
|
|
"loss": 1.0135743713378906,
|
|
"num_input_tokens_seen": 57615784,
|
|
"step": 40100,
|
|
"train_runtime": 80410.0168,
|
|
"train_tokens_per_second": 716.525
|
|
},
|
|
{
|
|
"epoch": 0.03871745419479267,
|
|
"grad_norm": 6.1595869064331055,
|
|
"learning_rate": 0.0001992794617370545,
|
|
"loss": 1.0793157196044922,
|
|
"num_input_tokens_seen": 57654456,
|
|
"step": 40150,
|
|
"train_runtime": 80473.9483,
|
|
"train_tokens_per_second": 716.436
|
|
},
|
|
{
|
|
"epoch": 0.038765670202507235,
|
|
"grad_norm": 5.983520984649658,
|
|
"learning_rate": 0.0001992776446199031,
|
|
"loss": 1.1270452117919922,
|
|
"num_input_tokens_seen": 57693496,
|
|
"step": 40200,
|
|
"train_runtime": 80539.3028,
|
|
"train_tokens_per_second": 716.34
|
|
},
|
|
{
|
|
"epoch": 0.03881388621022179,
|
|
"grad_norm": 6.291006565093994,
|
|
"learning_rate": 0.0001992758252226585,
|
|
"loss": 1.0893585205078125,
|
|
"num_input_tokens_seen": 57733984,
|
|
"step": 40250,
|
|
"train_runtime": 80604.7675,
|
|
"train_tokens_per_second": 716.26
|
|
},
|
|
{
|
|
"epoch": 0.03886210221793635,
|
|
"grad_norm": 5.44956636428833,
|
|
"learning_rate": 0.00019927400354536243,
|
|
"loss": 1.1210441589355469,
|
|
"num_input_tokens_seen": 57772056,
|
|
"step": 40300,
|
|
"train_runtime": 80669.0724,
|
|
"train_tokens_per_second": 716.161
|
|
},
|
|
{
|
|
"epoch": 0.038910318225650914,
|
|
"grad_norm": 6.8446831703186035,
|
|
"learning_rate": 0.00019927217958805679,
|
|
"loss": 1.13781494140625,
|
|
"num_input_tokens_seen": 57811032,
|
|
"step": 40350,
|
|
"train_runtime": 80733.7134,
|
|
"train_tokens_per_second": 716.071
|
|
},
|
|
{
|
|
"epoch": 0.038958534233365476,
|
|
"grad_norm": 7.003830432891846,
|
|
"learning_rate": 0.00019927035335078337,
|
|
"loss": 1.1172571563720703,
|
|
"num_input_tokens_seen": 57850400,
|
|
"step": 40400,
|
|
"train_runtime": 80798.2401,
|
|
"train_tokens_per_second": 715.986
|
|
},
|
|
{
|
|
"epoch": 0.03900675024108004,
|
|
"grad_norm": 6.489707946777344,
|
|
"learning_rate": 0.0001992685248335842,
|
|
"loss": 1.0948475646972655,
|
|
"num_input_tokens_seen": 57888776,
|
|
"step": 40450,
|
|
"train_runtime": 80862.1991,
|
|
"train_tokens_per_second": 715.894
|
|
},
|
|
{
|
|
"epoch": 0.0390549662487946,
|
|
"grad_norm": 5.1625590324401855,
|
|
"learning_rate": 0.00019926669403650128,
|
|
"loss": 1.179251937866211,
|
|
"num_input_tokens_seen": 57928472,
|
|
"step": 40500,
|
|
"train_runtime": 80926.4579,
|
|
"train_tokens_per_second": 715.816
|
|
},
|
|
{
|
|
"epoch": 0.03910318225650916,
|
|
"grad_norm": 5.90469217300415,
|
|
"learning_rate": 0.0001992648609595766,
|
|
"loss": 1.0675597381591797,
|
|
"num_input_tokens_seen": 57967168,
|
|
"step": 40550,
|
|
"train_runtime": 80990.7824,
|
|
"train_tokens_per_second": 715.725
|
|
},
|
|
{
|
|
"epoch": 0.03915139826422372,
|
|
"grad_norm": 7.586650371551514,
|
|
"learning_rate": 0.0001992630256028523,
|
|
"loss": 1.1270746612548828,
|
|
"num_input_tokens_seen": 58005576,
|
|
"step": 40600,
|
|
"train_runtime": 81055.4819,
|
|
"train_tokens_per_second": 715.628
|
|
},
|
|
{
|
|
"epoch": 0.039199614271938285,
|
|
"grad_norm": 6.915133953094482,
|
|
"learning_rate": 0.00019926118796637052,
|
|
"loss": 1.0857196044921875,
|
|
"num_input_tokens_seen": 58043536,
|
|
"step": 40650,
|
|
"train_runtime": 81119.0945,
|
|
"train_tokens_per_second": 715.535
|
|
},
|
|
{
|
|
"epoch": 0.03924783027965285,
|
|
"grad_norm": 5.938986301422119,
|
|
"learning_rate": 0.00019925934805017348,
|
|
"loss": 1.0953945159912108,
|
|
"num_input_tokens_seen": 58082896,
|
|
"step": 40700,
|
|
"train_runtime": 81183.2126,
|
|
"train_tokens_per_second": 715.455
|
|
},
|
|
{
|
|
"epoch": 0.03929604628736741,
|
|
"grad_norm": 7.874338150024414,
|
|
"learning_rate": 0.0001992575058543034,
|
|
"loss": 1.0851197814941407,
|
|
"num_input_tokens_seen": 58121320,
|
|
"step": 40750,
|
|
"train_runtime": 81248.2271,
|
|
"train_tokens_per_second": 715.355
|
|
},
|
|
{
|
|
"epoch": 0.03934426229508197,
|
|
"grad_norm": 7.433464527130127,
|
|
"learning_rate": 0.00019925566137880262,
|
|
"loss": 1.1037235260009766,
|
|
"num_input_tokens_seen": 58160864,
|
|
"step": 40800,
|
|
"train_runtime": 81315.3562,
|
|
"train_tokens_per_second": 715.251
|
|
},
|
|
{
|
|
"epoch": 0.039392478302796526,
|
|
"grad_norm": 5.255838394165039,
|
|
"learning_rate": 0.00019925381462371352,
|
|
"loss": 1.0976487731933593,
|
|
"num_input_tokens_seen": 58199328,
|
|
"step": 40850,
|
|
"train_runtime": 81379.9515,
|
|
"train_tokens_per_second": 715.156
|
|
},
|
|
{
|
|
"epoch": 0.03944069431051109,
|
|
"grad_norm": 5.259512901306152,
|
|
"learning_rate": 0.00019925196558907846,
|
|
"loss": 1.1118035888671876,
|
|
"num_input_tokens_seen": 58238720,
|
|
"step": 40900,
|
|
"train_runtime": 81444.825,
|
|
"train_tokens_per_second": 715.07
|
|
},
|
|
{
|
|
"epoch": 0.03948891031822565,
|
|
"grad_norm": 7.39116096496582,
|
|
"learning_rate": 0.00019925011427493995,
|
|
"loss": 1.1459592437744142,
|
|
"num_input_tokens_seen": 58276480,
|
|
"step": 40950,
|
|
"train_runtime": 81508.4828,
|
|
"train_tokens_per_second": 714.974
|
|
},
|
|
{
|
|
"epoch": 0.03953712632594021,
|
|
"grad_norm": 8.527722358703613,
|
|
"learning_rate": 0.0001992482606813405,
|
|
"loss": 1.1741757202148437,
|
|
"num_input_tokens_seen": 58316720,
|
|
"step": 41000,
|
|
"train_runtime": 81573.5862,
|
|
"train_tokens_per_second": 714.897
|
|
},
|
|
{
|
|
"epoch": 0.03958534233365477,
|
|
"grad_norm": 7.229602336883545,
|
|
"learning_rate": 0.00019924640480832264,
|
|
"loss": 1.1340157318115234,
|
|
"num_input_tokens_seen": 58355864,
|
|
"step": 41050,
|
|
"train_runtime": 81637.039,
|
|
"train_tokens_per_second": 714.821
|
|
},
|
|
{
|
|
"epoch": 0.039633558341369335,
|
|
"grad_norm": 5.4476141929626465,
|
|
"learning_rate": 0.00019924454665592905,
|
|
"loss": 1.139698715209961,
|
|
"num_input_tokens_seen": 58394864,
|
|
"step": 41100,
|
|
"train_runtime": 81701.1589,
|
|
"train_tokens_per_second": 714.737
|
|
},
|
|
{
|
|
"epoch": 0.0396817743490839,
|
|
"grad_norm": 7.265683650970459,
|
|
"learning_rate": 0.0001992426862242024,
|
|
"loss": 1.1192784118652344,
|
|
"num_input_tokens_seen": 58434960,
|
|
"step": 41150,
|
|
"train_runtime": 81764.6532,
|
|
"train_tokens_per_second": 714.673
|
|
},
|
|
{
|
|
"epoch": 0.03972999035679846,
|
|
"grad_norm": 6.422770023345947,
|
|
"learning_rate": 0.00019924082351318537,
|
|
"loss": 1.1440596771240235,
|
|
"num_input_tokens_seen": 58473936,
|
|
"step": 41200,
|
|
"train_runtime": 81828.3039,
|
|
"train_tokens_per_second": 714.593
|
|
},
|
|
{
|
|
"epoch": 0.03977820636451302,
|
|
"grad_norm": 5.489058017730713,
|
|
"learning_rate": 0.0001992389585229208,
|
|
"loss": 1.116007308959961,
|
|
"num_input_tokens_seen": 58512384,
|
|
"step": 41250,
|
|
"train_runtime": 81892.032,
|
|
"train_tokens_per_second": 714.506
|
|
},
|
|
{
|
|
"epoch": 0.03982642237222758,
|
|
"grad_norm": 6.675996780395508,
|
|
"learning_rate": 0.0001992370912534515,
|
|
"loss": 1.0990009307861328,
|
|
"num_input_tokens_seen": 58553096,
|
|
"step": 41300,
|
|
"train_runtime": 81957.5782,
|
|
"train_tokens_per_second": 714.432
|
|
},
|
|
{
|
|
"epoch": 0.039874638379942144,
|
|
"grad_norm": 11.782538414001465,
|
|
"learning_rate": 0.00019923522170482033,
|
|
"loss": 1.063866424560547,
|
|
"num_input_tokens_seen": 58590944,
|
|
"step": 41350,
|
|
"train_runtime": 82020.7268,
|
|
"train_tokens_per_second": 714.343
|
|
},
|
|
{
|
|
"epoch": 0.0399228543876567,
|
|
"grad_norm": 7.376985549926758,
|
|
"learning_rate": 0.00019923334987707026,
|
|
"loss": 1.1383811950683593,
|
|
"num_input_tokens_seen": 58629896,
|
|
"step": 41400,
|
|
"train_runtime": 82085.3836,
|
|
"train_tokens_per_second": 714.255
|
|
},
|
|
{
|
|
"epoch": 0.03997107039537126,
|
|
"grad_norm": 6.372163772583008,
|
|
"learning_rate": 0.0001992314757702443,
|
|
"loss": 1.1082178497314452,
|
|
"num_input_tokens_seen": 58668016,
|
|
"step": 41450,
|
|
"train_runtime": 82148.8867,
|
|
"train_tokens_per_second": 714.167
|
|
},
|
|
{
|
|
"epoch": 0.04001928640308582,
|
|
"grad_norm": 5.957989692687988,
|
|
"learning_rate": 0.0001992295993843854,
|
|
"loss": 1.0864712524414062,
|
|
"num_input_tokens_seen": 58708088,
|
|
"step": 41500,
|
|
"train_runtime": 82213.3179,
|
|
"train_tokens_per_second": 714.095
|
|
},
|
|
{
|
|
"epoch": 0.040067502410800385,
|
|
"grad_norm": 7.354833602905273,
|
|
"learning_rate": 0.00019922772071953674,
|
|
"loss": 1.1282964324951172,
|
|
"num_input_tokens_seen": 58746368,
|
|
"step": 41550,
|
|
"train_runtime": 82276.783,
|
|
"train_tokens_per_second": 714.009
|
|
},
|
|
{
|
|
"epoch": 0.040115718418514947,
|
|
"grad_norm": 5.82360315322876,
|
|
"learning_rate": 0.00019922583977574146,
|
|
"loss": 1.1430227661132812,
|
|
"num_input_tokens_seen": 58785168,
|
|
"step": 41600,
|
|
"train_runtime": 82340.0884,
|
|
"train_tokens_per_second": 713.931
|
|
},
|
|
{
|
|
"epoch": 0.04016393442622951,
|
|
"grad_norm": 5.404848098754883,
|
|
"learning_rate": 0.00019922395655304272,
|
|
"loss": 1.1054490661621095,
|
|
"num_input_tokens_seen": 58822928,
|
|
"step": 41650,
|
|
"train_runtime": 82403.0751,
|
|
"train_tokens_per_second": 713.844
|
|
},
|
|
{
|
|
"epoch": 0.04021215043394407,
|
|
"grad_norm": 6.93833065032959,
|
|
"learning_rate": 0.00019922207105148383,
|
|
"loss": 1.0978862762451171,
|
|
"num_input_tokens_seen": 58860272,
|
|
"step": 41700,
|
|
"train_runtime": 82465.6534,
|
|
"train_tokens_per_second": 713.755
|
|
},
|
|
{
|
|
"epoch": 0.04026036644165863,
|
|
"grad_norm": 11.568885803222656,
|
|
"learning_rate": 0.00019922018327110804,
|
|
"loss": 1.1668070983886718,
|
|
"num_input_tokens_seen": 58898232,
|
|
"step": 41750,
|
|
"train_runtime": 82529.2272,
|
|
"train_tokens_per_second": 713.665
|
|
},
|
|
{
|
|
"epoch": 0.040308582449373194,
|
|
"grad_norm": 5.938446998596191,
|
|
"learning_rate": 0.0001992182932119587,
|
|
"loss": 1.1857054901123047,
|
|
"num_input_tokens_seen": 58936576,
|
|
"step": 41800,
|
|
"train_runtime": 82593.5368,
|
|
"train_tokens_per_second": 713.574
|
|
},
|
|
{
|
|
"epoch": 0.040356798457087756,
|
|
"grad_norm": 6.6398444175720215,
|
|
"learning_rate": 0.00019921640087407924,
|
|
"loss": 1.1293959045410156,
|
|
"num_input_tokens_seen": 58975288,
|
|
"step": 41850,
|
|
"train_runtime": 82657.4352,
|
|
"train_tokens_per_second": 713.49
|
|
},
|
|
{
|
|
"epoch": 0.04040501446480232,
|
|
"grad_norm": 7.03749418258667,
|
|
"learning_rate": 0.00019921450625751317,
|
|
"loss": 1.1119629669189453,
|
|
"num_input_tokens_seen": 59014672,
|
|
"step": 41900,
|
|
"train_runtime": 82721.3106,
|
|
"train_tokens_per_second": 713.416
|
|
},
|
|
{
|
|
"epoch": 0.04045323047251687,
|
|
"grad_norm": 6.814823150634766,
|
|
"learning_rate": 0.00019921260936230393,
|
|
"loss": 1.0991464233398438,
|
|
"num_input_tokens_seen": 59054544,
|
|
"step": 41950,
|
|
"train_runtime": 82784.9556,
|
|
"train_tokens_per_second": 713.349
|
|
},
|
|
{
|
|
"epoch": 0.040501446480231434,
|
|
"grad_norm": 5.780966281890869,
|
|
"learning_rate": 0.0001992107101884951,
|
|
"loss": 1.1185302734375,
|
|
"num_input_tokens_seen": 59092232,
|
|
"step": 42000,
|
|
"train_runtime": 82848.0483,
|
|
"train_tokens_per_second": 713.26
|
|
},
|
|
{
|
|
"epoch": 0.040549662487945996,
|
|
"grad_norm": 7.495917320251465,
|
|
"learning_rate": 0.00019920880873613035,
|
|
"loss": 1.0834303283691407,
|
|
"num_input_tokens_seen": 59131672,
|
|
"step": 42050,
|
|
"train_runtime": 82912.2687,
|
|
"train_tokens_per_second": 713.184
|
|
},
|
|
{
|
|
"epoch": 0.04059787849566056,
|
|
"grad_norm": 6.12588357925415,
|
|
"learning_rate": 0.00019920690500525328,
|
|
"loss": 1.0632083892822266,
|
|
"num_input_tokens_seen": 59171456,
|
|
"step": 42100,
|
|
"train_runtime": 82975.7922,
|
|
"train_tokens_per_second": 713.117
|
|
},
|
|
{
|
|
"epoch": 0.04064609450337512,
|
|
"grad_norm": 5.406303405761719,
|
|
"learning_rate": 0.00019920499899590764,
|
|
"loss": 1.1221128082275391,
|
|
"num_input_tokens_seen": 59209968,
|
|
"step": 42150,
|
|
"train_runtime": 83039.21,
|
|
"train_tokens_per_second": 713.036
|
|
},
|
|
{
|
|
"epoch": 0.04069431051108968,
|
|
"grad_norm": 4.957583904266357,
|
|
"learning_rate": 0.00019920309070813722,
|
|
"loss": 1.0875952911376954,
|
|
"num_input_tokens_seen": 59247680,
|
|
"step": 42200,
|
|
"train_runtime": 83102.507,
|
|
"train_tokens_per_second": 712.947
|
|
},
|
|
{
|
|
"epoch": 0.040742526518804244,
|
|
"grad_norm": 6.164644718170166,
|
|
"learning_rate": 0.00019920118014198583,
|
|
"loss": 1.1442543792724609,
|
|
"num_input_tokens_seen": 59287368,
|
|
"step": 42250,
|
|
"train_runtime": 83167.4295,
|
|
"train_tokens_per_second": 712.868
|
|
},
|
|
{
|
|
"epoch": 0.040790742526518806,
|
|
"grad_norm": 6.553491592407227,
|
|
"learning_rate": 0.00019919926729749737,
|
|
"loss": 1.145168228149414,
|
|
"num_input_tokens_seen": 59326264,
|
|
"step": 42300,
|
|
"train_runtime": 83231.3243,
|
|
"train_tokens_per_second": 712.788
|
|
},
|
|
{
|
|
"epoch": 0.04083895853423337,
|
|
"grad_norm": 7.252501487731934,
|
|
"learning_rate": 0.00019919735217471576,
|
|
"loss": 1.1031824493408202,
|
|
"num_input_tokens_seen": 59365360,
|
|
"step": 42350,
|
|
"train_runtime": 83295.3992,
|
|
"train_tokens_per_second": 712.709
|
|
},
|
|
{
|
|
"epoch": 0.04088717454194793,
|
|
"grad_norm": 5.08110237121582,
|
|
"learning_rate": 0.00019919543477368496,
|
|
"loss": 1.1037052154541016,
|
|
"num_input_tokens_seen": 59403552,
|
|
"step": 42400,
|
|
"train_runtime": 83358.686,
|
|
"train_tokens_per_second": 712.626
|
|
},
|
|
{
|
|
"epoch": 0.04093539054966249,
|
|
"grad_norm": 9.536320686340332,
|
|
"learning_rate": 0.00019919351509444907,
|
|
"loss": 1.071955108642578,
|
|
"num_input_tokens_seen": 59443272,
|
|
"step": 42450,
|
|
"train_runtime": 83423.1662,
|
|
"train_tokens_per_second": 712.551
|
|
},
|
|
{
|
|
"epoch": 0.040983606557377046,
|
|
"grad_norm": 7.464327812194824,
|
|
"learning_rate": 0.0001991915931370521,
|
|
"loss": 1.1309600830078126,
|
|
"num_input_tokens_seen": 59481336,
|
|
"step": 42500,
|
|
"train_runtime": 83485.9022,
|
|
"train_tokens_per_second": 712.472
|
|
},
|
|
{
|
|
"epoch": 0.04103182256509161,
|
|
"grad_norm": 8.773487091064453,
|
|
"learning_rate": 0.00019918966890153822,
|
|
"loss": 1.0871048736572266,
|
|
"num_input_tokens_seen": 59519080,
|
|
"step": 42550,
|
|
"train_runtime": 83548.4812,
|
|
"train_tokens_per_second": 712.39
|
|
},
|
|
{
|
|
"epoch": 0.04108003857280617,
|
|
"grad_norm": 6.875967502593994,
|
|
"learning_rate": 0.00019918774238795165,
|
|
"loss": 1.0531513214111328,
|
|
"num_input_tokens_seen": 59558560,
|
|
"step": 42600,
|
|
"train_runtime": 83612.6112,
|
|
"train_tokens_per_second": 712.316
|
|
},
|
|
{
|
|
"epoch": 0.04112825458052073,
|
|
"grad_norm": 5.952065467834473,
|
|
"learning_rate": 0.00019918581359633662,
|
|
"loss": 1.1345443725585938,
|
|
"num_input_tokens_seen": 59597336,
|
|
"step": 42650,
|
|
"train_runtime": 83676.5029,
|
|
"train_tokens_per_second": 712.235
|
|
},
|
|
{
|
|
"epoch": 0.041176470588235294,
|
|
"grad_norm": 7.477481842041016,
|
|
"learning_rate": 0.00019918388252673745,
|
|
"loss": 1.1174463653564453,
|
|
"num_input_tokens_seen": 59634680,
|
|
"step": 42700,
|
|
"train_runtime": 83739.8611,
|
|
"train_tokens_per_second": 712.142
|
|
},
|
|
{
|
|
"epoch": 0.041224686595949855,
|
|
"grad_norm": 5.751140117645264,
|
|
"learning_rate": 0.00019918194917919844,
|
|
"loss": 1.1158394622802734,
|
|
"num_input_tokens_seen": 59673752,
|
|
"step": 42750,
|
|
"train_runtime": 83803.5936,
|
|
"train_tokens_per_second": 712.067
|
|
},
|
|
{
|
|
"epoch": 0.04127290260366442,
|
|
"grad_norm": 4.433112144470215,
|
|
"learning_rate": 0.00019918001355376404,
|
|
"loss": 1.021153106689453,
|
|
"num_input_tokens_seen": 59713464,
|
|
"step": 42800,
|
|
"train_runtime": 83868.7882,
|
|
"train_tokens_per_second": 711.987
|
|
},
|
|
{
|
|
"epoch": 0.04132111861137898,
|
|
"grad_norm": 5.590851783752441,
|
|
"learning_rate": 0.00019917807565047866,
|
|
"loss": 1.12966796875,
|
|
"num_input_tokens_seen": 59751520,
|
|
"step": 42850,
|
|
"train_runtime": 83932.0752,
|
|
"train_tokens_per_second": 711.903
|
|
},
|
|
{
|
|
"epoch": 0.04136933461909354,
|
|
"grad_norm": 5.066120147705078,
|
|
"learning_rate": 0.00019917613546938684,
|
|
"loss": 1.0877703857421874,
|
|
"num_input_tokens_seen": 59790600,
|
|
"step": 42900,
|
|
"train_runtime": 83995.9386,
|
|
"train_tokens_per_second": 711.827
|
|
},
|
|
{
|
|
"epoch": 0.0414175506268081,
|
|
"grad_norm": 5.29652738571167,
|
|
"learning_rate": 0.00019917419301053313,
|
|
"loss": 1.1015748596191406,
|
|
"num_input_tokens_seen": 59828176,
|
|
"step": 42950,
|
|
"train_runtime": 84059.5259,
|
|
"train_tokens_per_second": 711.736
|
|
},
|
|
{
|
|
"epoch": 0.041465766634522665,
|
|
"grad_norm": 7.3654890060424805,
|
|
"learning_rate": 0.00019917224827396214,
|
|
"loss": 1.093174057006836,
|
|
"num_input_tokens_seen": 59866928,
|
|
"step": 43000,
|
|
"train_runtime": 84123.9057,
|
|
"train_tokens_per_second": 711.652
|
|
},
|
|
{
|
|
"epoch": 0.04151398264223722,
|
|
"grad_norm": 5.9967570304870605,
|
|
"learning_rate": 0.0001991703012597186,
|
|
"loss": 1.0570814514160156,
|
|
"num_input_tokens_seen": 59906464,
|
|
"step": 43050,
|
|
"train_runtime": 84187.2767,
|
|
"train_tokens_per_second": 711.586
|
|
},
|
|
{
|
|
"epoch": 0.04156219864995178,
|
|
"grad_norm": 4.5439958572387695,
|
|
"learning_rate": 0.0001991683519678471,
|
|
"loss": 1.0845260620117188,
|
|
"num_input_tokens_seen": 59944904,
|
|
"step": 43100,
|
|
"train_runtime": 84249.874,
|
|
"train_tokens_per_second": 711.513
|
|
},
|
|
{
|
|
"epoch": 0.04161041465766634,
|
|
"grad_norm": 5.575229167938232,
|
|
"learning_rate": 0.0001991664003983925,
|
|
"loss": 1.088534393310547,
|
|
"num_input_tokens_seen": 59982248,
|
|
"step": 43150,
|
|
"train_runtime": 84313.1787,
|
|
"train_tokens_per_second": 711.422
|
|
},
|
|
{
|
|
"epoch": 0.041658630665380905,
|
|
"grad_norm": 5.951631546020508,
|
|
"learning_rate": 0.00019916444655139958,
|
|
"loss": 1.0676702117919923,
|
|
"num_input_tokens_seen": 60020712,
|
|
"step": 43200,
|
|
"train_runtime": 84377.2845,
|
|
"train_tokens_per_second": 711.337
|
|
},
|
|
{
|
|
"epoch": 0.04170684667309547,
|
|
"grad_norm": 5.43752384185791,
|
|
"learning_rate": 0.00019916249042691323,
|
|
"loss": 1.1083804321289064,
|
|
"num_input_tokens_seen": 60059184,
|
|
"step": 43250,
|
|
"train_runtime": 84441.0565,
|
|
"train_tokens_per_second": 711.256
|
|
},
|
|
{
|
|
"epoch": 0.04175506268081003,
|
|
"grad_norm": 5.997548580169678,
|
|
"learning_rate": 0.0001991605320249784,
|
|
"loss": 1.1346294403076171,
|
|
"num_input_tokens_seen": 60097016,
|
|
"step": 43300,
|
|
"train_runtime": 84503.9751,
|
|
"train_tokens_per_second": 711.174
|
|
},
|
|
{
|
|
"epoch": 0.04180327868852459,
|
|
"grad_norm": 7.328155517578125,
|
|
"learning_rate": 0.00019915857134564005,
|
|
"loss": 1.0261800384521484,
|
|
"num_input_tokens_seen": 60134936,
|
|
"step": 43350,
|
|
"train_runtime": 84568.9999,
|
|
"train_tokens_per_second": 711.075
|
|
},
|
|
{
|
|
"epoch": 0.04185149469623915,
|
|
"grad_norm": 6.223931789398193,
|
|
"learning_rate": 0.00019915660838894318,
|
|
"loss": 1.0907791137695313,
|
|
"num_input_tokens_seen": 60174080,
|
|
"step": 43400,
|
|
"train_runtime": 84633.6989,
|
|
"train_tokens_per_second": 710.994
|
|
},
|
|
{
|
|
"epoch": 0.041899710703953714,
|
|
"grad_norm": 5.749692916870117,
|
|
"learning_rate": 0.00019915464315493287,
|
|
"loss": 1.1210254669189452,
|
|
"num_input_tokens_seen": 60211928,
|
|
"step": 43450,
|
|
"train_runtime": 84697.8881,
|
|
"train_tokens_per_second": 710.902
|
|
},
|
|
{
|
|
"epoch": 0.041947926711668276,
|
|
"grad_norm": 7.507781982421875,
|
|
"learning_rate": 0.00019915267564365435,
|
|
"loss": 1.1197209930419922,
|
|
"num_input_tokens_seen": 60250552,
|
|
"step": 43500,
|
|
"train_runtime": 84762.6567,
|
|
"train_tokens_per_second": 710.815
|
|
},
|
|
{
|
|
"epoch": 0.04199614271938284,
|
|
"grad_norm": 7.228274822235107,
|
|
"learning_rate": 0.0001991507058551527,
|
|
"loss": 1.155557632446289,
|
|
"num_input_tokens_seen": 60287736,
|
|
"step": 43550,
|
|
"train_runtime": 84825.6068,
|
|
"train_tokens_per_second": 710.726
|
|
},
|
|
{
|
|
"epoch": 0.04204435872709739,
|
|
"grad_norm": 5.380199432373047,
|
|
"learning_rate": 0.0001991487337894732,
|
|
"loss": 1.0617800903320314,
|
|
"num_input_tokens_seen": 60327888,
|
|
"step": 43600,
|
|
"train_runtime": 84890.2644,
|
|
"train_tokens_per_second": 710.657
|
|
},
|
|
{
|
|
"epoch": 0.042092574734811955,
|
|
"grad_norm": 6.685075759887695,
|
|
"learning_rate": 0.00019914675944666116,
|
|
"loss": 1.1242279052734374,
|
|
"num_input_tokens_seen": 60365944,
|
|
"step": 43650,
|
|
"train_runtime": 84953.6104,
|
|
"train_tokens_per_second": 710.575
|
|
},
|
|
{
|
|
"epoch": 0.04214079074252652,
|
|
"grad_norm": 6.226441860198975,
|
|
"learning_rate": 0.0001991447828267619,
|
|
"loss": 1.0866598510742187,
|
|
"num_input_tokens_seen": 60403144,
|
|
"step": 43700,
|
|
"train_runtime": 85016.8797,
|
|
"train_tokens_per_second": 710.484
|
|
},
|
|
{
|
|
"epoch": 0.04218900675024108,
|
|
"grad_norm": 4.712273120880127,
|
|
"learning_rate": 0.00019914280392982082,
|
|
"loss": 1.1022730255126953,
|
|
"num_input_tokens_seen": 60443048,
|
|
"step": 43750,
|
|
"train_runtime": 85081.7691,
|
|
"train_tokens_per_second": 710.411
|
|
},
|
|
{
|
|
"epoch": 0.04223722275795564,
|
|
"grad_norm": 6.8003034591674805,
|
|
"learning_rate": 0.00019914082275588338,
|
|
"loss": 1.0647103881835938,
|
|
"num_input_tokens_seen": 60481728,
|
|
"step": 43800,
|
|
"train_runtime": 85145.6158,
|
|
"train_tokens_per_second": 710.333
|
|
},
|
|
{
|
|
"epoch": 0.0422854387656702,
|
|
"grad_norm": 7.979859828948975,
|
|
"learning_rate": 0.0001991388393049951,
|
|
"loss": 1.1283348846435546,
|
|
"num_input_tokens_seen": 60520016,
|
|
"step": 43850,
|
|
"train_runtime": 85208.8421,
|
|
"train_tokens_per_second": 710.255
|
|
},
|
|
{
|
|
"epoch": 0.042333654773384764,
|
|
"grad_norm": 7.216314315795898,
|
|
"learning_rate": 0.00019913685357720145,
|
|
"loss": 1.0865166473388672,
|
|
"num_input_tokens_seen": 60559176,
|
|
"step": 43900,
|
|
"train_runtime": 85273.2948,
|
|
"train_tokens_per_second": 710.178
|
|
},
|
|
{
|
|
"epoch": 0.042381870781099326,
|
|
"grad_norm": 5.638275146484375,
|
|
"learning_rate": 0.00019913486557254813,
|
|
"loss": 1.0832292938232422,
|
|
"num_input_tokens_seen": 60597584,
|
|
"step": 43950,
|
|
"train_runtime": 85337.1036,
|
|
"train_tokens_per_second": 710.097
|
|
},
|
|
{
|
|
"epoch": 0.04243008678881389,
|
|
"grad_norm": 5.698759078979492,
|
|
"learning_rate": 0.00019913287529108075,
|
|
"loss": 1.0703530883789063,
|
|
"num_input_tokens_seen": 60635176,
|
|
"step": 44000,
|
|
"train_runtime": 85402.1204,
|
|
"train_tokens_per_second": 709.996
|
|
},
|
|
{
|
|
"epoch": 0.04247830279652845,
|
|
"grad_norm": 5.747646331787109,
|
|
"learning_rate": 0.00019913088273284504,
|
|
"loss": 1.110373306274414,
|
|
"num_input_tokens_seen": 60673464,
|
|
"step": 44050,
|
|
"train_runtime": 85467.2477,
|
|
"train_tokens_per_second": 709.903
|
|
},
|
|
{
|
|
"epoch": 0.04252651880424301,
|
|
"grad_norm": 5.4896416664123535,
|
|
"learning_rate": 0.00019912888789788675,
|
|
"loss": 1.1065117645263671,
|
|
"num_input_tokens_seen": 60712272,
|
|
"step": 44100,
|
|
"train_runtime": 85535.4161,
|
|
"train_tokens_per_second": 709.791
|
|
},
|
|
{
|
|
"epoch": 0.04257473481195757,
|
|
"grad_norm": 5.181446075439453,
|
|
"learning_rate": 0.00019912689078625172,
|
|
"loss": 1.1170376586914061,
|
|
"num_input_tokens_seen": 60751008,
|
|
"step": 44150,
|
|
"train_runtime": 85604.5797,
|
|
"train_tokens_per_second": 709.67
|
|
},
|
|
{
|
|
"epoch": 0.04262295081967213,
|
|
"grad_norm": 7.943204879760742,
|
|
"learning_rate": 0.0001991248913979858,
|
|
"loss": 1.1304073333740234,
|
|
"num_input_tokens_seen": 60789728,
|
|
"step": 44200,
|
|
"train_runtime": 85670.3045,
|
|
"train_tokens_per_second": 709.578
|
|
},
|
|
{
|
|
"epoch": 0.04267116682738669,
|
|
"grad_norm": 8.077685356140137,
|
|
"learning_rate": 0.00019912288973313483,
|
|
"loss": 1.128107681274414,
|
|
"num_input_tokens_seen": 60828440,
|
|
"step": 44250,
|
|
"train_runtime": 85736.0579,
|
|
"train_tokens_per_second": 709.485
|
|
},
|
|
{
|
|
"epoch": 0.04271938283510125,
|
|
"grad_norm": 5.591845512390137,
|
|
"learning_rate": 0.00019912088579174494,
|
|
"loss": 1.1111499786376953,
|
|
"num_input_tokens_seen": 60866792,
|
|
"step": 44300,
|
|
"train_runtime": 85803.4405,
|
|
"train_tokens_per_second": 709.375
|
|
},
|
|
{
|
|
"epoch": 0.042767598842815814,
|
|
"grad_norm": 6.8503241539001465,
|
|
"learning_rate": 0.00019911887957386207,
|
|
"loss": 1.1333733367919923,
|
|
"num_input_tokens_seen": 60904032,
|
|
"step": 44350,
|
|
"train_runtime": 85869.1654,
|
|
"train_tokens_per_second": 709.265
|
|
},
|
|
{
|
|
"epoch": 0.042815814850530376,
|
|
"grad_norm": 5.778532028198242,
|
|
"learning_rate": 0.00019911687107953226,
|
|
"loss": 1.1486290740966796,
|
|
"num_input_tokens_seen": 60943488,
|
|
"step": 44400,
|
|
"train_runtime": 85936.511,
|
|
"train_tokens_per_second": 709.169
|
|
},
|
|
{
|
|
"epoch": 0.04286403085824494,
|
|
"grad_norm": 6.308884143829346,
|
|
"learning_rate": 0.00019911486030880167,
|
|
"loss": 1.1100527191162108,
|
|
"num_input_tokens_seen": 60981608,
|
|
"step": 44450,
|
|
"train_runtime": 86002.005,
|
|
"train_tokens_per_second": 709.072
|
|
},
|
|
{
|
|
"epoch": 0.0429122468659595,
|
|
"grad_norm": 6.434926986694336,
|
|
"learning_rate": 0.00019911284726171653,
|
|
"loss": 1.1353517913818358,
|
|
"num_input_tokens_seen": 61019768,
|
|
"step": 44500,
|
|
"train_runtime": 86067.1066,
|
|
"train_tokens_per_second": 708.979
|
|
},
|
|
{
|
|
"epoch": 0.04296046287367406,
|
|
"grad_norm": 6.261920928955078,
|
|
"learning_rate": 0.00019911083193832304,
|
|
"loss": 1.1000853729248048,
|
|
"num_input_tokens_seen": 61058136,
|
|
"step": 44550,
|
|
"train_runtime": 86133.6494,
|
|
"train_tokens_per_second": 708.877
|
|
},
|
|
{
|
|
"epoch": 0.04300867888138862,
|
|
"grad_norm": 5.7183451652526855,
|
|
"learning_rate": 0.00019910885471296762,
|
|
"loss": 1.1214158630371094,
|
|
"num_input_tokens_seen": 61096184,
|
|
"step": 44600,
|
|
"train_runtime": 86199.1884,
|
|
"train_tokens_per_second": 708.779
|
|
},
|
|
{
|
|
"epoch": 0.043056894889103185,
|
|
"grad_norm": 6.668750286102295,
|
|
"learning_rate": 0.00019910683488262015,
|
|
"loss": 1.1087693786621093,
|
|
"num_input_tokens_seen": 61133368,
|
|
"step": 44650,
|
|
"train_runtime": 86264.6007,
|
|
"train_tokens_per_second": 708.673
|
|
},
|
|
{
|
|
"epoch": 0.04310511089681774,
|
|
"grad_norm": 4.7046685218811035,
|
|
"learning_rate": 0.00019910481277610244,
|
|
"loss": 1.095248031616211,
|
|
"num_input_tokens_seen": 61171544,
|
|
"step": 44700,
|
|
"train_runtime": 86331.4395,
|
|
"train_tokens_per_second": 708.566
|
|
},
|
|
{
|
|
"epoch": 0.0431533269045323,
|
|
"grad_norm": 7.325972557067871,
|
|
"learning_rate": 0.00019910278839346089,
|
|
"loss": 1.0699791717529297,
|
|
"num_input_tokens_seen": 61209080,
|
|
"step": 44750,
|
|
"train_runtime": 86397.0807,
|
|
"train_tokens_per_second": 708.462
|
|
},
|
|
{
|
|
"epoch": 0.043201542912246864,
|
|
"grad_norm": 5.283923625946045,
|
|
"learning_rate": 0.00019910076173474198,
|
|
"loss": 1.1010159301757811,
|
|
"num_input_tokens_seen": 61247832,
|
|
"step": 44800,
|
|
"train_runtime": 86463.3826,
|
|
"train_tokens_per_second": 708.367
|
|
},
|
|
{
|
|
"epoch": 0.043249758919961426,
|
|
"grad_norm": 5.8142571449279785,
|
|
"learning_rate": 0.0001990987327999923,
|
|
"loss": 1.118205795288086,
|
|
"num_input_tokens_seen": 61285536,
|
|
"step": 44850,
|
|
"train_runtime": 86529.2706,
|
|
"train_tokens_per_second": 708.264
|
|
},
|
|
{
|
|
"epoch": 0.04329797492767599,
|
|
"grad_norm": 5.145359039306641,
|
|
"learning_rate": 0.00019909670158925843,
|
|
"loss": 1.1173128509521484,
|
|
"num_input_tokens_seen": 61323936,
|
|
"step": 44900,
|
|
"train_runtime": 86595.7189,
|
|
"train_tokens_per_second": 708.164
|
|
},
|
|
{
|
|
"epoch": 0.04334619093539055,
|
|
"grad_norm": 6.226546764373779,
|
|
"learning_rate": 0.000199094668102587,
|
|
"loss": 1.1148436737060547,
|
|
"num_input_tokens_seen": 61360944,
|
|
"step": 44950,
|
|
"train_runtime": 86660.9972,
|
|
"train_tokens_per_second": 708.057
|
|
},
|
|
{
|
|
"epoch": 0.04339440694310511,
|
|
"grad_norm": 6.172881603240967,
|
|
"learning_rate": 0.00019909263234002474,
|
|
"loss": 1.080862045288086,
|
|
"num_input_tokens_seen": 61400472,
|
|
"step": 45000,
|
|
"train_runtime": 86730.645,
|
|
"train_tokens_per_second": 707.944
|
|
},
|
|
{
|
|
"epoch": 0.04344262295081967,
|
|
"grad_norm": 6.3598408699035645,
|
|
"learning_rate": 0.0001990905943016184,
|
|
"loss": 1.057692184448242,
|
|
"num_input_tokens_seen": 61438728,
|
|
"step": 45050,
|
|
"train_runtime": 86798.0192,
|
|
"train_tokens_per_second": 707.836
|
|
},
|
|
{
|
|
"epoch": 0.043490838958534235,
|
|
"grad_norm": 6.273787975311279,
|
|
"learning_rate": 0.00019908855398741477,
|
|
"loss": 1.1078964233398438,
|
|
"num_input_tokens_seen": 61477488,
|
|
"step": 45100,
|
|
"train_runtime": 86863.7817,
|
|
"train_tokens_per_second": 707.746
|
|
},
|
|
{
|
|
"epoch": 0.0435390549662488,
|
|
"grad_norm": 5.88733434677124,
|
|
"learning_rate": 0.00019908651139746074,
|
|
"loss": 1.1152843475341796,
|
|
"num_input_tokens_seen": 61514928,
|
|
"step": 45150,
|
|
"train_runtime": 86928.9193,
|
|
"train_tokens_per_second": 707.646
|
|
},
|
|
{
|
|
"epoch": 0.04358727097396336,
|
|
"grad_norm": 6.782724857330322,
|
|
"learning_rate": 0.00019908446653180319,
|
|
"loss": 1.0635975646972655,
|
|
"num_input_tokens_seen": 61553232,
|
|
"step": 45200,
|
|
"train_runtime": 86994.5993,
|
|
"train_tokens_per_second": 707.552
|
|
},
|
|
{
|
|
"epoch": 0.043635486981677914,
|
|
"grad_norm": 5.472492694854736,
|
|
"learning_rate": 0.00019908241939048908,
|
|
"loss": 1.0865777587890626,
|
|
"num_input_tokens_seen": 61590976,
|
|
"step": 45250,
|
|
"train_runtime": 87059.9714,
|
|
"train_tokens_per_second": 707.455
|
|
},
|
|
{
|
|
"epoch": 0.043683702989392476,
|
|
"grad_norm": 6.69541072845459,
|
|
"learning_rate": 0.00019908036997356548,
|
|
"loss": 1.0738488006591798,
|
|
"num_input_tokens_seen": 61628928,
|
|
"step": 45300,
|
|
"train_runtime": 87125.1055,
|
|
"train_tokens_per_second": 707.361
|
|
},
|
|
{
|
|
"epoch": 0.04373191899710704,
|
|
"grad_norm": 5.815643310546875,
|
|
"learning_rate": 0.0001990783182810794,
|
|
"loss": 1.1452601623535157,
|
|
"num_input_tokens_seen": 61666512,
|
|
"step": 45350,
|
|
"train_runtime": 87189.0655,
|
|
"train_tokens_per_second": 707.273
|
|
},
|
|
{
|
|
"epoch": 0.0437801350048216,
|
|
"grad_norm": 6.952874660491943,
|
|
"learning_rate": 0.000199076264313078,
|
|
"loss": 1.1234237670898437,
|
|
"num_input_tokens_seen": 61704608,
|
|
"step": 45400,
|
|
"train_runtime": 87253.103,
|
|
"train_tokens_per_second": 707.191
|
|
},
|
|
{
|
|
"epoch": 0.04382835101253616,
|
|
"grad_norm": 5.294637680053711,
|
|
"learning_rate": 0.0001990742080696084,
|
|
"loss": 1.1037101745605469,
|
|
"num_input_tokens_seen": 61741936,
|
|
"step": 45450,
|
|
"train_runtime": 87316.0427,
|
|
"train_tokens_per_second": 707.109
|
|
},
|
|
{
|
|
"epoch": 0.04387656702025072,
|
|
"grad_norm": 4.5205912590026855,
|
|
"learning_rate": 0.0001990721495507179,
|
|
"loss": 1.124926528930664,
|
|
"num_input_tokens_seen": 61779184,
|
|
"step": 45500,
|
|
"train_runtime": 87379.3792,
|
|
"train_tokens_per_second": 707.022
|
|
},
|
|
{
|
|
"epoch": 0.043924783027965285,
|
|
"grad_norm": 7.249176979064941,
|
|
"learning_rate": 0.00019907008875645374,
|
|
"loss": 1.0519026184082032,
|
|
"num_input_tokens_seen": 61817376,
|
|
"step": 45550,
|
|
"train_runtime": 87442.608,
|
|
"train_tokens_per_second": 706.948
|
|
},
|
|
{
|
|
"epoch": 0.04397299903567985,
|
|
"grad_norm": 5.748585224151611,
|
|
"learning_rate": 0.00019906802568686325,
|
|
"loss": 1.0923573303222656,
|
|
"num_input_tokens_seen": 61857096,
|
|
"step": 45600,
|
|
"train_runtime": 87507.0357,
|
|
"train_tokens_per_second": 706.881
|
|
},
|
|
{
|
|
"epoch": 0.04402121504339441,
|
|
"grad_norm": 6.835485935211182,
|
|
"learning_rate": 0.0001990659603419938,
|
|
"loss": 1.088850860595703,
|
|
"num_input_tokens_seen": 61894328,
|
|
"step": 45650,
|
|
"train_runtime": 87570.1039,
|
|
"train_tokens_per_second": 706.797
|
|
},
|
|
{
|
|
"epoch": 0.04406943105110897,
|
|
"grad_norm": 7.06531286239624,
|
|
"learning_rate": 0.00019906389272189286,
|
|
"loss": 1.0785787963867188,
|
|
"num_input_tokens_seen": 61932032,
|
|
"step": 45700,
|
|
"train_runtime": 87633.4426,
|
|
"train_tokens_per_second": 706.717
|
|
},
|
|
{
|
|
"epoch": 0.04411764705882353,
|
|
"grad_norm": 6.092350006103516,
|
|
"learning_rate": 0.00019906182282660787,
|
|
"loss": 1.0777600860595704,
|
|
"num_input_tokens_seen": 61969896,
|
|
"step": 45750,
|
|
"train_runtime": 87696.6932,
|
|
"train_tokens_per_second": 706.639
|
|
},
|
|
{
|
|
"epoch": 0.04416586306653809,
|
|
"grad_norm": 4.175806045532227,
|
|
"learning_rate": 0.0001990597506561864,
|
|
"loss": 1.1456649017333984,
|
|
"num_input_tokens_seen": 62007232,
|
|
"step": 45800,
|
|
"train_runtime": 87759.42,
|
|
"train_tokens_per_second": 706.559
|
|
},
|
|
{
|
|
"epoch": 0.04421407907425265,
|
|
"grad_norm": 6.510632038116455,
|
|
"learning_rate": 0.00019905767621067604,
|
|
"loss": 1.1178430938720703,
|
|
"num_input_tokens_seen": 62044448,
|
|
"step": 45850,
|
|
"train_runtime": 87822.374,
|
|
"train_tokens_per_second": 706.477
|
|
},
|
|
{
|
|
"epoch": 0.04426229508196721,
|
|
"grad_norm": 4.705597877502441,
|
|
"learning_rate": 0.0001990555994901244,
|
|
"loss": 1.1228683471679688,
|
|
"num_input_tokens_seen": 62081480,
|
|
"step": 45900,
|
|
"train_runtime": 87885.1926,
|
|
"train_tokens_per_second": 706.393
|
|
},
|
|
{
|
|
"epoch": 0.04431051108968177,
|
|
"grad_norm": 7.5807318687438965,
|
|
"learning_rate": 0.00019905352049457925,
|
|
"loss": 1.0897943878173828,
|
|
"num_input_tokens_seen": 62118608,
|
|
"step": 45950,
|
|
"train_runtime": 87948.1317,
|
|
"train_tokens_per_second": 706.31
|
|
},
|
|
{
|
|
"epoch": 0.044358727097396335,
|
|
"grad_norm": 5.742594242095947,
|
|
"learning_rate": 0.00019905143922408825,
|
|
"loss": 1.1248424530029297,
|
|
"num_input_tokens_seen": 62156536,
|
|
"step": 46000,
|
|
"train_runtime": 88012.051,
|
|
"train_tokens_per_second": 706.228
|
|
},
|
|
{
|
|
"epoch": 0.044406943105110896,
|
|
"grad_norm": 6.542175769805908,
|
|
"learning_rate": 0.00019904935567869925,
|
|
"loss": 1.0765518188476562,
|
|
"num_input_tokens_seen": 62194960,
|
|
"step": 46050,
|
|
"train_runtime": 88075.3518,
|
|
"train_tokens_per_second": 706.156
|
|
},
|
|
{
|
|
"epoch": 0.04445515911282546,
|
|
"grad_norm": 6.278806209564209,
|
|
"learning_rate": 0.0001990472698584601,
|
|
"loss": 1.0737877655029298,
|
|
"num_input_tokens_seen": 62232600,
|
|
"step": 46100,
|
|
"train_runtime": 88138.8978,
|
|
"train_tokens_per_second": 706.074
|
|
},
|
|
{
|
|
"epoch": 0.04450337512054002,
|
|
"grad_norm": 6.76254415512085,
|
|
"learning_rate": 0.00019904518176341868,
|
|
"loss": 1.10368408203125,
|
|
"num_input_tokens_seen": 62271760,
|
|
"step": 46150,
|
|
"train_runtime": 88202.867,
|
|
"train_tokens_per_second": 706.006
|
|
},
|
|
{
|
|
"epoch": 0.04455159112825458,
|
|
"grad_norm": 4.682104587554932,
|
|
"learning_rate": 0.00019904309139362301,
|
|
"loss": 1.0732647705078124,
|
|
"num_input_tokens_seen": 62309608,
|
|
"step": 46200,
|
|
"train_runtime": 88266.4746,
|
|
"train_tokens_per_second": 705.926
|
|
},
|
|
{
|
|
"epoch": 0.044599807135969144,
|
|
"grad_norm": 5.942133903503418,
|
|
"learning_rate": 0.00019904099874912102,
|
|
"loss": 1.093145751953125,
|
|
"num_input_tokens_seen": 62347720,
|
|
"step": 46250,
|
|
"train_runtime": 88330.1978,
|
|
"train_tokens_per_second": 705.848
|
|
},
|
|
{
|
|
"epoch": 0.044648023143683706,
|
|
"grad_norm": 5.5875139236450195,
|
|
"learning_rate": 0.00019903890382996079,
|
|
"loss": 1.1218142700195313,
|
|
"num_input_tokens_seen": 62385736,
|
|
"step": 46300,
|
|
"train_runtime": 88393.9209,
|
|
"train_tokens_per_second": 705.77
|
|
},
|
|
{
|
|
"epoch": 0.04469623915139827,
|
|
"grad_norm": 7.979564666748047,
|
|
"learning_rate": 0.0001990368066361905,
|
|
"loss": 1.15791015625,
|
|
"num_input_tokens_seen": 62423272,
|
|
"step": 46350,
|
|
"train_runtime": 88457.2787,
|
|
"train_tokens_per_second": 705.688
|
|
},
|
|
{
|
|
"epoch": 0.04474445515911282,
|
|
"grad_norm": 6.165395736694336,
|
|
"learning_rate": 0.0001990347071678582,
|
|
"loss": 1.1021792602539062,
|
|
"num_input_tokens_seen": 62460856,
|
|
"step": 46400,
|
|
"train_runtime": 88520.528,
|
|
"train_tokens_per_second": 705.609
|
|
},
|
|
{
|
|
"epoch": 0.044792671166827384,
|
|
"grad_norm": 5.6581621170043945,
|
|
"learning_rate": 0.00019903260542501224,
|
|
"loss": 1.1300953674316405,
|
|
"num_input_tokens_seen": 62499448,
|
|
"step": 46450,
|
|
"train_runtime": 88584.5623,
|
|
"train_tokens_per_second": 705.534
|
|
},
|
|
{
|
|
"epoch": 0.044840887174541946,
|
|
"grad_norm": 5.873270034790039,
|
|
"learning_rate": 0.00019903050140770078,
|
|
"loss": 1.1107160949707031,
|
|
"num_input_tokens_seen": 62536064,
|
|
"step": 46500,
|
|
"train_runtime": 88647.4269,
|
|
"train_tokens_per_second": 705.447
|
|
},
|
|
{
|
|
"epoch": 0.04488910318225651,
|
|
"grad_norm": 5.400038719177246,
|
|
"learning_rate": 0.0001990283951159722,
|
|
"loss": 1.0995201873779297,
|
|
"num_input_tokens_seen": 62573840,
|
|
"step": 46550,
|
|
"train_runtime": 88710.351,
|
|
"train_tokens_per_second": 705.372
|
|
},
|
|
{
|
|
"epoch": 0.04493731918997107,
|
|
"grad_norm": 5.471010684967041,
|
|
"learning_rate": 0.00019902628654987488,
|
|
"loss": 1.0963829803466796,
|
|
"num_input_tokens_seen": 62610960,
|
|
"step": 46600,
|
|
"train_runtime": 88772.9827,
|
|
"train_tokens_per_second": 705.293
|
|
},
|
|
{
|
|
"epoch": 0.04498553519768563,
|
|
"grad_norm": 5.601696491241455,
|
|
"learning_rate": 0.0001990241757094572,
|
|
"loss": 1.1431580352783204,
|
|
"num_input_tokens_seen": 62648328,
|
|
"step": 46650,
|
|
"train_runtime": 88835.5544,
|
|
"train_tokens_per_second": 705.217
|
|
},
|
|
{
|
|
"epoch": 0.045033751205400194,
|
|
"grad_norm": 5.235311985015869,
|
|
"learning_rate": 0.00019902206259476767,
|
|
"loss": 1.1123374176025391,
|
|
"num_input_tokens_seen": 62685248,
|
|
"step": 46700,
|
|
"train_runtime": 88898.6652,
|
|
"train_tokens_per_second": 705.131
|
|
},
|
|
{
|
|
"epoch": 0.045081967213114756,
|
|
"grad_norm": 6.464602470397949,
|
|
"learning_rate": 0.0001990199472058548,
|
|
"loss": 1.1020435333251952,
|
|
"num_input_tokens_seen": 62723536,
|
|
"step": 46750,
|
|
"train_runtime": 88962.3096,
|
|
"train_tokens_per_second": 705.057
|
|
},
|
|
{
|
|
"epoch": 0.04513018322082932,
|
|
"grad_norm": 5.434655666351318,
|
|
"learning_rate": 0.00019901782954276725,
|
|
"loss": 1.0518150329589844,
|
|
"num_input_tokens_seen": 62761824,
|
|
"step": 46800,
|
|
"train_runtime": 89026.1918,
|
|
"train_tokens_per_second": 704.982
|
|
},
|
|
{
|
|
"epoch": 0.04517839922854388,
|
|
"grad_norm": 6.070550918579102,
|
|
"learning_rate": 0.00019901570960555355,
|
|
"loss": 1.0946149444580078,
|
|
"num_input_tokens_seen": 62800064,
|
|
"step": 46850,
|
|
"train_runtime": 89090.5243,
|
|
"train_tokens_per_second": 704.902
|
|
},
|
|
{
|
|
"epoch": 0.04522661523625844,
|
|
"grad_norm": 7.173372745513916,
|
|
"learning_rate": 0.00019901358739426246,
|
|
"loss": 1.0875858306884765,
|
|
"num_input_tokens_seen": 62836728,
|
|
"step": 46900,
|
|
"train_runtime": 89153.0371,
|
|
"train_tokens_per_second": 704.819
|
|
},
|
|
{
|
|
"epoch": 0.045274831243972996,
|
|
"grad_norm": 6.263072967529297,
|
|
"learning_rate": 0.0001990114629089427,
|
|
"loss": 1.0479897308349608,
|
|
"num_input_tokens_seen": 62874344,
|
|
"step": 46950,
|
|
"train_runtime": 89215.678,
|
|
"train_tokens_per_second": 704.745
|
|
},
|
|
{
|
|
"epoch": 0.04532304725168756,
|
|
"grad_norm": 4.274266719818115,
|
|
"learning_rate": 0.00019900933614964305,
|
|
"loss": 1.0903789520263671,
|
|
"num_input_tokens_seen": 62912024,
|
|
"step": 47000,
|
|
"train_runtime": 89278.5155,
|
|
"train_tokens_per_second": 704.671
|
|
},
|
|
{
|
|
"epoch": 0.04537126325940212,
|
|
"grad_norm": 4.378702163696289,
|
|
"learning_rate": 0.00019900720711641236,
|
|
"loss": 1.065982666015625,
|
|
"num_input_tokens_seen": 62949664,
|
|
"step": 47050,
|
|
"train_runtime": 89341.2554,
|
|
"train_tokens_per_second": 704.598
|
|
},
|
|
{
|
|
"epoch": 0.04541947926711668,
|
|
"grad_norm": 5.591025352478027,
|
|
"learning_rate": 0.00019900507580929955,
|
|
"loss": 1.0786627197265626,
|
|
"num_input_tokens_seen": 62987400,
|
|
"step": 47100,
|
|
"train_runtime": 89404.1428,
|
|
"train_tokens_per_second": 704.524
|
|
},
|
|
{
|
|
"epoch": 0.045467695274831244,
|
|
"grad_norm": 4.728970527648926,
|
|
"learning_rate": 0.00019900294222835352,
|
|
"loss": 1.0429413604736328,
|
|
"num_input_tokens_seen": 63024896,
|
|
"step": 47150,
|
|
"train_runtime": 89466.9847,
|
|
"train_tokens_per_second": 704.449
|
|
},
|
|
{
|
|
"epoch": 0.045515911282545805,
|
|
"grad_norm": 6.651847839355469,
|
|
"learning_rate": 0.00019900080637362332,
|
|
"loss": 1.130568389892578,
|
|
"num_input_tokens_seen": 63062728,
|
|
"step": 47200,
|
|
"train_runtime": 89531.1929,
|
|
"train_tokens_per_second": 704.366
|
|
},
|
|
{
|
|
"epoch": 0.04556412729026037,
|
|
"grad_norm": 6.347314834594727,
|
|
"learning_rate": 0.00019899866824515803,
|
|
"loss": 1.118763198852539,
|
|
"num_input_tokens_seen": 63098824,
|
|
"step": 47250,
|
|
"train_runtime": 89594.3543,
|
|
"train_tokens_per_second": 704.272
|
|
},
|
|
{
|
|
"epoch": 0.04561234329797493,
|
|
"grad_norm": 5.469791889190674,
|
|
"learning_rate": 0.00019899652784300664,
|
|
"loss": 1.0776570892333985,
|
|
"num_input_tokens_seen": 63137104,
|
|
"step": 47300,
|
|
"train_runtime": 89657.2428,
|
|
"train_tokens_per_second": 704.205
|
|
},
|
|
{
|
|
"epoch": 0.04566055930568949,
|
|
"grad_norm": 6.727424621582031,
|
|
"learning_rate": 0.00019899438516721843,
|
|
"loss": 1.0574757385253906,
|
|
"num_input_tokens_seen": 63174304,
|
|
"step": 47350,
|
|
"train_runtime": 89720.4753,
|
|
"train_tokens_per_second": 704.124
|
|
},
|
|
{
|
|
"epoch": 0.04570877531340405,
|
|
"grad_norm": 6.865376949310303,
|
|
"learning_rate": 0.00019899224021784255,
|
|
"loss": 1.1032933807373047,
|
|
"num_input_tokens_seen": 63212360,
|
|
"step": 47400,
|
|
"train_runtime": 89783.1716,
|
|
"train_tokens_per_second": 704.056
|
|
},
|
|
{
|
|
"epoch": 0.045756991321118615,
|
|
"grad_norm": 6.773983478546143,
|
|
"learning_rate": 0.0001989900929949283,
|
|
"loss": 1.1062725067138672,
|
|
"num_input_tokens_seen": 63249480,
|
|
"step": 47450,
|
|
"train_runtime": 89845.7793,
|
|
"train_tokens_per_second": 703.978
|
|
},
|
|
{
|
|
"epoch": 0.04580520732883317,
|
|
"grad_norm": 7.1187028884887695,
|
|
"learning_rate": 0.0001989879434985249,
|
|
"loss": 1.0890283966064453,
|
|
"num_input_tokens_seen": 63285880,
|
|
"step": 47500,
|
|
"train_runtime": 89908.7519,
|
|
"train_tokens_per_second": 703.89
|
|
},
|
|
{
|
|
"epoch": 0.04585342333654773,
|
|
"grad_norm": 4.246365070343018,
|
|
"learning_rate": 0.00019898579172868185,
|
|
"loss": 1.0813294219970704,
|
|
"num_input_tokens_seen": 63323808,
|
|
"step": 47550,
|
|
"train_runtime": 89972.3797,
|
|
"train_tokens_per_second": 703.814
|
|
},
|
|
{
|
|
"epoch": 0.04590163934426229,
|
|
"grad_norm": 6.491115570068359,
|
|
"learning_rate": 0.00019898368078859205,
|
|
"loss": 1.1182501983642579,
|
|
"num_input_tokens_seen": 63362264,
|
|
"step": 47600,
|
|
"train_runtime": 90036.5438,
|
|
"train_tokens_per_second": 703.739
|
|
},
|
|
{
|
|
"epoch": 0.045949855351976855,
|
|
"grad_norm": 6.216296672821045,
|
|
"learning_rate": 0.0001989815245174842,
|
|
"loss": 1.0838568115234375,
|
|
"num_input_tokens_seen": 63399712,
|
|
"step": 47650,
|
|
"train_runtime": 90099.0173,
|
|
"train_tokens_per_second": 703.667
|
|
},
|
|
{
|
|
"epoch": 0.04599807135969142,
|
|
"grad_norm": 7.238345146179199,
|
|
"learning_rate": 0.00019897936597308407,
|
|
"loss": 1.121667938232422,
|
|
"num_input_tokens_seen": 63436616,
|
|
"step": 47700,
|
|
"train_runtime": 90161.7468,
|
|
"train_tokens_per_second": 703.587
|
|
},
|
|
{
|
|
"epoch": 0.04604628736740598,
|
|
"grad_norm": 5.7228312492370605,
|
|
"learning_rate": 0.0001989772051554412,
|
|
"loss": 1.0678487396240235,
|
|
"num_input_tokens_seen": 63474080,
|
|
"step": 47750,
|
|
"train_runtime": 90225.333,
|
|
"train_tokens_per_second": 703.506
|
|
},
|
|
{
|
|
"epoch": 0.04609450337512054,
|
|
"grad_norm": 8.871320724487305,
|
|
"learning_rate": 0.00019897504206460527,
|
|
"loss": 1.0431044006347656,
|
|
"num_input_tokens_seen": 63512352,
|
|
"step": 47800,
|
|
"train_runtime": 90288.6795,
|
|
"train_tokens_per_second": 703.436
|
|
},
|
|
{
|
|
"epoch": 0.0461427193828351,
|
|
"grad_norm": 6.578616619110107,
|
|
"learning_rate": 0.00019897292003018198,
|
|
"loss": 1.1141391754150392,
|
|
"num_input_tokens_seen": 63549888,
|
|
"step": 47850,
|
|
"train_runtime": 90351.4743,
|
|
"train_tokens_per_second": 703.363
|
|
},
|
|
{
|
|
"epoch": 0.046190935390549664,
|
|
"grad_norm": 4.749424934387207,
|
|
"learning_rate": 0.00019897075243857033,
|
|
"loss": 1.1240965270996093,
|
|
"num_input_tokens_seen": 63587384,
|
|
"step": 47900,
|
|
"train_runtime": 90414.4888,
|
|
"train_tokens_per_second": 703.288
|
|
},
|
|
{
|
|
"epoch": 0.046239151398264226,
|
|
"grad_norm": 5.780368328094482,
|
|
"learning_rate": 0.00019896858257391378,
|
|
"loss": 1.0989958953857422,
|
|
"num_input_tokens_seen": 63625568,
|
|
"step": 47950,
|
|
"train_runtime": 90477.5486,
|
|
"train_tokens_per_second": 703.219
|
|
},
|
|
{
|
|
"epoch": 0.04628736740597879,
|
|
"grad_norm": 5.483687877655029,
|
|
"learning_rate": 0.0001989664104362622,
|
|
"loss": 1.100810775756836,
|
|
"num_input_tokens_seen": 63662648,
|
|
"step": 48000,
|
|
"train_runtime": 90540.1648,
|
|
"train_tokens_per_second": 703.143
|
|
},
|
|
{
|
|
"epoch": 0.04633558341369334,
|
|
"grad_norm": 7.057345390319824,
|
|
"learning_rate": 0.00019896423602566544,
|
|
"loss": 1.1149588775634767,
|
|
"num_input_tokens_seen": 63699584,
|
|
"step": 48050,
|
|
"train_runtime": 90603.5997,
|
|
"train_tokens_per_second": 703.058
|
|
},
|
|
{
|
|
"epoch": 0.046383799421407905,
|
|
"grad_norm": 14.982771873474121,
|
|
"learning_rate": 0.00019896205934217347,
|
|
"loss": 1.0962008666992187,
|
|
"num_input_tokens_seen": 63736936,
|
|
"step": 48100,
|
|
"train_runtime": 90666.7064,
|
|
"train_tokens_per_second": 702.981
|
|
},
|
|
{
|
|
"epoch": 0.04643201542912247,
|
|
"grad_norm": 6.4743547439575195,
|
|
"learning_rate": 0.00019895988038583627,
|
|
"loss": 1.0595723724365234,
|
|
"num_input_tokens_seen": 63774080,
|
|
"step": 48150,
|
|
"train_runtime": 90730.8821,
|
|
"train_tokens_per_second": 702.893
|
|
},
|
|
{
|
|
"epoch": 0.04648023143683703,
|
|
"grad_norm": 6.6175150871276855,
|
|
"learning_rate": 0.00019895769915670384,
|
|
"loss": 1.01388916015625,
|
|
"num_input_tokens_seen": 63811288,
|
|
"step": 48200,
|
|
"train_runtime": 90794.3545,
|
|
"train_tokens_per_second": 702.811
|
|
},
|
|
{
|
|
"epoch": 0.04652844744455159,
|
|
"grad_norm": 5.491447925567627,
|
|
"learning_rate": 0.00019895551565482633,
|
|
"loss": 1.0578984832763672,
|
|
"num_input_tokens_seen": 63848224,
|
|
"step": 48250,
|
|
"train_runtime": 90856.9371,
|
|
"train_tokens_per_second": 702.734
|
|
},
|
|
{
|
|
"epoch": 0.04657666345226615,
|
|
"grad_norm": 6.57129430770874,
|
|
"learning_rate": 0.00019895332988025387,
|
|
"loss": 1.0980815124511718,
|
|
"num_input_tokens_seen": 63885512,
|
|
"step": 48300,
|
|
"train_runtime": 90919.94,
|
|
"train_tokens_per_second": 702.657
|
|
},
|
|
{
|
|
"epoch": 0.046624879459980714,
|
|
"grad_norm": 6.906409740447998,
|
|
"learning_rate": 0.00019895114183303666,
|
|
"loss": 1.1324150848388672,
|
|
"num_input_tokens_seen": 63922416,
|
|
"step": 48350,
|
|
"train_runtime": 90983.3433,
|
|
"train_tokens_per_second": 702.573
|
|
},
|
|
{
|
|
"epoch": 0.046673095467695276,
|
|
"grad_norm": 4.065455913543701,
|
|
"learning_rate": 0.00019894895151322496,
|
|
"loss": 1.0932808685302735,
|
|
"num_input_tokens_seen": 63959072,
|
|
"step": 48400,
|
|
"train_runtime": 91046.105,
|
|
"train_tokens_per_second": 702.491
|
|
},
|
|
{
|
|
"epoch": 0.04672131147540984,
|
|
"grad_norm": 4.357213973999023,
|
|
"learning_rate": 0.00019894675892086908,
|
|
"loss": 1.079058837890625,
|
|
"num_input_tokens_seen": 63996152,
|
|
"step": 48450,
|
|
"train_runtime": 91108.9858,
|
|
"train_tokens_per_second": 702.413
|
|
},
|
|
{
|
|
"epoch": 0.0467695274831244,
|
|
"grad_norm": 4.044673442840576,
|
|
"learning_rate": 0.00019894456405601937,
|
|
"loss": 1.0691998291015625,
|
|
"num_input_tokens_seen": 64033200,
|
|
"step": 48500,
|
|
"train_runtime": 91171.6768,
|
|
"train_tokens_per_second": 702.337
|
|
},
|
|
{
|
|
"epoch": 0.04681774349083896,
|
|
"grad_norm": 4.718571186065674,
|
|
"learning_rate": 0.00019894236691872622,
|
|
"loss": 1.0931369018554689,
|
|
"num_input_tokens_seen": 64070664,
|
|
"step": 48550,
|
|
"train_runtime": 91235.3472,
|
|
"train_tokens_per_second": 702.257
|
|
},
|
|
{
|
|
"epoch": 0.04686595949855352,
|
|
"grad_norm": 5.413954734802246,
|
|
"learning_rate": 0.0001989401675090401,
|
|
"loss": 1.0575980377197265,
|
|
"num_input_tokens_seen": 64107408,
|
|
"step": 48600,
|
|
"train_runtime": 91298.3802,
|
|
"train_tokens_per_second": 702.175
|
|
},
|
|
{
|
|
"epoch": 0.04691417550626808,
|
|
"grad_norm": 6.2805328369140625,
|
|
"learning_rate": 0.00019893796582701154,
|
|
"loss": 1.1112313079833984,
|
|
"num_input_tokens_seen": 64144192,
|
|
"step": 48650,
|
|
"train_runtime": 91361.8506,
|
|
"train_tokens_per_second": 702.089
|
|
},
|
|
{
|
|
"epoch": 0.04696239151398264,
|
|
"grad_norm": 5.678617000579834,
|
|
"learning_rate": 0.00019893576187269107,
|
|
"loss": 1.069249038696289,
|
|
"num_input_tokens_seen": 64181816,
|
|
"step": 48700,
|
|
"train_runtime": 91424.9049,
|
|
"train_tokens_per_second": 702.017
|
|
},
|
|
{
|
|
"epoch": 0.0470106075216972,
|
|
"grad_norm": 5.753119945526123,
|
|
"learning_rate": 0.00019893355564612936,
|
|
"loss": 1.0944817352294922,
|
|
"num_input_tokens_seen": 64220496,
|
|
"step": 48750,
|
|
"train_runtime": 91489.9297,
|
|
"train_tokens_per_second": 701.941
|
|
},
|
|
{
|
|
"epoch": 0.047058823529411764,
|
|
"grad_norm": 4.728751182556152,
|
|
"learning_rate": 0.00019893134714737707,
|
|
"loss": 1.0584978485107421,
|
|
"num_input_tokens_seen": 64256584,
|
|
"step": 48800,
|
|
"train_runtime": 91552.1562,
|
|
"train_tokens_per_second": 701.858
|
|
},
|
|
{
|
|
"epoch": 0.047107039537126326,
|
|
"grad_norm": 4.633210182189941,
|
|
"learning_rate": 0.00019892913637648487,
|
|
"loss": 1.0972130584716797,
|
|
"num_input_tokens_seen": 64293728,
|
|
"step": 48850,
|
|
"train_runtime": 91615.3405,
|
|
"train_tokens_per_second": 701.779
|
|
},
|
|
{
|
|
"epoch": 0.04715525554484089,
|
|
"grad_norm": 6.403964519500732,
|
|
"learning_rate": 0.0001989269233335036,
|
|
"loss": 1.1198429107666015,
|
|
"num_input_tokens_seen": 64330832,
|
|
"step": 48900,
|
|
"train_runtime": 91678.1253,
|
|
"train_tokens_per_second": 701.703
|
|
},
|
|
{
|
|
"epoch": 0.04720347155255545,
|
|
"grad_norm": 5.978786468505859,
|
|
"learning_rate": 0.00019892470801848405,
|
|
"loss": 1.0726306915283204,
|
|
"num_input_tokens_seen": 64368232,
|
|
"step": 48950,
|
|
"train_runtime": 91740.7348,
|
|
"train_tokens_per_second": 701.632
|
|
},
|
|
{
|
|
"epoch": 0.04725168756027001,
|
|
"grad_norm": 5.547175407409668,
|
|
"learning_rate": 0.0001989224904314771,
|
|
"loss": 1.0509803771972657,
|
|
"num_input_tokens_seen": 64406672,
|
|
"step": 49000,
|
|
"train_runtime": 91804.1858,
|
|
"train_tokens_per_second": 701.566
|
|
},
|
|
{
|
|
"epoch": 0.04729990356798457,
|
|
"grad_norm": 5.752764701843262,
|
|
"learning_rate": 0.00019892027057253367,
|
|
"loss": 1.0961869049072266,
|
|
"num_input_tokens_seen": 64444128,
|
|
"step": 49050,
|
|
"train_runtime": 91867.0187,
|
|
"train_tokens_per_second": 701.494
|
|
},
|
|
{
|
|
"epoch": 0.047348119575699135,
|
|
"grad_norm": 6.716757297515869,
|
|
"learning_rate": 0.00019891804844170477,
|
|
"loss": 1.1393115997314454,
|
|
"num_input_tokens_seen": 64481528,
|
|
"step": 49100,
|
|
"train_runtime": 91930.602,
|
|
"train_tokens_per_second": 701.415
|
|
},
|
|
{
|
|
"epoch": 0.04739633558341369,
|
|
"grad_norm": 4.860964775085449,
|
|
"learning_rate": 0.00019891582403904146,
|
|
"loss": 1.0503327178955078,
|
|
"num_input_tokens_seen": 64518216,
|
|
"step": 49150,
|
|
"train_runtime": 91993.5422,
|
|
"train_tokens_per_second": 701.334
|
|
},
|
|
{
|
|
"epoch": 0.04744455159112825,
|
|
"grad_norm": 5.724836826324463,
|
|
"learning_rate": 0.00019891359736459475,
|
|
"loss": 1.0820333099365234,
|
|
"num_input_tokens_seen": 64554360,
|
|
"step": 49200,
|
|
"train_runtime": 92055.9565,
|
|
"train_tokens_per_second": 701.251
|
|
},
|
|
{
|
|
"epoch": 0.047492767598842814,
|
|
"grad_norm": 6.1201887130737305,
|
|
"learning_rate": 0.00019891136841841583,
|
|
"loss": 1.1426984405517577,
|
|
"num_input_tokens_seen": 64591040,
|
|
"step": 49250,
|
|
"train_runtime": 92118.8965,
|
|
"train_tokens_per_second": 701.17
|
|
},
|
|
{
|
|
"epoch": 0.047540983606557376,
|
|
"grad_norm": 5.48168420791626,
|
|
"learning_rate": 0.0001989091372005559,
|
|
"loss": 1.0797975158691406,
|
|
"num_input_tokens_seen": 64628464,
|
|
"step": 49300,
|
|
"train_runtime": 92182.0349,
|
|
"train_tokens_per_second": 701.096
|
|
},
|
|
{
|
|
"epoch": 0.04758919961427194,
|
|
"grad_norm": 4.704808712005615,
|
|
"learning_rate": 0.00019890690371106615,
|
|
"loss": 1.0980282592773438,
|
|
"num_input_tokens_seen": 64665184,
|
|
"step": 49350,
|
|
"train_runtime": 92245.1335,
|
|
"train_tokens_per_second": 701.015
|
|
},
|
|
{
|
|
"epoch": 0.0476374156219865,
|
|
"grad_norm": 6.813385486602783,
|
|
"learning_rate": 0.00019890466794999796,
|
|
"loss": 1.062330856323242,
|
|
"num_input_tokens_seen": 64702216,
|
|
"step": 49400,
|
|
"train_runtime": 92308.0431,
|
|
"train_tokens_per_second": 700.938
|
|
},
|
|
{
|
|
"epoch": 0.04768563162970106,
|
|
"grad_norm": 6.02133321762085,
|
|
"learning_rate": 0.0001989024299174026,
|
|
"loss": 1.1035018157958985,
|
|
"num_input_tokens_seen": 64739528,
|
|
"step": 49450,
|
|
"train_runtime": 92370.798,
|
|
"train_tokens_per_second": 700.866
|
|
},
|
|
{
|
|
"epoch": 0.04773384763741562,
|
|
"grad_norm": 6.185251712799072,
|
|
"learning_rate": 0.00019890018961333153,
|
|
"loss": 1.0923016357421875,
|
|
"num_input_tokens_seen": 64776744,
|
|
"step": 49500,
|
|
"train_runtime": 92433.725,
|
|
"train_tokens_per_second": 700.791
|
|
},
|
|
{
|
|
"epoch": 0.047782063645130185,
|
|
"grad_norm": 6.7074971199035645,
|
|
"learning_rate": 0.00019889794703783616,
|
|
"loss": 1.0900765991210937,
|
|
"num_input_tokens_seen": 64814192,
|
|
"step": 49550,
|
|
"train_runtime": 92496.505,
|
|
"train_tokens_per_second": 700.72
|
|
},
|
|
{
|
|
"epoch": 0.04783027965284475,
|
|
"grad_norm": 5.964073181152344,
|
|
"learning_rate": 0.000198895702190968,
|
|
"loss": 1.0909808349609376,
|
|
"num_input_tokens_seen": 64851776,
|
|
"step": 49600,
|
|
"train_runtime": 92559.4153,
|
|
"train_tokens_per_second": 700.65
|
|
},
|
|
{
|
|
"epoch": 0.04787849566055931,
|
|
"grad_norm": 5.655144214630127,
|
|
"learning_rate": 0.00019889345507277862,
|
|
"loss": 1.114906005859375,
|
|
"num_input_tokens_seen": 64890040,
|
|
"step": 49650,
|
|
"train_runtime": 92622.8933,
|
|
"train_tokens_per_second": 700.583
|
|
},
|
|
{
|
|
"epoch": 0.047926711668273864,
|
|
"grad_norm": 5.429858684539795,
|
|
"learning_rate": 0.00019889120568331964,
|
|
"loss": 1.0441293334960937,
|
|
"num_input_tokens_seen": 64926872,
|
|
"step": 49700,
|
|
"train_runtime": 92685.6332,
|
|
"train_tokens_per_second": 700.506
|
|
},
|
|
{
|
|
"epoch": 0.047974927675988426,
|
|
"grad_norm": 12.561508178710938,
|
|
"learning_rate": 0.00019888895402264272,
|
|
"loss": 1.0725577545166016,
|
|
"num_input_tokens_seen": 64963816,
|
|
"step": 49750,
|
|
"train_runtime": 92748.8795,
|
|
"train_tokens_per_second": 700.427
|
|
},
|
|
{
|
|
"epoch": 0.04802314368370299,
|
|
"grad_norm": 6.3970561027526855,
|
|
"learning_rate": 0.00019888670009079955,
|
|
"loss": 1.0769759368896485,
|
|
"num_input_tokens_seen": 65001704,
|
|
"step": 49800,
|
|
"train_runtime": 92811.6195,
|
|
"train_tokens_per_second": 700.362
|
|
},
|
|
{
|
|
"epoch": 0.04807135969141755,
|
|
"grad_norm": 6.208064079284668,
|
|
"learning_rate": 0.00019888444388784188,
|
|
"loss": 1.1256571197509766,
|
|
"num_input_tokens_seen": 65039696,
|
|
"step": 49850,
|
|
"train_runtime": 92875.4242,
|
|
"train_tokens_per_second": 700.29
|
|
},
|
|
{
|
|
"epoch": 0.04811957569913211,
|
|
"grad_norm": 5.842721939086914,
|
|
"learning_rate": 0.0001988821854138216,
|
|
"loss": 1.0794252777099609,
|
|
"num_input_tokens_seen": 65077536,
|
|
"step": 49900,
|
|
"train_runtime": 92938.2925,
|
|
"train_tokens_per_second": 700.223
|
|
},
|
|
{
|
|
"epoch": 0.04816779170684667,
|
|
"grad_norm": 6.414629936218262,
|
|
"learning_rate": 0.00019887992466879052,
|
|
"loss": 1.0827420806884767,
|
|
"num_input_tokens_seen": 65114808,
|
|
"step": 49950,
|
|
"train_runtime": 93001.7318,
|
|
"train_tokens_per_second": 700.146
|
|
},
|
|
{
|
|
"epoch": 0.048216007714561235,
|
|
"grad_norm": 4.840547561645508,
|
|
"learning_rate": 0.00019887766165280058,
|
|
"loss": 1.1061834716796874,
|
|
"num_input_tokens_seen": 65152840,
|
|
"step": 50000,
|
|
"train_runtime": 93065.1096,
|
|
"train_tokens_per_second": 700.078
|
|
},
|
|
{
|
|
"epoch": 0.048216007714561235,
|
|
"eval_loss": 2.4077675342559814,
|
|
"eval_runtime": 237.0011,
|
|
"eval_samples_per_second": 4.219,
|
|
"eval_steps_per_second": 4.219,
|
|
"num_input_tokens_seen": 65152840,
|
|
"step": 50000
|
|
},
|
|
{
|
|
"epoch": 0.0482642237222758,
|
|
"grad_norm": 5.700648784637451,
|
|
"learning_rate": 0.00019887539636590374,
|
|
"loss": 1.125943374633789,
|
|
"num_input_tokens_seen": 65189608,
|
|
"step": 50050,
|
|
"train_runtime": 93365.726,
|
|
"train_tokens_per_second": 698.218
|
|
},
|
|
{
|
|
"epoch": 0.04831243972999036,
|
|
"grad_norm": 5.728050231933594,
|
|
"learning_rate": 0.00019887312880815204,
|
|
"loss": 1.0888665771484376,
|
|
"num_input_tokens_seen": 65227760,
|
|
"step": 50100,
|
|
"train_runtime": 93429.3411,
|
|
"train_tokens_per_second": 698.151
|
|
},
|
|
{
|
|
"epoch": 0.04836065573770492,
|
|
"grad_norm": 6.099240779876709,
|
|
"learning_rate": 0.00019887085897959757,
|
|
"loss": 1.0750748443603515,
|
|
"num_input_tokens_seen": 65264776,
|
|
"step": 50150,
|
|
"train_runtime": 93492.0562,
|
|
"train_tokens_per_second": 698.078
|
|
},
|
|
{
|
|
"epoch": 0.04840887174541948,
|
|
"grad_norm": 10.261608123779297,
|
|
"learning_rate": 0.0001988685868802924,
|
|
"loss": 1.0469098663330079,
|
|
"num_input_tokens_seen": 65302472,
|
|
"step": 50200,
|
|
"train_runtime": 93554.8652,
|
|
"train_tokens_per_second": 698.013
|
|
},
|
|
{
|
|
"epoch": 0.04845708775313404,
|
|
"grad_norm": 6.981719970703125,
|
|
"learning_rate": 0.00019886631251028882,
|
|
"loss": 1.0855471038818358,
|
|
"num_input_tokens_seen": 65340824,
|
|
"step": 50250,
|
|
"train_runtime": 93618.3667,
|
|
"train_tokens_per_second": 697.949
|
|
},
|
|
{
|
|
"epoch": 0.0485053037608486,
|
|
"grad_norm": 8.098699569702148,
|
|
"learning_rate": 0.00019886403586963898,
|
|
"loss": 1.0810073852539062,
|
|
"num_input_tokens_seen": 65378272,
|
|
"step": 50300,
|
|
"train_runtime": 93681.7734,
|
|
"train_tokens_per_second": 697.876
|
|
},
|
|
{
|
|
"epoch": 0.04855351976856316,
|
|
"grad_norm": 6.0232062339782715,
|
|
"learning_rate": 0.0001988617569583952,
|
|
"loss": 1.0984326934814452,
|
|
"num_input_tokens_seen": 65416032,
|
|
"step": 50350,
|
|
"train_runtime": 93744.5054,
|
|
"train_tokens_per_second": 697.812
|
|
},
|
|
{
|
|
"epoch": 0.04860173577627772,
|
|
"grad_norm": 6.814391613006592,
|
|
"learning_rate": 0.0001988594757766098,
|
|
"loss": 1.0849295806884767,
|
|
"num_input_tokens_seen": 65453816,
|
|
"step": 50400,
|
|
"train_runtime": 93807.6702,
|
|
"train_tokens_per_second": 697.745
|
|
},
|
|
{
|
|
"epoch": 0.048649951783992285,
|
|
"grad_norm": 5.750856876373291,
|
|
"learning_rate": 0.0001988571923243352,
|
|
"loss": 1.0339530181884766,
|
|
"num_input_tokens_seen": 65492328,
|
|
"step": 50450,
|
|
"train_runtime": 93870.4397,
|
|
"train_tokens_per_second": 697.689
|
|
},
|
|
{
|
|
"epoch": 0.048698167791706846,
|
|
"grad_norm": 4.561461925506592,
|
|
"learning_rate": 0.00019885490660162381,
|
|
"loss": 1.1213204956054688,
|
|
"num_input_tokens_seen": 65529936,
|
|
"step": 50500,
|
|
"train_runtime": 93933.3925,
|
|
"train_tokens_per_second": 697.621
|
|
},
|
|
{
|
|
"epoch": 0.04874638379942141,
|
|
"grad_norm": 4.850639820098877,
|
|
"learning_rate": 0.00019885261860852816,
|
|
"loss": 1.0419647216796875,
|
|
"num_input_tokens_seen": 65568016,
|
|
"step": 50550,
|
|
"train_runtime": 93995.6215,
|
|
"train_tokens_per_second": 697.565
|
|
},
|
|
{
|
|
"epoch": 0.04879459980713597,
|
|
"grad_norm": 7.556947231292725,
|
|
"learning_rate": 0.00019885032834510076,
|
|
"loss": 1.0060662841796875,
|
|
"num_input_tokens_seen": 65606736,
|
|
"step": 50600,
|
|
"train_runtime": 94058.8457,
|
|
"train_tokens_per_second": 697.507
|
|
},
|
|
{
|
|
"epoch": 0.04884281581485053,
|
|
"grad_norm": 5.40386962890625,
|
|
"learning_rate": 0.00019884803581139427,
|
|
"loss": 1.040711441040039,
|
|
"num_input_tokens_seen": 65645360,
|
|
"step": 50650,
|
|
"train_runtime": 94121.946,
|
|
"train_tokens_per_second": 697.45
|
|
},
|
|
{
|
|
"epoch": 0.048891031822565094,
|
|
"grad_norm": 6.229318618774414,
|
|
"learning_rate": 0.00019884574100746124,
|
|
"loss": 1.0852950286865235,
|
|
"num_input_tokens_seen": 65682912,
|
|
"step": 50700,
|
|
"train_runtime": 94185.0042,
|
|
"train_tokens_per_second": 697.382
|
|
},
|
|
{
|
|
"epoch": 0.048939247830279656,
|
|
"grad_norm": 5.2549567222595215,
|
|
"learning_rate": 0.0001988434439333545,
|
|
"loss": 1.096235885620117,
|
|
"num_input_tokens_seen": 65720584,
|
|
"step": 50750,
|
|
"train_runtime": 94247.5448,
|
|
"train_tokens_per_second": 697.319
|
|
},
|
|
{
|
|
"epoch": 0.04898746383799421,
|
|
"grad_norm": 6.863006114959717,
|
|
"learning_rate": 0.00019884114458912673,
|
|
"loss": 1.1132228088378906,
|
|
"num_input_tokens_seen": 65757848,
|
|
"step": 50800,
|
|
"train_runtime": 94310.1269,
|
|
"train_tokens_per_second": 697.251
|
|
},
|
|
{
|
|
"epoch": 0.04903567984570877,
|
|
"grad_norm": 6.033262729644775,
|
|
"learning_rate": 0.00019883884297483074,
|
|
"loss": 1.1211375427246093,
|
|
"num_input_tokens_seen": 65795840,
|
|
"step": 50850,
|
|
"train_runtime": 94373.2269,
|
|
"train_tokens_per_second": 697.188
|
|
},
|
|
{
|
|
"epoch": 0.049083895853423334,
|
|
"grad_norm": 6.107789993286133,
|
|
"learning_rate": 0.0001988365390905194,
|
|
"loss": 1.07373291015625,
|
|
"num_input_tokens_seen": 65832760,
|
|
"step": 50900,
|
|
"train_runtime": 94435.8649,
|
|
"train_tokens_per_second": 697.116
|
|
},
|
|
{
|
|
"epoch": 0.049132111861137896,
|
|
"grad_norm": 5.7255964279174805,
|
|
"learning_rate": 0.00019883423293624562,
|
|
"loss": 1.0791056060791016,
|
|
"num_input_tokens_seen": 65871256,
|
|
"step": 50950,
|
|
"train_runtime": 94499.2445,
|
|
"train_tokens_per_second": 697.056
|
|
},
|
|
{
|
|
"epoch": 0.04918032786885246,
|
|
"grad_norm": 7.078096866607666,
|
|
"learning_rate": 0.00019883192451206237,
|
|
"loss": 1.0391049194335937,
|
|
"num_input_tokens_seen": 65910000,
|
|
"step": 51000,
|
|
"train_runtime": 94562.5208,
|
|
"train_tokens_per_second": 696.999
|
|
},
|
|
{
|
|
"epoch": 0.04922854387656702,
|
|
"grad_norm": 4.815710544586182,
|
|
"learning_rate": 0.0001988296138180227,
|
|
"loss": 1.0911857604980468,
|
|
"num_input_tokens_seen": 65948112,
|
|
"step": 51050,
|
|
"train_runtime": 94625.1273,
|
|
"train_tokens_per_second": 696.941
|
|
},
|
|
{
|
|
"epoch": 0.04927675988428158,
|
|
"grad_norm": 5.306153297424316,
|
|
"learning_rate": 0.00019882730085417962,
|
|
"loss": 1.0687948608398437,
|
|
"num_input_tokens_seen": 65986848,
|
|
"step": 51100,
|
|
"train_runtime": 94687.9221,
|
|
"train_tokens_per_second": 696.888
|
|
},
|
|
{
|
|
"epoch": 0.049324975891996144,
|
|
"grad_norm": 7.072540283203125,
|
|
"learning_rate": 0.0001988249856205863,
|
|
"loss": 1.0915890502929688,
|
|
"num_input_tokens_seen": 66025192,
|
|
"step": 51150,
|
|
"train_runtime": 94750.1131,
|
|
"train_tokens_per_second": 696.835
|
|
},
|
|
{
|
|
"epoch": 0.049373191899710706,
|
|
"grad_norm": 7.317570686340332,
|
|
"learning_rate": 0.00019882266811729592,
|
|
"loss": 1.0991387939453126,
|
|
"num_input_tokens_seen": 66063944,
|
|
"step": 51200,
|
|
"train_runtime": 94813.6016,
|
|
"train_tokens_per_second": 696.777
|
|
},
|
|
{
|
|
"epoch": 0.04942140790742527,
|
|
"grad_norm": 5.882178783416748,
|
|
"learning_rate": 0.00019882034834436163,
|
|
"loss": 1.092769546508789,
|
|
"num_input_tokens_seen": 66101432,
|
|
"step": 51250,
|
|
"train_runtime": 94876.6509,
|
|
"train_tokens_per_second": 696.709
|
|
},
|
|
{
|
|
"epoch": 0.04946962391513983,
|
|
"grad_norm": 7.188403606414795,
|
|
"learning_rate": 0.00019881802630183676,
|
|
"loss": 1.0633984375,
|
|
"num_input_tokens_seen": 66139176,
|
|
"step": 51300,
|
|
"train_runtime": 94939.5721,
|
|
"train_tokens_per_second": 696.645
|
|
},
|
|
{
|
|
"epoch": 0.04951783992285439,
|
|
"grad_norm": 6.992368698120117,
|
|
"learning_rate": 0.00019881570198977463,
|
|
"loss": 1.0731966400146484,
|
|
"num_input_tokens_seen": 66176872,
|
|
"step": 51350,
|
|
"train_runtime": 95002.0141,
|
|
"train_tokens_per_second": 696.584
|
|
},
|
|
{
|
|
"epoch": 0.049566055930568946,
|
|
"grad_norm": 5.417004108428955,
|
|
"learning_rate": 0.00019881337540822867,
|
|
"loss": 1.1604190826416017,
|
|
"num_input_tokens_seen": 66214392,
|
|
"step": 51400,
|
|
"train_runtime": 95064.7013,
|
|
"train_tokens_per_second": 696.519
|
|
},
|
|
{
|
|
"epoch": 0.04961427193828351,
|
|
"grad_norm": 6.552857398986816,
|
|
"learning_rate": 0.00019881104655725224,
|
|
"loss": 1.0725574493408203,
|
|
"num_input_tokens_seen": 66251832,
|
|
"step": 51450,
|
|
"train_runtime": 95127.9031,
|
|
"train_tokens_per_second": 696.45
|
|
},
|
|
{
|
|
"epoch": 0.04966248794599807,
|
|
"grad_norm": 4.994574546813965,
|
|
"learning_rate": 0.00019880871543689888,
|
|
"loss": 1.0776808166503906,
|
|
"num_input_tokens_seen": 66290088,
|
|
"step": 51500,
|
|
"train_runtime": 95190.7122,
|
|
"train_tokens_per_second": 696.392
|
|
},
|
|
{
|
|
"epoch": 0.04971070395371263,
|
|
"grad_norm": 5.774503707885742,
|
|
"learning_rate": 0.00019880638204722209,
|
|
"loss": 1.1202733612060547,
|
|
"num_input_tokens_seen": 66327424,
|
|
"step": 51550,
|
|
"train_runtime": 95253.1446,
|
|
"train_tokens_per_second": 696.328
|
|
},
|
|
{
|
|
"epoch": 0.049758919961427193,
|
|
"grad_norm": 7.75919246673584,
|
|
"learning_rate": 0.00019880404638827548,
|
|
"loss": 1.090117416381836,
|
|
"num_input_tokens_seen": 66365392,
|
|
"step": 51600,
|
|
"train_runtime": 95315.996,
|
|
"train_tokens_per_second": 696.267
|
|
},
|
|
{
|
|
"epoch": 0.049807135969141755,
|
|
"grad_norm": 5.369015693664551,
|
|
"learning_rate": 0.00019880170846011273,
|
|
"loss": 1.141769561767578,
|
|
"num_input_tokens_seen": 66402960,
|
|
"step": 51650,
|
|
"train_runtime": 95378.2619,
|
|
"train_tokens_per_second": 696.206
|
|
},
|
|
{
|
|
"epoch": 0.04985535197685632,
|
|
"grad_norm": 5.431924819946289,
|
|
"learning_rate": 0.00019879936826278744,
|
|
"loss": 1.0869375610351562,
|
|
"num_input_tokens_seen": 66440520,
|
|
"step": 51700,
|
|
"train_runtime": 95440.2472,
|
|
"train_tokens_per_second": 696.148
|
|
},
|
|
{
|
|
"epoch": 0.04990356798457088,
|
|
"grad_norm": 5.179593086242676,
|
|
"learning_rate": 0.00019879702579635343,
|
|
"loss": 1.081113052368164,
|
|
"num_input_tokens_seen": 66478160,
|
|
"step": 51750,
|
|
"train_runtime": 95503.0121,
|
|
"train_tokens_per_second": 696.084
|
|
},
|
|
{
|
|
"epoch": 0.04995178399228544,
|
|
"grad_norm": 6.182527542114258,
|
|
"learning_rate": 0.0001987946810608645,
|
|
"loss": 1.0739824676513672,
|
|
"num_input_tokens_seen": 66515776,
|
|
"step": 51800,
|
|
"train_runtime": 95565.5083,
|
|
"train_tokens_per_second": 696.023
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"grad_norm": 6.8564066886901855,
|
|
"learning_rate": 0.00019879233405637448,
|
|
"loss": 1.1114073944091798,
|
|
"num_input_tokens_seen": 66554728,
|
|
"step": 51850,
|
|
"train_runtime": 95628.4422,
|
|
"train_tokens_per_second": 695.972
|
|
},
|
|
{
|
|
"epoch": 0.050048216007714565,
|
|
"grad_norm": 6.1922502517700195,
|
|
"learning_rate": 0.00019878998478293727,
|
|
"loss": 1.0949848175048829,
|
|
"num_input_tokens_seen": 66592440,
|
|
"step": 51900,
|
|
"train_runtime": 95691.4481,
|
|
"train_tokens_per_second": 695.908
|
|
},
|
|
{
|
|
"epoch": 0.05009643201542912,
|
|
"grad_norm": 7.425135135650635,
|
|
"learning_rate": 0.0001987876332406068,
|
|
"loss": 1.1195326232910157,
|
|
"num_input_tokens_seen": 66630640,
|
|
"step": 51950,
|
|
"train_runtime": 95754.6022,
|
|
"train_tokens_per_second": 695.848
|
|
},
|
|
{
|
|
"epoch": 0.05014464802314368,
|
|
"grad_norm": 8.133561134338379,
|
|
"learning_rate": 0.00019878527942943718,
|
|
"loss": 1.0850336456298828,
|
|
"num_input_tokens_seen": 66668408,
|
|
"step": 52000,
|
|
"train_runtime": 95817.5756,
|
|
"train_tokens_per_second": 695.785
|
|
},
|
|
{
|
|
"epoch": 0.05019286403085824,
|
|
"grad_norm": 5.440564155578613,
|
|
"learning_rate": 0.00019878292334948235,
|
|
"loss": 1.076968231201172,
|
|
"num_input_tokens_seen": 66707160,
|
|
"step": 52050,
|
|
"train_runtime": 95880.4108,
|
|
"train_tokens_per_second": 695.733
|
|
},
|
|
{
|
|
"epoch": 0.050241080038572805,
|
|
"grad_norm": 6.607757568359375,
|
|
"learning_rate": 0.00019878056500079646,
|
|
"loss": 1.0913760375976562,
|
|
"num_input_tokens_seen": 66744152,
|
|
"step": 52100,
|
|
"train_runtime": 95942.5529,
|
|
"train_tokens_per_second": 695.668
|
|
},
|
|
{
|
|
"epoch": 0.05028929604628737,
|
|
"grad_norm": 5.116559982299805,
|
|
"learning_rate": 0.00019877820438343372,
|
|
"loss": 1.0788774108886718,
|
|
"num_input_tokens_seen": 66782736,
|
|
"step": 52150,
|
|
"train_runtime": 96005.8687,
|
|
"train_tokens_per_second": 695.611
|
|
},
|
|
{
|
|
"epoch": 0.05033751205400193,
|
|
"grad_norm": 5.994877338409424,
|
|
"learning_rate": 0.00019877584149744827,
|
|
"loss": 1.1152052307128906,
|
|
"num_input_tokens_seen": 66820360,
|
|
"step": 52200,
|
|
"train_runtime": 96068.5927,
|
|
"train_tokens_per_second": 695.548
|
|
},
|
|
{
|
|
"epoch": 0.05038572806171649,
|
|
"grad_norm": 6.56815242767334,
|
|
"learning_rate": 0.00019877347634289448,
|
|
"loss": 1.111905288696289,
|
|
"num_input_tokens_seen": 66858512,
|
|
"step": 52250,
|
|
"train_runtime": 96131.6678,
|
|
"train_tokens_per_second": 695.489
|
|
},
|
|
{
|
|
"epoch": 0.05043394406943105,
|
|
"grad_norm": 4.818546772003174,
|
|
"learning_rate": 0.00019877110891982657,
|
|
"loss": 1.0569239807128907,
|
|
"num_input_tokens_seen": 66896496,
|
|
"step": 52300,
|
|
"train_runtime": 96194.1606,
|
|
"train_tokens_per_second": 695.432
|
|
},
|
|
{
|
|
"epoch": 0.050482160077145614,
|
|
"grad_norm": 9.712207794189453,
|
|
"learning_rate": 0.00019876873922829895,
|
|
"loss": 1.065798568725586,
|
|
"num_input_tokens_seen": 66933704,
|
|
"step": 52350,
|
|
"train_runtime": 96256.1691,
|
|
"train_tokens_per_second": 695.371
|
|
},
|
|
{
|
|
"epoch": 0.050530376084860176,
|
|
"grad_norm": 6.784215450286865,
|
|
"learning_rate": 0.00019876636726836604,
|
|
"loss": 1.1093346405029296,
|
|
"num_input_tokens_seen": 66972184,
|
|
"step": 52400,
|
|
"train_runtime": 96319.2181,
|
|
"train_tokens_per_second": 695.315
|
|
},
|
|
{
|
|
"epoch": 0.05057859209257474,
|
|
"grad_norm": 6.617947101593018,
|
|
"learning_rate": 0.00019876399304008234,
|
|
"loss": 1.0484017181396483,
|
|
"num_input_tokens_seen": 67009232,
|
|
"step": 52450,
|
|
"train_runtime": 96381.7055,
|
|
"train_tokens_per_second": 695.248
|
|
},
|
|
{
|
|
"epoch": 0.05062680810028929,
|
|
"grad_norm": 6.607892036437988,
|
|
"learning_rate": 0.0001987616165435023,
|
|
"loss": 1.1289513397216797,
|
|
"num_input_tokens_seen": 67047264,
|
|
"step": 52500,
|
|
"train_runtime": 96444.2957,
|
|
"train_tokens_per_second": 695.192
|
|
},
|
|
{
|
|
"epoch": 0.050675024108003855,
|
|
"grad_norm": 6.265863418579102,
|
|
"learning_rate": 0.00019875923777868063,
|
|
"loss": 1.0844400787353516,
|
|
"num_input_tokens_seen": 67085488,
|
|
"step": 52550,
|
|
"train_runtime": 96506.7129,
|
|
"train_tokens_per_second": 695.138
|
|
},
|
|
{
|
|
"epoch": 0.05072324011571842,
|
|
"grad_norm": 6.795964241027832,
|
|
"learning_rate": 0.00019875690438855994,
|
|
"loss": 1.0714231872558593,
|
|
"num_input_tokens_seen": 67123976,
|
|
"step": 52600,
|
|
"train_runtime": 96569.1753,
|
|
"train_tokens_per_second": 695.087
|
|
},
|
|
{
|
|
"epoch": 0.05077145612343298,
|
|
"grad_norm": 5.047910213470459,
|
|
"learning_rate": 0.00019875456882012383,
|
|
"loss": 1.1059886932373046,
|
|
"num_input_tokens_seen": 67162024,
|
|
"step": 52650,
|
|
"train_runtime": 96631.9507,
|
|
"train_tokens_per_second": 695.029
|
|
},
|
|
{
|
|
"epoch": 0.05081967213114754,
|
|
"grad_norm": 6.233209609985352,
|
|
"learning_rate": 0.0001987521833416271,
|
|
"loss": 1.0813446807861329,
|
|
"num_input_tokens_seen": 67200760,
|
|
"step": 52700,
|
|
"train_runtime": 96695.1566,
|
|
"train_tokens_per_second": 694.975
|
|
},
|
|
{
|
|
"epoch": 0.0508678881388621,
|
|
"grad_norm": 6.517409324645996,
|
|
"learning_rate": 0.00019874979559510533,
|
|
"loss": 1.1201009368896484,
|
|
"num_input_tokens_seen": 67239152,
|
|
"step": 52750,
|
|
"train_runtime": 96758.2469,
|
|
"train_tokens_per_second": 694.919
|
|
},
|
|
{
|
|
"epoch": 0.050916104146576664,
|
|
"grad_norm": 6.549930095672607,
|
|
"learning_rate": 0.00019874740558061332,
|
|
"loss": 1.0376773834228517,
|
|
"num_input_tokens_seen": 67276456,
|
|
"step": 52800,
|
|
"train_runtime": 96820.3519,
|
|
"train_tokens_per_second": 694.859
|
|
},
|
|
{
|
|
"epoch": 0.050964320154291226,
|
|
"grad_norm": 5.80580997467041,
|
|
"learning_rate": 0.00019874501329820602,
|
|
"loss": 1.081588134765625,
|
|
"num_input_tokens_seen": 67314968,
|
|
"step": 52850,
|
|
"train_runtime": 96883.2888,
|
|
"train_tokens_per_second": 694.805
|
|
},
|
|
{
|
|
"epoch": 0.05101253616200579,
|
|
"grad_norm": 6.019951343536377,
|
|
"learning_rate": 0.00019874261874793835,
|
|
"loss": 1.0572615814208985,
|
|
"num_input_tokens_seen": 67353792,
|
|
"step": 52900,
|
|
"train_runtime": 96946.5742,
|
|
"train_tokens_per_second": 694.752
|
|
},
|
|
{
|
|
"epoch": 0.05106075216972035,
|
|
"grad_norm": 5.5576395988464355,
|
|
"learning_rate": 0.00019874022192986528,
|
|
"loss": 1.1029815673828125,
|
|
"num_input_tokens_seen": 67391456,
|
|
"step": 52950,
|
|
"train_runtime": 97009.2764,
|
|
"train_tokens_per_second": 694.691
|
|
},
|
|
{
|
|
"epoch": 0.05110896817743491,
|
|
"grad_norm": 6.625574588775635,
|
|
"learning_rate": 0.00019873782284404186,
|
|
"loss": 1.0263084411621093,
|
|
"num_input_tokens_seen": 67428600,
|
|
"step": 53000,
|
|
"train_runtime": 97072.1366,
|
|
"train_tokens_per_second": 694.624
|
|
},
|
|
{
|
|
"epoch": 0.05115718418514947,
|
|
"grad_norm": 4.897188186645508,
|
|
"learning_rate": 0.00019873542149052327,
|
|
"loss": 1.0459373474121094,
|
|
"num_input_tokens_seen": 67466960,
|
|
"step": 53050,
|
|
"train_runtime": 97136.2405,
|
|
"train_tokens_per_second": 694.56
|
|
},
|
|
{
|
|
"epoch": 0.05120540019286403,
|
|
"grad_norm": 5.395008087158203,
|
|
"learning_rate": 0.00019873301786936453,
|
|
"loss": 1.058653793334961,
|
|
"num_input_tokens_seen": 67505040,
|
|
"step": 53100,
|
|
"train_runtime": 97198.8054,
|
|
"train_tokens_per_second": 694.505
|
|
},
|
|
{
|
|
"epoch": 0.05125361620057859,
|
|
"grad_norm": 5.663567543029785,
|
|
"learning_rate": 0.00019873061198062095,
|
|
"loss": 1.0988433837890625,
|
|
"num_input_tokens_seen": 67543536,
|
|
"step": 53150,
|
|
"train_runtime": 97261.3662,
|
|
"train_tokens_per_second": 694.454
|
|
},
|
|
{
|
|
"epoch": 0.05130183220829315,
|
|
"grad_norm": 5.933988571166992,
|
|
"learning_rate": 0.00019872820382434774,
|
|
"loss": 1.0805130767822266,
|
|
"num_input_tokens_seen": 67581376,
|
|
"step": 53200,
|
|
"train_runtime": 97323.7139,
|
|
"train_tokens_per_second": 694.398
|
|
},
|
|
{
|
|
"epoch": 0.051350048216007714,
|
|
"grad_norm": 7.160494327545166,
|
|
"learning_rate": 0.0001987257934006002,
|
|
"loss": 1.0515485382080079,
|
|
"num_input_tokens_seen": 67619640,
|
|
"step": 53250,
|
|
"train_runtime": 97386.3213,
|
|
"train_tokens_per_second": 694.344
|
|
},
|
|
{
|
|
"epoch": 0.051398264223722276,
|
|
"grad_norm": 6.0483222007751465,
|
|
"learning_rate": 0.0001987233807094337,
|
|
"loss": 1.0917253875732422,
|
|
"num_input_tokens_seen": 67657264,
|
|
"step": 53300,
|
|
"train_runtime": 97449.0852,
|
|
"train_tokens_per_second": 694.283
|
|
},
|
|
{
|
|
"epoch": 0.05144648023143684,
|
|
"grad_norm": 4.916932582855225,
|
|
"learning_rate": 0.0001987209657509037,
|
|
"loss": 1.0769976043701173,
|
|
"num_input_tokens_seen": 67694856,
|
|
"step": 53350,
|
|
"train_runtime": 97511.6007,
|
|
"train_tokens_per_second": 694.224
|
|
},
|
|
{
|
|
"epoch": 0.0514946962391514,
|
|
"grad_norm": 5.656148433685303,
|
|
"learning_rate": 0.00019871854852506558,
|
|
"loss": 1.0949098205566405,
|
|
"num_input_tokens_seen": 67733040,
|
|
"step": 53400,
|
|
"train_runtime": 97574.9962,
|
|
"train_tokens_per_second": 694.164
|
|
},
|
|
{
|
|
"epoch": 0.05154291224686596,
|
|
"grad_norm": 6.365938186645508,
|
|
"learning_rate": 0.00019871612903197492,
|
|
"loss": 1.1406951904296876,
|
|
"num_input_tokens_seen": 67770600,
|
|
"step": 53450,
|
|
"train_runtime": 97637.1735,
|
|
"train_tokens_per_second": 694.107
|
|
},
|
|
{
|
|
"epoch": 0.05159112825458052,
|
|
"grad_norm": 5.59376859664917,
|
|
"learning_rate": 0.00019871370727168723,
|
|
"loss": 1.0760513305664063,
|
|
"num_input_tokens_seen": 67808392,
|
|
"step": 53500,
|
|
"train_runtime": 97699.4421,
|
|
"train_tokens_per_second": 694.051
|
|
},
|
|
{
|
|
"epoch": 0.051639344262295085,
|
|
"grad_norm": 4.8864665031433105,
|
|
"learning_rate": 0.0001987112832442582,
|
|
"loss": 1.107808837890625,
|
|
"num_input_tokens_seen": 67846216,
|
|
"step": 53550,
|
|
"train_runtime": 97762.0752,
|
|
"train_tokens_per_second": 693.993
|
|
},
|
|
{
|
|
"epoch": 0.05168756027000964,
|
|
"grad_norm": 4.693953514099121,
|
|
"learning_rate": 0.00019870885694974345,
|
|
"loss": 1.0884529113769532,
|
|
"num_input_tokens_seen": 67883464,
|
|
"step": 53600,
|
|
"train_runtime": 97824.9446,
|
|
"train_tokens_per_second": 693.928
|
|
},
|
|
{
|
|
"epoch": 0.0517357762777242,
|
|
"grad_norm": 4.380608558654785,
|
|
"learning_rate": 0.00019870642838819874,
|
|
"loss": 1.0542800903320313,
|
|
"num_input_tokens_seen": 67921336,
|
|
"step": 53650,
|
|
"train_runtime": 97887.668,
|
|
"train_tokens_per_second": 693.87
|
|
},
|
|
{
|
|
"epoch": 0.051783992285438764,
|
|
"grad_norm": 6.13679838180542,
|
|
"learning_rate": 0.00019870399755967982,
|
|
"loss": 1.1110757446289063,
|
|
"num_input_tokens_seen": 67958424,
|
|
"step": 53700,
|
|
"train_runtime": 97950.2949,
|
|
"train_tokens_per_second": 693.805
|
|
},
|
|
{
|
|
"epoch": 0.051832208293153326,
|
|
"grad_norm": 5.655235290527344,
|
|
"learning_rate": 0.0001987015644642425,
|
|
"loss": 1.0685281372070312,
|
|
"num_input_tokens_seen": 67996096,
|
|
"step": 53750,
|
|
"train_runtime": 98013.2702,
|
|
"train_tokens_per_second": 693.744
|
|
},
|
|
{
|
|
"epoch": 0.05188042430086789,
|
|
"grad_norm": 6.312813758850098,
|
|
"learning_rate": 0.0001986991291019427,
|
|
"loss": 1.1069348907470704,
|
|
"num_input_tokens_seen": 68033624,
|
|
"step": 53800,
|
|
"train_runtime": 98075.6016,
|
|
"train_tokens_per_second": 693.686
|
|
},
|
|
{
|
|
"epoch": 0.05192864030858245,
|
|
"grad_norm": 5.601328372955322,
|
|
"learning_rate": 0.00019869669147283637,
|
|
"loss": 1.082960433959961,
|
|
"num_input_tokens_seen": 68071280,
|
|
"step": 53850,
|
|
"train_runtime": 98138.4622,
|
|
"train_tokens_per_second": 693.625
|
|
},
|
|
{
|
|
"epoch": 0.05197685631629701,
|
|
"grad_norm": 6.32707405090332,
|
|
"learning_rate": 0.00019869425157697946,
|
|
"loss": 1.0730039978027344,
|
|
"num_input_tokens_seen": 68110032,
|
|
"step": 53900,
|
|
"train_runtime": 98201.2686,
|
|
"train_tokens_per_second": 693.576
|
|
},
|
|
{
|
|
"epoch": 0.05202507232401157,
|
|
"grad_norm": 6.152315139770508,
|
|
"learning_rate": 0.00019869180941442798,
|
|
"loss": 1.0593566131591796,
|
|
"num_input_tokens_seen": 68148392,
|
|
"step": 53950,
|
|
"train_runtime": 98265.2308,
|
|
"train_tokens_per_second": 693.515
|
|
},
|
|
{
|
|
"epoch": 0.052073288331726135,
|
|
"grad_norm": 6.070287227630615,
|
|
"learning_rate": 0.00019868936498523805,
|
|
"loss": 1.0442208099365233,
|
|
"num_input_tokens_seen": 68186176,
|
|
"step": 54000,
|
|
"train_runtime": 98328.4639,
|
|
"train_tokens_per_second": 693.453
|
|
},
|
|
{
|
|
"epoch": 0.0521215043394407,
|
|
"grad_norm": 4.8266448974609375,
|
|
"learning_rate": 0.00019868691828946582,
|
|
"loss": 1.0891627502441406,
|
|
"num_input_tokens_seen": 68224120,
|
|
"step": 54050,
|
|
"train_runtime": 98390.9161,
|
|
"train_tokens_per_second": 693.399
|
|
},
|
|
{
|
|
"epoch": 0.05216972034715526,
|
|
"grad_norm": 6.6126389503479,
|
|
"learning_rate": 0.00019868446932716746,
|
|
"loss": 1.1175228118896485,
|
|
"num_input_tokens_seen": 68262408,
|
|
"step": 54100,
|
|
"train_runtime": 98453.9321,
|
|
"train_tokens_per_second": 693.344
|
|
},
|
|
{
|
|
"epoch": 0.052217936354869814,
|
|
"grad_norm": 5.501289367675781,
|
|
"learning_rate": 0.00019868201809839926,
|
|
"loss": 1.0855635833740234,
|
|
"num_input_tokens_seen": 68300424,
|
|
"step": 54150,
|
|
"train_runtime": 98516.6741,
|
|
"train_tokens_per_second": 693.288
|
|
},
|
|
{
|
|
"epoch": 0.052266152362584375,
|
|
"grad_norm": 4.867039680480957,
|
|
"learning_rate": 0.00019867956460321745,
|
|
"loss": 1.1077796173095704,
|
|
"num_input_tokens_seen": 68338712,
|
|
"step": 54200,
|
|
"train_runtime": 98579.6694,
|
|
"train_tokens_per_second": 693.233
|
|
},
|
|
{
|
|
"epoch": 0.05231436837029894,
|
|
"grad_norm": 5.044168472290039,
|
|
"learning_rate": 0.00019867710884167842,
|
|
"loss": 1.0867769622802734,
|
|
"num_input_tokens_seen": 68377240,
|
|
"step": 54250,
|
|
"train_runtime": 98642.5983,
|
|
"train_tokens_per_second": 693.182
|
|
},
|
|
{
|
|
"epoch": 0.0523625843780135,
|
|
"grad_norm": 6.740469932556152,
|
|
"learning_rate": 0.0001986746508138386,
|
|
"loss": 1.066095428466797,
|
|
"num_input_tokens_seen": 68415448,
|
|
"step": 54300,
|
|
"train_runtime": 98705.7859,
|
|
"train_tokens_per_second": 693.125
|
|
},
|
|
{
|
|
"epoch": 0.05241080038572806,
|
|
"grad_norm": 7.535708427429199,
|
|
"learning_rate": 0.00019867219051975438,
|
|
"loss": 1.0797611236572267,
|
|
"num_input_tokens_seen": 68452376,
|
|
"step": 54350,
|
|
"train_runtime": 98768.3857,
|
|
"train_tokens_per_second": 693.06
|
|
},
|
|
{
|
|
"epoch": 0.05245901639344262,
|
|
"grad_norm": 5.7630510330200195,
|
|
"learning_rate": 0.00019866972795948228,
|
|
"loss": 1.105719985961914,
|
|
"num_input_tokens_seen": 68490744,
|
|
"step": 54400,
|
|
"train_runtime": 98831.2983,
|
|
"train_tokens_per_second": 693.007
|
|
},
|
|
{
|
|
"epoch": 0.052507232401157185,
|
|
"grad_norm": 6.341805934906006,
|
|
"learning_rate": 0.0001986672631330789,
|
|
"loss": 1.044507293701172,
|
|
"num_input_tokens_seen": 68529792,
|
|
"step": 54450,
|
|
"train_runtime": 98894.129,
|
|
"train_tokens_per_second": 692.961
|
|
},
|
|
{
|
|
"epoch": 0.05255544840887175,
|
|
"grad_norm": 8.729549407958984,
|
|
"learning_rate": 0.0001986647960406008,
|
|
"loss": 1.1158121490478516,
|
|
"num_input_tokens_seen": 68567632,
|
|
"step": 54500,
|
|
"train_runtime": 98957.2752,
|
|
"train_tokens_per_second": 692.901
|
|
},
|
|
{
|
|
"epoch": 0.05260366441658631,
|
|
"grad_norm": 6.706600666046143,
|
|
"learning_rate": 0.00019866232668210468,
|
|
"loss": 1.0801653289794921,
|
|
"num_input_tokens_seen": 68605456,
|
|
"step": 54550,
|
|
"train_runtime": 99020.0715,
|
|
"train_tokens_per_second": 692.844
|
|
},
|
|
{
|
|
"epoch": 0.05265188042430087,
|
|
"grad_norm": 6.021967887878418,
|
|
"learning_rate": 0.0001986598550576472,
|
|
"loss": 1.0484139251708984,
|
|
"num_input_tokens_seen": 68643592,
|
|
"step": 54600,
|
|
"train_runtime": 99082.5292,
|
|
"train_tokens_per_second": 692.792
|
|
},
|
|
{
|
|
"epoch": 0.05270009643201543,
|
|
"grad_norm": 10.24741268157959,
|
|
"learning_rate": 0.0001986573811672852,
|
|
"loss": 1.0574401092529297,
|
|
"num_input_tokens_seen": 68680712,
|
|
"step": 54650,
|
|
"train_runtime": 99145.4158,
|
|
"train_tokens_per_second": 692.727
|
|
},
|
|
{
|
|
"epoch": 0.05274831243972999,
|
|
"grad_norm": 5.185589790344238,
|
|
"learning_rate": 0.00019865490501107545,
|
|
"loss": 1.087511749267578,
|
|
"num_input_tokens_seen": 68718256,
|
|
"step": 54700,
|
|
"train_runtime": 99207.5826,
|
|
"train_tokens_per_second": 692.671
|
|
},
|
|
{
|
|
"epoch": 0.05279652844744455,
|
|
"grad_norm": 6.642266273498535,
|
|
"learning_rate": 0.00019865242658907478,
|
|
"loss": 1.0614599609375,
|
|
"num_input_tokens_seen": 68755264,
|
|
"step": 54750,
|
|
"train_runtime": 99270.4754,
|
|
"train_tokens_per_second": 692.605
|
|
},
|
|
{
|
|
"epoch": 0.05284474445515911,
|
|
"grad_norm": 5.243433475494385,
|
|
"learning_rate": 0.0001986499459013402,
|
|
"loss": 1.0708806610107422,
|
|
"num_input_tokens_seen": 68792704,
|
|
"step": 54800,
|
|
"train_runtime": 99332.9472,
|
|
"train_tokens_per_second": 692.547
|
|
},
|
|
{
|
|
"epoch": 0.05289296046287367,
|
|
"grad_norm": 5.2331953048706055,
|
|
"learning_rate": 0.00019864746294792865,
|
|
"loss": 1.071942367553711,
|
|
"num_input_tokens_seen": 68830560,
|
|
"step": 54850,
|
|
"train_runtime": 99395.4085,
|
|
"train_tokens_per_second": 692.492
|
|
},
|
|
{
|
|
"epoch": 0.052941176470588235,
|
|
"grad_norm": 4.694992542266846,
|
|
"learning_rate": 0.00019864497772889713,
|
|
"loss": 1.0969148254394532,
|
|
"num_input_tokens_seen": 68868672,
|
|
"step": 54900,
|
|
"train_runtime": 99458.2446,
|
|
"train_tokens_per_second": 692.438
|
|
},
|
|
{
|
|
"epoch": 0.052989392478302796,
|
|
"grad_norm": 5.487741470336914,
|
|
"learning_rate": 0.0001986424902443027,
|
|
"loss": 1.1086825561523437,
|
|
"num_input_tokens_seen": 68907392,
|
|
"step": 54950,
|
|
"train_runtime": 99521.4378,
|
|
"train_tokens_per_second": 692.387
|
|
},
|
|
{
|
|
"epoch": 0.05303760848601736,
|
|
"grad_norm": 6.801041603088379,
|
|
"learning_rate": 0.00019864000049420256,
|
|
"loss": 1.1428323364257813,
|
|
"num_input_tokens_seen": 68945096,
|
|
"step": 55000,
|
|
"train_runtime": 99584.5443,
|
|
"train_tokens_per_second": 692.327
|
|
},
|
|
{
|
|
"epoch": 0.05308582449373192,
|
|
"grad_norm": 6.829151153564453,
|
|
"learning_rate": 0.0001986375084786539,
|
|
"loss": 1.0789435577392579,
|
|
"num_input_tokens_seen": 68982424,
|
|
"step": 55050,
|
|
"train_runtime": 99647.5398,
|
|
"train_tokens_per_second": 692.264
|
|
},
|
|
{
|
|
"epoch": 0.05313404050144648,
|
|
"grad_norm": 4.048734664916992,
|
|
"learning_rate": 0.00019863501419771384,
|
|
"loss": 1.088760757446289,
|
|
"num_input_tokens_seen": 69020352,
|
|
"step": 55100,
|
|
"train_runtime": 99710.1232,
|
|
"train_tokens_per_second": 692.21
|
|
},
|
|
{
|
|
"epoch": 0.053182256509161044,
|
|
"grad_norm": 5.823894023895264,
|
|
"learning_rate": 0.00019863251765143977,
|
|
"loss": 1.0454186248779296,
|
|
"num_input_tokens_seen": 69057936,
|
|
"step": 55150,
|
|
"train_runtime": 99772.9263,
|
|
"train_tokens_per_second": 692.151
|
|
},
|
|
{
|
|
"epoch": 0.053230472516875606,
|
|
"grad_norm": 5.487285137176514,
|
|
"learning_rate": 0.000198630018839889,
|
|
"loss": 1.030979537963867,
|
|
"num_input_tokens_seen": 69096000,
|
|
"step": 55200,
|
|
"train_runtime": 99835.441,
|
|
"train_tokens_per_second": 692.099
|
|
},
|
|
{
|
|
"epoch": 0.05327868852459016,
|
|
"grad_norm": 4.553391933441162,
|
|
"learning_rate": 0.00019862751776311889,
|
|
"loss": 1.0549952697753906,
|
|
"num_input_tokens_seen": 69133528,
|
|
"step": 55250,
|
|
"train_runtime": 99898.0199,
|
|
"train_tokens_per_second": 692.041
|
|
},
|
|
{
|
|
"epoch": 0.05332690453230472,
|
|
"grad_norm": 5.979108810424805,
|
|
"learning_rate": 0.00019862501442118692,
|
|
"loss": 1.0889849853515625,
|
|
"num_input_tokens_seen": 69171512,
|
|
"step": 55300,
|
|
"train_runtime": 99960.6404,
|
|
"train_tokens_per_second": 691.987
|
|
},
|
|
{
|
|
"epoch": 0.053375120540019284,
|
|
"grad_norm": 6.236374378204346,
|
|
"learning_rate": 0.00019862250881415053,
|
|
"loss": 1.0809215545654296,
|
|
"num_input_tokens_seen": 69209376,
|
|
"step": 55350,
|
|
"train_runtime": 100023.1201,
|
|
"train_tokens_per_second": 691.934
|
|
},
|
|
{
|
|
"epoch": 0.053423336547733846,
|
|
"grad_norm": 5.2787370681762695,
|
|
"learning_rate": 0.00019862000094206735,
|
|
"loss": 1.094788818359375,
|
|
"num_input_tokens_seen": 69247024,
|
|
"step": 55400,
|
|
"train_runtime": 100085.8046,
|
|
"train_tokens_per_second": 691.877
|
|
},
|
|
{
|
|
"epoch": 0.05347155255544841,
|
|
"grad_norm": 6.189811706542969,
|
|
"learning_rate": 0.00019861749080499493,
|
|
"loss": 1.0825514221191406,
|
|
"num_input_tokens_seen": 69285248,
|
|
"step": 55450,
|
|
"train_runtime": 100148.4874,
|
|
"train_tokens_per_second": 691.825
|
|
},
|
|
{
|
|
"epoch": 0.05351976856316297,
|
|
"grad_norm": 4.915027141571045,
|
|
"learning_rate": 0.00019861497840299093,
|
|
"loss": 1.0550047302246093,
|
|
"num_input_tokens_seen": 69324280,
|
|
"step": 55500,
|
|
"train_runtime": 100211.5685,
|
|
"train_tokens_per_second": 691.779
|
|
},
|
|
{
|
|
"epoch": 0.05356798457087753,
|
|
"grad_norm": 6.982507705688477,
|
|
"learning_rate": 0.000198612463736113,
|
|
"loss": 1.0289259338378907,
|
|
"num_input_tokens_seen": 69362240,
|
|
"step": 55550,
|
|
"train_runtime": 100273.836,
|
|
"train_tokens_per_second": 691.728
|
|
},
|
|
{
|
|
"epoch": 0.053616200578592094,
|
|
"grad_norm": 4.410051345825195,
|
|
"learning_rate": 0.00019860994680441897,
|
|
"loss": 1.0522097778320312,
|
|
"num_input_tokens_seen": 69400304,
|
|
"step": 55600,
|
|
"train_runtime": 100337.1505,
|
|
"train_tokens_per_second": 691.671
|
|
},
|
|
{
|
|
"epoch": 0.053664416586306656,
|
|
"grad_norm": 6.152266979217529,
|
|
"learning_rate": 0.00019860742760796662,
|
|
"loss": 1.070514907836914,
|
|
"num_input_tokens_seen": 69438776,
|
|
"step": 55650,
|
|
"train_runtime": 100399.316,
|
|
"train_tokens_per_second": 691.626
|
|
},
|
|
{
|
|
"epoch": 0.05371263259402122,
|
|
"grad_norm": 6.5260233879089355,
|
|
"learning_rate": 0.00019860490614681376,
|
|
"loss": 1.0741069793701172,
|
|
"num_input_tokens_seen": 69476544,
|
|
"step": 55700,
|
|
"train_runtime": 100461.7859,
|
|
"train_tokens_per_second": 691.572
|
|
},
|
|
{
|
|
"epoch": 0.05376084860173578,
|
|
"grad_norm": 6.558162212371826,
|
|
"learning_rate": 0.00019860238242101842,
|
|
"loss": 1.0190866088867188,
|
|
"num_input_tokens_seen": 69514928,
|
|
"step": 55750,
|
|
"train_runtime": 100524.7856,
|
|
"train_tokens_per_second": 691.52
|
|
},
|
|
{
|
|
"epoch": 0.053809064609450334,
|
|
"grad_norm": 5.939774990081787,
|
|
"learning_rate": 0.00019859985643063844,
|
|
"loss": 1.0944289398193359,
|
|
"num_input_tokens_seen": 69552968,
|
|
"step": 55800,
|
|
"train_runtime": 100587.0901,
|
|
"train_tokens_per_second": 691.47
|
|
},
|
|
{
|
|
"epoch": 0.053857280617164896,
|
|
"grad_norm": 6.003909587860107,
|
|
"learning_rate": 0.00019859732817573185,
|
|
"loss": 1.0516502380371093,
|
|
"num_input_tokens_seen": 69590640,
|
|
"step": 55850,
|
|
"train_runtime": 100649.3287,
|
|
"train_tokens_per_second": 691.417
|
|
},
|
|
{
|
|
"epoch": 0.05390549662487946,
|
|
"grad_norm": 6.8758368492126465,
|
|
"learning_rate": 0.00019859479765635678,
|
|
"loss": 1.0678253936767579,
|
|
"num_input_tokens_seen": 69628544,
|
|
"step": 55900,
|
|
"train_runtime": 100711.4724,
|
|
"train_tokens_per_second": 691.367
|
|
},
|
|
{
|
|
"epoch": 0.05395371263259402,
|
|
"grad_norm": 4.569721698760986,
|
|
"learning_rate": 0.0001985922648725713,
|
|
"loss": 1.1068223571777345,
|
|
"num_input_tokens_seen": 69666400,
|
|
"step": 55950,
|
|
"train_runtime": 100774.8461,
|
|
"train_tokens_per_second": 691.307
|
|
},
|
|
{
|
|
"epoch": 0.05400192864030858,
|
|
"grad_norm": 5.409555912017822,
|
|
"learning_rate": 0.0001985897298244336,
|
|
"loss": 1.0968134307861328,
|
|
"num_input_tokens_seen": 69705016,
|
|
"step": 56000,
|
|
"train_runtime": 100837.5761,
|
|
"train_tokens_per_second": 691.26
|
|
},
|
|
{
|
|
"epoch": 0.05405014464802314,
|
|
"grad_norm": 5.647604465484619,
|
|
"learning_rate": 0.00019858719251200188,
|
|
"loss": 1.0370013427734375,
|
|
"num_input_tokens_seen": 69742696,
|
|
"step": 56050,
|
|
"train_runtime": 100900.1221,
|
|
"train_tokens_per_second": 691.205
|
|
},
|
|
{
|
|
"epoch": 0.054098360655737705,
|
|
"grad_norm": 4.912491321563721,
|
|
"learning_rate": 0.00019858465293533443,
|
|
"loss": 1.0893147277832032,
|
|
"num_input_tokens_seen": 69780576,
|
|
"step": 56100,
|
|
"train_runtime": 100963.0322,
|
|
"train_tokens_per_second": 691.15
|
|
},
|
|
{
|
|
"epoch": 0.05414657666345227,
|
|
"grad_norm": 6.638219833374023,
|
|
"learning_rate": 0.0001985821110944896,
|
|
"loss": 1.0506830596923828,
|
|
"num_input_tokens_seen": 69818544,
|
|
"step": 56150,
|
|
"train_runtime": 101025.8612,
|
|
"train_tokens_per_second": 691.096
|
|
},
|
|
{
|
|
"epoch": 0.05419479267116683,
|
|
"grad_norm": 4.0583014488220215,
|
|
"learning_rate": 0.00019857956698952572,
|
|
"loss": 1.0864540863037109,
|
|
"num_input_tokens_seen": 69856736,
|
|
"step": 56200,
|
|
"train_runtime": 101089.3811,
|
|
"train_tokens_per_second": 691.039
|
|
},
|
|
{
|
|
"epoch": 0.05424300867888139,
|
|
"grad_norm": 5.68791389465332,
|
|
"learning_rate": 0.00019857702062050123,
|
|
"loss": 1.0661793518066407,
|
|
"num_input_tokens_seen": 69894272,
|
|
"step": 56250,
|
|
"train_runtime": 101151.9352,
|
|
"train_tokens_per_second": 690.983
|
|
},
|
|
{
|
|
"epoch": 0.05429122468659595,
|
|
"grad_norm": 6.700109004974365,
|
|
"learning_rate": 0.00019857447198747466,
|
|
"loss": 1.0624216461181641,
|
|
"num_input_tokens_seen": 69933048,
|
|
"step": 56300,
|
|
"train_runtime": 101214.6782,
|
|
"train_tokens_per_second": 690.938
|
|
},
|
|
{
|
|
"epoch": 0.05433944069431051,
|
|
"grad_norm": 7.146411418914795,
|
|
"learning_rate": 0.0001985719210905045,
|
|
"loss": 1.079354019165039,
|
|
"num_input_tokens_seen": 69971528,
|
|
"step": 56350,
|
|
"train_runtime": 101277.1012,
|
|
"train_tokens_per_second": 690.892
|
|
},
|
|
{
|
|
"epoch": 0.05438765670202507,
|
|
"grad_norm": 6.429131507873535,
|
|
"learning_rate": 0.00019856936792964934,
|
|
"loss": 1.1150141143798828,
|
|
"num_input_tokens_seen": 70008448,
|
|
"step": 56400,
|
|
"train_runtime": 101339.5835,
|
|
"train_tokens_per_second": 690.83
|
|
},
|
|
{
|
|
"epoch": 0.05443587270973963,
|
|
"grad_norm": 6.023188591003418,
|
|
"learning_rate": 0.0001985668125049678,
|
|
"loss": 1.1234336853027345,
|
|
"num_input_tokens_seen": 70046304,
|
|
"step": 56450,
|
|
"train_runtime": 101402.2286,
|
|
"train_tokens_per_second": 690.777
|
|
},
|
|
{
|
|
"epoch": 0.05448408871745419,
|
|
"grad_norm": 6.377741813659668,
|
|
"learning_rate": 0.0001985642548165186,
|
|
"loss": 1.060301513671875,
|
|
"num_input_tokens_seen": 70083952,
|
|
"step": 56500,
|
|
"train_runtime": 101464.884,
|
|
"train_tokens_per_second": 690.721
|
|
},
|
|
{
|
|
"epoch": 0.054532304725168755,
|
|
"grad_norm": 5.944561958312988,
|
|
"learning_rate": 0.00019856169486436048,
|
|
"loss": 1.0622230529785157,
|
|
"num_input_tokens_seen": 70122912,
|
|
"step": 56550,
|
|
"train_runtime": 101527.8145,
|
|
"train_tokens_per_second": 690.677
|
|
},
|
|
{
|
|
"epoch": 0.05458052073288332,
|
|
"grad_norm": 6.812858581542969,
|
|
"learning_rate": 0.00019855913264855225,
|
|
"loss": 1.0894835662841797,
|
|
"num_input_tokens_seen": 70160704,
|
|
"step": 56600,
|
|
"train_runtime": 101590.7532,
|
|
"train_tokens_per_second": 690.621
|
|
},
|
|
{
|
|
"epoch": 0.05462873674059788,
|
|
"grad_norm": 7.518139362335205,
|
|
"learning_rate": 0.00019855656816915272,
|
|
"loss": 1.1048963165283203,
|
|
"num_input_tokens_seen": 70199728,
|
|
"step": 56650,
|
|
"train_runtime": 101653.4122,
|
|
"train_tokens_per_second": 690.579
|
|
},
|
|
{
|
|
"epoch": 0.05467695274831244,
|
|
"grad_norm": 7.592897415161133,
|
|
"learning_rate": 0.00019855400142622078,
|
|
"loss": 1.1092221069335937,
|
|
"num_input_tokens_seen": 70237664,
|
|
"step": 56700,
|
|
"train_runtime": 101715.8684,
|
|
"train_tokens_per_second": 690.528
|
|
},
|
|
{
|
|
"epoch": 0.054725168756027,
|
|
"grad_norm": 5.673698902130127,
|
|
"learning_rate": 0.00019855143241981544,
|
|
"loss": 1.086451873779297,
|
|
"num_input_tokens_seen": 70276232,
|
|
"step": 56750,
|
|
"train_runtime": 101779.0868,
|
|
"train_tokens_per_second": 690.478
|
|
},
|
|
{
|
|
"epoch": 0.054773384763741564,
|
|
"grad_norm": 6.740379333496094,
|
|
"learning_rate": 0.00019854886114999566,
|
|
"loss": 1.128118438720703,
|
|
"num_input_tokens_seen": 70314016,
|
|
"step": 56800,
|
|
"train_runtime": 101842.4345,
|
|
"train_tokens_per_second": 690.42
|
|
},
|
|
{
|
|
"epoch": 0.054821600771456126,
|
|
"grad_norm": 6.83579683303833,
|
|
"learning_rate": 0.0001985462876168205,
|
|
"loss": 1.111887435913086,
|
|
"num_input_tokens_seen": 70352136,
|
|
"step": 56850,
|
|
"train_runtime": 101904.7834,
|
|
"train_tokens_per_second": 690.371
|
|
},
|
|
{
|
|
"epoch": 0.05486981677917069,
|
|
"grad_norm": 6.116386413574219,
|
|
"learning_rate": 0.00019854371182034903,
|
|
"loss": 1.0994588470458984,
|
|
"num_input_tokens_seen": 70390056,
|
|
"step": 56900,
|
|
"train_runtime": 101966.7118,
|
|
"train_tokens_per_second": 690.324
|
|
},
|
|
{
|
|
"epoch": 0.05491803278688524,
|
|
"grad_norm": 7.152568340301514,
|
|
"learning_rate": 0.00019854113376064044,
|
|
"loss": 1.098544921875,
|
|
"num_input_tokens_seen": 70428088,
|
|
"step": 56950,
|
|
"train_runtime": 102029.344,
|
|
"train_tokens_per_second": 690.273
|
|
},
|
|
{
|
|
"epoch": 0.054966248794599805,
|
|
"grad_norm": 5.972755432128906,
|
|
"learning_rate": 0.000198538553437754,
|
|
"loss": 1.1252635192871094,
|
|
"num_input_tokens_seen": 70465936,
|
|
"step": 57000,
|
|
"train_runtime": 102092.1917,
|
|
"train_tokens_per_second": 690.219
|
|
},
|
|
{
|
|
"epoch": 0.05501446480231437,
|
|
"grad_norm": 7.44169282913208,
|
|
"learning_rate": 0.00019853597085174886,
|
|
"loss": 1.1211688232421875,
|
|
"num_input_tokens_seen": 70504376,
|
|
"step": 57050,
|
|
"train_runtime": 102155.0185,
|
|
"train_tokens_per_second": 690.17
|
|
},
|
|
{
|
|
"epoch": 0.05506268081002893,
|
|
"grad_norm": 6.2991180419921875,
|
|
"learning_rate": 0.0001985333860026844,
|
|
"loss": 1.101060333251953,
|
|
"num_input_tokens_seen": 70543432,
|
|
"step": 57100,
|
|
"train_runtime": 102217.6336,
|
|
"train_tokens_per_second": 690.13
|
|
},
|
|
{
|
|
"epoch": 0.05511089681774349,
|
|
"grad_norm": 7.63613748550415,
|
|
"learning_rate": 0.00019853079889061998,
|
|
"loss": 1.1182330322265626,
|
|
"num_input_tokens_seen": 70581072,
|
|
"step": 57150,
|
|
"train_runtime": 102280.1889,
|
|
"train_tokens_per_second": 690.076
|
|
},
|
|
{
|
|
"epoch": 0.05515911282545805,
|
|
"grad_norm": 9.373798370361328,
|
|
"learning_rate": 0.00019852820951561502,
|
|
"loss": 1.0829544830322266,
|
|
"num_input_tokens_seen": 70618832,
|
|
"step": 57200,
|
|
"train_runtime": 102342.9109,
|
|
"train_tokens_per_second": 690.022
|
|
},
|
|
{
|
|
"epoch": 0.055207328833172614,
|
|
"grad_norm": 6.938178062438965,
|
|
"learning_rate": 0.00019852561787772898,
|
|
"loss": 1.0546129608154298,
|
|
"num_input_tokens_seen": 70656240,
|
|
"step": 57250,
|
|
"train_runtime": 102405.9014,
|
|
"train_tokens_per_second": 689.963
|
|
},
|
|
{
|
|
"epoch": 0.055255544840887176,
|
|
"grad_norm": 5.483449459075928,
|
|
"learning_rate": 0.00019852302397702136,
|
|
"loss": 1.1256326293945313,
|
|
"num_input_tokens_seen": 70693880,
|
|
"step": 57300,
|
|
"train_runtime": 102468.4369,
|
|
"train_tokens_per_second": 689.909
|
|
},
|
|
{
|
|
"epoch": 0.05530376084860174,
|
|
"grad_norm": 6.58348274230957,
|
|
"learning_rate": 0.00019852042781355177,
|
|
"loss": 1.0964920043945312,
|
|
"num_input_tokens_seen": 70732104,
|
|
"step": 57350,
|
|
"train_runtime": 102531.0781,
|
|
"train_tokens_per_second": 689.86
|
|
},
|
|
{
|
|
"epoch": 0.0553519768563163,
|
|
"grad_norm": 6.998131275177002,
|
|
"learning_rate": 0.00019851782938737982,
|
|
"loss": 1.1237228393554688,
|
|
"num_input_tokens_seen": 70770328,
|
|
"step": 57400,
|
|
"train_runtime": 102594.1766,
|
|
"train_tokens_per_second": 689.808
|
|
},
|
|
{
|
|
"epoch": 0.05540019286403086,
|
|
"grad_norm": 6.55574893951416,
|
|
"learning_rate": 0.0001985152286985652,
|
|
"loss": 1.0945349884033204,
|
|
"num_input_tokens_seen": 70808544,
|
|
"step": 57450,
|
|
"train_runtime": 102656.6485,
|
|
"train_tokens_per_second": 689.761
|
|
},
|
|
{
|
|
"epoch": 0.05544840887174542,
|
|
"grad_norm": 7.2615180015563965,
|
|
"learning_rate": 0.00019851262574716762,
|
|
"loss": 1.080854949951172,
|
|
"num_input_tokens_seen": 70846056,
|
|
"step": 57500,
|
|
"train_runtime": 102720.257,
|
|
"train_tokens_per_second": 689.699
|
|
},
|
|
{
|
|
"epoch": 0.05549662487945998,
|
|
"grad_norm": 5.789703845977783,
|
|
"learning_rate": 0.00019851002053324686,
|
|
"loss": 1.163777847290039,
|
|
"num_input_tokens_seen": 70884224,
|
|
"step": 57550,
|
|
"train_runtime": 102783.0255,
|
|
"train_tokens_per_second": 689.649
|
|
},
|
|
{
|
|
"epoch": 0.05554484088717454,
|
|
"grad_norm": 5.323535919189453,
|
|
"learning_rate": 0.0001985074130568628,
|
|
"loss": 1.1521438598632812,
|
|
"num_input_tokens_seen": 70922240,
|
|
"step": 57600,
|
|
"train_runtime": 102845.1179,
|
|
"train_tokens_per_second": 689.602
|
|
},
|
|
{
|
|
"epoch": 0.0555930568948891,
|
|
"grad_norm": 7.014165878295898,
|
|
"learning_rate": 0.00019850480331807526,
|
|
"loss": 1.0912538909912108,
|
|
"num_input_tokens_seen": 70959696,
|
|
"step": 57650,
|
|
"train_runtime": 102907.6867,
|
|
"train_tokens_per_second": 689.547
|
|
},
|
|
{
|
|
"epoch": 0.055641272902603664,
|
|
"grad_norm": 6.197737693786621,
|
|
"learning_rate": 0.0001985021913169442,
|
|
"loss": 1.1291246032714843,
|
|
"num_input_tokens_seen": 70997800,
|
|
"step": 57700,
|
|
"train_runtime": 102970.2185,
|
|
"train_tokens_per_second": 689.498
|
|
},
|
|
{
|
|
"epoch": 0.055689488910318226,
|
|
"grad_norm": 5.893574237823486,
|
|
"learning_rate": 0.00019849957705352965,
|
|
"loss": 1.0935899353027343,
|
|
"num_input_tokens_seen": 71035440,
|
|
"step": 57750,
|
|
"train_runtime": 103033.0664,
|
|
"train_tokens_per_second": 689.443
|
|
},
|
|
{
|
|
"epoch": 0.05573770491803279,
|
|
"grad_norm": 7.281827926635742,
|
|
"learning_rate": 0.0001984969605278916,
|
|
"loss": 1.1107982635498046,
|
|
"num_input_tokens_seen": 71072616,
|
|
"step": 57800,
|
|
"train_runtime": 103095.5475,
|
|
"train_tokens_per_second": 689.386
|
|
},
|
|
{
|
|
"epoch": 0.05578592092574735,
|
|
"grad_norm": 5.332526683807373,
|
|
"learning_rate": 0.00019849434174009015,
|
|
"loss": 1.1316452789306641,
|
|
"num_input_tokens_seen": 71111128,
|
|
"step": 57850,
|
|
"train_runtime": 103158.511,
|
|
"train_tokens_per_second": 689.338
|
|
},
|
|
{
|
|
"epoch": 0.05583413693346191,
|
|
"grad_norm": 5.717688083648682,
|
|
"learning_rate": 0.00019849172069018547,
|
|
"loss": 1.105107650756836,
|
|
"num_input_tokens_seen": 71149496,
|
|
"step": 57900,
|
|
"train_runtime": 103221.0169,
|
|
"train_tokens_per_second": 689.293
|
|
},
|
|
{
|
|
"epoch": 0.05588235294117647,
|
|
"grad_norm": 6.65305233001709,
|
|
"learning_rate": 0.00019848909737823776,
|
|
"loss": 1.0610435485839844,
|
|
"num_input_tokens_seen": 71187488,
|
|
"step": 57950,
|
|
"train_runtime": 103283.6618,
|
|
"train_tokens_per_second": 689.242
|
|
},
|
|
{
|
|
"epoch": 0.055930568948891035,
|
|
"grad_norm": 5.961781978607178,
|
|
"learning_rate": 0.0001984864718043072,
|
|
"loss": 1.0710284423828125,
|
|
"num_input_tokens_seen": 71224856,
|
|
"step": 58000,
|
|
"train_runtime": 103346.1282,
|
|
"train_tokens_per_second": 689.187
|
|
},
|
|
{
|
|
"epoch": 0.05597878495660559,
|
|
"grad_norm": 6.161648273468018,
|
|
"learning_rate": 0.00019848389654733773,
|
|
"loss": 1.093815155029297,
|
|
"num_input_tokens_seen": 71262848,
|
|
"step": 58050,
|
|
"train_runtime": 103408.7151,
|
|
"train_tokens_per_second": 689.138
|
|
},
|
|
{
|
|
"epoch": 0.05602700096432015,
|
|
"grad_norm": 4.659296989440918,
|
|
"learning_rate": 0.00019848126649485922,
|
|
"loss": 1.0971614074707032,
|
|
"num_input_tokens_seen": 71301040,
|
|
"step": 58100,
|
|
"train_runtime": 103471.5404,
|
|
"train_tokens_per_second": 689.088
|
|
},
|
|
{
|
|
"epoch": 0.056075216972034714,
|
|
"grad_norm": 6.546747207641602,
|
|
"learning_rate": 0.00019847863418057771,
|
|
"loss": 1.1147906494140625,
|
|
"num_input_tokens_seen": 71338992,
|
|
"step": 58150,
|
|
"train_runtime": 103534.0294,
|
|
"train_tokens_per_second": 689.039
|
|
},
|
|
{
|
|
"epoch": 0.056123432979749276,
|
|
"grad_norm": 7.3388566970825195,
|
|
"learning_rate": 0.0001984759996045538,
|
|
"loss": 1.078953857421875,
|
|
"num_input_tokens_seen": 71377624,
|
|
"step": 58200,
|
|
"train_runtime": 103596.8994,
|
|
"train_tokens_per_second": 688.994
|
|
},
|
|
{
|
|
"epoch": 0.05617164898746384,
|
|
"grad_norm": 5.892655372619629,
|
|
"learning_rate": 0.00019847336276684785,
|
|
"loss": 1.1057695770263671,
|
|
"num_input_tokens_seen": 71415176,
|
|
"step": 58250,
|
|
"train_runtime": 103660.0025,
|
|
"train_tokens_per_second": 688.937
|
|
},
|
|
{
|
|
"epoch": 0.0562198649951784,
|
|
"grad_norm": 6.864397048950195,
|
|
"learning_rate": 0.0001984707236675205,
|
|
"loss": 1.0611978149414063,
|
|
"num_input_tokens_seen": 71452944,
|
|
"step": 58300,
|
|
"train_runtime": 103722.6758,
|
|
"train_tokens_per_second": 688.885
|
|
},
|
|
{
|
|
"epoch": 0.05626808100289296,
|
|
"grad_norm": 7.378507614135742,
|
|
"learning_rate": 0.00019846808230663233,
|
|
"loss": 1.136794891357422,
|
|
"num_input_tokens_seen": 71490960,
|
|
"step": 58350,
|
|
"train_runtime": 103785.6523,
|
|
"train_tokens_per_second": 688.833
|
|
},
|
|
{
|
|
"epoch": 0.05631629701060752,
|
|
"grad_norm": 6.07895040512085,
|
|
"learning_rate": 0.00019846543868424403,
|
|
"loss": 1.1095615386962892,
|
|
"num_input_tokens_seen": 71528976,
|
|
"step": 58400,
|
|
"train_runtime": 103847.9895,
|
|
"train_tokens_per_second": 688.785
|
|
},
|
|
{
|
|
"epoch": 0.056364513018322085,
|
|
"grad_norm": 5.756801605224609,
|
|
"learning_rate": 0.00019846279280041627,
|
|
"loss": 1.1647399139404297,
|
|
"num_input_tokens_seen": 71566704,
|
|
"step": 58450,
|
|
"train_runtime": 103910.6829,
|
|
"train_tokens_per_second": 688.733
|
|
},
|
|
{
|
|
"epoch": 0.05641272902603665,
|
|
"grad_norm": 5.80438756942749,
|
|
"learning_rate": 0.00019846014465520987,
|
|
"loss": 1.1205927276611327,
|
|
"num_input_tokens_seen": 71603688,
|
|
"step": 58500,
|
|
"train_runtime": 103973.2373,
|
|
"train_tokens_per_second": 688.674
|
|
},
|
|
{
|
|
"epoch": 0.05646094503375121,
|
|
"grad_norm": 9.575721740722656,
|
|
"learning_rate": 0.0001984574942486856,
|
|
"loss": 1.1270816802978516,
|
|
"num_input_tokens_seen": 71640600,
|
|
"step": 58550,
|
|
"train_runtime": 104035.361,
|
|
"train_tokens_per_second": 688.618
|
|
},
|
|
{
|
|
"epoch": 0.056509161041465764,
|
|
"grad_norm": 5.445420265197754,
|
|
"learning_rate": 0.0001984548415809044,
|
|
"loss": 1.1103467559814453,
|
|
"num_input_tokens_seen": 71678040,
|
|
"step": 58600,
|
|
"train_runtime": 104098.8351,
|
|
"train_tokens_per_second": 688.558
|
|
},
|
|
{
|
|
"epoch": 0.056557377049180325,
|
|
"grad_norm": 6.704199314117432,
|
|
"learning_rate": 0.0001984521866519271,
|
|
"loss": 1.1070419311523438,
|
|
"num_input_tokens_seen": 71715632,
|
|
"step": 58650,
|
|
"train_runtime": 104161.7629,
|
|
"train_tokens_per_second": 688.502
|
|
},
|
|
{
|
|
"epoch": 0.05660559305689489,
|
|
"grad_norm": 10.889113426208496,
|
|
"learning_rate": 0.00019844952946181476,
|
|
"loss": 1.1152851867675782,
|
|
"num_input_tokens_seen": 71753016,
|
|
"step": 58700,
|
|
"train_runtime": 104224.3706,
|
|
"train_tokens_per_second": 688.448
|
|
},
|
|
{
|
|
"epoch": 0.05665380906460945,
|
|
"grad_norm": 7.362584590911865,
|
|
"learning_rate": 0.00019844687001062836,
|
|
"loss": 1.0921344757080078,
|
|
"num_input_tokens_seen": 71790168,
|
|
"step": 58750,
|
|
"train_runtime": 104286.9688,
|
|
"train_tokens_per_second": 688.391
|
|
},
|
|
{
|
|
"epoch": 0.05670202507232401,
|
|
"grad_norm": 7.408133029937744,
|
|
"learning_rate": 0.00019844420829842897,
|
|
"loss": 1.1070396423339843,
|
|
"num_input_tokens_seen": 71828616,
|
|
"step": 58800,
|
|
"train_runtime": 104349.4962,
|
|
"train_tokens_per_second": 688.347
|
|
},
|
|
{
|
|
"epoch": 0.05675024108003857,
|
|
"grad_norm": 5.9214887619018555,
|
|
"learning_rate": 0.0001984415443252778,
|
|
"loss": 1.1035388946533202,
|
|
"num_input_tokens_seen": 71866240,
|
|
"step": 58850,
|
|
"train_runtime": 104412.2106,
|
|
"train_tokens_per_second": 688.293
|
|
},
|
|
{
|
|
"epoch": 0.056798457087753135,
|
|
"grad_norm": 6.797940254211426,
|
|
"learning_rate": 0.00019843887809123593,
|
|
"loss": 1.11995361328125,
|
|
"num_input_tokens_seen": 71903936,
|
|
"step": 58900,
|
|
"train_runtime": 104474.8251,
|
|
"train_tokens_per_second": 688.242
|
|
},
|
|
{
|
|
"epoch": 0.0568466730954677,
|
|
"grad_norm": 6.2381486892700195,
|
|
"learning_rate": 0.00019843620959636467,
|
|
"loss": 1.12690673828125,
|
|
"num_input_tokens_seen": 71941352,
|
|
"step": 58950,
|
|
"train_runtime": 104536.4406,
|
|
"train_tokens_per_second": 688.194
|
|
},
|
|
{
|
|
"epoch": 0.05689488910318226,
|
|
"grad_norm": 6.740571975708008,
|
|
"learning_rate": 0.00019843353884072524,
|
|
"loss": 1.128159637451172,
|
|
"num_input_tokens_seen": 71978144,
|
|
"step": 59000,
|
|
"train_runtime": 104598.7105,
|
|
"train_tokens_per_second": 688.136
|
|
},
|
|
{
|
|
"epoch": 0.05694310511089682,
|
|
"grad_norm": 5.105685234069824,
|
|
"learning_rate": 0.00019843086582437905,
|
|
"loss": 1.0665863800048827,
|
|
"num_input_tokens_seen": 72016824,
|
|
"step": 59050,
|
|
"train_runtime": 104661.028,
|
|
"train_tokens_per_second": 688.096
|
|
},
|
|
{
|
|
"epoch": 0.05699132111861138,
|
|
"grad_norm": 6.539072036743164,
|
|
"learning_rate": 0.00019842819054738744,
|
|
"loss": 1.0895140838623047,
|
|
"num_input_tokens_seen": 72054024,
|
|
"step": 59100,
|
|
"train_runtime": 104723.3626,
|
|
"train_tokens_per_second": 688.042
|
|
},
|
|
{
|
|
"epoch": 0.05703953712632594,
|
|
"grad_norm": 5.45567512512207,
|
|
"learning_rate": 0.00019842551300981186,
|
|
"loss": 1.1614559173583985,
|
|
"num_input_tokens_seen": 72091720,
|
|
"step": 59150,
|
|
"train_runtime": 104786.4307,
|
|
"train_tokens_per_second": 687.987
|
|
},
|
|
{
|
|
"epoch": 0.0570877531340405,
|
|
"grad_norm": 6.363440036773682,
|
|
"learning_rate": 0.00019842283321171386,
|
|
"loss": 1.1306178283691406,
|
|
"num_input_tokens_seen": 72129456,
|
|
"step": 59200,
|
|
"train_runtime": 104849.0093,
|
|
"train_tokens_per_second": 687.936
|
|
},
|
|
{
|
|
"epoch": 0.05713596914175506,
|
|
"grad_norm": 6.541209697723389,
|
|
"learning_rate": 0.00019842015115315492,
|
|
"loss": 1.1010404968261718,
|
|
"num_input_tokens_seen": 72165736,
|
|
"step": 59250,
|
|
"train_runtime": 104911.9658,
|
|
"train_tokens_per_second": 687.869
|
|
},
|
|
{
|
|
"epoch": 0.05718418514946962,
|
|
"grad_norm": 6.40272855758667,
|
|
"learning_rate": 0.00019841746683419665,
|
|
"loss": 1.1156348419189452,
|
|
"num_input_tokens_seen": 72202736,
|
|
"step": 59300,
|
|
"train_runtime": 104974.7017,
|
|
"train_tokens_per_second": 687.811
|
|
},
|
|
{
|
|
"epoch": 0.057232401157184185,
|
|
"grad_norm": 6.96003532409668,
|
|
"learning_rate": 0.0001984147802549007,
|
|
"loss": 1.1426805114746095,
|
|
"num_input_tokens_seen": 72240112,
|
|
"step": 59350,
|
|
"train_runtime": 105037.172,
|
|
"train_tokens_per_second": 687.758
|
|
},
|
|
{
|
|
"epoch": 0.057280617164898746,
|
|
"grad_norm": 6.653439998626709,
|
|
"learning_rate": 0.0001984120914153288,
|
|
"loss": 1.0952068328857423,
|
|
"num_input_tokens_seen": 72276728,
|
|
"step": 59400,
|
|
"train_runtime": 105099.2997,
|
|
"train_tokens_per_second": 687.699
|
|
},
|
|
{
|
|
"epoch": 0.05732883317261331,
|
|
"grad_norm": 6.185856342315674,
|
|
"learning_rate": 0.00019840940031554268,
|
|
"loss": 1.1194943237304686,
|
|
"num_input_tokens_seen": 72314144,
|
|
"step": 59450,
|
|
"train_runtime": 105161.4196,
|
|
"train_tokens_per_second": 687.649
|
|
},
|
|
{
|
|
"epoch": 0.05737704918032787,
|
|
"grad_norm": 6.133792877197266,
|
|
"learning_rate": 0.00019840670695560415,
|
|
"loss": 1.1020516204833983,
|
|
"num_input_tokens_seen": 72351496,
|
|
"step": 59500,
|
|
"train_runtime": 105224.0488,
|
|
"train_tokens_per_second": 687.595
|
|
},
|
|
{
|
|
"epoch": 0.05742526518804243,
|
|
"grad_norm": 7.464698314666748,
|
|
"learning_rate": 0.0001984040113355751,
|
|
"loss": 1.1599884033203125,
|
|
"num_input_tokens_seen": 72388624,
|
|
"step": 59550,
|
|
"train_runtime": 105286.0821,
|
|
"train_tokens_per_second": 687.542
|
|
},
|
|
{
|
|
"epoch": 0.057473481195756994,
|
|
"grad_norm": 6.0885539054870605,
|
|
"learning_rate": 0.00019840131345551736,
|
|
"loss": 1.1208595275878905,
|
|
"num_input_tokens_seen": 72425232,
|
|
"step": 59600,
|
|
"train_runtime": 105348.7242,
|
|
"train_tokens_per_second": 687.481
|
|
},
|
|
{
|
|
"epoch": 0.057521697203471556,
|
|
"grad_norm": 6.287527561187744,
|
|
"learning_rate": 0.00019839861331549298,
|
|
"loss": 1.1281004333496094,
|
|
"num_input_tokens_seen": 72462352,
|
|
"step": 59650,
|
|
"train_runtime": 105410.9668,
|
|
"train_tokens_per_second": 687.427
|
|
},
|
|
{
|
|
"epoch": 0.05756991321118611,
|
|
"grad_norm": 5.926757335662842,
|
|
"learning_rate": 0.0001983959109155639,
|
|
"loss": 1.1170046997070313,
|
|
"num_input_tokens_seen": 72498480,
|
|
"step": 59700,
|
|
"train_runtime": 105473.3587,
|
|
"train_tokens_per_second": 687.363
|
|
},
|
|
{
|
|
"epoch": 0.05761812921890067,
|
|
"grad_norm": 6.108429431915283,
|
|
"learning_rate": 0.00019839320625579225,
|
|
"loss": 1.118300323486328,
|
|
"num_input_tokens_seen": 72535624,
|
|
"step": 59750,
|
|
"train_runtime": 105535.4957,
|
|
"train_tokens_per_second": 687.31
|
|
},
|
|
{
|
|
"epoch": 0.057666345226615234,
|
|
"grad_norm": 6.544740676879883,
|
|
"learning_rate": 0.0001983904993362401,
|
|
"loss": 1.1110144805908204,
|
|
"num_input_tokens_seen": 72573376,
|
|
"step": 59800,
|
|
"train_runtime": 105598.2695,
|
|
"train_tokens_per_second": 687.259
|
|
},
|
|
{
|
|
"epoch": 0.057714561234329796,
|
|
"grad_norm": 5.529053688049316,
|
|
"learning_rate": 0.00019838779015696965,
|
|
"loss": 1.1140056610107423,
|
|
"num_input_tokens_seen": 72609640,
|
|
"step": 59850,
|
|
"train_runtime": 105660.7979,
|
|
"train_tokens_per_second": 687.196
|
|
},
|
|
{
|
|
"epoch": 0.05776277724204436,
|
|
"grad_norm": 5.745729446411133,
|
|
"learning_rate": 0.0001983850787180431,
|
|
"loss": 1.160475616455078,
|
|
"num_input_tokens_seen": 72647192,
|
|
"step": 59900,
|
|
"train_runtime": 105723.223,
|
|
"train_tokens_per_second": 687.145
|
|
},
|
|
{
|
|
"epoch": 0.05781099324975892,
|
|
"grad_norm": 4.432782173156738,
|
|
"learning_rate": 0.00019838236501952276,
|
|
"loss": 1.135994415283203,
|
|
"num_input_tokens_seen": 72684784,
|
|
"step": 59950,
|
|
"train_runtime": 105786.1813,
|
|
"train_tokens_per_second": 687.091
|
|
},
|
|
{
|
|
"epoch": 0.05785920925747348,
|
|
"grad_norm": 6.157080173492432,
|
|
"learning_rate": 0.0001983796490614709,
|
|
"loss": 1.1050515747070313,
|
|
"num_input_tokens_seen": 72721952,
|
|
"step": 60000,
|
|
"train_runtime": 105849.1444,
|
|
"train_tokens_per_second": 687.034
|
|
},
|
|
{
|
|
"epoch": 0.057907425265188044,
|
|
"grad_norm": 5.866724491119385,
|
|
"learning_rate": 0.00019837693084394996,
|
|
"loss": 1.0757476806640625,
|
|
"num_input_tokens_seen": 72759568,
|
|
"step": 60050,
|
|
"train_runtime": 105912.6261,
|
|
"train_tokens_per_second": 686.977
|
|
},
|
|
{
|
|
"epoch": 0.057955641272902605,
|
|
"grad_norm": 5.612886905670166,
|
|
"learning_rate": 0.00019837421036702227,
|
|
"loss": 1.0875664520263673,
|
|
"num_input_tokens_seen": 72796944,
|
|
"step": 60100,
|
|
"train_runtime": 105974.6658,
|
|
"train_tokens_per_second": 686.928
|
|
},
|
|
{
|
|
"epoch": 0.05800385728061717,
|
|
"grad_norm": 6.274423599243164,
|
|
"learning_rate": 0.00019837148763075042,
|
|
"loss": 1.0822592163085938,
|
|
"num_input_tokens_seen": 72834560,
|
|
"step": 60150,
|
|
"train_runtime": 106037.7724,
|
|
"train_tokens_per_second": 686.874
|
|
},
|
|
{
|
|
"epoch": 0.05805207328833173,
|
|
"grad_norm": 8.963086128234863,
|
|
"learning_rate": 0.0001983687626351969,
|
|
"loss": 1.1259310913085938,
|
|
"num_input_tokens_seen": 72872144,
|
|
"step": 60200,
|
|
"train_runtime": 106100.1898,
|
|
"train_tokens_per_second": 686.824
|
|
},
|
|
{
|
|
"epoch": 0.058100289296046284,
|
|
"grad_norm": 5.510324001312256,
|
|
"learning_rate": 0.00019836603538042426,
|
|
"loss": 1.0818808746337891,
|
|
"num_input_tokens_seen": 72910392,
|
|
"step": 60250,
|
|
"train_runtime": 106162.9405,
|
|
"train_tokens_per_second": 686.778
|
|
},
|
|
{
|
|
"epoch": 0.058148505303760846,
|
|
"grad_norm": 4.7128005027771,
|
|
"learning_rate": 0.00019836330586649517,
|
|
"loss": 1.1111705017089843,
|
|
"num_input_tokens_seen": 72947872,
|
|
"step": 60300,
|
|
"train_runtime": 106225.0504,
|
|
"train_tokens_per_second": 686.729
|
|
},
|
|
{
|
|
"epoch": 0.05819672131147541,
|
|
"grad_norm": 6.574122428894043,
|
|
"learning_rate": 0.00019836057409347235,
|
|
"loss": 1.1206739044189453,
|
|
"num_input_tokens_seen": 72985256,
|
|
"step": 60350,
|
|
"train_runtime": 106287.2366,
|
|
"train_tokens_per_second": 686.679
|
|
},
|
|
{
|
|
"epoch": 0.05824493731918997,
|
|
"grad_norm": 8.20466423034668,
|
|
"learning_rate": 0.00019835789476419766,
|
|
"loss": 1.0584026336669923,
|
|
"num_input_tokens_seen": 73023520,
|
|
"step": 60400,
|
|
"train_runtime": 106349.9855,
|
|
"train_tokens_per_second": 686.634
|
|
},
|
|
{
|
|
"epoch": 0.05829315332690453,
|
|
"grad_norm": 7.193441867828369,
|
|
"learning_rate": 0.0001983551585183543,
|
|
"loss": 1.1386991882324218,
|
|
"num_input_tokens_seen": 73059592,
|
|
"step": 60450,
|
|
"train_runtime": 106412.4706,
|
|
"train_tokens_per_second": 686.57
|
|
},
|
|
{
|
|
"epoch": 0.05834136933461909,
|
|
"grad_norm": 5.804190158843994,
|
|
"learning_rate": 0.00019835242001360433,
|
|
"loss": 1.1215548706054688,
|
|
"num_input_tokens_seen": 73097000,
|
|
"step": 60500,
|
|
"train_runtime": 106474.9801,
|
|
"train_tokens_per_second": 686.518
|
|
},
|
|
{
|
|
"epoch": 0.058389585342333655,
|
|
"grad_norm": 6.240005970001221,
|
|
"learning_rate": 0.00019834967925001058,
|
|
"loss": 1.0739830017089844,
|
|
"num_input_tokens_seen": 73134064,
|
|
"step": 60550,
|
|
"train_runtime": 106537.7442,
|
|
"train_tokens_per_second": 686.462
|
|
},
|
|
{
|
|
"epoch": 0.05843780135004822,
|
|
"grad_norm": 9.302186965942383,
|
|
"learning_rate": 0.00019834693622763604,
|
|
"loss": 1.1075597381591797,
|
|
"num_input_tokens_seen": 73170624,
|
|
"step": 60600,
|
|
"train_runtime": 106599.7564,
|
|
"train_tokens_per_second": 686.405
|
|
},
|
|
{
|
|
"epoch": 0.05848601735776278,
|
|
"grad_norm": 5.924857139587402,
|
|
"learning_rate": 0.0001983441909465437,
|
|
"loss": 1.0932445526123047,
|
|
"num_input_tokens_seen": 73208792,
|
|
"step": 60650,
|
|
"train_runtime": 106662.0674,
|
|
"train_tokens_per_second": 686.362
|
|
},
|
|
{
|
|
"epoch": 0.05853423336547734,
|
|
"grad_norm": 6.62031888961792,
|
|
"learning_rate": 0.0001983414434067966,
|
|
"loss": 1.1425421905517579,
|
|
"num_input_tokens_seen": 73245688,
|
|
"step": 60700,
|
|
"train_runtime": 106724.3484,
|
|
"train_tokens_per_second": 686.307
|
|
},
|
|
{
|
|
"epoch": 0.0585824493731919,
|
|
"grad_norm": 6.206148147583008,
|
|
"learning_rate": 0.00019833869360845783,
|
|
"loss": 1.094304656982422,
|
|
"num_input_tokens_seen": 73283256,
|
|
"step": 60750,
|
|
"train_runtime": 106786.5537,
|
|
"train_tokens_per_second": 686.259
|
|
},
|
|
{
|
|
"epoch": 0.05863066538090646,
|
|
"grad_norm": 6.438232898712158,
|
|
"learning_rate": 0.00019833594155159055,
|
|
"loss": 1.1129442596435546,
|
|
"num_input_tokens_seen": 73320664,
|
|
"step": 60800,
|
|
"train_runtime": 106849.2028,
|
|
"train_tokens_per_second": 686.207
|
|
},
|
|
{
|
|
"epoch": 0.05867888138862102,
|
|
"grad_norm": 5.467323303222656,
|
|
"learning_rate": 0.00019833318723625802,
|
|
"loss": 1.1068610382080077,
|
|
"num_input_tokens_seen": 73358112,
|
|
"step": 60850,
|
|
"train_runtime": 106911.8741,
|
|
"train_tokens_per_second": 686.155
|
|
},
|
|
{
|
|
"epoch": 0.05872709739633558,
|
|
"grad_norm": 6.488888740539551,
|
|
"learning_rate": 0.00019833043066252342,
|
|
"loss": 1.1314813232421874,
|
|
"num_input_tokens_seen": 73394976,
|
|
"step": 60900,
|
|
"train_runtime": 106974.6198,
|
|
"train_tokens_per_second": 686.097
|
|
},
|
|
{
|
|
"epoch": 0.05877531340405014,
|
|
"grad_norm": 9.566640853881836,
|
|
"learning_rate": 0.00019832767183045012,
|
|
"loss": 1.2045652770996094,
|
|
"num_input_tokens_seen": 73432080,
|
|
"step": 60950,
|
|
"train_runtime": 107037.0542,
|
|
"train_tokens_per_second": 686.044
|
|
},
|
|
{
|
|
"epoch": 0.058823529411764705,
|
|
"grad_norm": 5.6337714195251465,
|
|
"learning_rate": 0.00019832491074010144,
|
|
"loss": 1.1174143218994141,
|
|
"num_input_tokens_seen": 73469408,
|
|
"step": 61000,
|
|
"train_runtime": 107099.2374,
|
|
"train_tokens_per_second": 685.994
|
|
},
|
|
{
|
|
"epoch": 0.05887174541947927,
|
|
"grad_norm": 7.138758659362793,
|
|
"learning_rate": 0.00019832214739154083,
|
|
"loss": 1.129429702758789,
|
|
"num_input_tokens_seen": 73506960,
|
|
"step": 61050,
|
|
"train_runtime": 107162.201,
|
|
"train_tokens_per_second": 685.941
|
|
},
|
|
{
|
|
"epoch": 0.05891996142719383,
|
|
"grad_norm": 7.782101154327393,
|
|
"learning_rate": 0.00019831938178483172,
|
|
"loss": 1.077940673828125,
|
|
"num_input_tokens_seen": 73543632,
|
|
"step": 61100,
|
|
"train_runtime": 107224.7794,
|
|
"train_tokens_per_second": 685.883
|
|
},
|
|
{
|
|
"epoch": 0.05896817743490839,
|
|
"grad_norm": 6.5464324951171875,
|
|
"learning_rate": 0.00019831661392003764,
|
|
"loss": 1.0759806060791015,
|
|
"num_input_tokens_seen": 73581168,
|
|
"step": 61150,
|
|
"train_runtime": 107287.5546,
|
|
"train_tokens_per_second": 685.831
|
|
},
|
|
{
|
|
"epoch": 0.05901639344262295,
|
|
"grad_norm": 5.4477620124816895,
|
|
"learning_rate": 0.00019831384379722218,
|
|
"loss": 1.16283935546875,
|
|
"num_input_tokens_seen": 73618720,
|
|
"step": 61200,
|
|
"train_runtime": 107350.3147,
|
|
"train_tokens_per_second": 685.78
|
|
},
|
|
{
|
|
"epoch": 0.059064609450337514,
|
|
"grad_norm": 11.982522964477539,
|
|
"learning_rate": 0.00019831107141644893,
|
|
"loss": 1.078486328125,
|
|
"num_input_tokens_seen": 73655528,
|
|
"step": 61250,
|
|
"train_runtime": 107414.1246,
|
|
"train_tokens_per_second": 685.715
|
|
},
|
|
{
|
|
"epoch": 0.059112825458052076,
|
|
"grad_norm": 5.733062744140625,
|
|
"learning_rate": 0.0001983082967777816,
|
|
"loss": 1.1115536499023437,
|
|
"num_input_tokens_seen": 73693472,
|
|
"step": 61300,
|
|
"train_runtime": 107476.9905,
|
|
"train_tokens_per_second": 685.667
|
|
},
|
|
{
|
|
"epoch": 0.05916104146576663,
|
|
"grad_norm": 4.765565395355225,
|
|
"learning_rate": 0.00019830551988128385,
|
|
"loss": 1.1385633850097656,
|
|
"num_input_tokens_seen": 73730200,
|
|
"step": 61350,
|
|
"train_runtime": 107539.0501,
|
|
"train_tokens_per_second": 685.613
|
|
},
|
|
{
|
|
"epoch": 0.05920925747348119,
|
|
"grad_norm": 6.494258880615234,
|
|
"learning_rate": 0.00019830274072701952,
|
|
"loss": 1.099452133178711,
|
|
"num_input_tokens_seen": 73767040,
|
|
"step": 61400,
|
|
"train_runtime": 107601.5075,
|
|
"train_tokens_per_second": 685.558
|
|
},
|
|
{
|
|
"epoch": 0.059257473481195755,
|
|
"grad_norm": 6.096861839294434,
|
|
"learning_rate": 0.0001982999593150524,
|
|
"loss": 1.0917678833007813,
|
|
"num_input_tokens_seen": 73804616,
|
|
"step": 61450,
|
|
"train_runtime": 107664.3569,
|
|
"train_tokens_per_second": 685.506
|
|
},
|
|
{
|
|
"epoch": 0.05930568948891032,
|
|
"grad_norm": 6.95417594909668,
|
|
"learning_rate": 0.00019829717564544638,
|
|
"loss": 1.0906222534179688,
|
|
"num_input_tokens_seen": 73841960,
|
|
"step": 61500,
|
|
"train_runtime": 107727.4698,
|
|
"train_tokens_per_second": 685.452
|
|
},
|
|
{
|
|
"epoch": 0.05935390549662488,
|
|
"grad_norm": 6.772852897644043,
|
|
"learning_rate": 0.00019829438971826543,
|
|
"loss": 1.1739373016357422,
|
|
"num_input_tokens_seen": 73878816,
|
|
"step": 61550,
|
|
"train_runtime": 107789.4605,
|
|
"train_tokens_per_second": 685.399
|
|
},
|
|
{
|
|
"epoch": 0.05940212150433944,
|
|
"grad_norm": 6.631778717041016,
|
|
"learning_rate": 0.00019829160153357348,
|
|
"loss": 1.1675237274169923,
|
|
"num_input_tokens_seen": 73916328,
|
|
"step": 61600,
|
|
"train_runtime": 107851.634,
|
|
"train_tokens_per_second": 685.352
|
|
},
|
|
{
|
|
"epoch": 0.059450337512054,
|
|
"grad_norm": 7.1278839111328125,
|
|
"learning_rate": 0.0001982888110914346,
|
|
"loss": 1.1020042419433593,
|
|
"num_input_tokens_seen": 73953576,
|
|
"step": 61650,
|
|
"train_runtime": 107914.0402,
|
|
"train_tokens_per_second": 685.301
|
|
},
|
|
{
|
|
"epoch": 0.059498553519768564,
|
|
"grad_norm": 7.72106409072876,
|
|
"learning_rate": 0.00019828601839191285,
|
|
"loss": 1.1522307586669922,
|
|
"num_input_tokens_seen": 73991248,
|
|
"step": 61700,
|
|
"train_runtime": 107976.4124,
|
|
"train_tokens_per_second": 685.254
|
|
},
|
|
{
|
|
"epoch": 0.059546769527483126,
|
|
"grad_norm": 4.918510913848877,
|
|
"learning_rate": 0.0001982832234350724,
|
|
"loss": 1.105594482421875,
|
|
"num_input_tokens_seen": 74028184,
|
|
"step": 61750,
|
|
"train_runtime": 108039.0513,
|
|
"train_tokens_per_second": 685.198
|
|
},
|
|
{
|
|
"epoch": 0.05959498553519769,
|
|
"grad_norm": 6.697110652923584,
|
|
"learning_rate": 0.0001982804262209774,
|
|
"loss": 1.137255859375,
|
|
"num_input_tokens_seen": 74065440,
|
|
"step": 61800,
|
|
"train_runtime": 108101.8461,
|
|
"train_tokens_per_second": 685.145
|
|
},
|
|
{
|
|
"epoch": 0.05964320154291225,
|
|
"grad_norm": 5.351416110992432,
|
|
"learning_rate": 0.00019827762674969214,
|
|
"loss": 1.096043701171875,
|
|
"num_input_tokens_seen": 74103640,
|
|
"step": 61850,
|
|
"train_runtime": 108164.3266,
|
|
"train_tokens_per_second": 685.102
|
|
},
|
|
{
|
|
"epoch": 0.059691417550626805,
|
|
"grad_norm": 9.044157028198242,
|
|
"learning_rate": 0.0001982748250212809,
|
|
"loss": 1.118216323852539,
|
|
"num_input_tokens_seen": 74141720,
|
|
"step": 61900,
|
|
"train_runtime": 108227.4316,
|
|
"train_tokens_per_second": 685.055
|
|
},
|
|
{
|
|
"epoch": 0.059739633558341367,
|
|
"grad_norm": 7.770543575286865,
|
|
"learning_rate": 0.000198272021035808,
|
|
"loss": 1.0350054168701173,
|
|
"num_input_tokens_seen": 74180048,
|
|
"step": 61950,
|
|
"train_runtime": 108289.6842,
|
|
"train_tokens_per_second": 685.015
|
|
},
|
|
{
|
|
"epoch": 0.05978784956605593,
|
|
"grad_norm": 6.7702860832214355,
|
|
"learning_rate": 0.0001982692147933379,
|
|
"loss": 1.091366958618164,
|
|
"num_input_tokens_seen": 74217744,
|
|
"step": 62000,
|
|
"train_runtime": 108352.523,
|
|
"train_tokens_per_second": 684.966
|
|
},
|
|
{
|
|
"epoch": 0.05983606557377049,
|
|
"grad_norm": 5.735795974731445,
|
|
"learning_rate": 0.00019826640629393497,
|
|
"loss": 1.1353843688964844,
|
|
"num_input_tokens_seen": 74254840,
|
|
"step": 62050,
|
|
"train_runtime": 108414.5102,
|
|
"train_tokens_per_second": 684.916
|
|
},
|
|
{
|
|
"epoch": 0.05988428158148505,
|
|
"grad_norm": 6.948058605194092,
|
|
"learning_rate": 0.00019826359553766376,
|
|
"loss": 1.1179660034179688,
|
|
"num_input_tokens_seen": 74292144,
|
|
"step": 62100,
|
|
"train_runtime": 108477.2011,
|
|
"train_tokens_per_second": 684.864
|
|
},
|
|
{
|
|
"epoch": 0.059932497589199614,
|
|
"grad_norm": 6.494797229766846,
|
|
"learning_rate": 0.00019826078252458884,
|
|
"loss": 1.1120588684082031,
|
|
"num_input_tokens_seen": 74329888,
|
|
"step": 62150,
|
|
"train_runtime": 108539.5133,
|
|
"train_tokens_per_second": 684.819
|
|
},
|
|
{
|
|
"epoch": 0.059980713596914176,
|
|
"grad_norm": 6.379907131195068,
|
|
"learning_rate": 0.00019825796725477478,
|
|
"loss": 1.092867889404297,
|
|
"num_input_tokens_seen": 74367280,
|
|
"step": 62200,
|
|
"train_runtime": 108601.663,
|
|
"train_tokens_per_second": 684.771
|
|
},
|
|
{
|
|
"epoch": 0.06002892960462874,
|
|
"grad_norm": 6.369703769683838,
|
|
"learning_rate": 0.00019825514972828624,
|
|
"loss": 1.1911666870117188,
|
|
"num_input_tokens_seen": 74404912,
|
|
"step": 62250,
|
|
"train_runtime": 108664.9051,
|
|
"train_tokens_per_second": 684.719
|
|
},
|
|
{
|
|
"epoch": 0.0600771456123433,
|
|
"grad_norm": 9.305986404418945,
|
|
"learning_rate": 0.00019825232994518795,
|
|
"loss": 1.0971158599853517,
|
|
"num_input_tokens_seen": 74443232,
|
|
"step": 62300,
|
|
"train_runtime": 108727.7147,
|
|
"train_tokens_per_second": 684.676
|
|
},
|
|
{
|
|
"epoch": 0.06012536162005786,
|
|
"grad_norm": 7.734401702880859,
|
|
"learning_rate": 0.00019824950790554464,
|
|
"loss": 1.0996744537353516,
|
|
"num_input_tokens_seen": 74480552,
|
|
"step": 62350,
|
|
"train_runtime": 108790.392,
|
|
"train_tokens_per_second": 684.624
|
|
},
|
|
{
|
|
"epoch": 0.06017357762777242,
|
|
"grad_norm": 7.27135705947876,
|
|
"learning_rate": 0.00019824668360942114,
|
|
"loss": 1.0929202270507812,
|
|
"num_input_tokens_seen": 74518344,
|
|
"step": 62400,
|
|
"train_runtime": 108853.1934,
|
|
"train_tokens_per_second": 684.577
|
|
},
|
|
{
|
|
"epoch": 0.060221793635486985,
|
|
"grad_norm": 6.002157688140869,
|
|
"learning_rate": 0.00019824385705688235,
|
|
"loss": 1.116378631591797,
|
|
"num_input_tokens_seen": 74557032,
|
|
"step": 62450,
|
|
"train_runtime": 108916.2012,
|
|
"train_tokens_per_second": 684.536
|
|
},
|
|
{
|
|
"epoch": 0.06027000964320154,
|
|
"grad_norm": 6.035345554351807,
|
|
"learning_rate": 0.00019824102824799313,
|
|
"loss": 1.1129955291748046,
|
|
"num_input_tokens_seen": 74594808,
|
|
"step": 62500,
|
|
"train_runtime": 108978.9768,
|
|
"train_tokens_per_second": 684.488
|
|
},
|
|
{
|
|
"epoch": 0.0603182256509161,
|
|
"grad_norm": 8.092338562011719,
|
|
"learning_rate": 0.00019823819718281852,
|
|
"loss": 1.119823226928711,
|
|
"num_input_tokens_seen": 74632968,
|
|
"step": 62550,
|
|
"train_runtime": 109041.7731,
|
|
"train_tokens_per_second": 684.444
|
|
},
|
|
{
|
|
"epoch": 0.060366441658630664,
|
|
"grad_norm": 10.268393516540527,
|
|
"learning_rate": 0.0001982354205499619,
|
|
"loss": 1.1093325805664063,
|
|
"num_input_tokens_seen": 74670592,
|
|
"step": 62600,
|
|
"train_runtime": 109104.486,
|
|
"train_tokens_per_second": 684.395
|
|
},
|
|
{
|
|
"epoch": 0.060414657666345226,
|
|
"grad_norm": 9.801848411560059,
|
|
"learning_rate": 0.000198232585017534,
|
|
"loss": 1.1181729125976563,
|
|
"num_input_tokens_seen": 74708656,
|
|
"step": 62650,
|
|
"train_runtime": 109167.633,
|
|
"train_tokens_per_second": 684.348
|
|
},
|
|
{
|
|
"epoch": 0.06046287367405979,
|
|
"grad_norm": 6.750045299530029,
|
|
"learning_rate": 0.00019822974722901452,
|
|
"loss": 1.1202384185791017,
|
|
"num_input_tokens_seen": 74747048,
|
|
"step": 62700,
|
|
"train_runtime": 109230.8607,
|
|
"train_tokens_per_second": 684.303
|
|
},
|
|
{
|
|
"epoch": 0.06051108968177435,
|
|
"grad_norm": 7.940761089324951,
|
|
"learning_rate": 0.00019822690718446874,
|
|
"loss": 1.1168663787841797,
|
|
"num_input_tokens_seen": 74784168,
|
|
"step": 62750,
|
|
"train_runtime": 109293.2441,
|
|
"train_tokens_per_second": 684.252
|
|
},
|
|
{
|
|
"epoch": 0.06055930568948891,
|
|
"grad_norm": 8.924919128417969,
|
|
"learning_rate": 0.00019822406488396183,
|
|
"loss": 1.109958724975586,
|
|
"num_input_tokens_seen": 74822312,
|
|
"step": 62800,
|
|
"train_runtime": 109355.7386,
|
|
"train_tokens_per_second": 684.21
|
|
},
|
|
{
|
|
"epoch": 0.06060752169720347,
|
|
"grad_norm": 7.276103973388672,
|
|
"learning_rate": 0.00019822122032755907,
|
|
"loss": 1.1295201110839843,
|
|
"num_input_tokens_seen": 74860328,
|
|
"step": 62850,
|
|
"train_runtime": 109418.5526,
|
|
"train_tokens_per_second": 684.165
|
|
},
|
|
{
|
|
"epoch": 0.060655737704918035,
|
|
"grad_norm": 7.079374313354492,
|
|
"learning_rate": 0.00019821837351532585,
|
|
"loss": 1.1284422302246093,
|
|
"num_input_tokens_seen": 74897128,
|
|
"step": 62900,
|
|
"train_runtime": 109481.0148,
|
|
"train_tokens_per_second": 684.111
|
|
},
|
|
{
|
|
"epoch": 0.0607039537126326,
|
|
"grad_norm": 6.608506202697754,
|
|
"learning_rate": 0.00019821552444732746,
|
|
"loss": 1.1104880523681642,
|
|
"num_input_tokens_seen": 74934576,
|
|
"step": 62950,
|
|
"train_runtime": 109543.3323,
|
|
"train_tokens_per_second": 684.063
|
|
},
|
|
{
|
|
"epoch": 0.06075216972034716,
|
|
"grad_norm": 5.626640796661377,
|
|
"learning_rate": 0.0001982126731236294,
|
|
"loss": 1.1080575561523438,
|
|
"num_input_tokens_seen": 74971904,
|
|
"step": 63000,
|
|
"train_runtime": 109605.9923,
|
|
"train_tokens_per_second": 684.013
|
|
},
|
|
{
|
|
"epoch": 0.060800385728061714,
|
|
"grad_norm": 6.434770584106445,
|
|
"learning_rate": 0.0001982098195442971,
|
|
"loss": 1.10012451171875,
|
|
"num_input_tokens_seen": 75010232,
|
|
"step": 63050,
|
|
"train_runtime": 109669.4057,
|
|
"train_tokens_per_second": 683.967
|
|
},
|
|
{
|
|
"epoch": 0.060848601735776275,
|
|
"grad_norm": 6.3150224685668945,
|
|
"learning_rate": 0.00019820696370939614,
|
|
"loss": 1.1020169067382812,
|
|
"num_input_tokens_seen": 75047912,
|
|
"step": 63100,
|
|
"train_runtime": 109731.7503,
|
|
"train_tokens_per_second": 683.922
|
|
},
|
|
{
|
|
"epoch": 0.06089681774349084,
|
|
"grad_norm": 11.316041946411133,
|
|
"learning_rate": 0.0001982041056189921,
|
|
"loss": 1.1661359405517577,
|
|
"num_input_tokens_seen": 75086392,
|
|
"step": 63150,
|
|
"train_runtime": 109794.4069,
|
|
"train_tokens_per_second": 683.882
|
|
},
|
|
{
|
|
"epoch": 0.0609450337512054,
|
|
"grad_norm": 7.571619033813477,
|
|
"learning_rate": 0.00019820124527315065,
|
|
"loss": 1.0795281982421876,
|
|
"num_input_tokens_seen": 75123488,
|
|
"step": 63200,
|
|
"train_runtime": 109857.0104,
|
|
"train_tokens_per_second": 683.83
|
|
},
|
|
{
|
|
"epoch": 0.06099324975891996,
|
|
"grad_norm": 9.080229759216309,
|
|
"learning_rate": 0.00019819838267193745,
|
|
"loss": 1.1408436584472657,
|
|
"num_input_tokens_seen": 75161232,
|
|
"step": 63250,
|
|
"train_runtime": 109919.6816,
|
|
"train_tokens_per_second": 683.783
|
|
},
|
|
{
|
|
"epoch": 0.06104146576663452,
|
|
"grad_norm": 10.867049217224121,
|
|
"learning_rate": 0.00019819551781541823,
|
|
"loss": 1.103102340698242,
|
|
"num_input_tokens_seen": 75199024,
|
|
"step": 63300,
|
|
"train_runtime": 109981.8214,
|
|
"train_tokens_per_second": 683.74
|
|
},
|
|
{
|
|
"epoch": 0.061089681774349085,
|
|
"grad_norm": 7.269835948944092,
|
|
"learning_rate": 0.0001981926507036588,
|
|
"loss": 1.0926708984375,
|
|
"num_input_tokens_seen": 75236856,
|
|
"step": 63350,
|
|
"train_runtime": 110044.4117,
|
|
"train_tokens_per_second": 683.695
|
|
},
|
|
{
|
|
"epoch": 0.06113789778206365,
|
|
"grad_norm": 5.088568687438965,
|
|
"learning_rate": 0.000198189781336725,
|
|
"loss": 1.1138909912109376,
|
|
"num_input_tokens_seen": 75274584,
|
|
"step": 63400,
|
|
"train_runtime": 110106.8888,
|
|
"train_tokens_per_second": 683.65
|
|
},
|
|
{
|
|
"epoch": 0.06118611378977821,
|
|
"grad_norm": 6.273104190826416,
|
|
"learning_rate": 0.00019818690971468278,
|
|
"loss": 1.1414108276367188,
|
|
"num_input_tokens_seen": 75313008,
|
|
"step": 63450,
|
|
"train_runtime": 110169.2558,
|
|
"train_tokens_per_second": 683.612
|
|
},
|
|
{
|
|
"epoch": 0.06123432979749277,
|
|
"grad_norm": 6.905462265014648,
|
|
"learning_rate": 0.00019818409333723875,
|
|
"loss": 1.0941358184814454,
|
|
"num_input_tokens_seen": 75350488,
|
|
"step": 63500,
|
|
"train_runtime": 110231.7497,
|
|
"train_tokens_per_second": 683.564
|
|
},
|
|
{
|
|
"epoch": 0.06128254580520733,
|
|
"grad_norm": 11.631942749023438,
|
|
"learning_rate": 0.00019818121725027638,
|
|
"loss": 1.1086022186279296,
|
|
"num_input_tokens_seen": 75387144,
|
|
"step": 63550,
|
|
"train_runtime": 110294.5995,
|
|
"train_tokens_per_second": 683.507
|
|
},
|
|
{
|
|
"epoch": 0.06133076181292189,
|
|
"grad_norm": 5.843342304229736,
|
|
"learning_rate": 0.0001981783389084023,
|
|
"loss": 1.1250192260742187,
|
|
"num_input_tokens_seen": 75424840,
|
|
"step": 63600,
|
|
"train_runtime": 110357.3047,
|
|
"train_tokens_per_second": 683.46
|
|
},
|
|
{
|
|
"epoch": 0.06137897782063645,
|
|
"grad_norm": 8.194828033447266,
|
|
"learning_rate": 0.00019817545831168253,
|
|
"loss": 1.1610309600830078,
|
|
"num_input_tokens_seen": 75463336,
|
|
"step": 63650,
|
|
"train_runtime": 110419.966,
|
|
"train_tokens_per_second": 683.421
|
|
},
|
|
{
|
|
"epoch": 0.06142719382835101,
|
|
"grad_norm": 9.95604133605957,
|
|
"learning_rate": 0.00019817257546018323,
|
|
"loss": 1.1462559509277344,
|
|
"num_input_tokens_seen": 75501448,
|
|
"step": 63700,
|
|
"train_runtime": 110482.5743,
|
|
"train_tokens_per_second": 683.379
|
|
},
|
|
{
|
|
"epoch": 0.06147540983606557,
|
|
"grad_norm": 7.683218955993652,
|
|
"learning_rate": 0.00019816969035397068,
|
|
"loss": 1.1657695007324218,
|
|
"num_input_tokens_seen": 75539400,
|
|
"step": 63750,
|
|
"train_runtime": 110545.6606,
|
|
"train_tokens_per_second": 683.332
|
|
},
|
|
{
|
|
"epoch": 0.061523625843780134,
|
|
"grad_norm": 7.829223155975342,
|
|
"learning_rate": 0.0001981668029931111,
|
|
"loss": 1.0978803253173828,
|
|
"num_input_tokens_seen": 75577704,
|
|
"step": 63800,
|
|
"train_runtime": 110608.2291,
|
|
"train_tokens_per_second": 683.292
|
|
},
|
|
{
|
|
"epoch": 0.061571841851494696,
|
|
"grad_norm": 7.002161979675293,
|
|
"learning_rate": 0.00019816391337767079,
|
|
"loss": 1.1455943298339843,
|
|
"num_input_tokens_seen": 75615328,
|
|
"step": 63850,
|
|
"train_runtime": 110670.6981,
|
|
"train_tokens_per_second": 683.246
|
|
},
|
|
{
|
|
"epoch": 0.06162005785920926,
|
|
"grad_norm": 6.850635051727295,
|
|
"learning_rate": 0.00019816102150771613,
|
|
"loss": 1.1482688903808593,
|
|
"num_input_tokens_seen": 75652680,
|
|
"step": 63900,
|
|
"train_runtime": 110732.6304,
|
|
"train_tokens_per_second": 683.201
|
|
},
|
|
{
|
|
"epoch": 0.06166827386692382,
|
|
"grad_norm": 5.986904621124268,
|
|
"learning_rate": 0.00019815812738331354,
|
|
"loss": 1.0989680480957031,
|
|
"num_input_tokens_seen": 75691696,
|
|
"step": 63950,
|
|
"train_runtime": 110795.009,
|
|
"train_tokens_per_second": 683.169
|
|
},
|
|
{
|
|
"epoch": 0.06171648987463838,
|
|
"grad_norm": 7.937697887420654,
|
|
"learning_rate": 0.00019815523100452949,
|
|
"loss": 1.1254730224609375,
|
|
"num_input_tokens_seen": 75729120,
|
|
"step": 64000,
|
|
"train_runtime": 110858.2397,
|
|
"train_tokens_per_second": 683.117
|
|
},
|
|
{
|
|
"epoch": 0.061764705882352944,
|
|
"grad_norm": 6.496916770935059,
|
|
"learning_rate": 0.0001981523323714305,
|
|
"loss": 1.0858438110351563,
|
|
"num_input_tokens_seen": 75766648,
|
|
"step": 64050,
|
|
"train_runtime": 110920.7944,
|
|
"train_tokens_per_second": 683.07
|
|
},
|
|
{
|
|
"epoch": 0.061812921890067506,
|
|
"grad_norm": 7.585862159729004,
|
|
"learning_rate": 0.00019814943148408314,
|
|
"loss": 1.1238740539550782,
|
|
"num_input_tokens_seen": 75805304,
|
|
"step": 64100,
|
|
"train_runtime": 110983.2729,
|
|
"train_tokens_per_second": 683.034
|
|
},
|
|
{
|
|
"epoch": 0.06186113789778206,
|
|
"grad_norm": 7.906359672546387,
|
|
"learning_rate": 0.00019814652834255402,
|
|
"loss": 1.1279823303222656,
|
|
"num_input_tokens_seen": 75843096,
|
|
"step": 64150,
|
|
"train_runtime": 111046.2221,
|
|
"train_tokens_per_second": 682.987
|
|
},
|
|
{
|
|
"epoch": 0.06190935390549662,
|
|
"grad_norm": 6.445123195648193,
|
|
"learning_rate": 0.0001981436229469098,
|
|
"loss": 1.0996365356445312,
|
|
"num_input_tokens_seen": 75881000,
|
|
"step": 64200,
|
|
"train_runtime": 111108.4194,
|
|
"train_tokens_per_second": 682.946
|
|
},
|
|
{
|
|
"epoch": 0.061957569913211184,
|
|
"grad_norm": 5.639453411102295,
|
|
"learning_rate": 0.0001981407152972173,
|
|
"loss": 1.1362160491943358,
|
|
"num_input_tokens_seen": 75918088,
|
|
"step": 64250,
|
|
"train_runtime": 111171.4392,
|
|
"train_tokens_per_second": 682.892
|
|
},
|
|
{
|
|
"epoch": 0.062005785920925746,
|
|
"grad_norm": 7.45891809463501,
|
|
"learning_rate": 0.0001981378053935432,
|
|
"loss": 1.1291822814941406,
|
|
"num_input_tokens_seen": 75955168,
|
|
"step": 64300,
|
|
"train_runtime": 111234.4246,
|
|
"train_tokens_per_second": 682.839
|
|
},
|
|
{
|
|
"epoch": 0.06205400192864031,
|
|
"grad_norm": 5.767571449279785,
|
|
"learning_rate": 0.0001981348932359544,
|
|
"loss": 1.1631246948242187,
|
|
"num_input_tokens_seen": 75993472,
|
|
"step": 64350,
|
|
"train_runtime": 111296.9873,
|
|
"train_tokens_per_second": 682.799
|
|
},
|
|
{
|
|
"epoch": 0.06210221793635487,
|
|
"grad_norm": 6.514416694641113,
|
|
"learning_rate": 0.00019813197882451774,
|
|
"loss": 1.139356689453125,
|
|
"num_input_tokens_seen": 76030096,
|
|
"step": 64400,
|
|
"train_runtime": 111359.3767,
|
|
"train_tokens_per_second": 682.745
|
|
},
|
|
{
|
|
"epoch": 0.06215043394406943,
|
|
"grad_norm": 7.1891093254089355,
|
|
"learning_rate": 0.00019812906215930013,
|
|
"loss": 1.0819225311279297,
|
|
"num_input_tokens_seen": 76067248,
|
|
"step": 64450,
|
|
"train_runtime": 111421.364,
|
|
"train_tokens_per_second": 682.699
|
|
},
|
|
{
|
|
"epoch": 0.062198649951783994,
|
|
"grad_norm": 11.981500625610352,
|
|
"learning_rate": 0.00019812614324036862,
|
|
"loss": 1.1688265228271484,
|
|
"num_input_tokens_seen": 76105424,
|
|
"step": 64500,
|
|
"train_runtime": 111483.5591,
|
|
"train_tokens_per_second": 682.661
|
|
},
|
|
{
|
|
"epoch": 0.062246865959498555,
|
|
"grad_norm": 14.5863618850708,
|
|
"learning_rate": 0.0001981232220677902,
|
|
"loss": 1.15604248046875,
|
|
"num_input_tokens_seen": 76141896,
|
|
"step": 64550,
|
|
"train_runtime": 111545.6501,
|
|
"train_tokens_per_second": 682.607
|
|
},
|
|
{
|
|
"epoch": 0.06229508196721312,
|
|
"grad_norm": 6.14052677154541,
|
|
"learning_rate": 0.000198120298641632,
|
|
"loss": 1.1354222106933594,
|
|
"num_input_tokens_seen": 76179376,
|
|
"step": 64600,
|
|
"train_runtime": 111608.4777,
|
|
"train_tokens_per_second": 682.559
|
|
},
|
|
{
|
|
"epoch": 0.06234329797492768,
|
|
"grad_norm": 8.992289543151855,
|
|
"learning_rate": 0.00019811737296196116,
|
|
"loss": 1.1317434692382813,
|
|
"num_input_tokens_seen": 76216568,
|
|
"step": 64650,
|
|
"train_runtime": 111670.8241,
|
|
"train_tokens_per_second": 682.511
|
|
},
|
|
{
|
|
"epoch": 0.062391513982642234,
|
|
"grad_norm": 9.367021560668945,
|
|
"learning_rate": 0.00019811444502884485,
|
|
"loss": 1.199867706298828,
|
|
"num_input_tokens_seen": 76253912,
|
|
"step": 64700,
|
|
"train_runtime": 111733.0453,
|
|
"train_tokens_per_second": 682.465
|
|
},
|
|
{
|
|
"epoch": 0.062439729990356796,
|
|
"grad_norm": 8.53625774383545,
|
|
"learning_rate": 0.00019811151484235029,
|
|
"loss": 1.1419342041015625,
|
|
"num_input_tokens_seen": 76290776,
|
|
"step": 64750,
|
|
"train_runtime": 111795.6043,
|
|
"train_tokens_per_second": 682.413
|
|
},
|
|
{
|
|
"epoch": 0.06248794599807136,
|
|
"grad_norm": 7.355682849884033,
|
|
"learning_rate": 0.00019810858240254482,
|
|
"loss": 1.175681381225586,
|
|
"num_input_tokens_seen": 76328408,
|
|
"step": 64800,
|
|
"train_runtime": 111858.2964,
|
|
"train_tokens_per_second": 682.367
|
|
},
|
|
{
|
|
"epoch": 0.06253616200578592,
|
|
"grad_norm": 11.23934555053711,
|
|
"learning_rate": 0.0001981056477094958,
|
|
"loss": 1.1463819122314454,
|
|
"num_input_tokens_seen": 76365144,
|
|
"step": 64850,
|
|
"train_runtime": 111920.5826,
|
|
"train_tokens_per_second": 682.315
|
|
},
|
|
{
|
|
"epoch": 0.06258437801350049,
|
|
"grad_norm": 8.248231887817383,
|
|
"learning_rate": 0.00019810271076327058,
|
|
"loss": 1.1311028289794922,
|
|
"num_input_tokens_seen": 76402512,
|
|
"step": 64900,
|
|
"train_runtime": 111982.8389,
|
|
"train_tokens_per_second": 682.27
|
|
},
|
|
{
|
|
"epoch": 0.06263259402121504,
|
|
"grad_norm": 7.086453914642334,
|
|
"learning_rate": 0.00019809977156393663,
|
|
"loss": 1.1563079071044922,
|
|
"num_input_tokens_seen": 76440080,
|
|
"step": 64950,
|
|
"train_runtime": 112045.366,
|
|
"train_tokens_per_second": 682.224
|
|
},
|
|
{
|
|
"epoch": 0.0626808100289296,
|
|
"grad_norm": 8.092480659484863,
|
|
"learning_rate": 0.0001980968301115615,
|
|
"loss": 1.213731460571289,
|
|
"num_input_tokens_seen": 76477784,
|
|
"step": 65000,
|
|
"train_runtime": 112108.067,
|
|
"train_tokens_per_second": 682.179
|
|
},
|
|
{
|
|
"epoch": 0.06272902603664417,
|
|
"grad_norm": 11.879746437072754,
|
|
"learning_rate": 0.00019809388640621271,
|
|
"loss": 1.207436294555664,
|
|
"num_input_tokens_seen": 76514544,
|
|
"step": 65050,
|
|
"train_runtime": 112170.0605,
|
|
"train_tokens_per_second": 682.13
|
|
},
|
|
{
|
|
"epoch": 0.06277724204435872,
|
|
"grad_norm": 8.119400024414062,
|
|
"learning_rate": 0.00019809094044795787,
|
|
"loss": 1.1211883544921875,
|
|
"num_input_tokens_seen": 76553072,
|
|
"step": 65100,
|
|
"train_runtime": 112233.6883,
|
|
"train_tokens_per_second": 682.086
|
|
},
|
|
{
|
|
"epoch": 0.06282545805207329,
|
|
"grad_norm": 7.051201820373535,
|
|
"learning_rate": 0.00019808799223686461,
|
|
"loss": 1.106191177368164,
|
|
"num_input_tokens_seen": 76590352,
|
|
"step": 65150,
|
|
"train_runtime": 112296.0439,
|
|
"train_tokens_per_second": 682.04
|
|
},
|
|
{
|
|
"epoch": 0.06287367405978785,
|
|
"grad_norm": 9.8606538772583,
|
|
"learning_rate": 0.0001980850417730007,
|
|
"loss": 1.1369544219970704,
|
|
"num_input_tokens_seen": 76627536,
|
|
"step": 65200,
|
|
"train_runtime": 112359.8059,
|
|
"train_tokens_per_second": 681.984
|
|
},
|
|
{
|
|
"epoch": 0.06292189006750241,
|
|
"grad_norm": 9.793075561523438,
|
|
"learning_rate": 0.00019808208905643384,
|
|
"loss": 1.19390380859375,
|
|
"num_input_tokens_seen": 76665312,
|
|
"step": 65250,
|
|
"train_runtime": 112422.3525,
|
|
"train_tokens_per_second": 681.94
|
|
},
|
|
{
|
|
"epoch": 0.06297010607521697,
|
|
"grad_norm": 9.163419723510742,
|
|
"learning_rate": 0.0001980791340872319,
|
|
"loss": 1.1681425476074219,
|
|
"num_input_tokens_seen": 76702480,
|
|
"step": 65300,
|
|
"train_runtime": 112485.2152,
|
|
"train_tokens_per_second": 681.889
|
|
},
|
|
{
|
|
"epoch": 0.06301832208293154,
|
|
"grad_norm": 7.9919633865356445,
|
|
"learning_rate": 0.0001980761768654627,
|
|
"loss": 1.1034510040283203,
|
|
"num_input_tokens_seen": 76740088,
|
|
"step": 65350,
|
|
"train_runtime": 112547.4878,
|
|
"train_tokens_per_second": 681.846
|
|
},
|
|
{
|
|
"epoch": 0.0630665380906461,
|
|
"grad_norm": 8.062710762023926,
|
|
"learning_rate": 0.0001980732173911942,
|
|
"loss": 1.1706863403320313,
|
|
"num_input_tokens_seen": 76777464,
|
|
"step": 65400,
|
|
"train_runtime": 112609.6853,
|
|
"train_tokens_per_second": 681.802
|
|
},
|
|
{
|
|
"epoch": 0.06311475409836066,
|
|
"grad_norm": 6.9489922523498535,
|
|
"learning_rate": 0.00019807025566449433,
|
|
"loss": 1.1352531433105468,
|
|
"num_input_tokens_seen": 76815392,
|
|
"step": 65450,
|
|
"train_runtime": 112672.419,
|
|
"train_tokens_per_second": 681.759
|
|
},
|
|
{
|
|
"epoch": 0.06316297010607522,
|
|
"grad_norm": 9.999833106994629,
|
|
"learning_rate": 0.00019806729168543114,
|
|
"loss": 1.169154815673828,
|
|
"num_input_tokens_seen": 76853360,
|
|
"step": 65500,
|
|
"train_runtime": 112735.0023,
|
|
"train_tokens_per_second": 681.717
|
|
},
|
|
{
|
|
"epoch": 0.06321118611378977,
|
|
"grad_norm": 8.145416259765625,
|
|
"learning_rate": 0.0001980643254540727,
|
|
"loss": 1.1549246215820312,
|
|
"num_input_tokens_seen": 76891672,
|
|
"step": 65550,
|
|
"train_runtime": 112797.9993,
|
|
"train_tokens_per_second": 681.676
|
|
},
|
|
{
|
|
"epoch": 0.06325940212150434,
|
|
"grad_norm": 13.822686195373535,
|
|
"learning_rate": 0.00019806135697048713,
|
|
"loss": 1.0911719512939453,
|
|
"num_input_tokens_seen": 76929024,
|
|
"step": 65600,
|
|
"train_runtime": 112860.5277,
|
|
"train_tokens_per_second": 681.629
|
|
},
|
|
{
|
|
"epoch": 0.0633076181292189,
|
|
"grad_norm": 5.581392288208008,
|
|
"learning_rate": 0.0001980583862347426,
|
|
"loss": 1.1321220397949219,
|
|
"num_input_tokens_seen": 76966608,
|
|
"step": 65650,
|
|
"train_runtime": 112922.5709,
|
|
"train_tokens_per_second": 681.587
|
|
},
|
|
{
|
|
"epoch": 0.06335583413693346,
|
|
"grad_norm": 10.381382942199707,
|
|
"learning_rate": 0.00019805541324690736,
|
|
"loss": 1.1185501861572265,
|
|
"num_input_tokens_seen": 77004896,
|
|
"step": 65700,
|
|
"train_runtime": 112985.0256,
|
|
"train_tokens_per_second": 681.55
|
|
},
|
|
{
|
|
"epoch": 0.06340405014464802,
|
|
"grad_norm": 6.784235000610352,
|
|
"learning_rate": 0.00019805243800704965,
|
|
"loss": 1.1186434936523437,
|
|
"num_input_tokens_seen": 77041552,
|
|
"step": 65750,
|
|
"train_runtime": 113047.8678,
|
|
"train_tokens_per_second": 681.495
|
|
},
|
|
{
|
|
"epoch": 0.06345226615236259,
|
|
"grad_norm": 9.980734825134277,
|
|
"learning_rate": 0.00019804946051523781,
|
|
"loss": 1.1305064392089843,
|
|
"num_input_tokens_seen": 77079144,
|
|
"step": 65800,
|
|
"train_runtime": 113110.9254,
|
|
"train_tokens_per_second": 681.447
|
|
},
|
|
{
|
|
"epoch": 0.06350048216007714,
|
|
"grad_norm": 8.297513961791992,
|
|
"learning_rate": 0.0001980465403884823,
|
|
"loss": 1.162227325439453,
|
|
"num_input_tokens_seen": 77115752,
|
|
"step": 65850,
|
|
"train_runtime": 113173.6308,
|
|
"train_tokens_per_second": 681.393
|
|
},
|
|
{
|
|
"epoch": 0.06354869816779171,
|
|
"grad_norm": 11.984286308288574,
|
|
"learning_rate": 0.00019804355843800313,
|
|
"loss": 1.144571533203125,
|
|
"num_input_tokens_seen": 77152976,
|
|
"step": 65900,
|
|
"train_runtime": 113236.2921,
|
|
"train_tokens_per_second": 681.345
|
|
},
|
|
{
|
|
"epoch": 0.06359691417550627,
|
|
"grad_norm": 11.78315544128418,
|
|
"learning_rate": 0.00019804057423577378,
|
|
"loss": 1.1017686462402343,
|
|
"num_input_tokens_seen": 77190056,
|
|
"step": 65950,
|
|
"train_runtime": 113299.449,
|
|
"train_tokens_per_second": 681.292
|
|
},
|
|
{
|
|
"epoch": 0.06364513018322084,
|
|
"grad_norm": 7.911302089691162,
|
|
"learning_rate": 0.00019803758778186282,
|
|
"loss": 1.2084862518310546,
|
|
"num_input_tokens_seen": 77227744,
|
|
"step": 66000,
|
|
"train_runtime": 113362.0303,
|
|
"train_tokens_per_second": 681.249
|
|
},
|
|
{
|
|
"epoch": 0.06369334619093539,
|
|
"grad_norm": 11.588493347167969,
|
|
"learning_rate": 0.00019803459907633876,
|
|
"loss": 1.1809027099609375,
|
|
"num_input_tokens_seen": 77264784,
|
|
"step": 66050,
|
|
"train_runtime": 113424.4243,
|
|
"train_tokens_per_second": 681.201
|
|
},
|
|
{
|
|
"epoch": 0.06374156219864995,
|
|
"grad_norm": 8.643106460571289,
|
|
"learning_rate": 0.00019803160811927034,
|
|
"loss": 1.1521694946289063,
|
|
"num_input_tokens_seen": 77302184,
|
|
"step": 66100,
|
|
"train_runtime": 113486.9261,
|
|
"train_tokens_per_second": 681.155
|
|
},
|
|
{
|
|
"epoch": 0.06378977820636451,
|
|
"grad_norm": 11.877742767333984,
|
|
"learning_rate": 0.0001980286747969611,
|
|
"loss": 1.349749298095703,
|
|
"num_input_tokens_seen": 77339128,
|
|
"step": 66150,
|
|
"train_runtime": 113549.5947,
|
|
"train_tokens_per_second": 681.104
|
|
},
|
|
{
|
|
"epoch": 0.06383799421407907,
|
|
"grad_norm": 8.120502471923828,
|
|
"learning_rate": 0.00019802567938203742,
|
|
"loss": 1.1350501251220704,
|
|
"num_input_tokens_seen": 77377352,
|
|
"step": 66200,
|
|
"train_runtime": 113612.1586,
|
|
"train_tokens_per_second": 681.066
|
|
},
|
|
{
|
|
"epoch": 0.06388621022179364,
|
|
"grad_norm": 8.3599853515625,
|
|
"learning_rate": 0.0001980226817157742,
|
|
"loss": 1.1808929443359375,
|
|
"num_input_tokens_seen": 77414496,
|
|
"step": 66250,
|
|
"train_runtime": 113675.3451,
|
|
"train_tokens_per_second": 681.014
|
|
},
|
|
{
|
|
"epoch": 0.06393442622950819,
|
|
"grad_norm": 8.463664054870605,
|
|
"learning_rate": 0.00019801968179824028,
|
|
"loss": 1.157327651977539,
|
|
"num_input_tokens_seen": 77452376,
|
|
"step": 66300,
|
|
"train_runtime": 113738.226,
|
|
"train_tokens_per_second": 680.97
|
|
},
|
|
{
|
|
"epoch": 0.06398264223722276,
|
|
"grad_norm": 7.237782001495361,
|
|
"learning_rate": 0.00019801667962950455,
|
|
"loss": 1.1463134765625,
|
|
"num_input_tokens_seen": 77490024,
|
|
"step": 66350,
|
|
"train_runtime": 113800.621,
|
|
"train_tokens_per_second": 680.928
|
|
},
|
|
{
|
|
"epoch": 0.06403085824493732,
|
|
"grad_norm": 32.07834243774414,
|
|
"learning_rate": 0.00019801367520963598,
|
|
"loss": 1.1751631164550782,
|
|
"num_input_tokens_seen": 77527560,
|
|
"step": 66400,
|
|
"train_runtime": 113863.4031,
|
|
"train_tokens_per_second": 680.882
|
|
},
|
|
{
|
|
"epoch": 0.06407907425265189,
|
|
"grad_norm": 11.82642936706543,
|
|
"learning_rate": 0.00019801066853870355,
|
|
"loss": 1.130397491455078,
|
|
"num_input_tokens_seen": 77564768,
|
|
"step": 66450,
|
|
"train_runtime": 113925.8992,
|
|
"train_tokens_per_second": 680.835
|
|
},
|
|
{
|
|
"epoch": 0.06412729026036644,
|
|
"grad_norm": 15.885066986083984,
|
|
"learning_rate": 0.00019800765961677628,
|
|
"loss": 1.1952786254882812,
|
|
"num_input_tokens_seen": 77602520,
|
|
"step": 66500,
|
|
"train_runtime": 113988.5048,
|
|
"train_tokens_per_second": 680.793
|
|
},
|
|
{
|
|
"epoch": 0.06417550626808101,
|
|
"grad_norm": 12.763023376464844,
|
|
"learning_rate": 0.00019800464844392334,
|
|
"loss": 1.1958871459960938,
|
|
"num_input_tokens_seen": 77639336,
|
|
"step": 66550,
|
|
"train_runtime": 114050.4576,
|
|
"train_tokens_per_second": 680.746
|
|
},
|
|
{
|
|
"epoch": 0.06422372227579556,
|
|
"grad_norm": 11.488080024719238,
|
|
"learning_rate": 0.0001980016350202139,
|
|
"loss": 1.175879898071289,
|
|
"num_input_tokens_seen": 77677256,
|
|
"step": 66600,
|
|
"train_runtime": 114112.8886,
|
|
"train_tokens_per_second": 680.705
|
|
},
|
|
{
|
|
"epoch": 0.06427193828351012,
|
|
"grad_norm": 6.423185348510742,
|
|
"learning_rate": 0.00019799861934571706,
|
|
"loss": 1.1286878967285157,
|
|
"num_input_tokens_seen": 77715112,
|
|
"step": 66650,
|
|
"train_runtime": 114175.0966,
|
|
"train_tokens_per_second": 680.666
|
|
},
|
|
{
|
|
"epoch": 0.06432015429122469,
|
|
"grad_norm": 7.226300239562988,
|
|
"learning_rate": 0.00019799560142050223,
|
|
"loss": 1.2009384155273437,
|
|
"num_input_tokens_seen": 77752272,
|
|
"step": 66700,
|
|
"train_runtime": 114237.8616,
|
|
"train_tokens_per_second": 680.617
|
|
},
|
|
{
|
|
"epoch": 0.06436837029893924,
|
|
"grad_norm": 11.723835945129395,
|
|
"learning_rate": 0.00019799258124463857,
|
|
"loss": 1.190159683227539,
|
|
"num_input_tokens_seen": 77789560,
|
|
"step": 66750,
|
|
"train_runtime": 114300.5872,
|
|
"train_tokens_per_second": 680.57
|
|
},
|
|
{
|
|
"epoch": 0.06441658630665381,
|
|
"grad_norm": 8.1819429397583,
|
|
"learning_rate": 0.00019798955881819555,
|
|
"loss": 1.1951266479492189,
|
|
"num_input_tokens_seen": 77826480,
|
|
"step": 66800,
|
|
"train_runtime": 114363.4862,
|
|
"train_tokens_per_second": 680.519
|
|
},
|
|
{
|
|
"epoch": 0.06446480231436837,
|
|
"grad_norm": 7.7816362380981445,
|
|
"learning_rate": 0.00019798653414124256,
|
|
"loss": 1.212021942138672,
|
|
"num_input_tokens_seen": 77863536,
|
|
"step": 66850,
|
|
"train_runtime": 114426.0368,
|
|
"train_tokens_per_second": 680.47
|
|
},
|
|
{
|
|
"epoch": 0.06451301832208294,
|
|
"grad_norm": 9.847285270690918,
|
|
"learning_rate": 0.00019798350721384904,
|
|
"loss": 1.1681783294677734,
|
|
"num_input_tokens_seen": 77901280,
|
|
"step": 66900,
|
|
"train_runtime": 114488.4846,
|
|
"train_tokens_per_second": 680.429
|
|
},
|
|
{
|
|
"epoch": 0.06456123432979749,
|
|
"grad_norm": 9.51707649230957,
|
|
"learning_rate": 0.00019798047803608454,
|
|
"loss": 1.1384978485107422,
|
|
"num_input_tokens_seen": 77938456,
|
|
"step": 66950,
|
|
"train_runtime": 114550.9234,
|
|
"train_tokens_per_second": 680.383
|
|
},
|
|
{
|
|
"epoch": 0.06460945033751206,
|
|
"grad_norm": 6.01658821105957,
|
|
"learning_rate": 0.0001979774466080186,
|
|
"loss": 1.1733963775634766,
|
|
"num_input_tokens_seen": 77976080,
|
|
"step": 67000,
|
|
"train_runtime": 114613.921,
|
|
"train_tokens_per_second": 680.337
|
|
},
|
|
{
|
|
"epoch": 0.06465766634522661,
|
|
"grad_norm": 6.3508172035217285,
|
|
"learning_rate": 0.00019797441292972087,
|
|
"loss": 1.2337963104248046,
|
|
"num_input_tokens_seen": 78012704,
|
|
"step": 67050,
|
|
"train_runtime": 114676.1875,
|
|
"train_tokens_per_second": 680.287
|
|
},
|
|
{
|
|
"epoch": 0.06470588235294118,
|
|
"grad_norm": 11.662497520446777,
|
|
"learning_rate": 0.00019797137700126104,
|
|
"loss": 1.1299124145507813,
|
|
"num_input_tokens_seen": 78049848,
|
|
"step": 67100,
|
|
"train_runtime": 114738.6847,
|
|
"train_tokens_per_second": 680.24
|
|
},
|
|
{
|
|
"epoch": 0.06475409836065574,
|
|
"grad_norm": 7.3852972984313965,
|
|
"learning_rate": 0.0001979683388227088,
|
|
"loss": 1.1634918212890626,
|
|
"num_input_tokens_seen": 78088432,
|
|
"step": 67150,
|
|
"train_runtime": 114801.1433,
|
|
"train_tokens_per_second": 680.206
|
|
},
|
|
{
|
|
"epoch": 0.06480231436837029,
|
|
"grad_norm": 6.801599979400635,
|
|
"learning_rate": 0.00019796529839413393,
|
|
"loss": 1.156591262817383,
|
|
"num_input_tokens_seen": 78126024,
|
|
"step": 67200,
|
|
"train_runtime": 114863.5558,
|
|
"train_tokens_per_second": 680.164
|
|
},
|
|
{
|
|
"epoch": 0.06485053037608486,
|
|
"grad_norm": 13.359579086303711,
|
|
"learning_rate": 0.00019796225571560628,
|
|
"loss": 1.145983428955078,
|
|
"num_input_tokens_seen": 78162920,
|
|
"step": 67250,
|
|
"train_runtime": 114926.5303,
|
|
"train_tokens_per_second": 680.112
|
|
},
|
|
{
|
|
"epoch": 0.06489874638379942,
|
|
"grad_norm": 9.56835651397705,
|
|
"learning_rate": 0.00019795921078719572,
|
|
"loss": 1.1895063018798828,
|
|
"num_input_tokens_seen": 78200464,
|
|
"step": 67300,
|
|
"train_runtime": 114988.7934,
|
|
"train_tokens_per_second": 680.07
|
|
},
|
|
{
|
|
"epoch": 0.06494696239151398,
|
|
"grad_norm": 9.129262924194336,
|
|
"learning_rate": 0.00019795616360897215,
|
|
"loss": 1.1615853118896484,
|
|
"num_input_tokens_seen": 78237936,
|
|
"step": 67350,
|
|
"train_runtime": 115051.0528,
|
|
"train_tokens_per_second": 680.028
|
|
},
|
|
{
|
|
"epoch": 0.06499517839922854,
|
|
"grad_norm": 6.04575777053833,
|
|
"learning_rate": 0.00019795311418100559,
|
|
"loss": 1.121395263671875,
|
|
"num_input_tokens_seen": 78275960,
|
|
"step": 67400,
|
|
"train_runtime": 115114.0189,
|
|
"train_tokens_per_second": 679.986
|
|
},
|
|
{
|
|
"epoch": 0.06504339440694311,
|
|
"grad_norm": 12.550371170043945,
|
|
"learning_rate": 0.00019795006250336613,
|
|
"loss": 1.125506362915039,
|
|
"num_input_tokens_seen": 78313168,
|
|
"step": 67450,
|
|
"train_runtime": 115176.1685,
|
|
"train_tokens_per_second": 679.942
|
|
},
|
|
{
|
|
"epoch": 0.06509161041465766,
|
|
"grad_norm": 14.704473495483398,
|
|
"learning_rate": 0.00019794700857612375,
|
|
"loss": 1.1969541168212892,
|
|
"num_input_tokens_seen": 78350200,
|
|
"step": 67500,
|
|
"train_runtime": 115239.2263,
|
|
"train_tokens_per_second": 679.892
|
|
},
|
|
{
|
|
"epoch": 0.06513982642237223,
|
|
"grad_norm": 8.672008514404297,
|
|
"learning_rate": 0.0001979439523993486,
|
|
"loss": 1.142307891845703,
|
|
"num_input_tokens_seen": 78388016,
|
|
"step": 67550,
|
|
"train_runtime": 115302.0691,
|
|
"train_tokens_per_second": 679.849
|
|
},
|
|
{
|
|
"epoch": 0.06518804243008679,
|
|
"grad_norm": 7.482205867767334,
|
|
"learning_rate": 0.00019794089397311097,
|
|
"loss": 1.171025390625,
|
|
"num_input_tokens_seen": 78425512,
|
|
"step": 67600,
|
|
"train_runtime": 115364.3909,
|
|
"train_tokens_per_second": 679.807
|
|
},
|
|
{
|
|
"epoch": 0.06523625843780136,
|
|
"grad_norm": 7.396176815032959,
|
|
"learning_rate": 0.000197937833297481,
|
|
"loss": 1.1151951599121093,
|
|
"num_input_tokens_seen": 78462792,
|
|
"step": 67650,
|
|
"train_runtime": 115426.6042,
|
|
"train_tokens_per_second": 679.763
|
|
},
|
|
{
|
|
"epoch": 0.06528447444551591,
|
|
"grad_norm": 7.547196865081787,
|
|
"learning_rate": 0.00019793477037252907,
|
|
"loss": 1.149512710571289,
|
|
"num_input_tokens_seen": 78500680,
|
|
"step": 67700,
|
|
"train_runtime": 115489.5154,
|
|
"train_tokens_per_second": 679.721
|
|
},
|
|
{
|
|
"epoch": 0.06533269045323047,
|
|
"grad_norm": 8.398334503173828,
|
|
"learning_rate": 0.00019793170519832542,
|
|
"loss": 1.1834641265869141,
|
|
"num_input_tokens_seen": 78538008,
|
|
"step": 67750,
|
|
"train_runtime": 115553.026,
|
|
"train_tokens_per_second": 679.671
|
|
},
|
|
{
|
|
"epoch": 0.06538090646094503,
|
|
"grad_norm": 11.323487281799316,
|
|
"learning_rate": 0.00019792863777494055,
|
|
"loss": 1.1650677490234376,
|
|
"num_input_tokens_seen": 78575872,
|
|
"step": 67800,
|
|
"train_runtime": 115616.0838,
|
|
"train_tokens_per_second": 679.628
|
|
},
|
|
{
|
|
"epoch": 0.06542912246865959,
|
|
"grad_norm": 6.440436363220215,
|
|
"learning_rate": 0.00019792556810244486,
|
|
"loss": 1.1434661102294923,
|
|
"num_input_tokens_seen": 78613152,
|
|
"step": 67850,
|
|
"train_runtime": 115678.6682,
|
|
"train_tokens_per_second": 679.582
|
|
},
|
|
{
|
|
"epoch": 0.06547733847637416,
|
|
"grad_norm": 8.674132347106934,
|
|
"learning_rate": 0.00019792249618090884,
|
|
"loss": 1.123896026611328,
|
|
"num_input_tokens_seen": 78649984,
|
|
"step": 67900,
|
|
"train_runtime": 115741.1345,
|
|
"train_tokens_per_second": 679.534
|
|
},
|
|
{
|
|
"epoch": 0.06552555448408871,
|
|
"grad_norm": 5.883489608764648,
|
|
"learning_rate": 0.0001979194220104031,
|
|
"loss": 1.142643051147461,
|
|
"num_input_tokens_seen": 78688248,
|
|
"step": 67950,
|
|
"train_runtime": 115804.4165,
|
|
"train_tokens_per_second": 679.493
|
|
},
|
|
{
|
|
"epoch": 0.06557377049180328,
|
|
"grad_norm": 14.34758472442627,
|
|
"learning_rate": 0.00019791634559099817,
|
|
"loss": 1.1815642547607421,
|
|
"num_input_tokens_seen": 78725752,
|
|
"step": 68000,
|
|
"train_runtime": 115866.9087,
|
|
"train_tokens_per_second": 679.45
|
|
},
|
|
{
|
|
"epoch": 0.06562198649951784,
|
|
"grad_norm": 6.374905586242676,
|
|
"learning_rate": 0.0001979132669227647,
|
|
"loss": 1.1278973388671876,
|
|
"num_input_tokens_seen": 78763200,
|
|
"step": 68050,
|
|
"train_runtime": 115929.43,
|
|
"train_tokens_per_second": 679.406
|
|
},
|
|
{
|
|
"epoch": 0.0656702025072324,
|
|
"grad_norm": 8.963485717773438,
|
|
"learning_rate": 0.00019791018600577348,
|
|
"loss": 1.1319318389892579,
|
|
"num_input_tokens_seen": 78800792,
|
|
"step": 68100,
|
|
"train_runtime": 115991.7302,
|
|
"train_tokens_per_second": 679.366
|
|
},
|
|
{
|
|
"epoch": 0.06571841851494696,
|
|
"grad_norm": 18.8303279876709,
|
|
"learning_rate": 0.00019790710284009523,
|
|
"loss": 1.1221604919433594,
|
|
"num_input_tokens_seen": 78837848,
|
|
"step": 68150,
|
|
"train_runtime": 116054.0185,
|
|
"train_tokens_per_second": 679.32
|
|
},
|
|
{
|
|
"epoch": 0.06576663452266153,
|
|
"grad_norm": 8.451530456542969,
|
|
"learning_rate": 0.00019790401742580076,
|
|
"loss": 1.1766030120849609,
|
|
"num_input_tokens_seen": 78875536,
|
|
"step": 68200,
|
|
"train_runtime": 116117.0324,
|
|
"train_tokens_per_second": 679.276
|
|
},
|
|
{
|
|
"epoch": 0.06581485053037608,
|
|
"grad_norm": 8.510188102722168,
|
|
"learning_rate": 0.00019790092976296092,
|
|
"loss": 1.1892725372314452,
|
|
"num_input_tokens_seen": 78912600,
|
|
"step": 68250,
|
|
"train_runtime": 116179.8136,
|
|
"train_tokens_per_second": 679.228
|
|
},
|
|
{
|
|
"epoch": 0.06586306653809064,
|
|
"grad_norm": 14.1071138381958,
|
|
"learning_rate": 0.00019789783985164664,
|
|
"loss": 1.1883856964111328,
|
|
"num_input_tokens_seen": 78948904,
|
|
"step": 68300,
|
|
"train_runtime": 116242.2093,
|
|
"train_tokens_per_second": 679.176
|
|
},
|
|
{
|
|
"epoch": 0.06591128254580521,
|
|
"grad_norm": 10.756312370300293,
|
|
"learning_rate": 0.0001978948095571571,
|
|
"loss": 1.1681300354003907,
|
|
"num_input_tokens_seen": 78986664,
|
|
"step": 68350,
|
|
"train_runtime": 116305.1952,
|
|
"train_tokens_per_second": 679.133
|
|
},
|
|
{
|
|
"epoch": 0.06595949855351976,
|
|
"grad_norm": 8.64816665649414,
|
|
"learning_rate": 0.00019789171519407278,
|
|
"loss": 1.1950475311279296,
|
|
"num_input_tokens_seen": 79024632,
|
|
"step": 68400,
|
|
"train_runtime": 116367.8008,
|
|
"train_tokens_per_second": 679.094
|
|
},
|
|
{
|
|
"epoch": 0.06600771456123433,
|
|
"grad_norm": 13.163955688476562,
|
|
"learning_rate": 0.0001978886185827257,
|
|
"loss": 1.1934748077392578,
|
|
"num_input_tokens_seen": 79061472,
|
|
"step": 68450,
|
|
"train_runtime": 116430.4176,
|
|
"train_tokens_per_second": 679.045
|
|
},
|
|
{
|
|
"epoch": 0.06605593056894889,
|
|
"grad_norm": 6.4503889083862305,
|
|
"learning_rate": 0.00019788551972318687,
|
|
"loss": 1.1307715606689452,
|
|
"num_input_tokens_seen": 79098272,
|
|
"step": 68500,
|
|
"train_runtime": 116493.2221,
|
|
"train_tokens_per_second": 678.995
|
|
},
|
|
{
|
|
"epoch": 0.06610414657666346,
|
|
"grad_norm": 5.991762161254883,
|
|
"learning_rate": 0.00019788241861552755,
|
|
"loss": 1.214625015258789,
|
|
"num_input_tokens_seen": 79136456,
|
|
"step": 68550,
|
|
"train_runtime": 116555.9629,
|
|
"train_tokens_per_second": 678.957
|
|
},
|
|
{
|
|
"epoch": 0.06615236258437801,
|
|
"grad_norm": 7.302918434143066,
|
|
"learning_rate": 0.00019787931525981888,
|
|
"loss": 1.1943434143066407,
|
|
"num_input_tokens_seen": 79172752,
|
|
"step": 68600,
|
|
"train_runtime": 116619.3099,
|
|
"train_tokens_per_second": 678.899
|
|
},
|
|
{
|
|
"epoch": 0.06620057859209258,
|
|
"grad_norm": 6.872028827667236,
|
|
"learning_rate": 0.00019787620965613223,
|
|
"loss": 1.1300765991210937,
|
|
"num_input_tokens_seen": 79210048,
|
|
"step": 68650,
|
|
"train_runtime": 116681.7647,
|
|
"train_tokens_per_second": 678.855
|
|
},
|
|
{
|
|
"epoch": 0.06624879459980713,
|
|
"grad_norm": 6.021572113037109,
|
|
"learning_rate": 0.0001978731018045388,
|
|
"loss": 1.1575247192382812,
|
|
"num_input_tokens_seen": 79247536,
|
|
"step": 68700,
|
|
"train_runtime": 116743.9022,
|
|
"train_tokens_per_second": 678.815
|
|
},
|
|
{
|
|
"epoch": 0.0662970106075217,
|
|
"grad_norm": 7.0864033699035645,
|
|
"learning_rate": 0.0001978699917051101,
|
|
"loss": 1.127186050415039,
|
|
"num_input_tokens_seen": 79284392,
|
|
"step": 68750,
|
|
"train_runtime": 116806.8069,
|
|
"train_tokens_per_second": 678.765
|
|
},
|
|
{
|
|
"epoch": 0.06634522661523626,
|
|
"grad_norm": 8.243281364440918,
|
|
"learning_rate": 0.00019786687935791753,
|
|
"loss": 1.1409558868408203,
|
|
"num_input_tokens_seen": 79321576,
|
|
"step": 68800,
|
|
"train_runtime": 116868.6721,
|
|
"train_tokens_per_second": 678.724
|
|
},
|
|
{
|
|
"epoch": 0.06639344262295081,
|
|
"grad_norm": 5.645218372344971,
|
|
"learning_rate": 0.00019786376476303247,
|
|
"loss": 1.1355223083496093,
|
|
"num_input_tokens_seen": 79359440,
|
|
"step": 68850,
|
|
"train_runtime": 116931.1633,
|
|
"train_tokens_per_second": 678.685
|
|
},
|
|
{
|
|
"epoch": 0.06644165863066538,
|
|
"grad_norm": 6.588528633117676,
|
|
"learning_rate": 0.00019786064792052656,
|
|
"loss": 1.1438973999023438,
|
|
"num_input_tokens_seen": 79396448,
|
|
"step": 68900,
|
|
"train_runtime": 116993.9004,
|
|
"train_tokens_per_second": 678.637
|
|
},
|
|
{
|
|
"epoch": 0.06648987463837994,
|
|
"grad_norm": 8.164804458618164,
|
|
"learning_rate": 0.00019785752883047134,
|
|
"loss": 1.1725099182128906,
|
|
"num_input_tokens_seen": 79434104,
|
|
"step": 68950,
|
|
"train_runtime": 117056.283,
|
|
"train_tokens_per_second": 678.598
|
|
},
|
|
{
|
|
"epoch": 0.0665380906460945,
|
|
"grad_norm": 20.1795711517334,
|
|
"learning_rate": 0.00019785440749293847,
|
|
"loss": 1.1554071044921874,
|
|
"num_input_tokens_seen": 79471592,
|
|
"step": 69000,
|
|
"train_runtime": 117118.6962,
|
|
"train_tokens_per_second": 678.556
|
|
},
|
|
{
|
|
"epoch": 0.06658630665380906,
|
|
"grad_norm": 9.253666877746582,
|
|
"learning_rate": 0.0001978512839079996,
|
|
"loss": 1.1779163360595704,
|
|
"num_input_tokens_seen": 79508456,
|
|
"step": 69050,
|
|
"train_runtime": 117180.9982,
|
|
"train_tokens_per_second": 678.51
|
|
},
|
|
{
|
|
"epoch": 0.06663452266152363,
|
|
"grad_norm": 6.888736248016357,
|
|
"learning_rate": 0.0001978481580757265,
|
|
"loss": 1.1543569946289063,
|
|
"num_input_tokens_seen": 79546280,
|
|
"step": 69100,
|
|
"train_runtime": 117244.4715,
|
|
"train_tokens_per_second": 678.465
|
|
},
|
|
{
|
|
"epoch": 0.06668273866923818,
|
|
"grad_norm": 8.301615715026855,
|
|
"learning_rate": 0.00019784502999619096,
|
|
"loss": 1.2054548645019532,
|
|
"num_input_tokens_seen": 79583664,
|
|
"step": 69150,
|
|
"train_runtime": 117307.1394,
|
|
"train_tokens_per_second": 678.421
|
|
},
|
|
{
|
|
"epoch": 0.06673095467695275,
|
|
"grad_norm": 6.298430919647217,
|
|
"learning_rate": 0.00019784189966946477,
|
|
"loss": 1.1646295928955077,
|
|
"num_input_tokens_seen": 79621624,
|
|
"step": 69200,
|
|
"train_runtime": 117369.4372,
|
|
"train_tokens_per_second": 678.385
|
|
},
|
|
{
|
|
"epoch": 0.06677917068466731,
|
|
"grad_norm": 11.52436351776123,
|
|
"learning_rate": 0.0001978387670956199,
|
|
"loss": 1.1802553558349609,
|
|
"num_input_tokens_seen": 79658840,
|
|
"step": 69250,
|
|
"train_runtime": 117431.7885,
|
|
"train_tokens_per_second": 678.341
|
|
},
|
|
{
|
|
"epoch": 0.06682738669238188,
|
|
"grad_norm": 10.116995811462402,
|
|
"learning_rate": 0.00019783563227472825,
|
|
"loss": 1.1973839569091798,
|
|
"num_input_tokens_seen": 79695896,
|
|
"step": 69300,
|
|
"train_runtime": 117494.095,
|
|
"train_tokens_per_second": 678.297
|
|
},
|
|
{
|
|
"epoch": 0.06687560270009643,
|
|
"grad_norm": 9.029375076293945,
|
|
"learning_rate": 0.00019783249520686184,
|
|
"loss": 1.1854930877685548,
|
|
"num_input_tokens_seen": 79732944,
|
|
"step": 69350,
|
|
"train_runtime": 117556.4567,
|
|
"train_tokens_per_second": 678.252
|
|
},
|
|
{
|
|
"epoch": 0.06692381870781099,
|
|
"grad_norm": 7.093355655670166,
|
|
"learning_rate": 0.00019782935589209268,
|
|
"loss": 1.2076673126220703,
|
|
"num_input_tokens_seen": 79771216,
|
|
"step": 69400,
|
|
"train_runtime": 117619.4107,
|
|
"train_tokens_per_second": 678.215
|
|
},
|
|
{
|
|
"epoch": 0.06697203471552556,
|
|
"grad_norm": 20.07047462463379,
|
|
"learning_rate": 0.00019782621433049293,
|
|
"loss": 1.178141860961914,
|
|
"num_input_tokens_seen": 79809216,
|
|
"step": 69450,
|
|
"train_runtime": 117681.9903,
|
|
"train_tokens_per_second": 678.177
|
|
},
|
|
{
|
|
"epoch": 0.06702025072324011,
|
|
"grad_norm": 7.668863773345947,
|
|
"learning_rate": 0.0001978230705221347,
|
|
"loss": 1.223416290283203,
|
|
"num_input_tokens_seen": 79847176,
|
|
"step": 69500,
|
|
"train_runtime": 117744.7969,
|
|
"train_tokens_per_second": 678.138
|
|
},
|
|
{
|
|
"epoch": 0.06706846673095468,
|
|
"grad_norm": 7.908514499664307,
|
|
"learning_rate": 0.00019781992446709018,
|
|
"loss": 1.2046939086914064,
|
|
"num_input_tokens_seen": 79884928,
|
|
"step": 69550,
|
|
"train_runtime": 117807.4726,
|
|
"train_tokens_per_second": 678.097
|
|
},
|
|
{
|
|
"epoch": 0.06711668273866923,
|
|
"grad_norm": 11.552886962890625,
|
|
"learning_rate": 0.00019781677616543167,
|
|
"loss": 1.1499716186523437,
|
|
"num_input_tokens_seen": 79922352,
|
|
"step": 69600,
|
|
"train_runtime": 117870.0427,
|
|
"train_tokens_per_second": 678.055
|
|
},
|
|
{
|
|
"epoch": 0.0671648987463838,
|
|
"grad_norm": 17.524765014648438,
|
|
"learning_rate": 0.00019781362561723144,
|
|
"loss": 1.210535125732422,
|
|
"num_input_tokens_seen": 79958816,
|
|
"step": 69650,
|
|
"train_runtime": 117932.9858,
|
|
"train_tokens_per_second": 678.002
|
|
},
|
|
{
|
|
"epoch": 0.06721311475409836,
|
|
"grad_norm": 16.857341766357422,
|
|
"learning_rate": 0.00019781047282256187,
|
|
"loss": 1.2085854339599609,
|
|
"num_input_tokens_seen": 79995320,
|
|
"step": 69700,
|
|
"train_runtime": 117995.7986,
|
|
"train_tokens_per_second": 677.951
|
|
},
|
|
{
|
|
"epoch": 0.06726133076181293,
|
|
"grad_norm": 12.37498950958252,
|
|
"learning_rate": 0.00019780731778149538,
|
|
"loss": 1.1809371185302735,
|
|
"num_input_tokens_seen": 80032920,
|
|
"step": 69750,
|
|
"train_runtime": 118058.5478,
|
|
"train_tokens_per_second": 677.909
|
|
},
|
|
{
|
|
"epoch": 0.06730954676952748,
|
|
"grad_norm": 7.948763847351074,
|
|
"learning_rate": 0.00019780416049410438,
|
|
"loss": 1.2697270965576173,
|
|
"num_input_tokens_seen": 80070760,
|
|
"step": 69800,
|
|
"train_runtime": 118121.3976,
|
|
"train_tokens_per_second": 677.868
|
|
},
|
|
{
|
|
"epoch": 0.06735776277724205,
|
|
"grad_norm": 9.183773040771484,
|
|
"learning_rate": 0.00019780106417314705,
|
|
"loss": 1.2068573760986328,
|
|
"num_input_tokens_seen": 80107792,
|
|
"step": 69850,
|
|
"train_runtime": 118183.6703,
|
|
"train_tokens_per_second": 677.825
|
|
},
|
|
{
|
|
"epoch": 0.0674059787849566,
|
|
"grad_norm": 56.743980407714844,
|
|
"learning_rate": 0.00019779790243824757,
|
|
"loss": 1.2994314575195312,
|
|
"num_input_tokens_seen": 80145984,
|
|
"step": 69900,
|
|
"train_runtime": 118246.8808,
|
|
"train_tokens_per_second": 677.785
|
|
},
|
|
{
|
|
"epoch": 0.06745419479267116,
|
|
"grad_norm": 17.05137825012207,
|
|
"learning_rate": 0.00019779473845723988,
|
|
"loss": 1.2434465026855468,
|
|
"num_input_tokens_seen": 80183728,
|
|
"step": 69950,
|
|
"train_runtime": 118308.8994,
|
|
"train_tokens_per_second": 677.749
|
|
},
|
|
{
|
|
"epoch": 0.06750241080038573,
|
|
"grad_norm": 9.613424301147461,
|
|
"learning_rate": 0.00019779157223019658,
|
|
"loss": 1.2230125427246095,
|
|
"num_input_tokens_seen": 80220176,
|
|
"step": 70000,
|
|
"train_runtime": 118371.3683,
|
|
"train_tokens_per_second": 677.699
|
|
},
|
|
{
|
|
"epoch": 0.06755062680810028,
|
|
"grad_norm": 21.674924850463867,
|
|
"learning_rate": 0.00019778840375719043,
|
|
"loss": 1.3134774780273437,
|
|
"num_input_tokens_seen": 80257616,
|
|
"step": 70050,
|
|
"train_runtime": 118434.7468,
|
|
"train_tokens_per_second": 677.653
|
|
},
|
|
{
|
|
"epoch": 0.06759884281581485,
|
|
"grad_norm": 8.871304512023926,
|
|
"learning_rate": 0.00019778523303829422,
|
|
"loss": 1.2403815460205079,
|
|
"num_input_tokens_seen": 80296160,
|
|
"step": 70100,
|
|
"train_runtime": 118497.287,
|
|
"train_tokens_per_second": 677.62
|
|
},
|
|
{
|
|
"epoch": 0.06764705882352941,
|
|
"grad_norm": 32.50084686279297,
|
|
"learning_rate": 0.00019778206007358074,
|
|
"loss": 1.225639877319336,
|
|
"num_input_tokens_seen": 80333744,
|
|
"step": 70150,
|
|
"train_runtime": 118559.4004,
|
|
"train_tokens_per_second": 677.582
|
|
},
|
|
{
|
|
"epoch": 0.06769527483124398,
|
|
"grad_norm": 20.324485778808594,
|
|
"learning_rate": 0.00019777888486312287,
|
|
"loss": 1.3176580810546874,
|
|
"num_input_tokens_seen": 80371384,
|
|
"step": 70200,
|
|
"train_runtime": 118622.5256,
|
|
"train_tokens_per_second": 677.539
|
|
},
|
|
{
|
|
"epoch": 0.06774349083895853,
|
|
"grad_norm": 21.592823028564453,
|
|
"learning_rate": 0.00019777570740699352,
|
|
"loss": 1.207292251586914,
|
|
"num_input_tokens_seen": 80408616,
|
|
"step": 70250,
|
|
"train_runtime": 118685.1139,
|
|
"train_tokens_per_second": 677.495
|
|
},
|
|
{
|
|
"epoch": 0.0677917068466731,
|
|
"grad_norm": 7.853658199310303,
|
|
"learning_rate": 0.00019777252770526572,
|
|
"loss": 1.228662109375,
|
|
"num_input_tokens_seen": 80446552,
|
|
"step": 70300,
|
|
"train_runtime": 118747.6229,
|
|
"train_tokens_per_second": 677.458
|
|
},
|
|
{
|
|
"epoch": 0.06783992285438765,
|
|
"grad_norm": 17.77448272705078,
|
|
"learning_rate": 0.00019776934575801243,
|
|
"loss": 1.2207595825195312,
|
|
"num_input_tokens_seen": 80484232,
|
|
"step": 70350,
|
|
"train_runtime": 118810.1517,
|
|
"train_tokens_per_second": 677.419
|
|
},
|
|
{
|
|
"epoch": 0.06788813886210222,
|
|
"grad_norm": 9.965555191040039,
|
|
"learning_rate": 0.00019776622527116583,
|
|
"loss": 1.2929034423828125,
|
|
"num_input_tokens_seen": 80521496,
|
|
"step": 70400,
|
|
"train_runtime": 118872.6527,
|
|
"train_tokens_per_second": 677.376
|
|
},
|
|
{
|
|
"epoch": 0.06793635486981678,
|
|
"grad_norm": 11.346697807312012,
|
|
"learning_rate": 0.00019776303887798777,
|
|
"loss": 1.2592837524414062,
|
|
"num_input_tokens_seen": 80558784,
|
|
"step": 70450,
|
|
"train_runtime": 118935.3641,
|
|
"train_tokens_per_second": 677.332
|
|
},
|
|
{
|
|
"epoch": 0.06798457087753135,
|
|
"grad_norm": 25.669862747192383,
|
|
"learning_rate": 0.00019775985023950222,
|
|
"loss": 1.2456059265136719,
|
|
"num_input_tokens_seen": 80596776,
|
|
"step": 70500,
|
|
"train_runtime": 118998.5274,
|
|
"train_tokens_per_second": 677.292
|
|
},
|
|
{
|
|
"epoch": 0.0680327868852459,
|
|
"grad_norm": 64.81826782226562,
|
|
"learning_rate": 0.00019775665935578234,
|
|
"loss": 1.2321994018554687,
|
|
"num_input_tokens_seen": 80634472,
|
|
"step": 70550,
|
|
"train_runtime": 119060.6769,
|
|
"train_tokens_per_second": 677.255
|
|
},
|
|
{
|
|
"epoch": 0.06808100289296046,
|
|
"grad_norm": 7.578046798706055,
|
|
"learning_rate": 0.00019775346622690143,
|
|
"loss": 1.158494873046875,
|
|
"num_input_tokens_seen": 80671832,
|
|
"step": 70600,
|
|
"train_runtime": 119123.1253,
|
|
"train_tokens_per_second": 677.214
|
|
},
|
|
{
|
|
"epoch": 0.06812921890067503,
|
|
"grad_norm": 6.637514114379883,
|
|
"learning_rate": 0.00019775027085293286,
|
|
"loss": 1.2095219421386718,
|
|
"num_input_tokens_seen": 80708864,
|
|
"step": 70650,
|
|
"train_runtime": 119185.6269,
|
|
"train_tokens_per_second": 677.169
|
|
},
|
|
{
|
|
"epoch": 0.06817743490838958,
|
|
"grad_norm": 6.878465175628662,
|
|
"learning_rate": 0.00019774707323395,
|
|
"loss": 1.2281015014648438,
|
|
"num_input_tokens_seen": 80746984,
|
|
"step": 70700,
|
|
"train_runtime": 119248.1834,
|
|
"train_tokens_per_second": 677.134
|
|
},
|
|
{
|
|
"epoch": 0.06822565091610415,
|
|
"grad_norm": 15.62590503692627,
|
|
"learning_rate": 0.00019774387337002632,
|
|
"loss": 1.2569241333007812,
|
|
"num_input_tokens_seen": 80784376,
|
|
"step": 70750,
|
|
"train_runtime": 119310.8492,
|
|
"train_tokens_per_second": 677.092
|
|
},
|
|
{
|
|
"epoch": 0.0682738669238187,
|
|
"grad_norm": 47.551090240478516,
|
|
"learning_rate": 0.00019774067126123522,
|
|
"loss": 1.320075225830078,
|
|
"num_input_tokens_seen": 80821168,
|
|
"step": 70800,
|
|
"train_runtime": 119373.4503,
|
|
"train_tokens_per_second": 677.045
|
|
},
|
|
{
|
|
"epoch": 0.06832208293153327,
|
|
"grad_norm": 8.301772117614746,
|
|
"learning_rate": 0.00019773746690765034,
|
|
"loss": 1.2105585479736327,
|
|
"num_input_tokens_seen": 80857872,
|
|
"step": 70850,
|
|
"train_runtime": 119435.6784,
|
|
"train_tokens_per_second": 676.999
|
|
},
|
|
{
|
|
"epoch": 0.06837029893924783,
|
|
"grad_norm": 8.905570030212402,
|
|
"learning_rate": 0.00019773426030934523,
|
|
"loss": 1.2452957153320312,
|
|
"num_input_tokens_seen": 80895376,
|
|
"step": 70900,
|
|
"train_runtime": 119498.3219,
|
|
"train_tokens_per_second": 676.958
|
|
},
|
|
{
|
|
"epoch": 0.0684185149469624,
|
|
"grad_norm": 11.986289978027344,
|
|
"learning_rate": 0.00019773105146639355,
|
|
"loss": 1.235177001953125,
|
|
"num_input_tokens_seen": 80933104,
|
|
"step": 70950,
|
|
"train_runtime": 119561.1014,
|
|
"train_tokens_per_second": 676.918
|
|
},
|
|
{
|
|
"epoch": 0.06846673095467695,
|
|
"grad_norm": 10.296021461486816,
|
|
"learning_rate": 0.00019772784037886898,
|
|
"loss": 1.1977436828613282,
|
|
"num_input_tokens_seen": 80970568,
|
|
"step": 71000,
|
|
"train_runtime": 119623.9963,
|
|
"train_tokens_per_second": 676.876
|
|
},
|
|
{
|
|
"epoch": 0.06851494696239152,
|
|
"grad_norm": 15.743196487426758,
|
|
"learning_rate": 0.00019772462704684528,
|
|
"loss": 1.2852426147460938,
|
|
"num_input_tokens_seen": 81007944,
|
|
"step": 71050,
|
|
"train_runtime": 119686.8623,
|
|
"train_tokens_per_second": 676.832
|
|
},
|
|
{
|
|
"epoch": 0.06856316297010608,
|
|
"grad_norm": 18.010995864868164,
|
|
"learning_rate": 0.00019772141147039623,
|
|
"loss": 1.2461318206787109,
|
|
"num_input_tokens_seen": 81044560,
|
|
"step": 71100,
|
|
"train_runtime": 119749.4316,
|
|
"train_tokens_per_second": 676.785
|
|
},
|
|
{
|
|
"epoch": 0.06861137897782063,
|
|
"grad_norm": 6.691593170166016,
|
|
"learning_rate": 0.0001977181936495957,
|
|
"loss": 1.2031483459472656,
|
|
"num_input_tokens_seen": 81081312,
|
|
"step": 71150,
|
|
"train_runtime": 119811.9054,
|
|
"train_tokens_per_second": 676.738
|
|
},
|
|
{
|
|
"epoch": 0.0686595949855352,
|
|
"grad_norm": 7.792195796966553,
|
|
"learning_rate": 0.0001977149735845176,
|
|
"loss": 1.152122802734375,
|
|
"num_input_tokens_seen": 81118368,
|
|
"step": 71200,
|
|
"train_runtime": 119874.1671,
|
|
"train_tokens_per_second": 676.696
|
|
},
|
|
{
|
|
"epoch": 0.06870781099324975,
|
|
"grad_norm": 7.672152042388916,
|
|
"learning_rate": 0.00019771175127523586,
|
|
"loss": 1.2201973724365234,
|
|
"num_input_tokens_seen": 81155640,
|
|
"step": 71250,
|
|
"train_runtime": 119937.2044,
|
|
"train_tokens_per_second": 676.651
|
|
},
|
|
{
|
|
"epoch": 0.06875602700096432,
|
|
"grad_norm": 25.719514846801758,
|
|
"learning_rate": 0.00019770852672182452,
|
|
"loss": 1.2494983673095703,
|
|
"num_input_tokens_seen": 81192888,
|
|
"step": 71300,
|
|
"train_runtime": 119999.6582,
|
|
"train_tokens_per_second": 676.609
|
|
},
|
|
{
|
|
"epoch": 0.06880424300867888,
|
|
"grad_norm": 8.110085487365723,
|
|
"learning_rate": 0.00019770529992435763,
|
|
"loss": 1.2758522033691406,
|
|
"num_input_tokens_seen": 81229696,
|
|
"step": 71350,
|
|
"train_runtime": 120062.1011,
|
|
"train_tokens_per_second": 676.564
|
|
},
|
|
{
|
|
"epoch": 0.06885245901639345,
|
|
"grad_norm": 9.123574256896973,
|
|
"learning_rate": 0.00019770207088290928,
|
|
"loss": 1.1774546813964843,
|
|
"num_input_tokens_seen": 81266744,
|
|
"step": 71400,
|
|
"train_runtime": 120124.3703,
|
|
"train_tokens_per_second": 676.522
|
|
},
|
|
{
|
|
"epoch": 0.068900675024108,
|
|
"grad_norm": 9.092437744140625,
|
|
"learning_rate": 0.00019769883959755365,
|
|
"loss": 1.210035400390625,
|
|
"num_input_tokens_seen": 81304656,
|
|
"step": 71450,
|
|
"train_runtime": 120186.5307,
|
|
"train_tokens_per_second": 676.487
|
|
},
|
|
{
|
|
"epoch": 0.06894889103182257,
|
|
"grad_norm": 9.309332847595215,
|
|
"learning_rate": 0.0001976956060683649,
|
|
"loss": 1.223759765625,
|
|
"num_input_tokens_seen": 81341040,
|
|
"step": 71500,
|
|
"train_runtime": 120249.0367,
|
|
"train_tokens_per_second": 676.438
|
|
},
|
|
{
|
|
"epoch": 0.06899710703953713,
|
|
"grad_norm": 13.059093475341797,
|
|
"learning_rate": 0.0001976923702954174,
|
|
"loss": 1.2228529357910156,
|
|
"num_input_tokens_seen": 81379408,
|
|
"step": 71550,
|
|
"train_runtime": 120312.7456,
|
|
"train_tokens_per_second": 676.399
|
|
},
|
|
{
|
|
"epoch": 0.0690453230472517,
|
|
"grad_norm": 12.439266204833984,
|
|
"learning_rate": 0.00019768913227878536,
|
|
"loss": 1.2227188873291015,
|
|
"num_input_tokens_seen": 81417056,
|
|
"step": 71600,
|
|
"train_runtime": 120375.1116,
|
|
"train_tokens_per_second": 676.361
|
|
},
|
|
{
|
|
"epoch": 0.06909353905496625,
|
|
"grad_norm": 8.18659496307373,
|
|
"learning_rate": 0.0001976858920185432,
|
|
"loss": 1.2592413330078125,
|
|
"num_input_tokens_seen": 81454416,
|
|
"step": 71650,
|
|
"train_runtime": 120437.5842,
|
|
"train_tokens_per_second": 676.321
|
|
},
|
|
{
|
|
"epoch": 0.0691417550626808,
|
|
"grad_norm": 9.34676456451416,
|
|
"learning_rate": 0.00019768264951476532,
|
|
"loss": 1.2269029235839843,
|
|
"num_input_tokens_seen": 81491952,
|
|
"step": 71700,
|
|
"train_runtime": 120499.8352,
|
|
"train_tokens_per_second": 676.283
|
|
},
|
|
{
|
|
"epoch": 0.06918997107039537,
|
|
"grad_norm": 6.759321689605713,
|
|
"learning_rate": 0.0001976794047675262,
|
|
"loss": 1.2551199340820312,
|
|
"num_input_tokens_seen": 81529824,
|
|
"step": 71750,
|
|
"train_runtime": 120562.5766,
|
|
"train_tokens_per_second": 676.245
|
|
},
|
|
{
|
|
"epoch": 0.06923818707810993,
|
|
"grad_norm": 8.004858016967773,
|
|
"learning_rate": 0.00019767615777690036,
|
|
"loss": 1.1777852630615235,
|
|
"num_input_tokens_seen": 81566648,
|
|
"step": 71800,
|
|
"train_runtime": 120624.7883,
|
|
"train_tokens_per_second": 676.201
|
|
},
|
|
{
|
|
"epoch": 0.0692864030858245,
|
|
"grad_norm": 6.399603366851807,
|
|
"learning_rate": 0.00019767290854296235,
|
|
"loss": 1.2570533752441406,
|
|
"num_input_tokens_seen": 81603408,
|
|
"step": 71850,
|
|
"train_runtime": 120687.1081,
|
|
"train_tokens_per_second": 676.157
|
|
},
|
|
{
|
|
"epoch": 0.06933461909353905,
|
|
"grad_norm": 19.965007781982422,
|
|
"learning_rate": 0.00019766965706578685,
|
|
"loss": 1.1923794555664062,
|
|
"num_input_tokens_seen": 81640552,
|
|
"step": 71900,
|
|
"train_runtime": 120749.346,
|
|
"train_tokens_per_second": 676.116
|
|
},
|
|
{
|
|
"epoch": 0.06938283510125362,
|
|
"grad_norm": 9.138592720031738,
|
|
"learning_rate": 0.0001976664033454485,
|
|
"loss": 1.2353075408935548,
|
|
"num_input_tokens_seen": 81677432,
|
|
"step": 71950,
|
|
"train_runtime": 120811.7205,
|
|
"train_tokens_per_second": 676.072
|
|
},
|
|
{
|
|
"epoch": 0.06943105110896818,
|
|
"grad_norm": 9.91710376739502,
|
|
"learning_rate": 0.00019766314738202203,
|
|
"loss": 1.194725570678711,
|
|
"num_input_tokens_seen": 81715312,
|
|
"step": 72000,
|
|
"train_runtime": 120874.5182,
|
|
"train_tokens_per_second": 676.034
|
|
},
|
|
{
|
|
"epoch": 0.06947926711668274,
|
|
"grad_norm": 23.88457489013672,
|
|
"learning_rate": 0.00019765988917558222,
|
|
"loss": 1.2582249450683594,
|
|
"num_input_tokens_seen": 81752016,
|
|
"step": 72050,
|
|
"train_runtime": 120937.2573,
|
|
"train_tokens_per_second": 675.987
|
|
},
|
|
{
|
|
"epoch": 0.0695274831243973,
|
|
"grad_norm": 17.143028259277344,
|
|
"learning_rate": 0.0001976566287262039,
|
|
"loss": 1.2882765197753907,
|
|
"num_input_tokens_seen": 81790120,
|
|
"step": 72100,
|
|
"train_runtime": 120999.9332,
|
|
"train_tokens_per_second": 675.952
|
|
},
|
|
{
|
|
"epoch": 0.06957569913211187,
|
|
"grad_norm": 17.859071731567383,
|
|
"learning_rate": 0.00019765336603396193,
|
|
"loss": 1.273697509765625,
|
|
"num_input_tokens_seen": 81828048,
|
|
"step": 72150,
|
|
"train_runtime": 121062.4405,
|
|
"train_tokens_per_second": 675.916
|
|
},
|
|
{
|
|
"epoch": 0.06962391513982642,
|
|
"grad_norm": 15.899073600769043,
|
|
"learning_rate": 0.0001976501010989313,
|
|
"loss": 1.2410599517822265,
|
|
"num_input_tokens_seen": 81865496,
|
|
"step": 72200,
|
|
"train_runtime": 121125.2435,
|
|
"train_tokens_per_second": 675.875
|
|
},
|
|
{
|
|
"epoch": 0.06967213114754098,
|
|
"grad_norm": 21.599239349365234,
|
|
"learning_rate": 0.00019764683392118696,
|
|
"loss": 1.3242405700683593,
|
|
"num_input_tokens_seen": 81902328,
|
|
"step": 72250,
|
|
"train_runtime": 121187.9819,
|
|
"train_tokens_per_second": 675.829
|
|
},
|
|
{
|
|
"epoch": 0.06972034715525555,
|
|
"grad_norm": 12.7147855758667,
|
|
"learning_rate": 0.00019764356450080393,
|
|
"loss": 1.2577008819580078,
|
|
"num_input_tokens_seen": 81939256,
|
|
"step": 72300,
|
|
"train_runtime": 121250.3648,
|
|
"train_tokens_per_second": 675.786
|
|
},
|
|
{
|
|
"epoch": 0.0697685631629701,
|
|
"grad_norm": 8.766327857971191,
|
|
"learning_rate": 0.0001976402928378573,
|
|
"loss": 1.2588436889648438,
|
|
"num_input_tokens_seen": 81976880,
|
|
"step": 72350,
|
|
"train_runtime": 121313.178,
|
|
"train_tokens_per_second": 675.746
|
|
},
|
|
{
|
|
"epoch": 0.06981677917068467,
|
|
"grad_norm": 9.920838356018066,
|
|
"learning_rate": 0.00019763701893242224,
|
|
"loss": 1.2927862548828124,
|
|
"num_input_tokens_seen": 82014296,
|
|
"step": 72400,
|
|
"train_runtime": 121375.4907,
|
|
"train_tokens_per_second": 675.707
|
|
},
|
|
{
|
|
"epoch": 0.06986499517839923,
|
|
"grad_norm": 15.398935317993164,
|
|
"learning_rate": 0.00019763374278457393,
|
|
"loss": 1.2320116424560548,
|
|
"num_input_tokens_seen": 82051040,
|
|
"step": 72450,
|
|
"train_runtime": 121437.2412,
|
|
"train_tokens_per_second": 675.666
|
|
},
|
|
{
|
|
"epoch": 0.0699132111861138,
|
|
"grad_norm": 10.077899932861328,
|
|
"learning_rate": 0.00019763046439438763,
|
|
"loss": 1.2794468688964844,
|
|
"num_input_tokens_seen": 82089088,
|
|
"step": 72500,
|
|
"train_runtime": 121500.0788,
|
|
"train_tokens_per_second": 675.63
|
|
},
|
|
{
|
|
"epoch": 0.06996142719382835,
|
|
"grad_norm": 31.10654067993164,
|
|
"learning_rate": 0.0001976271837619386,
|
|
"loss": 1.254157180786133,
|
|
"num_input_tokens_seen": 82126296,
|
|
"step": 72550,
|
|
"train_runtime": 121562.4923,
|
|
"train_tokens_per_second": 675.589
|
|
},
|
|
{
|
|
"epoch": 0.07000964320154292,
|
|
"grad_norm": 9.439265251159668,
|
|
"learning_rate": 0.0001976239008873022,
|
|
"loss": 1.328443603515625,
|
|
"num_input_tokens_seen": 82162912,
|
|
"step": 72600,
|
|
"train_runtime": 121625.061,
|
|
"train_tokens_per_second": 675.543
|
|
},
|
|
{
|
|
"epoch": 0.07005785920925747,
|
|
"grad_norm": 7.740597724914551,
|
|
"learning_rate": 0.00019762061577055385,
|
|
"loss": 1.205087890625,
|
|
"num_input_tokens_seen": 82200184,
|
|
"step": 72650,
|
|
"train_runtime": 121687.274,
|
|
"train_tokens_per_second": 675.504
|
|
},
|
|
{
|
|
"epoch": 0.07010607521697204,
|
|
"grad_norm": 10.447400093078613,
|
|
"learning_rate": 0.00019761732841176895,
|
|
"loss": 1.2537755584716797,
|
|
"num_input_tokens_seen": 82238424,
|
|
"step": 72700,
|
|
"train_runtime": 121749.4966,
|
|
"train_tokens_per_second": 675.472
|
|
},
|
|
{
|
|
"epoch": 0.0701542912246866,
|
|
"grad_norm": 10.765146255493164,
|
|
"learning_rate": 0.00019761403881102304,
|
|
"loss": 1.2499148559570312,
|
|
"num_input_tokens_seen": 82275840,
|
|
"step": 72750,
|
|
"train_runtime": 121812.8988,
|
|
"train_tokens_per_second": 675.428
|
|
},
|
|
{
|
|
"epoch": 0.07020250723240115,
|
|
"grad_norm": 12.29460620880127,
|
|
"learning_rate": 0.00019761074696839163,
|
|
"loss": 1.196775894165039,
|
|
"num_input_tokens_seen": 82313336,
|
|
"step": 72800,
|
|
"train_runtime": 121875.2825,
|
|
"train_tokens_per_second": 675.39
|
|
},
|
|
{
|
|
"epoch": 0.07025072324011572,
|
|
"grad_norm": 8.967686653137207,
|
|
"learning_rate": 0.0001976074528839504,
|
|
"loss": 1.2998699951171875,
|
|
"num_input_tokens_seen": 82350848,
|
|
"step": 72850,
|
|
"train_runtime": 121937.8086,
|
|
"train_tokens_per_second": 675.351
|
|
},
|
|
{
|
|
"epoch": 0.07029893924783027,
|
|
"grad_norm": 10.835304260253906,
|
|
"learning_rate": 0.00019760415655777492,
|
|
"loss": 1.2356822967529297,
|
|
"num_input_tokens_seen": 82387808,
|
|
"step": 72900,
|
|
"train_runtime": 121999.9777,
|
|
"train_tokens_per_second": 675.31
|
|
},
|
|
{
|
|
"epoch": 0.07034715525554484,
|
|
"grad_norm": 10.73427963256836,
|
|
"learning_rate": 0.00019760085798994093,
|
|
"loss": 1.2440271759033203,
|
|
"num_input_tokens_seen": 82425968,
|
|
"step": 72950,
|
|
"train_runtime": 122062.5671,
|
|
"train_tokens_per_second": 675.276
|
|
},
|
|
{
|
|
"epoch": 0.0703953712632594,
|
|
"grad_norm": 11.432723999023438,
|
|
"learning_rate": 0.0001975975571805242,
|
|
"loss": 1.236361541748047,
|
|
"num_input_tokens_seen": 82463472,
|
|
"step": 73000,
|
|
"train_runtime": 122125.6939,
|
|
"train_tokens_per_second": 675.234
|
|
},
|
|
{
|
|
"epoch": 0.07044358727097397,
|
|
"grad_norm": 17.1837100982666,
|
|
"learning_rate": 0.00019759425412960052,
|
|
"loss": 1.21800537109375,
|
|
"num_input_tokens_seen": 82500800,
|
|
"step": 73050,
|
|
"train_runtime": 122188.2926,
|
|
"train_tokens_per_second": 675.194
|
|
},
|
|
{
|
|
"epoch": 0.07049180327868852,
|
|
"grad_norm": 10.079767227172852,
|
|
"learning_rate": 0.0001975909488372458,
|
|
"loss": 1.25732421875,
|
|
"num_input_tokens_seen": 82538472,
|
|
"step": 73100,
|
|
"train_runtime": 122250.6354,
|
|
"train_tokens_per_second": 675.158
|
|
},
|
|
{
|
|
"epoch": 0.07054001928640309,
|
|
"grad_norm": 11.475564956665039,
|
|
"learning_rate": 0.00019758764130353587,
|
|
"loss": 1.226166763305664,
|
|
"num_input_tokens_seen": 82576304,
|
|
"step": 73150,
|
|
"train_runtime": 122313.1129,
|
|
"train_tokens_per_second": 675.122
|
|
},
|
|
{
|
|
"epoch": 0.07058823529411765,
|
|
"grad_norm": 10.92429256439209,
|
|
"learning_rate": 0.00019758433152854675,
|
|
"loss": 1.1871161651611328,
|
|
"num_input_tokens_seen": 82614296,
|
|
"step": 73200,
|
|
"train_runtime": 122375.5592,
|
|
"train_tokens_per_second": 675.088
|
|
},
|
|
{
|
|
"epoch": 0.07063645130183221,
|
|
"grad_norm": 25.88380241394043,
|
|
"learning_rate": 0.0001975812182965265,
|
|
"loss": 1.5307632446289063,
|
|
"num_input_tokens_seen": 82651152,
|
|
"step": 73250,
|
|
"train_runtime": 122438.4854,
|
|
"train_tokens_per_second": 675.042
|
|
},
|
|
{
|
|
"epoch": 0.07068466730954677,
|
|
"grad_norm": 8.810757637023926,
|
|
"learning_rate": 0.00019757790417367253,
|
|
"loss": 1.2980715942382812,
|
|
"num_input_tokens_seen": 82688528,
|
|
"step": 73300,
|
|
"train_runtime": 122501.2812,
|
|
"train_tokens_per_second": 675.001
|
|
},
|
|
{
|
|
"epoch": 0.07073288331726132,
|
|
"grad_norm": 12.250165939331055,
|
|
"learning_rate": 0.00019757458780976302,
|
|
"loss": 1.2362574005126954,
|
|
"num_input_tokens_seen": 82725152,
|
|
"step": 73350,
|
|
"train_runtime": 122563.8812,
|
|
"train_tokens_per_second": 674.955
|
|
},
|
|
{
|
|
"epoch": 0.0707810993249759,
|
|
"grad_norm": 28.642112731933594,
|
|
"learning_rate": 0.0001975712692048741,
|
|
"loss": 1.2553501892089844,
|
|
"num_input_tokens_seen": 82763304,
|
|
"step": 73400,
|
|
"train_runtime": 122627.2944,
|
|
"train_tokens_per_second": 674.917
|
|
},
|
|
{
|
|
"epoch": 0.07082931533269045,
|
|
"grad_norm": 16.64663314819336,
|
|
"learning_rate": 0.00019756794835908197,
|
|
"loss": 1.3115293884277344,
|
|
"num_input_tokens_seen": 82801336,
|
|
"step": 73450,
|
|
"train_runtime": 122690.1504,
|
|
"train_tokens_per_second": 674.882
|
|
},
|
|
{
|
|
"epoch": 0.07087753134040502,
|
|
"grad_norm": 61.987876892089844,
|
|
"learning_rate": 0.0001975646252724629,
|
|
"loss": 1.3342648315429688,
|
|
"num_input_tokens_seen": 82838616,
|
|
"step": 73500,
|
|
"train_runtime": 122753.2516,
|
|
"train_tokens_per_second": 674.838
|
|
},
|
|
{
|
|
"epoch": 0.07092574734811957,
|
|
"grad_norm": 21.357383728027344,
|
|
"learning_rate": 0.00019756129994509327,
|
|
"loss": 1.3290684509277344,
|
|
"num_input_tokens_seen": 82875856,
|
|
"step": 73550,
|
|
"train_runtime": 122815.9381,
|
|
"train_tokens_per_second": 674.797
|
|
},
|
|
{
|
|
"epoch": 0.07097396335583414,
|
|
"grad_norm": 16.33174705505371,
|
|
"learning_rate": 0.0001975579723770494,
|
|
"loss": 1.3397740173339843,
|
|
"num_input_tokens_seen": 82914536,
|
|
"step": 73600,
|
|
"train_runtime": 122879.1248,
|
|
"train_tokens_per_second": 674.765
|
|
},
|
|
{
|
|
"epoch": 0.0710221793635487,
|
|
"grad_norm": 48.806114196777344,
|
|
"learning_rate": 0.00019755464256840776,
|
|
"loss": 1.3096804809570313,
|
|
"num_input_tokens_seen": 82951744,
|
|
"step": 73650,
|
|
"train_runtime": 122941.5291,
|
|
"train_tokens_per_second": 674.725
|
|
},
|
|
{
|
|
"epoch": 0.07107039537126326,
|
|
"grad_norm": 10.396586418151855,
|
|
"learning_rate": 0.00019755131051924472,
|
|
"loss": 1.3095591735839844,
|
|
"num_input_tokens_seen": 82988744,
|
|
"step": 73700,
|
|
"train_runtime": 123003.9433,
|
|
"train_tokens_per_second": 674.684
|
|
},
|
|
{
|
|
"epoch": 0.07111861137897782,
|
|
"grad_norm": 32.90802764892578,
|
|
"learning_rate": 0.00019754797622963693,
|
|
"loss": 1.3216778564453124,
|
|
"num_input_tokens_seen": 83026384,
|
|
"step": 73750,
|
|
"train_runtime": 123066.7558,
|
|
"train_tokens_per_second": 674.645
|
|
},
|
|
{
|
|
"epoch": 0.07116682738669239,
|
|
"grad_norm": 14.293683052062988,
|
|
"learning_rate": 0.00019754463969966094,
|
|
"loss": 1.3741368103027343,
|
|
"num_input_tokens_seen": 83063448,
|
|
"step": 73800,
|
|
"train_runtime": 123128.9345,
|
|
"train_tokens_per_second": 674.605
|
|
},
|
|
{
|
|
"epoch": 0.07121504339440694,
|
|
"grad_norm": 56.6582145690918,
|
|
"learning_rate": 0.0001975413009293933,
|
|
"loss": 1.428879852294922,
|
|
"num_input_tokens_seen": 83100896,
|
|
"step": 73850,
|
|
"train_runtime": 123191.4165,
|
|
"train_tokens_per_second": 674.567
|
|
},
|
|
{
|
|
"epoch": 0.0712632594021215,
|
|
"grad_norm": 11.056356430053711,
|
|
"learning_rate": 0.00019753795991891076,
|
|
"loss": 1.5114505004882812,
|
|
"num_input_tokens_seen": 83138664,
|
|
"step": 73900,
|
|
"train_runtime": 123253.5486,
|
|
"train_tokens_per_second": 674.534
|
|
},
|
|
{
|
|
"epoch": 0.07131147540983607,
|
|
"grad_norm": 172.64710998535156,
|
|
"learning_rate": 0.00019753461666829005,
|
|
"loss": 1.6648048400878905,
|
|
"num_input_tokens_seen": 83175880,
|
|
"step": 73950,
|
|
"train_runtime": 123315.8108,
|
|
"train_tokens_per_second": 674.495
|
|
},
|
|
{
|
|
"epoch": 0.07135969141755062,
|
|
"grad_norm": 98.35665130615234,
|
|
"learning_rate": 0.00019753127117760793,
|
|
"loss": 1.5318714904785156,
|
|
"num_input_tokens_seen": 83213512,
|
|
"step": 74000,
|
|
"train_runtime": 123378.3554,
|
|
"train_tokens_per_second": 674.458
|
|
},
|
|
{
|
|
"epoch": 0.07140790742526519,
|
|
"grad_norm": 13.323641777038574,
|
|
"learning_rate": 0.00019752792344694128,
|
|
"loss": 1.42196044921875,
|
|
"num_input_tokens_seen": 83251088,
|
|
"step": 74050,
|
|
"train_runtime": 123440.8679,
|
|
"train_tokens_per_second": 674.421
|
|
},
|
|
{
|
|
"epoch": 0.07145612343297975,
|
|
"grad_norm": 14.795919418334961,
|
|
"learning_rate": 0.00019752457347636693,
|
|
"loss": 1.3816334533691406,
|
|
"num_input_tokens_seen": 83289344,
|
|
"step": 74100,
|
|
"train_runtime": 123503.1468,
|
|
"train_tokens_per_second": 674.39
|
|
},
|
|
{
|
|
"epoch": 0.07150433944069431,
|
|
"grad_norm": 14.475448608398438,
|
|
"learning_rate": 0.00019752122126596183,
|
|
"loss": 1.4042384338378906,
|
|
"num_input_tokens_seen": 83325864,
|
|
"step": 74150,
|
|
"train_runtime": 123565.2001,
|
|
"train_tokens_per_second": 674.347
|
|
},
|
|
{
|
|
"epoch": 0.07155255544840887,
|
|
"grad_norm": 24.233612060546875,
|
|
"learning_rate": 0.00019751786681580303,
|
|
"loss": 1.3952008056640626,
|
|
"num_input_tokens_seen": 83362776,
|
|
"step": 74200,
|
|
"train_runtime": 123627.4446,
|
|
"train_tokens_per_second": 674.306
|
|
},
|
|
{
|
|
"epoch": 0.07160077145612344,
|
|
"grad_norm": 21.792070388793945,
|
|
"learning_rate": 0.0001975145101259675,
|
|
"loss": 1.456934051513672,
|
|
"num_input_tokens_seen": 83400376,
|
|
"step": 74250,
|
|
"train_runtime": 123689.8421,
|
|
"train_tokens_per_second": 674.27
|
|
},
|
|
{
|
|
"epoch": 0.071648987463838,
|
|
"grad_norm": 227.74729919433594,
|
|
"learning_rate": 0.00019751115119653233,
|
|
"loss": 1.394981689453125,
|
|
"num_input_tokens_seen": 83438032,
|
|
"step": 74300,
|
|
"train_runtime": 123752.5059,
|
|
"train_tokens_per_second": 674.233
|
|
},
|
|
{
|
|
"epoch": 0.07169720347155256,
|
|
"grad_norm": 15.874136924743652,
|
|
"learning_rate": 0.00019750779002757472,
|
|
"loss": 1.628187255859375,
|
|
"num_input_tokens_seen": 83475680,
|
|
"step": 74350,
|
|
"train_runtime": 123814.9787,
|
|
"train_tokens_per_second": 674.197
|
|
},
|
|
{
|
|
"epoch": 0.07174541947926712,
|
|
"grad_norm": 58.07904052734375,
|
|
"learning_rate": 0.00019750442661917186,
|
|
"loss": 1.5223991394042968,
|
|
"num_input_tokens_seen": 83512976,
|
|
"step": 74400,
|
|
"train_runtime": 123877.109,
|
|
"train_tokens_per_second": 674.16
|
|
},
|
|
{
|
|
"epoch": 0.07179363548698167,
|
|
"grad_norm": 35.22754669189453,
|
|
"learning_rate": 0.00019750106097140093,
|
|
"loss": 1.4954933166503905,
|
|
"num_input_tokens_seen": 83549816,
|
|
"step": 74450,
|
|
"train_runtime": 123939.1395,
|
|
"train_tokens_per_second": 674.12
|
|
},
|
|
{
|
|
"epoch": 0.07184185149469624,
|
|
"grad_norm": 43.81642532348633,
|
|
"learning_rate": 0.0001974976930843393,
|
|
"loss": 1.5496104431152344,
|
|
"num_input_tokens_seen": 83586688,
|
|
"step": 74500,
|
|
"train_runtime": 124001.3139,
|
|
"train_tokens_per_second": 674.079
|
|
},
|
|
{
|
|
"epoch": 0.0718900675024108,
|
|
"grad_norm": 24.077173233032227,
|
|
"learning_rate": 0.00019749432295806428,
|
|
"loss": 1.5813926696777343,
|
|
"num_input_tokens_seen": 83623960,
|
|
"step": 74550,
|
|
"train_runtime": 124063.6091,
|
|
"train_tokens_per_second": 674.041
|
|
},
|
|
{
|
|
"epoch": 0.07193828351012536,
|
|
"grad_norm": 12.083993911743164,
|
|
"learning_rate": 0.00019749095059265327,
|
|
"loss": 1.696486358642578,
|
|
"num_input_tokens_seen": 83662200,
|
|
"step": 74600,
|
|
"train_runtime": 124125.7053,
|
|
"train_tokens_per_second": 674.012
|
|
},
|
|
{
|
|
"epoch": 0.07198649951783992,
|
|
"grad_norm": 8.987173080444336,
|
|
"learning_rate": 0.00019748757598818376,
|
|
"loss": 1.4695242309570313,
|
|
"num_input_tokens_seen": 83700576,
|
|
"step": 74650,
|
|
"train_runtime": 124188.9253,
|
|
"train_tokens_per_second": 673.978
|
|
},
|
|
{
|
|
"epoch": 0.07203471552555449,
|
|
"grad_norm": 17.779211044311523,
|
|
"learning_rate": 0.0001974841991447332,
|
|
"loss": 1.3980747985839843,
|
|
"num_input_tokens_seen": 83738288,
|
|
"step": 74700,
|
|
"train_runtime": 124250.9676,
|
|
"train_tokens_per_second": 673.945
|
|
},
|
|
{
|
|
"epoch": 0.07208293153326904,
|
|
"grad_norm": 199.0033721923828,
|
|
"learning_rate": 0.00019748082006237918,
|
|
"loss": 1.4835536193847656,
|
|
"num_input_tokens_seen": 83776616,
|
|
"step": 74750,
|
|
"train_runtime": 124314.462,
|
|
"train_tokens_per_second": 673.909
|
|
},
|
|
{
|
|
"epoch": 0.07213114754098361,
|
|
"grad_norm": 36.91281509399414,
|
|
"learning_rate": 0.00019747743874119932,
|
|
"loss": 1.4442367553710938,
|
|
"num_input_tokens_seen": 83814896,
|
|
"step": 74800,
|
|
"train_runtime": 124377.2678,
|
|
"train_tokens_per_second": 673.876
|
|
},
|
|
{
|
|
"epoch": 0.07217936354869817,
|
|
"grad_norm": 25.196352005004883,
|
|
"learning_rate": 0.00019747405518127126,
|
|
"loss": 1.4595712280273438,
|
|
"num_input_tokens_seen": 83853000,
|
|
"step": 74850,
|
|
"train_runtime": 124439.9171,
|
|
"train_tokens_per_second": 673.843
|
|
},
|
|
{
|
|
"epoch": 0.07222757955641274,
|
|
"grad_norm": 39.640045166015625,
|
|
"learning_rate": 0.00019747066938267268,
|
|
"loss": 2.064040069580078,
|
|
"num_input_tokens_seen": 83891088,
|
|
"step": 74900,
|
|
"train_runtime": 124502.5158,
|
|
"train_tokens_per_second": 673.81
|
|
},
|
|
{
|
|
"epoch": 0.07227579556412729,
|
|
"grad_norm": 177.67355346679688,
|
|
"learning_rate": 0.00019746728134548142,
|
|
"loss": 1.6247065734863282,
|
|
"num_input_tokens_seen": 83929504,
|
|
"step": 74950,
|
|
"train_runtime": 124564.5186,
|
|
"train_tokens_per_second": 673.783
|
|
},
|
|
{
|
|
"epoch": 0.07232401157184185,
|
|
"grad_norm": 68.51436614990234,
|
|
"learning_rate": 0.0001974638910697752,
|
|
"loss": 1.7684764099121093,
|
|
"num_input_tokens_seen": 83968144,
|
|
"step": 75000,
|
|
"train_runtime": 124627.3263,
|
|
"train_tokens_per_second": 673.754
|
|
},
|
|
{
|
|
"epoch": 0.07237222757955641,
|
|
"grad_norm": 594.3804931640625,
|
|
"learning_rate": 0.00019746049855563194,
|
|
"loss": 2.0924945068359375,
|
|
"num_input_tokens_seen": 84006024,
|
|
"step": 75050,
|
|
"train_runtime": 124689.4508,
|
|
"train_tokens_per_second": 673.722
|
|
},
|
|
{
|
|
"epoch": 0.07242044358727097,
|
|
"grad_norm": 61.51227951049805,
|
|
"learning_rate": 0.000197457171720115,
|
|
"loss": 3.289195251464844,
|
|
"num_input_tokens_seen": 84043568,
|
|
"step": 75100,
|
|
"train_runtime": 124751.1331,
|
|
"train_tokens_per_second": 673.69
|
|
},
|
|
{
|
|
"epoch": 0.07246865959498554,
|
|
"grad_norm": 42.352943420410156,
|
|
"learning_rate": 0.00019745377477409627,
|
|
"loss": 1.635799102783203,
|
|
"num_input_tokens_seen": 84082080,
|
|
"step": 75150,
|
|
"train_runtime": 124814.1966,
|
|
"train_tokens_per_second": 673.658
|
|
},
|
|
{
|
|
"epoch": 0.07251687560270009,
|
|
"grad_norm": 23.551015853881836,
|
|
"learning_rate": 0.00019745037558987284,
|
|
"loss": 1.632807159423828,
|
|
"num_input_tokens_seen": 84119552,
|
|
"step": 75200,
|
|
"train_runtime": 124876.9701,
|
|
"train_tokens_per_second": 673.619
|
|
},
|
|
{
|
|
"epoch": 0.07256509161041466,
|
|
"grad_norm": 19.247129440307617,
|
|
"learning_rate": 0.0001974469741675228,
|
|
"loss": 1.65517333984375,
|
|
"num_input_tokens_seen": 84157512,
|
|
"step": 75250,
|
|
"train_runtime": 124939.6278,
|
|
"train_tokens_per_second": 673.585
|
|
},
|
|
{
|
|
"epoch": 0.07261330761812922,
|
|
"grad_norm": 17.27000617980957,
|
|
"learning_rate": 0.00019744357050712418,
|
|
"loss": 1.569679718017578,
|
|
"num_input_tokens_seen": 84195592,
|
|
"step": 75300,
|
|
"train_runtime": 125002.0428,
|
|
"train_tokens_per_second": 673.554
|
|
},
|
|
{
|
|
"epoch": 0.07266152362584379,
|
|
"grad_norm": 19.21133041381836,
|
|
"learning_rate": 0.00019744016460875524,
|
|
"loss": 1.6932432556152344,
|
|
"num_input_tokens_seen": 84233400,
|
|
"step": 75350,
|
|
"train_runtime": 125064.3173,
|
|
"train_tokens_per_second": 673.521
|
|
},
|
|
{
|
|
"epoch": 0.07270973963355834,
|
|
"grad_norm": 12.738866806030273,
|
|
"learning_rate": 0.00019743675647249415,
|
|
"loss": 1.4865664672851562,
|
|
"num_input_tokens_seen": 84271760,
|
|
"step": 75400,
|
|
"train_runtime": 125126.8182,
|
|
"train_tokens_per_second": 673.491
|
|
},
|
|
{
|
|
"epoch": 0.07275795564127291,
|
|
"grad_norm": 29.59440040588379,
|
|
"learning_rate": 0.00019743334609841922,
|
|
"loss": 1.548780975341797,
|
|
"num_input_tokens_seen": 84309528,
|
|
"step": 75450,
|
|
"train_runtime": 125189.4814,
|
|
"train_tokens_per_second": 673.455
|
|
},
|
|
{
|
|
"epoch": 0.07280617164898746,
|
|
"grad_norm": 23.389877319335938,
|
|
"learning_rate": 0.00019742993348660875,
|
|
"loss": 1.562229461669922,
|
|
"num_input_tokens_seen": 84348416,
|
|
"step": 75500,
|
|
"train_runtime": 125252.4285,
|
|
"train_tokens_per_second": 673.427
|
|
},
|
|
{
|
|
"epoch": 0.07285438765670202,
|
|
"grad_norm": 11.188277244567871,
|
|
"learning_rate": 0.00019742651863714113,
|
|
"loss": 1.5091419982910157,
|
|
"num_input_tokens_seen": 84386096,
|
|
"step": 75550,
|
|
"train_runtime": 125314.8381,
|
|
"train_tokens_per_second": 673.393
|
|
},
|
|
{
|
|
"epoch": 0.07290260366441659,
|
|
"grad_norm": 14.948112487792969,
|
|
"learning_rate": 0.0001974231015500948,
|
|
"loss": 1.495529327392578,
|
|
"num_input_tokens_seen": 84423512,
|
|
"step": 75600,
|
|
"train_runtime": 125378.2647,
|
|
"train_tokens_per_second": 673.35
|
|
},
|
|
{
|
|
"epoch": 0.07295081967213114,
|
|
"grad_norm": 15.181499481201172,
|
|
"learning_rate": 0.00019741968222554816,
|
|
"loss": 1.4849234008789063,
|
|
"num_input_tokens_seen": 84461944,
|
|
"step": 75650,
|
|
"train_runtime": 125441.2622,
|
|
"train_tokens_per_second": 673.319
|
|
},
|
|
{
|
|
"epoch": 0.07299903567984571,
|
|
"grad_norm": 15.800349235534668,
|
|
"learning_rate": 0.00019741626066357984,
|
|
"loss": 1.469507598876953,
|
|
"num_input_tokens_seen": 84500032,
|
|
"step": 75700,
|
|
"train_runtime": 125503.8623,
|
|
"train_tokens_per_second": 673.286
|
|
},
|
|
{
|
|
"epoch": 0.07304725168756027,
|
|
"grad_norm": 11.257926940917969,
|
|
"learning_rate": 0.0001974128368642684,
|
|
"loss": 1.463279266357422,
|
|
"num_input_tokens_seen": 84538072,
|
|
"step": 75750,
|
|
"train_runtime": 125566.8567,
|
|
"train_tokens_per_second": 673.251
|
|
},
|
|
{
|
|
"epoch": 0.07309546769527484,
|
|
"grad_norm": 16.19972038269043,
|
|
"learning_rate": 0.00019740941082769246,
|
|
"loss": 1.542850799560547,
|
|
"num_input_tokens_seen": 84576320,
|
|
"step": 75800,
|
|
"train_runtime": 125629.5939,
|
|
"train_tokens_per_second": 673.22
|
|
},
|
|
{
|
|
"epoch": 0.07314368370298939,
|
|
"grad_norm": 31.094377517700195,
|
|
"learning_rate": 0.00019740598255393068,
|
|
"loss": 1.5031980895996093,
|
|
"num_input_tokens_seen": 84614816,
|
|
"step": 75850,
|
|
"train_runtime": 125692.199,
|
|
"train_tokens_per_second": 673.191
|
|
},
|
|
{
|
|
"epoch": 0.07319189971070396,
|
|
"grad_norm": 19.120643615722656,
|
|
"learning_rate": 0.00019740255204306185,
|
|
"loss": 1.4571827697753905,
|
|
"num_input_tokens_seen": 84652640,
|
|
"step": 75900,
|
|
"train_runtime": 125754.8291,
|
|
"train_tokens_per_second": 673.156
|
|
},
|
|
{
|
|
"epoch": 0.07324011571841851,
|
|
"grad_norm": 12.450984001159668,
|
|
"learning_rate": 0.00019739911929516471,
|
|
"loss": 1.4886299133300782,
|
|
"num_input_tokens_seen": 84690704,
|
|
"step": 75950,
|
|
"train_runtime": 125817.2147,
|
|
"train_tokens_per_second": 673.125
|
|
},
|
|
{
|
|
"epoch": 0.07328833172613308,
|
|
"grad_norm": 49.75008773803711,
|
|
"learning_rate": 0.00019739568431031813,
|
|
"loss": 1.4570799255371094,
|
|
"num_input_tokens_seen": 84728368,
|
|
"step": 76000,
|
|
"train_runtime": 125880.0826,
|
|
"train_tokens_per_second": 673.088
|
|
},
|
|
{
|
|
"epoch": 0.07333654773384764,
|
|
"grad_norm": 7.941289901733398,
|
|
"learning_rate": 0.00019739224708860097,
|
|
"loss": 1.453165283203125,
|
|
"num_input_tokens_seen": 84766040,
|
|
"step": 76050,
|
|
"train_runtime": 125942.6132,
|
|
"train_tokens_per_second": 673.053
|
|
},
|
|
{
|
|
"epoch": 0.07338476374156219,
|
|
"grad_norm": 13.649178504943848,
|
|
"learning_rate": 0.00019738880763009223,
|
|
"loss": 1.423507537841797,
|
|
"num_input_tokens_seen": 84803056,
|
|
"step": 76100,
|
|
"train_runtime": 126005.1087,
|
|
"train_tokens_per_second": 673.013
|
|
},
|
|
{
|
|
"epoch": 0.07343297974927676,
|
|
"grad_norm": 32.557701110839844,
|
|
"learning_rate": 0.00019738536593487082,
|
|
"loss": 1.6479808044433595,
|
|
"num_input_tokens_seen": 84841328,
|
|
"step": 76150,
|
|
"train_runtime": 126068.0593,
|
|
"train_tokens_per_second": 672.98
|
|
},
|
|
{
|
|
"epoch": 0.07348119575699132,
|
|
"grad_norm": 10.554264068603516,
|
|
"learning_rate": 0.00019738192200301587,
|
|
"loss": 1.5743968200683593,
|
|
"num_input_tokens_seen": 84879008,
|
|
"step": 76200,
|
|
"train_runtime": 126130.3123,
|
|
"train_tokens_per_second": 672.947
|
|
},
|
|
{
|
|
"epoch": 0.07352941176470588,
|
|
"grad_norm": 91.37616729736328,
|
|
"learning_rate": 0.0001973784758346064,
|
|
"loss": 1.4892544555664062,
|
|
"num_input_tokens_seen": 84917216,
|
|
"step": 76250,
|
|
"train_runtime": 126193.383,
|
|
"train_tokens_per_second": 672.913
|
|
},
|
|
{
|
|
"epoch": 0.07357762777242044,
|
|
"grad_norm": 67.29042053222656,
|
|
"learning_rate": 0.00019737502742972162,
|
|
"loss": 1.5508273315429688,
|
|
"num_input_tokens_seen": 84955056,
|
|
"step": 76300,
|
|
"train_runtime": 126255.6354,
|
|
"train_tokens_per_second": 672.881
|
|
},
|
|
{
|
|
"epoch": 0.07362584378013501,
|
|
"grad_norm": 25.601125717163086,
|
|
"learning_rate": 0.00019737157678844072,
|
|
"loss": 1.6765501403808594,
|
|
"num_input_tokens_seen": 84992320,
|
|
"step": 76350,
|
|
"train_runtime": 126318.5398,
|
|
"train_tokens_per_second": 672.841
|
|
},
|
|
{
|
|
"epoch": 0.07367405978784956,
|
|
"grad_norm": 1115.2823486328125,
|
|
"learning_rate": 0.0001973681239108429,
|
|
"loss": 1.5675471496582032,
|
|
"num_input_tokens_seen": 85030216,
|
|
"step": 76400,
|
|
"train_runtime": 126381.2473,
|
|
"train_tokens_per_second": 672.807
|
|
},
|
|
{
|
|
"epoch": 0.07372227579556413,
|
|
"grad_norm": 39.09687423706055,
|
|
"learning_rate": 0.0001973646687970075,
|
|
"loss": 2.013770751953125,
|
|
"num_input_tokens_seen": 85068040,
|
|
"step": 76450,
|
|
"train_runtime": 126443.9489,
|
|
"train_tokens_per_second": 672.773
|
|
},
|
|
{
|
|
"epoch": 0.07377049180327869,
|
|
"grad_norm": 35.56536865234375,
|
|
"learning_rate": 0.00019736121144701388,
|
|
"loss": 1.5130360412597657,
|
|
"num_input_tokens_seen": 85106720,
|
|
"step": 76500,
|
|
"train_runtime": 126507.0023,
|
|
"train_tokens_per_second": 672.743
|
|
},
|
|
{
|
|
"epoch": 0.07381870781099326,
|
|
"grad_norm": 20.21633529663086,
|
|
"learning_rate": 0.00019735775186094143,
|
|
"loss": 1.5261842346191405,
|
|
"num_input_tokens_seen": 85144968,
|
|
"step": 76550,
|
|
"train_runtime": 126569.9248,
|
|
"train_tokens_per_second": 672.711
|
|
},
|
|
{
|
|
"epoch": 0.07386692381870781,
|
|
"grad_norm": 30.4970645904541,
|
|
"learning_rate": 0.00019735429003886958,
|
|
"loss": 1.5916075134277343,
|
|
"num_input_tokens_seen": 85182096,
|
|
"step": 76600,
|
|
"train_runtime": 126631.8255,
|
|
"train_tokens_per_second": 672.675
|
|
},
|
|
{
|
|
"epoch": 0.07391513982642237,
|
|
"grad_norm": 41.040897369384766,
|
|
"learning_rate": 0.0001973508259808779,
|
|
"loss": 1.6180413818359376,
|
|
"num_input_tokens_seen": 85220080,
|
|
"step": 76650,
|
|
"train_runtime": 126694.5703,
|
|
"train_tokens_per_second": 672.642
|
|
},
|
|
{
|
|
"epoch": 0.07396335583413693,
|
|
"grad_norm": 39.846736907958984,
|
|
"learning_rate": 0.00019734735968704591,
|
|
"loss": 1.5370405578613282,
|
|
"num_input_tokens_seen": 85258592,
|
|
"step": 76700,
|
|
"train_runtime": 126757.3442,
|
|
"train_tokens_per_second": 672.613
|
|
},
|
|
{
|
|
"epoch": 0.07401157184185149,
|
|
"grad_norm": 16.594717025756836,
|
|
"learning_rate": 0.00019734389115745322,
|
|
"loss": 1.537880401611328,
|
|
"num_input_tokens_seen": 85296544,
|
|
"step": 76750,
|
|
"train_runtime": 126820.3551,
|
|
"train_tokens_per_second": 672.578
|
|
},
|
|
{
|
|
"epoch": 0.07405978784956606,
|
|
"grad_norm": 19.152084350585938,
|
|
"learning_rate": 0.00019734042039217951,
|
|
"loss": 1.5593974304199218,
|
|
"num_input_tokens_seen": 85334688,
|
|
"step": 76800,
|
|
"train_runtime": 126883.2274,
|
|
"train_tokens_per_second": 672.545
|
|
},
|
|
{
|
|
"epoch": 0.07410800385728061,
|
|
"grad_norm": 12.580248832702637,
|
|
"learning_rate": 0.00019733694739130443,
|
|
"loss": 1.4779376220703124,
|
|
"num_input_tokens_seen": 85372568,
|
|
"step": 76850,
|
|
"train_runtime": 126945.8155,
|
|
"train_tokens_per_second": 672.512
|
|
},
|
|
{
|
|
"epoch": 0.07415621986499518,
|
|
"grad_norm": 13.974235534667969,
|
|
"learning_rate": 0.00019733347215490784,
|
|
"loss": 1.4972233581542969,
|
|
"num_input_tokens_seen": 85410648,
|
|
"step": 76900,
|
|
"train_runtime": 127008.7026,
|
|
"train_tokens_per_second": 672.479
|
|
},
|
|
{
|
|
"epoch": 0.07420443587270974,
|
|
"grad_norm": 29.74347496032715,
|
|
"learning_rate": 0.00019732999468306947,
|
|
"loss": 1.519033203125,
|
|
"num_input_tokens_seen": 85448072,
|
|
"step": 76950,
|
|
"train_runtime": 127071.291,
|
|
"train_tokens_per_second": 672.442
|
|
},
|
|
{
|
|
"epoch": 0.0742526518804243,
|
|
"grad_norm": 25.28717041015625,
|
|
"learning_rate": 0.00019732651497586924,
|
|
"loss": 1.5807394409179687,
|
|
"num_input_tokens_seen": 85486408,
|
|
"step": 77000,
|
|
"train_runtime": 127134.2919,
|
|
"train_tokens_per_second": 672.41
|
|
},
|
|
{
|
|
"epoch": 0.07430086788813886,
|
|
"grad_norm": 19.72300148010254,
|
|
"learning_rate": 0.00019732303303338707,
|
|
"loss": 1.4997953796386718,
|
|
"num_input_tokens_seen": 85524024,
|
|
"step": 77050,
|
|
"train_runtime": 127197.0537,
|
|
"train_tokens_per_second": 672.374
|
|
},
|
|
{
|
|
"epoch": 0.07434908389585343,
|
|
"grad_norm": 18.418380737304688,
|
|
"learning_rate": 0.00019731954885570288,
|
|
"loss": 1.5655119323730469,
|
|
"num_input_tokens_seen": 85562152,
|
|
"step": 77100,
|
|
"train_runtime": 127260.2078,
|
|
"train_tokens_per_second": 672.34
|
|
},
|
|
{
|
|
"epoch": 0.07439729990356798,
|
|
"grad_norm": 85.15625,
|
|
"learning_rate": 0.00019731606244289673,
|
|
"loss": 1.8430653381347657,
|
|
"num_input_tokens_seen": 85600056,
|
|
"step": 77150,
|
|
"train_runtime": 127322.6976,
|
|
"train_tokens_per_second": 672.308
|
|
},
|
|
{
|
|
"epoch": 0.07444551591128254,
|
|
"grad_norm": 18.911373138427734,
|
|
"learning_rate": 0.0001973125737950487,
|
|
"loss": 1.6233084106445312,
|
|
"num_input_tokens_seen": 85637936,
|
|
"step": 77200,
|
|
"train_runtime": 127385.166,
|
|
"train_tokens_per_second": 672.276
|
|
},
|
|
{
|
|
"epoch": 0.07449373191899711,
|
|
"grad_norm": 10.766900062561035,
|
|
"learning_rate": 0.00019730908291223887,
|
|
"loss": 1.5277760314941407,
|
|
"num_input_tokens_seen": 85676016,
|
|
"step": 77250,
|
|
"train_runtime": 127448.215,
|
|
"train_tokens_per_second": 672.242
|
|
},
|
|
{
|
|
"epoch": 0.07454194792671166,
|
|
"grad_norm": 14.093719482421875,
|
|
"learning_rate": 0.00019730558979454745,
|
|
"loss": 1.5256715393066407,
|
|
"num_input_tokens_seen": 85712880,
|
|
"step": 77300,
|
|
"train_runtime": 127510.9621,
|
|
"train_tokens_per_second": 672.2
|
|
},
|
|
{
|
|
"epoch": 0.07459016393442623,
|
|
"grad_norm": 21.076187133789062,
|
|
"learning_rate": 0.00019730209444205466,
|
|
"loss": 1.5029524230957032,
|
|
"num_input_tokens_seen": 85750272,
|
|
"step": 77350,
|
|
"train_runtime": 127573.817,
|
|
"train_tokens_per_second": 672.162
|
|
},
|
|
{
|
|
"epoch": 0.07463837994214079,
|
|
"grad_norm": 10.610611915588379,
|
|
"learning_rate": 0.00019729859685484075,
|
|
"loss": 1.5106861877441407,
|
|
"num_input_tokens_seen": 85787096,
|
|
"step": 77400,
|
|
"train_runtime": 127636.1564,
|
|
"train_tokens_per_second": 672.122
|
|
},
|
|
{
|
|
"epoch": 0.07468659594985536,
|
|
"grad_norm": 20.879892349243164,
|
|
"learning_rate": 0.00019729509703298608,
|
|
"loss": 1.5117967224121094,
|
|
"num_input_tokens_seen": 85826136,
|
|
"step": 77450,
|
|
"train_runtime": 127698.386,
|
|
"train_tokens_per_second": 672.1
|
|
},
|
|
{
|
|
"epoch": 0.07473481195756991,
|
|
"grad_norm": 43.972171783447266,
|
|
"learning_rate": 0.00019729159497657107,
|
|
"loss": 1.5023536682128906,
|
|
"num_input_tokens_seen": 85863560,
|
|
"step": 77500,
|
|
"train_runtime": 127761.3778,
|
|
"train_tokens_per_second": 672.062
|
|
},
|
|
{
|
|
"epoch": 0.07478302796528448,
|
|
"grad_norm": 13.194141387939453,
|
|
"learning_rate": 0.00019728809068567604,
|
|
"loss": 1.4329963684082032,
|
|
"num_input_tokens_seen": 85901528,
|
|
"step": 77550,
|
|
"train_runtime": 127824.8496,
|
|
"train_tokens_per_second": 672.025
|
|
},
|
|
{
|
|
"epoch": 0.07483124397299903,
|
|
"grad_norm": 9.500736236572266,
|
|
"learning_rate": 0.00019728458416038157,
|
|
"loss": 1.448887481689453,
|
|
"num_input_tokens_seen": 85939000,
|
|
"step": 77600,
|
|
"train_runtime": 127887.0071,
|
|
"train_tokens_per_second": 671.992
|
|
},
|
|
{
|
|
"epoch": 0.0748794599807136,
|
|
"grad_norm": 39.32691192626953,
|
|
"learning_rate": 0.00019728107540076812,
|
|
"loss": 1.424910888671875,
|
|
"num_input_tokens_seen": 85976104,
|
|
"step": 77650,
|
|
"train_runtime": 127949.6766,
|
|
"train_tokens_per_second": 671.952
|
|
},
|
|
{
|
|
"epoch": 0.07492767598842816,
|
|
"grad_norm": 112.47792053222656,
|
|
"learning_rate": 0.00019727756440691635,
|
|
"loss": 1.5169088745117187,
|
|
"num_input_tokens_seen": 86013256,
|
|
"step": 77700,
|
|
"train_runtime": 128011.763,
|
|
"train_tokens_per_second": 671.917
|
|
},
|
|
{
|
|
"epoch": 0.07497589199614271,
|
|
"grad_norm": 29.461746215820312,
|
|
"learning_rate": 0.00019727405117890684,
|
|
"loss": 1.4273260498046876,
|
|
"num_input_tokens_seen": 86050984,
|
|
"step": 77750,
|
|
"train_runtime": 128074.7406,
|
|
"train_tokens_per_second": 671.881
|
|
},
|
|
{
|
|
"epoch": 0.07502410800385728,
|
|
"grad_norm": 20.92491340637207,
|
|
"learning_rate": 0.00019727053571682034,
|
|
"loss": 1.4147792053222656,
|
|
"num_input_tokens_seen": 86088440,
|
|
"step": 77800,
|
|
"train_runtime": 128137.5511,
|
|
"train_tokens_per_second": 671.844
|
|
},
|
|
{
|
|
"epoch": 0.07507232401157184,
|
|
"grad_norm": 12.632670402526855,
|
|
"learning_rate": 0.0001972670180207375,
|
|
"loss": 1.4600450134277343,
|
|
"num_input_tokens_seen": 86125848,
|
|
"step": 77850,
|
|
"train_runtime": 128200.7511,
|
|
"train_tokens_per_second": 671.805
|
|
},
|
|
{
|
|
"epoch": 0.0751205400192864,
|
|
"grad_norm": 18.619537353515625,
|
|
"learning_rate": 0.00019726349809073916,
|
|
"loss": 1.4625225830078126,
|
|
"num_input_tokens_seen": 86163464,
|
|
"step": 77900,
|
|
"train_runtime": 128263.2453,
|
|
"train_tokens_per_second": 671.77
|
|
},
|
|
{
|
|
"epoch": 0.07516875602700096,
|
|
"grad_norm": 25.0731201171875,
|
|
"learning_rate": 0.00019725997592690616,
|
|
"loss": 1.4993479919433594,
|
|
"num_input_tokens_seen": 86201760,
|
|
"step": 77950,
|
|
"train_runtime": 128325.9901,
|
|
"train_tokens_per_second": 671.74
|
|
},
|
|
{
|
|
"epoch": 0.07521697203471553,
|
|
"grad_norm": 19.931299209594727,
|
|
"learning_rate": 0.00019725645152931942,
|
|
"loss": 1.4429109191894531,
|
|
"num_input_tokens_seen": 86239096,
|
|
"step": 78000,
|
|
"train_runtime": 128388.9364,
|
|
"train_tokens_per_second": 671.702
|
|
},
|
|
{
|
|
"epoch": 0.07526518804243008,
|
|
"grad_norm": 12.308609962463379,
|
|
"learning_rate": 0.00019725292489805983,
|
|
"loss": 1.4746298217773437,
|
|
"num_input_tokens_seen": 86277016,
|
|
"step": 78050,
|
|
"train_runtime": 128452.1897,
|
|
"train_tokens_per_second": 671.666
|
|
},
|
|
{
|
|
"epoch": 0.07531340405014465,
|
|
"grad_norm": 10.52625560760498,
|
|
"learning_rate": 0.00019724939603320843,
|
|
"loss": 1.4597393798828124,
|
|
"num_input_tokens_seen": 86315608,
|
|
"step": 78100,
|
|
"train_runtime": 128515.0153,
|
|
"train_tokens_per_second": 671.638
|
|
},
|
|
{
|
|
"epoch": 0.07536162005785921,
|
|
"grad_norm": 11.30103588104248,
|
|
"learning_rate": 0.00019724586493484624,
|
|
"loss": 1.4426412963867188,
|
|
"num_input_tokens_seen": 86353032,
|
|
"step": 78150,
|
|
"train_runtime": 128578.08,
|
|
"train_tokens_per_second": 671.6
|
|
},
|
|
{
|
|
"epoch": 0.07540983606557378,
|
|
"grad_norm": 17.295455932617188,
|
|
"learning_rate": 0.00019724233160305438,
|
|
"loss": 1.4417323303222656,
|
|
"num_input_tokens_seen": 86391896,
|
|
"step": 78200,
|
|
"train_runtime": 128641.0158,
|
|
"train_tokens_per_second": 671.573
|
|
},
|
|
{
|
|
"epoch": 0.07545805207328833,
|
|
"grad_norm": 14.063020706176758,
|
|
"learning_rate": 0.00019723879603791397,
|
|
"loss": 1.4613836669921876,
|
|
"num_input_tokens_seen": 86429528,
|
|
"step": 78250,
|
|
"train_runtime": 128704.2116,
|
|
"train_tokens_per_second": 671.536
|
|
},
|
|
{
|
|
"epoch": 0.07550626808100289,
|
|
"grad_norm": 31.774614334106445,
|
|
"learning_rate": 0.00019723525823950623,
|
|
"loss": 1.556214599609375,
|
|
"num_input_tokens_seen": 86466520,
|
|
"step": 78300,
|
|
"train_runtime": 128766.6082,
|
|
"train_tokens_per_second": 671.498
|
|
},
|
|
{
|
|
"epoch": 0.07555448408871746,
|
|
"grad_norm": 7.304618835449219,
|
|
"learning_rate": 0.0001972317182079124,
|
|
"loss": 1.5371458435058594,
|
|
"num_input_tokens_seen": 86505472,
|
|
"step": 78350,
|
|
"train_runtime": 128829.2387,
|
|
"train_tokens_per_second": 671.474
|
|
},
|
|
{
|
|
"epoch": 0.07560270009643201,
|
|
"grad_norm": 25.022279739379883,
|
|
"learning_rate": 0.0001972281759432138,
|
|
"loss": 1.4955252075195313,
|
|
"num_input_tokens_seen": 86543824,
|
|
"step": 78400,
|
|
"train_runtime": 128891.7167,
|
|
"train_tokens_per_second": 671.446
|
|
},
|
|
{
|
|
"epoch": 0.07565091610414658,
|
|
"grad_norm": 11.466940879821777,
|
|
"learning_rate": 0.00019722463144549178,
|
|
"loss": 1.5596994018554688,
|
|
"num_input_tokens_seen": 86581272,
|
|
"step": 78450,
|
|
"train_runtime": 128954.4365,
|
|
"train_tokens_per_second": 671.41
|
|
},
|
|
{
|
|
"epoch": 0.07569913211186113,
|
|
"grad_norm": 14.266871452331543,
|
|
"learning_rate": 0.00019722108471482774,
|
|
"loss": 1.625177001953125,
|
|
"num_input_tokens_seen": 86618864,
|
|
"step": 78500,
|
|
"train_runtime": 129018.0913,
|
|
"train_tokens_per_second": 671.37
|
|
},
|
|
{
|
|
"epoch": 0.0757473481195757,
|
|
"grad_norm": 38.09740447998047,
|
|
"learning_rate": 0.00019721753575130318,
|
|
"loss": 1.5649359130859375,
|
|
"num_input_tokens_seen": 86656392,
|
|
"step": 78550,
|
|
"train_runtime": 129080.6822,
|
|
"train_tokens_per_second": 671.335
|
|
},
|
|
{
|
|
"epoch": 0.07579556412729026,
|
|
"grad_norm": 10.961430549621582,
|
|
"learning_rate": 0.0001972139845549995,
|
|
"loss": 1.509986572265625,
|
|
"num_input_tokens_seen": 86694336,
|
|
"step": 78600,
|
|
"train_runtime": 129142.8266,
|
|
"train_tokens_per_second": 671.306
|
|
},
|
|
{
|
|
"epoch": 0.07584378013500483,
|
|
"grad_norm": 111.32006072998047,
|
|
"learning_rate": 0.00019721043112599836,
|
|
"loss": 1.604498291015625,
|
|
"num_input_tokens_seen": 86731456,
|
|
"step": 78650,
|
|
"train_runtime": 129205.7135,
|
|
"train_tokens_per_second": 671.266
|
|
},
|
|
{
|
|
"epoch": 0.07589199614271938,
|
|
"grad_norm": 60.2459831237793,
|
|
"learning_rate": 0.00019720687546438134,
|
|
"loss": 1.673992919921875,
|
|
"num_input_tokens_seen": 86769352,
|
|
"step": 78700,
|
|
"train_runtime": 129268.4237,
|
|
"train_tokens_per_second": 671.234
|
|
},
|
|
{
|
|
"epoch": 0.07594021215043395,
|
|
"grad_norm": 38.800411224365234,
|
|
"learning_rate": 0.00019720331757023008,
|
|
"loss": 1.80258056640625,
|
|
"num_input_tokens_seen": 86807208,
|
|
"step": 78750,
|
|
"train_runtime": 129331.6594,
|
|
"train_tokens_per_second": 671.198
|
|
},
|
|
{
|
|
"epoch": 0.0759884281581485,
|
|
"grad_norm": 36.16996383666992,
|
|
"learning_rate": 0.00019719975744362635,
|
|
"loss": 1.6040846252441405,
|
|
"num_input_tokens_seen": 86845168,
|
|
"step": 78800,
|
|
"train_runtime": 129393.8351,
|
|
"train_tokens_per_second": 671.169
|
|
},
|
|
{
|
|
"epoch": 0.07603664416586306,
|
|
"grad_norm": 30.35773468017578,
|
|
"learning_rate": 0.00019719619508465187,
|
|
"loss": 1.5595097351074219,
|
|
"num_input_tokens_seen": 86883448,
|
|
"step": 78850,
|
|
"train_runtime": 129456.7185,
|
|
"train_tokens_per_second": 671.139
|
|
},
|
|
{
|
|
"epoch": 0.07608486017357763,
|
|
"grad_norm": 42.93082809448242,
|
|
"learning_rate": 0.0001971926304933885,
|
|
"loss": 1.668134002685547,
|
|
"num_input_tokens_seen": 86920616,
|
|
"step": 78900,
|
|
"train_runtime": 129519.2913,
|
|
"train_tokens_per_second": 671.102
|
|
},
|
|
{
|
|
"epoch": 0.07613307618129218,
|
|
"grad_norm": 43.00521469116211,
|
|
"learning_rate": 0.00019718906366991798,
|
|
"loss": 1.5376153564453126,
|
|
"num_input_tokens_seen": 86958288,
|
|
"step": 78950,
|
|
"train_runtime": 129581.9401,
|
|
"train_tokens_per_second": 671.068
|
|
},
|
|
{
|
|
"epoch": 0.07618129218900675,
|
|
"grad_norm": 40.72639846801758,
|
|
"learning_rate": 0.00019718549461432238,
|
|
"loss": 1.6213516235351562,
|
|
"num_input_tokens_seen": 86995752,
|
|
"step": 79000,
|
|
"train_runtime": 129644.7509,
|
|
"train_tokens_per_second": 671.032
|
|
},
|
|
{
|
|
"epoch": 0.07622950819672131,
|
|
"grad_norm": 18.173959732055664,
|
|
"learning_rate": 0.0001971819233266836,
|
|
"loss": 1.5937161254882812,
|
|
"num_input_tokens_seen": 87033296,
|
|
"step": 79050,
|
|
"train_runtime": 129707.2446,
|
|
"train_tokens_per_second": 670.998
|
|
},
|
|
{
|
|
"epoch": 0.07627772420443588,
|
|
"grad_norm": 26.00728416442871,
|
|
"learning_rate": 0.0001971783498070837,
|
|
"loss": 1.5693345642089844,
|
|
"num_input_tokens_seen": 87071032,
|
|
"step": 79100,
|
|
"train_runtime": 129769.7134,
|
|
"train_tokens_per_second": 670.966
|
|
},
|
|
{
|
|
"epoch": 0.07632594021215043,
|
|
"grad_norm": 21.95258331298828,
|
|
"learning_rate": 0.00019717477405560468,
|
|
"loss": 1.5569729614257812,
|
|
"num_input_tokens_seen": 87108376,
|
|
"step": 79150,
|
|
"train_runtime": 129831.7055,
|
|
"train_tokens_per_second": 670.933
|
|
},
|
|
{
|
|
"epoch": 0.076374156219865,
|
|
"grad_norm": 17.689329147338867,
|
|
"learning_rate": 0.00019717119607232876,
|
|
"loss": 1.5745941162109376,
|
|
"num_input_tokens_seen": 87146592,
|
|
"step": 79200,
|
|
"train_runtime": 129894.6167,
|
|
"train_tokens_per_second": 670.902
|
|
},
|
|
{
|
|
"epoch": 0.07642237222757955,
|
|
"grad_norm": 50.906532287597656,
|
|
"learning_rate": 0.00019716761585733802,
|
|
"loss": 1.621045379638672,
|
|
"num_input_tokens_seen": 87184712,
|
|
"step": 79250,
|
|
"train_runtime": 129958.2161,
|
|
"train_tokens_per_second": 670.867
|
|
},
|
|
{
|
|
"epoch": 0.07647058823529412,
|
|
"grad_norm": 13.21219539642334,
|
|
"learning_rate": 0.00019716403341071476,
|
|
"loss": 1.7245101928710938,
|
|
"num_input_tokens_seen": 87222672,
|
|
"step": 79300,
|
|
"train_runtime": 130020.9562,
|
|
"train_tokens_per_second": 670.835
|
|
},
|
|
{
|
|
"epoch": 0.07651880424300868,
|
|
"grad_norm": 14.293977737426758,
|
|
"learning_rate": 0.0001971604487325412,
|
|
"loss": 1.7111453247070312,
|
|
"num_input_tokens_seen": 87260064,
|
|
"step": 79350,
|
|
"train_runtime": 130083.6685,
|
|
"train_tokens_per_second": 670.8
|
|
},
|
|
{
|
|
"epoch": 0.07656702025072323,
|
|
"grad_norm": 12.363946914672852,
|
|
"learning_rate": 0.00019715686182289973,
|
|
"loss": 1.7747323608398438,
|
|
"num_input_tokens_seen": 87298280,
|
|
"step": 79400,
|
|
"train_runtime": 130145.8465,
|
|
"train_tokens_per_second": 670.773
|
|
},
|
|
{
|
|
"epoch": 0.0766152362584378,
|
|
"grad_norm": 37.49530029296875,
|
|
"learning_rate": 0.0001971532726818727,
|
|
"loss": 1.6832215881347656,
|
|
"num_input_tokens_seen": 87336488,
|
|
"step": 79450,
|
|
"train_runtime": 130208.2351,
|
|
"train_tokens_per_second": 670.745
|
|
},
|
|
{
|
|
"epoch": 0.07666345226615236,
|
|
"grad_norm": 11.409509658813477,
|
|
"learning_rate": 0.0001971496813095425,
|
|
"loss": 1.6235867309570313,
|
|
"num_input_tokens_seen": 87374712,
|
|
"step": 79500,
|
|
"train_runtime": 130271.3425,
|
|
"train_tokens_per_second": 670.713
|
|
},
|
|
{
|
|
"epoch": 0.07671166827386693,
|
|
"grad_norm": 35.25929260253906,
|
|
"learning_rate": 0.00019714608770599168,
|
|
"loss": 1.6659657287597656,
|
|
"num_input_tokens_seen": 87413360,
|
|
"step": 79550,
|
|
"train_runtime": 130334.0656,
|
|
"train_tokens_per_second": 670.687
|
|
},
|
|
{
|
|
"epoch": 0.07675988428158148,
|
|
"grad_norm": 19.344255447387695,
|
|
"learning_rate": 0.00019714249187130273,
|
|
"loss": 1.627200927734375,
|
|
"num_input_tokens_seen": 87452552,
|
|
"step": 79600,
|
|
"train_runtime": 130396.8548,
|
|
"train_tokens_per_second": 670.665
|
|
},
|
|
{
|
|
"epoch": 0.07680810028929605,
|
|
"grad_norm": 137.4578094482422,
|
|
"learning_rate": 0.00019713889380555826,
|
|
"loss": 1.799536895751953,
|
|
"num_input_tokens_seen": 87490088,
|
|
"step": 79650,
|
|
"train_runtime": 130459.0905,
|
|
"train_tokens_per_second": 670.632
|
|
},
|
|
{
|
|
"epoch": 0.0768563162970106,
|
|
"grad_norm": 20.0741024017334,
|
|
"learning_rate": 0.00019713529350884088,
|
|
"loss": 1.6538809204101563,
|
|
"num_input_tokens_seen": 87527024,
|
|
"step": 79700,
|
|
"train_runtime": 130521.4935,
|
|
"train_tokens_per_second": 670.595
|
|
},
|
|
{
|
|
"epoch": 0.07690453230472517,
|
|
"grad_norm": 25.95866584777832,
|
|
"learning_rate": 0.0001971316909812333,
|
|
"loss": 1.5713520812988282,
|
|
"num_input_tokens_seen": 87564720,
|
|
"step": 79750,
|
|
"train_runtime": 130584.305,
|
|
"train_tokens_per_second": 670.561
|
|
},
|
|
{
|
|
"epoch": 0.07695274831243973,
|
|
"grad_norm": 32.167755126953125,
|
|
"learning_rate": 0.00019712808622281825,
|
|
"loss": 1.5495932006835937,
|
|
"num_input_tokens_seen": 87602952,
|
|
"step": 79800,
|
|
"train_runtime": 130647.4646,
|
|
"train_tokens_per_second": 670.529
|
|
},
|
|
{
|
|
"epoch": 0.0770009643201543,
|
|
"grad_norm": 25.169605255126953,
|
|
"learning_rate": 0.0001971244792336785,
|
|
"loss": 1.5978018188476562,
|
|
"num_input_tokens_seen": 87640336,
|
|
"step": 79850,
|
|
"train_runtime": 130709.8988,
|
|
"train_tokens_per_second": 670.495
|
|
},
|
|
{
|
|
"epoch": 0.07704918032786885,
|
|
"grad_norm": 168.33131408691406,
|
|
"learning_rate": 0.00019712087001389695,
|
|
"loss": 1.7798429870605468,
|
|
"num_input_tokens_seen": 87678840,
|
|
"step": 79900,
|
|
"train_runtime": 130772.6468,
|
|
"train_tokens_per_second": 670.468
|
|
},
|
|
{
|
|
"epoch": 0.0770973963355834,
|
|
"grad_norm": 27.502492904663086,
|
|
"learning_rate": 0.00019711725856355646,
|
|
"loss": 1.8275462341308595,
|
|
"num_input_tokens_seen": 87716984,
|
|
"step": 79950,
|
|
"train_runtime": 130835.6526,
|
|
"train_tokens_per_second": 670.436
|
|
},
|
|
{
|
|
"epoch": 0.07714561234329798,
|
|
"grad_norm": 143.951416015625,
|
|
"learning_rate": 0.00019711364488273994,
|
|
"loss": 1.7454002380371094,
|
|
"num_input_tokens_seen": 87755400,
|
|
"step": 80000,
|
|
"train_runtime": 130899.2478,
|
|
"train_tokens_per_second": 670.404
|
|
},
|
|
{
|
|
"epoch": 0.07719382835101253,
|
|
"grad_norm": 443.01361083984375,
|
|
"learning_rate": 0.0001971100289715304,
|
|
"loss": 2.1003814697265626,
|
|
"num_input_tokens_seen": 87792768,
|
|
"step": 80050,
|
|
"train_runtime": 130962.6981,
|
|
"train_tokens_per_second": 670.365
|
|
},
|
|
{
|
|
"epoch": 0.0772420443587271,
|
|
"grad_norm": 83.79534912109375,
|
|
"learning_rate": 0.00019710648321469784,
|
|
"loss": 2.252016296386719,
|
|
"num_input_tokens_seen": 87831504,
|
|
"step": 80100,
|
|
"train_runtime": 131025.4184,
|
|
"train_tokens_per_second": 670.339
|
|
},
|
|
{
|
|
"epoch": 0.07729026036644165,
|
|
"grad_norm": 228.33709716796875,
|
|
"learning_rate": 0.0001971028628875552,
|
|
"loss": 1.9783624267578126,
|
|
"num_input_tokens_seen": 87869136,
|
|
"step": 80150,
|
|
"train_runtime": 131088.7242,
|
|
"train_tokens_per_second": 670.303
|
|
},
|
|
{
|
|
"epoch": 0.07733847637415622,
|
|
"grad_norm": 76.32440185546875,
|
|
"learning_rate": 0.0001970992403302672,
|
|
"loss": 2.387911376953125,
|
|
"num_input_tokens_seen": 87907176,
|
|
"step": 80200,
|
|
"train_runtime": 131151.6359,
|
|
"train_tokens_per_second": 670.271
|
|
},
|
|
{
|
|
"epoch": 0.07738669238187078,
|
|
"grad_norm": 118.6132583618164,
|
|
"learning_rate": 0.00019709561554291703,
|
|
"loss": 1.8291929626464845,
|
|
"num_input_tokens_seen": 87945904,
|
|
"step": 80250,
|
|
"train_runtime": 131215.0644,
|
|
"train_tokens_per_second": 670.242
|
|
},
|
|
{
|
|
"epoch": 0.07743490838958535,
|
|
"grad_norm": 278.76318359375,
|
|
"learning_rate": 0.00019709198852558787,
|
|
"loss": 1.867969970703125,
|
|
"num_input_tokens_seen": 87984648,
|
|
"step": 80300,
|
|
"train_runtime": 131277.8773,
|
|
"train_tokens_per_second": 670.217
|
|
},
|
|
{
|
|
"epoch": 0.0774831243972999,
|
|
"grad_norm": 53.45292282104492,
|
|
"learning_rate": 0.00019708835927836316,
|
|
"loss": 2.0309230041503907,
|
|
"num_input_tokens_seen": 88023216,
|
|
"step": 80350,
|
|
"train_runtime": 131340.4984,
|
|
"train_tokens_per_second": 670.191
|
|
},
|
|
{
|
|
"epoch": 0.07753134040501447,
|
|
"grad_norm": 62.511497497558594,
|
|
"learning_rate": 0.00019708472780132614,
|
|
"loss": 1.7342857360839843,
|
|
"num_input_tokens_seen": 88061768,
|
|
"step": 80400,
|
|
"train_runtime": 131403.6818,
|
|
"train_tokens_per_second": 670.162
|
|
},
|
|
{
|
|
"epoch": 0.07757955641272903,
|
|
"grad_norm": 283.7810974121094,
|
|
"learning_rate": 0.00019708116679054635,
|
|
"loss": 2.216535186767578,
|
|
"num_input_tokens_seen": 88100408,
|
|
"step": 80450,
|
|
"train_runtime": 131466.3389,
|
|
"train_tokens_per_second": 670.137
|
|
},
|
|
{
|
|
"epoch": 0.07762777242044358,
|
|
"grad_norm": 40.35204315185547,
|
|
"learning_rate": 0.00019707753089872714,
|
|
"loss": 1.8982368469238282,
|
|
"num_input_tokens_seen": 88138416,
|
|
"step": 80500,
|
|
"train_runtime": 131529.4274,
|
|
"train_tokens_per_second": 670.104
|
|
},
|
|
{
|
|
"epoch": 0.07767598842815815,
|
|
"grad_norm": 38.25251388549805,
|
|
"learning_rate": 0.00019707389277734435,
|
|
"loss": 2.1621495056152344,
|
|
"num_input_tokens_seen": 88176320,
|
|
"step": 80550,
|
|
"train_runtime": 131592.1085,
|
|
"train_tokens_per_second": 670.073
|
|
},
|
|
{
|
|
"epoch": 0.0777242044358727,
|
|
"grad_norm": 30.880756378173828,
|
|
"learning_rate": 0.0001970702524264815,
|
|
"loss": 2.2903277587890627,
|
|
"num_input_tokens_seen": 88214304,
|
|
"step": 80600,
|
|
"train_runtime": 131654.492,
|
|
"train_tokens_per_second": 670.044
|
|
},
|
|
{
|
|
"epoch": 0.07777242044358727,
|
|
"grad_norm": 13.728896141052246,
|
|
"learning_rate": 0.00019706660984622224,
|
|
"loss": 1.7892440795898437,
|
|
"num_input_tokens_seen": 88252312,
|
|
"step": 80650,
|
|
"train_runtime": 131717.473,
|
|
"train_tokens_per_second": 670.012
|
|
},
|
|
{
|
|
"epoch": 0.07782063645130183,
|
|
"grad_norm": 11.512665748596191,
|
|
"learning_rate": 0.00019706296503665022,
|
|
"loss": 1.7712812805175782,
|
|
"num_input_tokens_seen": 88290288,
|
|
"step": 80700,
|
|
"train_runtime": 131780.115,
|
|
"train_tokens_per_second": 669.982
|
|
},
|
|
{
|
|
"epoch": 0.0778688524590164,
|
|
"grad_norm": 49.376922607421875,
|
|
"learning_rate": 0.0001970593179978492,
|
|
"loss": 1.7315946960449218,
|
|
"num_input_tokens_seen": 88328904,
|
|
"step": 80750,
|
|
"train_runtime": 131843.3563,
|
|
"train_tokens_per_second": 669.953
|
|
},
|
|
{
|
|
"epoch": 0.07791706846673095,
|
|
"grad_norm": 42.255958557128906,
|
|
"learning_rate": 0.00019705566872990282,
|
|
"loss": 1.71984130859375,
|
|
"num_input_tokens_seen": 88367568,
|
|
"step": 80800,
|
|
"train_runtime": 131906.1057,
|
|
"train_tokens_per_second": 669.928
|
|
},
|
|
{
|
|
"epoch": 0.07796528447444552,
|
|
"grad_norm": 22.22457504272461,
|
|
"learning_rate": 0.00019705201723289498,
|
|
"loss": 1.9253730773925781,
|
|
"num_input_tokens_seen": 88404864,
|
|
"step": 80850,
|
|
"train_runtime": 131968.6978,
|
|
"train_tokens_per_second": 669.893
|
|
},
|
|
{
|
|
"epoch": 0.07801350048216008,
|
|
"grad_norm": 16.168888092041016,
|
|
"learning_rate": 0.00019704836350690954,
|
|
"loss": 1.8235012817382812,
|
|
"num_input_tokens_seen": 88442784,
|
|
"step": 80900,
|
|
"train_runtime": 132031.2796,
|
|
"train_tokens_per_second": 669.862
|
|
},
|
|
{
|
|
"epoch": 0.07806171648987464,
|
|
"grad_norm": 31.324527740478516,
|
|
"learning_rate": 0.0001970447075520304,
|
|
"loss": 1.7552275085449218,
|
|
"num_input_tokens_seen": 88481416,
|
|
"step": 80950,
|
|
"train_runtime": 132094.3392,
|
|
"train_tokens_per_second": 669.835
|
|
},
|
|
{
|
|
"epoch": 0.0781099324975892,
|
|
"grad_norm": 95.38471984863281,
|
|
"learning_rate": 0.0001970410493683415,
|
|
"loss": 1.9478125,
|
|
"num_input_tokens_seen": 88518976,
|
|
"step": 81000,
|
|
"train_runtime": 132157.483,
|
|
"train_tokens_per_second": 669.799
|
|
},
|
|
{
|
|
"epoch": 0.07815814850530377,
|
|
"grad_norm": 131.64846801757812,
|
|
"learning_rate": 0.0001970373889559269,
|
|
"loss": 1.9308706665039062,
|
|
"num_input_tokens_seen": 88556928,
|
|
"step": 81050,
|
|
"train_runtime": 132220.1701,
|
|
"train_tokens_per_second": 669.769
|
|
},
|
|
{
|
|
"epoch": 0.07820636451301832,
|
|
"grad_norm": 32.143287658691406,
|
|
"learning_rate": 0.00019703372631487068,
|
|
"loss": 1.7807931518554687,
|
|
"num_input_tokens_seen": 88594352,
|
|
"step": 81100,
|
|
"train_runtime": 132282.9646,
|
|
"train_tokens_per_second": 669.734
|
|
},
|
|
{
|
|
"epoch": 0.07825458052073288,
|
|
"grad_norm": 124.81611633300781,
|
|
"learning_rate": 0.0001970300614452569,
|
|
"loss": 1.8204666137695313,
|
|
"num_input_tokens_seen": 88631744,
|
|
"step": 81150,
|
|
"train_runtime": 132345.0429,
|
|
"train_tokens_per_second": 669.702
|
|
},
|
|
{
|
|
"epoch": 0.07830279652844745,
|
|
"grad_norm": 36.71405792236328,
|
|
"learning_rate": 0.00019702639434716974,
|
|
"loss": 1.8467707824707031,
|
|
"num_input_tokens_seen": 88669648,
|
|
"step": 81200,
|
|
"train_runtime": 132407.571,
|
|
"train_tokens_per_second": 669.672
|
|
},
|
|
{
|
|
"epoch": 0.078351012536162,
|
|
"grad_norm": 34.56256866455078,
|
|
"learning_rate": 0.00019702272502069345,
|
|
"loss": 1.7136958312988282,
|
|
"num_input_tokens_seen": 88708024,
|
|
"step": 81250,
|
|
"train_runtime": 132470.4335,
|
|
"train_tokens_per_second": 669.644
|
|
},
|
|
{
|
|
"epoch": 0.07839922854387657,
|
|
"grad_norm": 18.063474655151367,
|
|
"learning_rate": 0.0001970190534659123,
|
|
"loss": 1.7226434326171876,
|
|
"num_input_tokens_seen": 88747072,
|
|
"step": 81300,
|
|
"train_runtime": 132533.2718,
|
|
"train_tokens_per_second": 669.621
|
|
},
|
|
{
|
|
"epoch": 0.07844744455159113,
|
|
"grad_norm": 18.987171173095703,
|
|
"learning_rate": 0.0001970153796829106,
|
|
"loss": 1.7428724670410156,
|
|
"num_input_tokens_seen": 88784680,
|
|
"step": 81350,
|
|
"train_runtime": 132596.5274,
|
|
"train_tokens_per_second": 669.585
|
|
},
|
|
{
|
|
"epoch": 0.0784956605593057,
|
|
"grad_norm": 28.030052185058594,
|
|
"learning_rate": 0.00019701170367177276,
|
|
"loss": 1.7457015991210938,
|
|
"num_input_tokens_seen": 88822264,
|
|
"step": 81400,
|
|
"train_runtime": 132659.3671,
|
|
"train_tokens_per_second": 669.551
|
|
},
|
|
{
|
|
"epoch": 0.07854387656702025,
|
|
"grad_norm": 34.97487258911133,
|
|
"learning_rate": 0.00019700802543258316,
|
|
"loss": 1.7917259216308594,
|
|
"num_input_tokens_seen": 88860584,
|
|
"step": 81450,
|
|
"train_runtime": 132722.1566,
|
|
"train_tokens_per_second": 669.523
|
|
},
|
|
{
|
|
"epoch": 0.07859209257473482,
|
|
"grad_norm": 41.41057586669922,
|
|
"learning_rate": 0.00019700434496542631,
|
|
"loss": 1.7075816345214845,
|
|
"num_input_tokens_seen": 88898272,
|
|
"step": 81500,
|
|
"train_runtime": 132784.933,
|
|
"train_tokens_per_second": 669.491
|
|
},
|
|
{
|
|
"epoch": 0.07864030858244937,
|
|
"grad_norm": 13.84016227722168,
|
|
"learning_rate": 0.00019700066227038672,
|
|
"loss": 1.6772798156738282,
|
|
"num_input_tokens_seen": 88935216,
|
|
"step": 81550,
|
|
"train_runtime": 132847.1281,
|
|
"train_tokens_per_second": 669.455
|
|
},
|
|
{
|
|
"epoch": 0.07868852459016394,
|
|
"grad_norm": 12.06406307220459,
|
|
"learning_rate": 0.00019699697734754898,
|
|
"loss": 1.7116476440429687,
|
|
"num_input_tokens_seen": 88973152,
|
|
"step": 81600,
|
|
"train_runtime": 132910.2343,
|
|
"train_tokens_per_second": 669.423
|
|
},
|
|
{
|
|
"epoch": 0.0787367405978785,
|
|
"grad_norm": 14.247344017028809,
|
|
"learning_rate": 0.00019699329019699771,
|
|
"loss": 1.7740823364257812,
|
|
"num_input_tokens_seen": 89011432,
|
|
"step": 81650,
|
|
"train_runtime": 132972.5894,
|
|
"train_tokens_per_second": 669.397
|
|
},
|
|
{
|
|
"epoch": 0.07878495660559305,
|
|
"grad_norm": 10.873311042785645,
|
|
"learning_rate": 0.00019698960081881758,
|
|
"loss": 1.7472283935546875,
|
|
"num_input_tokens_seen": 89049336,
|
|
"step": 81700,
|
|
"train_runtime": 133034.9552,
|
|
"train_tokens_per_second": 669.368
|
|
},
|
|
{
|
|
"epoch": 0.07883317261330762,
|
|
"grad_norm": 28.07518768310547,
|
|
"learning_rate": 0.00019698590921309338,
|
|
"loss": 1.7310685729980468,
|
|
"num_input_tokens_seen": 89087584,
|
|
"step": 81750,
|
|
"train_runtime": 133097.5339,
|
|
"train_tokens_per_second": 669.341
|
|
},
|
|
{
|
|
"epoch": 0.07888138862102217,
|
|
"grad_norm": 13.093722343444824,
|
|
"learning_rate": 0.00019698221537990982,
|
|
"loss": 1.7074349975585938,
|
|
"num_input_tokens_seen": 89125320,
|
|
"step": 81800,
|
|
"train_runtime": 133160.2208,
|
|
"train_tokens_per_second": 669.309
|
|
},
|
|
{
|
|
"epoch": 0.07892960462873674,
|
|
"grad_norm": 16.717477798461914,
|
|
"learning_rate": 0.00019697851931935181,
|
|
"loss": 1.7510285949707032,
|
|
"num_input_tokens_seen": 89163448,
|
|
"step": 81850,
|
|
"train_runtime": 133222.5994,
|
|
"train_tokens_per_second": 669.282
|
|
},
|
|
{
|
|
"epoch": 0.0789778206364513,
|
|
"grad_norm": 21.93857192993164,
|
|
"learning_rate": 0.00019697482103150416,
|
|
"loss": 1.6673345947265625,
|
|
"num_input_tokens_seen": 89201552,
|
|
"step": 81900,
|
|
"train_runtime": 133285.1258,
|
|
"train_tokens_per_second": 669.254
|
|
},
|
|
{
|
|
"epoch": 0.07902603664416587,
|
|
"grad_norm": 34.238224029541016,
|
|
"learning_rate": 0.00019697112051645187,
|
|
"loss": 1.695263671875,
|
|
"num_input_tokens_seen": 89240168,
|
|
"step": 81950,
|
|
"train_runtime": 133347.7167,
|
|
"train_tokens_per_second": 669.229
|
|
},
|
|
{
|
|
"epoch": 0.07907425265188042,
|
|
"grad_norm": 14.689729690551758,
|
|
"learning_rate": 0.00019696741777427992,
|
|
"loss": 1.640824737548828,
|
|
"num_input_tokens_seen": 89277592,
|
|
"step": 82000,
|
|
"train_runtime": 133410.6872,
|
|
"train_tokens_per_second": 669.194
|
|
},
|
|
{
|
|
"epoch": 0.07912246865959499,
|
|
"grad_norm": 25.110124588012695,
|
|
"learning_rate": 0.00019696371280507333,
|
|
"loss": 1.7703138732910155,
|
|
"num_input_tokens_seen": 89315776,
|
|
"step": 82050,
|
|
"train_runtime": 133473.3599,
|
|
"train_tokens_per_second": 669.166
|
|
},
|
|
{
|
|
"epoch": 0.07917068466730955,
|
|
"grad_norm": 16.36161994934082,
|
|
"learning_rate": 0.00019696000560891718,
|
|
"loss": 1.8094728088378906,
|
|
"num_input_tokens_seen": 89353904,
|
|
"step": 82100,
|
|
"train_runtime": 133536.2381,
|
|
"train_tokens_per_second": 669.136
|
|
},
|
|
{
|
|
"epoch": 0.07921890067502411,
|
|
"grad_norm": 21.13072395324707,
|
|
"learning_rate": 0.00019695629618589664,
|
|
"loss": 1.6926280212402345,
|
|
"num_input_tokens_seen": 89391816,
|
|
"step": 82150,
|
|
"train_runtime": 133599.4539,
|
|
"train_tokens_per_second": 669.103
|
|
},
|
|
{
|
|
"epoch": 0.07926711668273867,
|
|
"grad_norm": 14.892433166503906,
|
|
"learning_rate": 0.00019695258453609687,
|
|
"loss": 1.7320347595214844,
|
|
"num_input_tokens_seen": 89429608,
|
|
"step": 82200,
|
|
"train_runtime": 133662.032,
|
|
"train_tokens_per_second": 669.073
|
|
},
|
|
{
|
|
"epoch": 0.07931533269045322,
|
|
"grad_norm": 25.358386993408203,
|
|
"learning_rate": 0.00019694887065960316,
|
|
"loss": 1.775916748046875,
|
|
"num_input_tokens_seen": 89467864,
|
|
"step": 82250,
|
|
"train_runtime": 133725.4819,
|
|
"train_tokens_per_second": 669.041
|
|
},
|
|
{
|
|
"epoch": 0.0793635486981678,
|
|
"grad_norm": 23.342164993286133,
|
|
"learning_rate": 0.0001969451545565008,
|
|
"loss": 1.606768798828125,
|
|
"num_input_tokens_seen": 89505792,
|
|
"step": 82300,
|
|
"train_runtime": 133788.0543,
|
|
"train_tokens_per_second": 669.012
|
|
},
|
|
{
|
|
"epoch": 0.07941176470588235,
|
|
"grad_norm": 23.723737716674805,
|
|
"learning_rate": 0.0001969414362268751,
|
|
"loss": 1.6384201049804688,
|
|
"num_input_tokens_seen": 89543696,
|
|
"step": 82350,
|
|
"train_runtime": 133850.4426,
|
|
"train_tokens_per_second": 668.983
|
|
},
|
|
{
|
|
"epoch": 0.07945998071359692,
|
|
"grad_norm": 44.77687072753906,
|
|
"learning_rate": 0.00019693771567081151,
|
|
"loss": 1.6833131408691406,
|
|
"num_input_tokens_seen": 89581040,
|
|
"step": 82400,
|
|
"train_runtime": 133912.7171,
|
|
"train_tokens_per_second": 668.951
|
|
},
|
|
{
|
|
"epoch": 0.07950819672131147,
|
|
"grad_norm": 37.829566955566406,
|
|
"learning_rate": 0.00019693399288839544,
|
|
"loss": 1.7988192749023437,
|
|
"num_input_tokens_seen": 89618536,
|
|
"step": 82450,
|
|
"train_runtime": 133975.3128,
|
|
"train_tokens_per_second": 668.918
|
|
},
|
|
{
|
|
"epoch": 0.07955641272902604,
|
|
"grad_norm": 24.037614822387695,
|
|
"learning_rate": 0.0001969302678797124,
|
|
"loss": 1.7384536743164063,
|
|
"num_input_tokens_seen": 89657264,
|
|
"step": 82500,
|
|
"train_runtime": 134038.597,
|
|
"train_tokens_per_second": 668.891
|
|
},
|
|
{
|
|
"epoch": 0.0796046287367406,
|
|
"grad_norm": 53.284664154052734,
|
|
"learning_rate": 0.0001969265406448479,
|
|
"loss": 1.697433624267578,
|
|
"num_input_tokens_seen": 89696248,
|
|
"step": 82550,
|
|
"train_runtime": 134102.107,
|
|
"train_tokens_per_second": 668.865
|
|
},
|
|
{
|
|
"epoch": 0.07965284474445516,
|
|
"grad_norm": 12.655561447143555,
|
|
"learning_rate": 0.00019692281118388762,
|
|
"loss": 1.7819441223144532,
|
|
"num_input_tokens_seen": 89734072,
|
|
"step": 82600,
|
|
"train_runtime": 134164.7947,
|
|
"train_tokens_per_second": 668.835
|
|
},
|
|
{
|
|
"epoch": 0.07970106075216972,
|
|
"grad_norm": 14.802879333496094,
|
|
"learning_rate": 0.0001969190794969172,
|
|
"loss": 1.7019313049316407,
|
|
"num_input_tokens_seen": 89771864,
|
|
"step": 82650,
|
|
"train_runtime": 134227.4582,
|
|
"train_tokens_per_second": 668.804
|
|
},
|
|
{
|
|
"epoch": 0.07974927675988429,
|
|
"grad_norm": 12.352277755737305,
|
|
"learning_rate": 0.0001969153455840223,
|
|
"loss": 1.6832489013671874,
|
|
"num_input_tokens_seen": 89809272,
|
|
"step": 82700,
|
|
"train_runtime": 134290.1444,
|
|
"train_tokens_per_second": 668.77
|
|
},
|
|
{
|
|
"epoch": 0.07979749276759884,
|
|
"grad_norm": 19.142763137817383,
|
|
"learning_rate": 0.0001969116094452887,
|
|
"loss": 1.7375894165039063,
|
|
"num_input_tokens_seen": 89847616,
|
|
"step": 82750,
|
|
"train_runtime": 134353.0051,
|
|
"train_tokens_per_second": 668.743
|
|
},
|
|
{
|
|
"epoch": 0.0798457087753134,
|
|
"grad_norm": 10.712233543395996,
|
|
"learning_rate": 0.0001969078710808022,
|
|
"loss": 1.6483206176757812,
|
|
"num_input_tokens_seen": 89885464,
|
|
"step": 82800,
|
|
"train_runtime": 134415.7663,
|
|
"train_tokens_per_second": 668.712
|
|
},
|
|
{
|
|
"epoch": 0.07989392478302797,
|
|
"grad_norm": 43.737060546875,
|
|
"learning_rate": 0.00019690413049064867,
|
|
"loss": 1.6884056091308595,
|
|
"num_input_tokens_seen": 89923616,
|
|
"step": 82850,
|
|
"train_runtime": 134478.9492,
|
|
"train_tokens_per_second": 668.682
|
|
},
|
|
{
|
|
"epoch": 0.07994214079074252,
|
|
"grad_norm": 17.125402450561523,
|
|
"learning_rate": 0.00019690038767491402,
|
|
"loss": 1.7277326965332032,
|
|
"num_input_tokens_seen": 89961616,
|
|
"step": 82900,
|
|
"train_runtime": 134541.2357,
|
|
"train_tokens_per_second": 668.655
|
|
},
|
|
{
|
|
"epoch": 0.07999035679845709,
|
|
"grad_norm": 32.730201721191406,
|
|
"learning_rate": 0.0001968966426336842,
|
|
"loss": 1.7102835083007812,
|
|
"num_input_tokens_seen": 89999240,
|
|
"step": 82950,
|
|
"train_runtime": 134603.0991,
|
|
"train_tokens_per_second": 668.627
|
|
},
|
|
{
|
|
"epoch": 0.08003857280617165,
|
|
"grad_norm": 43.71906280517578,
|
|
"learning_rate": 0.00019689289536704526,
|
|
"loss": 1.7237730407714844,
|
|
"num_input_tokens_seen": 90037000,
|
|
"step": 83000,
|
|
"train_runtime": 134666.7036,
|
|
"train_tokens_per_second": 668.591
|
|
},
|
|
{
|
|
"epoch": 0.08008678881388621,
|
|
"grad_norm": 12.198511123657227,
|
|
"learning_rate": 0.00019688914587508318,
|
|
"loss": 1.65608154296875,
|
|
"num_input_tokens_seen": 90074976,
|
|
"step": 83050,
|
|
"train_runtime": 134729.3964,
|
|
"train_tokens_per_second": 668.562
|
|
},
|
|
{
|
|
"epoch": 0.08013500482160077,
|
|
"grad_norm": 15.541620254516602,
|
|
"learning_rate": 0.0001968854692140349,
|
|
"loss": 1.8727328491210937,
|
|
"num_input_tokens_seen": 90111848,
|
|
"step": 83100,
|
|
"train_runtime": 134792.0094,
|
|
"train_tokens_per_second": 668.525
|
|
},
|
|
{
|
|
"epoch": 0.08018322082931534,
|
|
"grad_norm": 61.3888053894043,
|
|
"learning_rate": 0.0001968817153161872,
|
|
"loss": 1.6505682373046875,
|
|
"num_input_tokens_seen": 90148984,
|
|
"step": 83150,
|
|
"train_runtime": 134854.4242,
|
|
"train_tokens_per_second": 668.491
|
|
},
|
|
{
|
|
"epoch": 0.08023143683702989,
|
|
"grad_norm": 11.03419303894043,
|
|
"learning_rate": 0.00019687795919327324,
|
|
"loss": 1.7649166870117188,
|
|
"num_input_tokens_seen": 90186568,
|
|
"step": 83200,
|
|
"train_runtime": 134916.8711,
|
|
"train_tokens_per_second": 668.46
|
|
},
|
|
{
|
|
"epoch": 0.08027965284474446,
|
|
"grad_norm": 49.362369537353516,
|
|
"learning_rate": 0.00019687420084537919,
|
|
"loss": 1.7454061889648438,
|
|
"num_input_tokens_seen": 90224376,
|
|
"step": 83250,
|
|
"train_runtime": 134979.5253,
|
|
"train_tokens_per_second": 668.43
|
|
},
|
|
{
|
|
"epoch": 0.08032786885245902,
|
|
"grad_norm": 13.629351615905762,
|
|
"learning_rate": 0.00019687044027259142,
|
|
"loss": 1.6678732299804688,
|
|
"num_input_tokens_seen": 90262104,
|
|
"step": 83300,
|
|
"train_runtime": 135041.9194,
|
|
"train_tokens_per_second": 668.401
|
|
},
|
|
{
|
|
"epoch": 0.08037608486017357,
|
|
"grad_norm": 104.44023132324219,
|
|
"learning_rate": 0.00019686667747499626,
|
|
"loss": 1.7640708923339843,
|
|
"num_input_tokens_seen": 90300008,
|
|
"step": 83350,
|
|
"train_runtime": 135105.1552,
|
|
"train_tokens_per_second": 668.368
|
|
},
|
|
{
|
|
"epoch": 0.08042430086788814,
|
|
"grad_norm": 15.19701099395752,
|
|
"learning_rate": 0.00019686291245268019,
|
|
"loss": 1.7186843872070312,
|
|
"num_input_tokens_seen": 90337296,
|
|
"step": 83400,
|
|
"train_runtime": 135167.3107,
|
|
"train_tokens_per_second": 668.337
|
|
},
|
|
{
|
|
"epoch": 0.0804725168756027,
|
|
"grad_norm": 64.81535339355469,
|
|
"learning_rate": 0.00019685914520572962,
|
|
"loss": 1.687647705078125,
|
|
"num_input_tokens_seen": 90374640,
|
|
"step": 83450,
|
|
"train_runtime": 135229.2592,
|
|
"train_tokens_per_second": 668.307
|
|
},
|
|
{
|
|
"epoch": 0.08052073288331726,
|
|
"grad_norm": 16.126750946044922,
|
|
"learning_rate": 0.00019685537573423107,
|
|
"loss": 1.7700363159179688,
|
|
"num_input_tokens_seen": 90412864,
|
|
"step": 83500,
|
|
"train_runtime": 135292.2632,
|
|
"train_tokens_per_second": 668.278
|
|
},
|
|
{
|
|
"epoch": 0.08056894889103182,
|
|
"grad_norm": 10.85144329071045,
|
|
"learning_rate": 0.00019685160403827117,
|
|
"loss": 1.770706329345703,
|
|
"num_input_tokens_seen": 90450840,
|
|
"step": 83550,
|
|
"train_runtime": 135355.0264,
|
|
"train_tokens_per_second": 668.249
|
|
},
|
|
{
|
|
"epoch": 0.08061716489874639,
|
|
"grad_norm": 15.423821449279785,
|
|
"learning_rate": 0.00019684783011793652,
|
|
"loss": 1.6595510864257812,
|
|
"num_input_tokens_seen": 90488328,
|
|
"step": 83600,
|
|
"train_runtime": 135417.9166,
|
|
"train_tokens_per_second": 668.215
|
|
},
|
|
{
|
|
"epoch": 0.08066538090646094,
|
|
"grad_norm": 39.634639739990234,
|
|
"learning_rate": 0.00019684405397331375,
|
|
"loss": 1.7174977111816405,
|
|
"num_input_tokens_seen": 90526104,
|
|
"step": 83650,
|
|
"train_runtime": 135480.1858,
|
|
"train_tokens_per_second": 668.187
|
|
},
|
|
{
|
|
"epoch": 0.08071359691417551,
|
|
"grad_norm": 11.833749771118164,
|
|
"learning_rate": 0.00019684027560448963,
|
|
"loss": 1.7185308837890625,
|
|
"num_input_tokens_seen": 90564344,
|
|
"step": 83700,
|
|
"train_runtime": 135543.3162,
|
|
"train_tokens_per_second": 668.158
|
|
},
|
|
{
|
|
"epoch": 0.08076181292189007,
|
|
"grad_norm": 13.336162567138672,
|
|
"learning_rate": 0.00019683649501155097,
|
|
"loss": 1.6506166076660156,
|
|
"num_input_tokens_seen": 90602496,
|
|
"step": 83750,
|
|
"train_runtime": 135607.17,
|
|
"train_tokens_per_second": 668.125
|
|
},
|
|
{
|
|
"epoch": 0.08081002892960464,
|
|
"grad_norm": 13.081968307495117,
|
|
"learning_rate": 0.0001968327121945845,
|
|
"loss": 1.6781643676757811,
|
|
"num_input_tokens_seen": 90639760,
|
|
"step": 83800,
|
|
"train_runtime": 135669.4766,
|
|
"train_tokens_per_second": 668.093
|
|
},
|
|
{
|
|
"epoch": 0.08085824493731919,
|
|
"grad_norm": 20.746593475341797,
|
|
"learning_rate": 0.0001968289271536772,
|
|
"loss": 1.707708740234375,
|
|
"num_input_tokens_seen": 90677728,
|
|
"step": 83850,
|
|
"train_runtime": 135732.0726,
|
|
"train_tokens_per_second": 668.064
|
|
},
|
|
{
|
|
"epoch": 0.08090646094503375,
|
|
"grad_norm": 172.85472106933594,
|
|
"learning_rate": 0.00019682513988891596,
|
|
"loss": 1.8292526245117187,
|
|
"num_input_tokens_seen": 90715064,
|
|
"step": 83900,
|
|
"train_runtime": 135794.6551,
|
|
"train_tokens_per_second": 668.031
|
|
},
|
|
{
|
|
"epoch": 0.08095467695274831,
|
|
"grad_norm": 76.90861511230469,
|
|
"learning_rate": 0.00019682135040038773,
|
|
"loss": 1.8422512817382812,
|
|
"num_input_tokens_seen": 90752392,
|
|
"step": 83950,
|
|
"train_runtime": 135857.5645,
|
|
"train_tokens_per_second": 667.997
|
|
},
|
|
{
|
|
"epoch": 0.08100289296046287,
|
|
"grad_norm": 19.471181869506836,
|
|
"learning_rate": 0.00019681755868817958,
|
|
"loss": 1.7535917663574219,
|
|
"num_input_tokens_seen": 90790224,
|
|
"step": 84000,
|
|
"train_runtime": 135920.6402,
|
|
"train_tokens_per_second": 667.965
|
|
},
|
|
{
|
|
"epoch": 0.08105110896817744,
|
|
"grad_norm": 20.35093879699707,
|
|
"learning_rate": 0.00019681376475237858,
|
|
"loss": 1.73511474609375,
|
|
"num_input_tokens_seen": 90827712,
|
|
"step": 84050,
|
|
"train_runtime": 135983.7259,
|
|
"train_tokens_per_second": 667.931
|
|
},
|
|
{
|
|
"epoch": 0.08109932497589199,
|
|
"grad_norm": 17.25792694091797,
|
|
"learning_rate": 0.0001968099685930719,
|
|
"loss": 1.6874281311035155,
|
|
"num_input_tokens_seen": 90865608,
|
|
"step": 84100,
|
|
"train_runtime": 136046.2198,
|
|
"train_tokens_per_second": 667.902
|
|
},
|
|
{
|
|
"epoch": 0.08114754098360656,
|
|
"grad_norm": 39.73930740356445,
|
|
"learning_rate": 0.00019680617021034666,
|
|
"loss": 1.7328616333007814,
|
|
"num_input_tokens_seen": 90903544,
|
|
"step": 84150,
|
|
"train_runtime": 136108.879,
|
|
"train_tokens_per_second": 667.874
|
|
},
|
|
{
|
|
"epoch": 0.08119575699132112,
|
|
"grad_norm": 27.475812911987305,
|
|
"learning_rate": 0.00019680236960429017,
|
|
"loss": 1.7434776306152344,
|
|
"num_input_tokens_seen": 90941248,
|
|
"step": 84200,
|
|
"train_runtime": 136171.8555,
|
|
"train_tokens_per_second": 667.842
|
|
},
|
|
{
|
|
"epoch": 0.08124397299903569,
|
|
"grad_norm": 24.966508865356445,
|
|
"learning_rate": 0.00019679856677498963,
|
|
"loss": 1.9329527282714845,
|
|
"num_input_tokens_seen": 90978768,
|
|
"step": 84250,
|
|
"train_runtime": 136235.5515,
|
|
"train_tokens_per_second": 667.805
|
|
},
|
|
{
|
|
"epoch": 0.08129218900675024,
|
|
"grad_norm": 22.657312393188477,
|
|
"learning_rate": 0.0001967947617225325,
|
|
"loss": 1.7820355224609374,
|
|
"num_input_tokens_seen": 91017192,
|
|
"step": 84300,
|
|
"train_runtime": 136298.7644,
|
|
"train_tokens_per_second": 667.777
|
|
},
|
|
{
|
|
"epoch": 0.08134040501446481,
|
|
"grad_norm": 22.090200424194336,
|
|
"learning_rate": 0.00019679095444700604,
|
|
"loss": 1.76084716796875,
|
|
"num_input_tokens_seen": 91054800,
|
|
"step": 84350,
|
|
"train_runtime": 136361.1157,
|
|
"train_tokens_per_second": 667.748
|
|
},
|
|
{
|
|
"epoch": 0.08138862102217936,
|
|
"grad_norm": 26.35546875,
|
|
"learning_rate": 0.00019678714494849778,
|
|
"loss": 1.7822622680664062,
|
|
"num_input_tokens_seen": 91092600,
|
|
"step": 84400,
|
|
"train_runtime": 136424.5953,
|
|
"train_tokens_per_second": 667.714
|
|
},
|
|
{
|
|
"epoch": 0.08143683702989392,
|
|
"grad_norm": 16.49291229248047,
|
|
"learning_rate": 0.00019678333322709519,
|
|
"loss": 1.8073777770996093,
|
|
"num_input_tokens_seen": 91130608,
|
|
"step": 84450,
|
|
"train_runtime": 136487.7885,
|
|
"train_tokens_per_second": 667.683
|
|
},
|
|
{
|
|
"epoch": 0.08148505303760849,
|
|
"grad_norm": 29.86390495300293,
|
|
"learning_rate": 0.00019677951928288577,
|
|
"loss": 1.8153244018554688,
|
|
"num_input_tokens_seen": 91169392,
|
|
"step": 84500,
|
|
"train_runtime": 136551.0519,
|
|
"train_tokens_per_second": 667.658
|
|
},
|
|
{
|
|
"epoch": 0.08153326904532304,
|
|
"grad_norm": 71.58811950683594,
|
|
"learning_rate": 0.00019677577946107785,
|
|
"loss": 2.627565612792969,
|
|
"num_input_tokens_seen": 91207456,
|
|
"step": 84550,
|
|
"train_runtime": 136614.2747,
|
|
"train_tokens_per_second": 667.628
|
|
},
|
|
{
|
|
"epoch": 0.08158148505303761,
|
|
"grad_norm": 25.61164665222168,
|
|
"learning_rate": 0.00019677196111596946,
|
|
"loss": 1.817720947265625,
|
|
"num_input_tokens_seen": 91245112,
|
|
"step": 84600,
|
|
"train_runtime": 136677.3055,
|
|
"train_tokens_per_second": 667.595
|
|
},
|
|
{
|
|
"epoch": 0.08162970106075217,
|
|
"grad_norm": 57.19950485229492,
|
|
"learning_rate": 0.00019676814054831544,
|
|
"loss": 1.7935409545898438,
|
|
"num_input_tokens_seen": 91282928,
|
|
"step": 84650,
|
|
"train_runtime": 136740.0538,
|
|
"train_tokens_per_second": 667.565
|
|
},
|
|
{
|
|
"epoch": 0.08167791706846673,
|
|
"grad_norm": 20.451038360595703,
|
|
"learning_rate": 0.00019676431775820358,
|
|
"loss": 1.9633535766601562,
|
|
"num_input_tokens_seen": 91321416,
|
|
"step": 84700,
|
|
"train_runtime": 136803.0288,
|
|
"train_tokens_per_second": 667.539
|
|
},
|
|
{
|
|
"epoch": 0.08172613307618129,
|
|
"grad_norm": 493.6308288574219,
|
|
"learning_rate": 0.00019676049274572165,
|
|
"loss": 1.8138812255859376,
|
|
"num_input_tokens_seen": 91360024,
|
|
"step": 84750,
|
|
"train_runtime": 136865.9572,
|
|
"train_tokens_per_second": 667.515
|
|
},
|
|
{
|
|
"epoch": 0.08177434908389586,
|
|
"grad_norm": 27.020795822143555,
|
|
"learning_rate": 0.0001967566655109575,
|
|
"loss": 1.9643562316894532,
|
|
"num_input_tokens_seen": 91397904,
|
|
"step": 84800,
|
|
"train_runtime": 136928.589,
|
|
"train_tokens_per_second": 667.486
|
|
},
|
|
{
|
|
"epoch": 0.08182256509161041,
|
|
"grad_norm": 135.03921508789062,
|
|
"learning_rate": 0.00019675283605399902,
|
|
"loss": 1.9529893493652344,
|
|
"num_input_tokens_seen": 91435632,
|
|
"step": 84850,
|
|
"train_runtime": 136991.1709,
|
|
"train_tokens_per_second": 667.456
|
|
},
|
|
{
|
|
"epoch": 0.08187078109932498,
|
|
"grad_norm": 30.912315368652344,
|
|
"learning_rate": 0.0001967490043749342,
|
|
"loss": 1.9865872192382812,
|
|
"num_input_tokens_seen": 91474320,
|
|
"step": 84900,
|
|
"train_runtime": 137054.1041,
|
|
"train_tokens_per_second": 667.432
|
|
},
|
|
{
|
|
"epoch": 0.08191899710703954,
|
|
"grad_norm": 25.38758087158203,
|
|
"learning_rate": 0.000196745170473851,
|
|
"loss": 2.0917984008789063,
|
|
"num_input_tokens_seen": 91512464,
|
|
"step": 84950,
|
|
"train_runtime": 137116.5258,
|
|
"train_tokens_per_second": 667.407
|
|
},
|
|
{
|
|
"epoch": 0.08196721311475409,
|
|
"grad_norm": 29.224170684814453,
|
|
"learning_rate": 0.00019674133435083747,
|
|
"loss": 2.130809783935547,
|
|
"num_input_tokens_seen": 91550520,
|
|
"step": 85000,
|
|
"train_runtime": 137179.2684,
|
|
"train_tokens_per_second": 667.379
|
|
},
|
|
{
|
|
"epoch": 0.08201542912246866,
|
|
"grad_norm": 375.28460693359375,
|
|
"learning_rate": 0.0001967374960059817,
|
|
"loss": 2.0083052062988282,
|
|
"num_input_tokens_seen": 91589016,
|
|
"step": 85050,
|
|
"train_runtime": 137244.2666,
|
|
"train_tokens_per_second": 667.343
|
|
},
|
|
{
|
|
"epoch": 0.08206364513018322,
|
|
"grad_norm": 375.0728759765625,
|
|
"learning_rate": 0.0001967336554393719,
|
|
"loss": 2.331800079345703,
|
|
"num_input_tokens_seen": 91627776,
|
|
"step": 85100,
|
|
"train_runtime": 137307.4001,
|
|
"train_tokens_per_second": 667.319
|
|
},
|
|
{
|
|
"epoch": 0.08211186113789778,
|
|
"grad_norm": 28.68709945678711,
|
|
"learning_rate": 0.00019672981265109627,
|
|
"loss": 2.6570223999023437,
|
|
"num_input_tokens_seen": 91664728,
|
|
"step": 85150,
|
|
"train_runtime": 137370.2119,
|
|
"train_tokens_per_second": 667.282
|
|
},
|
|
{
|
|
"epoch": 0.08216007714561234,
|
|
"grad_norm": 21.744661331176758,
|
|
"learning_rate": 0.000196725967641243,
|
|
"loss": 2.0556231689453126,
|
|
"num_input_tokens_seen": 91702784,
|
|
"step": 85200,
|
|
"train_runtime": 137433.1999,
|
|
"train_tokens_per_second": 667.254
|
|
},
|
|
{
|
|
"epoch": 0.08220829315332691,
|
|
"grad_norm": 585.04248046875,
|
|
"learning_rate": 0.00019672212040990048,
|
|
"loss": 2.760245361328125,
|
|
"num_input_tokens_seen": 91741424,
|
|
"step": 85250,
|
|
"train_runtime": 137496.4082,
|
|
"train_tokens_per_second": 667.228
|
|
},
|
|
{
|
|
"epoch": 0.08225650916104146,
|
|
"grad_norm": 52.565738677978516,
|
|
"learning_rate": 0.00019671842497791654,
|
|
"loss": 6.075245971679688,
|
|
"num_input_tokens_seen": 91779312,
|
|
"step": 85300,
|
|
"train_runtime": 137559.0038,
|
|
"train_tokens_per_second": 667.2
|
|
},
|
|
{
|
|
"epoch": 0.08230472516875603,
|
|
"grad_norm": 15.191622734069824,
|
|
"learning_rate": 0.00019671457339271136,
|
|
"loss": 5.699826049804687,
|
|
"num_input_tokens_seen": 91818008,
|
|
"step": 85350,
|
|
"train_runtime": 137621.4735,
|
|
"train_tokens_per_second": 667.178
|
|
},
|
|
{
|
|
"epoch": 0.08235294117647059,
|
|
"grad_norm": 46.97722625732422,
|
|
"learning_rate": 0.0001967107195862786,
|
|
"loss": 4.9015023803710935,
|
|
"num_input_tokens_seen": 91856848,
|
|
"step": 85400,
|
|
"train_runtime": 137684.161,
|
|
"train_tokens_per_second": 667.156
|
|
},
|
|
{
|
|
"epoch": 0.08240115718418516,
|
|
"grad_norm": 82.7729721069336,
|
|
"learning_rate": 0.00019670686355870672,
|
|
"loss": 3.0319232177734374,
|
|
"num_input_tokens_seen": 91893984,
|
|
"step": 85450,
|
|
"train_runtime": 137746.514,
|
|
"train_tokens_per_second": 667.124
|
|
},
|
|
{
|
|
"epoch": 0.08244937319189971,
|
|
"grad_norm": 47.85222625732422,
|
|
"learning_rate": 0.00019670300531008433,
|
|
"loss": 2.221375274658203,
|
|
"num_input_tokens_seen": 91931080,
|
|
"step": 85500,
|
|
"train_runtime": 137809.5766,
|
|
"train_tokens_per_second": 667.088
|
|
},
|
|
{
|
|
"epoch": 0.08249758919961427,
|
|
"grad_norm": 70.77473449707031,
|
|
"learning_rate": 0.0001966991448405,
|
|
"loss": 2.1113035583496096,
|
|
"num_input_tokens_seen": 91969144,
|
|
"step": 85550,
|
|
"train_runtime": 137871.7411,
|
|
"train_tokens_per_second": 667.063
|
|
},
|
|
{
|
|
"epoch": 0.08254580520732883,
|
|
"grad_norm": 227.17379760742188,
|
|
"learning_rate": 0.00019669528215004244,
|
|
"loss": 2.2623422241210935,
|
|
"num_input_tokens_seen": 92007240,
|
|
"step": 85600,
|
|
"train_runtime": 137934.1098,
|
|
"train_tokens_per_second": 667.038
|
|
},
|
|
{
|
|
"epoch": 0.08259402121504339,
|
|
"grad_norm": 45.706424713134766,
|
|
"learning_rate": 0.00019669141723880034,
|
|
"loss": 2.2700762939453125,
|
|
"num_input_tokens_seen": 92045104,
|
|
"step": 85650,
|
|
"train_runtime": 137996.8635,
|
|
"train_tokens_per_second": 667.009
|
|
},
|
|
{
|
|
"epoch": 0.08264223722275796,
|
|
"grad_norm": 90.3950424194336,
|
|
"learning_rate": 0.00019668755010686243,
|
|
"loss": 2.2854454040527346,
|
|
"num_input_tokens_seen": 92082512,
|
|
"step": 85700,
|
|
"train_runtime": 138059.5214,
|
|
"train_tokens_per_second": 666.977
|
|
},
|
|
{
|
|
"epoch": 0.08269045323047251,
|
|
"grad_norm": 11.497991561889648,
|
|
"learning_rate": 0.00019668383557105393,
|
|
"loss": 3.1636163330078126,
|
|
"num_input_tokens_seen": 92120200,
|
|
"step": 85750,
|
|
"train_runtime": 138122.1113,
|
|
"train_tokens_per_second": 666.948
|
|
},
|
|
{
|
|
"epoch": 0.08273866923818708,
|
|
"grad_norm": 41.857852935791016,
|
|
"learning_rate": 0.00019667996408681004,
|
|
"loss": 3.2000531005859374,
|
|
"num_input_tokens_seen": 92157952,
|
|
"step": 85800,
|
|
"train_runtime": 138184.4124,
|
|
"train_tokens_per_second": 666.92
|
|
},
|
|
{
|
|
"epoch": 0.08278688524590164,
|
|
"grad_norm": 13.03602123260498,
|
|
"learning_rate": 0.00019667609038213338,
|
|
"loss": 2.4989633178710937,
|
|
"num_input_tokens_seen": 92196384,
|
|
"step": 85850,
|
|
"train_runtime": 138246.8216,
|
|
"train_tokens_per_second": 666.897
|
|
},
|
|
{
|
|
"epoch": 0.0828351012536162,
|
|
"grad_norm": 25.592313766479492,
|
|
"learning_rate": 0.00019667221445711296,
|
|
"loss": 2.0033944702148436,
|
|
"num_input_tokens_seen": 92234352,
|
|
"step": 85900,
|
|
"train_runtime": 138309.6484,
|
|
"train_tokens_per_second": 666.869
|
|
},
|
|
{
|
|
"epoch": 0.08288331726133076,
|
|
"grad_norm": 21.592496871948242,
|
|
"learning_rate": 0.0001966683363118378,
|
|
"loss": 2.164889373779297,
|
|
"num_input_tokens_seen": 92272592,
|
|
"step": 85950,
|
|
"train_runtime": 138372.3301,
|
|
"train_tokens_per_second": 666.843
|
|
},
|
|
{
|
|
"epoch": 0.08293153326904533,
|
|
"grad_norm": 28.296932220458984,
|
|
"learning_rate": 0.00019666445594639697,
|
|
"loss": 1.9384934997558594,
|
|
"num_input_tokens_seen": 92310200,
|
|
"step": 86000,
|
|
"train_runtime": 138434.7416,
|
|
"train_tokens_per_second": 666.814
|
|
},
|
|
{
|
|
"epoch": 0.08297974927675988,
|
|
"grad_norm": 103.93315887451172,
|
|
"learning_rate": 0.00019666057336087958,
|
|
"loss": 2.409370880126953,
|
|
"num_input_tokens_seen": 92349448,
|
|
"step": 86050,
|
|
"train_runtime": 138497.6062,
|
|
"train_tokens_per_second": 666.795
|
|
},
|
|
{
|
|
"epoch": 0.08302796528447444,
|
|
"grad_norm": 68.04676055908203,
|
|
"learning_rate": 0.0001966566885553748,
|
|
"loss": 2.502145080566406,
|
|
"num_input_tokens_seen": 92387768,
|
|
"step": 86100,
|
|
"train_runtime": 138559.7641,
|
|
"train_tokens_per_second": 666.772
|
|
},
|
|
{
|
|
"epoch": 0.08307618129218901,
|
|
"grad_norm": 27.975011825561523,
|
|
"learning_rate": 0.00019665280152997183,
|
|
"loss": 1.9932575988769532,
|
|
"num_input_tokens_seen": 92425504,
|
|
"step": 86150,
|
|
"train_runtime": 138622.0379,
|
|
"train_tokens_per_second": 666.745
|
|
},
|
|
{
|
|
"epoch": 0.08312439729990356,
|
|
"grad_norm": 885.506591796875,
|
|
"learning_rate": 0.00019664891228476,
|
|
"loss": 3.3376425170898436,
|
|
"num_input_tokens_seen": 92462920,
|
|
"step": 86200,
|
|
"train_runtime": 138684.2745,
|
|
"train_tokens_per_second": 666.715
|
|
},
|
|
{
|
|
"epoch": 0.08317261330761813,
|
|
"grad_norm": 17.933536529541016,
|
|
"learning_rate": 0.0001966450208198286,
|
|
"loss": 5.69486083984375,
|
|
"num_input_tokens_seen": 92501024,
|
|
"step": 86250,
|
|
"train_runtime": 138746.6958,
|
|
"train_tokens_per_second": 666.69
|
|
},
|
|
{
|
|
"epoch": 0.08322082931533269,
|
|
"grad_norm": 20.765270233154297,
|
|
"learning_rate": 0.00019664112713526697,
|
|
"loss": 5.101023254394531,
|
|
"num_input_tokens_seen": 92539336,
|
|
"step": 86300,
|
|
"train_runtime": 138809.4052,
|
|
"train_tokens_per_second": 666.665
|
|
},
|
|
{
|
|
"epoch": 0.08326904532304726,
|
|
"grad_norm": 17.33600616455078,
|
|
"learning_rate": 0.00019663723123116458,
|
|
"loss": 4.699594421386719,
|
|
"num_input_tokens_seen": 92576536,
|
|
"step": 86350,
|
|
"train_runtime": 138871.7559,
|
|
"train_tokens_per_second": 666.633
|
|
},
|
|
{
|
|
"epoch": 0.08331726133076181,
|
|
"grad_norm": 133.6848907470703,
|
|
"learning_rate": 0.0001966333331076109,
|
|
"loss": 2.650348815917969,
|
|
"num_input_tokens_seen": 92614504,
|
|
"step": 86400,
|
|
"train_runtime": 138933.8315,
|
|
"train_tokens_per_second": 666.609
|
|
},
|
|
{
|
|
"epoch": 0.08336547733847638,
|
|
"grad_norm": 104.51781463623047,
|
|
"learning_rate": 0.00019662943276469545,
|
|
"loss": 2.79870361328125,
|
|
"num_input_tokens_seen": 92652440,
|
|
"step": 86450,
|
|
"train_runtime": 138995.9664,
|
|
"train_tokens_per_second": 666.584
|
|
},
|
|
{
|
|
"epoch": 0.08341369334619093,
|
|
"grad_norm": 62.063018798828125,
|
|
"learning_rate": 0.00019662553020250782,
|
|
"loss": 2.3658953857421876,
|
|
"num_input_tokens_seen": 92690992,
|
|
"step": 86500,
|
|
"train_runtime": 139058.9831,
|
|
"train_tokens_per_second": 666.559
|
|
},
|
|
{
|
|
"epoch": 0.0834619093539055,
|
|
"grad_norm": 33.44969177246094,
|
|
"learning_rate": 0.00019662162542113764,
|
|
"loss": 2.3223541259765623,
|
|
"num_input_tokens_seen": 92729840,
|
|
"step": 86550,
|
|
"train_runtime": 139121.4604,
|
|
"train_tokens_per_second": 666.539
|
|
},
|
|
{
|
|
"epoch": 0.08351012536162006,
|
|
"grad_norm": 31.876474380493164,
|
|
"learning_rate": 0.00019661771842067454,
|
|
"loss": 2.0832980346679686,
|
|
"num_input_tokens_seen": 92768408,
|
|
"step": 86600,
|
|
"train_runtime": 139184.0805,
|
|
"train_tokens_per_second": 666.516
|
|
},
|
|
{
|
|
"epoch": 0.08355834136933461,
|
|
"grad_norm": 6588.07568359375,
|
|
"learning_rate": 0.00019661380920120834,
|
|
"loss": 2.224429473876953,
|
|
"num_input_tokens_seen": 92806504,
|
|
"step": 86650,
|
|
"train_runtime": 139246.3306,
|
|
"train_tokens_per_second": 666.492
|
|
},
|
|
{
|
|
"epoch": 0.08360655737704918,
|
|
"grad_norm": 123.77045440673828,
|
|
"learning_rate": 0.0001966098977628288,
|
|
"loss": 3.864566650390625,
|
|
"num_input_tokens_seen": 92844448,
|
|
"step": 86700,
|
|
"train_runtime": 139309.0259,
|
|
"train_tokens_per_second": 666.464
|
|
},
|
|
{
|
|
"epoch": 0.08365477338476374,
|
|
"grad_norm": 33.68782424926758,
|
|
"learning_rate": 0.00019660598410562566,
|
|
"loss": 3.129827880859375,
|
|
"num_input_tokens_seen": 92882496,
|
|
"step": 86750,
|
|
"train_runtime": 139372.4507,
|
|
"train_tokens_per_second": 666.434
|
|
},
|
|
{
|
|
"epoch": 0.0837029893924783,
|
|
"grad_norm": 614.4100952148438,
|
|
"learning_rate": 0.00019660206822968892,
|
|
"loss": 2.5974932861328126,
|
|
"num_input_tokens_seen": 92919872,
|
|
"step": 86800,
|
|
"train_runtime": 139434.6498,
|
|
"train_tokens_per_second": 666.404
|
|
},
|
|
{
|
|
"epoch": 0.08375120540019286,
|
|
"grad_norm": 24.125835418701172,
|
|
"learning_rate": 0.00019659815013510845,
|
|
"loss": 2.3694085693359375,
|
|
"num_input_tokens_seen": 92957816,
|
|
"step": 86850,
|
|
"train_runtime": 139497.4845,
|
|
"train_tokens_per_second": 666.376
|
|
},
|
|
{
|
|
"epoch": 0.08379942140790743,
|
|
"grad_norm": 1031.843017578125,
|
|
"learning_rate": 0.00019659422982197427,
|
|
"loss": 2.2109274291992187,
|
|
"num_input_tokens_seen": 92996424,
|
|
"step": 86900,
|
|
"train_runtime": 139560.4244,
|
|
"train_tokens_per_second": 666.352
|
|
},
|
|
{
|
|
"epoch": 0.08384763741562198,
|
|
"grad_norm": 35.79362487792969,
|
|
"learning_rate": 0.0001965903072903764,
|
|
"loss": 2.236078643798828,
|
|
"num_input_tokens_seen": 93033800,
|
|
"step": 86950,
|
|
"train_runtime": 139622.5051,
|
|
"train_tokens_per_second": 666.324
|
|
},
|
|
{
|
|
"epoch": 0.08389585342333655,
|
|
"grad_norm": 124.81338500976562,
|
|
"learning_rate": 0.0001965863825404049,
|
|
"loss": 2.1719297790527343,
|
|
"num_input_tokens_seen": 93072008,
|
|
"step": 87000,
|
|
"train_runtime": 139685.7326,
|
|
"train_tokens_per_second": 666.296
|
|
},
|
|
{
|
|
"epoch": 0.08394406943105111,
|
|
"grad_norm": 21.301124572753906,
|
|
"learning_rate": 0.00019658245557214996,
|
|
"loss": 2.1525999450683595,
|
|
"num_input_tokens_seen": 93110040,
|
|
"step": 87050,
|
|
"train_runtime": 139748.7655,
|
|
"train_tokens_per_second": 666.267
|
|
},
|
|
{
|
|
"epoch": 0.08399228543876568,
|
|
"grad_norm": 102.71510314941406,
|
|
"learning_rate": 0.00019657852638570175,
|
|
"loss": 2.796351013183594,
|
|
"num_input_tokens_seen": 93148472,
|
|
"step": 87100,
|
|
"train_runtime": 139812.3319,
|
|
"train_tokens_per_second": 666.239
|
|
},
|
|
{
|
|
"epoch": 0.08404050144648023,
|
|
"grad_norm": 46.356536865234375,
|
|
"learning_rate": 0.0001965745949811505,
|
|
"loss": 2.9499160766601564,
|
|
"num_input_tokens_seen": 93186232,
|
|
"step": 87150,
|
|
"train_runtime": 139874.6031,
|
|
"train_tokens_per_second": 666.213
|
|
},
|
|
{
|
|
"epoch": 0.08408871745419479,
|
|
"grad_norm": 62.57208251953125,
|
|
"learning_rate": 0.00019657066135858657,
|
|
"loss": 2.2330291748046873,
|
|
"num_input_tokens_seen": 93224544,
|
|
"step": 87200,
|
|
"train_runtime": 139937.1673,
|
|
"train_tokens_per_second": 666.189
|
|
},
|
|
{
|
|
"epoch": 0.08413693346190936,
|
|
"grad_norm": 60.99797439575195,
|
|
"learning_rate": 0.0001965667255181002,
|
|
"loss": 2.052478485107422,
|
|
"num_input_tokens_seen": 93263264,
|
|
"step": 87250,
|
|
"train_runtime": 139999.9136,
|
|
"train_tokens_per_second": 666.167
|
|
},
|
|
{
|
|
"epoch": 0.08418514946962391,
|
|
"grad_norm": 10.081340789794922,
|
|
"learning_rate": 0.00019656278745978182,
|
|
"loss": 2.090927734375,
|
|
"num_input_tokens_seen": 93301328,
|
|
"step": 87300,
|
|
"train_runtime": 140062.967,
|
|
"train_tokens_per_second": 666.138
|
|
},
|
|
{
|
|
"epoch": 0.08423336547733848,
|
|
"grad_norm": 17.019058227539062,
|
|
"learning_rate": 0.0001965588471837219,
|
|
"loss": 1.9947555541992188,
|
|
"num_input_tokens_seen": 93339392,
|
|
"step": 87350,
|
|
"train_runtime": 140126.1136,
|
|
"train_tokens_per_second": 666.11
|
|
},
|
|
{
|
|
"epoch": 0.08428158148505303,
|
|
"grad_norm": 32.65163040161133,
|
|
"learning_rate": 0.0001965549046900109,
|
|
"loss": 2.1525816345214843,
|
|
"num_input_tokens_seen": 93377136,
|
|
"step": 87400,
|
|
"train_runtime": 140188.4765,
|
|
"train_tokens_per_second": 666.083
|
|
},
|
|
{
|
|
"epoch": 0.0843297974927676,
|
|
"grad_norm": 53.23382568359375,
|
|
"learning_rate": 0.0001965509599787394,
|
|
"loss": 2.1538970947265623,
|
|
"num_input_tokens_seen": 93415352,
|
|
"step": 87450,
|
|
"train_runtime": 140251.6229,
|
|
"train_tokens_per_second": 666.055
|
|
},
|
|
{
|
|
"epoch": 0.08437801350048216,
|
|
"grad_norm": 14.842714309692383,
|
|
"learning_rate": 0.000196547013049998,
|
|
"loss": 2.0462786865234377,
|
|
"num_input_tokens_seen": 93453328,
|
|
"step": 87500,
|
|
"train_runtime": 140314.6574,
|
|
"train_tokens_per_second": 666.027
|
|
},
|
|
{
|
|
"epoch": 0.08442622950819673,
|
|
"grad_norm": 18.013263702392578,
|
|
"learning_rate": 0.0001965430639038773,
|
|
"loss": 2.063346252441406,
|
|
"num_input_tokens_seen": 93491792,
|
|
"step": 87550,
|
|
"train_runtime": 140377.0303,
|
|
"train_tokens_per_second": 666.005
|
|
},
|
|
{
|
|
"epoch": 0.08447444551591128,
|
|
"grad_norm": 1242.1142578125,
|
|
"learning_rate": 0.0001965391125404681,
|
|
"loss": 2.03843505859375,
|
|
"num_input_tokens_seen": 93530328,
|
|
"step": 87600,
|
|
"train_runtime": 140439.4247,
|
|
"train_tokens_per_second": 665.983
|
|
},
|
|
{
|
|
"epoch": 0.08452266152362585,
|
|
"grad_norm": 27.412525177001953,
|
|
"learning_rate": 0.00019653515895986102,
|
|
"loss": 2.2536045837402345,
|
|
"num_input_tokens_seen": 93567536,
|
|
"step": 87650,
|
|
"train_runtime": 140501.7111,
|
|
"train_tokens_per_second": 665.953
|
|
},
|
|
{
|
|
"epoch": 0.0845708775313404,
|
|
"grad_norm": 27.58529281616211,
|
|
"learning_rate": 0.00019653120316214692,
|
|
"loss": 2.0490589904785157,
|
|
"num_input_tokens_seen": 93605400,
|
|
"step": 87700,
|
|
"train_runtime": 140565.2114,
|
|
"train_tokens_per_second": 665.922
|
|
},
|
|
{
|
|
"epoch": 0.08461909353905496,
|
|
"grad_norm": 14.992999076843262,
|
|
"learning_rate": 0.00019652724514741666,
|
|
"loss": 2.060832672119141,
|
|
"num_input_tokens_seen": 93643760,
|
|
"step": 87750,
|
|
"train_runtime": 140628.3892,
|
|
"train_tokens_per_second": 665.895
|
|
},
|
|
{
|
|
"epoch": 0.08466730954676953,
|
|
"grad_norm": 27.048660278320312,
|
|
"learning_rate": 0.00019652328491576117,
|
|
"loss": 2.0742671203613283,
|
|
"num_input_tokens_seen": 93681640,
|
|
"step": 87800,
|
|
"train_runtime": 140691.804,
|
|
"train_tokens_per_second": 665.864
|
|
},
|
|
{
|
|
"epoch": 0.08471552555448408,
|
|
"grad_norm": 14.083191871643066,
|
|
"learning_rate": 0.00019651932246727137,
|
|
"loss": 2.022095031738281,
|
|
"num_input_tokens_seen": 93720016,
|
|
"step": 87850,
|
|
"train_runtime": 140754.6234,
|
|
"train_tokens_per_second": 665.84
|
|
},
|
|
{
|
|
"epoch": 0.08476374156219865,
|
|
"grad_norm": 17.050949096679688,
|
|
"learning_rate": 0.0001965153578020382,
|
|
"loss": 2.0323236083984373,
|
|
"num_input_tokens_seen": 93757576,
|
|
"step": 87900,
|
|
"train_runtime": 140817.9554,
|
|
"train_tokens_per_second": 665.807
|
|
},
|
|
{
|
|
"epoch": 0.08481195756991321,
|
|
"grad_norm": 16.753742218017578,
|
|
"learning_rate": 0.00019651139092015285,
|
|
"loss": 2.130159454345703,
|
|
"num_input_tokens_seen": 93795120,
|
|
"step": 87950,
|
|
"train_runtime": 140880.2506,
|
|
"train_tokens_per_second": 665.779
|
|
},
|
|
{
|
|
"epoch": 0.08486017357762778,
|
|
"grad_norm": 21.802602767944336,
|
|
"learning_rate": 0.00019650742182170637,
|
|
"loss": 2.0435951232910154,
|
|
"num_input_tokens_seen": 93832424,
|
|
"step": 88000,
|
|
"train_runtime": 140943.2815,
|
|
"train_tokens_per_second": 665.746
|
|
},
|
|
{
|
|
"epoch": 0.08490838958534233,
|
|
"grad_norm": 29.80690574645996,
|
|
"learning_rate": 0.00019650345050678986,
|
|
"loss": 2.0551606750488283,
|
|
"num_input_tokens_seen": 93870736,
|
|
"step": 88050,
|
|
"train_runtime": 141005.8003,
|
|
"train_tokens_per_second": 665.723
|
|
},
|
|
{
|
|
"epoch": 0.0849566055930569,
|
|
"grad_norm": 11.846317291259766,
|
|
"learning_rate": 0.0001964994769754946,
|
|
"loss": 2.056718292236328,
|
|
"num_input_tokens_seen": 93909016,
|
|
"step": 88100,
|
|
"train_runtime": 141068.4243,
|
|
"train_tokens_per_second": 665.698
|
|
},
|
|
{
|
|
"epoch": 0.08500482160077145,
|
|
"grad_norm": 17.201017379760742,
|
|
"learning_rate": 0.0001964955012279118,
|
|
"loss": 2.027194061279297,
|
|
"num_input_tokens_seen": 93947088,
|
|
"step": 88150,
|
|
"train_runtime": 141131.114,
|
|
"train_tokens_per_second": 665.672
|
|
},
|
|
{
|
|
"epoch": 0.08505303760848602,
|
|
"grad_norm": 22.550302505493164,
|
|
"learning_rate": 0.00019649152326413284,
|
|
"loss": 2.0317108154296877,
|
|
"num_input_tokens_seen": 93986040,
|
|
"step": 88200,
|
|
"train_runtime": 141193.8888,
|
|
"train_tokens_per_second": 665.652
|
|
},
|
|
{
|
|
"epoch": 0.08510125361620058,
|
|
"grad_norm": 15.69747257232666,
|
|
"learning_rate": 0.000196487543084249,
|
|
"loss": 2.023460693359375,
|
|
"num_input_tokens_seen": 94023112,
|
|
"step": 88250,
|
|
"train_runtime": 141256.7573,
|
|
"train_tokens_per_second": 665.619
|
|
},
|
|
{
|
|
"epoch": 0.08514946962391513,
|
|
"grad_norm": 40.05237579345703,
|
|
"learning_rate": 0.00019648356068835177,
|
|
"loss": 2.0463304138183593,
|
|
"num_input_tokens_seen": 94061072,
|
|
"step": 88300,
|
|
"train_runtime": 141319.9843,
|
|
"train_tokens_per_second": 665.589
|
|
},
|
|
{
|
|
"epoch": 0.0851976856316297,
|
|
"grad_norm": 44.233463287353516,
|
|
"learning_rate": 0.00019647957607653253,
|
|
"loss": 2.0270234680175783,
|
|
"num_input_tokens_seen": 94098664,
|
|
"step": 88350,
|
|
"train_runtime": 141382.9098,
|
|
"train_tokens_per_second": 665.559
|
|
},
|
|
{
|
|
"epoch": 0.08524590163934426,
|
|
"grad_norm": 77.29163360595703,
|
|
"learning_rate": 0.00019647558924888286,
|
|
"loss": 2.113689117431641,
|
|
"num_input_tokens_seen": 94137080,
|
|
"step": 88400,
|
|
"train_runtime": 141445.8986,
|
|
"train_tokens_per_second": 665.534
|
|
},
|
|
{
|
|
"epoch": 0.08529411764705883,
|
|
"grad_norm": 21.641651153564453,
|
|
"learning_rate": 0.00019647160020549428,
|
|
"loss": 1.9762701416015624,
|
|
"num_input_tokens_seen": 94175032,
|
|
"step": 88450,
|
|
"train_runtime": 141508.6515,
|
|
"train_tokens_per_second": 665.507
|
|
},
|
|
{
|
|
"epoch": 0.08534233365477338,
|
|
"grad_norm": 27.20618438720703,
|
|
"learning_rate": 0.00019646760894645847,
|
|
"loss": 2.0197413635253905,
|
|
"num_input_tokens_seen": 94213424,
|
|
"step": 88500,
|
|
"train_runtime": 141571.9609,
|
|
"train_tokens_per_second": 665.481
|
|
},
|
|
{
|
|
"epoch": 0.08539054966248795,
|
|
"grad_norm": 12.198922157287598,
|
|
"learning_rate": 0.000196463615471867,
|
|
"loss": 1.9360966491699219,
|
|
"num_input_tokens_seen": 94251568,
|
|
"step": 88550,
|
|
"train_runtime": 141634.6823,
|
|
"train_tokens_per_second": 665.455
|
|
},
|
|
{
|
|
"epoch": 0.0854387656702025,
|
|
"grad_norm": 15.237981796264648,
|
|
"learning_rate": 0.00019645961978181166,
|
|
"loss": 2.22507080078125,
|
|
"num_input_tokens_seen": 94289328,
|
|
"step": 88600,
|
|
"train_runtime": 141697.1569,
|
|
"train_tokens_per_second": 665.429
|
|
},
|
|
{
|
|
"epoch": 0.08548698167791707,
|
|
"grad_norm": 11.601311683654785,
|
|
"learning_rate": 0.0001964556218763842,
|
|
"loss": 1.93480224609375,
|
|
"num_input_tokens_seen": 94327264,
|
|
"step": 88650,
|
|
"train_runtime": 141760.1725,
|
|
"train_tokens_per_second": 665.4
|
|
},
|
|
{
|
|
"epoch": 0.08553519768563163,
|
|
"grad_norm": 8.9138765335083,
|
|
"learning_rate": 0.00019645162175567645,
|
|
"loss": 1.9276145935058593,
|
|
"num_input_tokens_seen": 94365864,
|
|
"step": 88700,
|
|
"train_runtime": 141822.5265,
|
|
"train_tokens_per_second": 665.38
|
|
},
|
|
{
|
|
"epoch": 0.0855834136933462,
|
|
"grad_norm": 19.912460327148438,
|
|
"learning_rate": 0.00019644761941978026,
|
|
"loss": 1.91871826171875,
|
|
"num_input_tokens_seen": 94403296,
|
|
"step": 88750,
|
|
"train_runtime": 141885.3609,
|
|
"train_tokens_per_second": 665.349
|
|
},
|
|
{
|
|
"epoch": 0.08563162970106075,
|
|
"grad_norm": 14.381782531738281,
|
|
"learning_rate": 0.00019644361486878756,
|
|
"loss": 1.9587416076660156,
|
|
"num_input_tokens_seen": 94441792,
|
|
"step": 88800,
|
|
"train_runtime": 141947.6649,
|
|
"train_tokens_per_second": 665.328
|
|
},
|
|
{
|
|
"epoch": 0.0856798457087753,
|
|
"grad_norm": 10.847372055053711,
|
|
"learning_rate": 0.0001964396081027903,
|
|
"loss": 1.892574462890625,
|
|
"num_input_tokens_seen": 94479664,
|
|
"step": 88850,
|
|
"train_runtime": 142010.4005,
|
|
"train_tokens_per_second": 665.301
|
|
},
|
|
{
|
|
"epoch": 0.08572806171648988,
|
|
"grad_norm": 56.03398513793945,
|
|
"learning_rate": 0.00019643559912188056,
|
|
"loss": 1.9652487182617187,
|
|
"num_input_tokens_seen": 94517600,
|
|
"step": 88900,
|
|
"train_runtime": 142073.236,
|
|
"train_tokens_per_second": 665.274
|
|
},
|
|
{
|
|
"epoch": 0.08577627772420443,
|
|
"grad_norm": 20.00489044189453,
|
|
"learning_rate": 0.00019643158792615037,
|
|
"loss": 1.96383056640625,
|
|
"num_input_tokens_seen": 94554840,
|
|
"step": 88950,
|
|
"train_runtime": 142135.9416,
|
|
"train_tokens_per_second": 665.242
|
|
},
|
|
{
|
|
"epoch": 0.085824493731919,
|
|
"grad_norm": 9.221293449401855,
|
|
"learning_rate": 0.00019642757451569185,
|
|
"loss": 1.862859344482422,
|
|
"num_input_tokens_seen": 94592496,
|
|
"step": 89000,
|
|
"train_runtime": 142199.2531,
|
|
"train_tokens_per_second": 665.211
|
|
},
|
|
{
|
|
"epoch": 0.08587270973963355,
|
|
"grad_norm": 13.038932800292969,
|
|
"learning_rate": 0.0001964235588905972,
|
|
"loss": 1.915480499267578,
|
|
"num_input_tokens_seen": 94630944,
|
|
"step": 89050,
|
|
"train_runtime": 142262.1235,
|
|
"train_tokens_per_second": 665.187
|
|
},
|
|
{
|
|
"epoch": 0.08592092574734812,
|
|
"grad_norm": 11.969846725463867,
|
|
"learning_rate": 0.0001964195410509586,
|
|
"loss": 1.9390151977539063,
|
|
"num_input_tokens_seen": 94668360,
|
|
"step": 89100,
|
|
"train_runtime": 142324.6962,
|
|
"train_tokens_per_second": 665.158
|
|
},
|
|
{
|
|
"epoch": 0.08596914175506268,
|
|
"grad_norm": 10.87924861907959,
|
|
"learning_rate": 0.0001964155209968684,
|
|
"loss": 1.948747100830078,
|
|
"num_input_tokens_seen": 94705664,
|
|
"step": 89150,
|
|
"train_runtime": 142386.9437,
|
|
"train_tokens_per_second": 665.129
|
|
},
|
|
{
|
|
"epoch": 0.08601735776277725,
|
|
"grad_norm": 12.821775436401367,
|
|
"learning_rate": 0.00019641149872841887,
|
|
"loss": 1.9093887329101562,
|
|
"num_input_tokens_seen": 94743768,
|
|
"step": 89200,
|
|
"train_runtime": 142450.0502,
|
|
"train_tokens_per_second": 665.102
|
|
},
|
|
{
|
|
"epoch": 0.0860655737704918,
|
|
"grad_norm": 16.25474739074707,
|
|
"learning_rate": 0.0001964074742457024,
|
|
"loss": 1.85373291015625,
|
|
"num_input_tokens_seen": 94781736,
|
|
"step": 89250,
|
|
"train_runtime": 142513.2973,
|
|
"train_tokens_per_second": 665.073
|
|
},
|
|
{
|
|
"epoch": 0.08611378977820637,
|
|
"grad_norm": 13.100603103637695,
|
|
"learning_rate": 0.00019640344754881146,
|
|
"loss": 1.9385955810546875,
|
|
"num_input_tokens_seen": 94819504,
|
|
"step": 89300,
|
|
"train_runtime": 142575.8428,
|
|
"train_tokens_per_second": 665.046
|
|
},
|
|
{
|
|
"epoch": 0.08616200578592093,
|
|
"grad_norm": 13.915572166442871,
|
|
"learning_rate": 0.0001963994186378385,
|
|
"loss": 1.8920968627929688,
|
|
"num_input_tokens_seen": 94857304,
|
|
"step": 89350,
|
|
"train_runtime": 142638.4655,
|
|
"train_tokens_per_second": 665.019
|
|
},
|
|
{
|
|
"epoch": 0.08621022179363548,
|
|
"grad_norm": 10.605253219604492,
|
|
"learning_rate": 0.000196395387512876,
|
|
"loss": 1.9732431030273438,
|
|
"num_input_tokens_seen": 94895328,
|
|
"step": 89400,
|
|
"train_runtime": 142700.9942,
|
|
"train_tokens_per_second": 664.994
|
|
},
|
|
{
|
|
"epoch": 0.08625843780135005,
|
|
"grad_norm": 24.619190216064453,
|
|
"learning_rate": 0.0001963913541740166,
|
|
"loss": 1.9235589599609375,
|
|
"num_input_tokens_seen": 94932968,
|
|
"step": 89450,
|
|
"train_runtime": 142763.3951,
|
|
"train_tokens_per_second": 664.967
|
|
},
|
|
{
|
|
"epoch": 0.0863066538090646,
|
|
"grad_norm": 35.23280715942383,
|
|
"learning_rate": 0.00019638731862135295,
|
|
"loss": 1.858843536376953,
|
|
"num_input_tokens_seen": 94971120,
|
|
"step": 89500,
|
|
"train_runtime": 142826.2441,
|
|
"train_tokens_per_second": 664.942
|
|
},
|
|
{
|
|
"epoch": 0.08635486981677917,
|
|
"grad_norm": 25.464420318603516,
|
|
"learning_rate": 0.0001963832808549777,
|
|
"loss": 1.8922831726074218,
|
|
"num_input_tokens_seen": 95008752,
|
|
"step": 89550,
|
|
"train_runtime": 142889.5528,
|
|
"train_tokens_per_second": 664.91
|
|
},
|
|
{
|
|
"epoch": 0.08640308582449373,
|
|
"grad_norm": 17.06697654724121,
|
|
"learning_rate": 0.0001963792408749836,
|
|
"loss": 1.9558522033691406,
|
|
"num_input_tokens_seen": 95046256,
|
|
"step": 89600,
|
|
"train_runtime": 142952.0059,
|
|
"train_tokens_per_second": 664.882
|
|
},
|
|
{
|
|
"epoch": 0.0864513018322083,
|
|
"grad_norm": 14.525040626525879,
|
|
"learning_rate": 0.00019637519868146341,
|
|
"loss": 1.9307963562011718,
|
|
"num_input_tokens_seen": 95083712,
|
|
"step": 89650,
|
|
"train_runtime": 143014.5033,
|
|
"train_tokens_per_second": 664.854
|
|
},
|
|
{
|
|
"epoch": 0.08649951783992285,
|
|
"grad_norm": 14.679251670837402,
|
|
"learning_rate": 0.00019637115427451,
|
|
"loss": 1.9459162902832032,
|
|
"num_input_tokens_seen": 95121248,
|
|
"step": 89700,
|
|
"train_runtime": 143077.0095,
|
|
"train_tokens_per_second": 664.826
|
|
},
|
|
{
|
|
"epoch": 0.08654773384763742,
|
|
"grad_norm": 13.255271911621094,
|
|
"learning_rate": 0.00019636710765421622,
|
|
"loss": 1.90025634765625,
|
|
"num_input_tokens_seen": 95159632,
|
|
"step": 89750,
|
|
"train_runtime": 143139.6243,
|
|
"train_tokens_per_second": 664.803
|
|
},
|
|
{
|
|
"epoch": 0.08659594985535198,
|
|
"grad_norm": 39.449981689453125,
|
|
"learning_rate": 0.00019636305882067505,
|
|
"loss": 2.0280238342285157,
|
|
"num_input_tokens_seen": 95197856,
|
|
"step": 89800,
|
|
"train_runtime": 143202.2385,
|
|
"train_tokens_per_second": 664.779
|
|
},
|
|
{
|
|
"epoch": 0.08664416586306654,
|
|
"grad_norm": 31.53631591796875,
|
|
"learning_rate": 0.00019635900777397947,
|
|
"loss": 1.8694400024414062,
|
|
"num_input_tokens_seen": 95236184,
|
|
"step": 89850,
|
|
"train_runtime": 143264.6544,
|
|
"train_tokens_per_second": 664.757
|
|
},
|
|
{
|
|
"epoch": 0.0866923818707811,
|
|
"grad_norm": 72.02757263183594,
|
|
"learning_rate": 0.00019635495451422247,
|
|
"loss": 1.9010140991210938,
|
|
"num_input_tokens_seen": 95274456,
|
|
"step": 89900,
|
|
"train_runtime": 143329.1086,
|
|
"train_tokens_per_second": 664.725
|
|
},
|
|
{
|
|
"epoch": 0.08674059787849565,
|
|
"grad_norm": 62.024784088134766,
|
|
"learning_rate": 0.0001963508990414972,
|
|
"loss": 2.3161875915527346,
|
|
"num_input_tokens_seen": 95312392,
|
|
"step": 89950,
|
|
"train_runtime": 143392.8435,
|
|
"train_tokens_per_second": 664.694
|
|
},
|
|
{
|
|
"epoch": 0.08678881388621022,
|
|
"grad_norm": 39.0665283203125,
|
|
"learning_rate": 0.00019634684135589678,
|
|
"loss": 2.0900511169433593,
|
|
"num_input_tokens_seen": 95349472,
|
|
"step": 90000,
|
|
"train_runtime": 143456.1864,
|
|
"train_tokens_per_second": 664.659
|
|
},
|
|
{
|
|
"epoch": 0.08683702989392478,
|
|
"grad_norm": 59.40183639526367,
|
|
"learning_rate": 0.0001963427814575144,
|
|
"loss": 1.9795826721191405,
|
|
"num_input_tokens_seen": 95387616,
|
|
"step": 90050,
|
|
"train_runtime": 143521.1592,
|
|
"train_tokens_per_second": 664.624
|
|
},
|
|
{
|
|
"epoch": 0.08688524590163935,
|
|
"grad_norm": 15.570008277893066,
|
|
"learning_rate": 0.00019633871934644334,
|
|
"loss": 1.979904327392578,
|
|
"num_input_tokens_seen": 95425928,
|
|
"step": 90100,
|
|
"train_runtime": 143584.6285,
|
|
"train_tokens_per_second": 664.597
|
|
},
|
|
{
|
|
"epoch": 0.0869334619093539,
|
|
"grad_norm": 68.32030487060547,
|
|
"learning_rate": 0.0001963346550227768,
|
|
"loss": 1.8752310180664062,
|
|
"num_input_tokens_seen": 95463936,
|
|
"step": 90150,
|
|
"train_runtime": 143647.2066,
|
|
"train_tokens_per_second": 664.572
|
|
},
|
|
{
|
|
"epoch": 0.08698167791706847,
|
|
"grad_norm": 12.045650482177734,
|
|
"learning_rate": 0.00019633058848660822,
|
|
"loss": 1.9371932983398437,
|
|
"num_input_tokens_seen": 95502128,
|
|
"step": 90200,
|
|
"train_runtime": 143710.4896,
|
|
"train_tokens_per_second": 664.545
|
|
},
|
|
{
|
|
"epoch": 0.08702989392478302,
|
|
"grad_norm": 13.60068416595459,
|
|
"learning_rate": 0.00019632651973803094,
|
|
"loss": 1.898198699951172,
|
|
"num_input_tokens_seen": 95540376,
|
|
"step": 90250,
|
|
"train_runtime": 143773.9643,
|
|
"train_tokens_per_second": 664.518
|
|
},
|
|
{
|
|
"epoch": 0.0870781099324976,
|
|
"grad_norm": 29.714200973510742,
|
|
"learning_rate": 0.00019632244877713847,
|
|
"loss": 1.9622386169433594,
|
|
"num_input_tokens_seen": 95577904,
|
|
"step": 90300,
|
|
"train_runtime": 143837.2898,
|
|
"train_tokens_per_second": 664.486
|
|
},
|
|
{
|
|
"epoch": 0.08712632594021215,
|
|
"grad_norm": 11.639894485473633,
|
|
"learning_rate": 0.0001963183756040242,
|
|
"loss": 1.9811048889160157,
|
|
"num_input_tokens_seen": 95616224,
|
|
"step": 90350,
|
|
"train_runtime": 143900.3756,
|
|
"train_tokens_per_second": 664.461
|
|
},
|
|
{
|
|
"epoch": 0.08717454194792672,
|
|
"grad_norm": 11.78386402130127,
|
|
"learning_rate": 0.00019631430021878178,
|
|
"loss": 1.9775137329101562,
|
|
"num_input_tokens_seen": 95654752,
|
|
"step": 90400,
|
|
"train_runtime": 143963.5945,
|
|
"train_tokens_per_second": 664.437
|
|
},
|
|
{
|
|
"epoch": 0.08722275795564127,
|
|
"grad_norm": 13.143448829650879,
|
|
"learning_rate": 0.00019631022262150475,
|
|
"loss": 1.9043856811523439,
|
|
"num_input_tokens_seen": 95692208,
|
|
"step": 90450,
|
|
"train_runtime": 144025.7803,
|
|
"train_tokens_per_second": 664.41
|
|
},
|
|
{
|
|
"epoch": 0.08727097396335583,
|
|
"grad_norm": 227.21250915527344,
|
|
"learning_rate": 0.0001963061428122868,
|
|
"loss": 1.9542396545410157,
|
|
"num_input_tokens_seen": 95729992,
|
|
"step": 90500,
|
|
"train_runtime": 144088.303,
|
|
"train_tokens_per_second": 664.384
|
|
},
|
|
{
|
|
"epoch": 0.0873191899710704,
|
|
"grad_norm": 10.28619384765625,
|
|
"learning_rate": 0.0001963020607912216,
|
|
"loss": 2.0645985412597656,
|
|
"num_input_tokens_seen": 95768480,
|
|
"step": 90550,
|
|
"train_runtime": 144151.8384,
|
|
"train_tokens_per_second": 664.358
|
|
},
|
|
{
|
|
"epoch": 0.08736740597878495,
|
|
"grad_norm": 24.24940299987793,
|
|
"learning_rate": 0.0001962979765584029,
|
|
"loss": 1.9718643188476563,
|
|
"num_input_tokens_seen": 95807400,
|
|
"step": 90600,
|
|
"train_runtime": 144215.3424,
|
|
"train_tokens_per_second": 664.336
|
|
},
|
|
{
|
|
"epoch": 0.08741562198649952,
|
|
"grad_norm": 16.385604858398438,
|
|
"learning_rate": 0.00019629389011392454,
|
|
"loss": 1.9506013488769531,
|
|
"num_input_tokens_seen": 95845632,
|
|
"step": 90650,
|
|
"train_runtime": 144278.1772,
|
|
"train_tokens_per_second": 664.311
|
|
},
|
|
{
|
|
"epoch": 0.08746383799421407,
|
|
"grad_norm": 43.12853240966797,
|
|
"learning_rate": 0.00019628980145788033,
|
|
"loss": 1.953353271484375,
|
|
"num_input_tokens_seen": 95884640,
|
|
"step": 90700,
|
|
"train_runtime": 144340.8403,
|
|
"train_tokens_per_second": 664.293
|
|
},
|
|
{
|
|
"epoch": 0.08751205400192864,
|
|
"grad_norm": 28.55571746826172,
|
|
"learning_rate": 0.00019628571059036415,
|
|
"loss": 1.9486882019042968,
|
|
"num_input_tokens_seen": 95922768,
|
|
"step": 90750,
|
|
"train_runtime": 144404.1738,
|
|
"train_tokens_per_second": 664.266
|
|
},
|
|
{
|
|
"epoch": 0.0875602700096432,
|
|
"grad_norm": 18.617816925048828,
|
|
"learning_rate": 0.00019628161751147004,
|
|
"loss": 1.9872026062011718,
|
|
"num_input_tokens_seen": 95960936,
|
|
"step": 90800,
|
|
"train_runtime": 144466.855,
|
|
"train_tokens_per_second": 664.242
|
|
},
|
|
{
|
|
"epoch": 0.08760848601735777,
|
|
"grad_norm": 80.60220336914062,
|
|
"learning_rate": 0.00019627752222129194,
|
|
"loss": 2.0140916442871095,
|
|
"num_input_tokens_seen": 95998104,
|
|
"step": 90850,
|
|
"train_runtime": 144529.8778,
|
|
"train_tokens_per_second": 664.209
|
|
},
|
|
{
|
|
"epoch": 0.08765670202507232,
|
|
"grad_norm": 14.98727798461914,
|
|
"learning_rate": 0.00019627342471992393,
|
|
"loss": 2.0083599853515626,
|
|
"num_input_tokens_seen": 96036736,
|
|
"step": 90900,
|
|
"train_runtime": 144592.9696,
|
|
"train_tokens_per_second": 664.187
|
|
},
|
|
{
|
|
"epoch": 0.08770491803278689,
|
|
"grad_norm": 31.604618072509766,
|
|
"learning_rate": 0.00019626932500746013,
|
|
"loss": 1.9033355712890625,
|
|
"num_input_tokens_seen": 96074040,
|
|
"step": 90950,
|
|
"train_runtime": 144655.3226,
|
|
"train_tokens_per_second": 664.158
|
|
},
|
|
{
|
|
"epoch": 0.08775313404050145,
|
|
"grad_norm": 79.02655029296875,
|
|
"learning_rate": 0.00019626522308399466,
|
|
"loss": 2.0599169921875,
|
|
"num_input_tokens_seen": 96112416,
|
|
"step": 91000,
|
|
"train_runtime": 144718.6891,
|
|
"train_tokens_per_second": 664.133
|
|
},
|
|
{
|
|
"epoch": 0.087801350048216,
|
|
"grad_norm": 31.613895416259766,
|
|
"learning_rate": 0.00019626111894962173,
|
|
"loss": 2.046968994140625,
|
|
"num_input_tokens_seen": 96150656,
|
|
"step": 91050,
|
|
"train_runtime": 144781.4641,
|
|
"train_tokens_per_second": 664.109
|
|
},
|
|
{
|
|
"epoch": 0.08784956605593057,
|
|
"grad_norm": 14.49528980255127,
|
|
"learning_rate": 0.00019625701260443562,
|
|
"loss": 1.9385997009277345,
|
|
"num_input_tokens_seen": 96189048,
|
|
"step": 91100,
|
|
"train_runtime": 144844.2836,
|
|
"train_tokens_per_second": 664.086
|
|
},
|
|
{
|
|
"epoch": 0.08789778206364512,
|
|
"grad_norm": 53.25993728637695,
|
|
"learning_rate": 0.00019625290404853062,
|
|
"loss": 1.9991246032714844,
|
|
"num_input_tokens_seen": 96227688,
|
|
"step": 91150,
|
|
"train_runtime": 144906.7496,
|
|
"train_tokens_per_second": 664.066
|
|
},
|
|
{
|
|
"epoch": 0.0879459980713597,
|
|
"grad_norm": 38.771575927734375,
|
|
"learning_rate": 0.00019624879328200115,
|
|
"loss": 1.9576438903808593,
|
|
"num_input_tokens_seen": 96265368,
|
|
"step": 91200,
|
|
"train_runtime": 144969.4793,
|
|
"train_tokens_per_second": 664.039
|
|
},
|
|
{
|
|
"epoch": 0.08799421407907425,
|
|
"grad_norm": 81.96832275390625,
|
|
"learning_rate": 0.00019624468030494154,
|
|
"loss": 1.934375,
|
|
"num_input_tokens_seen": 96303152,
|
|
"step": 91250,
|
|
"train_runtime": 145032.3525,
|
|
"train_tokens_per_second": 664.012
|
|
},
|
|
{
|
|
"epoch": 0.08804243008678882,
|
|
"grad_norm": 17.97835350036621,
|
|
"learning_rate": 0.00019624056511744633,
|
|
"loss": 1.928380126953125,
|
|
"num_input_tokens_seen": 96342072,
|
|
"step": 91300,
|
|
"train_runtime": 145095.2652,
|
|
"train_tokens_per_second": 663.992
|
|
},
|
|
{
|
|
"epoch": 0.08809064609450337,
|
|
"grad_norm": 111.1414566040039,
|
|
"learning_rate": 0.00019623644771960997,
|
|
"loss": 2.0197433471679687,
|
|
"num_input_tokens_seen": 96380344,
|
|
"step": 91350,
|
|
"train_runtime": 145158.4636,
|
|
"train_tokens_per_second": 663.966
|
|
},
|
|
{
|
|
"epoch": 0.08813886210221794,
|
|
"grad_norm": 4919.03076171875,
|
|
"learning_rate": 0.0001962326577615085,
|
|
"loss": 5.074176025390625,
|
|
"num_input_tokens_seen": 96418008,
|
|
"step": 91400,
|
|
"train_runtime": 145220.5672,
|
|
"train_tokens_per_second": 663.942
|
|
},
|
|
{
|
|
"epoch": 0.0881870781099325,
|
|
"grad_norm": 55.729881286621094,
|
|
"learning_rate": 0.00019622853612008228,
|
|
"loss": 2.3785870361328123,
|
|
"num_input_tokens_seen": 96456296,
|
|
"step": 91450,
|
|
"train_runtime": 145283.0207,
|
|
"train_tokens_per_second": 663.92
|
|
},
|
|
{
|
|
"epoch": 0.08823529411764706,
|
|
"grad_norm": 23.50056266784668,
|
|
"learning_rate": 0.00019622441226859122,
|
|
"loss": 1.9779930114746094,
|
|
"num_input_tokens_seen": 96494232,
|
|
"step": 91500,
|
|
"train_runtime": 145346.3238,
|
|
"train_tokens_per_second": 663.892
|
|
},
|
|
{
|
|
"epoch": 0.08828351012536162,
|
|
"grad_norm": 29.52114486694336,
|
|
"learning_rate": 0.00019622028620713,
|
|
"loss": 1.9526777648925782,
|
|
"num_input_tokens_seen": 96531984,
|
|
"step": 91550,
|
|
"train_runtime": 145409.7473,
|
|
"train_tokens_per_second": 663.862
|
|
},
|
|
{
|
|
"epoch": 0.08833172613307617,
|
|
"grad_norm": 37.353946685791016,
|
|
"learning_rate": 0.00019621615793579338,
|
|
"loss": 1.8873312377929687,
|
|
"num_input_tokens_seen": 96570016,
|
|
"step": 91600,
|
|
"train_runtime": 145473.749,
|
|
"train_tokens_per_second": 663.831
|
|
},
|
|
{
|
|
"epoch": 0.08837994214079074,
|
|
"grad_norm": 32.69992446899414,
|
|
"learning_rate": 0.00019621202745467623,
|
|
"loss": 2.018964996337891,
|
|
"num_input_tokens_seen": 96608496,
|
|
"step": 91650,
|
|
"train_runtime": 145536.7327,
|
|
"train_tokens_per_second": 663.808
|
|
},
|
|
{
|
|
"epoch": 0.0884281581485053,
|
|
"grad_norm": 21.70285415649414,
|
|
"learning_rate": 0.00019620789476387335,
|
|
"loss": 2.071495361328125,
|
|
"num_input_tokens_seen": 96647056,
|
|
"step": 91700,
|
|
"train_runtime": 145599.4785,
|
|
"train_tokens_per_second": 663.787
|
|
},
|
|
{
|
|
"epoch": 0.08847637415621987,
|
|
"grad_norm": 10.009458541870117,
|
|
"learning_rate": 0.00019620375986347967,
|
|
"loss": 1.9968014526367188,
|
|
"num_input_tokens_seen": 96684928,
|
|
"step": 91750,
|
|
"train_runtime": 145662.2735,
|
|
"train_tokens_per_second": 663.761
|
|
},
|
|
{
|
|
"epoch": 0.08852459016393442,
|
|
"grad_norm": 17.564367294311523,
|
|
"learning_rate": 0.00019619962275359013,
|
|
"loss": 1.9653125,
|
|
"num_input_tokens_seen": 96723088,
|
|
"step": 91800,
|
|
"train_runtime": 145724.7671,
|
|
"train_tokens_per_second": 663.738
|
|
},
|
|
{
|
|
"epoch": 0.08857280617164899,
|
|
"grad_norm": 20.180400848388672,
|
|
"learning_rate": 0.0001961954834342998,
|
|
"loss": 2.050068054199219,
|
|
"num_input_tokens_seen": 96761208,
|
|
"step": 91850,
|
|
"train_runtime": 145787.5946,
|
|
"train_tokens_per_second": 663.714
|
|
},
|
|
{
|
|
"epoch": 0.08862102217936355,
|
|
"grad_norm": 12.53288745880127,
|
|
"learning_rate": 0.00019619134190570375,
|
|
"loss": 1.9411447143554688,
|
|
"num_input_tokens_seen": 96799496,
|
|
"step": 91900,
|
|
"train_runtime": 145850.5169,
|
|
"train_tokens_per_second": 663.69
|
|
},
|
|
{
|
|
"epoch": 0.08866923818707811,
|
|
"grad_norm": 20.713972091674805,
|
|
"learning_rate": 0.00019618719816789706,
|
|
"loss": 2.137564849853516,
|
|
"num_input_tokens_seen": 96837640,
|
|
"step": 91950,
|
|
"train_runtime": 145913.1597,
|
|
"train_tokens_per_second": 663.666
|
|
},
|
|
{
|
|
"epoch": 0.08871745419479267,
|
|
"grad_norm": 15.788455963134766,
|
|
"learning_rate": 0.0001961830522209749,
|
|
"loss": 1.9689521789550781,
|
|
"num_input_tokens_seen": 96875872,
|
|
"step": 92000,
|
|
"train_runtime": 145975.6033,
|
|
"train_tokens_per_second": 663.644
|
|
},
|
|
{
|
|
"epoch": 0.08876567020250724,
|
|
"grad_norm": 17.018898010253906,
|
|
"learning_rate": 0.0001961789040650325,
|
|
"loss": 1.9274456787109375,
|
|
"num_input_tokens_seen": 96913520,
|
|
"step": 92050,
|
|
"train_runtime": 146038.0912,
|
|
"train_tokens_per_second": 663.618
|
|
},
|
|
{
|
|
"epoch": 0.08881388621022179,
|
|
"grad_norm": 23.389156341552734,
|
|
"learning_rate": 0.00019617475370016513,
|
|
"loss": 2.0213691711425783,
|
|
"num_input_tokens_seen": 96951880,
|
|
"step": 92100,
|
|
"train_runtime": 146100.7592,
|
|
"train_tokens_per_second": 663.596
|
|
},
|
|
{
|
|
"epoch": 0.08886210221793636,
|
|
"grad_norm": 14.991084098815918,
|
|
"learning_rate": 0.00019617060112646812,
|
|
"loss": 1.9621612548828125,
|
|
"num_input_tokens_seen": 96990240,
|
|
"step": 92150,
|
|
"train_runtime": 146163.5954,
|
|
"train_tokens_per_second": 663.573
|
|
},
|
|
{
|
|
"epoch": 0.08891031822565092,
|
|
"grad_norm": 15.38088321685791,
|
|
"learning_rate": 0.00019616644634403682,
|
|
"loss": 1.9429843139648437,
|
|
"num_input_tokens_seen": 97028656,
|
|
"step": 92200,
|
|
"train_runtime": 146226.3444,
|
|
"train_tokens_per_second": 663.551
|
|
},
|
|
{
|
|
"epoch": 0.08895853423336547,
|
|
"grad_norm": 42.89073944091797,
|
|
"learning_rate": 0.0001961622893529667,
|
|
"loss": 1.9169171142578125,
|
|
"num_input_tokens_seen": 97067488,
|
|
"step": 92250,
|
|
"train_runtime": 146290.0737,
|
|
"train_tokens_per_second": 663.528
|
|
},
|
|
{
|
|
"epoch": 0.08900675024108004,
|
|
"grad_norm": 18.29239845275879,
|
|
"learning_rate": 0.00019615813015335317,
|
|
"loss": 2.0016439819335936,
|
|
"num_input_tokens_seen": 97105504,
|
|
"step": 92300,
|
|
"train_runtime": 146352.5264,
|
|
"train_tokens_per_second": 663.504
|
|
},
|
|
{
|
|
"epoch": 0.0890549662487946,
|
|
"grad_norm": 29.280113220214844,
|
|
"learning_rate": 0.0001961539687452918,
|
|
"loss": 1.917425537109375,
|
|
"num_input_tokens_seen": 97142992,
|
|
"step": 92350,
|
|
"train_runtime": 146415.2912,
|
|
"train_tokens_per_second": 663.476
|
|
},
|
|
{
|
|
"epoch": 0.08910318225650916,
|
|
"grad_norm": 25.691926956176758,
|
|
"learning_rate": 0.0001961498051288781,
|
|
"loss": 2.1702694702148437,
|
|
"num_input_tokens_seen": 97181224,
|
|
"step": 92400,
|
|
"train_runtime": 146478.2363,
|
|
"train_tokens_per_second": 663.452
|
|
},
|
|
{
|
|
"epoch": 0.08915139826422372,
|
|
"grad_norm": 16.67594337463379,
|
|
"learning_rate": 0.00019614563930420777,
|
|
"loss": 2.527384948730469,
|
|
"num_input_tokens_seen": 97219184,
|
|
"step": 92450,
|
|
"train_runtime": 146540.5973,
|
|
"train_tokens_per_second": 663.428
|
|
},
|
|
{
|
|
"epoch": 0.08919961427193829,
|
|
"grad_norm": 29.616769790649414,
|
|
"learning_rate": 0.0001961414712713765,
|
|
"loss": 1.9912237548828124,
|
|
"num_input_tokens_seen": 97256872,
|
|
"step": 92500,
|
|
"train_runtime": 146603.2361,
|
|
"train_tokens_per_second": 663.402
|
|
},
|
|
{
|
|
"epoch": 0.08924783027965284,
|
|
"grad_norm": 23.51951026916504,
|
|
"learning_rate": 0.0001961373010304799,
|
|
"loss": 1.9297962951660157,
|
|
"num_input_tokens_seen": 97295336,
|
|
"step": 92550,
|
|
"train_runtime": 146666.2323,
|
|
"train_tokens_per_second": 663.379
|
|
},
|
|
{
|
|
"epoch": 0.08929604628736741,
|
|
"grad_norm": 33.01461410522461,
|
|
"learning_rate": 0.00019613312858161386,
|
|
"loss": 1.955753173828125,
|
|
"num_input_tokens_seen": 97333528,
|
|
"step": 92600,
|
|
"train_runtime": 146728.6733,
|
|
"train_tokens_per_second": 663.357
|
|
},
|
|
{
|
|
"epoch": 0.08934426229508197,
|
|
"grad_norm": 286.0633850097656,
|
|
"learning_rate": 0.00019612895392487415,
|
|
"loss": 3.4998760986328126,
|
|
"num_input_tokens_seen": 97372440,
|
|
"step": 92650,
|
|
"train_runtime": 146791.528,
|
|
"train_tokens_per_second": 663.338
|
|
},
|
|
{
|
|
"epoch": 0.08939247830279654,
|
|
"grad_norm": 627.7567138671875,
|
|
"learning_rate": 0.00019612477706035667,
|
|
"loss": 3.987329406738281,
|
|
"num_input_tokens_seen": 97411400,
|
|
"step": 92700,
|
|
"train_runtime": 146854.6562,
|
|
"train_tokens_per_second": 663.318
|
|
},
|
|
{
|
|
"epoch": 0.08944069431051109,
|
|
"grad_norm": 21.216032028198242,
|
|
"learning_rate": 0.00019612059798815738,
|
|
"loss": 4.975804748535157,
|
|
"num_input_tokens_seen": 97448952,
|
|
"step": 92750,
|
|
"train_runtime": 146917.2892,
|
|
"train_tokens_per_second": 663.291
|
|
},
|
|
{
|
|
"epoch": 0.08948891031822565,
|
|
"grad_norm": 158.384521484375,
|
|
"learning_rate": 0.00019611641670837219,
|
|
"loss": 4.019295654296875,
|
|
"num_input_tokens_seen": 97487896,
|
|
"step": 92800,
|
|
"train_runtime": 146980.1786,
|
|
"train_tokens_per_second": 663.272
|
|
},
|
|
{
|
|
"epoch": 0.08953712632594021,
|
|
"grad_norm": 111.30355834960938,
|
|
"learning_rate": 0.0001961122332210972,
|
|
"loss": 2.2994950866699218,
|
|
"num_input_tokens_seen": 97526136,
|
|
"step": 92850,
|
|
"train_runtime": 147042.8046,
|
|
"train_tokens_per_second": 663.25
|
|
},
|
|
{
|
|
"epoch": 0.08958534233365477,
|
|
"grad_norm": 16.871028900146484,
|
|
"learning_rate": 0.00019610804752642842,
|
|
"loss": 1.9650274658203124,
|
|
"num_input_tokens_seen": 97564080,
|
|
"step": 92900,
|
|
"train_runtime": 147105.3534,
|
|
"train_tokens_per_second": 663.226
|
|
},
|
|
{
|
|
"epoch": 0.08963355834136934,
|
|
"grad_norm": 58.112003326416016,
|
|
"learning_rate": 0.00019610385962446202,
|
|
"loss": 1.9797833251953125,
|
|
"num_input_tokens_seen": 97601840,
|
|
"step": 92950,
|
|
"train_runtime": 147168.1248,
|
|
"train_tokens_per_second": 663.2
|
|
},
|
|
{
|
|
"epoch": 0.08968177434908389,
|
|
"grad_norm": 17.74005699157715,
|
|
"learning_rate": 0.0001960996695152942,
|
|
"loss": 1.9251220703125,
|
|
"num_input_tokens_seen": 97639008,
|
|
"step": 93000,
|
|
"train_runtime": 147231.2821,
|
|
"train_tokens_per_second": 663.168
|
|
},
|
|
{
|
|
"epoch": 0.08972999035679846,
|
|
"grad_norm": 21.738853454589844,
|
|
"learning_rate": 0.00019609547719902118,
|
|
"loss": 1.8856649780273438,
|
|
"num_input_tokens_seen": 97676760,
|
|
"step": 93050,
|
|
"train_runtime": 147294.227,
|
|
"train_tokens_per_second": 663.14
|
|
},
|
|
{
|
|
"epoch": 0.08977820636451302,
|
|
"grad_norm": 33.55712127685547,
|
|
"learning_rate": 0.00019609128267573925,
|
|
"loss": 1.90356689453125,
|
|
"num_input_tokens_seen": 97716040,
|
|
"step": 93100,
|
|
"train_runtime": 147357.3293,
|
|
"train_tokens_per_second": 663.123
|
|
},
|
|
{
|
|
"epoch": 0.08982642237222759,
|
|
"grad_norm": 196.40557861328125,
|
|
"learning_rate": 0.00019608708594554472,
|
|
"loss": 4.055553588867188,
|
|
"num_input_tokens_seen": 97754640,
|
|
"step": 93150,
|
|
"train_runtime": 147420.4446,
|
|
"train_tokens_per_second": 663.101
|
|
},
|
|
{
|
|
"epoch": 0.08987463837994214,
|
|
"grad_norm": 33.782344818115234,
|
|
"learning_rate": 0.00019608288700853402,
|
|
"loss": 2.3960507202148436,
|
|
"num_input_tokens_seen": 97793096,
|
|
"step": 93200,
|
|
"train_runtime": 147483.2879,
|
|
"train_tokens_per_second": 663.079
|
|
},
|
|
{
|
|
"epoch": 0.08992285438765671,
|
|
"grad_norm": 38.50969696044922,
|
|
"learning_rate": 0.0001960786858648035,
|
|
"loss": 2.120165252685547,
|
|
"num_input_tokens_seen": 97831864,
|
|
"step": 93250,
|
|
"train_runtime": 147546.4386,
|
|
"train_tokens_per_second": 663.058
|
|
},
|
|
{
|
|
"epoch": 0.08997107039537126,
|
|
"grad_norm": 13.014695167541504,
|
|
"learning_rate": 0.00019607448251444978,
|
|
"loss": 2.0071717834472658,
|
|
"num_input_tokens_seen": 97870224,
|
|
"step": 93300,
|
|
"train_runtime": 147609.2357,
|
|
"train_tokens_per_second": 663.036
|
|
},
|
|
{
|
|
"epoch": 0.09001928640308582,
|
|
"grad_norm": 26.79749298095703,
|
|
"learning_rate": 0.00019607027695756928,
|
|
"loss": 2.022077941894531,
|
|
"num_input_tokens_seen": 97908800,
|
|
"step": 93350,
|
|
"train_runtime": 147672.232,
|
|
"train_tokens_per_second": 663.014
|
|
},
|
|
{
|
|
"epoch": 0.09006750241080039,
|
|
"grad_norm": 17.592378616333008,
|
|
"learning_rate": 0.00019606606919425862,
|
|
"loss": 2.0180810546875,
|
|
"num_input_tokens_seen": 97946704,
|
|
"step": 93400,
|
|
"train_runtime": 147734.6845,
|
|
"train_tokens_per_second": 662.991
|
|
},
|
|
{
|
|
"epoch": 0.09011571841851494,
|
|
"grad_norm": 125.5819091796875,
|
|
"learning_rate": 0.00019606185922461448,
|
|
"loss": 1.9633078002929687,
|
|
"num_input_tokens_seen": 97985656,
|
|
"step": 93450,
|
|
"train_runtime": 147797.2179,
|
|
"train_tokens_per_second": 662.974
|
|
},
|
|
{
|
|
"epoch": 0.09016393442622951,
|
|
"grad_norm": 34.06214904785156,
|
|
"learning_rate": 0.00019605764704873352,
|
|
"loss": 1.9428683471679689,
|
|
"num_input_tokens_seen": 98024488,
|
|
"step": 93500,
|
|
"train_runtime": 147860.8721,
|
|
"train_tokens_per_second": 662.951
|
|
},
|
|
{
|
|
"epoch": 0.09021215043394407,
|
|
"grad_norm": 56.31159973144531,
|
|
"learning_rate": 0.00019605343266671245,
|
|
"loss": 1.9510031127929688,
|
|
"num_input_tokens_seen": 98062384,
|
|
"step": 93550,
|
|
"train_runtime": 147923.7962,
|
|
"train_tokens_per_second": 662.925
|
|
},
|
|
{
|
|
"epoch": 0.09026036644165863,
|
|
"grad_norm": 16.246145248413086,
|
|
"learning_rate": 0.0001960492160786481,
|
|
"loss": 2.092909088134766,
|
|
"num_input_tokens_seen": 98099976,
|
|
"step": 93600,
|
|
"train_runtime": 147986.4762,
|
|
"train_tokens_per_second": 662.898
|
|
},
|
|
{
|
|
"epoch": 0.09030858244937319,
|
|
"grad_norm": 105.89008331298828,
|
|
"learning_rate": 0.0001960449972846373,
|
|
"loss": 2.25677734375,
|
|
"num_input_tokens_seen": 98138960,
|
|
"step": 93650,
|
|
"train_runtime": 148049.5523,
|
|
"train_tokens_per_second": 662.879
|
|
},
|
|
{
|
|
"epoch": 0.09035679845708776,
|
|
"grad_norm": 20.900028228759766,
|
|
"learning_rate": 0.00019604077628477697,
|
|
"loss": 2.0097802734375,
|
|
"num_input_tokens_seen": 98177056,
|
|
"step": 93700,
|
|
"train_runtime": 148112.5762,
|
|
"train_tokens_per_second": 662.854
|
|
},
|
|
{
|
|
"epoch": 0.09040501446480231,
|
|
"grad_norm": 36.71495819091797,
|
|
"learning_rate": 0.00019603655307916403,
|
|
"loss": 1.9395753479003905,
|
|
"num_input_tokens_seen": 98214864,
|
|
"step": 93750,
|
|
"train_runtime": 148175.3564,
|
|
"train_tokens_per_second": 662.829
|
|
},
|
|
{
|
|
"epoch": 0.09045323047251688,
|
|
"grad_norm": 33.812095642089844,
|
|
"learning_rate": 0.00019603232766789543,
|
|
"loss": 1.9396356201171876,
|
|
"num_input_tokens_seen": 98253184,
|
|
"step": 93800,
|
|
"train_runtime": 148237.8345,
|
|
"train_tokens_per_second": 662.808
|
|
},
|
|
{
|
|
"epoch": 0.09050144648023144,
|
|
"grad_norm": 14.377096176147461,
|
|
"learning_rate": 0.0001960281000510683,
|
|
"loss": 1.922464599609375,
|
|
"num_input_tokens_seen": 98291848,
|
|
"step": 93850,
|
|
"train_runtime": 148300.4957,
|
|
"train_tokens_per_second": 662.788
|
|
},
|
|
{
|
|
"epoch": 0.09054966248794599,
|
|
"grad_norm": 20.7000732421875,
|
|
"learning_rate": 0.0001960238702287797,
|
|
"loss": 1.9767715454101562,
|
|
"num_input_tokens_seen": 98329768,
|
|
"step": 93900,
|
|
"train_runtime": 148363.2392,
|
|
"train_tokens_per_second": 662.764
|
|
},
|
|
{
|
|
"epoch": 0.09059787849566056,
|
|
"grad_norm": 24000.97265625,
|
|
"learning_rate": 0.0001960197228632917,
|
|
"loss": 3.232272033691406,
|
|
"num_input_tokens_seen": 98368128,
|
|
"step": 93950,
|
|
"train_runtime": 148425.7573,
|
|
"train_tokens_per_second": 662.743
|
|
},
|
|
{
|
|
"epoch": 0.09064609450337512,
|
|
"grad_norm": 143.78494262695312,
|
|
"learning_rate": 0.000196015488674476,
|
|
"loss": 7.0809521484375,
|
|
"num_input_tokens_seen": 98407120,
|
|
"step": 94000,
|
|
"train_runtime": 148488.7972,
|
|
"train_tokens_per_second": 662.724
|
|
},
|
|
{
|
|
"epoch": 0.09069431051108968,
|
|
"grad_norm": 35.479042053222656,
|
|
"learning_rate": 0.00019601125228048847,
|
|
"loss": 4.172344970703125,
|
|
"num_input_tokens_seen": 98445688,
|
|
"step": 94050,
|
|
"train_runtime": 148551.5755,
|
|
"train_tokens_per_second": 662.704
|
|
},
|
|
{
|
|
"epoch": 0.09074252651880424,
|
|
"grad_norm": 30.854352951049805,
|
|
"learning_rate": 0.0001960070136814264,
|
|
"loss": 2.0040321350097656,
|
|
"num_input_tokens_seen": 98483672,
|
|
"step": 94100,
|
|
"train_runtime": 148613.8097,
|
|
"train_tokens_per_second": 662.682
|
|
},
|
|
{
|
|
"epoch": 0.09079074252651881,
|
|
"grad_norm": 772.1053466796875,
|
|
"learning_rate": 0.00019600277287738714,
|
|
"loss": 4.81131591796875,
|
|
"num_input_tokens_seen": 98521520,
|
|
"step": 94150,
|
|
"train_runtime": 148676.6655,
|
|
"train_tokens_per_second": 662.656
|
|
},
|
|
{
|
|
"epoch": 0.09083895853423336,
|
|
"grad_norm": 11407.05859375,
|
|
"learning_rate": 0.00019599852986846805,
|
|
"loss": 5.205994873046875,
|
|
"num_input_tokens_seen": 98560168,
|
|
"step": 94200,
|
|
"train_runtime": 148739.1515,
|
|
"train_tokens_per_second": 662.638
|
|
},
|
|
{
|
|
"epoch": 0.09088717454194793,
|
|
"grad_norm": 48.707645416259766,
|
|
"learning_rate": 0.00019599428465476667,
|
|
"loss": 5.8417816162109375,
|
|
"num_input_tokens_seen": 98597384,
|
|
"step": 94250,
|
|
"train_runtime": 148802.0387,
|
|
"train_tokens_per_second": 662.608
|
|
},
|
|
{
|
|
"epoch": 0.09093539054966249,
|
|
"grad_norm": 212.68731689453125,
|
|
"learning_rate": 0.00019599003723638037,
|
|
"loss": 5.438114624023438,
|
|
"num_input_tokens_seen": 98635104,
|
|
"step": 94300,
|
|
"train_runtime": 148865.0648,
|
|
"train_tokens_per_second": 662.581
|
|
},
|
|
{
|
|
"epoch": 0.09098360655737706,
|
|
"grad_norm": 213.78390502929688,
|
|
"learning_rate": 0.00019598578761340684,
|
|
"loss": 5.36521484375,
|
|
"num_input_tokens_seen": 98673232,
|
|
"step": 94350,
|
|
"train_runtime": 148928.5673,
|
|
"train_tokens_per_second": 662.554
|
|
},
|
|
{
|
|
"epoch": 0.09103182256509161,
|
|
"grad_norm": 137.0510711669922,
|
|
"learning_rate": 0.00019598153578594357,
|
|
"loss": 5.23910888671875,
|
|
"num_input_tokens_seen": 98711288,
|
|
"step": 94400,
|
|
"train_runtime": 148991.3332,
|
|
"train_tokens_per_second": 662.53
|
|
},
|
|
{
|
|
"epoch": 0.09108003857280617,
|
|
"grad_norm": 2714.43896484375,
|
|
"learning_rate": 0.0001959772817540883,
|
|
"loss": 5.304745483398437,
|
|
"num_input_tokens_seen": 98749400,
|
|
"step": 94450,
|
|
"train_runtime": 149053.6926,
|
|
"train_tokens_per_second": 662.509
|
|
},
|
|
{
|
|
"epoch": 0.09112825458052073,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 14.820858154296875,
|
|
"num_input_tokens_seen": 98787072,
|
|
"step": 94500,
|
|
"train_runtime": 149116.7375,
|
|
"train_tokens_per_second": 662.481
|
|
},
|
|
{
|
|
"epoch": 0.09117647058823529,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 98824616,
|
|
"step": 94550,
|
|
"train_runtime": 149177.8928,
|
|
"train_tokens_per_second": 662.462
|
|
},
|
|
{
|
|
"epoch": 0.09122468659594986,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 6.648922729492187,
|
|
"num_input_tokens_seen": 98862656,
|
|
"step": 94600,
|
|
"train_runtime": 149239.3119,
|
|
"train_tokens_per_second": 662.444
|
|
},
|
|
{
|
|
"epoch": 0.09127290260366441,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 98900872,
|
|
"step": 94650,
|
|
"train_runtime": 149300.9678,
|
|
"train_tokens_per_second": 662.426
|
|
},
|
|
{
|
|
"epoch": 0.09132111861137898,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.04076553344726563,
|
|
"num_input_tokens_seen": 98938768,
|
|
"step": 94700,
|
|
"train_runtime": 149362.2249,
|
|
"train_tokens_per_second": 662.408
|
|
},
|
|
{
|
|
"epoch": 0.09136933461909354,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 98976464,
|
|
"step": 94750,
|
|
"train_runtime": 149424.0655,
|
|
"train_tokens_per_second": 662.386
|
|
},
|
|
{
|
|
"epoch": 0.0914175506268081,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99014272,
|
|
"step": 94800,
|
|
"train_runtime": 149485.6202,
|
|
"train_tokens_per_second": 662.367
|
|
},
|
|
{
|
|
"epoch": 0.09146576663452266,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99052176,
|
|
"step": 94850,
|
|
"train_runtime": 149547.1618,
|
|
"train_tokens_per_second": 662.347
|
|
},
|
|
{
|
|
"epoch": 0.09151398264223723,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99090968,
|
|
"step": 94900,
|
|
"train_runtime": 149608.2447,
|
|
"train_tokens_per_second": 662.336
|
|
},
|
|
{
|
|
"epoch": 0.09156219864995178,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99128720,
|
|
"step": 94950,
|
|
"train_runtime": 149669.4006,
|
|
"train_tokens_per_second": 662.318
|
|
},
|
|
{
|
|
"epoch": 0.09161041465766634,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99167192,
|
|
"step": 95000,
|
|
"train_runtime": 149731.6251,
|
|
"train_tokens_per_second": 662.3
|
|
},
|
|
{
|
|
"epoch": 0.09165863066538091,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99206568,
|
|
"step": 95050,
|
|
"train_runtime": 149793.4876,
|
|
"train_tokens_per_second": 662.289
|
|
},
|
|
{
|
|
"epoch": 0.09170684667309546,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99245264,
|
|
"step": 95100,
|
|
"train_runtime": 149854.0568,
|
|
"train_tokens_per_second": 662.279
|
|
},
|
|
{
|
|
"epoch": 0.09175506268081003,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.17355632781982422,
|
|
"num_input_tokens_seen": 99284288,
|
|
"step": 95150,
|
|
"train_runtime": 149915.8288,
|
|
"train_tokens_per_second": 662.267
|
|
},
|
|
{
|
|
"epoch": 0.09180327868852459,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99323008,
|
|
"step": 95200,
|
|
"train_runtime": 149976.588,
|
|
"train_tokens_per_second": 662.257
|
|
},
|
|
{
|
|
"epoch": 0.09185149469623916,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99360464,
|
|
"step": 95250,
|
|
"train_runtime": 150038.3892,
|
|
"train_tokens_per_second": 662.234
|
|
},
|
|
{
|
|
"epoch": 0.09189971070395371,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99398992,
|
|
"step": 95300,
|
|
"train_runtime": 150100.2532,
|
|
"train_tokens_per_second": 662.217
|
|
},
|
|
{
|
|
"epoch": 0.09194792671166828,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.1854681396484375,
|
|
"num_input_tokens_seen": 99437088,
|
|
"step": 95350,
|
|
"train_runtime": 150161.3824,
|
|
"train_tokens_per_second": 662.201
|
|
},
|
|
{
|
|
"epoch": 0.09199614271938283,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99475312,
|
|
"step": 95400,
|
|
"train_runtime": 150222.4415,
|
|
"train_tokens_per_second": 662.187
|
|
},
|
|
{
|
|
"epoch": 0.0920443587270974,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99512528,
|
|
"step": 95450,
|
|
"train_runtime": 150283.7535,
|
|
"train_tokens_per_second": 662.164
|
|
},
|
|
{
|
|
"epoch": 0.09209257473481196,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99550800,
|
|
"step": 95500,
|
|
"train_runtime": 150345.6244,
|
|
"train_tokens_per_second": 662.146
|
|
},
|
|
{
|
|
"epoch": 0.09214079074252651,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99588432,
|
|
"step": 95550,
|
|
"train_runtime": 150406.4438,
|
|
"train_tokens_per_second": 662.129
|
|
},
|
|
{
|
|
"epoch": 0.09218900675024108,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99626272,
|
|
"step": 95600,
|
|
"train_runtime": 150468.0638,
|
|
"train_tokens_per_second": 662.109
|
|
},
|
|
{
|
|
"epoch": 0.09223722275795564,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 7.9249365234375,
|
|
"num_input_tokens_seen": 99664136,
|
|
"step": 95650,
|
|
"train_runtime": 150529.8591,
|
|
"train_tokens_per_second": 662.089
|
|
},
|
|
{
|
|
"epoch": 0.0922854387656702,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99701968,
|
|
"step": 95700,
|
|
"train_runtime": 150592.047,
|
|
"train_tokens_per_second": 662.067
|
|
},
|
|
{
|
|
"epoch": 0.09233365477338476,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99740336,
|
|
"step": 95750,
|
|
"train_runtime": 150653.692,
|
|
"train_tokens_per_second": 662.05
|
|
},
|
|
{
|
|
"epoch": 0.09238187078109933,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99777344,
|
|
"step": 95800,
|
|
"train_runtime": 150714.4249,
|
|
"train_tokens_per_second": 662.029
|
|
},
|
|
{
|
|
"epoch": 0.09243008678881388,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99815256,
|
|
"step": 95850,
|
|
"train_runtime": 150775.9767,
|
|
"train_tokens_per_second": 662.01
|
|
},
|
|
{
|
|
"epoch": 0.09247830279652845,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99852752,
|
|
"step": 95900,
|
|
"train_runtime": 150837.1907,
|
|
"train_tokens_per_second": 661.99
|
|
},
|
|
{
|
|
"epoch": 0.09252651880424301,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99890344,
|
|
"step": 95950,
|
|
"train_runtime": 150899.3722,
|
|
"train_tokens_per_second": 661.967
|
|
},
|
|
{
|
|
"epoch": 0.09257473481195758,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99929096,
|
|
"step": 96000,
|
|
"train_runtime": 150961.6954,
|
|
"train_tokens_per_second": 661.95
|
|
},
|
|
{
|
|
"epoch": 0.09262295081967213,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 99966688,
|
|
"step": 96050,
|
|
"train_runtime": 151023.0242,
|
|
"train_tokens_per_second": 661.93
|
|
},
|
|
{
|
|
"epoch": 0.09267116682738669,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100004656,
|
|
"step": 96100,
|
|
"train_runtime": 151084.6262,
|
|
"train_tokens_per_second": 661.912
|
|
},
|
|
{
|
|
"epoch": 0.09271938283510126,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100042056,
|
|
"step": 96150,
|
|
"train_runtime": 151146.3091,
|
|
"train_tokens_per_second": 661.889
|
|
},
|
|
{
|
|
"epoch": 0.09276759884281581,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.2900853729248047,
|
|
"num_input_tokens_seen": 100079248,
|
|
"step": 96200,
|
|
"train_runtime": 151207.8982,
|
|
"train_tokens_per_second": 661.865
|
|
},
|
|
{
|
|
"epoch": 0.09281581485053038,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.1300486946105957,
|
|
"num_input_tokens_seen": 100117448,
|
|
"step": 96250,
|
|
"train_runtime": 151269.7818,
|
|
"train_tokens_per_second": 661.847
|
|
},
|
|
{
|
|
"epoch": 0.09286403085824493,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0749733543395996,
|
|
"num_input_tokens_seen": 100156288,
|
|
"step": 96300,
|
|
"train_runtime": 151331.2463,
|
|
"train_tokens_per_second": 661.835
|
|
},
|
|
{
|
|
"epoch": 0.0929122468659595,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100193920,
|
|
"step": 96350,
|
|
"train_runtime": 151392.5303,
|
|
"train_tokens_per_second": 661.815
|
|
},
|
|
{
|
|
"epoch": 0.09296046287367406,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.36689125061035155,
|
|
"num_input_tokens_seen": 100231472,
|
|
"step": 96400,
|
|
"train_runtime": 151453.8061,
|
|
"train_tokens_per_second": 661.796
|
|
},
|
|
{
|
|
"epoch": 0.09300867888138863,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100269408,
|
|
"step": 96450,
|
|
"train_runtime": 151514.7836,
|
|
"train_tokens_per_second": 661.78
|
|
},
|
|
{
|
|
"epoch": 0.09305689488910318,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100307448,
|
|
"step": 96500,
|
|
"train_runtime": 151576.2825,
|
|
"train_tokens_per_second": 661.762
|
|
},
|
|
{
|
|
"epoch": 0.09310511089681775,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100345072,
|
|
"step": 96550,
|
|
"train_runtime": 151637.1693,
|
|
"train_tokens_per_second": 661.745
|
|
},
|
|
{
|
|
"epoch": 0.0931533269045323,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100383824,
|
|
"step": 96600,
|
|
"train_runtime": 151698.8311,
|
|
"train_tokens_per_second": 661.731
|
|
},
|
|
{
|
|
"epoch": 0.09320154291224686,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100421872,
|
|
"step": 96650,
|
|
"train_runtime": 151759.6717,
|
|
"train_tokens_per_second": 661.716
|
|
},
|
|
{
|
|
"epoch": 0.09324975891996143,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100460216,
|
|
"step": 96700,
|
|
"train_runtime": 151820.2603,
|
|
"train_tokens_per_second": 661.705
|
|
},
|
|
{
|
|
"epoch": 0.09329797492767598,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100498616,
|
|
"step": 96750,
|
|
"train_runtime": 151881.8222,
|
|
"train_tokens_per_second": 661.69
|
|
},
|
|
{
|
|
"epoch": 0.09334619093539055,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100536616,
|
|
"step": 96800,
|
|
"train_runtime": 151942.6583,
|
|
"train_tokens_per_second": 661.675
|
|
},
|
|
{
|
|
"epoch": 0.09339440694310511,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100574584,
|
|
"step": 96850,
|
|
"train_runtime": 152003.5962,
|
|
"train_tokens_per_second": 661.659
|
|
},
|
|
{
|
|
"epoch": 0.09344262295081968,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100612328,
|
|
"step": 96900,
|
|
"train_runtime": 152065.0067,
|
|
"train_tokens_per_second": 661.64
|
|
},
|
|
{
|
|
"epoch": 0.09349083895853423,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100651328,
|
|
"step": 96950,
|
|
"train_runtime": 152126.1702,
|
|
"train_tokens_per_second": 661.631
|
|
},
|
|
{
|
|
"epoch": 0.0935390549662488,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100689728,
|
|
"step": 97000,
|
|
"train_runtime": 152187.809,
|
|
"train_tokens_per_second": 661.615
|
|
},
|
|
{
|
|
"epoch": 0.09358727097396335,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100727392,
|
|
"step": 97050,
|
|
"train_runtime": 152248.9123,
|
|
"train_tokens_per_second": 661.597
|
|
},
|
|
{
|
|
"epoch": 0.09363548698167792,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100764160,
|
|
"step": 97100,
|
|
"train_runtime": 152310.1669,
|
|
"train_tokens_per_second": 661.572
|
|
},
|
|
{
|
|
"epoch": 0.09368370298939248,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100801984,
|
|
"step": 97150,
|
|
"train_runtime": 152371.3931,
|
|
"train_tokens_per_second": 661.555
|
|
},
|
|
{
|
|
"epoch": 0.09373191899710703,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.761360855102539,
|
|
"num_input_tokens_seen": 100839768,
|
|
"step": 97200,
|
|
"train_runtime": 152433.0089,
|
|
"train_tokens_per_second": 661.535
|
|
},
|
|
{
|
|
"epoch": 0.0937801350048216,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100878032,
|
|
"step": 97250,
|
|
"train_runtime": 152495.266,
|
|
"train_tokens_per_second": 661.516
|
|
},
|
|
{
|
|
"epoch": 0.09382835101253616,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100915944,
|
|
"step": 97300,
|
|
"train_runtime": 152556.9324,
|
|
"train_tokens_per_second": 661.497
|
|
},
|
|
{
|
|
"epoch": 0.09387656702025073,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 100954552,
|
|
"step": 97350,
|
|
"train_runtime": 152618.4588,
|
|
"train_tokens_per_second": 661.483
|
|
},
|
|
{
|
|
"epoch": 0.09392478302796528,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.24944992065429689,
|
|
"num_input_tokens_seen": 100992320,
|
|
"step": 97400,
|
|
"train_runtime": 152679.7162,
|
|
"train_tokens_per_second": 661.465
|
|
},
|
|
{
|
|
"epoch": 0.09397299903567985,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101030648,
|
|
"step": 97450,
|
|
"train_runtime": 152741.3448,
|
|
"train_tokens_per_second": 661.449
|
|
},
|
|
{
|
|
"epoch": 0.0940212150433944,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101068512,
|
|
"step": 97500,
|
|
"train_runtime": 152803.4726,
|
|
"train_tokens_per_second": 661.428
|
|
},
|
|
{
|
|
"epoch": 0.09406943105110897,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101105864,
|
|
"step": 97550,
|
|
"train_runtime": 152864.8419,
|
|
"train_tokens_per_second": 661.407
|
|
},
|
|
{
|
|
"epoch": 0.09411764705882353,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101144272,
|
|
"step": 97600,
|
|
"train_runtime": 152926.8289,
|
|
"train_tokens_per_second": 661.39
|
|
},
|
|
{
|
|
"epoch": 0.0941658630665381,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101181840,
|
|
"step": 97650,
|
|
"train_runtime": 152987.8996,
|
|
"train_tokens_per_second": 661.372
|
|
},
|
|
{
|
|
"epoch": 0.09421407907425265,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101219832,
|
|
"step": 97700,
|
|
"train_runtime": 153049.062,
|
|
"train_tokens_per_second": 661.355
|
|
},
|
|
{
|
|
"epoch": 0.0942622950819672,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101257760,
|
|
"step": 97750,
|
|
"train_runtime": 153110.7834,
|
|
"train_tokens_per_second": 661.337
|
|
},
|
|
{
|
|
"epoch": 0.09431051108968178,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101295760,
|
|
"step": 97800,
|
|
"train_runtime": 153172.5863,
|
|
"train_tokens_per_second": 661.318
|
|
},
|
|
{
|
|
"epoch": 0.09435872709739633,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101333624,
|
|
"step": 97850,
|
|
"train_runtime": 153234.2515,
|
|
"train_tokens_per_second": 661.299
|
|
},
|
|
{
|
|
"epoch": 0.0944069431051109,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101370296,
|
|
"step": 97900,
|
|
"train_runtime": 153295.6402,
|
|
"train_tokens_per_second": 661.273
|
|
},
|
|
{
|
|
"epoch": 0.09445515911282545,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101407648,
|
|
"step": 97950,
|
|
"train_runtime": 153356.7671,
|
|
"train_tokens_per_second": 661.253
|
|
},
|
|
{
|
|
"epoch": 0.09450337512054002,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101445392,
|
|
"step": 98000,
|
|
"train_runtime": 153418.9059,
|
|
"train_tokens_per_second": 661.231
|
|
},
|
|
{
|
|
"epoch": 0.09455159112825458,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101483208,
|
|
"step": 98050,
|
|
"train_runtime": 153480.4035,
|
|
"train_tokens_per_second": 661.213
|
|
},
|
|
{
|
|
"epoch": 0.09459980713596915,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101521072,
|
|
"step": 98100,
|
|
"train_runtime": 153541.9354,
|
|
"train_tokens_per_second": 661.194
|
|
},
|
|
{
|
|
"epoch": 0.0946480231436837,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101558368,
|
|
"step": 98150,
|
|
"train_runtime": 153603.2314,
|
|
"train_tokens_per_second": 661.173
|
|
},
|
|
{
|
|
"epoch": 0.09469623915139827,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.14291729927062988,
|
|
"num_input_tokens_seen": 101596088,
|
|
"step": 98200,
|
|
"train_runtime": 153664.6702,
|
|
"train_tokens_per_second": 661.154
|
|
},
|
|
{
|
|
"epoch": 0.09474445515911283,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101634216,
|
|
"step": 98250,
|
|
"train_runtime": 153726.3923,
|
|
"train_tokens_per_second": 661.137
|
|
},
|
|
{
|
|
"epoch": 0.09479267116682738,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101672520,
|
|
"step": 98300,
|
|
"train_runtime": 153787.5579,
|
|
"train_tokens_per_second": 661.123
|
|
},
|
|
{
|
|
"epoch": 0.09484088717454195,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.05244992733001709,
|
|
"num_input_tokens_seen": 101710496,
|
|
"step": 98350,
|
|
"train_runtime": 153849.0838,
|
|
"train_tokens_per_second": 661.106
|
|
},
|
|
{
|
|
"epoch": 0.0948891031822565,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101748760,
|
|
"step": 98400,
|
|
"train_runtime": 153910.2959,
|
|
"train_tokens_per_second": 661.091
|
|
},
|
|
{
|
|
"epoch": 0.09493731918997107,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.061989483833312986,
|
|
"num_input_tokens_seen": 101786344,
|
|
"step": 98450,
|
|
"train_runtime": 153971.7185,
|
|
"train_tokens_per_second": 661.072
|
|
},
|
|
{
|
|
"epoch": 0.09498553519768563,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101824200,
|
|
"step": 98500,
|
|
"train_runtime": 154033.6847,
|
|
"train_tokens_per_second": 661.052
|
|
},
|
|
{
|
|
"epoch": 0.0950337512054002,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 124.3665625,
|
|
"num_input_tokens_seen": 101861920,
|
|
"step": 98550,
|
|
"train_runtime": 154095.7176,
|
|
"train_tokens_per_second": 661.03
|
|
},
|
|
{
|
|
"epoch": 0.09508196721311475,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101899144,
|
|
"step": 98600,
|
|
"train_runtime": 154156.9698,
|
|
"train_tokens_per_second": 661.009
|
|
},
|
|
{
|
|
"epoch": 0.09513018322082932,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101936920,
|
|
"step": 98650,
|
|
"train_runtime": 154218.176,
|
|
"train_tokens_per_second": 660.992
|
|
},
|
|
{
|
|
"epoch": 0.09517839922854388,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 101974248,
|
|
"step": 98700,
|
|
"train_runtime": 154279.6464,
|
|
"train_tokens_per_second": 660.97
|
|
},
|
|
{
|
|
"epoch": 0.09522661523625844,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102011080,
|
|
"step": 98750,
|
|
"train_runtime": 154341.1528,
|
|
"train_tokens_per_second": 660.945
|
|
},
|
|
{
|
|
"epoch": 0.095274831243973,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.062340917587280276,
|
|
"num_input_tokens_seen": 102048784,
|
|
"step": 98800,
|
|
"train_runtime": 154402.1144,
|
|
"train_tokens_per_second": 660.929
|
|
},
|
|
{
|
|
"epoch": 0.09532304725168755,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102087064,
|
|
"step": 98850,
|
|
"train_runtime": 154463.6807,
|
|
"train_tokens_per_second": 660.913
|
|
},
|
|
{
|
|
"epoch": 0.09537126325940212,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102124592,
|
|
"step": 98900,
|
|
"train_runtime": 154525.2035,
|
|
"train_tokens_per_second": 660.893
|
|
},
|
|
{
|
|
"epoch": 0.09541947926711668,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102162328,
|
|
"step": 98950,
|
|
"train_runtime": 154586.8039,
|
|
"train_tokens_per_second": 660.874
|
|
},
|
|
{
|
|
"epoch": 0.09546769527483125,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102199912,
|
|
"step": 99000,
|
|
"train_runtime": 154648.2775,
|
|
"train_tokens_per_second": 660.854
|
|
},
|
|
{
|
|
"epoch": 0.0955159112825458,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102238704,
|
|
"step": 99050,
|
|
"train_runtime": 154710.2924,
|
|
"train_tokens_per_second": 660.84
|
|
},
|
|
{
|
|
"epoch": 0.09556412729026037,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102276632,
|
|
"step": 99100,
|
|
"train_runtime": 154771.6876,
|
|
"train_tokens_per_second": 660.823
|
|
},
|
|
{
|
|
"epoch": 0.09561234329797492,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.957949447631836,
|
|
"num_input_tokens_seen": 102313776,
|
|
"step": 99150,
|
|
"train_runtime": 154832.5901,
|
|
"train_tokens_per_second": 660.803
|
|
},
|
|
{
|
|
"epoch": 0.0956605593056895,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102351776,
|
|
"step": 99200,
|
|
"train_runtime": 154893.8346,
|
|
"train_tokens_per_second": 660.787
|
|
},
|
|
{
|
|
"epoch": 0.09570877531340405,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102388160,
|
|
"step": 99250,
|
|
"train_runtime": 154955.3583,
|
|
"train_tokens_per_second": 660.759
|
|
},
|
|
{
|
|
"epoch": 0.09575699132111862,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102425848,
|
|
"step": 99300,
|
|
"train_runtime": 155016.5754,
|
|
"train_tokens_per_second": 660.741
|
|
},
|
|
{
|
|
"epoch": 0.09580520732883317,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.04968575954437256,
|
|
"num_input_tokens_seen": 102463304,
|
|
"step": 99350,
|
|
"train_runtime": 155077.6004,
|
|
"train_tokens_per_second": 660.723
|
|
},
|
|
{
|
|
"epoch": 0.09585342333654773,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102501128,
|
|
"step": 99400,
|
|
"train_runtime": 155138.8062,
|
|
"train_tokens_per_second": 660.706
|
|
},
|
|
{
|
|
"epoch": 0.0959016393442623,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102538688,
|
|
"step": 99450,
|
|
"train_runtime": 155200.3885,
|
|
"train_tokens_per_second": 660.686
|
|
},
|
|
{
|
|
"epoch": 0.09594985535197685,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102575504,
|
|
"step": 99500,
|
|
"train_runtime": 155261.9554,
|
|
"train_tokens_per_second": 660.661
|
|
},
|
|
{
|
|
"epoch": 0.09599807135969142,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102612320,
|
|
"step": 99550,
|
|
"train_runtime": 155323.6141,
|
|
"train_tokens_per_second": 660.636
|
|
},
|
|
{
|
|
"epoch": 0.09604628736740597,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102650952,
|
|
"step": 99600,
|
|
"train_runtime": 155385.0456,
|
|
"train_tokens_per_second": 660.623
|
|
},
|
|
{
|
|
"epoch": 0.09609450337512054,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102688096,
|
|
"step": 99650,
|
|
"train_runtime": 155446.4974,
|
|
"train_tokens_per_second": 660.601
|
|
},
|
|
{
|
|
"epoch": 0.0961427193828351,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 58.745751953125,
|
|
"num_input_tokens_seen": 102725128,
|
|
"step": 99700,
|
|
"train_runtime": 155507.981,
|
|
"train_tokens_per_second": 660.578
|
|
},
|
|
{
|
|
"epoch": 0.09619093539054967,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102762768,
|
|
"step": 99750,
|
|
"train_runtime": 155569.341,
|
|
"train_tokens_per_second": 660.559
|
|
},
|
|
{
|
|
"epoch": 0.09623915139826422,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102799768,
|
|
"step": 99800,
|
|
"train_runtime": 155630.8643,
|
|
"train_tokens_per_second": 660.536
|
|
},
|
|
{
|
|
"epoch": 0.09628736740597879,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102837552,
|
|
"step": 99850,
|
|
"train_runtime": 155692.7166,
|
|
"train_tokens_per_second": 660.516
|
|
},
|
|
{
|
|
"epoch": 0.09633558341369335,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102875208,
|
|
"step": 99900,
|
|
"train_runtime": 155753.9297,
|
|
"train_tokens_per_second": 660.498
|
|
},
|
|
{
|
|
"epoch": 0.0963837994214079,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.055871224403381346,
|
|
"num_input_tokens_seen": 102912360,
|
|
"step": 99950,
|
|
"train_runtime": 155815.1891,
|
|
"train_tokens_per_second": 660.477
|
|
},
|
|
{
|
|
"epoch": 0.09643201542912247,
|
|
"grad_norm": NaN,
|
|
"learning_rate": 0.0001959743877533278,
|
|
"loss": 0.0,
|
|
"num_input_tokens_seen": 102949296,
|
|
"step": 100000,
|
|
"train_runtime": 155876.7999,
|
|
"train_tokens_per_second": 660.453
|
|
},
|
|
{
|
|
"epoch": 0.09643201542912247,
|
|
"eval_loss": 9.197757720947266,
|
|
"eval_runtime": 235.8912,
|
|
"eval_samples_per_second": 4.239,
|
|
"eval_steps_per_second": 4.239,
|
|
"num_input_tokens_seen": 102949296,
|
|
"step": 100000
|
|
}
|
|
],
|
|
"logging_steps": 50,
|
|
"max_steps": 1037000,
|
|
"num_input_tokens_seen": 102949296,
|
|
"num_train_epochs": 9223372036854775807,
|
|
"save_steps": 10000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 4.4181327445115535e+18,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|