/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/torch/cuda/__init__.py:734: UserWarning: Can't initialize NVML
  warnings.warn("Can't initialize NVML")
[INFO|2026-10-13 02:56:22] llamafactory.hparams.parser:651 >> Process rank: 0, world size: 1, device: cuda:0, distributed training: False, compute dtype: torch.bfloat16
[INFO|configuration_utils.py:765] 2026-10-13 02:56:22,232 >> loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
[INFO|configuration_utils.py:841] 2026-10-13 02:56:22,241 >> Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}

Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
[INFO|configuration_utils.py:765] 2026-10-13 02:56:23,843 >> loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
[INFO|configuration_utils.py:841] 2026-10-13 02:56:23,846 >> Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}

[INFO|configuration_utils.py:765] 2026-10-13 02:56:23,991 >> loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
[INFO|configuration_utils.py:841] 2026-10-13 02:56:23,995 >> Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}

[INFO|2026-10-13 02:56:24] llamafactory.data.loader:144 >> Loading dataset aya_slovak_hpo_30k.jsonl...
training example:
input_ids:
[20548, 336, 349, 396, 13126, 369, 13966, 264, 3638, 28723, 12018, 264, 2899, 369, 6582, 1999, 2691, 274, 272, 2159, 28723, 13, 13, 27332, 3133, 3112, 28747, 13, 28828, 2176, 28711, 28863, 29114, 10268, 28709, 6612, 28714, 2892, 493, 363, 6294, 10719, 363, 3811, 28723, 7379, 626, 28889, 307, 14637, 311, 28768, 2218, 22885, 3748, 28725, 446, 6909, 28820, 637, 3531, 598, 28820, 284, 8341, 6729, 345, 28738, 28739, 363, 8357, 28710, 307, 14637, 311, 28768, 626, 363, 29826, 17339, 28723, 524, 4634, 28711, 570, 1879, 261, 28863, 532, 613, 14483, 28718, 28723, 367, 280, 28879, 570, 9335, 3175, 29826, 626, 323, 7509, 17984, 2950, 28718, 16986, 29826, 28708, 345, 15962, 28739, 363, 3292, 10719, 6612, 529, 28710, 818, 5237, 626, 4845, 1879, 15173, 537, 284, 8341, 705, 28723, 367, 280, 28879, 570, 4415, 28716, 28797, 9335, 3175, 29826, 626, 323, 412, 8514, 16986, 29826, 28708, 345, 15962, 28739, 1879, 15173, 537, 1221, 4566, 28718, 325, 28707, 28723, 461, 28723, 724, 494, 8891, 24160, 28725, 8582, 28862, 24160, 28725, 20532, 28764, 271, 28725, 438, 29365, 15745, 1319, 12035, 28862, 8269, 284, 28827, 2762, 28709, 264, 4798, 8359, 1450, 8325, 12121, 1798, 420, 762, 1089, 290, 28906, 18765, 724, 2331, 29114, 1221, 4304, 1780, 363, 13881, 29826, 316, 2085, 28708, 28723, 22627, 28873, 263, 335, 20208, 284, 28827, 2762, 28709, 264, 4798, 5424, 10056, 1286, 290, 28906, 18765, 724, 2331, 29114, 11323, 10719, 12490, 363, 13881, 29826, 316, 284, 8341, 2390, 28723, 22127, 280, 28879, 21022, 1150, 424, 724, 28827, 1144, 28873, 340, 17066, 270, 21022, 485, 284, 8341, 705, 28725, 446, 6909, 28797, 637, 28705, 29114, 28708, 28879, 4798, 6612, 28827, 1100, 28768, 28863, 28723, 320, 412, 28879, 637, 15612, 28716, 28889, 28726, 1150, 424, 19523, 412, 28873, 276, 28797, 2390, 284, 8341, 2390, 363, 23407, 11277, 9538, 2085, 28708, 28723, 9532, 2144, 686, 7865, 28718, 341, 14475, 1687, 28706, 18037, 452, 270, 8269, 284, 8341, 705, 28725, 290, 4827, 486, 2710, 2144, 332, 1800, 16344, 29114, 6588, 269, 28862, 28711, 28863, 686, 1653, 5388, 28718, 710, 261, 1296, 28709, 284, 8341, 705, 28723, 351, 28711, 1371, 28797, 1776, 29826, 8269, 284, 8341, 705, 268, 28863, 1776, 29826, 8269, 1879, 3497, 598, 8269, 8631, 28879, 279, 412, 28725, 12121, 7988, 268, 28863, 24270, 12115, 28797, 1879, 5626, 263, 28862, 8269, 8631, 28879, 279, 412, 28723, 318, 15612, 1473, 276, 15690, 2245, 626, 15690, 307, 14637, 311, 28768, 300, 15469, 28711, 570, 446, 450, 4798, 29826, 333, 28729, 1879, 319, 3976, 294, 405, 28768, 4882, 405, 28725, 534, 28724, 2710, 724, 313, 4827, 2245, 626, 28889, 20532, 28764, 271, 28723, 10650, 300, 12235, 28827, 28873, 424, 268, 27172, 2245, 28723, 1054, 15504, 28879, 424, 724, 313, 8768, 4545, 504, 270, 8269, 2124, 2245, 626, 12689, 4584, 10906, 28718, 710, 18782, 28879, 28715, 28797, 1135, 10356, 28723, 2645, 28764, 12275, 28820, 28873, 29114, 13067, 549, 2892, 5872, 3811, 8631, 25991, 3026, 29114, 408, 28906, 28764, 485, 2082, 1403, 12121, 1798, 1773, 29826, 28729, 22160, 710, 408, 28906, 28764, 485, 1135, 10874, 1776, 4536, 28873, 300, 23407, 11277, 9538, 2085, 28708, 28723, 22127, 3361, 13470, 1150, 317, 28873, 424, 2082, 7330, 511, 2085, 28708, 28723, 401, 492, 13591, 28820, 261, 2220, 28862, 10766, 381, 28827, 486, 29114, 363, 28879, 4689, 3418, 28879, 21775, 29114, 280, 28723, 418, 28820, 11277, 28716, 6294, 26177, 903, 12689, 6612, 20122, 28733, 12868, 291, 2124, 2085, 28708, 1879, 6670, 28862, 9348, 493, 686, 375, 5620, 386, 28862, 28827, 28725, 23374, 4536, 25306, 16388, 957, 450, 15612, 28764, 2126, 29114, 511, 2152, 363, 25769, 14110, 17413, 26177, 903, 28873, 15808, 19396, 28723, 351, 28906, 28879, 3811, 14628, 28879, 8631, 28879, 28710, 29114, 307, 14637, 311, 28768, 7379, 1879, 277, 7939, 1879, 724, 313, 8768, 2245, 28718, 363, 446, 551, 9538, 12121, 1798, 24473, 21694, 300, 261, 5869, 28723, 384, 28728, 491, 28712, 4566, 15469, 28711, 570, 1879, 2245, 28725, 534, 28724, 2710, 7463, 15612, 13335, 28728, 4371, 1144, 28723, 10650, 300, 15469, 28711, 570, 1879, 1160, 28709, 28879, 3907, 13288, 491, 363, 3292, 10719, 6612, 529, 28710, 818, 5237, 626, 4845, 28725, 534, 28724, 637, 686, 598, 5237, 5945, 17984, 28718, 2117, 18904, 3146, 515, 13288, 25208, 28723, 367, 280, 28879, 570, 12472, 1006, 5872, 28863, 358, 446, 311, 4845, 1879, 6149, 783, 494, 28718, 2245, 28718, 363, 17984, 28718, 405, 13288, 491, 28723, 13343, 29826, 28729, 385, 29114, 284, 8341, 705, 28747, 399, 3711, 3175, 29826, 626, 12990, 17984, 28718, 2117, 268, 6125, 15690, 345, 28738, 28739, 16986, 29826, 28708, 1773, 29826, 10641, 2124, 345, 28738, 28739, 582, 20524, 12214, 1773, 29826, 28729, 385, 29114, 284, 8341, 705, 28723, 351, 28906, 28879, 3811, 14628, 28879, 8631, 28879, 28710, 29114, 307, 14637, 311, 28768, 15173, 537, 28718, 325, 849, 3748, 28725, 446, 6909, 28820, 3061, 28720, 300, 28827, 1520, 6612, 749, 1780, 20532, 28764, 271, 586, 28873, 28710, 363, 8357, 28710, 307, 14637, 311, 28768, 626, 363, 29826, 17339, 28731, 1879, 686, 6729, 1773, 29826, 28729, 22160, 284, 8341, 705, 28723, 550, 11245, 412, 28747, 550, 11245, 412, 1683, 28827, 16032, 271, 1342, 4295, 3191, 316, 28729, 6449, 2245, 28718, 28723, 367, 280, 28879, 570, 9335, 3175, 29826, 626, 323, 7509, 17984, 2950, 28718, 16986, 29826, 28708, 22885, 2557, 28725, 446, 6909, 28820, 637, 3531, 598, 28820, 345, 28741, 28739, 1879, 22954, 338, 28718, 297, 12689, 345, 28741, 28739, 686, 2129, 28710, 29114, 16986, 28863, 358, 28723, 17563, 971, 28747, 17563, 971, 582, 20524, 12214, 1342, 28764, 1193, 1342, 4295, 5765, 6175, 2959, 15416, 28710, 13288, 491, 3589, 28723, 9532, 484, 28717, 3811, 18904, 17101, 29114, 22399, 971, 28725, 15612, 13335, 28728, 4371, 28711, 570, 13288, 20996, 28725, 446, 6909, 28797, 484, 28717, 3811, 18904, 17101, 29114, 28725, 264, 2513, 300, 8631, 28879, 570, 9335, 3175, 29826, 626, 323, 7509, 17984, 2950, 28718, 16986, 29826, 28708, 22885, 2557, 268, 345, 28741, 28739, 264, 28790, 28724, 537, 424, 2245, 626, 28889, 307, 14637, 311, 28768, 28723, 550, 28724, 537, 424, 284, 28827, 2762, 28709, 28723, 1921, 313, 1150, 424, 268, 27172, 2245, 28723, 500, 783, 494, 424, 1773, 29826, 28729, 385, 29114, 264, 4321, 303, 715, 2245, 28718, 28723, 550, 28724, 28764, 1520, 28862, 424, 1773, 22605, 284, 8341, 705, 28723, 2, 13, 13]
inputs:
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Zhrnúť tento článok v jednej vete. Textový nástroj je ikona, ktorá sa podobá písmenu "T" v paneli nástrojov vľavo. Kliknite na túto ikonu. Použite rozbaľovaciu ponuku vedľa "Character" v hornej časti obrazovky na výber písma. Použite druhé rozbaľovacie menu vedľa "Character" na výber formátu (t. j. pravidelný, tučný, kurzor, atď.). Tradičné písmo ako Times New Roman alebo Garamond môže pridať formálny vzhľad loga. Bezšerifové písmo ako Helvetica môže pridať modernejší vzhľad písmu. Nepoužívajte príliš dekoratívne písma, ktoré sa ťažko čítajú. Tiež sa vyhýbajte zmiešanému písmu v návrhu loga. Ak si z internetu stiahnete bezplatné písma, mali by ste si uvedomiť licenčnú zmluvu pre tieto písma. Mnohé voľné písma sú voľné na osobné použitie, ale nie sú povolené na komerčné použitie. S vybraným textovým nástrojom kliknite kdekoľvek na grafickej doske, aby ste pridali textový kurzor. Potom napíšte svoj text. Zvážte pridanie samostatného textového objektu pre každé slovo. Obzvlášť ak plánujete používať rôzne farby alebo veľkosti pre rôzne slová vo vašom návrhu loga. Nepridávaj ešte farbu do loga. Farebná tlač nemusí byť vždy možnosťou. Návrh jednoduchého čierno-bieleho loga na začiatok zabezpečí, že vaše logo bude vyzerať dobre v jeho najjednoduchšej forme. Môžete tiež použiť nástroj Text na ceste na pridanie textu v kruhu alebo zakrivenom tvare. Dvakrát kliknite na text, aby ste ho vyzdvihli. Potom kliknite na položku znak v hornej časti obrazovky, aby sa zobrazila ponuka nastavenia znakov. Použite nasledujúce kroky na úpravu textu v ponuke znak. Veľkosť písma: Rozbaľovacia ponuka s malým "T" vedľa veľkého "T" upravuje veľkosť písma. Môžete tiež použiť nástroj výberu (ikona, ktorá pripomína čierny kurzor myši v paneli nástrojov vľavo) na zmenu veľkosti písma. Vedenie: Vedenie mení priestor medzi riadkami textu. Použite rozbaľovaciu ponuku vedľa ikony, ktorá sa podobá "A" na vrchu iného "A" zmeniť vedúce. Kerning: Kerning upravuje medzery medzi konkrétnymi znakmi. Ak chcete nastaviť kerning, vyzdvihnite znaky, ktoré chcete nastaviť, a potom použite rozbaľovaciu ponuku vedľa ikony s "A" aVyberte textový nástroj. Vyberte písmo. Pridajte svoj text. Upravte veľkosť a odstup textu. Vyznačte vektor písma.</s>


label_ids:
[-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 28790, 28724, 537, 424, 2245, 626, 28889, 307, 14637, 311, 28768, 28723, 550, 28724, 537, 424, 284, 28827, 2762, 28709, 28723, 1921, 313, 1150, 424, 268, 27172, 2245, 28723, 500, 783, 494, 424, 1773, 29826, 28729, 385, 29114, 264, 4321, 303, 715, 2245, 28718, 28723, 550, 28724, 28764, 1520, 28862, 424, 1773, 22605, 284, 8341, 705, 28723, 2, 13, 13]
labels:
Vyberte textový nástroj. Vyberte písmo. Pridajte svoj text. Upravte veľkosť a odstup textu. Vyznačte vektor písma.</s>


eval example:
input_ids:
[20548, 336, 349, 396, 13126, 369, 13966, 264, 3638, 28723, 12018, 264, 2899, 369, 6582, 1999, 2691, 274, 272, 2159, 28723, 13, 13, 27332, 3133, 3112, 28747, 13, 28965, 28709, 637, 8631, 25991, 3026, 28725, 13067, 10531, 28729, 350, 2591, 686, 3023, 28862, 28827, 284, 28873, 269, 13096, 28711, 28863, 6149, 3399, 28804, 550, 13881, 29826, 316, 300, 1879, 7871, 338, 28820, 6936, 1150, 28863, 7340, 6957, 8905, 3907, 12235, 28827, 28873, 424, 5765, 772, 28725, 446, 6909, 28889, 14848, 912, 12214, 4321, 28720, 751, 29365, 28723, 351, 28906, 18765, 298, 486, 29114, 28705, 28740, 387, 28705, 28750, 28734, 22116, 28827, 28723, 8294, 772, 28747, 13, 13, 27332, 12107, 28747, 13, 15774, 4295, 28873, 841, 335, 681, 28820, 9335, 1294, 17122, 29114, 549, 350, 5905, 2218, 6612, 28710, 26041, 28862, 485, 686, 350, 28720, 2947, 20946, 6670, 298, 28725, 23374, 17984, 28863, 28729, 433, 408, 28906, 7745, 271, 350, 385, 29114, 363, 1879, 28873, 300, 6294, 291, 28723, 560, 12423, 841, 335, 681, 28820, 9335, 1294, 17122, 29114, 28725, 9335, 1294, 17122, 29114, 12121, 28714, 363, 408, 10422, 1189, 6294, 8269, 2124, 4415, 9538, 28725, 307, 10422, 14628, 28879, 17984, 28863, 2117, 1776, 29826, 7330, 363, 1879, 28873, 15808, 1117, 458, 28723, 9532, 686, 346, 28716, 28820, 6149, 311, 1705, 363, 1326, 493, 517, 28863, 267, 28725, 668, 328, 412, 28716, 433, 637, 1879, 1627, 29826, 28711, 1371, 3382, 350, 5856, 1252, 28718, 9335, 1294, 17122, 29114, 28725, 534, 28724, 991, 28706, 13288, 626, 28718, 686, 293, 316, 2689, 284, 28906, 670, 7988, 28862, 9619, 4147, 15690, 28723, 9532, 284, 374, 284, 374, 626, 380, 29826, 686, 3023, 28862, 28827, 6149, 3399, 284, 28873, 269, 535, 28725, 290, 28906, 28879, 5037, 363, 12472, 1006, 5872, 28863, 675, 6739, 686, 293, 12035, 29114, 4321, 328, 10719, 28873, 7509, 4321, 3399, 284, 28873, 269, 535, 28725, 3061, 28862, 300, 637, 668, 328, 412, 28716, 433, 1879, 363, 28711, 24043, 2737, 841, 335, 681, 28863, 9335, 1294, 17122, 29114, 28723, 351, 28906, 28879, 5037, 637, 363, 28764, 1705, 29114, 1219, 28729, 9041, 284, 28873, 269, 535, 363, 711, 28768, 532, 818, 4081, 28710, 264, 363, 846, 12035, 29114, 6149, 452, 485, 297, 28889, 4415, 28716, 28725, 668, 328, 412, 28716, 1150, 28863, 28717, 637, 1879, 1342, 28764, 313, 551, 28716, 626, 28863, 9335, 1294, 17122, 29114, 28723, 384, 493, 266, 2591, 23371, 1627, 29826, 28711, 1371, 3382, 350, 5856, 9883, 668, 5053, 28862, 21775, 29114, 28725, 446, 6909, 28820, 2413, 5856, 485, 284, 374, 12214, 1326, 493, 517, 28863, 643, 28725, 637, 363, 4273, 28862, 279, 300, 3614, 314, 4371, 28718, 668, 328, 412, 2799, 1879, 287, 2563, 2023, 28764, 6454, 28723, 2, 13, 13]
inputs:
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Čo sa používa, ak škodca zničí pšeničnú úrodu? Vzhľadom na predchádzajúcu otázku napíšte kontext, ktorý obsahuje odpoveď. Môže to byť 1 - 20 vetí. Kontext:

### Response:
Medzišpecifická rozmanitosť plodín je čiastočne zodpovedná za to, že ponúkame rôznorodosť v našom jedle. Intraspecifická rozmanitosť, rozmanitosť alel v rámci jedného druhu, nám tiež ponúka voľbu v našej strave. Ak zlyhá úroda v monokultúre, spoliehame sa na poľnohospodársku rozmanitosť, aby sme znovu zasadili pôdu niečím novým. Ak pest pestovateľ zničí úrodu pšenice, môžeme v nasledujúcom roku zasadiť odolnejšiu odrodu pšenice, pričom sa spoliehame na vnútrospecifickú rozmanitosť. Môžeme sa vzdať produkcie pšenice v tejto oblasti a vysadiť úplne iný druh, spoliehajúc sa na medzidruhovú rozmanitosť. Dokonca aj poľnohospodárska spoločnosť, ktorá primárne pestuje monokultúry, sa v určitom okamihu spolieha na biodiverzitu.</s>


label_ids:
[-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 15774, 4295, 28873, 841, 335, 681, 28820, 9335, 1294, 17122, 29114, 549, 350, 5905, 2218, 6612, 28710, 26041, 28862, 485, 686, 350, 28720, 2947, 20946, 6670, 298, 28725, 23374, 17984, 28863, 28729, 433, 408, 28906, 7745, 271, 350, 385, 29114, 363, 1879, 28873, 300, 6294, 291, 28723, 560, 12423, 841, 335, 681, 28820, 9335, 1294, 17122, 29114, 28725, 9335, 1294, 17122, 29114, 12121, 28714, 363, 408, 10422, 1189, 6294, 8269, 2124, 4415, 9538, 28725, 307, 10422, 14628, 28879, 17984, 28863, 2117, 1776, 29826, 7330, 363, 1879, 28873, 15808, 1117, 458, 28723, 9532, 686, 346, 28716, 28820, 6149, 311, 1705, 363, 1326, 493, 517, 28863, 267, 28725, 668, 328, 412, 28716, 433, 637, 1879, 1627, 29826, 28711, 1371, 3382, 350, 5856, 1252, 28718, 9335, 1294, 17122, 29114, 28725, 534, 28724, 991, 28706, 13288, 626, 28718, 686, 293, 316, 2689, 284, 28906, 670, 7988, 28862, 9619, 4147, 15690, 28723, 9532, 284, 374, 284, 374, 626, 380, 29826, 686, 3023, 28862, 28827, 6149, 3399, 284, 28873, 269, 535, 28725, 290, 28906, 28879, 5037, 363, 12472, 1006, 5872, 28863, 675, 6739, 686, 293, 12035, 29114, 4321, 328, 10719, 28873, 7509, 4321, 3399, 284, 28873, 269, 535, 28725, 3061, 28862, 300, 637, 668, 328, 412, 28716, 433, 1879, 363, 28711, 24043, 2737, 841, 335, 681, 28863, 9335, 1294, 17122, 29114, 28723, 351, 28906, 28879, 5037, 637, 363, 28764, 1705, 29114, 1219, 28729, 9041, 284, 28873, 269, 535, 363, 711, 28768, 532, 818, 4081, 28710, 264, 363, 846, 12035, 29114, 6149, 452, 485, 297, 28889, 4415, 28716, 28725, 668, 328, 412, 28716, 1150, 28863, 28717, 637, 1879, 1342, 28764, 313, 551, 28716, 626, 28863, 9335, 1294, 17122, 29114, 28723, 384, 493, 266, 2591, 23371, 1627, 29826, 28711, 1371, 3382, 350, 5856, 9883, 668, 5053, 28862, 21775, 29114, 28725, 446, 6909, 28820, 2413, 5856, 485, 284, 374, 12214, 1326, 493, 517, 28863, 643, 28725, 637, 363, 4273, 28862, 279, 300, 3614, 314, 4371, 28718, 668, 328, 412, 2799, 1879, 287, 2563, 2023, 28764, 6454, 28723, 2, 13, 13]
labels:
Medzišpecifická rozmanitosť plodín je čiastočne zodpovedná za to, že ponúkame rôznorodosť v našom jedle. Intraspecifická rozmanitosť, rozmanitosť alel v rámci jedného druhu, nám tiež ponúka voľbu v našej strave. Ak zlyhá úroda v monokultúre, spoliehame sa na poľnohospodársku rozmanitosť, aby sme znovu zasadili pôdu niečím novým. Ak pest pestovateľ zničí úrodu pšenice, môžeme v nasledujúcom roku zasadiť odolnejšiu odrodu pšenice, pričom sa spoliehame na vnútrospecifickú rozmanitosť. Môžeme sa vzdať produkcie pšenice v tejto oblasti a vysadiť úplne iný druh, spoliehajúc sa na medzidruhovú rozmanitosť. Dokonca aj poľnohospodárska spoločnosť, ktorá primárne pestuje monokultúry, sa v určitom okamihu spolieha na biodiverzitu.</s>


[INFO|configuration_utils.py:765] 2026-10-13 02:56:25,469 >> loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
[INFO|configuration_utils.py:841] 2026-10-13 02:56:25,473 >> Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}

[INFO|2026-10-13 02:56:25] llamafactory.model.model_utils.kv_cache:144 >> KV cache is disabled during training.
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/unsloth/__init__.py:165: UserWarning: WARNING: Unsloth should be imported before [trl, transformers, peft] to ensure all optimizations are applied. Your code may run slower or encounter memory issues without these optimizations.

Please restructure your imports with 'import unsloth' at the top of your file.
  from ._gpu_init import *
🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/torch/cuda/__init__.py:734: UserWarning: Can't initialize NVML
  warnings.warn("Can't initialize NVML")
🦥 Unsloth Zoo will now patch everything to make training faster!
loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}

Unsloth: WARNING `trust_remote_code` is True.
Are you certain you want to do remote code execution?
==((====))==  Unsloth 2026.6.1: Fast Mistral patching. Transformers: 5.5.0.
   \\   /|    NVIDIA RTX A4500. Num GPUs = 1. Max memory: 19.698 GB. Platform: Linux.
O^O/ \_/ \    Torch: 2.6.0+cu124. CUDA: 8.6. CUDA Toolkit: 12.4. Triton: 3.2.0
\        /    Bfloat16 = TRUE. FA [Xformers = 0.0.29.post3. FA2 = False]
 "-____-"     Free license: http://github.com/unslothai/unsloth
Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!
loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}

loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}

loading weights file model.safetensors from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/model.safetensors.index.json
Will use dtype=torch.bfloat16 as defined in model's config object
Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "output_attentions": false,
  "output_hidden_states": false,
  "pad_token_id": 2,
  "use_cache": true
}


Loading weights:   0%|          | 0/291 [00:00<?, ?it/s]
Loading weights:   2%|▏         | 5/291 [00:00<00:06, 43.02it/s]
Loading weights:   6%|▌         | 18/291 [00:00<00:03, 87.41it/s]
Loading weights:  11%|█         | 31/291 [00:00<00:02, 100.85it/s]
Loading weights:  14%|█▍        | 42/291 [00:00<00:02, 95.56it/s] 
Loading weights:  19%|█▉        | 56/291 [00:00<00:02, 109.46it/s]
Loading weights:  23%|██▎       | 68/291 [00:00<00:02, 101.69it/s]
Loading weights:  29%|██▉       | 85/291 [00:00<00:01, 114.14it/s]
Loading weights:  33%|███▎      | 97/291 [00:00<00:01, 103.52it/s]
Loading weights:  37%|███▋      | 108/291 [00:01<00:01, 105.19it/s]
Loading weights:  41%|████      | 119/291 [00:01<00:01, 104.64it/s]
Loading weights:  45%|████▌     | 131/291 [00:01<00:01, 104.75it/s]
Loading weights:  49%|████▉     | 142/291 [00:01<00:01, 104.44it/s]
Loading weights:  54%|█████▍    | 158/291 [00:01<00:01, 118.00it/s]
Loading weights:  58%|█████▊    | 170/291 [00:01<00:01, 113.59it/s]
Loading weights:  63%|██████▎   | 182/291 [00:01<00:00, 112.12it/s]
Loading weights:  67%|██████▋   | 194/291 [00:01<00:00, 106.45it/s]
Loading weights:  70%|███████   | 205/291 [00:01<00:00, 99.80it/s] 
Loading weights:  74%|███████▍  | 216/291 [00:02<00:00, 100.64it/s]
Loading weights:  79%|███████▊  | 229/291 [00:02<00:00, 102.21it/s]
Loading weights:  82%|████████▏ | 240/291 [00:02<00:00, 93.54it/s] 
Loading weights:  87%|████████▋ | 254/291 [00:02<00:00, 105.02it/s]
Loading weights:  91%|█████████ | 265/291 [00:02<00:00, 101.77it/s]
Loading weights:  95%|█████████▍| 276/291 [00:02<00:00, 90.57it/s] 
Loading weights:  99%|█████████▉| 288/291 [00:02<00:00, 96.37it/s]
Loading weights: 100%|██████████| 291/291 [00:02<00:00, 102.62it/s]
loading configuration file generation_config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/generation_config.json
Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2
}

Could not locate the custom_generate/generate.py inside slovak-nlp/mistral-sk-7b.
loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}

loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}

Unsloth: slovak-nlp/mistral-sk-7b had a bad pad_token (</s>). Using pad_token = <unk>.
/home/schwarc/LLaMA-Factory/src/llamafactory/model/model_utils/checkpointing.py:68: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
  @torch.cuda.amp.custom_fwd
/home/schwarc/LLaMA-Factory/src/llamafactory/model/model_utils/checkpointing.py:85: FutureWarning: `torch.cuda.amp.custom_bwd(args...)` is deprecated. Please use `torch.amp.custom_bwd(args..., device_type='cuda')` instead.
  @torch.cuda.amp.custom_bwd
[INFO|2026-10-13 02:56:42] llamafactory.model.model_utils.checkpointing:144 >> Gradient checkpointing enabled.
[INFO|2026-10-13 02:56:42] llamafactory.model.adapter:144 >> Upcasting trainable params to float32.
[INFO|2026-10-13 02:56:42] llamafactory.model.adapter:144 >> Fine-tuning method: LoRA
Unsloth 2026.6.1 patched 32 layers with 32 QKV layers, 32 O layers and 32 MLP layers.
[INFO|2026-10-13 02:56:45] llamafactory.model.loader:144 >> trainable params: 41,943,040 || all params: 7,283,675,136 || trainable%: 0.5758
The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'pad_token_id': 2}.
==((====))==  Unsloth - 2x faster free finetuning | Num GPUs used = 1
   \\   /|    Num examples = 29,000 | Num Epochs = 1 | Total steps = 1,813
O^O/ \_/ \    Batch size per device = 1 | Gradient accumulation steps = 16
\        /    Data Parallel GPUs = 1 | Total batch size (1 x 16 x 1) = 16
 "-____-"     Trainable parameters = 41,943,040 of 7,283,675,136 (0.58% trained)

  0%|          | 0/1813 [00:00<?, ?it/s]`use_return_dict` is deprecated! Use `return_dict` instead!
Unsloth: Double buffering enabled (parallel H2D + compute) for backward pass.
Unsloth: Will smartly offload gradients to save VRAM!

  0%|          | 1/1813 [00:07<3:36:20,  7.16s/it]
  0%|          | 2/1813 [00:13<3:25:26,  6.81s/it]
  0%|          | 3/1813 [00:19<3:05:06,  6.14s/it]
  0%|          | 4/1813 [00:23<2:40:13,  5.31s/it]
  0%|          | 5/1813 [00:29<2:53:22,  5.75s/it]
  0%|          | 6/1813 [00:37<3:11:14,  6.35s/it]
  0%|          | 7/1813 [00:43<3:14:43,  6.47s/it]
  0%|          | 8/1813 [00:49<3:04:56,  6.15s/it]
  0%|          | 9/1813 [00:57<3:19:45,  6.64s/it]
  1%|          | 10/1813 [01:02<3:10:40,  6.35s/it]
                                                   
{'loss': '1.797', 'grad_norm': '2.267', 'learning_rate': '6e-06', 'epoch': '0.005517', 'num_input_tokens_seen': 65928, 'train_runtime': '62.74', 'train_tokens_per_second': '1051'}

  1%|          | 10/1813 [01:02<3:10:40,  6.35s/it]
  1%|          | 11/1813 [01:09<3:11:15,  6.37s/it]
  1%|          | 12/1813 [01:17<3:25:28,  6.85s/it]
  1%|          | 13/1813 [01:21<3:03:18,  6.11s/it]
  1%|          | 14/1813 [01:27<3:03:08,  6.11s/it]
  1%|          | 15/1813 [01:32<2:53:14,  5.78s/it]
  1%|          | 16/1813 [01:38<2:55:32,  5.86s/it]
  1%|          | 17/1813 [01:45<3:00:08,  6.02s/it]
  1%|          | 18/1813 [01:51<3:00:41,  6.04s/it]
  1%|          | 19/1813 [01:57<3:07:00,  6.25s/it]
  1%|          | 20/1813 [02:04<3:05:29,  6.21s/it]
                                                   
{'loss': '1.533', 'grad_norm': '1.407', 'learning_rate': '1.267e-05', 'epoch': '0.01103', 'num_input_tokens_seen': 131352, 'train_runtime': '124', 'train_tokens_per_second': '1059'}

  1%|          | 20/1813 [02:04<3:05:29,  6.21s/it]
  1%|          | 21/1813 [02:10<3:03:51,  6.16s/it]
  1%|          | 22/1813 [02:15<2:54:24,  5.84s/it]
  1%|▏         | 23/1813 [02:20<2:51:10,  5.74s/it]
  1%|▏         | 24/1813 [02:26<2:52:59,  5.80s/it]
  1%|▏         | 25/1813 [02:33<3:05:31,  6.23s/it]
  1%|▏         | 26/1813 [02:41<3:15:17,  6.56s/it]
  1%|▏         | 27/1813 [02:47<3:10:34,  6.40s/it]
  2%|▏         | 28/1813 [02:54<3:15:36,  6.57s/it]
  2%|▏         | 29/1813 [03:02<3:28:43,  7.02s/it]
  2%|▏         | 30/1813 [03:07<3:09:51,  6.39s/it]
                                                   
{'loss': '1.443', 'grad_norm': '1.26', 'learning_rate': '1.933e-05', 'epoch': '0.01655', 'num_input_tokens_seen': 197376, 'train_runtime': '187.1', 'train_tokens_per_second': '1055'}

  2%|▏         | 30/1813 [03:07<3:09:51,  6.39s/it]
  2%|▏         | 31/1813 [03:13<3:10:27,  6.41s/it]
  2%|▏         | 32/1813 [03:19<3:01:57,  6.13s/it]
  2%|▏         | 33/1813 [03:25<3:01:37,  6.12s/it]
  2%|▏         | 34/1813 [03:32<3:15:21,  6.59s/it]
  2%|▏         | 35/1813 [03:39<3:15:38,  6.60s/it]
  2%|▏         | 36/1813 [03:45<3:13:41,  6.54s/it]
  2%|▏         | 37/1813 [03:51<3:00:56,  6.11s/it]
  2%|▏         | 38/1813 [03:56<2:51:17,  5.79s/it]
  2%|▏         | 39/1813 [04:01<2:51:43,  5.81s/it]
  2%|▏         | 40/1813 [04:07<2:53:21,  5.87s/it]
                                                   
{'loss': '1.301', 'grad_norm': '1.084', 'learning_rate': '2.6e-05', 'epoch': '0.02207', 'num_input_tokens_seen': 261168, 'train_runtime': '247.9', 'train_tokens_per_second': '1054'}

  2%|▏         | 40/1813 [04:07<2:53:21,  5.87s/it]
  2%|▏         | 41/1813 [04:13<2:49:31,  5.74s/it]
  2%|▏         | 42/1813 [04:19<2:52:17,  5.84s/it]
  2%|▏         | 43/1813 [04:27<3:08:30,  6.39s/it]
  2%|▏         | 44/1813 [04:33<3:11:22,  6.49s/it]
  2%|▏         | 45/1813 [04:41<3:21:03,  6.82s/it]
  3%|▎         | 46/1813 [04:47<3:13:08,  6.56s/it]
  3%|▎         | 47/1813 [04:52<3:04:15,  6.26s/it]
  3%|▎         | 48/1813 [04:59<3:07:53,  6.39s/it]
  3%|▎         | 49/1813 [05:05<3:06:59,  6.36s/it]
  3%|▎         | 50/1813 [05:12<3:05:33,  6.31s/it]
                                                   
{'loss': '1.326', 'grad_norm': '1.65', 'learning_rate': '3.267e-05', 'epoch': '0.02759', 'num_input_tokens_seen': 330104, 'train_runtime': '312.1', 'train_tokens_per_second': '1058'}

  3%|▎         | 50/1813 [05:12<3:05:33,  6.31s/it]
  3%|▎         | 51/1813 [05:19<3:15:37,  6.66s/it]
  3%|▎         | 52/1813 [05:28<3:38:59,  7.46s/it]
  3%|▎         | 53/1813 [05:34<3:25:19,  7.00s/it]
  3%|▎         | 54/1813 [05:42<3:30:30,  7.18s/it]
  3%|▎         | 55/1813 [05:48<3:23:50,  6.96s/it]
  3%|▎         | 56/1813 [05:55<3:22:37,  6.92s/it]
  3%|▎         | 57/1813 [06:01<3:08:41,  6.45s/it]
  3%|▎         | 58/1813 [06:09<3:25:49,  7.04s/it]
  3%|▎         | 59/1813 [06:16<3:26:35,  7.07s/it]
  3%|▎         | 60/1813 [06:22<3:12:28,  6.59s/it]
                                                   
{'loss': '1.219', 'grad_norm': '1.516', 'learning_rate': '3.933e-05', 'epoch': '0.0331', 'num_input_tokens_seen': 407792, 'train_runtime': '382.1', 'train_tokens_per_second': '1067'}

  3%|▎         | 60/1813 [06:22<3:12:28,  6.59s/it]
  3%|▎         | 61/1813 [06:27<2:58:58,  6.13s/it]
  3%|▎         | 62/1813 [06:32<2:53:30,  5.95s/it]
  3%|▎         | 63/1813 [06:38<2:51:15,  5.87s/it]
  4%|▎         | 64/1813 [06:44<2:49:43,  5.82s/it]
  4%|▎         | 65/1813 [06:51<3:02:19,  6.26s/it]
  4%|▎         | 66/1813 [06:57<3:04:42,  6.34s/it]
  4%|▎         | 67/1813 [07:03<2:59:37,  6.17s/it]
  4%|▍         | 68/1813 [07:10<3:01:38,  6.25s/it]
  4%|▍         | 69/1813 [07:17<3:10:55,  6.57s/it]
  4%|▍         | 70/1813 [07:24<3:19:32,  6.87s/it]
                                                   
{'loss': '1.098', 'grad_norm': '1.199', 'learning_rate': '4.6e-05', 'epoch': '0.03862', 'num_input_tokens_seen': 474368, 'train_runtime': '444.9', 'train_tokens_per_second': '1066'}

  4%|▍         | 70/1813 [07:24<3:19:32,  6.87s/it]
  4%|▍         | 71/1813 [07:30<3:09:12,  6.52s/it]
  4%|▍         | 72/1813 [07:39<3:29:12,  7.21s/it]
  4%|▍         | 73/1813 [07:45<3:15:03,  6.73s/it]
  4%|▍         | 74/1813 [07:51<3:11:53,  6.62s/it]
  4%|▍         | 75/1813 [07:58<3:13:42,  6.69s/it]
  4%|▍         | 76/1813 [08:04<3:08:19,  6.51s/it]
  4%|▍         | 77/1813 [08:11<3:12:07,  6.64s/it]
  4%|▍         | 78/1813 [08:16<3:01:45,  6.29s/it]
  4%|▍         | 79/1813 [08:22<2:54:40,  6.04s/it]
  4%|▍         | 80/1813 [08:28<2:54:55,  6.06s/it]
                                                   
{'loss': '1.126', 'grad_norm': '1.306', 'learning_rate': '5.267e-05', 'epoch': '0.04414', 'num_input_tokens_seen': 541616, 'train_runtime': '508.3', 'train_tokens_per_second': '1065'}

  4%|▍         | 80/1813 [08:28<2:54:55,  6.06s/it]
  4%|▍         | 81/1813 [08:34<2:52:51,  5.99s/it]
  5%|▍         | 82/1813 [08:41<3:02:19,  6.32s/it]
  5%|▍         | 83/1813 [08:48<3:08:55,  6.55s/it]
  5%|▍         | 84/1813 [08:55<3:12:58,  6.70s/it]
  5%|▍         | 85/1813 [09:01<3:07:28,  6.51s/it]
  5%|▍         | 86/1813 [09:07<3:06:01,  6.46s/it]
  5%|▍         | 87/1813 [09:12<2:51:57,  5.98s/it]
  5%|▍         | 88/1813 [09:18<2:51:33,  5.97s/it]
  5%|▍         | 89/1813 [09:24<2:49:58,  5.92s/it]
  5%|▍         | 90/1813 [09:30<2:53:33,  6.04s/it]
                                                   
{'loss': '1.05', 'grad_norm': '1.049', 'learning_rate': '5.933e-05', 'epoch': '0.04966', 'num_input_tokens_seen': 608792, 'train_runtime': '570.7', 'train_tokens_per_second': '1067'}

  5%|▍         | 90/1813 [09:30<2:53:33,  6.04s/it]
  5%|▌         | 91/1813 [09:36<2:49:44,  5.91s/it]
  5%|▌         | 92/1813 [09:41<2:39:43,  5.57s/it]
  5%|▌         | 93/1813 [09:47<2:42:39,  5.67s/it]
  5%|▌         | 94/1813 [09:53<2:48:56,  5.90s/it]
  5%|▌         | 95/1813 [09:59<2:53:21,  6.05s/it]
  5%|▌         | 96/1813 [10:05<2:52:28,  6.03s/it]
  5%|▌         | 97/1813 [10:12<2:56:41,  6.18s/it]
  5%|▌         | 98/1813 [10:17<2:47:12,  5.85s/it]
  5%|▌         | 99/1813 [10:22<2:44:17,  5.75s/it]
  6%|▌         | 100/1813 [10:29<2:48:45,  5.91s/it]
                                                    
{'loss': '1.1', 'grad_norm': '1.002', 'learning_rate': '6.6e-05', 'epoch': '0.05517', 'num_input_tokens_seen': 670936, 'train_runtime': '629.3', 'train_tokens_per_second': '1066'}

  6%|▌         | 100/1813 [10:29<2:48:45,  5.91s/it]
  6%|▌         | 101/1813 [10:35<2:54:45,  6.12s/it]
  6%|▌         | 102/1813 [10:42<2:59:17,  6.29s/it]
  6%|▌         | 103/1813 [10:48<2:56:49,  6.20s/it]
  6%|▌         | 104/1813 [10:55<2:59:00,  6.28s/it]
  6%|▌         | 105/1813 [11:00<2:51:53,  6.04s/it]
  6%|▌         | 106/1813 [11:06<2:51:31,  6.03s/it]
  6%|▌         | 107/1813 [11:12<2:54:21,  6.13s/it]
  6%|▌         | 108/1813 [11:19<2:56:11,  6.20s/it]
  6%|▌         | 109/1813 [11:25<2:55:09,  6.17s/it]
  6%|▌         | 110/1813 [11:32<2:59:47,  6.33s/it]
                                                    
{'loss': '1.11', 'grad_norm': '0.9462', 'learning_rate': '7.267e-05', 'epoch': '0.06069', 'num_input_tokens_seen': 738632, 'train_runtime': '692.1', 'train_tokens_per_second': '1067'}

  6%|▌         | 110/1813 [11:32<2:59:47,  6.33s/it]
  6%|▌         | 111/1813 [11:38<3:02:52,  6.45s/it]
  6%|▌         | 112/1813 [11:45<3:05:05,  6.53s/it]
  6%|▌         | 113/1813 [11:51<3:04:21,  6.51s/it]
  6%|▋         | 114/1813 [11:59<3:13:35,  6.84s/it]
  6%|▋         | 115/1813 [12:05<3:07:00,  6.61s/it]
  6%|▋         | 116/1813 [12:12<3:10:12,  6.73s/it]
  6%|▋         | 117/1813 [12:18<3:01:30,  6.42s/it]
  7%|▋         | 118/1813 [12:24<2:57:56,  6.30s/it]
  7%|▋         | 119/1813 [12:30<2:59:08,  6.34s/it]
  7%|▋         | 120/1813 [12:37<3:00:19,  6.39s/it]
                                                    
{'loss': '1.124', 'grad_norm': '1.452', 'learning_rate': '7.933e-05', 'epoch': '0.06621', 'num_input_tokens_seen': 808824, 'train_runtime': '757.3', 'train_tokens_per_second': '1068'}

  7%|▋         | 120/1813 [12:37<3:00:19,  6.39s/it]
  7%|▋         | 121/1813 [12:41<2:43:41,  5.80s/it]
  7%|▋         | 122/1813 [12:47<2:39:05,  5.64s/it]
  7%|▋         | 123/1813 [12:53<2:46:59,  5.93s/it]
  7%|▋         | 124/1813 [12:58<2:40:51,  5.71s/it]
  7%|▋         | 125/1813 [13:05<2:49:11,  6.01s/it]
  7%|▋         | 126/1813 [13:11<2:51:41,  6.11s/it]
  7%|▋         | 127/1813 [13:16<2:39:11,  5.67s/it]
  7%|▋         | 128/1813 [13:20<2:29:28,  5.32s/it]
  7%|▋         | 129/1813 [13:29<2:52:06,  6.13s/it]
  7%|▋         | 130/1813 [13:35<2:57:22,  6.32s/it]
                                                    
{'loss': '1.061', 'grad_norm': '0.8902', 'learning_rate': '8.6e-05', 'epoch': '0.07172', 'num_input_tokens_seen': 869720, 'train_runtime': '815.8', 'train_tokens_per_second': '1066'}

  7%|▋         | 130/1813 [13:35<2:57:22,  6.32s/it]
  7%|▋         | 131/1813 [13:41<2:53:58,  6.21s/it]
  7%|▋         | 132/1813 [13:47<2:48:13,  6.00s/it]
  7%|▋         | 133/1813 [13:52<2:44:28,  5.87s/it]
  7%|▋         | 134/1813 [13:57<2:36:34,  5.60s/it]
  7%|▋         | 135/1813 [14:02<2:31:44,  5.43s/it]
  8%|▊         | 136/1813 [14:08<2:34:53,  5.54s/it]
  8%|▊         | 137/1813 [14:14<2:38:19,  5.67s/it]
  8%|▊         | 138/1813 [14:21<2:50:23,  6.10s/it]
  8%|▊         | 139/1813 [14:28<2:54:57,  6.27s/it]
  8%|▊         | 140/1813 [14:35<3:01:33,  6.51s/it]
                                                    
{'loss': '1.051', 'grad_norm': '1.229', 'learning_rate': '9.267e-05', 'epoch': '0.07724', 'num_input_tokens_seen': 932000, 'train_runtime': '875.4', 'train_tokens_per_second': '1065'}

  8%|▊         | 140/1813 [14:35<3:01:33,  6.51s/it]
  8%|▊         | 141/1813 [14:41<2:54:08,  6.25s/it]
  8%|▊         | 142/1813 [14:48<3:07:40,  6.74s/it]
  8%|▊         | 143/1813 [14:54<2:55:48,  6.32s/it]
  8%|▊         | 144/1813 [14:59<2:45:31,  5.95s/it]
  8%|▊         | 145/1813 [15:06<2:54:22,  6.27s/it]
  8%|▊         | 146/1813 [15:12<2:52:44,  6.22s/it]
  8%|▊         | 147/1813 [15:17<2:45:16,  5.95s/it]
  8%|▊         | 148/1813 [15:23<2:45:10,  5.95s/it]
  8%|▊         | 149/1813 [15:29<2:44:12,  5.92s/it]
  8%|▊         | 150/1813 [15:35<2:46:37,  6.01s/it]
                                                    
{'loss': '1.109', 'grad_norm': '1.101', 'learning_rate': '9.933e-05', 'epoch': '0.08276', 'num_input_tokens_seen': 997296, 'train_runtime': '935.9', 'train_tokens_per_second': '1066'}

  8%|▊         | 150/1813 [15:35<2:46:37,  6.01s/it]
  8%|▊         | 151/1813 [15:41<2:43:45,  5.91s/it]
  8%|▊         | 152/1813 [15:47<2:41:31,  5.83s/it]
  8%|▊         | 153/1813 [15:52<2:41:09,  5.82s/it]
  8%|▊         | 154/1813 [15:59<2:46:22,  6.02s/it]
  9%|▊         | 155/1813 [16:06<2:55:39,  6.36s/it]
  9%|▊         | 156/1813 [16:12<2:51:46,  6.22s/it]
  9%|▊         | 157/1813 [16:18<2:51:23,  6.21s/it]
  9%|▊         | 158/1813 [16:23<2:42:30,  5.89s/it]
  9%|▉         | 159/1813 [16:29<2:42:57,  5.91s/it]
  9%|▉         | 160/1813 [16:35<2:40:14,  5.82s/it]
                                                    
{'loss': '1.037', 'grad_norm': '1.749', 'learning_rate': '9.999e-05', 'epoch': '0.08828', 'num_input_tokens_seen': 1060096, 'train_runtime': '995.4', 'train_tokens_per_second': '1065'}

  9%|▉         | 160/1813 [16:35<2:40:14,  5.82s/it]
  9%|▉         | 161/1813 [16:41<2:39:26,  5.79s/it]
  9%|▉         | 162/1813 [16:45<2:26:32,  5.33s/it]
  9%|▉         | 163/1813 [16:52<2:38:31,  5.76s/it]
  9%|▉         | 164/1813 [16:59<2:52:21,  6.27s/it]
  9%|▉         | 165/1813 [17:06<2:53:20,  6.31s/it]
  9%|▉         | 166/1813 [17:13<3:06:02,  6.78s/it]
  9%|▉         | 167/1813 [17:20<3:07:08,  6.82s/it]
  9%|▉         | 168/1813 [17:28<3:11:05,  6.97s/it]
  9%|▉         | 169/1813 [17:33<3:01:53,  6.64s/it]
  9%|▉         | 170/1813 [17:40<3:03:27,  6.70s/it]
                                                    
{'loss': '1.061', 'grad_norm': '0.6994', 'learning_rate': '9.997e-05', 'epoch': '0.09379', 'num_input_tokens_seen': 1130368, 'train_runtime': '1061', 'train_tokens_per_second': '1066'}

  9%|▉         | 170/1813 [17:40<3:03:27,  6.70s/it]
  9%|▉         | 171/1813 [17:46<2:54:24,  6.37s/it]
  9%|▉         | 172/1813 [17:52<2:48:39,  6.17s/it]
 10%|▉         | 173/1813 [17:58<2:51:39,  6.28s/it]
 10%|▉         | 174/1813 [18:04<2:48:50,  6.18s/it]
 10%|▉         | 175/1813 [18:11<2:50:30,  6.25s/it]
 10%|▉         | 176/1813 [18:16<2:42:51,  5.97s/it]
 10%|▉         | 177/1813 [18:23<2:55:27,  6.44s/it]
 10%|▉         | 178/1813 [18:28<2:42:51,  5.98s/it]
 10%|▉         | 179/1813 [18:34<2:42:07,  5.95s/it]
 10%|▉         | 180/1813 [18:40<2:45:03,  6.06s/it]
                                                    
{'loss': '1.044', 'grad_norm': '1.103', 'learning_rate': '9.992e-05', 'epoch': '0.09931', 'num_input_tokens_seen': 1193192, 'train_runtime': '1121', 'train_tokens_per_second': '1064'}

 10%|▉         | 180/1813 [18:40<2:45:03,  6.06s/it]
 10%|▉         | 181/1813 [18:46<2:42:47,  5.99s/it]
 10%|█         | 182/1813 [18:52<2:38:53,  5.85s/it]
 10%|█         | 183/1813 [18:58<2:38:23,  5.83s/it]
 10%|█         | 184/1813 [19:03<2:37:17,  5.79s/it]
 10%|█         | 185/1813 [19:11<2:56:02,  6.49s/it]
 10%|█         | 186/1813 [19:18<2:54:24,  6.43s/it]
 10%|█         | 187/1813 [19:24<2:51:18,  6.32s/it]
 10%|█         | 188/1813 [19:29<2:42:12,  5.99s/it]
 10%|█         | 189/1813 [19:36<2:47:50,  6.20s/it]
 10%|█         | 190/1813 [19:43<2:52:51,  6.39s/it]
                                                    
{'loss': '0.9859', 'grad_norm': '1.041', 'learning_rate': '9.986e-05', 'epoch': '0.1048', 'num_input_tokens_seen': 1259336, 'train_runtime': '1183', 'train_tokens_per_second': '1065'}

 10%|█         | 190/1813 [19:43<2:52:51,  6.39s/it]
 11%|█         | 191/1813 [19:48<2:46:34,  6.16s/it]
 11%|█         | 192/1813 [19:55<2:49:30,  6.27s/it]
 11%|█         | 193/1813 [20:01<2:51:13,  6.34s/it]
 11%|█         | 194/1813 [20:07<2:47:19,  6.20s/it]
 11%|█         | 195/1813 [20:15<2:57:52,  6.60s/it]
 11%|█         | 196/1813 [20:20<2:46:44,  6.19s/it]
 11%|█         | 197/1813 [20:27<2:54:05,  6.46s/it]
 11%|█         | 198/1813 [20:34<3:00:57,  6.72s/it]
 11%|█         | 199/1813 [20:41<3:00:42,  6.72s/it]
 11%|█         | 200/1813 [20:48<2:59:31,  6.68s/it]
                                                    
{'loss': '1.094', 'grad_norm': '1.185', 'learning_rate': '9.979e-05', 'epoch': '0.1103', 'num_input_tokens_seen': 1331224, 'train_runtime': '1248', 'train_tokens_per_second': '1067'}

 11%|█         | 200/1813 [20:48<2:59:31,  6.68s/it]
 11%|█         | 201/1813 [20:53<2:51:21,  6.38s/it]
 11%|█         | 202/1813 [20:58<2:41:35,  6.02s/it]
 11%|█         | 203/1813 [21:03<2:31:41,  5.65s/it]
 11%|█▏        | 204/1813 [21:10<2:41:20,  6.02s/it]
 11%|█▏        | 205/1813 [21:16<2:37:27,  5.88s/it]
 11%|█▏        | 206/1813 [21:22<2:38:46,  5.93s/it]
 11%|█▏        | 207/1813 [21:27<2:37:48,  5.90s/it]
 11%|█▏        | 208/1813 [21:35<2:53:51,  6.50s/it]
 12%|█▏        | 209/1813 [21:41<2:42:54,  6.09s/it]
 12%|█▏        | 210/1813 [21:47<2:43:49,  6.13s/it]
                                                    
{'loss': '0.9715', 'grad_norm': '1.195', 'learning_rate': '9.969e-05', 'epoch': '0.1159', 'num_input_tokens_seen': 1392472, 'train_runtime': '1307', 'train_tokens_per_second': '1065'}

 12%|█▏        | 210/1813 [21:47<2:43:49,  6.13s/it]
 12%|█▏        | 211/1813 [21:56<3:04:46,  6.92s/it]
 12%|█▏        | 212/1813 [22:01<2:53:30,  6.50s/it]
 12%|█▏        | 213/1813 [22:07<2:45:24,  6.20s/it]
 12%|█▏        | 214/1813 [22:12<2:38:15,  5.94s/it]
 12%|█▏        | 215/1813 [22:18<2:35:59,  5.86s/it]
 12%|█▏        | 216/1813 [22:22<2:27:57,  5.56s/it]
 12%|█▏        | 217/1813 [22:28<2:25:28,  5.47s/it]
 12%|█▏        | 218/1813 [22:34<2:32:23,  5.73s/it]
 12%|█▏        | 219/1813 [22:40<2:35:48,  5.87s/it]
 12%|█▏        | 220/1813 [22:46<2:38:22,  5.97s/it]
                                                    
{'loss': '1.041', 'grad_norm': '0.8222', 'learning_rate': '9.958e-05', 'epoch': '0.1214', 'num_input_tokens_seen': 1454040, 'train_runtime': '1367', 'train_tokens_per_second': '1064'}

 12%|█▏        | 220/1813 [22:46<2:38:22,  5.97s/it]
 12%|█▏        | 221/1813 [22:53<2:42:49,  6.14s/it]
 12%|█▏        | 222/1813 [22:58<2:36:13,  5.89s/it]
 12%|█▏        | 223/1813 [23:06<2:50:41,  6.44s/it]
 12%|█▏        | 224/1813 [23:11<2:39:37,  6.03s/it]
 12%|█▏        | 225/1813 [23:18<2:49:07,  6.39s/it]
 12%|█▏        | 226/1813 [23:25<2:52:47,  6.53s/it]
 13%|█▎        | 227/1813 [23:31<2:47:35,  6.34s/it]
 13%|█▎        | 228/1813 [23:38<2:49:57,  6.43s/it]
 13%|█▎        | 229/1813 [23:45<2:54:55,  6.63s/it]
 13%|█▎        | 230/1813 [23:50<2:43:20,  6.19s/it]
                                                    
{'loss': '1.012', 'grad_norm': '1.35', 'learning_rate': '9.944e-05', 'epoch': '0.1269', 'num_input_tokens_seen': 1522056, 'train_runtime': '1430', 'train_tokens_per_second': '1064'}

 13%|█▎        | 230/1813 [23:50<2:43:20,  6.19s/it]
 13%|█▎        | 231/1813 [23:55<2:34:26,  5.86s/it]
 13%|█▎        | 232/1813 [24:02<2:47:20,  6.35s/it]
 13%|█▎        | 233/1813 [24:08<2:38:38,  6.02s/it]
 13%|█▎        | 234/1813 [24:13<2:34:05,  5.86s/it]
 13%|█▎        | 235/1813 [24:20<2:43:05,  6.20s/it]
 13%|█▎        | 236/1813 [24:28<2:54:34,  6.64s/it]
 13%|█▎        | 237/1813 [24:35<2:55:25,  6.68s/it]
 13%|█▎        | 238/1813 [24:40<2:46:21,  6.34s/it]
 13%|█▎        | 239/1813 [24:48<2:56:06,  6.71s/it]
 13%|█▎        | 240/1813 [24:54<2:51:33,  6.54s/it]
                                                    
{'loss': '1.003', 'grad_norm': '0.8033', 'learning_rate': '9.929e-05', 'epoch': '0.1324', 'num_input_tokens_seen': 1590200, 'train_runtime': '1494', 'train_tokens_per_second': '1064'}

 13%|█▎        | 240/1813 [24:54<2:51:33,  6.54s/it]
 13%|█▎        | 241/1813 [25:00<2:50:21,  6.50s/it]
 13%|█▎        | 242/1813 [25:06<2:46:49,  6.37s/it]
 13%|█▎        | 243/1813 [25:12<2:39:19,  6.09s/it]
 13%|█▎        | 244/1813 [25:19<2:46:12,  6.36s/it]
 14%|█▎        | 245/1813 [25:26<2:50:56,  6.54s/it]
 14%|█▎        | 246/1813 [25:31<2:41:26,  6.18s/it]
 14%|█▎        | 247/1813 [25:38<2:46:39,  6.39s/it]
 14%|█▎        | 248/1813 [25:46<2:56:43,  6.78s/it]
 14%|█▎        | 249/1813 [25:51<2:44:35,  6.31s/it]
 14%|█▍        | 250/1813 [25:56<2:38:23,  6.08s/it]
                                                    
{'loss': '1.092', 'grad_norm': '0.9446', 'learning_rate': '9.913e-05', 'epoch': '0.1379', 'num_input_tokens_seen': 1658648, 'train_runtime': '1557', 'train_tokens_per_second': '1065'}

 14%|█▍        | 250/1813 [25:56<2:38:23,  6.08s/it]
 14%|█▍        | 251/1813 [26:01<2:26:16,  5.62s/it]
 14%|█▍        | 252/1813 [26:06<2:23:52,  5.53s/it]
 14%|█▍        | 253/1813 [26:13<2:29:53,  5.77s/it]
 14%|█▍        | 254/1813 [26:20<2:41:42,  6.22s/it]
 14%|█▍        | 255/1813 [26:27<2:44:42,  6.34s/it]
 14%|█▍        | 256/1813 [26:32<2:36:54,  6.05s/it]
 14%|█▍        | 257/1813 [26:39<2:43:02,  6.29s/it]
 14%|█▍        | 258/1813 [26:46<2:47:58,  6.48s/it]
 14%|█▍        | 259/1813 [26:50<2:34:30,  5.97s/it]
 14%|█▍        | 260/1813 [26:57<2:36:20,  6.04s/it]
                                                    
{'loss': '0.8911', 'grad_norm': '1.303', 'learning_rate': '9.894e-05', 'epoch': '0.1434', 'num_input_tokens_seen': 1722792, 'train_runtime': '1617', 'train_tokens_per_second': '1065'}

 14%|█▍        | 260/1813 [26:57<2:36:20,  6.04s/it]
 14%|█▍        | 261/1813 [27:04<2:46:09,  6.42s/it]
 14%|█▍        | 262/1813 [27:11<2:49:02,  6.54s/it]
 15%|█▍        | 263/1813 [27:17<2:49:50,  6.57s/it]
 15%|█▍        | 264/1813 [27:24<2:47:12,  6.48s/it]
 15%|█▍        | 265/1813 [27:30<2:45:34,  6.42s/it]
 15%|█▍        | 266/1813 [27:35<2:34:18,  5.98s/it]
 15%|█▍        | 267/1813 [27:41<2:31:16,  5.87s/it]
 15%|█▍        | 268/1813 [27:46<2:26:58,  5.71s/it]
 15%|█▍        | 269/1813 [27:52<2:30:55,  5.87s/it]
 15%|█▍        | 270/1813 [27:58<2:31:25,  5.89s/it]
                                                    
{'loss': '0.9272', 'grad_norm': '0.9646', 'learning_rate': '9.874e-05', 'epoch': '0.149', 'num_input_tokens_seen': 1786808, 'train_runtime': '1679', 'train_tokens_per_second': '1064'}

 15%|█▍        | 270/1813 [27:58<2:31:25,  5.89s/it]
 15%|█▍        | 271/1813 [28:06<2:48:29,  6.56s/it]
 15%|█▌        | 272/1813 [28:12<2:39:05,  6.19s/it]
 15%|█▌        | 273/1813 [28:20<2:55:46,  6.85s/it]
 15%|█▌        | 274/1813 [28:27<2:55:24,  6.84s/it]
 15%|█▌        | 275/1813 [28:32<2:42:56,  6.36s/it]
 15%|█▌        | 276/1813 [28:37<2:35:29,  6.07s/it]
 15%|█▌        | 277/1813 [28:44<2:37:36,  6.16s/it]
 15%|█▌        | 278/1813 [28:50<2:38:13,  6.18s/it]
 15%|█▌        | 279/1813 [28:58<2:50:07,  6.65s/it]
 15%|█▌        | 280/1813 [29:04<2:50:09,  6.66s/it]
                                                    
{'loss': '1.002', 'grad_norm': '0.9154', 'learning_rate': '9.852e-05', 'epoch': '0.1545', 'num_input_tokens_seen': 1858112, 'train_runtime': '1745', 'train_tokens_per_second': '1065'}

 15%|█▌        | 280/1813 [29:04<2:50:09,  6.66s/it]
 15%|█▌        | 281/1813 [29:10<2:43:54,  6.42s/it]
 16%|█▌        | 282/1813 [29:16<2:38:27,  6.21s/it]
 16%|█▌        | 283/1813 [29:21<2:32:27,  5.98s/it]
 16%|█▌        | 284/1813 [29:27<2:30:24,  5.90s/it]
 16%|█▌        | 285/1813 [29:34<2:37:01,  6.17s/it]
 16%|█▌        | 286/1813 [29:40<2:35:25,  6.11s/it]
 16%|█▌        | 287/1813 [29:46<2:35:30,  6.11s/it]
 16%|█▌        | 288/1813 [29:51<2:29:35,  5.89s/it]
 16%|█▌        | 289/1813 [29:58<2:33:08,  6.03s/it]
 16%|█▌        | 290/1813 [30:04<2:36:40,  6.17s/it]
                                                    
{'loss': '0.973', 'grad_norm': '0.8369', 'learning_rate': '9.829e-05', 'epoch': '0.16', 'num_input_tokens_seen': 1920600, 'train_runtime': '1805', 'train_tokens_per_second': '1064'}

 16%|█▌        | 290/1813 [30:04<2:36:40,  6.17s/it]
 16%|█▌        | 291/1813 [30:11<2:42:21,  6.40s/it]
 16%|█▌        | 292/1813 [30:18<2:48:28,  6.65s/it]
 16%|█▌        | 293/1813 [30:24<2:42:43,  6.42s/it]
 16%|█▌        | 294/1813 [30:31<2:48:06,  6.64s/it]
 16%|█▋        | 295/1813 [30:39<2:54:26,  6.89s/it]
 16%|█▋        | 296/1813 [30:45<2:45:40,  6.55s/it]
 16%|█▋        | 297/1813 [30:51<2:43:17,  6.46s/it]
 16%|█▋        | 298/1813 [30:56<2:32:44,  6.05s/it]
 16%|█▋        | 299/1813 [31:02<2:33:08,  6.07s/it]
 17%|█▋        | 300/1813 [31:08<2:32:20,  6.04s/it]
                                                    
{'loss': '1.042', 'grad_norm': '0.9333', 'learning_rate': '9.803e-05', 'epoch': '0.1655', 'num_input_tokens_seen': 1988312, 'train_runtime': '1869', 'train_tokens_per_second': '1064'}

 17%|█▋        | 300/1813 [31:08<2:32:20,  6.04s/it]
***** Running Evaluation *****
  Num examples = 1000
  Batch size = 1
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:71: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:281: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:172: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:202: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:254: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)


  0%|          | 0/1000 [00:00<?, ?it/s]

  0%|          | 3/1000 [00:00<01:03, 15.79it/s]

  0%|          | 5/1000 [00:00<02:17,  7.24it/s]

  1%|          | 7/1000 [00:00<01:59,  8.33it/s]

  1%|          | 9/1000 [00:01<02:33,  6.46it/s]

  1%|          | 11/1000 [00:01<02:02,  8.07it/s]

  1%|▏         | 13/1000 [00:01<02:20,  7.00it/s]

  1%|▏         | 14/1000 [00:01<02:24,  6.84it/s]

  2%|▏         | 15/1000 [00:02<02:44,  5.97it/s]

  2%|▏         | 16/1000 [00:02<02:51,  5.72it/s]

  2%|▏         | 18/1000 [00:02<02:42,  6.05it/s]

  2%|▏         | 19/1000 [00:02<03:10,  5.15it/s]

  2%|▏         | 20/1000 [00:03<03:33,  4.60it/s]

  2%|▏         | 22/1000 [00:03<02:36,  6.25it/s]

  2%|▏         | 23/1000 [00:03<02:54,  5.59it/s]

  2%|▎         | 25/1000 [00:03<02:12,  7.36it/s]

  3%|▎         | 26/1000 [00:04<02:35,  6.27it/s]

  3%|▎         | 28/1000 [00:04<02:42,  5.99it/s]

  3%|▎         | 29/1000 [00:04<02:32,  6.36it/s]

  3%|▎         | 30/1000 [00:04<02:42,  5.96it/s]

  3%|▎         | 31/1000 [00:04<03:01,  5.35it/s]

  3%|▎         | 32/1000 [00:05<02:41,  5.99it/s]

  3%|▎         | 33/1000 [00:05<02:48,  5.76it/s]

  4%|▎         | 35/1000 [00:05<02:06,  7.65it/s]

  4%|▎         | 37/1000 [00:05<01:45,  9.10it/s]

  4%|▍         | 39/1000 [00:05<02:06,  7.57it/s]

  4%|▍         | 40/1000 [00:05<02:03,  7.75it/s]

  4%|▍         | 42/1000 [00:06<01:45,  9.11it/s]

  4%|▍         | 44/1000 [00:06<01:32, 10.33it/s]

  5%|▍         | 46/1000 [00:06<01:45,  9.05it/s]

  5%|▍         | 47/1000 [00:06<02:09,  7.36it/s]

  5%|▍         | 49/1000 [00:06<01:48,  8.76it/s]

  5%|▌         | 51/1000 [00:07<01:35,  9.92it/s]

  5%|▌         | 53/1000 [00:07<01:26, 10.95it/s]

  6%|▌         | 55/1000 [00:07<01:28, 10.74it/s]

  6%|▌         | 57/1000 [00:07<01:41,  9.29it/s]

  6%|▌         | 59/1000 [00:08<01:54,  8.20it/s]

  6%|▌         | 61/1000 [00:08<01:40,  9.34it/s]

  6%|▋         | 63/1000 [00:08<01:36,  9.75it/s]

  6%|▋         | 65/1000 [00:08<01:51,  8.36it/s]

  7%|▋         | 67/1000 [00:09<02:03,  7.58it/s]

  7%|▋         | 69/1000 [00:09<01:52,  8.27it/s]

  7%|▋         | 70/1000 [00:09<02:13,  6.99it/s]

  7%|▋         | 72/1000 [00:09<02:18,  6.71it/s]

  7%|▋         | 74/1000 [00:09<01:54,  8.12it/s]

  8%|▊         | 75/1000 [00:10<02:14,  6.86it/s]

  8%|▊         | 76/1000 [00:10<02:18,  6.66it/s]

  8%|▊         | 78/1000 [00:10<02:25,  6.32it/s]

  8%|▊         | 80/1000 [00:10<01:57,  7.86it/s]

  8%|▊         | 82/1000 [00:10<01:39,  9.19it/s]

  8%|▊         | 84/1000 [00:11<01:54,  8.02it/s]

  8%|▊         | 85/1000 [00:11<02:14,  6.79it/s]

  9%|▊         | 86/1000 [00:11<02:33,  5.95it/s]

  9%|▊         | 87/1000 [00:11<02:49,  5.39it/s]

  9%|▉         | 89/1000 [00:12<02:09,  7.02it/s]

  9%|▉         | 90/1000 [00:12<02:05,  7.25it/s]

  9%|▉         | 91/1000 [00:12<02:29,  6.07it/s]

  9%|▉         | 92/1000 [00:12<02:27,  6.17it/s]

  9%|▉         | 93/1000 [00:12<02:36,  5.78it/s]

 10%|▉         | 95/1000 [00:13<02:43,  5.53it/s]

 10%|▉         | 97/1000 [00:13<02:13,  6.79it/s]

 10%|▉         | 99/1000 [00:13<01:47,  8.36it/s]

 10%|█         | 101/1000 [00:13<01:33,  9.64it/s]

 10%|█         | 103/1000 [00:14<01:55,  7.75it/s]

 10%|█         | 104/1000 [00:14<01:54,  7.82it/s]

 11%|█         | 106/1000 [00:14<01:35,  9.32it/s]

 11%|█         | 108/1000 [00:14<01:25, 10.45it/s]

 11%|█         | 110/1000 [00:14<01:19, 11.21it/s]

 11%|█         | 112/1000 [00:14<01:13, 12.05it/s]

 11%|█▏        | 114/1000 [00:14<01:10, 12.53it/s]

 12%|█▏        | 116/1000 [00:15<01:09, 12.81it/s]

 12%|█▏        | 118/1000 [00:15<01:06, 13.19it/s]

 12%|█▏        | 120/1000 [00:15<02:07,  6.90it/s]

 12%|█▏        | 122/1000 [00:15<01:48,  8.06it/s]

 12%|█▏        | 124/1000 [00:16<01:58,  7.42it/s]

 12%|█▎        | 125/1000 [00:16<02:33,  5.71it/s]

 13%|█▎        | 126/1000 [00:16<02:22,  6.13it/s]

 13%|█▎        | 127/1000 [00:16<02:30,  5.79it/s]

 13%|█▎        | 128/1000 [00:17<02:45,  5.28it/s]

 13%|█▎        | 130/1000 [00:17<02:02,  7.10it/s]

 13%|█▎        | 132/1000 [00:17<01:39,  8.69it/s]

 13%|█▎        | 134/1000 [00:17<01:25, 10.13it/s]

 14%|█▎        | 136/1000 [00:17<01:29,  9.64it/s]

 14%|█▍        | 138/1000 [00:18<01:27,  9.88it/s]

 14%|█▍        | 140/1000 [00:18<01:26,  9.97it/s]

 14%|█▍        | 142/1000 [00:18<01:34,  9.04it/s]

 14%|█▍        | 143/1000 [00:18<01:36,  8.90it/s]

 14%|█▍        | 145/1000 [00:18<01:24, 10.08it/s]

 15%|█▍        | 147/1000 [00:19<01:41,  8.43it/s]

 15%|█▍        | 148/1000 [00:19<01:40,  8.50it/s]

 15%|█▌        | 150/1000 [00:19<01:25,  9.93it/s]

 15%|█▌        | 152/1000 [00:19<01:16, 11.04it/s]

 15%|█▌        | 154/1000 [00:19<01:21, 10.40it/s]

 16%|█▌        | 156/1000 [00:20<02:06,  6.65it/s]

 16%|█▌        | 158/1000 [00:20<01:45,  7.97it/s]

 16%|█▌        | 160/1000 [00:20<01:37,  8.60it/s]

 16%|█▌        | 162/1000 [00:20<01:47,  7.81it/s]

 16%|█▋        | 163/1000 [00:21<01:51,  7.50it/s]

 16%|█▋        | 164/1000 [00:21<02:10,  6.40it/s]

 16%|█▋        | 165/1000 [00:21<02:27,  5.67it/s]

 17%|█▋        | 166/1000 [00:21<02:41,  5.17it/s]

 17%|█▋        | 167/1000 [00:21<02:24,  5.78it/s]

 17%|█▋        | 169/1000 [00:22<01:46,  7.84it/s]

 17%|█▋        | 171/1000 [00:22<01:55,  7.16it/s]

 17%|█▋        | 172/1000 [00:22<02:14,  6.15it/s]

 17%|█▋        | 173/1000 [00:22<02:12,  6.22it/s]

 17%|█▋        | 174/1000 [00:22<02:02,  6.74it/s]

 18%|█▊        | 176/1000 [00:23<01:37,  8.46it/s]

 18%|█▊        | 177/1000 [00:23<02:01,  6.80it/s]

 18%|█▊        | 179/1000 [00:23<01:35,  8.58it/s]

 18%|█▊        | 180/1000 [00:23<01:36,  8.52it/s]

 18%|█▊        | 181/1000 [00:23<02:01,  6.74it/s]

 18%|█▊        | 182/1000 [00:24<02:23,  5.72it/s]

 18%|█▊        | 183/1000 [00:24<02:21,  5.79it/s]

 18%|█▊        | 185/1000 [00:24<01:45,  7.73it/s]

 19%|█▊        | 186/1000 [00:24<01:43,  7.88it/s]

 19%|█▊        | 187/1000 [00:24<02:07,  6.38it/s]

 19%|█▉        | 189/1000 [00:24<01:39,  8.11it/s]

 19%|█▉        | 190/1000 [00:25<02:02,  6.63it/s]

 19%|█▉        | 192/1000 [00:25<02:04,  6.47it/s]

 19%|█▉        | 194/1000 [00:25<02:06,  6.37it/s]

 20%|█▉        | 196/1000 [00:25<01:43,  7.75it/s]

 20%|█▉        | 198/1000 [00:26<01:27,  9.19it/s]

 20%|██        | 200/1000 [00:26<01:15, 10.67it/s]

 20%|██        | 202/1000 [00:26<01:31,  8.77it/s]

 20%|██        | 204/1000 [00:26<01:32,  8.63it/s]

 21%|██        | 206/1000 [00:26<01:20,  9.92it/s]

 21%|██        | 208/1000 [00:27<01:33,  8.51it/s]

 21%|██        | 210/1000 [00:27<01:33,  8.48it/s]

 21%|██        | 212/1000 [00:27<01:21,  9.65it/s]

 21%|██▏       | 214/1000 [00:27<01:29,  8.73it/s]

 22%|██▏       | 216/1000 [00:28<01:25,  9.15it/s]

 22%|██▏       | 217/1000 [00:28<01:44,  7.50it/s]

 22%|██▏       | 219/1000 [00:28<01:30,  8.63it/s]

 22%|██▏       | 220/1000 [00:28<02:04,  6.25it/s]

 22%|██▏       | 221/1000 [00:28<02:04,  6.26it/s]

 22%|██▏       | 223/1000 [00:29<02:20,  5.52it/s]

 22%|██▏       | 224/1000 [00:29<02:09,  6.00it/s]

 22%|██▎       | 225/1000 [00:29<02:07,  6.06it/s]

 23%|██▎       | 226/1000 [00:29<02:23,  5.41it/s]

 23%|██▎       | 228/1000 [00:30<01:53,  6.81it/s]

 23%|██▎       | 229/1000 [00:30<02:10,  5.90it/s]

 23%|██▎       | 230/1000 [00:30<02:01,  6.35it/s]

 23%|██▎       | 232/1000 [00:30<01:35,  8.01it/s]

 23%|██▎       | 233/1000 [00:30<01:33,  8.20it/s]

 24%|██▎       | 235/1000 [00:30<01:16,  9.97it/s]

 24%|██▎       | 237/1000 [00:31<01:20,  9.46it/s]

 24%|██▍       | 239/1000 [00:31<01:24,  8.97it/s]

 24%|██▍       | 241/1000 [00:31<01:31,  8.34it/s]

 24%|██▍       | 242/1000 [00:31<02:06,  6.01it/s]

 24%|██▍       | 243/1000 [00:32<02:18,  5.47it/s]

 24%|██▍       | 245/1000 [00:32<01:53,  6.65it/s]

 25%|██▍       | 247/1000 [00:32<01:31,  8.24it/s]

 25%|██▍       | 248/1000 [00:32<01:49,  6.85it/s]

 25%|██▍       | 249/1000 [00:33<02:06,  5.96it/s]

 25%|██▌       | 250/1000 [00:33<02:07,  5.87it/s]

 25%|██▌       | 252/1000 [00:33<02:04,  6.03it/s]

 25%|██▌       | 253/1000 [00:33<02:10,  5.74it/s]

 26%|██▌       | 255/1000 [00:33<01:41,  7.37it/s]

 26%|██▌       | 256/1000 [00:33<01:36,  7.70it/s]

 26%|██▌       | 258/1000 [00:34<01:24,  8.75it/s]

 26%|██▌       | 260/1000 [00:34<01:36,  7.68it/s]

 26%|██▌       | 261/1000 [00:34<01:53,  6.51it/s]

 26%|██▌       | 262/1000 [00:34<01:54,  6.42it/s]

 26%|██▋       | 264/1000 [00:35<01:56,  6.33it/s]

 26%|██▋       | 265/1000 [00:35<01:51,  6.59it/s]

 27%|██▋       | 266/1000 [00:35<01:46,  6.90it/s]

 27%|██▋       | 268/1000 [00:35<01:37,  7.53it/s]

 27%|██▋       | 270/1000 [00:35<01:43,  7.03it/s]

 27%|██▋       | 271/1000 [00:36<02:14,  5.44it/s]

 27%|██▋       | 273/1000 [00:36<02:07,  5.70it/s]

 28%|██▊       | 275/1000 [00:36<01:48,  6.70it/s]

 28%|██▊       | 277/1000 [00:37<01:29,  8.05it/s]

 28%|██▊       | 278/1000 [00:37<01:46,  6.80it/s]

 28%|██▊       | 280/1000 [00:37<01:48,  6.62it/s]

 28%|██▊       | 282/1000 [00:37<01:29,  8.02it/s]

 28%|██▊       | 283/1000 [00:38<02:02,  5.85it/s]

 28%|██▊       | 284/1000 [00:38<02:05,  5.70it/s]

 29%|██▊       | 286/1000 [00:38<01:36,  7.43it/s]

 29%|██▉       | 288/1000 [00:38<01:21,  8.74it/s]

 29%|██▉       | 290/1000 [00:38<01:31,  7.79it/s]

 29%|██▉       | 291/1000 [00:39<01:41,  7.01it/s]

 29%|██▉       | 292/1000 [00:39<01:56,  6.07it/s]

 29%|██▉       | 294/1000 [00:39<01:38,  7.19it/s]

 30%|██▉       | 296/1000 [00:39<01:42,  6.90it/s]

 30%|██▉       | 298/1000 [00:39<01:25,  8.19it/s]

 30%|██▉       | 299/1000 [00:40<01:48,  6.47it/s]

 30%|███       | 300/1000 [00:40<01:42,  6.84it/s]

 30%|███       | 301/1000 [00:40<01:38,  7.11it/s]

 30%|███       | 303/1000 [00:40<01:19,  8.76it/s]

 30%|███       | 304/1000 [00:40<01:26,  8.08it/s]

 30%|███       | 305/1000 [00:40<01:25,  8.15it/s]

 31%|███       | 306/1000 [00:41<01:39,  6.94it/s]

 31%|███       | 307/1000 [00:41<01:42,  6.78it/s]

 31%|███       | 309/1000 [00:41<01:18,  8.79it/s]

 31%|███       | 311/1000 [00:41<01:07, 10.20it/s]

 31%|███▏      | 313/1000 [00:41<01:00, 11.27it/s]

 32%|███▏      | 315/1000 [00:41<01:06, 10.26it/s]

 32%|███▏      | 317/1000 [00:42<01:11,  9.59it/s]

 32%|███▏      | 319/1000 [00:42<01:34,  7.23it/s]

 32%|███▏      | 321/1000 [00:42<01:38,  6.89it/s]

 32%|███▏      | 322/1000 [00:43<01:45,  6.45it/s]

 32%|███▏      | 324/1000 [00:43<01:27,  7.76it/s]

 32%|███▎      | 325/1000 [00:43<01:58,  5.70it/s]

 33%|███▎      | 327/1000 [00:43<01:30,  7.42it/s]

 33%|███▎      | 328/1000 [00:43<01:33,  7.18it/s]

 33%|███▎      | 330/1000 [00:44<01:38,  6.80it/s]

 33%|███▎      | 332/1000 [00:44<01:41,  6.58it/s]

 33%|███▎      | 333/1000 [00:44<01:35,  6.96it/s]

 33%|███▎      | 334/1000 [00:44<01:44,  6.39it/s]

 34%|███▎      | 336/1000 [00:45<01:22,  8.05it/s]

 34%|███▍      | 338/1000 [00:45<01:14,  8.84it/s]

 34%|███▍      | 340/1000 [00:45<01:05, 10.04it/s]

 34%|███▍      | 342/1000 [00:45<01:00, 10.89it/s]

 34%|███▍      | 344/1000 [00:45<01:26,  7.60it/s]

 34%|███▍      | 345/1000 [00:46<01:24,  7.73it/s]

 35%|███▍      | 346/1000 [00:46<01:30,  7.23it/s]

 35%|███▍      | 347/1000 [00:46<01:28,  7.42it/s]

 35%|███▍      | 349/1000 [00:46<01:33,  6.93it/s]

 35%|███▌      | 350/1000 [00:46<01:49,  5.96it/s]

 35%|███▌      | 352/1000 [00:47<01:24,  7.65it/s]

 35%|███▌      | 354/1000 [00:47<01:25,  7.55it/s]

 36%|███▌      | 355/1000 [00:47<01:27,  7.35it/s]

 36%|███▌      | 357/1000 [00:47<01:11,  8.94it/s]

 36%|███▌      | 359/1000 [00:47<01:00, 10.55it/s]

 36%|███▌      | 361/1000 [00:48<01:07,  9.41it/s]

 36%|███▋      | 363/1000 [00:48<01:28,  7.18it/s]

 36%|███▋      | 364/1000 [00:48<01:41,  6.27it/s]

 36%|███▋      | 365/1000 [00:49<02:09,  4.92it/s]

 37%|███▋      | 367/1000 [00:49<01:57,  5.36it/s]

 37%|███▋      | 368/1000 [00:49<02:05,  5.02it/s]

 37%|███▋      | 369/1000 [00:49<01:52,  5.60it/s]

 37%|███▋      | 371/1000 [00:49<01:23,  7.55it/s]

 37%|███▋      | 372/1000 [00:49<01:21,  7.73it/s]

 37%|███▋      | 374/1000 [00:50<01:17,  8.09it/s]

 38%|███▊      | 375/1000 [00:50<01:40,  6.22it/s]

 38%|███▊      | 376/1000 [00:50<01:53,  5.48it/s]

 38%|███▊      | 377/1000 [00:50<01:40,  6.19it/s]

 38%|███▊      | 379/1000 [00:50<01:15,  8.18it/s]

 38%|███▊      | 381/1000 [00:51<01:07,  9.20it/s]

 38%|███▊      | 383/1000 [00:51<01:11,  8.57it/s]

 38%|███▊      | 385/1000 [00:51<01:07,  9.08it/s]

 39%|███▊      | 387/1000 [00:51<01:21,  7.56it/s]

 39%|███▉      | 388/1000 [00:52<01:23,  7.30it/s]

 39%|███▉      | 390/1000 [00:52<01:17,  7.85it/s]

 39%|███▉      | 391/1000 [00:52<01:21,  7.50it/s]

 39%|███▉      | 393/1000 [00:52<01:07,  9.02it/s]

 40%|███▉      | 395/1000 [00:53<01:20,  7.51it/s]

 40%|███▉      | 397/1000 [00:53<01:08,  8.82it/s]

 40%|███▉      | 398/1000 [00:53<01:23,  7.25it/s]

 40%|███▉      | 399/1000 [00:53<01:40,  5.95it/s]

 40%|████      | 400/1000 [00:53<01:51,  5.37it/s]

 40%|████      | 402/1000 [00:54<01:43,  5.76it/s]

 40%|████      | 404/1000 [00:54<01:22,  7.26it/s]

 41%|████      | 406/1000 [00:54<01:08,  8.62it/s]

 41%|████      | 407/1000 [00:54<01:23,  7.07it/s]

 41%|████      | 408/1000 [00:55<01:36,  6.15it/s]

 41%|████      | 410/1000 [00:55<01:33,  6.31it/s]

 41%|████      | 411/1000 [00:55<01:44,  5.64it/s]

 41%|████      | 412/1000 [00:55<01:53,  5.17it/s]

 41%|████▏     | 414/1000 [00:55<01:23,  7.05it/s]

 42%|████▏     | 416/1000 [00:56<01:26,  6.79it/s]

 42%|████▏     | 418/1000 [00:56<01:10,  8.31it/s]

 42%|████▏     | 420/1000 [00:56<01:08,  8.50it/s]

 42%|████▏     | 421/1000 [00:56<01:16,  7.52it/s]

 42%|████▏     | 423/1000 [00:57<01:26,  6.68it/s]

 42%|████▏     | 424/1000 [00:57<01:37,  5.92it/s]

 42%|████▎     | 425/1000 [00:57<01:30,  6.36it/s]

 43%|████▎     | 427/1000 [00:57<01:11,  7.97it/s]

 43%|████▎     | 428/1000 [00:57<01:15,  7.55it/s]

 43%|████▎     | 429/1000 [00:57<01:12,  7.85it/s]

 43%|████▎     | 431/1000 [00:58<00:59,  9.53it/s]

 43%|████▎     | 433/1000 [00:58<00:51, 11.00it/s]

 44%|████▎     | 435/1000 [00:58<00:48, 11.76it/s]

 44%|████▎     | 437/1000 [00:58<00:53, 10.51it/s]

 44%|████▍     | 439/1000 [00:58<01:09,  8.09it/s]

 44%|████▍     | 441/1000 [00:59<01:00,  9.31it/s]

 44%|████▍     | 443/1000 [00:59<01:08,  8.09it/s]

 44%|████▍     | 444/1000 [00:59<01:16,  7.26it/s]

 45%|████▍     | 446/1000 [00:59<01:03,  8.74it/s]

 45%|████▍     | 448/1000 [01:00<01:13,  7.49it/s]

 45%|████▌     | 450/1000 [01:00<01:18,  7.01it/s]

 45%|████▌     | 451/1000 [01:00<01:28,  6.18it/s]

 45%|████▌     | 452/1000 [01:00<01:38,  5.59it/s]

 45%|████▌     | 454/1000 [01:01<01:15,  7.19it/s]

 46%|████▌     | 456/1000 [01:01<01:03,  8.50it/s]

 46%|████▌     | 457/1000 [01:01<01:09,  7.80it/s]

 46%|████▌     | 459/1000 [01:01<00:58,  9.26it/s]

 46%|████▌     | 461/1000 [01:01<00:49, 10.83it/s]

 46%|████▋     | 463/1000 [01:02<01:10,  7.63it/s]

 46%|████▋     | 465/1000 [01:02<01:19,  6.75it/s]

 47%|████▋     | 466/1000 [01:02<01:28,  6.01it/s]

 47%|████▋     | 467/1000 [01:03<01:50,  4.83it/s]

 47%|████▋     | 469/1000 [01:03<01:24,  6.31it/s]

 47%|████▋     | 471/1000 [01:03<01:07,  7.86it/s]

 47%|████▋     | 472/1000 [01:03<01:04,  8.20it/s]

 47%|████▋     | 473/1000 [01:03<01:11,  7.37it/s]

 47%|████▋     | 474/1000 [01:03<01:25,  6.17it/s]

 48%|████▊     | 476/1000 [01:04<01:24,  6.19it/s]

 48%|████▊     | 477/1000 [01:04<01:38,  5.29it/s]

 48%|████▊     | 479/1000 [01:04<01:13,  7.09it/s]

 48%|████▊     | 480/1000 [01:04<01:19,  6.51it/s]

 48%|████▊     | 482/1000 [01:04<01:04,  8.05it/s]

 48%|████▊     | 484/1000 [01:05<01:10,  7.30it/s]

 48%|████▊     | 485/1000 [01:05<01:21,  6.28it/s]

 49%|████▊     | 486/1000 [01:05<01:21,  6.28it/s]

 49%|████▉     | 488/1000 [01:05<01:04,  7.99it/s]

 49%|████▉     | 489/1000 [01:06<01:17,  6.62it/s]

 49%|████▉     | 491/1000 [01:06<01:01,  8.22it/s]

 49%|████▉     | 492/1000 [01:06<01:01,  8.28it/s]

 49%|████▉     | 494/1000 [01:06<00:50,  9.99it/s]

 50%|████▉     | 496/1000 [01:06<00:59,  8.41it/s]

 50%|████▉     | 498/1000 [01:07<00:59,  8.39it/s]

 50%|████▉     | 499/1000 [01:07<01:15,  6.64it/s]

 50%|█████     | 500/1000 [01:07<01:24,  5.92it/s]

 50%|█████     | 502/1000 [01:07<01:06,  7.53it/s]

 50%|█████     | 503/1000 [01:07<01:13,  6.79it/s]

 50%|█████     | 505/1000 [01:08<01:15,  6.56it/s]

 51%|█████     | 506/1000 [01:08<01:25,  5.80it/s]

 51%|█████     | 508/1000 [01:08<01:06,  7.43it/s]

 51%|█████     | 510/1000 [01:08<00:54,  8.95it/s]

 51%|█████     | 512/1000 [01:08<00:48,  9.97it/s]

 51%|█████▏    | 514/1000 [01:09<01:06,  7.27it/s]

 52%|█████▏    | 515/1000 [01:09<01:04,  7.53it/s]

 52%|█████▏    | 516/1000 [01:09<01:08,  7.10it/s]

 52%|█████▏    | 518/1000 [01:09<00:59,  8.07it/s]

 52%|█████▏    | 519/1000 [01:10<01:15,  6.37it/s]

 52%|█████▏    | 521/1000 [01:10<00:59,  8.02it/s]

 52%|█████▏    | 522/1000 [01:10<01:11,  6.68it/s]

 52%|█████▏    | 523/1000 [01:10<01:22,  5.81it/s]

 52%|█████▏    | 524/1000 [01:10<01:25,  5.56it/s]

 53%|█████▎    | 526/1000 [01:11<01:12,  6.58it/s]

 53%|█████▎    | 528/1000 [01:11<01:12,  6.53it/s]

 53%|█████▎    | 529/1000 [01:11<01:13,  6.40it/s]

 53%|█████▎    | 531/1000 [01:11<00:57,  8.14it/s]

 53%|█████▎    | 533/1000 [01:11<00:47,  9.74it/s]

 54%|█████▎    | 535/1000 [01:12<01:09,  6.69it/s]

 54%|█████▎    | 536/1000 [01:12<01:12,  6.36it/s]

 54%|█████▎    | 537/1000 [01:12<01:21,  5.67it/s]

 54%|█████▍    | 539/1000 [01:13<01:17,  5.93it/s]

 54%|█████▍    | 540/1000 [01:13<01:19,  5.76it/s]

 54%|█████▍    | 541/1000 [01:13<01:27,  5.26it/s]

 54%|█████▍    | 543/1000 [01:13<01:05,  6.94it/s]

 55%|█████▍    | 545/1000 [01:14<01:04,  7.07it/s]

 55%|█████▍    | 546/1000 [01:14<01:09,  6.49it/s]

 55%|█████▍    | 547/1000 [01:14<01:19,  5.69it/s]

 55%|█████▍    | 549/1000 [01:14<01:16,  5.92it/s]

 55%|█████▌    | 551/1000 [01:14<00:59,  7.51it/s]

 55%|█████▌    | 552/1000 [01:15<01:01,  7.26it/s]

 55%|█████▌    | 553/1000 [01:15<01:12,  6.17it/s]

 55%|█████▌    | 554/1000 [01:15<01:15,  5.94it/s]

 56%|█████▌    | 556/1000 [01:15<00:57,  7.77it/s]

 56%|█████▌    | 557/1000 [01:15<01:02,  7.03it/s]

 56%|█████▌    | 559/1000 [01:15<00:49,  8.87it/s]

 56%|█████▌    | 561/1000 [01:16<00:43, 10.07it/s]

 56%|█████▋    | 563/1000 [01:16<00:52,  8.38it/s]

 56%|█████▋    | 565/1000 [01:16<00:54,  7.99it/s]

 57%|█████▋    | 566/1000 [01:16<01:04,  6.75it/s]

 57%|█████▋    | 568/1000 [01:17<01:05,  6.56it/s]

 57%|█████▋    | 569/1000 [01:17<01:06,  6.44it/s]

 57%|█████▋    | 571/1000 [01:17<01:06,  6.44it/s]

 57%|█████▋    | 572/1000 [01:17<01:07,  6.31it/s]

 57%|█████▋    | 574/1000 [01:18<01:07,  6.35it/s]

 58%|█████▊    | 576/1000 [01:18<00:54,  7.83it/s]

 58%|█████▊    | 577/1000 [01:18<01:13,  5.73it/s]

 58%|█████▊    | 578/1000 [01:18<01:20,  5.25it/s]

 58%|█████▊    | 580/1000 [01:19<01:00,  6.97it/s]

 58%|█████▊    | 582/1000 [01:19<00:48,  8.56it/s]

 58%|█████▊    | 584/1000 [01:19<00:54,  7.57it/s]

 58%|█████▊    | 585/1000 [01:19<01:00,  6.90it/s]

 59%|█████▊    | 587/1000 [01:20<00:57,  7.14it/s]

 59%|█████▉    | 589/1000 [01:20<00:48,  8.53it/s]

 59%|█████▉    | 590/1000 [01:20<01:00,  6.75it/s]

 59%|█████▉    | 592/1000 [01:20<00:49,  8.18it/s]

 59%|█████▉    | 593/1000 [01:20<00:59,  6.81it/s]

 60%|█████▉    | 595/1000 [01:21<00:48,  8.40it/s]

 60%|█████▉    | 596/1000 [01:21<00:58,  6.88it/s]

 60%|█████▉    | 597/1000 [01:21<01:00,  6.68it/s]

 60%|█████▉    | 599/1000 [01:21<01:01,  6.48it/s]

 60%|██████    | 601/1000 [01:22<01:02,  6.40it/s]

 60%|██████    | 602/1000 [01:22<00:59,  6.71it/s]

 60%|██████    | 604/1000 [01:22<01:09,  5.69it/s]

 61%|██████    | 606/1000 [01:22<00:55,  7.11it/s]

 61%|██████    | 608/1000 [01:22<00:49,  7.85it/s]

 61%|██████    | 610/1000 [01:23<00:45,  8.49it/s]

 61%|██████    | 612/1000 [01:23<00:39,  9.75it/s]

 61%|██████▏   | 614/1000 [01:23<00:35, 10.84it/s]

 62%|██████▏   | 616/1000 [01:23<00:50,  7.63it/s]

 62%|██████▏   | 617/1000 [01:24<00:49,  7.76it/s]

 62%|██████▏   | 619/1000 [01:24<00:41,  9.11it/s]

 62%|██████▏   | 621/1000 [01:24<00:47,  8.05it/s]

 62%|██████▏   | 623/1000 [01:24<00:45,  8.22it/s]

 62%|██████▎   | 625/1000 [01:25<00:50,  7.46it/s]

 63%|██████▎   | 627/1000 [01:25<00:43,  8.63it/s]

 63%|██████▎   | 628/1000 [01:25<00:51,  7.19it/s]

 63%|██████▎   | 629/1000 [01:25<00:59,  6.22it/s]

 63%|██████▎   | 631/1000 [01:25<00:46,  7.87it/s]

 63%|██████▎   | 633/1000 [01:25<00:38,  9.44it/s]

 64%|██████▎   | 635/1000 [01:26<00:54,  6.72it/s]

 64%|██████▎   | 636/1000 [01:26<00:51,  7.07it/s]

 64%|██████▍   | 638/1000 [01:26<00:45,  7.95it/s]

 64%|██████▍   | 640/1000 [01:26<00:39,  9.18it/s]

 64%|██████▍   | 642/1000 [01:27<00:44,  7.97it/s]

 64%|██████▍   | 643/1000 [01:27<00:46,  7.60it/s]

 64%|██████▍   | 645/1000 [01:27<00:49,  7.10it/s]

 65%|██████▍   | 647/1000 [01:27<00:46,  7.58it/s]

 65%|██████▍   | 648/1000 [01:28<00:53,  6.52it/s]

 65%|██████▌   | 650/1000 [01:28<00:53,  6.56it/s]

 65%|██████▌   | 652/1000 [01:28<00:55,  6.32it/s]

 65%|██████▌   | 654/1000 [01:28<00:44,  7.71it/s]

 66%|██████▌   | 656/1000 [01:29<00:38,  8.92it/s]

 66%|██████▌   | 658/1000 [01:29<00:42,  8.11it/s]

 66%|██████▌   | 659/1000 [01:29<00:56,  6.00it/s]

 66%|██████▌   | 661/1000 [01:29<00:44,  7.56it/s]

 66%|██████▌   | 662/1000 [01:30<00:52,  6.48it/s]

 66%|██████▋   | 664/1000 [01:30<00:58,  5.77it/s]

 66%|██████▋   | 665/1000 [01:30<01:02,  5.32it/s]

 67%|██████▋   | 667/1000 [01:31<00:59,  5.61it/s]

 67%|██████▋   | 668/1000 [01:31<01:03,  5.20it/s]

 67%|██████▋   | 669/1000 [01:31<00:58,  5.69it/s]

 67%|██████▋   | 671/1000 [01:31<00:55,  5.88it/s]

 67%|██████▋   | 673/1000 [01:31<00:49,  6.63it/s]

 68%|██████▊   | 675/1000 [01:32<00:44,  7.27it/s]

 68%|██████▊   | 677/1000 [01:32<00:37,  8.66it/s]

 68%|██████▊   | 679/1000 [01:32<00:33,  9.69it/s]

 68%|██████▊   | 681/1000 [01:32<00:29, 10.97it/s]

 68%|██████▊   | 683/1000 [01:32<00:35,  8.93it/s]

 68%|██████▊   | 685/1000 [01:33<00:31,  9.89it/s]

 69%|██████▊   | 687/1000 [01:33<00:45,  6.86it/s]

 69%|██████▉   | 688/1000 [01:33<00:43,  7.17it/s]

 69%|██████▉   | 690/1000 [01:34<00:45,  6.81it/s]

 69%|██████▉   | 692/1000 [01:34<00:39,  7.83it/s]

 69%|██████▉   | 694/1000 [01:34<00:42,  7.25it/s]

 70%|██████▉   | 695/1000 [01:34<00:41,  7.42it/s]

 70%|██████▉   | 696/1000 [01:34<00:47,  6.34it/s]

 70%|██████▉   | 698/1000 [01:35<00:43,  6.95it/s]

 70%|██████▉   | 699/1000 [01:35<00:49,  6.04it/s]

 70%|███████   | 701/1000 [01:35<00:39,  7.59it/s]

 70%|███████   | 702/1000 [01:35<00:53,  5.61it/s]

 70%|███████   | 704/1000 [01:36<00:41,  7.22it/s]

 70%|███████   | 705/1000 [01:36<00:54,  5.41it/s]

 71%|███████   | 707/1000 [01:36<00:41,  7.02it/s]

 71%|███████   | 709/1000 [01:36<00:38,  7.62it/s]

 71%|███████   | 710/1000 [01:36<00:44,  6.50it/s]

 71%|███████   | 712/1000 [01:37<00:37,  7.71it/s]

 71%|███████▏  | 713/1000 [01:37<00:36,  7.86it/s]

 72%|███████▏  | 715/1000 [01:37<00:30,  9.34it/s]

 72%|███████▏  | 717/1000 [01:37<00:35,  8.05it/s]

 72%|███████▏  | 718/1000 [01:37<00:41,  6.80it/s]

 72%|███████▏  | 719/1000 [01:38<00:47,  5.93it/s]

 72%|███████▏  | 720/1000 [01:38<00:43,  6.46it/s]

 72%|███████▏  | 722/1000 [01:38<00:34,  8.14it/s]

 72%|███████▏  | 723/1000 [01:38<00:33,  8.23it/s]

 72%|███████▏  | 724/1000 [01:38<00:33,  8.25it/s]

 72%|███████▎  | 725/1000 [01:38<00:33,  8.31it/s]

 73%|███████▎  | 727/1000 [01:38<00:26, 10.13it/s]

 73%|███████▎  | 729/1000 [01:39<00:23, 11.61it/s]

 73%|███████▎  | 731/1000 [01:39<00:32,  8.32it/s]

 73%|███████▎  | 733/1000 [01:39<00:28,  9.51it/s]

 74%|███████▎  | 735/1000 [01:39<00:26,  9.87it/s]

 74%|███████▎  | 737/1000 [01:40<00:27,  9.52it/s]

 74%|███████▍  | 739/1000 [01:40<00:26,  9.78it/s]

 74%|███████▍  | 741/1000 [01:40<00:31,  8.30it/s]

 74%|███████▍  | 743/1000 [01:40<00:30,  8.35it/s]

 74%|███████▍  | 745/1000 [01:40<00:26,  9.60it/s]

 75%|███████▍  | 747/1000 [01:41<00:24, 10.43it/s]

 75%|███████▍  | 749/1000 [01:41<00:29,  8.63it/s]

 75%|███████▌  | 750/1000 [01:41<00:32,  7.68it/s]

 75%|███████▌  | 751/1000 [01:41<00:40,  6.16it/s]

 75%|███████▌  | 753/1000 [01:42<00:34,  7.23it/s]

 75%|███████▌  | 754/1000 [01:42<00:39,  6.23it/s]

 76%|███████▌  | 756/1000 [01:42<00:38,  6.40it/s]

 76%|███████▌  | 758/1000 [01:42<00:31,  7.61it/s]

 76%|███████▌  | 759/1000 [01:42<00:32,  7.32it/s]

 76%|███████▌  | 761/1000 [01:43<00:27,  8.72it/s]

 76%|███████▋  | 763/1000 [01:43<00:30,  7.66it/s]

 76%|███████▋  | 764/1000 [01:43<00:35,  6.61it/s]

 77%|███████▋  | 766/1000 [01:43<00:36,  6.47it/s]

 77%|███████▋  | 768/1000 [01:44<00:29,  7.79it/s]

 77%|███████▋  | 769/1000 [01:44<00:34,  6.63it/s]

 77%|███████▋  | 770/1000 [01:44<00:35,  6.55it/s]

 77%|███████▋  | 772/1000 [01:44<00:28,  8.13it/s]

 77%|███████▋  | 773/1000 [01:44<00:35,  6.39it/s]

 77%|███████▋  | 774/1000 [01:45<00:33,  6.79it/s]

 78%|███████▊  | 776/1000 [01:45<00:28,  7.89it/s]

 78%|███████▊  | 778/1000 [01:45<00:23,  9.60it/s]

 78%|███████▊  | 780/1000 [01:45<00:31,  6.94it/s]

 78%|███████▊  | 782/1000 [01:46<00:26,  8.36it/s]

 78%|███████▊  | 784/1000 [01:46<00:30,  7.15it/s]

 79%|███████▊  | 786/1000 [01:46<00:28,  7.53it/s]

 79%|███████▉  | 788/1000 [01:46<00:25,  8.36it/s]

 79%|███████▉  | 790/1000 [01:46<00:23,  8.99it/s]

 79%|███████▉  | 791/1000 [01:47<00:25,  8.22it/s]

 79%|███████▉  | 792/1000 [01:47<00:26,  7.73it/s]

 79%|███████▉  | 793/1000 [01:47<00:25,  7.97it/s]

 80%|███████▉  | 795/1000 [01:47<00:28,  7.19it/s]

 80%|███████▉  | 797/1000 [01:48<00:29,  6.86it/s]

 80%|███████▉  | 798/1000 [01:48<00:33,  6.01it/s]

 80%|████████  | 800/1000 [01:48<00:29,  6.72it/s]

 80%|████████  | 802/1000 [01:48<00:25,  7.64it/s]

 80%|████████  | 804/1000 [01:48<00:25,  7.83it/s]

 81%|████████  | 806/1000 [01:49<00:21,  9.18it/s]

 81%|████████  | 807/1000 [01:49<00:21,  8.98it/s]

 81%|████████  | 809/1000 [01:49<00:18, 10.22it/s]

 81%|████████  | 811/1000 [01:49<00:16, 11.24it/s]

 81%|████████▏ | 813/1000 [01:49<00:20,  9.05it/s]

 82%|████████▏ | 815/1000 [01:50<00:19,  9.31it/s]

 82%|████████▏ | 817/1000 [01:50<00:22,  8.14it/s]

 82%|████████▏ | 819/1000 [01:50<00:19,  9.20it/s]

 82%|████████▏ | 821/1000 [01:50<00:22,  8.05it/s]

 82%|████████▏ | 823/1000 [01:51<00:22,  7.82it/s]

 82%|████████▏ | 824/1000 [01:51<00:26,  6.75it/s]

 82%|████████▎ | 825/1000 [01:51<00:25,  7.00it/s]

 83%|████████▎ | 826/1000 [01:51<00:30,  5.80it/s]

 83%|████████▎ | 828/1000 [01:52<00:32,  5.23it/s]

 83%|████████▎ | 829/1000 [01:52<00:29,  5.73it/s]

 83%|████████▎ | 831/1000 [01:52<00:24,  7.01it/s]

 83%|████████▎ | 832/1000 [01:52<00:29,  5.75it/s]

 83%|████████▎ | 833/1000 [01:52<00:26,  6.23it/s]

 83%|████████▎ | 834/1000 [01:53<00:27,  6.02it/s]

 84%|████████▎ | 835/1000 [01:53<00:25,  6.54it/s]

 84%|████████▎ | 836/1000 [01:53<00:26,  6.11it/s]

 84%|████████▍ | 838/1000 [01:53<00:21,  7.46it/s]

 84%|████████▍ | 840/1000 [01:53<00:24,  6.62it/s]

 84%|████████▍ | 842/1000 [01:54<00:19,  8.16it/s]

 84%|████████▍ | 844/1000 [01:54<00:24,  6.42it/s]

 84%|████████▍ | 845/1000 [01:54<00:26,  5.77it/s]

 85%|████████▍ | 847/1000 [01:55<00:24,  6.25it/s]

 85%|████████▍ | 849/1000 [01:55<00:20,  7.49it/s]

 85%|████████▌ | 850/1000 [01:55<00:23,  6.46it/s]

 85%|████████▌ | 851/1000 [01:55<00:21,  6.84it/s]

 85%|████████▌ | 853/1000 [01:55<00:17,  8.45it/s]

 86%|████████▌ | 855/1000 [01:55<00:14, 10.03it/s]

 86%|████████▌ | 857/1000 [01:56<00:14, 10.19it/s]

 86%|████████▌ | 859/1000 [01:56<00:16,  8.51it/s]

 86%|████████▌ | 861/1000 [01:56<00:14,  9.75it/s]

 86%|████████▋ | 863/1000 [01:56<00:12, 10.61it/s]

 86%|████████▋ | 865/1000 [01:56<00:11, 11.63it/s]

 87%|████████▋ | 867/1000 [01:57<00:14,  9.28it/s]

 87%|████████▋ | 869/1000 [01:57<00:12, 10.25it/s]

 87%|████████▋ | 871/1000 [01:57<00:11, 11.27it/s]

 87%|████████▋ | 873/1000 [01:57<00:16,  7.76it/s]

 88%|████████▊ | 875/1000 [01:58<00:16,  7.63it/s]

 88%|████████▊ | 877/1000 [01:58<00:13,  8.88it/s]

 88%|████████▊ | 879/1000 [01:58<00:17,  6.87it/s]

 88%|████████▊ | 881/1000 [01:58<00:15,  7.60it/s]

 88%|████████▊ | 882/1000 [01:59<00:18,  6.54it/s]

 88%|████████▊ | 884/1000 [01:59<00:14,  7.96it/s]

 89%|████████▊ | 886/1000 [01:59<00:12,  9.18it/s]

 89%|████████▉ | 888/1000 [01:59<00:10, 10.35it/s]

 89%|████████▉ | 890/1000 [01:59<00:11,  9.77it/s]

 89%|████████▉ | 892/1000 [01:59<00:10, 10.76it/s]

 89%|████████▉ | 894/1000 [02:00<00:13,  7.60it/s]

 90%|████████▉ | 896/1000 [02:00<00:11,  8.84it/s]

 90%|████████▉ | 898/1000 [02:00<00:15,  6.53it/s]

 90%|█████████ | 900/1000 [02:01<00:12,  7.70it/s]

 90%|█████████ | 902/1000 [02:01<00:12,  7.86it/s]

 90%|█████████ | 904/1000 [02:01<00:10,  9.06it/s]

 91%|█████████ | 906/1000 [02:01<00:13,  7.04it/s]

 91%|█████████ | 908/1000 [02:02<00:11,  8.30it/s]

 91%|█████████ | 910/1000 [02:02<00:11,  7.58it/s]

 91%|█████████ | 912/1000 [02:02<00:10,  8.77it/s]

 91%|█████████▏| 914/1000 [02:02<00:11,  7.39it/s]

 92%|█████████▏| 916/1000 [02:03<00:11,  7.09it/s]

 92%|█████████▏| 917/1000 [02:03<00:11,  7.37it/s]

 92%|█████████▏| 918/1000 [02:03<00:14,  5.60it/s]

 92%|█████████▏| 919/1000 [02:03<00:14,  5.72it/s]

 92%|█████████▏| 921/1000 [02:04<00:14,  5.59it/s]

 92%|█████████▏| 922/1000 [02:04<00:13,  5.94it/s]

 92%|█████████▏| 924/1000 [02:04<00:10,  7.17it/s]

 93%|█████████▎| 926/1000 [02:04<00:08,  8.65it/s]

 93%|█████████▎| 927/1000 [02:04<00:09,  8.10it/s]

 93%|█████████▎| 928/1000 [02:05<00:10,  6.65it/s]

 93%|█████████▎| 930/1000 [02:05<00:10,  6.47it/s]

 93%|█████████▎| 931/1000 [02:05<00:10,  6.82it/s]

 93%|█████████▎| 933/1000 [02:05<00:10,  6.61it/s]

 93%|█████████▎| 934/1000 [02:06<00:10,  6.17it/s]

 94%|█████████▎| 936/1000 [02:06<00:08,  7.31it/s]

 94%|█████████▍| 938/1000 [02:06<00:07,  8.85it/s]

 94%|█████████▍| 939/1000 [02:06<00:07,  8.04it/s]

 94%|█████████▍| 940/1000 [02:06<00:07,  8.14it/s]

 94%|█████████▍| 942/1000 [02:07<00:09,  6.34it/s]

 94%|█████████▍| 944/1000 [02:07<00:07,  7.08it/s]

 95%|█████████▍| 946/1000 [02:07<00:06,  8.38it/s]

 95%|█████████▍| 948/1000 [02:07<00:05,  9.69it/s]

 95%|█████████▌| 950/1000 [02:07<00:05,  8.82it/s]

 95%|█████████▌| 952/1000 [02:08<00:06,  7.41it/s]

 95%|█████████▌| 954/1000 [02:08<00:07,  6.16it/s]

 96%|█████████▌| 956/1000 [02:08<00:05,  7.40it/s]

 96%|█████████▌| 957/1000 [02:09<00:06,  6.41it/s]

 96%|█████████▌| 959/1000 [02:09<00:07,  5.78it/s]

 96%|█████████▌| 961/1000 [02:09<00:05,  6.82it/s]

 96%|█████████▌| 962/1000 [02:09<00:06,  6.04it/s]

 96%|█████████▋| 964/1000 [02:10<00:04,  7.50it/s]

 96%|█████████▋| 965/1000 [02:10<00:05,  6.44it/s]

 97%|█████████▋| 966/1000 [02:10<00:05,  6.34it/s]

 97%|█████████▋| 968/1000 [02:10<00:03,  8.01it/s]

 97%|█████████▋| 970/1000 [02:10<00:03,  9.42it/s]

 97%|█████████▋| 972/1000 [02:11<00:03,  8.03it/s]

 97%|█████████▋| 974/1000 [02:11<00:02,  9.21it/s]

 98%|█████████▊| 976/1000 [02:11<00:02,  9.81it/s]

 98%|█████████▊| 978/1000 [02:11<00:02, 10.81it/s]

 98%|█████████▊| 980/1000 [02:11<00:02,  8.42it/s]

 98%|█████████▊| 981/1000 [02:12<00:02,  7.05it/s]

 98%|█████████▊| 982/1000 [02:12<00:03,  5.43it/s]

 98%|█████████▊| 984/1000 [02:12<00:02,  6.91it/s]

 99%|█████████▊| 986/1000 [02:12<00:01,  8.36it/s]

 99%|█████████▉| 988/1000 [02:13<00:01,  6.74it/s]

 99%|█████████▉| 989/1000 [02:13<00:01,  5.99it/s]

 99%|█████████▉| 991/1000 [02:13<00:01,  6.15it/s]

 99%|█████████▉| 992/1000 [02:14<00:01,  4.98it/s]

 99%|█████████▉| 994/1000 [02:14<00:00,  6.54it/s]

100%|█████████▉| 995/1000 [02:14<00:00,  5.53it/s]

100%|█████████▉| 997/1000 [02:14<00:00,  7.05it/s]

100%|█████████▉| 999/1000 [02:15<00:00,  6.77it/s]

100%|██████████| 1000/1000 [02:15<00:00,  6.67it/s]
                                                    

                                                   
{'eval_loss': '0.8473', 'eval_runtime': '135.4', 'eval_samples_per_second': '7.384', 'eval_steps_per_second': '7.384', 'epoch': '0.1655', 'num_input_tokens_seen': 1988312}

 17%|█▋        | 300/1813 [33:24<2:32:20,  6.04s/it]

100%|██████████| 1000/1000 [02:15<00:00,  6.67it/s]

                                                   
 17%|█▋        | 301/1813 [33:29<19:32:14, 46.52s/it]
 17%|█▋        | 302/1813 [33:34<14:17:15, 34.04s/it]
 17%|█▋        | 303/1813 [33:41<10:51:02, 25.87s/it]
 17%|█▋        | 304/1813 [33:48<8:31:47, 20.35s/it] 
 17%|█▋        | 305/1813 [33:54<6:44:44, 16.10s/it]
 17%|█▋        | 306/1813 [34:00<5:26:49, 13.01s/it]
 17%|█▋        | 307/1813 [34:06<4:29:24, 10.73s/it]
 17%|█▋        | 308/1813 [34:11<3:49:36,  9.15s/it]
 17%|█▋        | 309/1813 [34:17<3:28:26,  8.32s/it]
 17%|█▋        | 310/1813 [34:22<3:02:28,  7.28s/it]
                                                    
{'loss': '0.9655', 'grad_norm': '1.182', 'learning_rate': '9.776e-05', 'epoch': '0.171', 'num_input_tokens_seen': 2050672, 'train_runtime': '2063', 'train_tokens_per_second': '994.1'}

 17%|█▋        | 310/1813 [34:22<3:02:28,  7.28s/it]
 17%|█▋        | 311/1813 [34:30<3:01:29,  7.25s/it]
 17%|█▋        | 312/1813 [34:37<3:02:06,  7.28s/it]
 17%|█▋        | 313/1813 [34:44<2:57:49,  7.11s/it]
 17%|█▋        | 314/1813 [34:49<2:46:38,  6.67s/it]
 17%|█▋        | 315/1813 [34:56<2:48:44,  6.76s/it]
 17%|█▋        | 316/1813 [35:03<2:46:41,  6.68s/it]
 17%|█▋        | 317/1813 [35:09<2:41:28,  6.48s/it]
 18%|█▊        | 318/1813 [35:14<2:34:29,  6.20s/it]
 18%|█▊        | 319/1813 [35:19<2:25:34,  5.85s/it]
 18%|█▊        | 320/1813 [35:25<2:25:59,  5.87s/it]
                                                    
{'loss': '1.054', 'grad_norm': '0.6159', 'learning_rate': '9.747e-05', 'epoch': '0.1766', 'num_input_tokens_seen': 2118000, 'train_runtime': '2126', 'train_tokens_per_second': '996.4'}

 18%|█▊        | 320/1813 [35:25<2:25:59,  5.87s/it]
 18%|█▊        | 321/1813 [35:31<2:26:50,  5.91s/it]
 18%|█▊        | 322/1813 [35:37<2:27:57,  5.95s/it]
 18%|█▊        | 323/1813 [35:44<2:31:31,  6.10s/it]
 18%|█▊        | 324/1813 [35:51<2:37:40,  6.35s/it]
 18%|█▊        | 325/1813 [35:58<2:41:37,  6.52s/it]
 18%|█▊        | 326/1813 [36:04<2:37:48,  6.37s/it]
 18%|█▊        | 327/1813 [36:09<2:32:44,  6.17s/it]
 18%|█▊        | 328/1813 [36:16<2:36:09,  6.31s/it]
 18%|█▊        | 329/1813 [36:22<2:31:17,  6.12s/it]
 18%|█▊        | 330/1813 [36:27<2:27:41,  5.98s/it]
                                                    
{'loss': '0.9614', 'grad_norm': '0.9737', 'learning_rate': '9.717e-05', 'epoch': '0.1821', 'num_input_tokens_seen': 2184640, 'train_runtime': '2188', 'train_tokens_per_second': '998.6'}

 18%|█▊        | 330/1813 [36:27<2:27:41,  5.98s/it]
 18%|█▊        | 331/1813 [36:33<2:29:12,  6.04s/it]
 18%|█▊        | 332/1813 [36:38<2:21:18,  5.72s/it]
 18%|█▊        | 333/1813 [36:44<2:22:39,  5.78s/it]
 18%|█▊        | 334/1813 [36:50<2:22:18,  5.77s/it]
 18%|█▊        | 335/1813 [36:58<2:36:20,  6.35s/it]
 19%|█▊        | 336/1813 [37:05<2:41:12,  6.55s/it]
 19%|█▊        | 337/1813 [37:11<2:35:28,  6.32s/it]
 19%|█▊        | 338/1813 [37:17<2:35:16,  6.32s/it]
 19%|█▊        | 339/1813 [37:23<2:31:47,  6.18s/it]
 19%|█▉        | 340/1813 [37:30<2:39:15,  6.49s/it]
                                                    
{'loss': '0.9404', 'grad_norm': '1.043', 'learning_rate': '9.685e-05', 'epoch': '0.1876', 'num_input_tokens_seen': 2251392, 'train_runtime': '2250', 'train_tokens_per_second': '1000'}

 19%|█▉        | 340/1813 [37:30<2:39:15,  6.49s/it]
 19%|█▉        | 341/1813 [37:36<2:38:28,  6.46s/it]
 19%|█▉        | 342/1813 [37:44<2:45:27,  6.75s/it]
 19%|█▉        | 343/1813 [37:49<2:37:48,  6.44s/it]
 19%|█▉        | 344/1813 [37:55<2:32:53,  6.24s/it]
 19%|█▉        | 345/1813 [38:03<2:40:47,  6.57s/it]
 19%|█▉        | 346/1813 [38:09<2:39:34,  6.53s/it]
 19%|█▉        | 347/1813 [38:14<2:28:45,  6.09s/it]
 19%|█▉        | 348/1813 [38:21<2:32:25,  6.24s/it]
 19%|█▉        | 349/1813 [38:29<2:48:21,  6.90s/it]
 19%|█▉        | 350/1813 [38:37<2:55:03,  7.18s/it]
                                                    
{'loss': '1.055', 'grad_norm': '0.817', 'learning_rate': '9.651e-05', 'epoch': '0.1931', 'num_input_tokens_seen': 2324712, 'train_runtime': '2317', 'train_tokens_per_second': '1003'}

 19%|█▉        | 350/1813 [38:37<2:55:03,  7.18s/it]
 19%|█▉        | 351/1813 [38:44<2:53:43,  7.13s/it]
 19%|█▉        | 352/1813 [38:50<2:45:46,  6.81s/it]
 19%|█▉        | 353/1813 [38:56<2:37:54,  6.49s/it]
 20%|█▉        | 354/1813 [39:02<2:33:32,  6.31s/it]
 20%|█▉        | 355/1813 [39:08<2:32:35,  6.28s/it]
 20%|█▉        | 356/1813 [39:15<2:37:58,  6.51s/it]
 20%|█▉        | 357/1813 [39:21<2:33:44,  6.34s/it]
 20%|█▉        | 358/1813 [39:27<2:34:41,  6.38s/it]
 20%|█▉        | 359/1813 [39:33<2:31:38,  6.26s/it]
 20%|█▉        | 360/1813 [39:40<2:35:54,  6.44s/it]
                                                    
{'loss': '0.9962', 'grad_norm': '1.841', 'learning_rate': '9.615e-05', 'epoch': '0.1986', 'num_input_tokens_seen': 2390776, 'train_runtime': '2381', 'train_tokens_per_second': '1004'}

 20%|█▉        | 360/1813 [39:40<2:35:54,  6.44s/it]
 20%|█▉        | 361/1813 [39:45<2:25:53,  6.03s/it]
 20%|█▉        | 362/1813 [39:51<2:23:05,  5.92s/it]
 20%|██        | 363/1813 [39:58<2:29:58,  6.21s/it]
 20%|██        | 364/1813 [40:04<2:32:40,  6.32s/it]
 20%|██        | 365/1813 [40:10<2:29:31,  6.20s/it]
 20%|██        | 366/1813 [40:17<2:35:08,  6.43s/it]
 20%|██        | 367/1813 [40:23<2:32:05,  6.31s/it]
 20%|██        | 368/1813 [40:29<2:25:52,  6.06s/it]
 20%|██        | 369/1813 [40:33<2:15:27,  5.63s/it]
 20%|██        | 370/1813 [40:39<2:16:58,  5.70s/it]
                                                    
{'loss': '0.9922', 'grad_norm': '1.217', 'learning_rate': '9.578e-05', 'epoch': '0.2041', 'num_input_tokens_seen': 2454808, 'train_runtime': '2440', 'train_tokens_per_second': '1006'}

 20%|██        | 370/1813 [40:39<2:16:58,  5.70s/it]
 20%|██        | 371/1813 [40:44<2:12:04,  5.50s/it]
 21%|██        | 372/1813 [40:52<2:31:20,  6.30s/it]
 21%|██        | 373/1813 [40:59<2:29:50,  6.24s/it]
 21%|██        | 374/1813 [41:06<2:38:04,  6.59s/it]
 21%|██        | 375/1813 [41:13<2:39:30,  6.66s/it]
 21%|██        | 376/1813 [41:18<2:29:23,  6.24s/it]
 21%|██        | 377/1813 [41:24<2:28:12,  6.19s/it]
 21%|██        | 378/1813 [41:30<2:26:21,  6.12s/it]
 21%|██        | 379/1813 [41:35<2:18:08,  5.78s/it]
 21%|██        | 380/1813 [41:40<2:12:59,  5.57s/it]
                                                    
{'loss': '0.9639', 'grad_norm': '1.139', 'learning_rate': '9.539e-05', 'epoch': '0.2097', 'num_input_tokens_seen': 2520472, 'train_runtime': '2501', 'train_tokens_per_second': '1008'}

 21%|██        | 380/1813 [41:40<2:12:59,  5.57s/it]
 21%|██        | 381/1813 [41:47<2:22:48,  5.98s/it]
 21%|██        | 382/1813 [41:54<2:28:42,  6.24s/it]
 21%|██        | 383/1813 [42:00<2:27:29,  6.19s/it]
 21%|██        | 384/1813 [42:06<2:26:11,  6.14s/it]
 21%|██        | 385/1813 [42:12<2:26:06,  6.14s/it]
 21%|██▏       | 386/1813 [42:17<2:14:55,  5.67s/it]
 21%|██▏       | 387/1813 [42:23<2:17:28,  5.78s/it]
 21%|██▏       | 388/1813 [42:30<2:26:33,  6.17s/it]
 21%|██▏       | 389/1813 [42:38<2:37:26,  6.63s/it]
 22%|██▏       | 390/1813 [42:44<2:37:12,  6.63s/it]
                                                    
{'loss': '1.002', 'grad_norm': '0.7518', 'learning_rate': '9.499e-05', 'epoch': '0.2152', 'num_input_tokens_seen': 2591512, 'train_runtime': '2565', 'train_tokens_per_second': '1010'}

 22%|██▏       | 390/1813 [42:44<2:37:12,  6.63s/it]
 22%|██▏       | 391/1813 [42:50<2:33:27,  6.47s/it]
 22%|██▏       | 392/1813 [42:57<2:32:32,  6.44s/it]
 22%|██▏       | 393/1813 [43:03<2:34:58,  6.55s/it]
 22%|██▏       | 394/1813 [43:08<2:22:52,  6.04s/it]
 22%|██▏       | 395/1813 [43:14<2:18:36,  5.86s/it]
 22%|██▏       | 396/1813 [43:20<2:23:04,  6.06s/it]
 22%|██▏       | 397/1813 [43:25<2:17:06,  5.81s/it]
 22%|██▏       | 398/1813 [43:32<2:21:34,  6.00s/it]
 22%|██▏       | 399/1813 [43:40<2:33:32,  6.52s/it]
 22%|██▏       | 400/1813 [43:48<2:46:13,  7.06s/it]
                                                    
{'loss': '0.9768', 'grad_norm': '0.8913', 'learning_rate': '9.457e-05', 'epoch': '0.2207', 'num_input_tokens_seen': 2660336, 'train_runtime': '2628', 'train_tokens_per_second': '1012'}

 22%|██▏       | 400/1813 [43:48<2:46:13,  7.06s/it]
 22%|██▏       | 401/1813 [43:55<2:48:11,  7.15s/it]
 22%|██▏       | 402/1813 [44:00<2:32:49,  6.50s/it]
 22%|██▏       | 403/1813 [44:07<2:31:08,  6.43s/it]
 22%|██▏       | 404/1813 [44:14<2:34:45,  6.59s/it]
 22%|██▏       | 405/1813 [44:21<2:39:34,  6.80s/it]
 22%|██▏       | 406/1813 [44:26<2:25:54,  6.22s/it]
 22%|██▏       | 407/1813 [44:30<2:13:42,  5.71s/it]
 23%|██▎       | 408/1813 [44:36<2:15:24,  5.78s/it]
 23%|██▎       | 409/1813 [44:42<2:16:54,  5.85s/it]
 23%|██▎       | 410/1813 [44:48<2:14:53,  5.77s/it]
                                                    
{'loss': '1.009', 'grad_norm': '1.12', 'learning_rate': '9.413e-05', 'epoch': '0.2262', 'num_input_tokens_seen': 2722056, 'train_runtime': '2688', 'train_tokens_per_second': '1013'}

 23%|██▎       | 410/1813 [44:48<2:14:53,  5.77s/it]
 23%|██▎       | 411/1813 [44:54<2:18:39,  5.93s/it]
 23%|██▎       | 412/1813 [45:00<2:21:49,  6.07s/it]
 23%|██▎       | 413/1813 [45:08<2:28:47,  6.38s/it]
 23%|██▎       | 414/1813 [45:13<2:20:33,  6.03s/it]
 23%|██▎       | 415/1813 [45:19<2:21:37,  6.08s/it]
 23%|██▎       | 416/1813 [45:26<2:25:04,  6.23s/it]
 23%|██▎       | 417/1813 [45:33<2:34:17,  6.63s/it]
 23%|██▎       | 418/1813 [45:39<2:27:20,  6.34s/it]
 23%|██▎       | 419/1813 [45:45<2:28:53,  6.41s/it]
 23%|██▎       | 420/1813 [45:51<2:24:52,  6.24s/it]
                                                    
{'loss': '0.9971', 'grad_norm': '0.6842', 'learning_rate': '9.368e-05', 'epoch': '0.2317', 'num_input_tokens_seen': 2790960, 'train_runtime': '2752', 'train_tokens_per_second': '1014'}

 23%|██▎       | 420/1813 [45:51<2:24:52,  6.24s/it]
 23%|██▎       | 421/1813 [45:58<2:25:41,  6.28s/it]
 23%|██▎       | 422/1813 [46:05<2:32:41,  6.59s/it]
 23%|██▎       | 423/1813 [46:11<2:27:24,  6.36s/it]
 23%|██▎       | 424/1813 [46:17<2:24:34,  6.25s/it]
 23%|██▎       | 425/1813 [46:22<2:19:06,  6.01s/it]
 23%|██▎       | 426/1813 [46:29<2:27:26,  6.38s/it]
 24%|██▎       | 427/1813 [46:35<2:24:30,  6.26s/it]
 24%|██▎       | 428/1813 [46:41<2:23:18,  6.21s/it]
 24%|██▎       | 429/1813 [46:47<2:16:24,  5.91s/it]
 24%|██▎       | 430/1813 [46:54<2:27:45,  6.41s/it]
                                                    
{'loss': '0.986', 'grad_norm': '0.6879', 'learning_rate': '9.321e-05', 'epoch': '0.2372', 'num_input_tokens_seen': 2860096, 'train_runtime': '2815', 'train_tokens_per_second': '1016'}

 24%|██▎       | 430/1813 [46:54<2:27:45,  6.41s/it]
 24%|██▍       | 431/1813 [47:00<2:25:02,  6.30s/it]
 24%|██▍       | 432/1813 [47:06<2:20:56,  6.12s/it]
 24%|██▍       | 433/1813 [47:11<2:15:26,  5.89s/it]
 24%|██▍       | 434/1813 [47:18<2:19:26,  6.07s/it]
 24%|██▍       | 435/1813 [47:24<2:18:04,  6.01s/it]
 24%|██▍       | 436/1813 [47:30<2:20:31,  6.12s/it]
 24%|██▍       | 437/1813 [47:36<2:17:36,  6.00s/it]
 24%|██▍       | 438/1813 [47:42<2:19:36,  6.09s/it]
 24%|██▍       | 439/1813 [47:48<2:18:31,  6.05s/it]
 24%|██▍       | 440/1813 [47:54<2:19:28,  6.10s/it]
                                                    
{'loss': '0.8981', 'grad_norm': '1.202', 'learning_rate': '9.273e-05', 'epoch': '0.2428', 'num_input_tokens_seen': 2924856, 'train_runtime': '2875', 'train_tokens_per_second': '1017'}

 24%|██▍       | 440/1813 [47:54<2:19:28,  6.10s/it]
 24%|██▍       | 441/1813 [48:00<2:18:12,  6.04s/it]
 24%|██▍       | 442/1813 [48:06<2:19:22,  6.10s/it]
 24%|██▍       | 443/1813 [48:13<2:24:00,  6.31s/it]
 24%|██▍       | 444/1813 [48:19<2:18:22,  6.07s/it]
 25%|██▍       | 445/1813 [48:26<2:25:36,  6.39s/it]
 25%|██▍       | 446/1813 [48:32<2:25:10,  6.37s/it]
 25%|██▍       | 447/1813 [48:38<2:23:03,  6.28s/it]
 25%|██▍       | 448/1813 [48:44<2:22:00,  6.24s/it]
 25%|██▍       | 449/1813 [48:50<2:14:42,  5.93s/it]
 25%|██▍       | 450/1813 [48:55<2:10:33,  5.75s/it]
                                                    
{'loss': '1.027', 'grad_norm': '0.9296', 'learning_rate': '9.223e-05', 'epoch': '0.2483', 'num_input_tokens_seen': 2990040, 'train_runtime': '2935', 'train_tokens_per_second': '1019'}

 25%|██▍       | 450/1813 [48:55<2:10:33,  5.75s/it]
 25%|██▍       | 451/1813 [49:02<2:22:07,  6.26s/it]
 25%|██▍       | 452/1813 [49:08<2:18:14,  6.09s/it]
 25%|██▍       | 453/1813 [49:13<2:10:49,  5.77s/it]
 25%|██▌       | 454/1813 [49:20<2:17:15,  6.06s/it]
 25%|██▌       | 455/1813 [49:26<2:19:48,  6.18s/it]
 25%|██▌       | 456/1813 [49:31<2:06:45,  5.60s/it]
 25%|██▌       | 457/1813 [49:37<2:10:00,  5.75s/it]
 25%|██▌       | 458/1813 [49:45<2:24:41,  6.41s/it]
 25%|██▌       | 459/1813 [49:52<2:28:00,  6.56s/it]
 25%|██▌       | 460/1813 [49:58<2:26:23,  6.49s/it]
                                                    
{'loss': '1.088', 'grad_norm': '0.7194', 'learning_rate': '9.172e-05', 'epoch': '0.2538', 'num_input_tokens_seen': 3058848, 'train_runtime': '2998', 'train_tokens_per_second': '1020'}

 25%|██▌       | 460/1813 [49:58<2:26:23,  6.49s/it]
 25%|██▌       | 461/1813 [50:04<2:22:40,  6.33s/it]
 25%|██▌       | 462/1813 [50:11<2:29:43,  6.65s/it]
 26%|██▌       | 463/1813 [50:17<2:24:26,  6.42s/it]
 26%|██▌       | 464/1813 [50:22<2:14:54,  6.00s/it]
 26%|██▌       | 465/1813 [50:28<2:11:58,  5.87s/it]
 26%|██▌       | 466/1813 [50:34<2:16:52,  6.10s/it]
 26%|██▌       | 467/1813 [50:40<2:14:22,  5.99s/it]
 26%|██▌       | 468/1813 [50:47<2:17:38,  6.14s/it]
 26%|██▌       | 469/1813 [50:53<2:19:39,  6.23s/it]
 26%|██▌       | 470/1813 [51:00<2:21:55,  6.34s/it]
                                                    
{'loss': '0.9541', 'grad_norm': '0.6546', 'learning_rate': '9.119e-05', 'epoch': '0.2593', 'num_input_tokens_seen': 3126680, 'train_runtime': '3060', 'train_tokens_per_second': '1022'}

 26%|██▌       | 470/1813 [51:00<2:21:55,  6.34s/it]
 26%|██▌       | 471/1813 [51:05<2:16:46,  6.12s/it]
 26%|██▌       | 472/1813 [51:12<2:19:39,  6.25s/it]
 26%|██▌       | 473/1813 [51:18<2:22:19,  6.37s/it]
 26%|██▌       | 474/1813 [51:24<2:20:02,  6.27s/it]
 26%|██▌       | 475/1813 [51:30<2:12:29,  5.94s/it]
 26%|██▋       | 476/1813 [51:36<2:12:18,  5.94s/it]
 26%|██▋       | 477/1813 [51:42<2:16:15,  6.12s/it]
 26%|██▋       | 478/1813 [51:49<2:21:54,  6.38s/it]
 26%|██▋       | 479/1813 [51:55<2:17:50,  6.20s/it]
 26%|██▋       | 480/1813 [52:01<2:19:22,  6.27s/it]
                                                    
{'loss': '1.059', 'grad_norm': '0.9186', 'learning_rate': '9.065e-05', 'epoch': '0.2648', 'num_input_tokens_seen': 3193704, 'train_runtime': '3122', 'train_tokens_per_second': '1023'}

 26%|██▋       | 480/1813 [52:01<2:19:22,  6.27s/it]
 27%|██▋       | 481/1813 [52:08<2:19:30,  6.28s/it]
 27%|██▋       | 482/1813 [52:14<2:22:30,  6.42s/it]
 27%|██▋       | 483/1813 [52:22<2:30:37,  6.80s/it]
 27%|██▋       | 484/1813 [52:28<2:24:46,  6.54s/it]
 27%|██▋       | 485/1813 [52:36<2:33:15,  6.92s/it]
 27%|██▋       | 486/1813 [52:42<2:28:58,  6.74s/it]
 27%|██▋       | 487/1813 [52:49<2:30:07,  6.79s/it]
 27%|██▋       | 488/1813 [52:55<2:23:35,  6.50s/it]
 27%|██▋       | 489/1813 [53:02<2:27:40,  6.69s/it]
 27%|██▋       | 490/1813 [53:08<2:25:42,  6.61s/it]
                                                    
{'loss': '1.011', 'grad_norm': '0.9458', 'learning_rate': '9.009e-05', 'epoch': '0.2703', 'num_input_tokens_seen': 3268064, 'train_runtime': '3189', 'train_tokens_per_second': '1025'}

 27%|██▋       | 490/1813 [53:08<2:25:42,  6.61s/it]
 27%|██▋       | 491/1813 [53:15<2:27:54,  6.71s/it]
 27%|██▋       | 492/1813 [53:23<2:33:49,  6.99s/it]
 27%|██▋       | 493/1813 [53:29<2:25:04,  6.59s/it]
 27%|██▋       | 494/1813 [53:34<2:20:09,  6.38s/it]
 27%|██▋       | 495/1813 [53:42<2:25:48,  6.64s/it]
 27%|██▋       | 496/1813 [53:48<2:24:22,  6.58s/it]
 27%|██▋       | 497/1813 [53:54<2:17:04,  6.25s/it]
 27%|██▋       | 498/1813 [54:01<2:23:07,  6.53s/it]
 28%|██▊       | 499/1813 [54:07<2:19:53,  6.39s/it]
 28%|██▊       | 500/1813 [54:16<2:37:35,  7.20s/it]
                                                    
{'loss': '1.094', 'grad_norm': '0.6796', 'learning_rate': '8.952e-05', 'epoch': '0.2759', 'num_input_tokens_seen': 3341536, 'train_runtime': '3257', 'train_tokens_per_second': '1026'}

 28%|██▊       | 500/1813 [54:16<2:37:35,  7.20s/it]
 28%|██▊       | 501/1813 [54:22<2:29:40,  6.85s/it]
 28%|██▊       | 502/1813 [54:28<2:21:17,  6.47s/it]
 28%|██▊       | 503/1813 [54:33<2:12:08,  6.05s/it]
 28%|██▊       | 504/1813 [54:39<2:13:19,  6.11s/it]
 28%|██▊       | 505/1813 [54:46<2:19:34,  6.40s/it]
 28%|██▊       | 506/1813 [54:52<2:16:28,  6.27s/it]
 28%|██▊       | 507/1813 [54:59<2:23:19,  6.58s/it]
 28%|██▊       | 508/1813 [55:05<2:14:37,  6.19s/it]
 28%|██▊       | 509/1813 [55:10<2:08:06,  5.89s/it]
 28%|██▊       | 510/1813 [55:15<2:05:43,  5.79s/it]
                                                    
{'loss': '0.9266', 'grad_norm': '1.227', 'learning_rate': '8.894e-05', 'epoch': '0.2814', 'num_input_tokens_seen': 3402712, 'train_runtime': '3316', 'train_tokens_per_second': '1026'}

 28%|██▊       | 510/1813 [55:15<2:05:43,  5.79s/it]
 28%|██▊       | 511/1813 [55:21<2:04:31,  5.74s/it]
 28%|██▊       | 512/1813 [55:28<2:11:30,  6.07s/it]
 28%|██▊       | 513/1813 [55:35<2:18:14,  6.38s/it]
 28%|██▊       | 514/1813 [55:42<2:20:52,  6.51s/it]
 28%|██▊       | 515/1813 [55:47<2:11:26,  6.08s/it]
 28%|██▊       | 516/1813 [55:52<2:08:07,  5.93s/it]
 29%|██▊       | 517/1813 [55:59<2:12:32,  6.14s/it]
 29%|██▊       | 518/1813 [56:05<2:11:57,  6.11s/it]
 29%|██▊       | 519/1813 [56:11<2:12:26,  6.14s/it]
 29%|██▊       | 520/1813 [56:18<2:17:18,  6.37s/it]
                                                    
{'loss': '0.9738', 'grad_norm': '0.9356', 'learning_rate': '8.834e-05', 'epoch': '0.2869', 'num_input_tokens_seen': 3469624, 'train_runtime': '3379', 'train_tokens_per_second': '1027'}

 29%|██▊       | 520/1813 [56:18<2:17:18,  6.37s/it]
 29%|██▊       | 521/1813 [56:22<2:04:08,  5.77s/it]
 29%|██▉       | 522/1813 [56:29<2:06:20,  5.87s/it]
 29%|██▉       | 523/1813 [56:35<2:07:41,  5.94s/it]
 29%|██▉       | 524/1813 [56:41<2:09:52,  6.05s/it]
 29%|██▉       | 525/1813 [56:46<2:03:03,  5.73s/it]
 29%|██▉       | 526/1813 [56:53<2:09:05,  6.02s/it]
 29%|██▉       | 527/1813 [56:59<2:12:40,  6.19s/it]
 29%|██▉       | 528/1813 [57:06<2:17:12,  6.41s/it]
 29%|██▉       | 529/1813 [57:13<2:21:22,  6.61s/it]
 29%|██▉       | 530/1813 [57:19<2:16:08,  6.37s/it]
                                                    
{'loss': '0.965', 'grad_norm': '1.142', 'learning_rate': '8.772e-05', 'epoch': '0.2924', 'num_input_tokens_seen': 3534904, 'train_runtime': '3440', 'train_tokens_per_second': '1028'}

 29%|██▉       | 530/1813 [57:19<2:16:08,  6.37s/it]
 29%|██▉       | 531/1813 [57:27<2:27:23,  6.90s/it]
 29%|██▉       | 532/1813 [57:33<2:23:11,  6.71s/it]
 29%|██▉       | 533/1813 [57:41<2:25:38,  6.83s/it]
 29%|██▉       | 534/1813 [57:48<2:28:08,  6.95s/it]
 30%|██▉       | 535/1813 [57:52<2:11:29,  6.17s/it]
 30%|██▉       | 536/1813 [57:57<2:04:38,  5.86s/it]
 30%|██▉       | 537/1813 [58:04<2:09:08,  6.07s/it]
 30%|██▉       | 538/1813 [58:09<2:05:50,  5.92s/it]
 30%|██▉       | 539/1813 [58:16<2:07:52,  6.02s/it]
 30%|██▉       | 540/1813 [58:22<2:09:56,  6.12s/it]
                                                    
{'loss': '0.9709', 'grad_norm': '0.7969', 'learning_rate': '8.71e-05', 'epoch': '0.2979', 'num_input_tokens_seen': 3603488, 'train_runtime': '3503', 'train_tokens_per_second': '1029'}

 30%|██▉       | 540/1813 [58:22<2:09:56,  6.12s/it]
 30%|██▉       | 541/1813 [58:27<2:05:31,  5.92s/it]
 30%|██▉       | 542/1813 [58:33<2:04:44,  5.89s/it]
 30%|██▉       | 543/1813 [58:41<2:14:03,  6.33s/it]
 30%|███       | 544/1813 [58:49<2:27:09,  6.96s/it]
 30%|███       | 545/1813 [58:56<2:24:30,  6.84s/it]
 30%|███       | 546/1813 [59:02<2:22:21,  6.74s/it]
 30%|███       | 547/1813 [59:10<2:27:49,  7.01s/it]
 30%|███       | 548/1813 [59:17<2:30:28,  7.14s/it]
 30%|███       | 549/1813 [59:23<2:22:19,  6.76s/it]
 30%|███       | 550/1813 [59:29<2:17:30,  6.53s/it]
                                                    
{'loss': '0.9095', 'grad_norm': '0.9145', 'learning_rate': '8.646e-05', 'epoch': '0.3034', 'num_input_tokens_seen': 3676576, 'train_runtime': '3570', 'train_tokens_per_second': '1030'}

 30%|███       | 550/1813 [59:29<2:17:30,  6.53s/it]
 30%|███       | 551/1813 [59:35<2:13:48,  6.36s/it]
 30%|███       | 552/1813 [59:40<2:07:27,  6.06s/it]
 31%|███       | 553/1813 [59:45<1:59:41,  5.70s/it]
 31%|███       | 554/1813 [59:52<2:06:26,  6.03s/it]
 31%|███       | 555/1813 [59:57<2:01:14,  5.78s/it]
 31%|███       | 556/1813 [1:00:03<2:03:09,  5.88s/it]
 31%|███       | 557/1813 [1:00:10<2:09:39,  6.19s/it]
 31%|███       | 558/1813 [1:00:16<2:07:13,  6.08s/it]
 31%|███       | 559/1813 [1:00:21<2:01:13,  5.80s/it]
 31%|███       | 560/1813 [1:00:28<2:05:30,  6.01s/it]
                                                      
{'loss': '0.9786', 'grad_norm': '0.6304', 'learning_rate': '8.58e-05', 'epoch': '0.309', 'num_input_tokens_seen': 3738056, 'train_runtime': '3628', 'train_tokens_per_second': '1030'}

 31%|███       | 560/1813 [1:00:28<2:05:30,  6.01s/it]
 31%|███       | 561/1813 [1:00:34<2:04:46,  5.98s/it]
 31%|███       | 562/1813 [1:00:40<2:08:41,  6.17s/it]
 31%|███       | 563/1813 [1:00:47<2:13:18,  6.40s/it]
 31%|███       | 564/1813 [1:00:53<2:11:48,  6.33s/it]
 31%|███       | 565/1813 [1:00:59<2:07:35,  6.13s/it]
 31%|███       | 566/1813 [1:01:06<2:10:25,  6.28s/it]
 31%|███▏      | 567/1813 [1:01:11<2:03:57,  5.97s/it]
 31%|███▏      | 568/1813 [1:01:18<2:08:15,  6.18s/it]
 31%|███▏      | 569/1813 [1:01:25<2:16:06,  6.56s/it]
 31%|███▏      | 570/1813 [1:01:33<2:22:01,  6.86s/it]
                                                      
{'loss': '0.9762', 'grad_norm': '0.6829', 'learning_rate': '8.514e-05', 'epoch': '0.3145', 'num_input_tokens_seen': 3808208, 'train_runtime': '3693', 'train_tokens_per_second': '1031'}

 31%|███▏      | 570/1813 [1:01:33<2:22:01,  6.86s/it]
 31%|███▏      | 571/1813 [1:01:39<2:21:19,  6.83s/it]
 32%|███▏      | 572/1813 [1:01:45<2:15:52,  6.57s/it]
 32%|███▏      | 573/1813 [1:01:51<2:07:03,  6.15s/it]
 32%|███▏      | 574/1813 [1:01:56<2:03:53,  6.00s/it]
 32%|███▏      | 575/1813 [1:02:03<2:07:42,  6.19s/it]
 32%|███▏      | 576/1813 [1:02:08<1:58:57,  5.77s/it]
 32%|███▏      | 577/1813 [1:02:14<2:05:01,  6.07s/it]
 32%|███▏      | 578/1813 [1:02:21<2:06:16,  6.14s/it]
 32%|███▏      | 579/1813 [1:02:27<2:07:20,  6.19s/it]
 32%|███▏      | 580/1813 [1:02:33<2:08:36,  6.26s/it]
                                                      
{'loss': '0.9771', 'grad_norm': '0.8526', 'learning_rate': '8.446e-05', 'epoch': '0.32', 'num_input_tokens_seen': 3872328, 'train_runtime': '3754', 'train_tokens_per_second': '1032'}

 32%|███▏      | 580/1813 [1:02:33<2:08:36,  6.26s/it]
 32%|███▏      | 581/1813 [1:02:39<2:06:19,  6.15s/it]
 32%|███▏      | 582/1813 [1:02:45<2:02:31,  5.97s/it]
 32%|███▏      | 583/1813 [1:02:51<2:02:46,  5.99s/it]
 32%|███▏      | 584/1813 [1:02:57<2:05:18,  6.12s/it]
 32%|███▏      | 585/1813 [1:03:03<2:03:50,  6.05s/it]
 32%|███▏      | 586/1813 [1:03:10<2:05:49,  6.15s/it]
 32%|███▏      | 587/1813 [1:03:15<2:03:47,  6.06s/it]
 32%|███▏      | 588/1813 [1:03:21<2:03:29,  6.05s/it]
 32%|███▏      | 589/1813 [1:03:28<2:04:12,  6.09s/it]
 33%|███▎      | 590/1813 [1:03:34<2:03:55,  6.08s/it]
                                                      
{'loss': '0.8897', 'grad_norm': '0.9513', 'learning_rate': '8.377e-05', 'epoch': '0.3255', 'num_input_tokens_seen': 3936024, 'train_runtime': '3814', 'train_tokens_per_second': '1032'}

 33%|███▎      | 590/1813 [1:03:34<2:03:55,  6.08s/it]
 33%|███▎      | 591/1813 [1:03:39<1:59:42,  5.88s/it]
 33%|███▎      | 592/1813 [1:03:45<2:00:52,  5.94s/it]
 33%|███▎      | 593/1813 [1:03:52<2:04:03,  6.10s/it]
 33%|███▎      | 594/1813 [1:03:58<2:03:00,  6.05s/it]
 33%|███▎      | 595/1813 [1:04:03<2:00:12,  5.92s/it]
 33%|███▎      | 596/1813 [1:04:09<2:00:46,  5.95s/it]
 33%|███▎      | 597/1813 [1:04:15<1:58:44,  5.86s/it]
 33%|███▎      | 598/1813 [1:04:21<1:57:52,  5.82s/it]
 33%|███▎      | 599/1813 [1:04:27<2:00:33,  5.96s/it]
 33%|███▎      | 600/1813 [1:04:34<2:07:05,  6.29s/it]
                                                      
{'loss': '0.9384', 'grad_norm': '0.7574', 'learning_rate': '8.307e-05', 'epoch': '0.331', 'num_input_tokens_seen': 3999176, 'train_runtime': '3874', 'train_tokens_per_second': '1032'}

 33%|███▎      | 600/1813 [1:04:34<2:07:05,  6.29s/it]
***** Running Evaluation *****
  Num examples = 1000
  Batch size = 1


  0%|          | 0/1000 [00:00<?, ?it/s]

  0%|          | 3/1000 [00:00<01:03, 15.74it/s]

  0%|          | 5/1000 [00:00<02:17,  7.24it/s]

  1%|          | 7/1000 [00:00<01:59,  8.34it/s]

  1%|          | 9/1000 [00:01<02:37,  6.29it/s]

  1%|          | 11/1000 [00:01<02:05,  7.88it/s]

  1%|▏         | 13/1000 [00:01<02:23,  6.88it/s]

  1%|▏         | 14/1000 [00:01<02:26,  6.74it/s]

  2%|▏         | 15/1000 [00:02<02:46,  5.92it/s]

  2%|▏         | 16/1000 [00:02<02:52,  5.69it/s]

  2%|▏         | 18/1000 [00:02<02:43,  6.02it/s]

  2%|▏         | 19/1000 [00:02<03:11,  5.13it/s]

  2%|▏         | 20/1000 [00:03<03:33,  4.59it/s]

  2%|▏         | 22/1000 [00:03<02:36,  6.24it/s]

  2%|▏         | 23/1000 [00:03<02:54,  5.58it/s]

  2%|▎         | 25/1000 [00:03<02:12,  7.34it/s]

  3%|▎         | 26/1000 [00:04<02:35,  6.25it/s]

  3%|▎         | 28/1000 [00:04<02:42,  5.99it/s]

  3%|▎         | 29/1000 [00:04<02:32,  6.36it/s]

  3%|▎         | 30/1000 [00:04<02:42,  5.96it/s]

  3%|▎         | 31/1000 [00:04<03:01,  5.34it/s]

  3%|▎         | 32/1000 [00:05<02:41,  5.99it/s]

  3%|▎         | 33/1000 [00:05<02:47,  5.76it/s]

  4%|▎         | 35/1000 [00:05<02:05,  7.67it/s]

  4%|▎         | 37/1000 [00:05<01:45,  9.10it/s]

  4%|▍         | 39/1000 [00:05<02:06,  7.58it/s]

  4%|▍         | 40/1000 [00:06<02:03,  7.75it/s]

  4%|▍         | 42/1000 [00:06<01:45,  9.11it/s]

  4%|▍         | 44/1000 [00:06<01:32, 10.33it/s]

  5%|▍         | 46/1000 [00:06<01:45,  9.05it/s]

  5%|▍         | 47/1000 [00:06<02:09,  7.36it/s]

  5%|▍         | 49/1000 [00:06<01:48,  8.75it/s]

  5%|▌         | 51/1000 [00:07<01:35,  9.91it/s]

  5%|▌         | 53/1000 [00:07<01:26, 10.94it/s]

  6%|▌         | 55/1000 [00:07<01:27, 10.75it/s]

  6%|▌         | 57/1000 [00:07<01:41,  9.30it/s]

  6%|▌         | 59/1000 [00:08<01:54,  8.19it/s]

  6%|▌         | 61/1000 [00:08<01:40,  9.33it/s]

  6%|▋         | 63/1000 [00:08<01:36,  9.75it/s]

  6%|▋         | 65/1000 [00:08<01:51,  8.37it/s]

  7%|▋         | 67/1000 [00:09<02:03,  7.57it/s]

  7%|▋         | 69/1000 [00:09<01:52,  8.25it/s]

  7%|▋         | 70/1000 [00:09<02:13,  6.99it/s]

  7%|▋         | 72/1000 [00:09<02:18,  6.71it/s]

  7%|▋         | 74/1000 [00:09<01:54,  8.11it/s]

  8%|▊         | 75/1000 [00:10<02:14,  6.85it/s]

  8%|▊         | 76/1000 [00:10<02:18,  6.67it/s]

  8%|▊         | 78/1000 [00:10<02:25,  6.33it/s]

  8%|▊         | 80/1000 [00:10<01:57,  7.86it/s]

  8%|▊         | 82/1000 [00:10<01:39,  9.19it/s]

  8%|▊         | 84/1000 [00:11<01:54,  8.01it/s]

  8%|▊         | 85/1000 [00:11<02:14,  6.79it/s]

  9%|▊         | 86/1000 [00:11<02:33,  5.95it/s]

  9%|▊         | 87/1000 [00:12<02:49,  5.39it/s]

  9%|▉         | 89/1000 [00:12<02:10,  7.01it/s]

  9%|▉         | 90/1000 [00:12<02:05,  7.25it/s]

  9%|▉         | 91/1000 [00:12<02:29,  6.08it/s]

  9%|▉         | 92/1000 [00:12<02:27,  6.17it/s]

  9%|▉         | 93/1000 [00:12<02:36,  5.78it/s]

 10%|▉         | 95/1000 [00:13<02:44,  5.52it/s]

 10%|▉         | 97/1000 [00:13<02:13,  6.79it/s]

 10%|▉         | 99/1000 [00:13<01:47,  8.37it/s]

 10%|█         | 101/1000 [00:13<01:33,  9.63it/s]

 10%|█         | 103/1000 [00:14<01:55,  7.75it/s]

 10%|█         | 104/1000 [00:14<01:54,  7.82it/s]

 11%|█         | 106/1000 [00:14<01:36,  9.28it/s]

 11%|█         | 108/1000 [00:14<01:25, 10.40it/s]

 11%|█         | 110/1000 [00:14<01:19, 11.15it/s]

 11%|█         | 112/1000 [00:14<01:14, 11.98it/s]

 11%|█▏        | 114/1000 [00:14<01:10, 12.48it/s]

 12%|█▏        | 116/1000 [00:15<01:09, 12.78it/s]

 12%|█▏        | 118/1000 [00:15<01:06, 13.23it/s]

 12%|█▏        | 120/1000 [00:15<02:07,  6.91it/s]

 12%|█▏        | 122/1000 [00:16<01:48,  8.09it/s]

 12%|█▏        | 124/1000 [00:16<01:57,  7.44it/s]

 12%|█▎        | 125/1000 [00:16<02:32,  5.72it/s]

 13%|█▎        | 126/1000 [00:16<02:22,  6.14it/s]

 13%|█▎        | 127/1000 [00:17<02:30,  5.80it/s]

 13%|█▎        | 128/1000 [00:17<02:44,  5.29it/s]

 13%|█▎        | 130/1000 [00:17<02:02,  7.10it/s]

 13%|█▎        | 132/1000 [00:17<01:39,  8.71it/s]

 13%|█▎        | 134/1000 [00:17<01:25, 10.15it/s]

 14%|█▎        | 136/1000 [00:17<01:29,  9.65it/s]

 14%|█▍        | 138/1000 [00:18<01:27,  9.89it/s]

 14%|█▍        | 140/1000 [00:18<01:26,  9.95it/s]

 14%|█▍        | 142/1000 [00:18<01:35,  9.02it/s]

 14%|█▍        | 143/1000 [00:18<01:36,  8.89it/s]

 14%|█▍        | 145/1000 [00:18<01:24, 10.07it/s]

 15%|█▍        | 147/1000 [00:19<01:41,  8.44it/s]

 15%|█▍        | 148/1000 [00:19<01:40,  8.49it/s]

 15%|█▌        | 150/1000 [00:19<01:25,  9.91it/s]

 15%|█▌        | 152/1000 [00:19<01:16, 11.02it/s]

 15%|█▌        | 154/1000 [00:19<01:21, 10.38it/s]

 16%|█▌        | 156/1000 [00:20<02:07,  6.64it/s]

 16%|█▌        | 158/1000 [00:20<01:45,  7.96it/s]

 16%|█▌        | 160/1000 [00:20<01:37,  8.60it/s]

 16%|█▌        | 162/1000 [00:20<01:47,  7.81it/s]

 16%|█▋        | 163/1000 [00:21<01:51,  7.50it/s]

 16%|█▋        | 164/1000 [00:21<02:10,  6.40it/s]

 16%|█▋        | 165/1000 [00:21<02:27,  5.67it/s]

 17%|█▋        | 166/1000 [00:21<02:41,  5.18it/s]

 17%|█▋        | 167/1000 [00:21<02:24,  5.77it/s]

 17%|█▋        | 169/1000 [00:22<01:46,  7.83it/s]

 17%|█▋        | 171/1000 [00:22<01:56,  7.14it/s]

 17%|█▋        | 172/1000 [00:22<02:14,  6.14it/s]

 17%|█▋        | 173/1000 [00:22<02:13,  6.22it/s]

 17%|█▋        | 174/1000 [00:22<02:02,  6.74it/s]

 18%|█▊        | 176/1000 [00:23<01:37,  8.45it/s]

 18%|█▊        | 177/1000 [00:23<02:00,  6.80it/s]

 18%|█▊        | 179/1000 [00:23<01:35,  8.58it/s]

 18%|█▊        | 180/1000 [00:23<01:36,  8.51it/s]

 18%|█▊        | 181/1000 [00:23<02:01,  6.75it/s]

 18%|█▊        | 182/1000 [00:24<02:23,  5.72it/s]

 18%|█▊        | 183/1000 [00:24<02:21,  5.79it/s]

 18%|█▊        | 185/1000 [00:24<01:45,  7.74it/s]

 19%|█▊        | 186/1000 [00:24<01:43,  7.89it/s]

 19%|█▊        | 187/1000 [00:24<02:07,  6.37it/s]

 19%|█▉        | 189/1000 [00:24<01:39,  8.11it/s]

 19%|█▉        | 190/1000 [00:25<02:02,  6.62it/s]

 19%|█▉        | 192/1000 [00:25<02:04,  6.48it/s]

 19%|█▉        | 194/1000 [00:25<02:06,  6.37it/s]

 20%|█▉        | 196/1000 [00:25<01:43,  7.75it/s]

 20%|█▉        | 198/1000 [00:26<01:27,  9.19it/s]

 20%|██        | 200/1000 [00:26<01:15, 10.65it/s]

 20%|██        | 202/1000 [00:26<01:30,  8.78it/s]

 20%|██        | 204/1000 [00:26<01:32,  8.63it/s]

 21%|██        | 206/1000 [00:26<01:19,  9.93it/s]

 21%|██        | 208/1000 [00:27<01:32,  8.52it/s]

 21%|██        | 210/1000 [00:27<01:33,  8.48it/s]

 21%|██        | 212/1000 [00:27<01:21,  9.68it/s]

 21%|██▏       | 214/1000 [00:27<01:30,  8.73it/s]

 22%|██▏       | 216/1000 [00:28<01:25,  9.14it/s]

 22%|██▏       | 217/1000 [00:28<01:44,  7.50it/s]

 22%|██▏       | 219/1000 [00:28<01:28,  8.78it/s]

 22%|██▏       | 220/1000 [00:28<02:03,  6.30it/s]

 22%|██▏       | 221/1000 [00:28<02:03,  6.29it/s]

 22%|██▏       | 223/1000 [00:29<02:20,  5.55it/s]

 22%|██▏       | 224/1000 [00:29<02:08,  6.04it/s]

 22%|██▎       | 225/1000 [00:29<02:07,  6.09it/s]

 23%|██▎       | 226/1000 [00:29<02:23,  5.41it/s]

 23%|██▎       | 228/1000 [00:30<01:53,  6.81it/s]

 23%|██▎       | 229/1000 [00:30<02:10,  5.89it/s]

 23%|██▎       | 230/1000 [00:30<02:01,  6.36it/s]

 23%|██▎       | 232/1000 [00:30<01:35,  8.02it/s]

 23%|██▎       | 233/1000 [00:30<01:33,  8.19it/s]

 24%|██▎       | 235/1000 [00:30<01:17,  9.92it/s]

 24%|██▎       | 237/1000 [00:31<01:20,  9.43it/s]

 24%|██▍       | 239/1000 [00:31<01:25,  8.95it/s]

 24%|██▍       | 241/1000 [00:31<01:30,  8.35it/s]

 24%|██▍       | 242/1000 [00:31<02:06,  6.00it/s]

 24%|██▍       | 243/1000 [00:32<02:18,  5.45it/s]

 24%|██▍       | 245/1000 [00:32<01:53,  6.64it/s]

 25%|██▍       | 247/1000 [00:32<01:31,  8.24it/s]

 25%|██▍       | 248/1000 [00:32<01:49,  6.85it/s]

 25%|██▍       | 249/1000 [00:33<02:06,  5.95it/s]

 25%|██▌       | 250/1000 [00:33<02:07,  5.86it/s]

 25%|██▌       | 252/1000 [00:33<02:04,  6.03it/s]

 25%|██▌       | 253/1000 [00:33<02:10,  5.74it/s]

 26%|██▌       | 255/1000 [00:33<01:42,  7.27it/s]

 26%|██▌       | 256/1000 [00:33<01:37,  7.62it/s]

 26%|██▌       | 258/1000 [00:34<01:26,  8.59it/s]

 26%|██▌       | 260/1000 [00:34<01:37,  7.62it/s]

 26%|██▌       | 261/1000 [00:34<01:54,  6.47it/s]

 26%|██▌       | 262/1000 [00:34<01:55,  6.39it/s]

 26%|██▋       | 264/1000 [00:35<01:56,  6.31it/s]

 26%|██▋       | 265/1000 [00:35<01:51,  6.58it/s]

 27%|██▋       | 266/1000 [00:35<01:46,  6.90it/s]

 27%|██▋       | 268/1000 [00:35<01:37,  7.51it/s]

 27%|██▋       | 270/1000 [00:36<01:44,  6.99it/s]

 27%|██▋       | 271/1000 [00:36<02:14,  5.42it/s]

 27%|██▋       | 273/1000 [00:36<02:07,  5.69it/s]

 28%|██▊       | 275/1000 [00:36<01:48,  6.68it/s]

 28%|██▊       | 277/1000 [00:37<01:30,  8.03it/s]

 28%|██▊       | 278/1000 [00:37<01:46,  6.80it/s]

 28%|██▊       | 280/1000 [00:37<01:48,  6.62it/s]

 28%|██▊       | 282/1000 [00:37<01:29,  8.01it/s]

 28%|██▊       | 283/1000 [00:38<02:02,  5.84it/s]

 28%|██▊       | 284/1000 [00:38<02:05,  5.70it/s]

 29%|██▊       | 286/1000 [00:38<01:36,  7.43it/s]

 29%|██▉       | 288/1000 [00:38<01:21,  8.72it/s]

 29%|██▉       | 290/1000 [00:38<01:31,  7.76it/s]

 29%|██▉       | 291/1000 [00:39<01:41,  6.99it/s]

 29%|██▉       | 292/1000 [00:39<01:56,  6.06it/s]

 29%|██▉       | 294/1000 [00:39<01:38,  7.18it/s]

 30%|██▉       | 296/1000 [00:39<01:42,  6.88it/s]

 30%|██▉       | 298/1000 [00:40<01:25,  8.18it/s]

 30%|██▉       | 299/1000 [00:40<01:48,  6.46it/s]

 30%|███       | 300/1000 [00:40<01:42,  6.85it/s]

 30%|███       | 301/1000 [00:40<01:38,  7.13it/s]

 30%|███       | 303/1000 [00:40<01:19,  8.77it/s]

 30%|███       | 304/1000 [00:40<01:26,  8.08it/s]

 30%|███       | 305/1000 [00:40<01:25,  8.13it/s]

 31%|███       | 306/1000 [00:41<01:40,  6.93it/s]

 31%|███       | 307/1000 [00:41<01:42,  6.77it/s]

 31%|███       | 309/1000 [00:41<01:18,  8.78it/s]

 31%|███       | 311/1000 [00:41<01:07, 10.19it/s]

 31%|███▏      | 313/1000 [00:41<01:01, 11.24it/s]

 32%|███▏      | 315/1000 [00:41<01:07, 10.22it/s]

 32%|███▏      | 317/1000 [00:42<01:11,  9.56it/s]

 32%|███▏      | 319/1000 [00:42<01:34,  7.23it/s]

 32%|███▏      | 321/1000 [00:42<01:38,  6.89it/s]

 32%|███▏      | 322/1000 [00:43<01:45,  6.43it/s]

 32%|███▏      | 324/1000 [00:43<01:27,  7.75it/s]

 32%|███▎      | 325/1000 [00:43<01:58,  5.70it/s]

 33%|███▎      | 327/1000 [00:43<01:30,  7.40it/s]

 33%|███▎      | 328/1000 [00:43<01:33,  7.16it/s]

 33%|███▎      | 330/1000 [00:44<01:38,  6.78it/s]

 33%|███▎      | 332/1000 [00:44<01:41,  6.57it/s]

 33%|███▎      | 333/1000 [00:44<01:36,  6.95it/s]

 33%|███▎      | 334/1000 [00:44<01:44,  6.37it/s]

 34%|███▎      | 336/1000 [00:45<01:22,  8.04it/s]

 34%|███▍      | 338/1000 [00:45<01:15,  8.82it/s]

 34%|███▍      | 340/1000 [00:45<01:05, 10.02it/s]

 34%|███▍      | 342/1000 [00:45<01:00, 10.86it/s]

 34%|███▍      | 344/1000 [00:46<01:26,  7.60it/s]

 34%|███▍      | 345/1000 [00:46<01:24,  7.71it/s]

 35%|███▍      | 346/1000 [00:46<01:30,  7.21it/s]

 35%|███▍      | 347/1000 [00:46<01:28,  7.40it/s]

 35%|███▍      | 349/1000 [00:46<01:34,  6.90it/s]

 35%|███▌      | 350/1000 [00:46<01:49,  5.94it/s]

 35%|███▌      | 352/1000 [00:47<01:24,  7.63it/s]

 35%|███▌      | 354/1000 [00:47<01:25,  7.55it/s]

 36%|███▌      | 355/1000 [00:47<01:27,  7.36it/s]

 36%|███▌      | 357/1000 [00:47<01:11,  8.96it/s]

 36%|███▌      | 359/1000 [00:47<01:00, 10.58it/s]

 36%|███▌      | 361/1000 [00:48<01:07,  9.42it/s]

 36%|███▋      | 363/1000 [00:48<01:28,  7.19it/s]

 36%|███▋      | 364/1000 [00:48<01:41,  6.27it/s]

 36%|███▋      | 365/1000 [00:49<02:09,  4.92it/s]

 37%|███▋      | 367/1000 [00:49<01:58,  5.36it/s]

 37%|███▋      | 368/1000 [00:49<02:05,  5.02it/s]

 37%|███▋      | 369/1000 [00:49<01:52,  5.60it/s]

 37%|███▋      | 371/1000 [00:49<01:23,  7.55it/s]

 37%|███▋      | 372/1000 [00:50<01:21,  7.73it/s]

 37%|███▋      | 374/1000 [00:50<01:17,  8.09it/s]

 38%|███▊      | 375/1000 [00:50<01:40,  6.21it/s]

 38%|███▊      | 376/1000 [00:50<01:53,  5.48it/s]

 38%|███▊      | 378/1000 [00:50<01:29,  6.91it/s]

 38%|███▊      | 380/1000 [00:51<01:10,  8.76it/s]

 38%|███▊      | 382/1000 [00:51<01:18,  7.89it/s]

 38%|███▊      | 384/1000 [00:51<01:07,  9.17it/s]

 39%|███▊      | 386/1000 [00:51<01:07,  9.16it/s]

 39%|███▉      | 388/1000 [00:52<01:25,  7.13it/s]

 39%|███▉      | 390/1000 [00:52<01:19,  7.63it/s]

 39%|███▉      | 391/1000 [00:52<01:22,  7.35it/s]

 39%|███▉      | 393/1000 [00:52<01:09,  8.77it/s]

 40%|███▉      | 395/1000 [00:53<01:21,  7.46it/s]

 40%|███▉      | 397/1000 [00:53<01:08,  8.75it/s]

 40%|███▉      | 399/1000 [00:53<01:36,  6.22it/s]

 40%|████      | 400/1000 [00:53<01:45,  5.68it/s]

 40%|████      | 402/1000 [00:54<01:41,  5.92it/s]

 40%|████      | 404/1000 [00:54<01:22,  7.23it/s]

 41%|████      | 406/1000 [00:54<01:10,  8.48it/s]

 41%|████      | 408/1000 [00:55<01:32,  6.39it/s]

 41%|████      | 410/1000 [00:55<01:31,  6.44it/s]

 41%|████      | 411/1000 [00:55<01:41,  5.83it/s]

 41%|████      | 412/1000 [00:55<01:49,  5.36it/s]

 41%|████▏     | 414/1000 [00:56<01:23,  7.06it/s]

 42%|████▏     | 416/1000 [00:56<01:25,  6.81it/s]

 42%|████▏     | 418/1000 [00:56<01:10,  8.25it/s]

 42%|████▏     | 420/1000 [00:56<01:08,  8.44it/s]

 42%|████▏     | 421/1000 [00:56<01:17,  7.50it/s]

 42%|████▏     | 423/1000 [00:57<01:26,  6.69it/s]

 42%|████▏     | 424/1000 [00:57<01:37,  5.92it/s]

 42%|████▎     | 425/1000 [00:57<01:30,  6.36it/s]

 43%|████▎     | 427/1000 [00:57<01:12,  7.95it/s]

 43%|████▎     | 428/1000 [00:57<01:15,  7.54it/s]

 43%|████▎     | 429/1000 [00:58<01:12,  7.84it/s]

 43%|████▎     | 431/1000 [00:58<00:59,  9.56it/s]

 43%|████▎     | 433/1000 [00:58<00:51, 11.03it/s]

 44%|████▎     | 435/1000 [00:58<00:48, 11.77it/s]

 44%|████▎     | 437/1000 [00:58<00:53, 10.50it/s]

 44%|████▍     | 439/1000 [00:59<01:09,  8.08it/s]

 44%|████▍     | 441/1000 [00:59<01:00,  9.29it/s]

 44%|████▍     | 443/1000 [00:59<01:10,  7.93it/s]

 44%|████▍     | 444/1000 [00:59<01:17,  7.15it/s]

 45%|████▍     | 446/1000 [00:59<01:04,  8.63it/s]

 45%|████▍     | 448/1000 [01:00<01:16,  7.26it/s]

 45%|████▌     | 450/1000 [01:00<01:19,  6.88it/s]

 45%|████▌     | 451/1000 [01:00<01:29,  6.10it/s]

 45%|████▌     | 452/1000 [01:01<01:39,  5.52it/s]

 45%|████▌     | 454/1000 [01:01<01:16,  7.12it/s]

 46%|████▌     | 456/1000 [01:01<01:04,  8.44it/s]

 46%|████▌     | 457/1000 [01:01<01:09,  7.76it/s]

 46%|████▌     | 459/1000 [01:01<00:58,  9.21it/s]

 46%|████▌     | 461/1000 [01:01<00:50, 10.78it/s]

 46%|████▋     | 463/1000 [01:02<01:10,  7.61it/s]

 46%|████▋     | 465/1000 [01:02<01:19,  6.73it/s]

 47%|████▋     | 466/1000 [01:02<01:29,  6.00it/s]

 47%|████▋     | 467/1000 [01:03<01:50,  4.82it/s]

 47%|████▋     | 469/1000 [01:03<01:24,  6.30it/s]

 47%|████▋     | 471/1000 [01:03<01:07,  7.84it/s]

 47%|████▋     | 472/1000 [01:03<01:04,  8.19it/s]

 47%|████▋     | 473/1000 [01:03<01:11,  7.36it/s]

 47%|████▋     | 474/1000 [01:04<01:25,  6.17it/s]

 48%|████▊     | 476/1000 [01:04<01:24,  6.18it/s]

 48%|████▊     | 477/1000 [01:04<01:38,  5.29it/s]

 48%|████▊     | 479/1000 [01:04<01:13,  7.09it/s]

 48%|████▊     | 480/1000 [01:04<01:19,  6.51it/s]

 48%|████▊     | 482/1000 [01:05<01:04,  8.05it/s]

 48%|████▊     | 484/1000 [01:05<01:10,  7.29it/s]

 48%|████▊     | 485/1000 [01:05<01:21,  6.28it/s]

 49%|████▊     | 486/1000 [01:05<01:21,  6.28it/s]

 49%|████▉     | 488/1000 [01:05<01:04,  8.00it/s]

 49%|████▉     | 489/1000 [01:06<01:17,  6.62it/s]

 49%|████▉     | 491/1000 [01:06<01:01,  8.22it/s]

 49%|████▉     | 492/1000 [01:06<01:01,  8.26it/s]

 49%|████▉     | 494/1000 [01:06<00:50,  9.98it/s]

 50%|████▉     | 496/1000 [01:06<00:59,  8.41it/s]

 50%|████▉     | 498/1000 [01:07<00:59,  8.43it/s]

 50%|████▉     | 499/1000 [01:07<01:15,  6.65it/s]

 50%|█████     | 500/1000 [01:07<01:24,  5.92it/s]

 50%|█████     | 502/1000 [01:07<01:06,  7.53it/s]

 50%|█████     | 503/1000 [01:08<01:13,  6.80it/s]

 50%|█████     | 505/1000 [01:08<01:15,  6.55it/s]

 51%|█████     | 506/1000 [01:08<01:25,  5.80it/s]

 51%|█████     | 508/1000 [01:08<01:06,  7.42it/s]

 51%|█████     | 510/1000 [01:08<00:54,  8.95it/s]

 51%|█████     | 512/1000 [01:09<00:48,  9.96it/s]

 51%|█████▏    | 514/1000 [01:09<01:06,  7.28it/s]

 52%|█████▏    | 515/1000 [01:09<01:04,  7.53it/s]

 52%|█████▏    | 516/1000 [01:09<01:08,  7.10it/s]

 52%|█████▏    | 518/1000 [01:09<00:59,  8.07it/s]

 52%|█████▏    | 519/1000 [01:10<01:15,  6.38it/s]

 52%|█████▏    | 521/1000 [01:10<01:00,  7.97it/s]

 52%|█████▏    | 522/1000 [01:10<01:11,  6.65it/s]

 52%|█████▏    | 523/1000 [01:10<01:22,  5.79it/s]

 52%|█████▏    | 524/1000 [01:11<01:25,  5.55it/s]

 53%|█████▎    | 526/1000 [01:11<01:12,  6.58it/s]

 53%|█████▎    | 528/1000 [01:11<01:12,  6.53it/s]

 53%|█████▎    | 529/1000 [01:11<01:13,  6.39it/s]

 53%|█████▎    | 531/1000 [01:11<00:57,  8.10it/s]

 53%|█████▎    | 533/1000 [01:12<00:48,  9.66it/s]

 54%|█████▎    | 535/1000 [01:12<01:09,  6.68it/s]

 54%|█████▎    | 536/1000 [01:12<01:13,  6.35it/s]

 54%|█████▎    | 537/1000 [01:12<01:22,  5.64it/s]

 54%|█████▍    | 539/1000 [01:13<01:17,  5.92it/s]

 54%|█████▍    | 540/1000 [01:13<01:20,  5.75it/s]

 54%|█████▍    | 541/1000 [01:13<01:27,  5.26it/s]

 54%|█████▍    | 543/1000 [01:13<01:06,  6.92it/s]

 55%|█████▍    | 545/1000 [01:14<01:04,  7.05it/s]

 55%|█████▍    | 546/1000 [01:14<01:09,  6.49it/s]

 55%|█████▍    | 547/1000 [01:14<01:19,  5.70it/s]

 55%|█████▍    | 549/1000 [01:14<01:16,  5.91it/s]

 55%|█████▌    | 551/1000 [01:15<00:59,  7.51it/s]

 55%|█████▌    | 552/1000 [01:15<01:01,  7.26it/s]

 55%|█████▌    | 553/1000 [01:15<01:12,  6.18it/s]

 55%|█████▌    | 554/1000 [01:15<01:14,  5.95it/s]

 56%|█████▌    | 556/1000 [01:15<00:57,  7.77it/s]

 56%|█████▌    | 557/1000 [01:15<01:03,  7.03it/s]

 56%|█████▌    | 559/1000 [01:16<00:49,  8.86it/s]

 56%|█████▌    | 561/1000 [01:16<00:43, 10.04it/s]

 56%|█████▋    | 563/1000 [01:16<00:52,  8.37it/s]

 56%|█████▋    | 565/1000 [01:16<00:54,  7.98it/s]

 57%|█████▋    | 566/1000 [01:17<01:04,  6.75it/s]

 57%|█████▋    | 568/1000 [01:17<01:05,  6.55it/s]

 57%|█████▋    | 569/1000 [01:17<01:06,  6.45it/s]

 57%|█████▋    | 571/1000 [01:17<01:06,  6.44it/s]

 57%|█████▋    | 572/1000 [01:18<01:07,  6.31it/s]

 57%|█████▋    | 574/1000 [01:18<01:07,  6.33it/s]

 58%|█████▊    | 576/1000 [01:18<00:54,  7.81it/s]

 58%|█████▊    | 577/1000 [01:18<01:13,  5.72it/s]

 58%|█████▊    | 578/1000 [01:19<01:20,  5.25it/s]

 58%|█████▊    | 580/1000 [01:19<01:00,  6.97it/s]

 58%|█████▊    | 582/1000 [01:19<00:48,  8.55it/s]

 58%|█████▊    | 584/1000 [01:19<00:54,  7.57it/s]

 58%|█████▊    | 585/1000 [01:19<01:00,  6.91it/s]

 59%|█████▊    | 587/1000 [01:20<00:57,  7.15it/s]

 59%|█████▉    | 589/1000 [01:20<00:48,  8.53it/s]

 59%|█████▉    | 590/1000 [01:20<01:00,  6.75it/s]

 59%|█████▉    | 592/1000 [01:20<00:49,  8.18it/s]

 59%|█████▉    | 593/1000 [01:20<00:59,  6.80it/s]

 60%|█████▉    | 595/1000 [01:21<00:48,  8.40it/s]

 60%|█████▉    | 596/1000 [01:21<00:58,  6.87it/s]

 60%|█████▉    | 597/1000 [01:21<01:00,  6.66it/s]

 60%|█████▉    | 599/1000 [01:21<01:02,  6.46it/s]

 60%|██████    | 601/1000 [01:22<01:02,  6.39it/s]

 60%|██████    | 602/1000 [01:22<00:59,  6.70it/s]

 60%|██████    | 604/1000 [01:22<01:10,  5.58it/s]

 61%|██████    | 606/1000 [01:22<00:56,  7.00it/s]

 61%|██████    | 608/1000 [01:23<00:50,  7.77it/s]

 61%|██████    | 610/1000 [01:23<00:46,  8.39it/s]

 61%|██████    | 612/1000 [01:23<00:40,  9.64it/s]

 61%|██████▏   | 614/1000 [01:23<00:36, 10.72it/s]

 62%|██████▏   | 616/1000 [01:24<00:50,  7.59it/s]

 62%|██████▏   | 617/1000 [01:24<00:49,  7.73it/s]

 62%|██████▏   | 619/1000 [01:24<00:42,  9.07it/s]

 62%|██████▏   | 621/1000 [01:24<00:47,  8.00it/s]

 62%|██████▏   | 623/1000 [01:24<00:46,  8.18it/s]

 62%|██████▎   | 625/1000 [01:25<00:50,  7.45it/s]

 63%|██████▎   | 627/1000 [01:25<00:43,  8.63it/s]

 63%|██████▎   | 628/1000 [01:25<00:51,  7.17it/s]

 63%|██████▎   | 629/1000 [01:25<00:59,  6.21it/s]

 63%|██████▎   | 631/1000 [01:25<00:47,  7.84it/s]

 63%|██████▎   | 633/1000 [01:26<00:38,  9.42it/s]

 64%|██████▎   | 635/1000 [01:26<00:54,  6.72it/s]

 64%|██████▎   | 636/1000 [01:26<00:51,  7.07it/s]

 64%|██████▍   | 638/1000 [01:26<00:45,  7.94it/s]

 64%|██████▍   | 640/1000 [01:26<00:39,  9.17it/s]

 64%|██████▍   | 642/1000 [01:27<00:44,  7.96it/s]

 64%|██████▍   | 643/1000 [01:27<00:46,  7.60it/s]

 64%|██████▍   | 645/1000 [01:27<00:49,  7.11it/s]

 65%|██████▍   | 647/1000 [01:28<00:46,  7.58it/s]

 65%|██████▍   | 648/1000 [01:28<00:53,  6.52it/s]

 65%|██████▌   | 650/1000 [01:28<00:53,  6.54it/s]

 65%|██████▌   | 652/1000 [01:28<00:55,  6.31it/s]

 65%|██████▌   | 654/1000 [01:29<00:45,  7.69it/s]

 66%|██████▌   | 656/1000 [01:29<00:38,  8.90it/s]

 66%|██████▌   | 658/1000 [01:29<00:42,  8.08it/s]

 66%|██████▌   | 659/1000 [01:29<00:56,  5.99it/s]

 66%|██████▌   | 661/1000 [01:29<00:44,  7.56it/s]

 66%|██████▌   | 662/1000 [01:30<00:52,  6.47it/s]

 66%|██████▋   | 664/1000 [01:30<00:58,  5.77it/s]

 66%|██████▋   | 665/1000 [01:30<01:02,  5.33it/s]

 67%|██████▋   | 667/1000 [01:31<00:59,  5.61it/s]

 67%|██████▋   | 668/1000 [01:31<01:03,  5.20it/s]

 67%|██████▋   | 669/1000 [01:31<00:58,  5.70it/s]

 67%|██████▋   | 671/1000 [01:31<00:55,  5.88it/s]

 67%|██████▋   | 673/1000 [01:32<00:49,  6.62it/s]

 68%|██████▊   | 675/1000 [01:32<00:44,  7.25it/s]

 68%|██████▊   | 677/1000 [01:32<00:37,  8.64it/s]

 68%|██████▊   | 679/1000 [01:32<00:33,  9.68it/s]

 68%|██████▊   | 681/1000 [01:32<00:29, 10.95it/s]

 68%|██████▊   | 683/1000 [01:33<00:36,  8.75it/s]

 68%|██████▊   | 685/1000 [01:33<00:32,  9.74it/s]

 69%|██████▊   | 687/1000 [01:33<00:45,  6.81it/s]

 69%|██████▉   | 688/1000 [01:33<00:43,  7.11it/s]

 69%|██████▉   | 690/1000 [01:34<00:45,  6.77it/s]

 69%|██████▉   | 692/1000 [01:34<00:39,  7.80it/s]

 69%|██████▉   | 694/1000 [01:34<00:42,  7.24it/s]

 70%|██████▉   | 695/1000 [01:34<00:41,  7.40it/s]

 70%|██████▉   | 696/1000 [01:35<00:48,  6.32it/s]

 70%|██████▉   | 698/1000 [01:35<00:43,  6.93it/s]

 70%|██████▉   | 699/1000 [01:35<00:49,  6.05it/s]

 70%|███████   | 701/1000 [01:35<00:39,  7.60it/s]

 70%|███████   | 702/1000 [01:36<00:53,  5.61it/s]

 70%|███████   | 704/1000 [01:36<00:41,  7.22it/s]

 70%|███████   | 705/1000 [01:36<00:54,  5.42it/s]

 71%|███████   | 707/1000 [01:36<00:41,  7.03it/s]

 71%|███████   | 709/1000 [01:36<00:38,  7.62it/s]

 71%|███████   | 710/1000 [01:37<00:44,  6.50it/s]

 71%|███████   | 712/1000 [01:37<00:37,  7.72it/s]

 71%|███████▏  | 713/1000 [01:37<00:36,  7.87it/s]

 72%|███████▏  | 715/1000 [01:37<00:30,  9.38it/s]

 72%|███████▏  | 717/1000 [01:37<00:35,  8.05it/s]

 72%|███████▏  | 718/1000 [01:38<00:41,  6.80it/s]

 72%|███████▏  | 719/1000 [01:38<00:47,  5.93it/s]

 72%|███████▏  | 720/1000 [01:38<00:43,  6.47it/s]

 72%|███████▏  | 722/1000 [01:38<00:34,  8.16it/s]

 72%|███████▏  | 723/1000 [01:38<00:33,  8.22it/s]

 72%|███████▏  | 724/1000 [01:38<00:33,  8.23it/s]

 72%|███████▎  | 725/1000 [01:39<00:33,  8.30it/s]

 73%|███████▎  | 727/1000 [01:39<00:27, 10.10it/s]

 73%|███████▎  | 729/1000 [01:39<00:23, 11.57it/s]

 73%|███████▎  | 731/1000 [01:39<00:32,  8.31it/s]

 73%|███████▎  | 733/1000 [01:39<00:28,  9.51it/s]

 74%|███████▎  | 735/1000 [01:39<00:26,  9.86it/s]

 74%|███████▎  | 737/1000 [01:40<00:27,  9.51it/s]

 74%|███████▍  | 739/1000 [01:40<00:26,  9.76it/s]

 74%|███████▍  | 741/1000 [01:40<00:31,  8.30it/s]

 74%|███████▍  | 743/1000 [01:40<00:30,  8.36it/s]

 74%|███████▍  | 745/1000 [01:41<00:26,  9.60it/s]

 75%|███████▍  | 747/1000 [01:41<00:24, 10.44it/s]

 75%|███████▍  | 749/1000 [01:41<00:29,  8.64it/s]

 75%|███████▌  | 750/1000 [01:41<00:32,  7.68it/s]

 75%|███████▌  | 751/1000 [01:42<00:40,  6.16it/s]

 75%|███████▌  | 753/1000 [01:42<00:34,  7.23it/s]

 75%|███████▌  | 754/1000 [01:42<00:39,  6.22it/s]

 76%|███████▌  | 756/1000 [01:42<00:38,  6.40it/s]

 76%|███████▌  | 758/1000 [01:42<00:31,  7.60it/s]

 76%|███████▌  | 759/1000 [01:43<00:32,  7.32it/s]

 76%|███████▌  | 761/1000 [01:43<00:27,  8.71it/s]

 76%|███████▋  | 763/1000 [01:43<00:31,  7.64it/s]

 76%|███████▋  | 764/1000 [01:43<00:35,  6.60it/s]

 77%|███████▋  | 766/1000 [01:44<00:36,  6.47it/s]

 77%|███████▋  | 768/1000 [01:44<00:29,  7.79it/s]

 77%|███████▋  | 769/1000 [01:44<00:34,  6.62it/s]

 77%|███████▋  | 770/1000 [01:44<00:35,  6.55it/s]

 77%|███████▋  | 772/1000 [01:44<00:28,  8.11it/s]

 77%|███████▋  | 773/1000 [01:45<00:35,  6.38it/s]

 77%|███████▋  | 774/1000 [01:45<00:33,  6.78it/s]

 78%|███████▊  | 776/1000 [01:45<00:28,  7.88it/s]

 78%|███████▊  | 778/1000 [01:45<00:23,  9.59it/s]

 78%|███████▊  | 780/1000 [01:46<00:31,  6.94it/s]

 78%|███████▊  | 782/1000 [01:46<00:26,  8.37it/s]

 78%|███████▊  | 784/1000 [01:46<00:30,  7.15it/s]

 79%|███████▊  | 786/1000 [01:46<00:28,  7.53it/s]

 79%|███████▉  | 788/1000 [01:46<00:25,  8.36it/s]

 79%|███████▉  | 790/1000 [01:47<00:23,  8.99it/s]

 79%|███████▉  | 791/1000 [01:47<00:25,  8.22it/s]

 79%|███████▉  | 792/1000 [01:47<00:26,  7.73it/s]

 79%|███████▉  | 793/1000 [01:47<00:25,  7.97it/s]

 80%|███████▉  | 795/1000 [01:47<00:28,  7.18it/s]

 80%|███████▉  | 797/1000 [01:48<00:29,  6.86it/s]

 80%|███████▉  | 798/1000 [01:48<00:33,  6.01it/s]

 80%|████████  | 800/1000 [01:48<00:29,  6.71it/s]

 80%|████████  | 802/1000 [01:48<00:25,  7.63it/s]

 80%|████████  | 804/1000 [01:49<00:25,  7.83it/s]

 81%|████████  | 806/1000 [01:49<00:21,  9.17it/s]

 81%|████████  | 807/1000 [01:49<00:21,  8.96it/s]

 81%|████████  | 809/1000 [01:49<00:18, 10.20it/s]

 81%|████████  | 811/1000 [01:49<00:16, 11.21it/s]

 81%|████████▏ | 813/1000 [01:50<00:20,  9.03it/s]

 82%|████████▏ | 815/1000 [01:50<00:19,  9.25it/s]

 82%|████████▏ | 817/1000 [01:50<00:22,  8.11it/s]

 82%|████████▏ | 819/1000 [01:50<00:19,  9.17it/s]

 82%|████████▏ | 821/1000 [01:50<00:22,  8.03it/s]

 82%|████████▏ | 823/1000 [01:51<00:22,  7.81it/s]

 82%|████████▏ | 824/1000 [01:51<00:26,  6.75it/s]

 82%|████████▎ | 825/1000 [01:51<00:25,  6.99it/s]

 83%|████████▎ | 826/1000 [01:51<00:30,  5.79it/s]

 83%|████████▎ | 828/1000 [01:52<00:32,  5.23it/s]

 83%|████████▎ | 829/1000 [01:52<00:29,  5.73it/s]

 83%|████████▎ | 831/1000 [01:52<00:24,  7.00it/s]

 83%|████████▎ | 832/1000 [01:52<00:29,  5.74it/s]

 83%|████████▎ | 833/1000 [01:53<00:26,  6.23it/s]

 83%|████████▎ | 834/1000 [01:53<00:27,  6.02it/s]

 84%|████████▎ | 835/1000 [01:53<00:25,  6.54it/s]

 84%|████████▎ | 836/1000 [01:53<00:26,  6.11it/s]

 84%|████████▍ | 838/1000 [01:53<00:21,  7.44it/s]

 84%|████████▍ | 840/1000 [01:54<00:24,  6.62it/s]

 84%|████████▍ | 842/1000 [01:54<00:19,  8.15it/s]

 84%|████████▍ | 844/1000 [01:54<00:24,  6.41it/s]

 84%|████████▍ | 845/1000 [01:54<00:26,  5.77it/s]

 85%|████████▍ | 847/1000 [01:55<00:24,  6.25it/s]

 85%|████████▍ | 849/1000 [01:55<00:20,  7.54it/s]

 85%|████████▌ | 850/1000 [01:55<00:23,  6.48it/s]

 85%|████████▌ | 851/1000 [01:55<00:21,  6.86it/s]

 85%|████████▌ | 853/1000 [01:55<00:17,  8.46it/s]

 86%|████████▌ | 855/1000 [01:55<00:14, 10.03it/s]

 86%|████████▌ | 857/1000 [01:56<00:14, 10.19it/s]

 86%|████████▌ | 859/1000 [01:56<00:16,  8.52it/s]

 86%|████████▌ | 861/1000 [01:56<00:14,  9.76it/s]

 86%|████████▋ | 863/1000 [01:56<00:12, 10.63it/s]

 86%|████████▋ | 865/1000 [01:56<00:11, 11.70it/s]

 87%|████████▋ | 867/1000 [01:57<00:14,  9.31it/s]

 87%|████████▋ | 869/1000 [01:57<00:12, 10.27it/s]

 87%|████████▋ | 871/1000 [01:57<00:11, 11.29it/s]

 87%|████████▋ | 873/1000 [01:57<00:16,  7.78it/s]

 88%|████████▊ | 875/1000 [01:58<00:16,  7.64it/s]

 88%|████████▊ | 877/1000 [01:58<00:13,  8.88it/s]

 88%|████████▊ | 879/1000 [01:58<00:17,  6.87it/s]

 88%|████████▊ | 881/1000 [01:59<00:15,  7.60it/s]

 88%|████████▊ | 882/1000 [01:59<00:18,  6.54it/s]

 88%|████████▊ | 884/1000 [01:59<00:14,  7.95it/s]

 89%|████████▊ | 886/1000 [01:59<00:12,  9.16it/s]

 89%|████████▉ | 888/1000 [01:59<00:10, 10.35it/s]

 89%|████████▉ | 890/1000 [01:59<00:11,  9.76it/s]

 89%|████████▉ | 892/1000 [02:00<00:10, 10.76it/s]

 89%|████████▉ | 894/1000 [02:00<00:13,  7.60it/s]

 90%|████████▉ | 896/1000 [02:00<00:11,  8.83it/s]

 90%|████████▉ | 898/1000 [02:01<00:15,  6.53it/s]

 90%|█████████ | 900/1000 [02:01<00:13,  7.69it/s]

 90%|█████████ | 902/1000 [02:01<00:12,  7.86it/s]

 90%|█████████ | 904/1000 [02:01<00:10,  9.06it/s]

 91%|█████████ | 906/1000 [02:02<00:13,  7.04it/s]

 91%|█████████ | 908/1000 [02:02<00:11,  8.31it/s]

 91%|█████████ | 910/1000 [02:02<00:11,  7.58it/s]

 91%|█████████ | 912/1000 [02:02<00:10,  8.76it/s]

 91%|█████████▏| 914/1000 [02:03<00:11,  7.38it/s]

 92%|█████████▏| 916/1000 [02:03<00:11,  7.08it/s]

 92%|█████████▏| 917/1000 [02:03<00:11,  7.36it/s]

 92%|█████████▏| 918/1000 [02:03<00:14,  5.60it/s]

 92%|█████████▏| 919/1000 [02:04<00:14,  5.71it/s]

 92%|█████████▏| 921/1000 [02:04<00:14,  5.58it/s]

 92%|█████████▏| 922/1000 [02:04<00:13,  5.93it/s]

 92%|█████████▏| 924/1000 [02:04<00:10,  7.17it/s]

 93%|█████████▎| 926/1000 [02:04<00:08,  8.65it/s]

 93%|█████████▎| 927/1000 [02:05<00:09,  8.10it/s]

 93%|█████████▎| 928/1000 [02:05<00:10,  6.64it/s]

 93%|█████████▎| 930/1000 [02:05<00:10,  6.48it/s]

 93%|█████████▎| 931/1000 [02:05<00:10,  6.82it/s]

 93%|█████████▎| 933/1000 [02:06<00:10,  6.60it/s]

 93%|█████████▎| 934/1000 [02:06<00:10,  6.16it/s]

 94%|█████████▎| 936/1000 [02:06<00:08,  7.30it/s]

 94%|█████████▍| 938/1000 [02:06<00:07,  8.83it/s]

 94%|█████████▍| 939/1000 [02:06<00:07,  8.04it/s]

 94%|█████████▍| 940/1000 [02:06<00:07,  8.13it/s]

 94%|█████████▍| 942/1000 [02:07<00:09,  6.33it/s]

 94%|█████████▍| 944/1000 [02:07<00:07,  7.08it/s]

 95%|█████████▍| 946/1000 [02:07<00:06,  8.40it/s]

 95%|█████████▍| 948/1000 [02:07<00:05,  9.72it/s]

 95%|█████████▌| 950/1000 [02:08<00:05,  8.84it/s]

 95%|█████████▌| 952/1000 [02:08<00:06,  7.40it/s]

 95%|█████████▌| 954/1000 [02:08<00:07,  6.16it/s]

 96%|█████████▌| 956/1000 [02:08<00:05,  7.40it/s]

 96%|█████████▌| 957/1000 [02:09<00:06,  6.40it/s]

 96%|█████████▌| 959/1000 [02:09<00:07,  5.77it/s]

 96%|█████████▌| 961/1000 [02:09<00:05,  6.81it/s]

 96%|█████████▌| 962/1000 [02:10<00:06,  6.05it/s]

 96%|█████████▋| 964/1000 [02:10<00:04,  7.49it/s]

 96%|█████████▋| 965/1000 [02:10<00:05,  6.44it/s]

 97%|█████████▋| 966/1000 [02:10<00:05,  6.32it/s]

 97%|█████████▋| 968/1000 [02:10<00:03,  8.00it/s]

 97%|█████████▋| 970/1000 [02:10<00:03,  9.41it/s]

 97%|█████████▋| 972/1000 [02:11<00:03,  8.01it/s]

 97%|█████████▋| 974/1000 [02:11<00:02,  9.18it/s]

 98%|█████████▊| 976/1000 [02:11<00:02,  9.78it/s]

 98%|█████████▊| 978/1000 [02:11<00:02, 10.77it/s]

 98%|█████████▊| 980/1000 [02:12<00:02,  8.43it/s]

 98%|█████████▊| 981/1000 [02:12<00:02,  7.05it/s]

 98%|█████████▊| 982/1000 [02:12<00:03,  5.43it/s]

 98%|█████████▊| 984/1000 [02:12<00:02,  6.91it/s]

 99%|█████████▊| 986/1000 [02:12<00:01,  8.36it/s]

 99%|█████████▉| 988/1000 [02:13<00:01,  6.73it/s]

 99%|█████████▉| 989/1000 [02:13<00:01,  5.99it/s]

 99%|█████████▉| 991/1000 [02:13<00:01,  6.15it/s]

 99%|█████████▉| 992/1000 [02:14<00:01,  4.98it/s]

 99%|█████████▉| 994/1000 [02:14<00:00,  6.54it/s]

100%|█████████▉| 995/1000 [02:14<00:00,  5.52it/s]

100%|█████████▉| 997/1000 [02:14<00:00,  7.05it/s]

100%|█████████▉| 999/1000 [02:15<00:00,  6.76it/s]

100%|██████████| 1000/1000 [02:15<00:00,  6.67it/s]
                                                      

                                                   
{'eval_loss': '0.8095', 'eval_runtime': '135.5', 'eval_samples_per_second': '7.379', 'eval_steps_per_second': '7.379', 'epoch': '0.331', 'num_input_tokens_seen': 3999176}

 33%|███▎      | 600/1813 [1:06:49<2:07:05,  6.29s/it]

100%|██████████| 1000/1000 [02:15<00:00,  6.67it/s]

                                                   
 33%|███▎      | 601/1813 [1:06:54<15:37:31, 46.41s/it]
 33%|███▎      | 602/1813 [1:06:59<11:25:30, 33.96s/it]
 33%|███▎      | 603/1813 [1:07:04<8:32:28, 25.41s/it] 
 33%|███▎      | 604/1813 [1:07:10<6:35:12, 19.61s/it]
 33%|███▎      | 605/1813 [1:07:18<5:24:35, 16.12s/it]
 33%|███▎      | 606/1813 [1:07:26<4:31:29, 13.50s/it]
 33%|███▎      | 607/1813 [1:07:32<3:46:50, 11.29s/it]
 34%|███▎      | 608/1813 [1:07:38<3:16:38,  9.79s/it]
 34%|███▎      | 609/1813 [1:07:44<2:54:56,  8.72s/it]
 34%|███▎      | 610/1813 [1:07:51<2:40:12,  7.99s/it]
                                                      
{'loss': '0.98', 'grad_norm': '0.6249', 'learning_rate': '8.235e-05', 'epoch': '0.3366', 'num_input_tokens_seen': 4066376, 'train_runtime': '4071', 'train_tokens_per_second': '998.8'}

 34%|███▎      | 610/1813 [1:07:51<2:40:12,  7.99s/it]
 34%|███▎      | 611/1813 [1:07:56<2:23:39,  7.17s/it]
 34%|███▍      | 612/1813 [1:08:00<2:05:28,  6.27s/it]
 34%|███▍      | 613/1813 [1:08:06<2:03:51,  6.19s/it]
 34%|███▍      | 614/1813 [1:08:12<2:02:54,  6.15s/it]
 34%|███▍      | 615/1813 [1:08:18<1:57:52,  5.90s/it]
 34%|███▍      | 616/1813 [1:08:23<1:54:26,  5.74s/it]
 34%|███▍      | 617/1813 [1:08:28<1:52:52,  5.66s/it]
 34%|███▍      | 618/1813 [1:08:35<2:01:09,  6.08s/it]
 34%|███▍      | 619/1813 [1:08:40<1:53:59,  5.73s/it]
 34%|███▍      | 620/1813 [1:08:47<1:58:41,  5.97s/it]
                                                      
{'loss': '0.8698', 'grad_norm': '0.8595', 'learning_rate': '8.163e-05', 'epoch': '0.3421', 'num_input_tokens_seen': 4123976, 'train_runtime': '4127', 'train_tokens_per_second': '999.2'}

 34%|███▍      | 620/1813 [1:08:47<1:58:41,  5.97s/it]
 34%|███▍      | 621/1813 [1:08:54<2:03:47,  6.23s/it]
 34%|███▍      | 622/1813 [1:09:01<2:12:24,  6.67s/it]
 34%|███▍      | 623/1813 [1:09:06<2:02:54,  6.20s/it]
 34%|███▍      | 624/1813 [1:09:13<2:03:53,  6.25s/it]
 34%|███▍      | 625/1813 [1:09:18<1:56:20,  5.88s/it]
 35%|███▍      | 626/1813 [1:09:22<1:47:39,  5.44s/it]
 35%|███▍      | 627/1813 [1:09:28<1:51:53,  5.66s/it]
 35%|███▍      | 628/1813 [1:09:35<1:56:08,  5.88s/it]
 35%|███▍      | 629/1813 [1:09:43<2:10:15,  6.60s/it]
 35%|███▍      | 630/1813 [1:09:50<2:10:51,  6.64s/it]
                                                      
{'loss': '0.9488', 'grad_norm': '0.6753', 'learning_rate': '8.089e-05', 'epoch': '0.3476', 'num_input_tokens_seen': 4191992, 'train_runtime': '4190', 'train_tokens_per_second': '1000'}

 35%|███▍      | 630/1813 [1:09:50<2:10:51,  6.64s/it]
 35%|███▍      | 631/1813 [1:09:56<2:09:24,  6.57s/it]
 35%|███▍      | 632/1813 [1:10:02<2:05:53,  6.40s/it]
 35%|███▍      | 633/1813 [1:10:08<2:01:34,  6.18s/it]
 35%|███▍      | 634/1813 [1:10:15<2:07:48,  6.50s/it]
 35%|███▌      | 635/1813 [1:10:22<2:09:53,  6.62s/it]
 35%|███▌      | 636/1813 [1:10:27<2:01:54,  6.21s/it]
 35%|███▌      | 637/1813 [1:10:34<2:06:17,  6.44s/it]
 35%|███▌      | 638/1813 [1:10:40<2:01:43,  6.22s/it]
 35%|███▌      | 639/1813 [1:10:45<1:55:40,  5.91s/it]
 35%|███▌      | 640/1813 [1:10:51<1:55:59,  5.93s/it]
                                                      
{'loss': '0.9611', 'grad_norm': '0.9323', 'learning_rate': '8.014e-05', 'epoch': '0.3531', 'num_input_tokens_seen': 4257760, 'train_runtime': '4252', 'train_tokens_per_second': '1001'}

 35%|███▌      | 640/1813 [1:10:51<1:55:59,  5.93s/it]
 35%|███▌      | 641/1813 [1:10:57<1:53:10,  5.79s/it]
 35%|███▌      | 642/1813 [1:11:04<2:01:45,  6.24s/it]
 35%|███▌      | 643/1813 [1:11:11<2:03:40,  6.34s/it]
 36%|███▌      | 644/1813 [1:11:16<1:58:11,  6.07s/it]
 36%|███▌      | 645/1813 [1:11:22<1:57:55,  6.06s/it]
 36%|███▌      | 646/1813 [1:11:28<1:56:26,  5.99s/it]
 36%|███▌      | 647/1813 [1:11:34<1:57:54,  6.07s/it]
 36%|███▌      | 648/1813 [1:11:41<2:03:10,  6.34s/it]
 36%|███▌      | 649/1813 [1:11:47<1:58:58,  6.13s/it]
 36%|███▌      | 650/1813 [1:11:52<1:52:30,  5.80s/it]
                                                      
{'loss': '0.9568', 'grad_norm': '0.9603', 'learning_rate': '7.938e-05', 'epoch': '0.3586', 'num_input_tokens_seen': 4322136, 'train_runtime': '4312', 'train_tokens_per_second': '1002'}

 36%|███▌      | 650/1813 [1:11:52<1:52:30,  5.80s/it]
 36%|███▌      | 651/1813 [1:11:58<1:56:18,  6.01s/it]
 36%|███▌      | 652/1813 [1:12:05<2:00:44,  6.24s/it]
 36%|███▌      | 653/1813 [1:12:10<1:55:34,  5.98s/it]
 36%|███▌      | 654/1813 [1:12:16<1:51:31,  5.77s/it]
 36%|███▌      | 655/1813 [1:12:22<1:54:07,  5.91s/it]
 36%|███▌      | 656/1813 [1:12:27<1:50:39,  5.74s/it]
 36%|███▌      | 657/1813 [1:12:32<1:46:32,  5.53s/it]
 36%|███▋      | 658/1813 [1:12:39<1:51:25,  5.79s/it]
 36%|███▋      | 659/1813 [1:12:45<1:54:53,  5.97s/it]
 36%|███▋      | 660/1813 [1:12:51<1:52:26,  5.85s/it]
                                                      
{'loss': '0.8933', 'grad_norm': '0.8715', 'learning_rate': '7.861e-05', 'epoch': '0.3641', 'num_input_tokens_seen': 4385688, 'train_runtime': '4371', 'train_tokens_per_second': '1003'}

 36%|███▋      | 660/1813 [1:12:51<1:52:26,  5.85s/it]
 36%|███▋      | 661/1813 [1:12:57<1:52:57,  5.88s/it]
 37%|███▋      | 662/1813 [1:13:03<1:53:58,  5.94s/it]
 37%|███▋      | 663/1813 [1:13:09<1:58:34,  6.19s/it]
 37%|███▋      | 664/1813 [1:13:16<1:58:55,  6.21s/it]
 37%|███▋      | 665/1813 [1:13:21<1:51:19,  5.82s/it]
 37%|███▋      | 666/1813 [1:13:26<1:48:10,  5.66s/it]
 37%|███▋      | 667/1813 [1:13:33<1:53:59,  5.97s/it]
 37%|███▋      | 668/1813 [1:13:39<1:55:49,  6.07s/it]
 37%|███▋      | 669/1813 [1:13:45<1:54:34,  6.01s/it]
 37%|███▋      | 670/1813 [1:13:50<1:52:05,  5.88s/it]
                                                      
{'loss': '0.9825', 'grad_norm': '0.9484', 'learning_rate': '7.783e-05', 'epoch': '0.3697', 'num_input_tokens_seen': 4449456, 'train_runtime': '4431', 'train_tokens_per_second': '1004'}

 37%|███▋      | 670/1813 [1:13:50<1:52:05,  5.88s/it]
 37%|███▋      | 671/1813 [1:13:56<1:53:18,  5.95s/it]
 37%|███▋      | 672/1813 [1:14:03<1:57:17,  6.17s/it]
 37%|███▋      | 673/1813 [1:14:09<1:57:21,  6.18s/it]
 37%|███▋      | 674/1813 [1:14:16<2:00:11,  6.33s/it]
 37%|███▋      | 675/1813 [1:14:22<1:57:30,  6.20s/it]
 37%|███▋      | 676/1813 [1:14:27<1:53:34,  5.99s/it]
 37%|███▋      | 677/1813 [1:14:36<2:06:12,  6.67s/it]
 37%|███▋      | 678/1813 [1:14:41<1:57:30,  6.21s/it]
 37%|███▋      | 679/1813 [1:14:46<1:51:24,  5.89s/it]
 38%|███▊      | 680/1813 [1:14:51<1:49:02,  5.77s/it]
                                                      
{'loss': '0.939', 'grad_norm': '0.789', 'learning_rate': '7.704e-05', 'epoch': '0.3752', 'num_input_tokens_seen': 4514984, 'train_runtime': '4492', 'train_tokens_per_second': '1005'}

 38%|███▊      | 680/1813 [1:14:51<1:49:02,  5.77s/it]
 38%|███▊      | 681/1813 [1:14:58<1:52:35,  5.97s/it]
 38%|███▊      | 682/1813 [1:15:03<1:47:35,  5.71s/it]
 38%|███▊      | 683/1813 [1:15:09<1:49:24,  5.81s/it]
 38%|███▊      | 684/1813 [1:15:16<1:53:50,  6.05s/it]
 38%|███▊      | 685/1813 [1:15:23<2:02:35,  6.52s/it]
 38%|███▊      | 686/1813 [1:15:30<2:01:50,  6.49s/it]
 38%|███▊      | 687/1813 [1:15:37<2:08:24,  6.84s/it]
 38%|███▊      | 688/1813 [1:15:42<1:55:02,  6.14s/it]
 38%|███▊      | 689/1813 [1:15:50<2:09:07,  6.89s/it]
 38%|███▊      | 690/1813 [1:15:58<2:10:16,  6.96s/it]
                                                      
{'loss': '0.9791', 'grad_norm': '0.9098', 'learning_rate': '7.624e-05', 'epoch': '0.3807', 'num_input_tokens_seen': 4587840, 'train_runtime': '4558', 'train_tokens_per_second': '1007'}

 38%|███▊      | 690/1813 [1:15:58<2:10:16,  6.96s/it]
 38%|███▊      | 691/1813 [1:16:03<2:02:42,  6.56s/it]
 38%|███▊      | 692/1813 [1:16:09<2:00:39,  6.46s/it]
 38%|███▊      | 693/1813 [1:16:15<1:55:43,  6.20s/it]
 38%|███▊      | 694/1813 [1:16:21<1:56:43,  6.26s/it]
 38%|███▊      | 695/1813 [1:16:28<1:56:11,  6.24s/it]
 38%|███▊      | 696/1813 [1:16:36<2:05:58,  6.77s/it]
 38%|███▊      | 697/1813 [1:16:40<1:54:29,  6.16s/it]
 38%|███▊      | 698/1813 [1:16:46<1:49:45,  5.91s/it]
 39%|███▊      | 699/1813 [1:16:53<1:55:46,  6.24s/it]
 39%|███▊      | 700/1813 [1:16:59<1:58:23,  6.38s/it]
                                                      
{'loss': '1.001', 'grad_norm': '0.9895', 'learning_rate': '7.543e-05', 'epoch': '0.3862', 'num_input_tokens_seen': 4653312, 'train_runtime': '4620', 'train_tokens_per_second': '1007'}

 39%|███▊      | 700/1813 [1:16:59<1:58:23,  6.38s/it]
 39%|███▊      | 701/1813 [1:17:07<2:03:25,  6.66s/it]
 39%|███▊      | 702/1813 [1:17:13<2:00:52,  6.53s/it]
 39%|███▉      | 703/1813 [1:17:21<2:08:18,  6.94s/it]
 39%|███▉      | 704/1813 [1:17:26<2:01:06,  6.55s/it]
 39%|███▉      | 705/1813 [1:17:33<2:02:55,  6.66s/it]
 39%|███▉      | 706/1813 [1:17:40<2:00:41,  6.54s/it]
 39%|███▉      | 707/1813 [1:17:49<2:17:38,  7.47s/it]
 39%|███▉      | 708/1813 [1:17:57<2:17:02,  7.44s/it]
 39%|███▉      | 709/1813 [1:18:03<2:12:04,  7.18s/it]
 39%|███▉      | 710/1813 [1:18:09<2:03:23,  6.71s/it]
                                                      
{'loss': '0.957', 'grad_norm': '0.7076', 'learning_rate': '7.462e-05', 'epoch': '0.3917', 'num_input_tokens_seen': 4732080, 'train_runtime': '4689', 'train_tokens_per_second': '1009'}

 39%|███▉      | 710/1813 [1:18:09<2:03:23,  6.71s/it]
 39%|███▉      | 711/1813 [1:18:16<2:04:32,  6.78s/it]
 39%|███▉      | 712/1813 [1:18:23<2:04:10,  6.77s/it]
 39%|███▉      | 713/1813 [1:18:28<1:58:06,  6.44s/it]
 39%|███▉      | 714/1813 [1:18:34<1:56:27,  6.36s/it]
 39%|███▉      | 715/1813 [1:18:41<1:58:20,  6.47s/it]
 39%|███▉      | 716/1813 [1:18:48<2:01:15,  6.63s/it]
 40%|███▉      | 717/1813 [1:18:54<1:58:54,  6.51s/it]
 40%|███▉      | 718/1813 [1:19:01<1:58:53,  6.51s/it]
 40%|███▉      | 719/1813 [1:19:06<1:52:15,  6.16s/it]
 40%|███▉      | 720/1813 [1:19:13<1:53:10,  6.21s/it]
                                                      
{'loss': '0.9892', 'grad_norm': '0.8414', 'learning_rate': '7.379e-05', 'epoch': '0.3972', 'num_input_tokens_seen': 4799552, 'train_runtime': '4753', 'train_tokens_per_second': '1010'}

 40%|███▉      | 720/1813 [1:19:13<1:53:10,  6.21s/it]
 40%|███▉      | 721/1813 [1:19:19<1:55:14,  6.33s/it]
 40%|███▉      | 722/1813 [1:19:24<1:48:13,  5.95s/it]
 40%|███▉      | 723/1813 [1:19:29<1:43:53,  5.72s/it]
 40%|███▉      | 724/1813 [1:19:37<1:55:35,  6.37s/it]
 40%|███▉      | 725/1813 [1:19:46<2:06:33,  6.98s/it]
 40%|████      | 726/1813 [1:19:52<2:04:37,  6.88s/it]
 40%|████      | 727/1813 [1:19:58<2:00:36,  6.66s/it]
 40%|████      | 728/1813 [1:20:04<1:52:14,  6.21s/it]
 40%|████      | 729/1813 [1:20:09<1:50:06,  6.09s/it]
 40%|████      | 730/1813 [1:20:15<1:45:59,  5.87s/it]
                                                      
{'loss': '0.9659', 'grad_norm': '1.013', 'learning_rate': '7.296e-05', 'epoch': '0.4028', 'num_input_tokens_seen': 4866864, 'train_runtime': '4815', 'train_tokens_per_second': '1011'}

 40%|████      | 730/1813 [1:20:15<1:45:59,  5.87s/it]
 40%|████      | 731/1813 [1:20:22<1:51:42,  6.19s/it]
 40%|████      | 732/1813 [1:20:28<1:51:32,  6.19s/it]
 40%|████      | 733/1813 [1:20:35<1:57:44,  6.54s/it]
 40%|████      | 734/1813 [1:20:42<1:59:40,  6.66s/it]
 41%|████      | 735/1813 [1:20:49<1:59:35,  6.66s/it]
 41%|████      | 736/1813 [1:20:55<1:54:36,  6.39s/it]
 41%|████      | 737/1813 [1:21:00<1:51:05,  6.19s/it]
 41%|████      | 738/1813 [1:21:05<1:44:55,  5.86s/it]
 41%|████      | 739/1813 [1:21:11<1:44:38,  5.85s/it]
 41%|████      | 740/1813 [1:21:18<1:48:19,  6.06s/it]
                                                      
{'loss': '0.8938', 'grad_norm': '0.6765', 'learning_rate': '7.211e-05', 'epoch': '0.4083', 'num_input_tokens_seen': 4936352, 'train_runtime': '4878', 'train_tokens_per_second': '1012'}

 41%|████      | 740/1813 [1:21:18<1:48:19,  6.06s/it]
 41%|████      | 741/1813 [1:21:24<1:50:08,  6.16s/it]
 41%|████      | 742/1813 [1:21:32<1:56:50,  6.55s/it]
 41%|████      | 743/1813 [1:21:39<2:01:06,  6.79s/it]
 41%|████      | 744/1813 [1:21:46<1:59:53,  6.73s/it]
 41%|████      | 745/1813 [1:21:53<2:01:11,  6.81s/it]
 41%|████      | 746/1813 [1:21:59<1:56:48,  6.57s/it]
 41%|████      | 747/1813 [1:22:07<2:03:53,  6.97s/it]
 41%|████▏     | 748/1813 [1:22:12<1:55:47,  6.52s/it]
 41%|████▏     | 749/1813 [1:22:18<1:54:40,  6.47s/it]
 41%|████▏     | 750/1813 [1:22:24<1:50:49,  6.26s/it]
                                                      
{'loss': '0.978', 'grad_norm': '0.7119', 'learning_rate': '7.126e-05', 'epoch': '0.4138', 'num_input_tokens_seen': 5011064, 'train_runtime': '4945', 'train_tokens_per_second': '1013'}

 41%|████▏     | 750/1813 [1:22:24<1:50:49,  6.26s/it]
 41%|████▏     | 751/1813 [1:22:30<1:48:53,  6.15s/it]
 41%|████▏     | 752/1813 [1:22:36<1:47:00,  6.05s/it]
 42%|████▏     | 753/1813 [1:22:42<1:49:25,  6.19s/it]
 42%|████▏     | 754/1813 [1:22:51<2:01:25,  6.88s/it]
 42%|████▏     | 755/1813 [1:22:56<1:51:51,  6.34s/it]
 42%|████▏     | 756/1813 [1:23:02<1:48:16,  6.15s/it]
 42%|████▏     | 757/1813 [1:23:07<1:46:45,  6.07s/it]
 42%|████▏     | 758/1813 [1:23:14<1:50:35,  6.29s/it]
 42%|████▏     | 759/1813 [1:23:21<1:54:32,  6.52s/it]
 42%|████▏     | 760/1813 [1:23:28<1:52:46,  6.43s/it]
                                                      
{'loss': '0.9966', 'grad_norm': '1.093', 'learning_rate': '7.04e-05', 'epoch': '0.4193', 'num_input_tokens_seen': 5078960, 'train_runtime': '5008', 'train_tokens_per_second': '1014'}

 42%|████▏     | 760/1813 [1:23:28<1:52:46,  6.43s/it]
 42%|████▏     | 761/1813 [1:23:34<1:54:50,  6.55s/it]
 42%|████▏     | 762/1813 [1:23:41<1:55:59,  6.62s/it]
 42%|████▏     | 763/1813 [1:23:48<1:59:09,  6.81s/it]
 42%|████▏     | 764/1813 [1:23:55<1:59:31,  6.84s/it]
 42%|████▏     | 765/1813 [1:24:03<2:02:16,  7.00s/it]
 42%|████▏     | 766/1813 [1:24:09<1:59:03,  6.82s/it]
 42%|████▏     | 767/1813 [1:24:15<1:51:37,  6.40s/it]
 42%|████▏     | 768/1813 [1:24:19<1:39:38,  5.72s/it]
 42%|████▏     | 769/1813 [1:24:25<1:44:30,  6.01s/it]
 42%|████▏     | 770/1813 [1:24:32<1:45:09,  6.05s/it]
                                                      
{'loss': '0.9243', 'grad_norm': '0.8774', 'learning_rate': '6.954e-05', 'epoch': '0.4248', 'num_input_tokens_seen': 5148504, 'train_runtime': '5072', 'train_tokens_per_second': '1015'}

 42%|████▏     | 770/1813 [1:24:32<1:45:09,  6.05s/it]
 43%|████▎     | 771/1813 [1:24:38<1:47:11,  6.17s/it]
 43%|████▎     | 772/1813 [1:24:45<1:52:43,  6.50s/it]
 43%|████▎     | 773/1813 [1:24:51<1:48:56,  6.28s/it]
 43%|████▎     | 774/1813 [1:24:56<1:42:06,  5.90s/it]
 43%|████▎     | 775/1813 [1:25:02<1:42:16,  5.91s/it]
 43%|████▎     | 776/1813 [1:25:09<1:46:28,  6.16s/it]
 43%|████▎     | 777/1813 [1:25:16<1:53:59,  6.60s/it]
 43%|████▎     | 778/1813 [1:25:22<1:46:49,  6.19s/it]
 43%|████▎     | 779/1813 [1:25:27<1:40:57,  5.86s/it]
 43%|████▎     | 780/1813 [1:25:33<1:45:57,  6.15s/it]
                                                      
{'loss': '0.8832', 'grad_norm': '0.9475', 'learning_rate': '6.866e-05', 'epoch': '0.4303', 'num_input_tokens_seen': 5215784, 'train_runtime': '5134', 'train_tokens_per_second': '1016'}

 43%|████▎     | 780/1813 [1:25:33<1:45:57,  6.15s/it]
 43%|████▎     | 781/1813 [1:25:40<1:49:44,  6.38s/it]
 43%|████▎     | 782/1813 [1:25:49<1:59:11,  6.94s/it]
 43%|████▎     | 783/1813 [1:25:56<2:00:13,  7.00s/it]
 43%|████▎     | 784/1813 [1:26:02<1:54:48,  6.69s/it]
 43%|████▎     | 785/1813 [1:26:09<1:56:57,  6.83s/it]
 43%|████▎     | 786/1813 [1:26:16<1:58:47,  6.94s/it]
 43%|████▎     | 787/1813 [1:26:22<1:51:00,  6.49s/it]
 43%|████▎     | 788/1813 [1:26:27<1:46:36,  6.24s/it]
 44%|████▎     | 789/1813 [1:26:33<1:42:08,  5.99s/it]
 44%|████▎     | 790/1813 [1:26:38<1:41:14,  5.94s/it]
                                                      
{'loss': '0.9949', 'grad_norm': '1.252', 'learning_rate': '6.778e-05', 'epoch': '0.4359', 'num_input_tokens_seen': 5285160, 'train_runtime': '5199', 'train_tokens_per_second': '1017'}

 44%|████▎     | 790/1813 [1:26:38<1:41:14,  5.94s/it]
 44%|████▎     | 791/1813 [1:26:45<1:41:56,  5.98s/it]
 44%|████▎     | 792/1813 [1:26:52<1:47:44,  6.33s/it]
 44%|████▎     | 793/1813 [1:26:59<1:52:06,  6.59s/it]
 44%|████▍     | 794/1813 [1:27:05<1:51:17,  6.55s/it]
 44%|████▍     | 795/1813 [1:27:11<1:47:30,  6.34s/it]
 44%|████▍     | 796/1813 [1:27:18<1:49:39,  6.47s/it]
 44%|████▍     | 797/1813 [1:27:26<1:55:10,  6.80s/it]
 44%|████▍     | 798/1813 [1:27:32<1:51:27,  6.59s/it]
 44%|████▍     | 799/1813 [1:27:38<1:48:22,  6.41s/it]
 44%|████▍     | 800/1813 [1:27:43<1:45:16,  6.24s/it]
                                                      
{'loss': '0.9382', 'grad_norm': '0.7748', 'learning_rate': '6.69e-05', 'epoch': '0.4414', 'num_input_tokens_seen': 5357720, 'train_runtime': '5264', 'train_tokens_per_second': '1018'}

 44%|████▍     | 800/1813 [1:27:43<1:45:16,  6.24s/it]
 44%|████▍     | 801/1813 [1:27:49<1:40:55,  5.98s/it]
 44%|████▍     | 802/1813 [1:27:55<1:41:48,  6.04s/it]
 44%|████▍     | 803/1813 [1:28:03<1:51:53,  6.65s/it]
 44%|████▍     | 804/1813 [1:28:09<1:50:02,  6.54s/it]
 44%|████▍     | 805/1813 [1:28:15<1:46:40,  6.35s/it]
 44%|████▍     | 806/1813 [1:28:21<1:44:25,  6.22s/it]
 45%|████▍     | 807/1813 [1:28:27<1:40:52,  6.02s/it]
 45%|████▍     | 808/1813 [1:28:34<1:49:18,  6.53s/it]
 45%|████▍     | 809/1813 [1:28:41<1:49:43,  6.56s/it]
 45%|████▍     | 810/1813 [1:28:49<1:55:46,  6.93s/it]
                                                      
{'loss': '0.9547', 'grad_norm': '0.6789', 'learning_rate': '6.601e-05', 'epoch': '0.4469', 'num_input_tokens_seen': 5430288, 'train_runtime': '5329', 'train_tokens_per_second': '1019'}

 45%|████▍     | 810/1813 [1:28:49<1:55:46,  6.93s/it]
 45%|████▍     | 811/1813 [1:28:56<1:55:09,  6.90s/it]
 45%|████▍     | 812/1813 [1:29:01<1:49:38,  6.57s/it]
 45%|████▍     | 813/1813 [1:29:07<1:45:41,  6.34s/it]
 45%|████▍     | 814/1813 [1:29:14<1:45:20,  6.33s/it]
 45%|████▍     | 815/1813 [1:29:18<1:38:03,  5.90s/it]
 45%|████▌     | 816/1813 [1:29:25<1:42:41,  6.18s/it]
 45%|████▌     | 817/1813 [1:29:31<1:40:30,  6.05s/it]
 45%|████▌     | 818/1813 [1:29:38<1:45:43,  6.38s/it]
 45%|████▌     | 819/1813 [1:29:45<1:46:40,  6.44s/it]
 45%|████▌     | 820/1813 [1:29:52<1:51:29,  6.74s/it]
                                                      
{'loss': '0.8936', 'grad_norm': '0.7883', 'learning_rate': '6.511e-05', 'epoch': '0.4524', 'num_input_tokens_seen': 5497552, 'train_runtime': '5393', 'train_tokens_per_second': '1019'}

 45%|████▌     | 820/1813 [1:29:52<1:51:29,  6.74s/it]
 45%|████▌     | 821/1813 [1:29:59<1:49:50,  6.64s/it]
 45%|████▌     | 822/1813 [1:30:03<1:40:48,  6.10s/it]
 45%|████▌     | 823/1813 [1:30:08<1:33:52,  5.69s/it]
 45%|████▌     | 824/1813 [1:30:15<1:37:06,  5.89s/it]
 46%|████▌     | 825/1813 [1:30:21<1:38:57,  6.01s/it]
 46%|████▌     | 826/1813 [1:30:28<1:42:58,  6.26s/it]
 46%|████▌     | 827/1813 [1:30:33<1:40:26,  6.11s/it]
 46%|████▌     | 828/1813 [1:30:39<1:39:17,  6.05s/it]
 46%|████▌     | 829/1813 [1:30:45<1:36:50,  5.90s/it]
 46%|████▌     | 830/1813 [1:30:52<1:44:01,  6.35s/it]
                                                      
{'loss': '0.7945', 'grad_norm': '0.8077', 'learning_rate': '6.421e-05', 'epoch': '0.4579', 'num_input_tokens_seen': 5563144, 'train_runtime': '5453', 'train_tokens_per_second': '1020'}

 46%|████▌     | 830/1813 [1:30:52<1:44:01,  6.35s/it]
 46%|████▌     | 831/1813 [1:30:59<1:43:54,  6.35s/it]
 46%|████▌     | 832/1813 [1:31:06<1:49:41,  6.71s/it]
 46%|████▌     | 833/1813 [1:31:13<1:48:19,  6.63s/it]
 46%|████▌     | 834/1813 [1:31:19<1:48:02,  6.62s/it]
 46%|████▌     | 835/1813 [1:31:25<1:44:27,  6.41s/it]
 46%|████▌     | 836/1813 [1:31:32<1:45:48,  6.50s/it]
 46%|████▌     | 837/1813 [1:31:40<1:51:39,  6.86s/it]
 46%|████▌     | 838/1813 [1:31:45<1:45:45,  6.51s/it]
 46%|████▋     | 839/1813 [1:31:51<1:42:53,  6.34s/it]
 46%|████▋     | 840/1813 [1:31:57<1:39:03,  6.11s/it]
                                                      
{'loss': '0.9685', 'grad_norm': '0.9255', 'learning_rate': '6.33e-05', 'epoch': '0.4634', 'num_input_tokens_seen': 5634104, 'train_runtime': '5517', 'train_tokens_per_second': '1021'}

 46%|████▋     | 840/1813 [1:31:57<1:39:03,  6.11s/it]
 46%|████▋     | 841/1813 [1:32:03<1:37:17,  6.01s/it]
 46%|████▋     | 842/1813 [1:32:09<1:40:04,  6.18s/it]
 46%|████▋     | 843/1813 [1:32:15<1:38:51,  6.12s/it]
 47%|████▋     | 844/1813 [1:32:21<1:35:12,  5.90s/it]
 47%|████▋     | 845/1813 [1:32:27<1:36:36,  5.99s/it]
 47%|████▋     | 846/1813 [1:32:33<1:38:59,  6.14s/it]
 47%|████▋     | 847/1813 [1:32:40<1:42:50,  6.39s/it]
 47%|████▋     | 848/1813 [1:32:47<1:46:32,  6.62s/it]
 47%|████▋     | 849/1813 [1:32:53<1:39:35,  6.20s/it]
 47%|████▋     | 850/1813 [1:33:01<1:50:12,  6.87s/it]
                                                      
{'loss': '0.9214', 'grad_norm': '0.7279', 'learning_rate': '6.239e-05', 'epoch': '0.469', 'num_input_tokens_seen': 5704744, 'train_runtime': '5581', 'train_tokens_per_second': '1022'}

 47%|████▋     | 850/1813 [1:33:01<1:50:12,  6.87s/it]
 47%|████▋     | 851/1813 [1:33:08<1:49:55,  6.86s/it]
 47%|████▋     | 852/1813 [1:33:13<1:40:59,  6.31s/it]
 47%|████▋     | 853/1813 [1:33:19<1:40:45,  6.30s/it]
 47%|████▋     | 854/1813 [1:33:26<1:42:45,  6.43s/it]
 47%|████▋     | 855/1813 [1:33:32<1:41:25,  6.35s/it]
 47%|████▋     | 856/1813 [1:33:38<1:40:26,  6.30s/it]
 47%|████▋     | 857/1813 [1:33:43<1:35:20,  5.98s/it]
 47%|████▋     | 858/1813 [1:33:48<1:26:58,  5.46s/it]
 47%|████▋     | 859/1813 [1:33:54<1:31:24,  5.75s/it]
 47%|████▋     | 860/1813 [1:34:01<1:35:44,  6.03s/it]
                                                      
{'loss': '0.9454', 'grad_norm': '0.9392', 'learning_rate': '6.147e-05', 'epoch': '0.4745', 'num_input_tokens_seen': 5766424, 'train_runtime': '5641', 'train_tokens_per_second': '1022'}

 47%|████▋     | 860/1813 [1:34:01<1:35:44,  6.03s/it]
 47%|████▋     | 861/1813 [1:34:06<1:30:55,  5.73s/it]
 48%|████▊     | 862/1813 [1:34:13<1:36:04,  6.06s/it]
 48%|████▊     | 863/1813 [1:34:19<1:36:03,  6.07s/it]
 48%|████▊     | 864/1813 [1:34:23<1:27:50,  5.55s/it]
 48%|████▊     | 865/1813 [1:34:30<1:34:30,  5.98s/it]
 48%|████▊     | 866/1813 [1:34:36<1:34:41,  6.00s/it]
 48%|████▊     | 867/1813 [1:34:42<1:32:55,  5.89s/it]
 48%|████▊     | 868/1813 [1:34:47<1:31:36,  5.82s/it]
 48%|████▊     | 869/1813 [1:34:55<1:38:30,  6.26s/it]
 48%|████▊     | 870/1813 [1:35:02<1:45:16,  6.70s/it]
                                                      
{'loss': '0.9217', 'grad_norm': '0.7004', 'learning_rate': '6.055e-05', 'epoch': '0.48', 'num_input_tokens_seen': 5831352, 'train_runtime': '5703', 'train_tokens_per_second': '1023'}

 48%|████▊     | 870/1813 [1:35:02<1:45:16,  6.70s/it]
 48%|████▊     | 871/1813 [1:35:08<1:39:09,  6.32s/it]
 48%|████▊     | 872/1813 [1:35:15<1:43:16,  6.58s/it]
 48%|████▊     | 873/1813 [1:35:22<1:44:15,  6.65s/it]
 48%|████▊     | 874/1813 [1:35:29<1:48:21,  6.92s/it]
 48%|████▊     | 875/1813 [1:35:37<1:52:20,  7.19s/it]
 48%|████▊     | 876/1813 [1:35:44<1:50:19,  7.06s/it]
 48%|████▊     | 877/1813 [1:35:52<1:54:28,  7.34s/it]
 48%|████▊     | 878/1813 [1:35:58<1:49:51,  7.05s/it]
 48%|████▊     | 879/1813 [1:36:06<1:51:49,  7.18s/it]
 49%|████▊     | 880/1813 [1:36:11<1:39:55,  6.43s/it]
                                                      
{'loss': '0.9442', 'grad_norm': '1.086', 'learning_rate': '5.962e-05', 'epoch': '0.4855', 'num_input_tokens_seen': 5907208, 'train_runtime': '5771', 'train_tokens_per_second': '1024'}

 49%|████▊     | 880/1813 [1:36:11<1:39:55,  6.43s/it]
 49%|████▊     | 881/1813 [1:36:16<1:35:17,  6.13s/it]
 49%|████▊     | 882/1813 [1:36:22<1:35:52,  6.18s/it]
 49%|████▊     | 883/1813 [1:36:29<1:38:55,  6.38s/it]
 49%|████▉     | 884/1813 [1:36:35<1:38:17,  6.35s/it]
 49%|████▉     | 885/1813 [1:36:41<1:36:45,  6.26s/it]
 49%|████▉     | 886/1813 [1:36:48<1:36:31,  6.25s/it]
 49%|████▉     | 887/1813 [1:36:55<1:43:53,  6.73s/it]
 49%|████▉     | 888/1813 [1:37:02<1:43:27,  6.71s/it]
 49%|████▉     | 889/1813 [1:37:09<1:45:26,  6.85s/it]
 49%|████▉     | 890/1813 [1:37:16<1:42:33,  6.67s/it]
                                                      
{'loss': '0.9144', 'grad_norm': '0.7531', 'learning_rate': '5.869e-05', 'epoch': '0.491', 'num_input_tokens_seen': 5978048, 'train_runtime': '5836', 'train_tokens_per_second': '1024'}

 49%|████▉     | 890/1813 [1:37:16<1:42:33,  6.67s/it]
 49%|████▉     | 891/1813 [1:37:22<1:40:04,  6.51s/it]
 49%|████▉     | 892/1813 [1:37:29<1:44:15,  6.79s/it]
 49%|████▉     | 893/1813 [1:37:35<1:41:33,  6.62s/it]
 49%|████▉     | 894/1813 [1:37:41<1:37:58,  6.40s/it]
 49%|████▉     | 895/1813 [1:37:49<1:42:03,  6.67s/it]
 49%|████▉     | 896/1813 [1:37:54<1:36:45,  6.33s/it]
 49%|████▉     | 897/1813 [1:38:00<1:34:37,  6.20s/it]
 50%|████▉     | 898/1813 [1:38:07<1:39:24,  6.52s/it]
 50%|████▉     | 899/1813 [1:38:15<1:42:56,  6.76s/it]
 50%|████▉     | 900/1813 [1:38:22<1:46:52,  7.02s/it]
                                                      
{'loss': '0.9864', 'grad_norm': '2.774', 'learning_rate': '5.776e-05', 'epoch': '0.4966', 'num_input_tokens_seen': 6050856, 'train_runtime': '5903', 'train_tokens_per_second': '1025'}

 50%|████▉     | 900/1813 [1:38:22<1:46:52,  7.02s/it]
***** Running Evaluation *****
  Num examples = 1000
  Batch size = 1


  0%|          | 0/1000 [00:00<?, ?it/s]

  0%|          | 3/1000 [00:00<01:03, 15.73it/s]

  0%|          | 5/1000 [00:00<02:17,  7.22it/s]

  1%|          | 7/1000 [00:00<01:59,  8.31it/s]

  1%|          | 9/1000 [00:01<02:33,  6.47it/s]

  1%|          | 11/1000 [00:01<02:02,  8.06it/s]

  1%|▏         | 13/1000 [00:01<02:21,  6.99it/s]

  1%|▏         | 14/1000 [00:01<02:24,  6.82it/s]

  2%|▏         | 15/1000 [00:02<02:45,  5.96it/s]

  2%|▏         | 16/1000 [00:02<02:51,  5.72it/s]

  2%|▏         | 18/1000 [00:02<02:42,  6.05it/s]

  2%|▏         | 19/1000 [00:02<03:10,  5.14it/s]

  2%|▏         | 20/1000 [00:03<03:33,  4.60it/s]

  2%|▏         | 22/1000 [00:03<02:36,  6.24it/s]

  2%|▏         | 23/1000 [00:03<02:54,  5.59it/s]

  2%|▎         | 25/1000 [00:03<02:16,  7.15it/s]

  3%|▎         | 26/1000 [00:04<02:38,  6.16it/s]

  3%|▎         | 28/1000 [00:04<02:43,  5.94it/s]

  3%|▎         | 29/1000 [00:04<02:33,  6.32it/s]

  3%|▎         | 30/1000 [00:04<02:44,  5.90it/s]

  3%|▎         | 31/1000 [00:04<03:02,  5.31it/s]

  3%|▎         | 32/1000 [00:05<02:42,  5.96it/s]

  3%|▎         | 33/1000 [00:05<02:48,  5.74it/s]

  4%|▎         | 35/1000 [00:05<02:06,  7.66it/s]

  4%|▎         | 37/1000 [00:05<01:47,  8.99it/s]

  4%|▍         | 39/1000 [00:05<02:07,  7.51it/s]

  4%|▍         | 40/1000 [00:06<02:04,  7.71it/s]

  4%|▍         | 42/1000 [00:06<01:45,  9.07it/s]

  4%|▍         | 44/1000 [00:06<01:35, 10.05it/s]

  5%|▍         | 46/1000 [00:06<01:47,  8.89it/s]

  5%|▍         | 47/1000 [00:06<02:11,  7.27it/s]

  5%|▍         | 49/1000 [00:07<01:49,  8.67it/s]

  5%|▌         | 51/1000 [00:07<01:36,  9.81it/s]

  5%|▌         | 53/1000 [00:07<01:27, 10.86it/s]

  6%|▌         | 55/1000 [00:07<01:28, 10.70it/s]

  6%|▌         | 57/1000 [00:07<01:41,  9.28it/s]

  6%|▌         | 59/1000 [00:08<01:55,  8.18it/s]

  6%|▌         | 61/1000 [00:08<01:40,  9.33it/s]

  6%|▋         | 63/1000 [00:08<01:36,  9.74it/s]

  6%|▋         | 65/1000 [00:08<01:51,  8.36it/s]

  7%|▋         | 67/1000 [00:09<02:03,  7.56it/s]

  7%|▋         | 69/1000 [00:09<01:52,  8.25it/s]

  7%|▋         | 70/1000 [00:09<02:13,  6.99it/s]

  7%|▋         | 72/1000 [00:09<02:18,  6.71it/s]

  7%|▋         | 74/1000 [00:09<01:54,  8.11it/s]

  8%|▊         | 75/1000 [00:10<02:14,  6.86it/s]

  8%|▊         | 76/1000 [00:10<02:18,  6.66it/s]

  8%|▊         | 78/1000 [00:10<02:25,  6.32it/s]

  8%|▊         | 80/1000 [00:10<01:57,  7.85it/s]

  8%|▊         | 82/1000 [00:10<01:39,  9.19it/s]

  8%|▊         | 84/1000 [00:11<01:54,  8.02it/s]

  8%|▊         | 85/1000 [00:11<02:14,  6.78it/s]

  9%|▊         | 86/1000 [00:11<02:33,  5.94it/s]

  9%|▊         | 87/1000 [00:12<02:49,  5.37it/s]

  9%|▉         | 89/1000 [00:12<02:10,  6.99it/s]

  9%|▉         | 90/1000 [00:12<02:05,  7.25it/s]

  9%|▉         | 91/1000 [00:12<02:29,  6.07it/s]

  9%|▉         | 92/1000 [00:12<02:27,  6.17it/s]

  9%|▉         | 93/1000 [00:12<02:36,  5.78it/s]

 10%|▉         | 95/1000 [00:13<02:44,  5.52it/s]

 10%|▉         | 97/1000 [00:13<02:13,  6.78it/s]

 10%|▉         | 99/1000 [00:13<01:47,  8.36it/s]

 10%|█         | 101/1000 [00:13<01:33,  9.62it/s]

 10%|█         | 103/1000 [00:14<01:55,  7.74it/s]

 10%|█         | 104/1000 [00:14<01:54,  7.82it/s]

 11%|█         | 106/1000 [00:14<01:35,  9.31it/s]

 11%|█         | 108/1000 [00:14<01:25, 10.43it/s]

 11%|█         | 110/1000 [00:14<01:19, 11.20it/s]

 11%|█         | 112/1000 [00:14<01:13, 12.03it/s]

 11%|█▏        | 114/1000 [00:14<01:10, 12.51it/s]

 12%|█▏        | 116/1000 [00:15<01:09, 12.80it/s]

 12%|█▏        | 118/1000 [00:15<01:06, 13.23it/s]

 12%|█▏        | 120/1000 [00:15<02:07,  6.91it/s]

 12%|█▏        | 122/1000 [00:16<01:48,  8.08it/s]

 12%|█▏        | 124/1000 [00:16<01:57,  7.43it/s]

 12%|█▎        | 125/1000 [00:16<02:32,  5.72it/s]

 13%|█▎        | 126/1000 [00:16<02:22,  6.14it/s]

 13%|█▎        | 127/1000 [00:17<02:30,  5.80it/s]

 13%|█▎        | 128/1000 [00:17<02:45,  5.28it/s]

 13%|█▎        | 130/1000 [00:17<02:02,  7.09it/s]

 13%|█▎        | 132/1000 [00:17<01:39,  8.70it/s]

 13%|█▎        | 134/1000 [00:17<01:25, 10.15it/s]

 14%|█▎        | 136/1000 [00:17<01:29,  9.64it/s]

 14%|█▍        | 138/1000 [00:18<01:27,  9.91it/s]

 14%|█▍        | 140/1000 [00:18<01:26,  9.95it/s]

 14%|█▍        | 142/1000 [00:18<01:35,  9.03it/s]

 14%|█▍        | 143/1000 [00:18<01:36,  8.89it/s]

 14%|█▍        | 145/1000 [00:18<01:24, 10.07it/s]

 15%|█▍        | 147/1000 [00:19<01:41,  8.44it/s]

 15%|█▍        | 148/1000 [00:19<01:40,  8.49it/s]

 15%|█▌        | 150/1000 [00:19<01:25,  9.91it/s]

 15%|█▌        | 152/1000 [00:19<01:17, 10.94it/s]

 15%|█▌        | 154/1000 [00:19<01:21, 10.36it/s]

 16%|█▌        | 156/1000 [00:20<02:07,  6.63it/s]

 16%|█▌        | 158/1000 [00:20<01:46,  7.94it/s]

 16%|█▌        | 160/1000 [00:20<01:37,  8.59it/s]

 16%|█▌        | 162/1000 [00:20<01:47,  7.80it/s]

 16%|█▋        | 163/1000 [00:21<01:51,  7.50it/s]

 16%|█▋        | 164/1000 [00:21<02:10,  6.39it/s]

 16%|█▋        | 165/1000 [00:21<02:27,  5.66it/s]

 17%|█▋        | 166/1000 [00:21<02:41,  5.18it/s]

 17%|█▋        | 167/1000 [00:21<02:24,  5.78it/s]

 17%|█▋        | 169/1000 [00:22<01:45,  7.84it/s]

 17%|█▋        | 171/1000 [00:22<01:56,  7.14it/s]

 17%|█▋        | 172/1000 [00:22<02:14,  6.13it/s]

 17%|█▋        | 173/1000 [00:22<02:13,  6.21it/s]

 17%|█▋        | 174/1000 [00:22<02:02,  6.74it/s]

 18%|█▊        | 176/1000 [00:23<01:37,  8.44it/s]

 18%|█▊        | 177/1000 [00:23<02:00,  6.80it/s]

 18%|█▊        | 179/1000 [00:23<01:38,  8.33it/s]

 18%|█▊        | 180/1000 [00:23<01:38,  8.32it/s]

 18%|█▊        | 181/1000 [00:23<02:03,  6.66it/s]

 18%|█▊        | 182/1000 [00:24<02:24,  5.67it/s]

 18%|█▊        | 183/1000 [00:24<02:22,  5.75it/s]

 18%|█▊        | 185/1000 [00:24<01:46,  7.67it/s]

 19%|█▊        | 186/1000 [00:24<01:43,  7.85it/s]

 19%|█▊        | 187/1000 [00:24<02:07,  6.37it/s]

 19%|█▉        | 189/1000 [00:24<01:40,  8.11it/s]

 19%|█▉        | 190/1000 [00:25<02:02,  6.62it/s]

 19%|█▉        | 192/1000 [00:25<02:04,  6.47it/s]

 19%|█▉        | 194/1000 [00:25<02:06,  6.37it/s]

 20%|█▉        | 196/1000 [00:25<01:43,  7.75it/s]

 20%|█▉        | 198/1000 [00:26<01:27,  9.19it/s]

 20%|██        | 200/1000 [00:26<01:15, 10.65it/s]

 20%|██        | 202/1000 [00:26<01:31,  8.75it/s]

 20%|██        | 204/1000 [00:26<01:32,  8.62it/s]

 21%|██        | 206/1000 [00:26<01:20,  9.91it/s]

 21%|██        | 208/1000 [00:27<01:33,  8.51it/s]

 21%|██        | 210/1000 [00:27<01:33,  8.48it/s]

 21%|██        | 212/1000 [00:27<01:21,  9.65it/s]

 21%|██▏       | 214/1000 [00:27<01:30,  8.72it/s]

 22%|██▏       | 216/1000 [00:28<01:25,  9.13it/s]

 22%|██▏       | 217/1000 [00:28<01:44,  7.48it/s]

 22%|██▏       | 219/1000 [00:28<01:28,  8.78it/s]

 22%|██▏       | 220/1000 [00:28<02:03,  6.30it/s]

 22%|██▏       | 221/1000 [00:28<02:03,  6.29it/s]

 22%|██▏       | 223/1000 [00:29<02:20,  5.54it/s]

 22%|██▏       | 224/1000 [00:29<02:08,  6.05it/s]

 22%|██▎       | 225/1000 [00:29<02:07,  6.09it/s]

 23%|██▎       | 226/1000 [00:29<02:22,  5.42it/s]

 23%|██▎       | 228/1000 [00:30<01:53,  6.82it/s]

 23%|██▎       | 229/1000 [00:30<02:10,  5.90it/s]

 23%|██▎       | 230/1000 [00:30<02:00,  6.36it/s]

 23%|██▎       | 232/1000 [00:30<01:37,  7.87it/s]

 23%|██▎       | 233/1000 [00:30<01:34,  8.08it/s]

 24%|██▎       | 235/1000 [00:30<01:17,  9.84it/s]

 24%|██▎       | 237/1000 [00:31<01:21,  9.41it/s]

 24%|██▍       | 239/1000 [00:31<01:25,  8.93it/s]

 24%|██▍       | 241/1000 [00:31<01:31,  8.32it/s]

 24%|██▍       | 242/1000 [00:32<02:06,  6.00it/s]

 24%|██▍       | 243/1000 [00:32<02:18,  5.46it/s]

 24%|██▍       | 245/1000 [00:32<01:53,  6.64it/s]

 25%|██▍       | 247/1000 [00:32<01:31,  8.25it/s]

 25%|██▍       | 248/1000 [00:32<01:49,  6.85it/s]

 25%|██▍       | 249/1000 [00:33<02:06,  5.95it/s]

 25%|██▌       | 250/1000 [00:33<02:08,  5.86it/s]

 25%|██▌       | 252/1000 [00:33<02:04,  6.02it/s]

 25%|██▌       | 253/1000 [00:33<02:10,  5.73it/s]

 26%|██▌       | 255/1000 [00:33<01:41,  7.36it/s]

 26%|██▌       | 256/1000 [00:34<01:36,  7.67it/s]

 26%|██▌       | 258/1000 [00:34<01:24,  8.73it/s]

 26%|██▌       | 260/1000 [00:34<01:36,  7.68it/s]

 26%|██▌       | 261/1000 [00:34<01:53,  6.51it/s]

 26%|██▌       | 262/1000 [00:34<01:54,  6.42it/s]

 26%|██▋       | 264/1000 [00:35<01:56,  6.33it/s]

 26%|██▋       | 265/1000 [00:35<01:51,  6.59it/s]

 27%|██▋       | 266/1000 [00:35<01:46,  6.90it/s]

 27%|██▋       | 268/1000 [00:35<01:37,  7.53it/s]

 27%|██▋       | 270/1000 [00:36<01:43,  7.02it/s]

 27%|██▋       | 271/1000 [00:36<02:14,  5.43it/s]

 27%|██▋       | 273/1000 [00:36<02:07,  5.69it/s]

 28%|██▊       | 275/1000 [00:36<01:48,  6.69it/s]

 28%|██▊       | 277/1000 [00:37<01:29,  8.06it/s]

 28%|██▊       | 278/1000 [00:37<01:46,  6.81it/s]

 28%|██▊       | 280/1000 [00:37<01:48,  6.61it/s]

 28%|██▊       | 282/1000 [00:37<01:29,  8.03it/s]

 28%|██▊       | 283/1000 [00:38<02:02,  5.85it/s]

 28%|██▊       | 284/1000 [00:38<02:05,  5.70it/s]

 29%|██▊       | 286/1000 [00:38<01:36,  7.42it/s]

 29%|██▉       | 288/1000 [00:38<01:21,  8.71it/s]

 29%|██▉       | 290/1000 [00:38<01:31,  7.75it/s]

 29%|██▉       | 291/1000 [00:39<01:41,  6.99it/s]

 29%|██▉       | 292/1000 [00:39<01:56,  6.07it/s]

 29%|██▉       | 294/1000 [00:39<01:38,  7.19it/s]

 30%|██▉       | 296/1000 [00:39<01:42,  6.88it/s]

 30%|██▉       | 298/1000 [00:40<01:25,  8.17it/s]

 30%|██▉       | 299/1000 [00:40<01:48,  6.45it/s]

 30%|███       | 300/1000 [00:40<01:42,  6.84it/s]

 30%|███       | 301/1000 [00:40<01:38,  7.11it/s]

 30%|███       | 303/1000 [00:40<01:19,  8.75it/s]

 30%|███       | 304/1000 [00:40<01:26,  8.07it/s]

 30%|███       | 305/1000 [00:41<01:25,  8.13it/s]

 31%|███       | 306/1000 [00:41<01:40,  6.93it/s]

 31%|███       | 307/1000 [00:41<01:42,  6.78it/s]

 31%|███       | 309/1000 [00:41<01:18,  8.79it/s]

 31%|███       | 311/1000 [00:41<01:07, 10.20it/s]

 31%|███▏      | 313/1000 [00:41<01:00, 11.26it/s]

 32%|███▏      | 315/1000 [00:42<01:06, 10.23it/s]

 32%|███▏      | 317/1000 [00:42<01:11,  9.58it/s]

 32%|███▏      | 319/1000 [00:42<01:34,  7.23it/s]

 32%|███▏      | 321/1000 [00:43<01:38,  6.88it/s]

 32%|███▏      | 322/1000 [00:43<01:45,  6.43it/s]

 32%|███▏      | 324/1000 [00:43<01:27,  7.74it/s]

 32%|███▎      | 325/1000 [00:43<01:58,  5.69it/s]

 33%|███▎      | 327/1000 [00:43<01:30,  7.40it/s]

 33%|███▎      | 328/1000 [00:44<01:33,  7.16it/s]

 33%|███▎      | 330/1000 [00:44<01:38,  6.78it/s]

 33%|███▎      | 332/1000 [00:44<01:41,  6.57it/s]

 33%|███▎      | 333/1000 [00:44<01:35,  6.95it/s]

 33%|███▎      | 334/1000 [00:44<01:44,  6.37it/s]

 34%|███▎      | 336/1000 [00:45<01:22,  8.04it/s]

 34%|███▍      | 338/1000 [00:45<01:15,  8.81it/s]

 34%|███▍      | 340/1000 [00:45<01:07,  9.82it/s]

 34%|███▍      | 342/1000 [00:45<01:01, 10.69it/s]

 34%|███▍      | 344/1000 [00:46<01:26,  7.55it/s]

 34%|███▍      | 345/1000 [00:46<01:25,  7.68it/s]

 35%|███▍      | 346/1000 [00:46<01:31,  7.18it/s]

 35%|███▍      | 347/1000 [00:46<01:28,  7.37it/s]

 35%|███▍      | 349/1000 [00:46<01:34,  6.88it/s]

 35%|███▌      | 350/1000 [00:47<01:49,  5.94it/s]

 35%|███▌      | 352/1000 [00:47<01:25,  7.62it/s]

 35%|███▌      | 354/1000 [00:47<01:25,  7.55it/s]

 36%|███▌      | 355/1000 [00:47<01:27,  7.35it/s]

 36%|███▌      | 357/1000 [00:47<01:11,  8.95it/s]

 36%|███▌      | 359/1000 [00:47<01:00, 10.57it/s]

 36%|███▌      | 361/1000 [00:48<01:07,  9.41it/s]

 36%|███▋      | 363/1000 [00:48<01:28,  7.19it/s]

 36%|███▋      | 364/1000 [00:48<01:41,  6.25it/s]

 36%|███▋      | 365/1000 [00:49<02:09,  4.90it/s]

 37%|███▋      | 367/1000 [00:49<01:58,  5.36it/s]

 37%|███▋      | 368/1000 [00:49<02:05,  5.02it/s]

 37%|███▋      | 369/1000 [00:49<01:52,  5.59it/s]

 37%|███▋      | 371/1000 [00:49<01:23,  7.54it/s]

 37%|███▋      | 372/1000 [00:50<01:21,  7.71it/s]

 37%|███▋      | 374/1000 [00:50<01:17,  8.07it/s]

 38%|███▊      | 375/1000 [00:50<01:40,  6.21it/s]

 38%|███▊      | 376/1000 [00:50<01:54,  5.47it/s]

 38%|███▊      | 378/1000 [00:51<01:29,  6.92it/s]

 38%|███▊      | 380/1000 [00:51<01:11,  8.72it/s]

 38%|███▊      | 382/1000 [00:51<01:18,  7.87it/s]

 38%|███▊      | 384/1000 [00:51<01:07,  9.18it/s]

 39%|███▊      | 386/1000 [00:51<01:06,  9.17it/s]

 39%|███▉      | 388/1000 [00:52<01:25,  7.14it/s]

 39%|███▉      | 390/1000 [00:52<01:19,  7.64it/s]

 39%|███▉      | 391/1000 [00:52<01:22,  7.36it/s]

 39%|███▉      | 393/1000 [00:52<01:09,  8.78it/s]

 40%|███▉      | 395/1000 [00:53<01:21,  7.47it/s]

 40%|███▉      | 397/1000 [00:53<01:08,  8.75it/s]

 40%|███▉      | 399/1000 [00:53<01:36,  6.22it/s]

 40%|████      | 400/1000 [00:54<01:45,  5.68it/s]

 40%|████      | 402/1000 [00:54<01:41,  5.92it/s]

 40%|████      | 404/1000 [00:54<01:22,  7.23it/s]

 41%|████      | 406/1000 [00:54<01:10,  8.48it/s]

 41%|████      | 408/1000 [00:55<01:32,  6.39it/s]

 41%|████      | 410/1000 [00:55<01:31,  6.44it/s]

 41%|████      | 411/1000 [00:55<01:41,  5.82it/s]

 41%|████      | 412/1000 [00:55<01:49,  5.35it/s]

 41%|████▏     | 414/1000 [00:56<01:23,  7.05it/s]

 42%|████▏     | 416/1000 [00:56<01:25,  6.81it/s]

 42%|████▏     | 418/1000 [00:56<01:10,  8.25it/s]

 42%|████▏     | 420/1000 [00:56<01:08,  8.45it/s]

 42%|████▏     | 421/1000 [00:56<01:17,  7.50it/s]

 42%|████▏     | 423/1000 [00:57<01:26,  6.69it/s]

 42%|████▏     | 424/1000 [00:57<01:37,  5.93it/s]

 42%|████▎     | 425/1000 [00:57<01:30,  6.37it/s]

 43%|████▎     | 427/1000 [00:57<01:12,  7.95it/s]

 43%|████▎     | 428/1000 [00:57<01:15,  7.54it/s]

 43%|████▎     | 429/1000 [00:58<01:12,  7.85it/s]

 43%|████▎     | 431/1000 [00:58<00:59,  9.56it/s]

 43%|████▎     | 433/1000 [00:58<00:51, 11.03it/s]

 44%|████▎     | 435/1000 [00:58<00:47, 11.81it/s]

 44%|████▎     | 437/1000 [00:58<00:53, 10.52it/s]

 44%|████▍     | 439/1000 [00:59<01:09,  8.09it/s]

 44%|████▍     | 441/1000 [00:59<01:00,  9.32it/s]

 44%|████▍     | 443/1000 [00:59<01:08,  8.09it/s]

 44%|████▍     | 444/1000 [00:59<01:16,  7.24it/s]

 45%|████▍     | 446/1000 [00:59<01:03,  8.72it/s]

 45%|████▍     | 448/1000 [01:00<01:13,  7.48it/s]

 45%|████▌     | 450/1000 [01:00<01:18,  7.02it/s]

 45%|████▌     | 451/1000 [01:00<01:28,  6.17it/s]

 45%|████▌     | 452/1000 [01:01<01:38,  5.58it/s]

 45%|████▌     | 454/1000 [01:01<01:16,  7.17it/s]

 46%|████▌     | 456/1000 [01:01<01:04,  8.49it/s]

 46%|████▌     | 457/1000 [01:01<01:09,  7.80it/s]

 46%|████▌     | 459/1000 [01:01<00:58,  9.25it/s]

 46%|████▌     | 461/1000 [01:01<00:49, 10.82it/s]

 46%|████▋     | 463/1000 [01:02<01:10,  7.62it/s]

 46%|████▋     | 465/1000 [01:02<01:19,  6.74it/s]

 47%|████▋     | 466/1000 [01:02<01:28,  6.01it/s]

 47%|████▋     | 467/1000 [01:03<01:50,  4.82it/s]

 47%|████▋     | 469/1000 [01:03<01:24,  6.30it/s]

 47%|████▋     | 471/1000 [01:03<01:07,  7.85it/s]

 47%|████▋     | 473/1000 [01:03<01:09,  7.57it/s]

 47%|████▋     | 474/1000 [01:04<01:20,  6.50it/s]

 48%|████▊     | 476/1000 [01:04<01:22,  6.39it/s]

 48%|████▊     | 477/1000 [01:04<01:35,  5.49it/s]

 48%|████▊     | 479/1000 [01:04<01:12,  7.15it/s]

 48%|████▊     | 480/1000 [01:04<01:19,  6.57it/s]

 48%|████▊     | 482/1000 [01:05<01:04,  8.04it/s]

 48%|████▊     | 484/1000 [01:05<01:10,  7.30it/s]

 48%|████▊     | 485/1000 [01:05<01:21,  6.30it/s]

 49%|████▊     | 486/1000 [01:05<01:21,  6.29it/s]

 49%|████▉     | 488/1000 [01:05<01:04,  7.98it/s]

 49%|████▉     | 489/1000 [01:06<01:17,  6.61it/s]

 49%|████▉     | 491/1000 [01:06<01:02,  8.21it/s]

 49%|████▉     | 492/1000 [01:06<01:01,  8.27it/s]

 49%|████▉     | 494/1000 [01:06<00:50,  9.99it/s]

 50%|████▉     | 496/1000 [01:06<00:59,  8.40it/s]

 50%|████▉     | 498/1000 [01:07<00:59,  8.43it/s]

 50%|████▉     | 499/1000 [01:07<01:15,  6.66it/s]

 50%|█████     | 500/1000 [01:07<01:24,  5.93it/s]

 50%|█████     | 502/1000 [01:07<01:05,  7.55it/s]

 50%|█████     | 503/1000 [01:08<01:13,  6.81it/s]

 50%|█████     | 505/1000 [01:08<01:15,  6.56it/s]

 51%|█████     | 506/1000 [01:08<01:24,  5.81it/s]

 51%|█████     | 508/1000 [01:08<01:06,  7.43it/s]

 51%|█████     | 510/1000 [01:08<00:55,  8.89it/s]

 51%|█████     | 512/1000 [01:09<00:49,  9.93it/s]

 51%|█████▏    | 514/1000 [01:09<01:06,  7.27it/s]

 52%|█████▏    | 515/1000 [01:09<01:04,  7.52it/s]

 52%|█████▏    | 516/1000 [01:09<01:08,  7.10it/s]

 52%|█████▏    | 518/1000 [01:09<00:59,  8.05it/s]

 52%|█████▏    | 519/1000 [01:10<01:15,  6.37it/s]

 52%|█████▏    | 521/1000 [01:10<00:59,  8.02it/s]

 52%|█████▏    | 522/1000 [01:10<01:11,  6.67it/s]

 52%|█████▏    | 523/1000 [01:10<01:22,  5.79it/s]

 52%|█████▏    | 524/1000 [01:11<01:25,  5.55it/s]

 53%|█████▎    | 526/1000 [01:11<01:12,  6.57it/s]

 53%|█████▎    | 528/1000 [01:11<01:12,  6.53it/s]

 53%|█████▎    | 529/1000 [01:11<01:13,  6.39it/s]

 53%|█████▎    | 531/1000 [01:11<00:57,  8.12it/s]

 53%|█████▎    | 533/1000 [01:12<00:48,  9.72it/s]

 54%|█████▎    | 535/1000 [01:12<01:09,  6.69it/s]

 54%|█████▎    | 536/1000 [01:12<01:12,  6.36it/s]

 54%|█████▎    | 537/1000 [01:12<01:21,  5.66it/s]

 54%|█████▍    | 539/1000 [01:13<01:17,  5.92it/s]

 54%|█████▍    | 540/1000 [01:13<01:19,  5.75it/s]

 54%|█████▍    | 541/1000 [01:13<01:27,  5.25it/s]

 54%|█████▍    | 543/1000 [01:13<01:05,  6.93it/s]

 55%|█████▍    | 545/1000 [01:14<01:04,  7.06it/s]

 55%|█████▍    | 546/1000 [01:14<01:09,  6.50it/s]

 55%|█████▍    | 547/1000 [01:14<01:19,  5.69it/s]

 55%|█████▍    | 549/1000 [01:14<01:16,  5.89it/s]

 55%|█████▌    | 551/1000 [01:15<00:59,  7.48it/s]

 55%|█████▌    | 552/1000 [01:15<01:01,  7.24it/s]

 55%|█████▌    | 553/1000 [01:15<01:12,  6.16it/s]

 55%|█████▌    | 554/1000 [01:15<01:15,  5.92it/s]

 56%|█████▌    | 556/1000 [01:15<00:57,  7.75it/s]

 56%|█████▌    | 557/1000 [01:15<01:03,  7.01it/s]

 56%|█████▌    | 559/1000 [01:16<00:49,  8.85it/s]

 56%|█████▌    | 561/1000 [01:16<00:43, 10.05it/s]

 56%|█████▋    | 563/1000 [01:16<00:52,  8.36it/s]

 56%|█████▋    | 565/1000 [01:16<00:54,  7.97it/s]

 57%|█████▋    | 566/1000 [01:17<01:04,  6.75it/s]

 57%|█████▋    | 568/1000 [01:17<01:05,  6.55it/s]

 57%|█████▋    | 569/1000 [01:17<01:06,  6.45it/s]

 57%|█████▋    | 571/1000 [01:17<01:06,  6.44it/s]

 57%|█████▋    | 572/1000 [01:18<01:07,  6.31it/s]

 57%|█████▋    | 574/1000 [01:18<01:07,  6.35it/s]

 58%|█████▊    | 576/1000 [01:18<00:54,  7.83it/s]

 58%|█████▊    | 577/1000 [01:18<01:13,  5.73it/s]

 58%|█████▊    | 578/1000 [01:19<01:20,  5.25it/s]

 58%|█████▊    | 580/1000 [01:19<01:00,  6.97it/s]

 58%|█████▊    | 582/1000 [01:19<00:48,  8.56it/s]

 58%|█████▊    | 584/1000 [01:19<00:54,  7.58it/s]

 58%|█████▊    | 585/1000 [01:19<01:00,  6.91it/s]

 59%|█████▊    | 587/1000 [01:20<00:57,  7.16it/s]

 59%|█████▉    | 589/1000 [01:20<00:48,  8.53it/s]

 59%|█████▉    | 590/1000 [01:20<01:00,  6.75it/s]

 59%|█████▉    | 592/1000 [01:20<00:51,  7.97it/s]

 59%|█████▉    | 593/1000 [01:21<01:00,  6.70it/s]

 60%|█████▉    | 595/1000 [01:21<00:48,  8.29it/s]

 60%|█████▉    | 596/1000 [01:21<00:59,  6.82it/s]

 60%|█████▉    | 597/1000 [01:21<01:00,  6.61it/s]

 60%|█████▉    | 599/1000 [01:21<01:02,  6.44it/s]

 60%|██████    | 601/1000 [01:22<01:02,  6.38it/s]

 60%|██████    | 602/1000 [01:22<00:59,  6.70it/s]

 60%|██████    | 604/1000 [01:22<01:09,  5.67it/s]

 61%|██████    | 606/1000 [01:22<00:55,  7.09it/s]

 61%|██████    | 608/1000 [01:23<00:49,  7.86it/s]

 61%|██████    | 610/1000 [01:23<00:45,  8.48it/s]

 61%|██████    | 612/1000 [01:23<00:39,  9.73it/s]

 61%|██████▏   | 614/1000 [01:23<00:35, 10.79it/s]

 62%|██████▏   | 616/1000 [01:24<00:50,  7.60it/s]

 62%|██████▏   | 617/1000 [01:24<00:49,  7.75it/s]

 62%|██████▏   | 619/1000 [01:24<00:41,  9.09it/s]

 62%|██████▏   | 621/1000 [01:24<00:47,  8.02it/s]

 62%|██████▏   | 623/1000 [01:24<00:46,  8.19it/s]

 62%|██████▎   | 625/1000 [01:25<00:50,  7.45it/s]

 63%|██████▎   | 627/1000 [01:25<00:43,  8.63it/s]

 63%|██████▎   | 628/1000 [01:25<00:51,  7.19it/s]

 63%|██████▎   | 629/1000 [01:25<00:59,  6.21it/s]

 63%|██████▎   | 631/1000 [01:25<00:47,  7.84it/s]

 63%|██████▎   | 633/1000 [01:26<00:39,  9.32it/s]

 64%|██████▎   | 635/1000 [01:26<00:54,  6.69it/s]

 64%|██████▎   | 636/1000 [01:26<00:51,  7.04it/s]

 64%|██████▍   | 638/1000 [01:26<00:45,  7.92it/s]

 64%|██████▍   | 640/1000 [01:27<00:39,  9.15it/s]

 64%|██████▍   | 642/1000 [01:27<00:44,  7.96it/s]

 64%|██████▍   | 643/1000 [01:27<00:47,  7.59it/s]

 64%|██████▍   | 645/1000 [01:27<00:49,  7.11it/s]

 65%|██████▍   | 647/1000 [01:28<00:46,  7.59it/s]

 65%|██████▍   | 648/1000 [01:28<00:53,  6.53it/s]

 65%|██████▌   | 650/1000 [01:28<00:53,  6.57it/s]

 65%|██████▌   | 652/1000 [01:28<00:54,  6.33it/s]

 65%|██████▌   | 654/1000 [01:29<00:44,  7.72it/s]

 66%|██████▌   | 656/1000 [01:29<00:38,  8.93it/s]

 66%|██████▌   | 658/1000 [01:29<00:42,  8.13it/s]

 66%|██████▌   | 659/1000 [01:29<00:56,  6.01it/s]

 66%|██████▌   | 661/1000 [01:29<00:44,  7.58it/s]

 66%|██████▌   | 662/1000 [01:30<00:52,  6.48it/s]

 66%|██████▋   | 664/1000 [01:30<00:58,  5.77it/s]

 66%|██████▋   | 665/1000 [01:30<01:02,  5.33it/s]

 67%|██████▋   | 667/1000 [01:31<00:59,  5.61it/s]

 67%|██████▋   | 668/1000 [01:31<01:03,  5.19it/s]

 67%|██████▋   | 669/1000 [01:31<00:58,  5.70it/s]

 67%|██████▋   | 671/1000 [01:31<00:55,  5.89it/s]

 67%|██████▋   | 673/1000 [01:32<00:49,  6.64it/s]

 68%|██████▊   | 675/1000 [01:32<00:44,  7.27it/s]

 68%|██████▊   | 677/1000 [01:32<00:37,  8.65it/s]

 68%|██████▊   | 679/1000 [01:32<00:33,  9.69it/s]

 68%|██████▊   | 681/1000 [01:32<00:29, 10.97it/s]

 68%|██████▊   | 683/1000 [01:33<00:35,  8.93it/s]

 68%|██████▊   | 685/1000 [01:33<00:31,  9.89it/s]

 69%|██████▊   | 687/1000 [01:33<00:45,  6.86it/s]

 69%|██████▉   | 688/1000 [01:33<00:43,  7.16it/s]

 69%|██████▉   | 690/1000 [01:34<00:45,  6.80it/s]

 69%|██████▉   | 692/1000 [01:34<00:39,  7.84it/s]

 69%|██████▉   | 694/1000 [01:34<00:42,  7.26it/s]

 70%|██████▉   | 695/1000 [01:34<00:41,  7.42it/s]

 70%|██████▉   | 696/1000 [01:35<00:47,  6.34it/s]

 70%|██████▉   | 698/1000 [01:35<00:43,  6.95it/s]

 70%|██████▉   | 699/1000 [01:35<00:49,  6.04it/s]

 70%|███████   | 701/1000 [01:35<00:39,  7.55it/s]

 70%|███████   | 702/1000 [01:36<00:53,  5.59it/s]

 70%|███████   | 704/1000 [01:36<00:41,  7.20it/s]

 70%|███████   | 705/1000 [01:36<00:54,  5.41it/s]

 71%|███████   | 707/1000 [01:36<00:41,  7.01it/s]

 71%|███████   | 709/1000 [01:36<00:38,  7.61it/s]

 71%|███████   | 710/1000 [01:37<00:44,  6.49it/s]

 71%|███████   | 712/1000 [01:37<00:37,  7.70it/s]

 71%|███████▏  | 713/1000 [01:37<00:36,  7.85it/s]

 72%|███████▏  | 715/1000 [01:37<00:30,  9.36it/s]

 72%|███████▏  | 717/1000 [01:37<00:35,  8.06it/s]

 72%|███████▏  | 718/1000 [01:38<00:41,  6.80it/s]

 72%|███████▏  | 719/1000 [01:38<00:47,  5.94it/s]

 72%|███████▏  | 720/1000 [01:38<00:43,  6.47it/s]

 72%|███████▏  | 722/1000 [01:38<00:34,  8.15it/s]

 72%|███████▏  | 723/1000 [01:38<00:33,  8.23it/s]

 72%|███████▏  | 724/1000 [01:38<00:33,  8.25it/s]

 72%|███████▎  | 725/1000 [01:39<00:33,  8.31it/s]

 73%|███████▎  | 727/1000 [01:39<00:26, 10.14it/s]

 73%|███████▎  | 729/1000 [01:39<00:23, 11.62it/s]

 73%|███████▎  | 731/1000 [01:39<00:32,  8.32it/s]

 73%|███████▎  | 733/1000 [01:39<00:28,  9.52it/s]

 74%|███████▎  | 735/1000 [01:39<00:26,  9.89it/s]

 74%|███████▎  | 737/1000 [01:40<00:27,  9.53it/s]

 74%|███████▍  | 739/1000 [01:40<00:26,  9.77it/s]

 74%|███████▍  | 741/1000 [01:40<00:31,  8.30it/s]

 74%|███████▍  | 743/1000 [01:40<00:30,  8.35it/s]

 74%|███████▍  | 745/1000 [01:41<00:26,  9.60it/s]

 75%|███████▍  | 747/1000 [01:41<00:24, 10.42it/s]

 75%|███████▍  | 749/1000 [01:41<00:29,  8.64it/s]

 75%|███████▌  | 750/1000 [01:41<00:32,  7.68it/s]

 75%|███████▌  | 751/1000 [01:42<00:40,  6.16it/s]

 75%|███████▌  | 753/1000 [01:42<00:34,  7.23it/s]

 75%|███████▌  | 754/1000 [01:42<00:39,  6.23it/s]

 76%|███████▌  | 756/1000 [01:42<00:38,  6.41it/s]

 76%|███████▌  | 758/1000 [01:42<00:31,  7.61it/s]

 76%|███████▌  | 759/1000 [01:43<00:32,  7.32it/s]

 76%|███████▌  | 761/1000 [01:43<00:27,  8.72it/s]

 76%|███████▋  | 763/1000 [01:43<00:30,  7.66it/s]

 76%|███████▋  | 764/1000 [01:43<00:35,  6.61it/s]

 77%|███████▋  | 766/1000 [01:44<00:36,  6.46it/s]

 77%|███████▋  | 768/1000 [01:44<00:29,  7.79it/s]

 77%|███████▋  | 769/1000 [01:44<00:34,  6.64it/s]

 77%|███████▋  | 770/1000 [01:44<00:35,  6.56it/s]

 77%|███████▋  | 772/1000 [01:44<00:28,  8.12it/s]

 77%|███████▋  | 773/1000 [01:45<00:35,  6.38it/s]

 77%|███████▋  | 774/1000 [01:45<00:33,  6.79it/s]

 78%|███████▊  | 776/1000 [01:45<00:28,  7.91it/s]

 78%|███████▊  | 778/1000 [01:45<00:23,  9.59it/s]

 78%|███████▊  | 780/1000 [01:46<00:31,  6.94it/s]

 78%|███████▊  | 782/1000 [01:46<00:26,  8.36it/s]

 78%|███████▊  | 784/1000 [01:46<00:30,  7.16it/s]

 79%|███████▊  | 786/1000 [01:46<00:28,  7.53it/s]

 79%|███████▉  | 788/1000 [01:46<00:25,  8.36it/s]

 79%|███████▉  | 790/1000 [01:47<00:23,  8.94it/s]

 79%|███████▉  | 791/1000 [01:47<00:25,  8.19it/s]

 79%|███████▉  | 792/1000 [01:47<00:27,  7.70it/s]

 79%|███████▉  | 793/1000 [01:47<00:26,  7.94it/s]

 80%|███████▉  | 795/1000 [01:47<00:28,  7.17it/s]

 80%|███████▉  | 797/1000 [01:48<00:29,  6.85it/s]

 80%|███████▉  | 798/1000 [01:48<00:33,  6.01it/s]

 80%|████████  | 800/1000 [01:48<00:29,  6.71it/s]

 80%|████████  | 802/1000 [01:48<00:25,  7.64it/s]

 80%|████████  | 804/1000 [01:49<00:25,  7.83it/s]

 81%|████████  | 806/1000 [01:49<00:21,  9.17it/s]

 81%|████████  | 807/1000 [01:49<00:21,  8.97it/s]

 81%|████████  | 809/1000 [01:49<00:18, 10.21it/s]

 81%|████████  | 811/1000 [01:49<00:16, 11.22it/s]

 81%|████████▏ | 813/1000 [01:49<00:20,  9.04it/s]

 82%|████████▏ | 815/1000 [01:50<00:19,  9.30it/s]

 82%|████████▏ | 817/1000 [01:50<00:22,  8.14it/s]

 82%|████████▏ | 819/1000 [01:50<00:19,  9.19it/s]

 82%|████████▏ | 821/1000 [01:50<00:22,  8.03it/s]

 82%|████████▏ | 823/1000 [01:51<00:22,  7.82it/s]

 82%|████████▏ | 824/1000 [01:51<00:26,  6.75it/s]

 82%|████████▎ | 825/1000 [01:51<00:25,  6.99it/s]

 83%|████████▎ | 826/1000 [01:51<00:30,  5.79it/s]

 83%|████████▎ | 828/1000 [01:52<00:32,  5.24it/s]

 83%|████████▎ | 829/1000 [01:52<00:29,  5.73it/s]

 83%|████████▎ | 831/1000 [01:52<00:24,  7.00it/s]

 83%|████████▎ | 832/1000 [01:52<00:29,  5.73it/s]

 83%|████████▎ | 833/1000 [01:53<00:26,  6.21it/s]

 83%|████████▎ | 834/1000 [01:53<00:27,  6.00it/s]

 84%|████████▎ | 835/1000 [01:53<00:25,  6.52it/s]

 84%|████████▎ | 836/1000 [01:53<00:26,  6.10it/s]

 84%|████████▍ | 838/1000 [01:53<00:21,  7.44it/s]

 84%|████████▍ | 840/1000 [01:54<00:24,  6.62it/s]

 84%|████████▍ | 842/1000 [01:54<00:19,  8.15it/s]

 84%|████████▍ | 844/1000 [01:54<00:24,  6.41it/s]

 84%|████████▍ | 845/1000 [01:54<00:26,  5.77it/s]

 85%|████████▍ | 847/1000 [01:55<00:24,  6.25it/s]

 85%|████████▍ | 849/1000 [01:55<00:20,  7.55it/s]

 85%|████████▌ | 850/1000 [01:55<00:23,  6.49it/s]

 85%|████████▌ | 851/1000 [01:55<00:21,  6.87it/s]

 85%|████████▌ | 853/1000 [01:55<00:17,  8.47it/s]

 86%|████████▌ | 855/1000 [01:55<00:14, 10.05it/s]

 86%|████████▌ | 857/1000 [01:56<00:14, 10.20it/s]

 86%|████████▌ | 859/1000 [01:56<00:16,  8.52it/s]

 86%|████████▌ | 861/1000 [01:56<00:14,  9.76it/s]

 86%|████████▋ | 863/1000 [01:56<00:12, 10.61it/s]

 86%|████████▋ | 865/1000 [01:56<00:11, 11.69it/s]

 87%|████████▋ | 867/1000 [01:57<00:14,  9.33it/s]

 87%|████████▋ | 869/1000 [01:57<00:12, 10.28it/s]

 87%|████████▋ | 871/1000 [01:57<00:11, 11.30it/s]

 87%|████████▋ | 873/1000 [01:57<00:16,  7.77it/s]

 88%|████████▊ | 875/1000 [01:58<00:16,  7.63it/s]

 88%|████████▊ | 877/1000 [01:58<00:13,  8.87it/s]

 88%|████████▊ | 879/1000 [01:58<00:17,  6.86it/s]

 88%|████████▊ | 881/1000 [01:59<00:15,  7.60it/s]

 88%|████████▊ | 882/1000 [01:59<00:18,  6.54it/s]

 88%|████████▊ | 884/1000 [01:59<00:14,  7.96it/s]

 89%|████████▊ | 886/1000 [01:59<00:12,  9.17it/s]

 89%|████████▉ | 888/1000 [01:59<00:10, 10.35it/s]

 89%|████████▉ | 890/1000 [01:59<00:11,  9.76it/s]

 89%|████████▉ | 892/1000 [02:00<00:10, 10.75it/s]

 89%|████████▉ | 894/1000 [02:00<00:13,  7.61it/s]

 90%|████████▉ | 896/1000 [02:00<00:11,  8.84it/s]

 90%|████████▉ | 898/1000 [02:01<00:15,  6.52it/s]

 90%|█████████ | 900/1000 [02:01<00:13,  7.68it/s]

 90%|█████████ | 902/1000 [02:01<00:12,  7.85it/s]

 90%|█████████ | 904/1000 [02:01<00:10,  9.05it/s]

 91%|█████████ | 906/1000 [02:02<00:13,  7.04it/s]

 91%|█████████ | 908/1000 [02:02<00:11,  8.31it/s]

 91%|█████████ | 910/1000 [02:02<00:11,  7.58it/s]

 91%|█████████ | 912/1000 [02:02<00:10,  8.78it/s]

 91%|█████████▏| 914/1000 [02:03<00:11,  7.38it/s]

 92%|█████████▏| 916/1000 [02:03<00:11,  7.07it/s]

 92%|█████████▏| 917/1000 [02:03<00:11,  7.36it/s]

 92%|█████████▏| 918/1000 [02:03<00:14,  5.59it/s]

 92%|█████████▏| 919/1000 [02:04<00:14,  5.71it/s]

 92%|█████████▏| 921/1000 [02:04<00:14,  5.58it/s]

 92%|█████████▏| 922/1000 [02:04<00:13,  5.94it/s]

 92%|█████████▏| 924/1000 [02:04<00:10,  7.16it/s]

 93%|█████████▎| 926/1000 [02:04<00:08,  8.64it/s]

 93%|█████████▎| 927/1000 [02:04<00:09,  8.09it/s]

 93%|█████████▎| 928/1000 [02:05<00:10,  6.65it/s]

 93%|█████████▎| 930/1000 [02:05<00:10,  6.48it/s]

 93%|█████████▎| 931/1000 [02:05<00:10,  6.82it/s]

 93%|█████████▎| 933/1000 [02:06<00:10,  6.60it/s]

 93%|█████████▎| 934/1000 [02:06<00:10,  6.17it/s]

 94%|█████████▎| 936/1000 [02:06<00:08,  7.31it/s]

 94%|█████████▍| 938/1000 [02:06<00:07,  8.83it/s]

 94%|█████████▍| 939/1000 [02:06<00:07,  8.03it/s]

 94%|█████████▍| 940/1000 [02:06<00:07,  8.12it/s]

 94%|█████████▍| 942/1000 [02:07<00:09,  6.34it/s]

 94%|█████████▍| 944/1000 [02:07<00:07,  7.09it/s]

 95%|█████████▍| 946/1000 [02:07<00:06,  8.40it/s]

 95%|█████████▍| 948/1000 [02:07<00:05,  9.57it/s]

 95%|█████████▌| 950/1000 [02:08<00:05,  8.76it/s]

 95%|█████████▌| 952/1000 [02:08<00:06,  7.38it/s]

 95%|█████████▌| 954/1000 [02:08<00:07,  6.14it/s]

 96%|█████████▌| 956/1000 [02:08<00:05,  7.38it/s]

 96%|█████████▌| 957/1000 [02:09<00:06,  6.39it/s]

 96%|█████████▌| 959/1000 [02:09<00:07,  5.77it/s]

 96%|█████████▌| 961/1000 [02:09<00:05,  6.81it/s]

 96%|█████████▌| 962/1000 [02:10<00:06,  6.04it/s]

 96%|█████████▋| 964/1000 [02:10<00:04,  7.49it/s]

 96%|█████████▋| 965/1000 [02:10<00:05,  6.44it/s]

 97%|█████████▋| 966/1000 [02:10<00:05,  6.33it/s]

 97%|█████████▋| 968/1000 [02:10<00:03,  8.01it/s]

 97%|█████████▋| 970/1000 [02:10<00:03,  9.41it/s]

 97%|█████████▋| 972/1000 [02:11<00:03,  8.01it/s]

 97%|█████████▋| 974/1000 [02:11<00:02,  9.19it/s]

 98%|█████████▊| 976/1000 [02:11<00:02,  9.78it/s]

 98%|█████████▊| 978/1000 [02:11<00:02, 10.80it/s]

 98%|█████████▊| 980/1000 [02:12<00:02,  8.42it/s]

 98%|█████████▊| 981/1000 [02:12<00:02,  7.06it/s]

 98%|█████████▊| 982/1000 [02:12<00:03,  5.44it/s]

 98%|█████████▊| 984/1000 [02:12<00:02,  6.93it/s]

 99%|█████████▊| 986/1000 [02:12<00:01,  8.36it/s]

 99%|█████████▉| 988/1000 [02:13<00:01,  6.73it/s]

 99%|█████████▉| 989/1000 [02:13<00:01,  5.99it/s]

 99%|█████████▉| 991/1000 [02:13<00:01,  6.14it/s]

 99%|█████████▉| 992/1000 [02:14<00:01,  4.97it/s]

 99%|█████████▉| 994/1000 [02:14<00:00,  6.54it/s]

100%|█████████▉| 995/1000 [02:14<00:00,  5.53it/s]

100%|█████████▉| 997/1000 [02:14<00:00,  7.05it/s]

100%|█████████▉| 999/1000 [02:15<00:00,  6.76it/s]

100%|██████████| 1000/1000 [02:15<00:00,  6.66it/s]
                                                      

                                                   
{'eval_loss': '0.7795', 'eval_runtime': '135.5', 'eval_samples_per_second': '7.379', 'eval_steps_per_second': '7.379', 'epoch': '0.4966', 'num_input_tokens_seen': 6050856}

 50%|████▉     | 900/1813 [1:40:38<1:46:52,  7.02s/it]

100%|██████████| 1000/1000 [02:15<00:00,  6.66it/s]

                                                   
 50%|████▉     | 901/1813 [1:40:44<12:01:10, 47.45s/it]
 50%|████▉     | 902/1813 [1:40:50<8:50:53, 34.97s/it] 
 50%|████▉     | 903/1813 [1:40:56<6:38:55, 26.30s/it]
 50%|████▉     | 904/1813 [1:41:02<5:06:08, 20.21s/it]
 50%|████▉     | 905/1813 [1:41:10<4:10:06, 16.53s/it]
 50%|████▉     | 906/1813 [1:41:15<3:19:28, 13.20s/it]
 50%|█████     | 907/1813 [1:41:20<2:40:21, 10.62s/it]
 50%|█████     | 908/1813 [1:41:26<2:17:46,  9.13s/it]
 50%|█████     | 909/1813 [1:41:32<2:06:31,  8.40s/it]
 50%|█████     | 910/1813 [1:41:39<1:57:12,  7.79s/it]
                                                      
{'loss': '0.9172', 'grad_norm': '1.044', 'learning_rate': '5.683e-05', 'epoch': '0.5021', 'num_input_tokens_seen': 6115160, 'train_runtime': '6099', 'train_tokens_per_second': '1003'}

 50%|█████     | 910/1813 [1:41:39<1:57:12,  7.79s/it]
 50%|█████     | 911/1813 [1:41:44<1:47:27,  7.15s/it]
 50%|█████     | 912/1813 [1:41:50<1:40:35,  6.70s/it]
 50%|█████     | 913/1813 [1:41:55<1:34:12,  6.28s/it]
 50%|█████     | 914/1813 [1:42:00<1:28:26,  5.90s/it]
 50%|█████     | 915/1813 [1:42:08<1:36:14,  6.43s/it]
 51%|█████     | 916/1813 [1:42:15<1:39:02,  6.63s/it]
 51%|█████     | 917/1813 [1:42:22<1:40:17,  6.72s/it]
 51%|█████     | 918/1813 [1:42:28<1:35:54,  6.43s/it]
 51%|█████     | 919/1813 [1:42:34<1:35:38,  6.42s/it]
 51%|█████     | 920/1813 [1:42:40<1:31:17,  6.13s/it]
                                                      
{'loss': '0.9485', 'grad_norm': '0.7058', 'learning_rate': '5.589e-05', 'epoch': '0.5076', 'num_input_tokens_seen': 6178904, 'train_runtime': '6160', 'train_tokens_per_second': '1003'}

 51%|█████     | 920/1813 [1:42:40<1:31:17,  6.13s/it]
 51%|█████     | 921/1813 [1:42:45<1:29:00,  5.99s/it]
 51%|█████     | 922/1813 [1:42:51<1:27:18,  5.88s/it]
 51%|█████     | 923/1813 [1:42:57<1:28:15,  5.95s/it]
 51%|█████     | 924/1813 [1:43:04<1:32:52,  6.27s/it]
 51%|█████     | 925/1813 [1:43:10<1:32:04,  6.22s/it]
 51%|█████     | 926/1813 [1:43:17<1:34:19,  6.38s/it]
 51%|█████     | 927/1813 [1:43:23<1:32:24,  6.26s/it]
 51%|█████     | 928/1813 [1:43:28<1:29:19,  6.06s/it]
 51%|█████     | 929/1813 [1:43:34<1:28:49,  6.03s/it]
 51%|█████▏    | 930/1813 [1:43:41<1:32:25,  6.28s/it]
                                                      
{'loss': '0.9088', 'grad_norm': '1.081', 'learning_rate': '5.495e-05', 'epoch': '0.5131', 'num_input_tokens_seen': 6244360, 'train_runtime': '6222', 'train_tokens_per_second': '1004'}

 51%|█████▏    | 930/1813 [1:43:41<1:32:25,  6.28s/it]
 51%|█████▏    | 931/1813 [1:43:48<1:34:52,  6.45s/it]
 51%|█████▏    | 932/1813 [1:43:53<1:30:16,  6.15s/it]
 51%|█████▏    | 933/1813 [1:43:59<1:28:43,  6.05s/it]
 52%|█████▏    | 934/1813 [1:44:06<1:30:58,  6.21s/it]
 52%|█████▏    | 935/1813 [1:44:15<1:42:25,  7.00s/it]
 52%|█████▏    | 936/1813 [1:44:21<1:39:44,  6.82s/it]
 52%|█████▏    | 937/1813 [1:44:27<1:36:23,  6.60s/it]
 52%|█████▏    | 938/1813 [1:44:34<1:38:16,  6.74s/it]
 52%|█████▏    | 939/1813 [1:44:40<1:34:11,  6.47s/it]
 52%|█████▏    | 940/1813 [1:44:47<1:36:34,  6.64s/it]
                                                      
{'loss': '0.893', 'grad_norm': '0.9855', 'learning_rate': '5.401e-05', 'epoch': '0.5186', 'num_input_tokens_seen': 6318968, 'train_runtime': '6288', 'train_tokens_per_second': '1005'}

 52%|█████▏    | 940/1813 [1:44:47<1:36:34,  6.64s/it]
 52%|█████▏    | 941/1813 [1:44:52<1:29:42,  6.17s/it]
 52%|█████▏    | 942/1813 [1:44:58<1:26:41,  5.97s/it]
 52%|█████▏    | 943/1813 [1:45:03<1:24:41,  5.84s/it]
 52%|█████▏    | 944/1813 [1:45:09<1:24:57,  5.87s/it]
 52%|█████▏    | 945/1813 [1:45:15<1:23:15,  5.76s/it]
 52%|█████▏    | 946/1813 [1:45:21<1:25:38,  5.93s/it]
 52%|█████▏    | 947/1813 [1:45:27<1:26:17,  5.98s/it]
 52%|█████▏    | 948/1813 [1:45:33<1:27:24,  6.06s/it]
 52%|█████▏    | 949/1813 [1:45:38<1:23:03,  5.77s/it]
 52%|█████▏    | 950/1813 [1:45:45<1:25:24,  5.94s/it]
                                                      
{'loss': '0.9497', 'grad_norm': '1.029', 'learning_rate': '5.307e-05', 'epoch': '0.5241', 'num_input_tokens_seen': 6379704, 'train_runtime': '6345', 'train_tokens_per_second': '1005'}

 52%|█████▏    | 950/1813 [1:45:45<1:25:24,  5.94s/it]
 52%|█████▏    | 951/1813 [1:45:50<1:22:57,  5.77s/it]
 53%|█████▎    | 952/1813 [1:45:56<1:21:48,  5.70s/it]
 53%|█████▎    | 953/1813 [1:46:02<1:22:43,  5.77s/it]
 53%|█████▎    | 954/1813 [1:46:07<1:22:04,  5.73s/it]
 53%|█████▎    | 955/1813 [1:46:13<1:21:48,  5.72s/it]
 53%|█████▎    | 956/1813 [1:46:19<1:21:08,  5.68s/it]
 53%|█████▎    | 957/1813 [1:46:24<1:20:27,  5.64s/it]
 53%|█████▎    | 958/1813 [1:46:29<1:15:36,  5.31s/it]
 53%|█████▎    | 959/1813 [1:46:34<1:17:48,  5.47s/it]
 53%|█████▎    | 960/1813 [1:46:43<1:29:08,  6.27s/it]
                                                      
{'loss': '0.9562', 'grad_norm': '0.655', 'learning_rate': '5.212e-05', 'epoch': '0.5297', 'num_input_tokens_seen': 6441656, 'train_runtime': '6403', 'train_tokens_per_second': '1006'}

 53%|█████▎    | 960/1813 [1:46:43<1:29:08,  6.27s/it]
 53%|█████▎    | 961/1813 [1:46:49<1:30:06,  6.35s/it]
 53%|█████▎    | 962/1813 [1:46:57<1:36:05,  6.77s/it]
 53%|█████▎    | 963/1813 [1:47:04<1:36:10,  6.79s/it]
 53%|█████▎    | 964/1813 [1:47:10<1:31:46,  6.49s/it]
 53%|█████▎    | 965/1813 [1:47:15<1:29:02,  6.30s/it]
 53%|█████▎    | 966/1813 [1:47:23<1:34:05,  6.67s/it]
 53%|█████▎    | 967/1813 [1:47:30<1:37:06,  6.89s/it]
 53%|█████▎    | 968/1813 [1:47:36<1:31:07,  6.47s/it]
 53%|█████▎    | 969/1813 [1:47:42<1:28:49,  6.31s/it]
 54%|█████▎    | 970/1813 [1:47:46<1:21:48,  5.82s/it]
                                                      
{'loss': '1.004', 'grad_norm': '0.9707', 'learning_rate': '5.118e-05', 'epoch': '0.5352', 'num_input_tokens_seen': 6512320, 'train_runtime': '6467', 'train_tokens_per_second': '1007'}

 54%|█████▎    | 970/1813 [1:47:46<1:21:48,  5.82s/it]
 54%|█████▎    | 971/1813 [1:47:53<1:25:46,  6.11s/it]
 54%|█████▎    | 972/1813 [1:48:00<1:26:52,  6.20s/it]
 54%|█████▎    | 973/1813 [1:48:06<1:25:46,  6.13s/it]
 54%|█████▎    | 974/1813 [1:48:14<1:35:28,  6.83s/it]
 54%|█████▍    | 975/1813 [1:48:20<1:33:16,  6.68s/it]
 54%|█████▍    | 976/1813 [1:48:26<1:28:52,  6.37s/it]
 54%|█████▍    | 977/1813 [1:48:34<1:34:55,  6.81s/it]
 54%|█████▍    | 978/1813 [1:48:40<1:33:13,  6.70s/it]
 54%|█████▍    | 979/1813 [1:48:48<1:35:21,  6.86s/it]
 54%|█████▍    | 980/1813 [1:48:54<1:34:06,  6.78s/it]
                                                      
{'loss': '0.9326', 'grad_norm': '1.548', 'learning_rate': '5.024e-05', 'epoch': '0.5407', 'num_input_tokens_seen': 6586672, 'train_runtime': '6535', 'train_tokens_per_second': '1008'}

 54%|█████▍    | 980/1813 [1:48:54<1:34:06,  6.78s/it]
 54%|█████▍    | 981/1813 [1:49:01<1:32:42,  6.69s/it]
 54%|█████▍    | 982/1813 [1:49:06<1:26:01,  6.21s/it]
 54%|█████▍    | 983/1813 [1:49:11<1:21:53,  5.92s/it]
 54%|█████▍    | 984/1813 [1:49:16<1:19:29,  5.75s/it]
 54%|█████▍    | 985/1813 [1:49:23<1:22:56,  6.01s/it]
 54%|█████▍    | 986/1813 [1:49:31<1:29:23,  6.49s/it]
 54%|█████▍    | 987/1813 [1:49:37<1:28:05,  6.40s/it]
 54%|█████▍    | 988/1813 [1:49:42<1:24:27,  6.14s/it]
 55%|█████▍    | 989/1813 [1:49:47<1:19:33,  5.79s/it]
 55%|█████▍    | 990/1813 [1:49:55<1:28:15,  6.43s/it]
                                                      
{'loss': '0.8963', 'grad_norm': '0.9012', 'learning_rate': '4.929e-05', 'epoch': '0.5462', 'num_input_tokens_seen': 6653096, 'train_runtime': '6596', 'train_tokens_per_second': '1009'}

 55%|█████▍    | 990/1813 [1:49:55<1:28:15,  6.43s/it]
 55%|█████▍    | 991/1813 [1:50:00<1:22:47,  6.04s/it]
 55%|█████▍    | 992/1813 [1:50:08<1:27:43,  6.41s/it]
 55%|█████▍    | 993/1813 [1:50:13<1:25:01,  6.22s/it]
 55%|█████▍    | 994/1813 [1:50:22<1:33:28,  6.85s/it]
 55%|█████▍    | 995/1813 [1:50:27<1:28:50,  6.52s/it]
 55%|█████▍    | 996/1813 [1:50:34<1:27:22,  6.42s/it]
 55%|█████▍    | 997/1813 [1:50:39<1:25:08,  6.26s/it]
 55%|█████▌    | 998/1813 [1:50:45<1:20:35,  5.93s/it]
 55%|█████▌    | 999/1813 [1:50:50<1:19:01,  5.82s/it]
 55%|█████▌    | 1000/1813 [1:50:55<1:16:29,  5.65s/it]
                                                       
{'loss': '1.002', 'grad_norm': '0.8292', 'learning_rate': '4.835e-05', 'epoch': '0.5517', 'num_input_tokens_seen': 6716784, 'train_runtime': '6656', 'train_tokens_per_second': '1009'}

 55%|█████▌    | 1000/1813 [1:50:55<1:16:29,  5.65s/it]
 55%|█████▌    | 1001/1813 [1:51:02<1:19:47,  5.90s/it]
 55%|█████▌    | 1002/1813 [1:51:08<1:21:05,  6.00s/it]
 55%|█████▌    | 1003/1813 [1:51:15<1:25:08,  6.31s/it]
 55%|█████▌    | 1004/1813 [1:51:21<1:21:06,  6.01s/it]
 55%|█████▌    | 1005/1813 [1:51:28<1:25:35,  6.36s/it]
 55%|█████▌    | 1006/1813 [1:51:34<1:26:55,  6.46s/it]
 56%|█████▌    | 1007/1813 [1:51:40<1:24:38,  6.30s/it]
 56%|█████▌    | 1008/1813 [1:51:46<1:23:37,  6.23s/it]
 56%|█████▌    | 1009/1813 [1:51:53<1:23:45,  6.25s/it]
 56%|█████▌    | 1010/1813 [1:51:58<1:20:59,  6.05s/it]
                                                       
{'loss': '0.9426', 'grad_norm': '1.046', 'learning_rate': '4.74e-05', 'epoch': '0.5572', 'num_input_tokens_seen': 6783768, 'train_runtime': '6719', 'train_tokens_per_second': '1010'}

 56%|█████▌    | 1010/1813 [1:51:58<1:20:59,  6.05s/it]
 56%|█████▌    | 1011/1813 [1:52:05<1:23:47,  6.27s/it]
 56%|█████▌    | 1012/1813 [1:52:10<1:17:36,  5.81s/it]
 56%|█████▌    | 1013/1813 [1:52:14<1:12:31,  5.44s/it]
 56%|█████▌    | 1014/1813 [1:52:23<1:24:14,  6.33s/it]
 56%|█████▌    | 1015/1813 [1:52:28<1:20:52,  6.08s/it]
 56%|█████▌    | 1016/1813 [1:52:34<1:18:27,  5.91s/it]
 56%|█████▌    | 1017/1813 [1:52:41<1:23:03,  6.26s/it]
 56%|█████▌    | 1018/1813 [1:52:47<1:23:31,  6.30s/it]
 56%|█████▌    | 1019/1813 [1:52:52<1:19:11,  5.98s/it]
 56%|█████▋    | 1020/1813 [1:52:58<1:16:17,  5.77s/it]
                                                       
{'loss': '0.8596', 'grad_norm': '1.019', 'learning_rate': '4.646e-05', 'epoch': '0.5628', 'num_input_tokens_seen': 6844992, 'train_runtime': '6778', 'train_tokens_per_second': '1010'}

 56%|█████▋    | 1020/1813 [1:52:58<1:16:17,  5.77s/it]
 56%|█████▋    | 1021/1813 [1:53:05<1:21:48,  6.20s/it]
 56%|█████▋    | 1022/1813 [1:53:11<1:22:17,  6.24s/it]
 56%|█████▋    | 1023/1813 [1:53:19<1:27:37,  6.65s/it]
 56%|█████▋    | 1024/1813 [1:53:25<1:26:29,  6.58s/it]
 57%|█████▋    | 1025/1813 [1:53:35<1:36:39,  7.36s/it]
 57%|█████▋    | 1026/1813 [1:53:40<1:28:24,  6.74s/it]
 57%|█████▋    | 1027/1813 [1:53:46<1:25:41,  6.54s/it]
 57%|█████▋    | 1028/1813 [1:53:53<1:28:47,  6.79s/it]
 57%|█████▋    | 1029/1813 [1:54:00<1:27:25,  6.69s/it]
 57%|█████▋    | 1030/1813 [1:54:07<1:28:05,  6.75s/it]
                                                       
{'loss': '0.9955', 'grad_norm': '0.6896', 'learning_rate': '4.552e-05', 'epoch': '0.5683', 'num_input_tokens_seen': 6920856, 'train_runtime': '6847', 'train_tokens_per_second': '1011'}

 57%|█████▋    | 1030/1813 [1:54:07<1:28:05,  6.75s/it]
 57%|█████▋    | 1031/1813 [1:54:12<1:23:37,  6.42s/it]
 57%|█████▋    | 1032/1813 [1:54:19<1:24:50,  6.52s/it]
 57%|█████▋    | 1033/1813 [1:54:25<1:23:40,  6.44s/it]
 57%|█████▋    | 1034/1813 [1:54:31<1:21:42,  6.29s/it]
 57%|█████▋    | 1035/1813 [1:54:38<1:21:53,  6.32s/it]
 57%|█████▋    | 1036/1813 [1:54:44<1:22:28,  6.37s/it]
 57%|█████▋    | 1037/1813 [1:54:50<1:20:56,  6.26s/it]
 57%|█████▋    | 1038/1813 [1:54:56<1:21:03,  6.28s/it]
 57%|█████▋    | 1039/1813 [1:55:03<1:23:53,  6.50s/it]
 57%|█████▋    | 1040/1813 [1:55:10<1:25:54,  6.67s/it]
                                                       
{'loss': '0.9234', 'grad_norm': '0.722', 'learning_rate': '4.458e-05', 'epoch': '0.5738', 'num_input_tokens_seen': 6988568, 'train_runtime': '6911', 'train_tokens_per_second': '1011'}

 57%|█████▋    | 1040/1813 [1:55:10<1:25:54,  6.67s/it]
 57%|█████▋    | 1041/1813 [1:55:17<1:23:41,  6.50s/it]
 57%|█████▋    | 1042/1813 [1:55:23<1:23:31,  6.50s/it]
 58%|█████▊    | 1043/1813 [1:55:29<1:20:26,  6.27s/it]
 58%|█████▊    | 1044/1813 [1:55:34<1:17:07,  6.02s/it]
 58%|█████▊    | 1045/1813 [1:55:40<1:16:12,  5.95s/it]
 58%|█████▊    | 1046/1813 [1:55:46<1:16:18,  5.97s/it]
 58%|█████▊    | 1047/1813 [1:55:53<1:18:38,  6.16s/it]
 58%|█████▊    | 1048/1813 [1:56:00<1:22:07,  6.44s/it]
 58%|█████▊    | 1049/1813 [1:56:05<1:19:19,  6.23s/it]
 58%|█████▊    | 1050/1813 [1:56:12<1:18:30,  6.17s/it]
                                                       
{'loss': '0.8991', 'grad_norm': '1.065', 'learning_rate': '4.364e-05', 'epoch': '0.5793', 'num_input_tokens_seen': 7051808, 'train_runtime': '6972', 'train_tokens_per_second': '1011'}

 58%|█████▊    | 1050/1813 [1:56:12<1:18:30,  6.17s/it]
 58%|█████▊    | 1051/1813 [1:56:17<1:14:41,  5.88s/it]
 58%|█████▊    | 1052/1813 [1:56:22<1:13:55,  5.83s/it]
 58%|█████▊    | 1053/1813 [1:56:28<1:13:32,  5.81s/it]
 58%|█████▊    | 1054/1813 [1:56:34<1:12:54,  5.76s/it]
 58%|█████▊    | 1055/1813 [1:56:39<1:10:53,  5.61s/it]
 58%|█████▊    | 1056/1813 [1:56:45<1:11:23,  5.66s/it]
 58%|█████▊    | 1057/1813 [1:56:51<1:14:52,  5.94s/it]
 58%|█████▊    | 1058/1813 [1:56:56<1:10:57,  5.64s/it]
 58%|█████▊    | 1059/1813 [1:57:01<1:07:49,  5.40s/it]
 58%|█████▊    | 1060/1813 [1:57:08<1:13:18,  5.84s/it]
                                                       
{'loss': '0.9138', 'grad_norm': '0.6532', 'learning_rate': '4.271e-05', 'epoch': '0.5848', 'num_input_tokens_seen': 7110624, 'train_runtime': '7029', 'train_tokens_per_second': '1012'}

 58%|█████▊    | 1060/1813 [1:57:08<1:13:18,  5.84s/it]
 59%|█████▊    | 1061/1813 [1:57:13<1:09:23,  5.54s/it]
 59%|█████▊    | 1062/1813 [1:57:18<1:07:12,  5.37s/it]
 59%|█████▊    | 1063/1813 [1:57:25<1:11:56,  5.76s/it]
 59%|█████▊    | 1064/1813 [1:57:32<1:18:19,  6.27s/it]
 59%|█████▊    | 1065/1813 [1:57:39<1:20:19,  6.44s/it]
 59%|█████▉    | 1066/1813 [1:57:46<1:24:26,  6.78s/it]
 59%|█████▉    | 1067/1813 [1:57:53<1:23:16,  6.70s/it]
 59%|█████▉    | 1068/1813 [1:57:58<1:16:58,  6.20s/it]
 59%|█████▉    | 1069/1813 [1:58:06<1:23:20,  6.72s/it]
 59%|█████▉    | 1070/1813 [1:58:12<1:19:33,  6.42s/it]
                                                       
{'loss': '0.9113', 'grad_norm': '0.9644', 'learning_rate': '4.177e-05', 'epoch': '0.5903', 'num_input_tokens_seen': 7179728, 'train_runtime': '7092', 'train_tokens_per_second': '1012'}

 59%|█████▉    | 1070/1813 [1:58:12<1:19:33,  6.42s/it]
 59%|█████▉    | 1071/1813 [1:58:17<1:15:52,  6.14s/it]
 59%|█████▉    | 1072/1813 [1:58:23<1:16:34,  6.20s/it]
 59%|█████▉    | 1073/1813 [1:58:29<1:15:18,  6.11s/it]
 59%|█████▉    | 1074/1813 [1:58:35<1:13:00,  5.93s/it]
 59%|█████▉    | 1075/1813 [1:58:41<1:14:57,  6.09s/it]
 59%|█████▉    | 1076/1813 [1:58:48<1:17:20,  6.30s/it]
 59%|█████▉    | 1077/1813 [1:58:53<1:11:41,  5.84s/it]
 59%|█████▉    | 1078/1813 [1:58:58<1:09:38,  5.68s/it]
 60%|█████▉    | 1079/1813 [1:59:05<1:12:54,  5.96s/it]
 60%|█████▉    | 1080/1813 [1:59:11<1:14:18,  6.08s/it]
                                                       
{'loss': '0.9093', 'grad_norm': '0.7117', 'learning_rate': '4.084e-05', 'epoch': '0.5959', 'num_input_tokens_seen': 7240984, 'train_runtime': '7152', 'train_tokens_per_second': '1012'}

 60%|█████▉    | 1080/1813 [1:59:11<1:14:18,  6.08s/it]
 60%|█████▉    | 1081/1813 [1:59:17<1:14:15,  6.09s/it]
 60%|█████▉    | 1082/1813 [1:59:23<1:12:25,  5.95s/it]
 60%|█████▉    | 1083/1813 [1:59:29<1:13:21,  6.03s/it]
 60%|█████▉    | 1084/1813 [1:59:35<1:13:17,  6.03s/it]
 60%|█████▉    | 1085/1813 [1:59:41<1:13:22,  6.05s/it]
 60%|█████▉    | 1086/1813 [1:59:46<1:07:05,  5.54s/it]
 60%|█████▉    | 1087/1813 [1:59:51<1:08:00,  5.62s/it]
 60%|██████    | 1088/1813 [1:59:57<1:08:52,  5.70s/it]
 60%|██████    | 1089/1813 [2:00:04<1:12:19,  5.99s/it]
 60%|██████    | 1090/1813 [2:00:10<1:12:08,  5.99s/it]
                                                       
{'loss': '0.8324', 'grad_norm': '0.8991', 'learning_rate': '3.992e-05', 'epoch': '0.6014', 'num_input_tokens_seen': 7301824, 'train_runtime': '7210', 'train_tokens_per_second': '1013'}

 60%|██████    | 1090/1813 [2:00:10<1:12:08,  5.99s/it]
 60%|██████    | 1091/1813 [2:00:16<1:12:40,  6.04s/it]
 60%|██████    | 1092/1813 [2:00:22<1:11:41,  5.97s/it]
 60%|██████    | 1093/1813 [2:00:27<1:09:35,  5.80s/it]
 60%|██████    | 1094/1813 [2:00:34<1:11:05,  5.93s/it]
 60%|██████    | 1095/1813 [2:00:40<1:11:36,  5.98s/it]
 60%|██████    | 1096/1813 [2:00:45<1:09:13,  5.79s/it]
 61%|██████    | 1097/1813 [2:00:51<1:09:29,  5.82s/it]
 61%|██████    | 1098/1813 [2:00:58<1:14:12,  6.23s/it]
 61%|██████    | 1099/1813 [2:01:04<1:14:20,  6.25s/it]
 61%|██████    | 1100/1813 [2:01:12<1:19:49,  6.72s/it]
                                                       
{'loss': '0.8953', 'grad_norm': '0.9429', 'learning_rate': '3.899e-05', 'epoch': '0.6069', 'num_input_tokens_seen': 7369528, 'train_runtime': '7273', 'train_tokens_per_second': '1013'}

 61%|██████    | 1100/1813 [2:01:12<1:19:49,  6.72s/it]
 61%|██████    | 1101/1813 [2:01:19<1:18:28,  6.61s/it]
 61%|██████    | 1102/1813 [2:01:26<1:19:40,  6.72s/it]
 61%|██████    | 1103/1813 [2:01:31<1:14:38,  6.31s/it]
 61%|██████    | 1104/1813 [2:01:38<1:18:36,  6.65s/it]
 61%|██████    | 1105/1813 [2:01:43<1:11:25,  6.05s/it]
 61%|██████    | 1106/1813 [2:01:49<1:09:38,  5.91s/it]
 61%|██████    | 1107/1813 [2:01:57<1:18:35,  6.68s/it]
 61%|██████    | 1108/1813 [2:02:03<1:14:47,  6.37s/it]
 61%|██████    | 1109/1813 [2:02:09<1:15:23,  6.43s/it]
 61%|██████    | 1110/1813 [2:02:17<1:19:52,  6.82s/it]
                                                       
{'loss': '0.9365', 'grad_norm': '0.8699', 'learning_rate': '3.807e-05', 'epoch': '0.6124', 'num_input_tokens_seen': 7441040, 'train_runtime': '7337', 'train_tokens_per_second': '1014'}

 61%|██████    | 1110/1813 [2:02:17<1:19:52,  6.82s/it]
 61%|██████▏   | 1111/1813 [2:02:22<1:13:03,  6.24s/it]
 61%|██████▏   | 1112/1813 [2:02:28<1:11:57,  6.16s/it]
 61%|██████▏   | 1113/1813 [2:02:34<1:12:56,  6.25s/it]
 61%|██████▏   | 1114/1813 [2:02:42<1:16:24,  6.56s/it]
 62%|██████▏   | 1115/1813 [2:02:48<1:17:14,  6.64s/it]
 62%|██████▏   | 1116/1813 [2:02:55<1:16:51,  6.62s/it]
 62%|██████▏   | 1117/1813 [2:03:01<1:13:42,  6.35s/it]
 62%|██████▏   | 1118/1813 [2:03:06<1:09:14,  5.98s/it]
 62%|██████▏   | 1119/1813 [2:03:12<1:10:47,  6.12s/it]
 62%|██████▏   | 1120/1813 [2:03:19<1:12:53,  6.31s/it]
                                                       
{'loss': '0.8833', 'grad_norm': '1.248', 'learning_rate': '3.716e-05', 'epoch': '0.6179', 'num_input_tokens_seen': 7504976, 'train_runtime': '7400', 'train_tokens_per_second': '1014'}

 62%|██████▏   | 1120/1813 [2:03:19<1:12:53,  6.31s/it]
 62%|██████▏   | 1121/1813 [2:03:27<1:18:28,  6.80s/it]
 62%|██████▏   | 1122/1813 [2:03:32<1:11:19,  6.19s/it]
 62%|██████▏   | 1123/1813 [2:03:39<1:16:15,  6.63s/it]
 62%|██████▏   | 1124/1813 [2:03:45<1:12:46,  6.34s/it]
 62%|██████▏   | 1125/1813 [2:03:52<1:14:28,  6.49s/it]
 62%|██████▏   | 1126/1813 [2:03:58<1:13:07,  6.39s/it]
 62%|██████▏   | 1127/1813 [2:04:04<1:10:06,  6.13s/it]
 62%|██████▏   | 1128/1813 [2:04:09<1:07:36,  5.92s/it]
 62%|██████▏   | 1129/1813 [2:04:14<1:04:55,  5.69s/it]
 62%|██████▏   | 1130/1813 [2:04:19<1:03:12,  5.55s/it]
                                                       
{'loss': '0.8771', 'grad_norm': '0.831', 'learning_rate': '3.625e-05', 'epoch': '0.6234', 'num_input_tokens_seen': 7568576, 'train_runtime': '7460', 'train_tokens_per_second': '1015'}

 62%|██████▏   | 1130/1813 [2:04:19<1:03:12,  5.55s/it]
 62%|██████▏   | 1131/1813 [2:04:25<1:04:01,  5.63s/it]
 62%|██████▏   | 1132/1813 [2:04:31<1:04:52,  5.72s/it]
 62%|██████▏   | 1133/1813 [2:04:38<1:07:10,  5.93s/it]
 63%|██████▎   | 1134/1813 [2:04:45<1:13:34,  6.50s/it]
 63%|██████▎   | 1135/1813 [2:04:52<1:14:29,  6.59s/it]
 63%|██████▎   | 1136/1813 [2:04:59<1:15:40,  6.71s/it]
 63%|██████▎   | 1137/1813 [2:05:06<1:14:55,  6.65s/it]
 63%|██████▎   | 1138/1813 [2:05:13<1:15:59,  6.75s/it]
 63%|██████▎   | 1139/1813 [2:05:18<1:11:18,  6.35s/it]
 63%|██████▎   | 1140/1813 [2:05:24<1:08:46,  6.13s/it]
                                                       
{'loss': '0.95', 'grad_norm': '0.8641', 'learning_rate': '3.534e-05', 'epoch': '0.629', 'num_input_tokens_seen': 7639168, 'train_runtime': '7524', 'train_tokens_per_second': '1015'}

 63%|██████▎   | 1140/1813 [2:05:24<1:08:46,  6.13s/it]
 63%|██████▎   | 1141/1813 [2:05:30<1:08:29,  6.12s/it]
 63%|██████▎   | 1142/1813 [2:05:36<1:07:40,  6.05s/it]
 63%|██████▎   | 1143/1813 [2:05:42<1:06:51,  5.99s/it]
 63%|██████▎   | 1144/1813 [2:05:48<1:09:36,  6.24s/it]
 63%|██████▎   | 1145/1813 [2:05:55<1:09:57,  6.28s/it]
 63%|██████▎   | 1146/1813 [2:06:00<1:06:55,  6.02s/it]
 63%|██████▎   | 1147/1813 [2:06:08<1:11:47,  6.47s/it]
 63%|██████▎   | 1148/1813 [2:06:15<1:13:19,  6.62s/it]
 63%|██████▎   | 1149/1813 [2:06:20<1:10:03,  6.33s/it]
 63%|██████▎   | 1150/1813 [2:06:28<1:13:57,  6.69s/it]
                                                       
{'loss': '0.881', 'grad_norm': '0.7982', 'learning_rate': '3.444e-05', 'epoch': '0.6345', 'num_input_tokens_seen': 7707832, 'train_runtime': '7588', 'train_tokens_per_second': '1016'}

 63%|██████▎   | 1150/1813 [2:06:28<1:13:57,  6.69s/it]
 63%|██████▎   | 1151/1813 [2:06:32<1:04:52,  5.88s/it]
 64%|██████▎   | 1152/1813 [2:06:37<1:03:18,  5.75s/it]
 64%|██████▎   | 1153/1813 [2:06:44<1:07:38,  6.15s/it]
 64%|██████▎   | 1154/1813 [2:06:50<1:07:21,  6.13s/it]
 64%|██████▎   | 1155/1813 [2:06:57<1:08:54,  6.28s/it]
 64%|██████▍   | 1156/1813 [2:07:03<1:09:13,  6.32s/it]
 64%|██████▍   | 1157/1813 [2:07:11<1:13:13,  6.70s/it]
 64%|██████▍   | 1158/1813 [2:07:18<1:13:11,  6.70s/it]
 64%|██████▍   | 1159/1813 [2:07:25<1:14:37,  6.85s/it]
 64%|██████▍   | 1160/1813 [2:07:31<1:12:15,  6.64s/it]
                                                       
{'loss': '0.9272', 'grad_norm': '0.6358', 'learning_rate': '3.355e-05', 'epoch': '0.64', 'num_input_tokens_seen': 7775872, 'train_runtime': '7652', 'train_tokens_per_second': '1016'}

 64%|██████▍   | 1160/1813 [2:07:31<1:12:15,  6.64s/it]
 64%|██████▍   | 1161/1813 [2:07:39<1:14:41,  6.87s/it]
 64%|██████▍   | 1162/1813 [2:07:45<1:14:20,  6.85s/it]
 64%|██████▍   | 1163/1813 [2:07:52<1:12:59,  6.74s/it]
 64%|██████▍   | 1164/1813 [2:07:58<1:11:14,  6.59s/it]
 64%|██████▍   | 1165/1813 [2:08:04<1:10:33,  6.53s/it]
 64%|██████▍   | 1166/1813 [2:08:10<1:08:27,  6.35s/it]
 64%|██████▍   | 1167/1813 [2:08:17<1:10:18,  6.53s/it]
 64%|██████▍   | 1168/1813 [2:08:24<1:09:51,  6.50s/it]
 64%|██████▍   | 1169/1813 [2:08:30<1:08:42,  6.40s/it]
 65%|██████▍   | 1170/1813 [2:08:36<1:06:44,  6.23s/it]
                                                       
{'loss': '0.908', 'grad_norm': '0.9535', 'learning_rate': '3.266e-05', 'epoch': '0.6455', 'num_input_tokens_seen': 7846688, 'train_runtime': '7716', 'train_tokens_per_second': '1017'}

 65%|██████▍   | 1170/1813 [2:08:36<1:06:44,  6.23s/it]
 65%|██████▍   | 1171/1813 [2:08:43<1:10:15,  6.57s/it]
 65%|██████▍   | 1172/1813 [2:08:50<1:11:47,  6.72s/it]
 65%|██████▍   | 1173/1813 [2:08:56<1:07:41,  6.35s/it]
 65%|██████▍   | 1174/1813 [2:09:01<1:03:55,  6.00s/it]
 65%|██████▍   | 1175/1813 [2:09:07<1:03:11,  5.94s/it]
 65%|██████▍   | 1176/1813 [2:09:13<1:04:09,  6.04s/it]
 65%|██████▍   | 1177/1813 [2:09:19<1:02:48,  5.92s/it]
 65%|██████▍   | 1178/1813 [2:09:25<1:03:02,  5.96s/it]
 65%|██████▌   | 1179/1813 [2:09:31<1:03:35,  6.02s/it]
 65%|██████▌   | 1180/1813 [2:09:38<1:05:55,  6.25s/it]
                                                       
{'loss': '0.8907', 'grad_norm': '0.9056', 'learning_rate': '3.177e-05', 'epoch': '0.651', 'num_input_tokens_seen': 7914072, 'train_runtime': '7778', 'train_tokens_per_second': '1017'}

 65%|██████▌   | 1180/1813 [2:09:38<1:05:55,  6.25s/it]
 65%|██████▌   | 1181/1813 [2:09:45<1:11:10,  6.76s/it]
 65%|██████▌   | 1182/1813 [2:09:53<1:14:23,  7.07s/it]
 65%|██████▌   | 1183/1813 [2:10:00<1:14:28,  7.09s/it]
 65%|██████▌   | 1184/1813 [2:10:06<1:11:00,  6.77s/it]
 65%|██████▌   | 1185/1813 [2:10:14<1:14:24,  7.11s/it]
 65%|██████▌   | 1186/1813 [2:10:22<1:15:24,  7.22s/it]
 65%|██████▌   | 1187/1813 [2:10:29<1:14:32,  7.14s/it]
 66%|██████▌   | 1188/1813 [2:10:34<1:09:41,  6.69s/it]
 66%|██████▌   | 1189/1813 [2:10:40<1:05:47,  6.33s/it]
 66%|██████▌   | 1190/1813 [2:10:46<1:06:29,  6.40s/it]
                                                       
{'loss': '0.9446', 'grad_norm': '1.067', 'learning_rate': '3.09e-05', 'epoch': '0.6566', 'num_input_tokens_seen': 7989064, 'train_runtime': '7847', 'train_tokens_per_second': '1018'}

 66%|██████▌   | 1190/1813 [2:10:46<1:06:29,  6.40s/it]
 66%|██████▌   | 1191/1813 [2:10:52<1:04:29,  6.22s/it]
 66%|██████▌   | 1192/1813 [2:10:59<1:05:53,  6.37s/it]
 66%|██████▌   | 1193/1813 [2:11:05<1:05:04,  6.30s/it]
 66%|██████▌   | 1194/1813 [2:11:12<1:06:11,  6.42s/it]
 66%|██████▌   | 1195/1813 [2:11:17<1:01:46,  6.00s/it]
 66%|██████▌   | 1196/1813 [2:11:23<1:02:11,  6.05s/it]
 66%|██████▌   | 1197/1813 [2:11:29<1:02:39,  6.10s/it]
 66%|██████▌   | 1198/1813 [2:11:35<1:01:29,  6.00s/it]
 66%|██████▌   | 1199/1813 [2:11:41<1:00:51,  5.95s/it]
 66%|██████▌   | 1200/1813 [2:11:48<1:05:05,  6.37s/it]
                                                       
{'loss': '0.8617', 'grad_norm': '0.8818', 'learning_rate': '3.003e-05', 'epoch': '0.6621', 'num_input_tokens_seen': 8055352, 'train_runtime': '7909', 'train_tokens_per_second': '1019'}

 66%|██████▌   | 1200/1813 [2:11:48<1:05:05,  6.37s/it]
***** Running Evaluation *****
  Num examples = 1000
  Batch size = 1


  0%|          | 0/1000 [00:00<?, ?it/s]

  0%|          | 3/1000 [00:00<01:03, 15.68it/s]

  0%|          | 5/1000 [00:00<02:17,  7.22it/s]

  1%|          | 7/1000 [00:00<01:59,  8.32it/s]

  1%|          | 9/1000 [00:01<02:33,  6.46it/s]

  1%|          | 11/1000 [00:01<02:02,  8.07it/s]

  1%|▏         | 13/1000 [00:01<02:21,  6.99it/s]

  1%|▏         | 14/1000 [00:01<02:24,  6.83it/s]

  2%|▏         | 15/1000 [00:02<02:44,  5.97it/s]

  2%|▏         | 16/1000 [00:02<02:51,  5.73it/s]

  2%|▏         | 18/1000 [00:02<02:42,  6.05it/s]

  2%|▏         | 19/1000 [00:02<03:10,  5.14it/s]

  2%|▏         | 20/1000 [00:03<03:33,  4.59it/s]

  2%|▏         | 22/1000 [00:03<02:36,  6.24it/s]

  2%|▏         | 23/1000 [00:03<02:55,  5.58it/s]

  2%|▎         | 25/1000 [00:03<02:12,  7.35it/s]

  3%|▎         | 26/1000 [00:04<02:35,  6.25it/s]

  3%|▎         | 28/1000 [00:04<02:42,  5.98it/s]

  3%|▎         | 29/1000 [00:04<02:32,  6.35it/s]

  3%|▎         | 30/1000 [00:04<02:42,  5.96it/s]

  3%|▎         | 31/1000 [00:04<03:01,  5.34it/s]

  3%|▎         | 32/1000 [00:05<02:41,  5.98it/s]

  3%|▎         | 33/1000 [00:05<02:48,  5.74it/s]

  4%|▎         | 35/1000 [00:05<02:06,  7.65it/s]

  4%|▎         | 37/1000 [00:05<01:45,  9.09it/s]

  4%|▍         | 39/1000 [00:05<02:07,  7.56it/s]

  4%|▍         | 40/1000 [00:06<02:04,  7.74it/s]

  4%|▍         | 42/1000 [00:06<01:45,  9.11it/s]

  4%|▍         | 44/1000 [00:06<01:32, 10.33it/s]

  5%|▍         | 46/1000 [00:06<01:45,  9.05it/s]

  5%|▍         | 47/1000 [00:06<02:09,  7.35it/s]

  5%|▍         | 49/1000 [00:06<01:48,  8.74it/s]

  5%|▌         | 51/1000 [00:07<01:35,  9.91it/s]

  5%|▌         | 53/1000 [00:07<01:26, 10.93it/s]

  6%|▌         | 55/1000 [00:07<01:28, 10.73it/s]

  6%|▌         | 57/1000 [00:07<01:41,  9.28it/s]

  6%|▌         | 59/1000 [00:08<01:55,  8.18it/s]

  6%|▌         | 61/1000 [00:08<01:42,  9.15it/s]

  6%|▋         | 63/1000 [00:08<01:37,  9.62it/s]

  6%|▋         | 65/1000 [00:08<01:52,  8.31it/s]

  7%|▋         | 67/1000 [00:09<02:03,  7.53it/s]

  7%|▋         | 69/1000 [00:09<01:53,  8.22it/s]

  7%|▋         | 70/1000 [00:09<02:13,  6.97it/s]

  7%|▋         | 72/1000 [00:09<02:18,  6.70it/s]

  7%|▋         | 74/1000 [00:09<01:54,  8.11it/s]

  8%|▊         | 75/1000 [00:10<02:15,  6.84it/s]

  8%|▊         | 76/1000 [00:10<02:18,  6.66it/s]

  8%|▊         | 78/1000 [00:10<02:26,  6.31it/s]

  8%|▊         | 80/1000 [00:10<01:57,  7.82it/s]

  8%|▊         | 82/1000 [00:10<01:40,  9.17it/s]

  8%|▊         | 84/1000 [00:11<01:54,  8.00it/s]

  8%|▊         | 85/1000 [00:11<02:15,  6.77it/s]

  9%|▊         | 86/1000 [00:11<02:33,  5.94it/s]

  9%|▊         | 87/1000 [00:12<02:49,  5.38it/s]

  9%|▉         | 89/1000 [00:12<02:10,  7.00it/s]

  9%|▉         | 90/1000 [00:12<02:05,  7.25it/s]

  9%|▉         | 91/1000 [00:12<02:29,  6.08it/s]

  9%|▉         | 92/1000 [00:12<02:27,  6.17it/s]

  9%|▉         | 93/1000 [00:12<02:36,  5.78it/s]

 10%|▉         | 95/1000 [00:13<02:44,  5.52it/s]

 10%|▉         | 97/1000 [00:13<02:13,  6.79it/s]

 10%|▉         | 99/1000 [00:13<01:47,  8.36it/s]

 10%|█         | 101/1000 [00:13<01:33,  9.63it/s]

 10%|█         | 103/1000 [00:14<01:55,  7.74it/s]

 10%|█         | 104/1000 [00:14<01:54,  7.82it/s]

 11%|█         | 106/1000 [00:14<01:35,  9.32it/s]

 11%|█         | 108/1000 [00:14<01:25, 10.44it/s]

 11%|█         | 110/1000 [00:14<01:19, 11.21it/s]

 11%|█         | 112/1000 [00:14<01:13, 12.05it/s]

 11%|█▏        | 114/1000 [00:14<01:10, 12.53it/s]

 12%|█▏        | 116/1000 [00:15<01:08, 12.81it/s]

 12%|█▏        | 118/1000 [00:15<01:06, 13.19it/s]

 12%|█▏        | 120/1000 [00:15<02:07,  6.90it/s]

 12%|█▏        | 122/1000 [00:16<01:48,  8.07it/s]

 12%|█▏        | 124/1000 [00:16<01:58,  7.42it/s]

 12%|█▎        | 125/1000 [00:16<02:33,  5.71it/s]

 13%|█▎        | 126/1000 [00:16<02:22,  6.13it/s]

 13%|█▎        | 127/1000 [00:17<02:30,  5.79it/s]

 13%|█▎        | 128/1000 [00:17<02:44,  5.29it/s]

 13%|█▎        | 130/1000 [00:17<02:02,  7.10it/s]

 13%|█▎        | 132/1000 [00:17<01:39,  8.68it/s]

 13%|█▎        | 134/1000 [00:17<01:25, 10.12it/s]

 14%|█▎        | 136/1000 [00:17<01:29,  9.64it/s]

 14%|█▍        | 138/1000 [00:18<01:27,  9.89it/s]

 14%|█▍        | 140/1000 [00:18<01:26,  9.96it/s]

 14%|█▍        | 142/1000 [00:18<01:34,  9.04it/s]

 14%|█▍        | 143/1000 [00:18<01:36,  8.89it/s]

 14%|█▍        | 145/1000 [00:18<01:24, 10.06it/s]

 15%|█▍        | 147/1000 [00:19<01:41,  8.43it/s]

 15%|█▍        | 148/1000 [00:19<01:40,  8.49it/s]

 15%|█▌        | 150/1000 [00:19<01:25,  9.91it/s]

 15%|█▌        | 152/1000 [00:19<01:16, 11.04it/s]

 15%|█▌        | 154/1000 [00:19<01:21, 10.39it/s]

 16%|█▌        | 156/1000 [00:20<02:06,  6.65it/s]

 16%|█▌        | 158/1000 [00:20<01:45,  7.97it/s]

 16%|█▌        | 160/1000 [00:20<01:37,  8.60it/s]

 16%|█▌        | 162/1000 [00:20<01:47,  7.80it/s]

 16%|█▋        | 163/1000 [00:21<01:51,  7.49it/s]

 16%|█▋        | 164/1000 [00:21<02:10,  6.40it/s]

 16%|█▋        | 165/1000 [00:21<02:27,  5.66it/s]

 17%|█▋        | 166/1000 [00:21<02:41,  5.18it/s]

 17%|█▋        | 167/1000 [00:21<02:24,  5.78it/s]

 17%|█▋        | 169/1000 [00:22<01:45,  7.84it/s]

 17%|█▋        | 171/1000 [00:22<01:56,  7.14it/s]

 17%|█▋        | 172/1000 [00:22<02:14,  6.15it/s]

 17%|█▋        | 173/1000 [00:22<02:12,  6.22it/s]

 17%|█▋        | 174/1000 [00:22<02:02,  6.73it/s]

 18%|█▊        | 176/1000 [00:23<01:37,  8.45it/s]

 18%|█▊        | 177/1000 [00:23<02:00,  6.80it/s]

 18%|█▊        | 179/1000 [00:23<01:35,  8.57it/s]

 18%|█▊        | 180/1000 [00:23<01:36,  8.50it/s]

 18%|█▊        | 181/1000 [00:23<02:01,  6.75it/s]

 18%|█▊        | 182/1000 [00:24<02:23,  5.72it/s]

 18%|█▊        | 183/1000 [00:24<02:21,  5.79it/s]

 18%|█▊        | 185/1000 [00:24<01:45,  7.73it/s]

 19%|█▊        | 186/1000 [00:24<01:43,  7.88it/s]

 19%|█▊        | 187/1000 [00:24<02:07,  6.37it/s]

 19%|█▉        | 189/1000 [00:24<01:40,  8.10it/s]

 19%|█▉        | 190/1000 [00:25<02:02,  6.63it/s]

 19%|█▉        | 192/1000 [00:25<02:04,  6.48it/s]

 19%|█▉        | 194/1000 [00:25<02:06,  6.37it/s]

 20%|█▉        | 196/1000 [00:25<01:43,  7.75it/s]

 20%|█▉        | 198/1000 [00:26<01:27,  9.20it/s]

 20%|██        | 200/1000 [00:26<01:15, 10.64it/s]

 20%|██        | 202/1000 [00:26<01:31,  8.76it/s]

 20%|██        | 204/1000 [00:26<01:32,  8.62it/s]

 21%|██        | 206/1000 [00:26<01:20,  9.91it/s]

 21%|██        | 208/1000 [00:27<01:33,  8.51it/s]

 21%|██        | 210/1000 [00:27<01:33,  8.48it/s]

 21%|██        | 212/1000 [00:27<01:21,  9.67it/s]

 21%|██▏       | 214/1000 [00:27<01:29,  8.73it/s]

 22%|██▏       | 216/1000 [00:28<01:25,  9.15it/s]

 22%|██▏       | 217/1000 [00:28<01:44,  7.50it/s]

 22%|██▏       | 219/1000 [00:28<01:28,  8.79it/s]

 22%|██▏       | 220/1000 [00:28<02:04,  6.28it/s]

 22%|██▏       | 221/1000 [00:28<02:04,  6.28it/s]

 22%|██▏       | 223/1000 [00:29<02:20,  5.54it/s]

 22%|██▏       | 224/1000 [00:29<02:08,  6.03it/s]

 22%|██▎       | 225/1000 [00:29<02:07,  6.08it/s]

 23%|██▎       | 226/1000 [00:29<02:22,  5.41it/s]

 23%|██▎       | 228/1000 [00:30<01:53,  6.83it/s]

 23%|██▎       | 229/1000 [00:30<02:10,  5.90it/s]

 23%|██▎       | 230/1000 [00:30<02:01,  6.36it/s]

 23%|██▎       | 232/1000 [00:30<01:35,  8.02it/s]

 23%|██▎       | 233/1000 [00:30<01:33,  8.21it/s]

 24%|██▎       | 235/1000 [00:30<01:16,  9.97it/s]

 24%|██▎       | 237/1000 [00:31<01:20,  9.47it/s]

 24%|██▍       | 239/1000 [00:31<01:24,  8.97it/s]

 24%|██▍       | 241/1000 [00:31<01:30,  8.35it/s]

 24%|██▍       | 242/1000 [00:31<02:06,  6.02it/s]

 24%|██▍       | 243/1000 [00:32<02:18,  5.47it/s]

 24%|██▍       | 245/1000 [00:32<01:53,  6.65it/s]

 25%|██▍       | 247/1000 [00:32<01:31,  8.25it/s]

 25%|██▍       | 248/1000 [00:32<01:49,  6.85it/s]

 25%|██▍       | 249/1000 [00:33<02:06,  5.96it/s]

 25%|██▌       | 250/1000 [00:33<02:07,  5.87it/s]

 25%|██▌       | 252/1000 [00:33<02:04,  6.02it/s]

 25%|██▌       | 253/1000 [00:33<02:10,  5.73it/s]

 26%|██▌       | 255/1000 [00:33<01:41,  7.36it/s]

 26%|██▌       | 256/1000 [00:33<01:36,  7.69it/s]

 26%|██▌       | 258/1000 [00:34<01:24,  8.74it/s]

 26%|██▌       | 260/1000 [00:34<01:36,  7.68it/s]

 26%|██▌       | 261/1000 [00:34<01:53,  6.51it/s]

 26%|██▌       | 262/1000 [00:34<01:54,  6.43it/s]

 26%|██▋       | 264/1000 [00:35<01:56,  6.33it/s]

 26%|██▋       | 265/1000 [00:35<01:51,  6.59it/s]

 27%|██▋       | 266/1000 [00:35<01:46,  6.90it/s]

 27%|██▋       | 268/1000 [00:35<01:37,  7.52it/s]

 27%|██▋       | 270/1000 [00:36<01:43,  7.03it/s]

 27%|██▋       | 271/1000 [00:36<02:14,  5.44it/s]

 27%|██▋       | 273/1000 [00:36<02:07,  5.69it/s]

 28%|██▊       | 275/1000 [00:36<01:48,  6.69it/s]

 28%|██▊       | 277/1000 [00:37<01:29,  8.05it/s]

 28%|██▊       | 278/1000 [00:37<01:46,  6.81it/s]

 28%|██▊       | 280/1000 [00:37<01:48,  6.61it/s]

 28%|██▊       | 282/1000 [00:37<01:29,  8.01it/s]

 28%|██▊       | 283/1000 [00:38<02:02,  5.85it/s]

 28%|██▊       | 284/1000 [00:38<02:05,  5.71it/s]

 29%|██▊       | 286/1000 [00:38<01:35,  7.44it/s]

 29%|██▉       | 288/1000 [00:38<01:21,  8.74it/s]

 29%|██▉       | 290/1000 [00:38<01:31,  7.76it/s]

 29%|██▉       | 291/1000 [00:39<01:41,  6.99it/s]

 29%|██▉       | 292/1000 [00:39<01:56,  6.07it/s]

 29%|██▉       | 294/1000 [00:39<01:38,  7.19it/s]

 30%|██▉       | 296/1000 [00:39<01:42,  6.88it/s]

 30%|██▉       | 298/1000 [00:40<01:25,  8.18it/s]

 30%|██▉       | 299/1000 [00:40<01:48,  6.46it/s]

 30%|███       | 300/1000 [00:40<01:42,  6.85it/s]

 30%|███       | 301/1000 [00:40<01:38,  7.11it/s]

 30%|███       | 303/1000 [00:40<01:19,  8.76it/s]

 30%|███       | 304/1000 [00:40<01:26,  8.08it/s]

 30%|███       | 305/1000 [00:40<01:25,  8.14it/s]

 31%|███       | 306/1000 [00:41<01:39,  6.95it/s]

 31%|███       | 307/1000 [00:41<01:42,  6.78it/s]

 31%|███       | 309/1000 [00:41<01:18,  8.78it/s]

 31%|███       | 311/1000 [00:41<01:07, 10.19it/s]

 31%|███▏      | 313/1000 [00:41<01:01, 11.25it/s]

 32%|███▏      | 315/1000 [00:41<01:06, 10.23it/s]

 32%|███▏      | 317/1000 [00:42<01:11,  9.56it/s]

 32%|███▏      | 319/1000 [00:42<01:34,  7.22it/s]

 32%|███▏      | 321/1000 [00:42<01:38,  6.88it/s]

 32%|███▏      | 322/1000 [00:43<01:45,  6.43it/s]

 32%|███▏      | 324/1000 [00:43<01:27,  7.74it/s]

 32%|███▎      | 325/1000 [00:43<01:58,  5.69it/s]

 33%|███▎      | 327/1000 [00:43<01:30,  7.40it/s]

 33%|███▎      | 328/1000 [00:43<01:33,  7.16it/s]

 33%|███▎      | 330/1000 [00:44<01:38,  6.79it/s]

 33%|███▎      | 332/1000 [00:44<01:41,  6.58it/s]

 33%|███▎      | 333/1000 [00:44<01:35,  6.95it/s]

 33%|███▎      | 334/1000 [00:44<01:44,  6.36it/s]

 34%|███▎      | 336/1000 [00:45<01:22,  8.03it/s]

 34%|███▍      | 338/1000 [00:45<01:15,  8.81it/s]

 34%|███▍      | 340/1000 [00:45<01:05, 10.02it/s]

 34%|███▍      | 342/1000 [00:45<01:00, 10.88it/s]

 34%|███▍      | 344/1000 [00:45<01:26,  7.59it/s]

 34%|███▍      | 345/1000 [00:46<01:24,  7.71it/s]

 35%|███▍      | 346/1000 [00:46<01:30,  7.22it/s]

 35%|███▍      | 347/1000 [00:46<01:27,  7.42it/s]

 35%|███▍      | 349/1000 [00:46<01:34,  6.92it/s]

 35%|███▌      | 350/1000 [00:46<01:49,  5.95it/s]

 35%|███▌      | 352/1000 [00:47<01:24,  7.64it/s]

 35%|███▌      | 354/1000 [00:47<01:25,  7.56it/s]

 36%|███▌      | 355/1000 [00:47<01:27,  7.35it/s]

 36%|███▌      | 357/1000 [00:47<01:11,  8.94it/s]

 36%|███▌      | 359/1000 [00:47<01:00, 10.56it/s]

 36%|███▌      | 361/1000 [00:48<01:07,  9.41it/s]

 36%|███▋      | 363/1000 [00:48<01:28,  7.18it/s]

 36%|███▋      | 364/1000 [00:48<01:41,  6.27it/s]

 36%|███▋      | 365/1000 [00:49<02:09,  4.92it/s]

 37%|███▋      | 367/1000 [00:49<01:57,  5.36it/s]

 37%|███▋      | 368/1000 [00:49<02:05,  5.02it/s]

 37%|███▋      | 369/1000 [00:49<01:52,  5.59it/s]

 37%|███▋      | 371/1000 [00:49<01:23,  7.53it/s]

 37%|███▋      | 372/1000 [00:50<01:21,  7.70it/s]

 37%|███▋      | 374/1000 [00:50<01:17,  8.07it/s]

 38%|███▊      | 375/1000 [00:50<01:40,  6.20it/s]

 38%|███▊      | 376/1000 [00:50<01:53,  5.47it/s]

 38%|███▊      | 377/1000 [00:50<01:40,  6.18it/s]

 38%|███▊      | 379/1000 [00:51<01:17,  8.03it/s]

 38%|███▊      | 381/1000 [00:51<01:08,  9.08it/s]

 38%|███▊      | 382/1000 [00:51<01:18,  7.84it/s]

 38%|███▊      | 384/1000 [00:51<01:05,  9.36it/s]

 39%|███▊      | 386/1000 [00:51<01:05,  9.31it/s]

 39%|███▊      | 387/1000 [00:52<01:24,  7.25it/s]

 39%|███▉      | 388/1000 [00:52<01:27,  7.02it/s]

 39%|███▉      | 390/1000 [00:52<01:19,  7.70it/s]

 39%|███▉      | 391/1000 [00:52<01:22,  7.36it/s]

 39%|███▉      | 393/1000 [00:52<01:07,  8.98it/s]

 40%|███▉      | 395/1000 [00:53<01:21,  7.46it/s]

 40%|███▉      | 397/1000 [00:53<01:08,  8.82it/s]

 40%|███▉      | 398/1000 [00:53<01:23,  7.20it/s]

 40%|███▉      | 399/1000 [00:53<01:41,  5.91it/s]

 40%|████      | 400/1000 [00:53<01:52,  5.34it/s]

 40%|████      | 402/1000 [00:54<01:44,  5.74it/s]

 40%|████      | 404/1000 [00:54<01:22,  7.24it/s]

 41%|████      | 406/1000 [00:54<01:09,  8.59it/s]

 41%|████      | 407/1000 [00:54<01:23,  7.06it/s]

 41%|████      | 408/1000 [00:55<01:36,  6.14it/s]

 41%|████      | 410/1000 [00:55<01:33,  6.29it/s]

 41%|████      | 411/1000 [00:55<01:44,  5.63it/s]

 41%|████      | 412/1000 [00:55<01:53,  5.16it/s]

 41%|████▏     | 414/1000 [00:55<01:23,  7.04it/s]

 42%|████▏     | 416/1000 [00:56<01:25,  6.79it/s]

 42%|████▏     | 418/1000 [00:56<01:10,  8.31it/s]

 42%|████▏     | 420/1000 [00:56<01:08,  8.50it/s]

 42%|████▏     | 421/1000 [00:56<01:17,  7.51it/s]

 42%|████▏     | 423/1000 [00:57<01:26,  6.68it/s]

 42%|████▏     | 424/1000 [00:57<01:37,  5.92it/s]

 42%|████▎     | 425/1000 [00:57<01:30,  6.36it/s]

 43%|████▎     | 427/1000 [00:57<01:12,  7.92it/s]

 43%|████▎     | 428/1000 [00:57<01:16,  7.52it/s]

 43%|████▎     | 429/1000 [00:58<01:13,  7.82it/s]

 43%|████▎     | 431/1000 [00:58<00:59,  9.52it/s]

 43%|████▎     | 433/1000 [00:58<00:51, 10.98it/s]

 44%|████▎     | 435/1000 [00:58<00:48, 11.76it/s]

 44%|████▎     | 437/1000 [00:58<00:53, 10.50it/s]

 44%|████▍     | 439/1000 [00:59<01:09,  8.08it/s]

 44%|████▍     | 441/1000 [00:59<01:00,  9.30it/s]

 44%|████▍     | 443/1000 [00:59<01:08,  8.09it/s]

 44%|████▍     | 444/1000 [00:59<01:16,  7.24it/s]

 45%|████▍     | 446/1000 [00:59<01:03,  8.72it/s]

 45%|████▍     | 448/1000 [01:00<01:13,  7.47it/s]

 45%|████▌     | 450/1000 [01:00<01:18,  7.01it/s]

 45%|████▌     | 451/1000 [01:00<01:28,  6.18it/s]

 45%|████▌     | 452/1000 [01:01<01:38,  5.57it/s]

 45%|████▌     | 454/1000 [01:01<01:16,  7.17it/s]

 46%|████▌     | 456/1000 [01:01<01:04,  8.49it/s]

 46%|████▌     | 457/1000 [01:01<01:09,  7.80it/s]

 46%|████▌     | 459/1000 [01:01<00:58,  9.25it/s]

 46%|████▌     | 461/1000 [01:01<00:49, 10.82it/s]

 46%|████▋     | 463/1000 [01:02<01:10,  7.61it/s]

 46%|████▋     | 465/1000 [01:02<01:19,  6.74it/s]

 47%|████▋     | 466/1000 [01:02<01:28,  6.01it/s]

 47%|████▋     | 467/1000 [01:03<01:50,  4.82it/s]

 47%|████▋     | 469/1000 [01:03<01:24,  6.30it/s]

 47%|████▋     | 471/1000 [01:03<01:07,  7.84it/s]

 47%|████▋     | 473/1000 [01:03<01:09,  7.56it/s]

 47%|████▋     | 474/1000 [01:03<01:21,  6.49it/s]

 48%|████▊     | 476/1000 [01:04<01:22,  6.38it/s]

 48%|████▊     | 477/1000 [01:04<01:35,  5.49it/s]

 48%|████▊     | 479/1000 [01:04<01:12,  7.14it/s]

 48%|████▊     | 480/1000 [01:04<01:19,  6.57it/s]

 48%|████▊     | 482/1000 [01:05<01:04,  8.05it/s]

 48%|████▊     | 484/1000 [01:05<01:10,  7.30it/s]

 48%|████▊     | 485/1000 [01:05<01:21,  6.31it/s]

 49%|████▊     | 486/1000 [01:05<01:21,  6.29it/s]

 49%|████▉     | 488/1000 [01:05<01:04,  7.97it/s]

 49%|████▉     | 489/1000 [01:06<01:17,  6.61it/s]

 49%|████▉     | 491/1000 [01:06<01:02,  8.19it/s]

 49%|████▉     | 492/1000 [01:06<01:01,  8.27it/s]

 49%|████▉     | 494/1000 [01:06<00:50,  9.98it/s]

 50%|████▉     | 496/1000 [01:06<00:59,  8.41it/s]

 50%|████▉     | 498/1000 [01:07<00:59,  8.43it/s]

 50%|████▉     | 499/1000 [01:07<01:15,  6.65it/s]

 50%|█████     | 500/1000 [01:07<01:24,  5.92it/s]

 50%|█████     | 502/1000 [01:07<01:06,  7.54it/s]

 50%|█████     | 503/1000 [01:07<01:13,  6.80it/s]

 50%|█████     | 505/1000 [01:08<01:15,  6.55it/s]

 51%|█████     | 506/1000 [01:08<01:25,  5.80it/s]

 51%|█████     | 508/1000 [01:08<01:06,  7.42it/s]

 51%|█████     | 510/1000 [01:08<00:54,  8.95it/s]

 51%|█████     | 512/1000 [01:08<00:49,  9.96it/s]

 51%|█████▏    | 514/1000 [01:09<01:06,  7.27it/s]

 52%|█████▏    | 515/1000 [01:09<01:04,  7.52it/s]

 52%|█████▏    | 516/1000 [01:09<01:08,  7.09it/s]

 52%|█████▏    | 518/1000 [01:09<00:59,  8.07it/s]

 52%|█████▏    | 519/1000 [01:10<01:15,  6.38it/s]

 52%|█████▏    | 521/1000 [01:10<00:59,  8.03it/s]

 52%|█████▏    | 522/1000 [01:10<01:11,  6.67it/s]

 52%|█████▏    | 523/1000 [01:10<01:22,  5.80it/s]

 52%|█████▏    | 524/1000 [01:11<01:25,  5.55it/s]

 53%|█████▎    | 526/1000 [01:11<01:11,  6.59it/s]

 53%|█████▎    | 528/1000 [01:11<01:12,  6.53it/s]

 53%|█████▎    | 529/1000 [01:11<01:13,  6.39it/s]

 53%|█████▎    | 531/1000 [01:11<00:57,  8.11it/s]

 53%|█████▎    | 533/1000 [01:11<00:48,  9.71it/s]

 54%|█████▎    | 535/1000 [01:12<01:09,  6.69it/s]

 54%|█████▎    | 536/1000 [01:12<01:12,  6.36it/s]

 54%|█████▎    | 537/1000 [01:12<01:21,  5.66it/s]

 54%|█████▍    | 539/1000 [01:13<01:17,  5.93it/s]

 54%|█████▍    | 540/1000 [01:13<01:19,  5.75it/s]

 54%|█████▍    | 541/1000 [01:13<01:27,  5.26it/s]

 54%|█████▍    | 543/1000 [01:13<01:05,  6.93it/s]

 55%|█████▍    | 545/1000 [01:14<01:04,  7.05it/s]

 55%|█████▍    | 546/1000 [01:14<01:10,  6.49it/s]

 55%|█████▍    | 547/1000 [01:14<01:19,  5.69it/s]

 55%|█████▍    | 549/1000 [01:14<01:16,  5.91it/s]

 55%|█████▌    | 551/1000 [01:14<00:59,  7.50it/s]

 55%|█████▌    | 552/1000 [01:15<01:01,  7.25it/s]

 55%|█████▌    | 553/1000 [01:15<01:12,  6.15it/s]

 55%|█████▌    | 554/1000 [01:15<01:15,  5.93it/s]

 56%|█████▌    | 556/1000 [01:15<00:58,  7.53it/s]

 56%|█████▌    | 557/1000 [01:15<01:04,  6.88it/s]

 56%|█████▌    | 559/1000 [01:16<00:50,  8.72it/s]

 56%|█████▌    | 561/1000 [01:16<00:44,  9.93it/s]

 56%|█████▋    | 563/1000 [01:16<00:52,  8.28it/s]

 56%|█████▋    | 565/1000 [01:16<00:55,  7.91it/s]

 57%|█████▋    | 566/1000 [01:17<01:04,  6.72it/s]

 57%|█████▋    | 568/1000 [01:17<01:06,  6.53it/s]

 57%|█████▋    | 569/1000 [01:17<01:07,  6.42it/s]

 57%|█████▋    | 571/1000 [01:17<01:06,  6.41it/s]

 57%|█████▋    | 572/1000 [01:18<01:08,  6.29it/s]

 57%|█████▋    | 574/1000 [01:18<01:07,  6.32it/s]

 58%|█████▊    | 576/1000 [01:18<00:54,  7.81it/s]

 58%|█████▊    | 577/1000 [01:18<01:14,  5.72it/s]

 58%|█████▊    | 578/1000 [01:19<01:20,  5.24it/s]

 58%|█████▊    | 580/1000 [01:19<01:00,  6.95it/s]

 58%|█████▊    | 582/1000 [01:19<00:49,  8.53it/s]

 58%|█████▊    | 584/1000 [01:19<00:54,  7.57it/s]

 58%|█████▊    | 585/1000 [01:19<01:00,  6.89it/s]

 59%|█████▊    | 587/1000 [01:20<00:57,  7.13it/s]

 59%|█████▉    | 589/1000 [01:20<00:48,  8.51it/s]

 59%|█████▉    | 590/1000 [01:20<01:00,  6.74it/s]

 59%|█████▉    | 592/1000 [01:20<00:49,  8.17it/s]

 59%|█████▉    | 593/1000 [01:20<00:59,  6.79it/s]

 60%|█████▉    | 595/1000 [01:21<00:48,  8.38it/s]

 60%|█████▉    | 596/1000 [01:21<00:58,  6.86it/s]

 60%|█████▉    | 597/1000 [01:21<01:00,  6.66it/s]

 60%|█████▉    | 599/1000 [01:21<01:02,  6.47it/s]

 60%|██████    | 601/1000 [01:22<01:02,  6.38it/s]

 60%|██████    | 602/1000 [01:22<00:59,  6.70it/s]

 60%|██████    | 604/1000 [01:22<01:09,  5.68it/s]

 61%|██████    | 606/1000 [01:22<00:55,  7.09it/s]

 61%|██████    | 608/1000 [01:23<00:50,  7.84it/s]

 61%|██████    | 610/1000 [01:23<00:46,  8.46it/s]

 61%|██████    | 612/1000 [01:23<00:39,  9.72it/s]

 61%|██████▏   | 614/1000 [01:23<00:35, 10.79it/s]

 62%|██████▏   | 616/1000 [01:24<00:50,  7.61it/s]

 62%|██████▏   | 617/1000 [01:24<00:49,  7.72it/s]

 62%|██████▏   | 619/1000 [01:24<00:41,  9.07it/s]

 62%|██████▏   | 621/1000 [01:24<00:47,  8.02it/s]

 62%|██████▏   | 623/1000 [01:24<00:46,  8.16it/s]

 62%|██████▎   | 625/1000 [01:25<00:50,  7.41it/s]

 63%|██████▎   | 627/1000 [01:25<00:43,  8.58it/s]

 63%|██████▎   | 628/1000 [01:25<00:51,  7.16it/s]

 63%|██████▎   | 629/1000 [01:25<00:59,  6.20it/s]

 63%|██████▎   | 631/1000 [01:25<00:47,  7.85it/s]

 63%|██████▎   | 633/1000 [01:26<00:38,  9.42it/s]

 64%|██████▎   | 635/1000 [01:26<00:54,  6.71it/s]

 64%|██████▎   | 636/1000 [01:26<00:51,  7.06it/s]

 64%|██████▍   | 638/1000 [01:26<00:45,  7.95it/s]

 64%|██████▍   | 640/1000 [01:26<00:39,  9.17it/s]

 64%|██████▍   | 642/1000 [01:27<00:44,  7.96it/s]

 64%|██████▍   | 643/1000 [01:27<00:47,  7.59it/s]

 64%|██████▍   | 645/1000 [01:27<00:50,  7.10it/s]

 65%|██████▍   | 647/1000 [01:28<00:46,  7.59it/s]

 65%|██████▍   | 648/1000 [01:28<00:53,  6.52it/s]

 65%|██████▌   | 650/1000 [01:28<00:53,  6.56it/s]

 65%|██████▌   | 652/1000 [01:28<00:55,  6.32it/s]

 65%|██████▌   | 654/1000 [01:29<00:44,  7.71it/s]

 66%|██████▌   | 656/1000 [01:29<00:38,  8.92it/s]

 66%|██████▌   | 658/1000 [01:29<00:42,  8.09it/s]

 66%|██████▌   | 659/1000 [01:29<00:56,  5.99it/s]

 66%|██████▌   | 661/1000 [01:29<00:44,  7.54it/s]

 66%|██████▌   | 662/1000 [01:30<00:52,  6.47it/s]

 66%|██████▋   | 664/1000 [01:30<00:58,  5.77it/s]

 66%|██████▋   | 665/1000 [01:30<01:03,  5.31it/s]

 67%|██████▋   | 667/1000 [01:31<00:59,  5.61it/s]

 67%|██████▋   | 668/1000 [01:31<01:03,  5.19it/s]

 67%|██████▋   | 669/1000 [01:31<00:58,  5.70it/s]

 67%|██████▋   | 671/1000 [01:31<00:55,  5.88it/s]

 67%|██████▋   | 673/1000 [01:32<00:49,  6.63it/s]

 68%|██████▊   | 675/1000 [01:32<00:44,  7.26it/s]

 68%|██████▊   | 677/1000 [01:32<00:37,  8.66it/s]

 68%|██████▊   | 679/1000 [01:32<00:33,  9.70it/s]

 68%|██████▊   | 681/1000 [01:32<00:29, 10.97it/s]

 68%|██████▊   | 683/1000 [01:33<00:35,  8.92it/s]

 68%|██████▊   | 685/1000 [01:33<00:31,  9.89it/s]

 69%|██████▊   | 687/1000 [01:33<00:45,  6.86it/s]

 69%|██████▉   | 688/1000 [01:33<00:43,  7.16it/s]

 69%|██████▉   | 690/1000 [01:34<00:45,  6.81it/s]

 69%|██████▉   | 692/1000 [01:34<00:39,  7.83it/s]

 69%|██████▉   | 694/1000 [01:34<00:42,  7.26it/s]

 70%|██████▉   | 695/1000 [01:34<00:41,  7.42it/s]

 70%|██████▉   | 696/1000 [01:35<00:47,  6.33it/s]

 70%|██████▉   | 698/1000 [01:35<00:43,  6.93it/s]

 70%|██████▉   | 699/1000 [01:35<00:49,  6.04it/s]

 70%|███████   | 701/1000 [01:35<00:39,  7.58it/s]

 70%|███████   | 702/1000 [01:36<00:53,  5.61it/s]

 70%|███████   | 704/1000 [01:36<00:41,  7.21it/s]

 70%|███████   | 705/1000 [01:36<00:54,  5.41it/s]

 71%|███████   | 707/1000 [01:36<00:41,  7.03it/s]

 71%|███████   | 709/1000 [01:36<00:38,  7.62it/s]

 71%|███████   | 710/1000 [01:37<00:44,  6.50it/s]

 71%|███████   | 712/1000 [01:37<00:37,  7.70it/s]

 71%|███████▏  | 713/1000 [01:37<00:36,  7.85it/s]

 72%|███████▏  | 715/1000 [01:37<00:30,  9.36it/s]

 72%|███████▏  | 717/1000 [01:37<00:35,  8.06it/s]

 72%|███████▏  | 718/1000 [01:38<00:41,  6.80it/s]

 72%|███████▏  | 719/1000 [01:38<00:47,  5.92it/s]

 72%|███████▏  | 720/1000 [01:38<00:43,  6.46it/s]

 72%|███████▏  | 722/1000 [01:38<00:34,  8.15it/s]

 72%|███████▏  | 723/1000 [01:38<00:33,  8.24it/s]

 72%|███████▏  | 724/1000 [01:38<00:33,  8.25it/s]

 72%|███████▎  | 725/1000 [01:38<00:33,  8.31it/s]

 73%|███████▎  | 727/1000 [01:39<00:26, 10.14it/s]

 73%|███████▎  | 729/1000 [01:39<00:23, 11.62it/s]

 73%|███████▎  | 731/1000 [01:39<00:32,  8.30it/s]

 73%|███████▎  | 733/1000 [01:39<00:28,  9.50it/s]

 74%|███████▎  | 735/1000 [01:39<00:26,  9.88it/s]

 74%|███████▎  | 737/1000 [01:40<00:27,  9.53it/s]

 74%|███████▍  | 739/1000 [01:40<00:26,  9.77it/s]

 74%|███████▍  | 741/1000 [01:40<00:31,  8.29it/s]

 74%|███████▍  | 743/1000 [01:40<00:30,  8.35it/s]

 74%|███████▍  | 745/1000 [01:41<00:26,  9.60it/s]

 75%|███████▍  | 747/1000 [01:41<00:24, 10.44it/s]

 75%|███████▍  | 749/1000 [01:41<00:29,  8.63it/s]

 75%|███████▌  | 750/1000 [01:41<00:32,  7.67it/s]

 75%|███████▌  | 751/1000 [01:42<00:40,  6.16it/s]

 75%|███████▌  | 753/1000 [01:42<00:34,  7.23it/s]

 75%|███████▌  | 754/1000 [01:42<00:39,  6.22it/s]

 76%|███████▌  | 756/1000 [01:42<00:38,  6.40it/s]

 76%|███████▌  | 758/1000 [01:42<00:31,  7.60it/s]

 76%|███████▌  | 759/1000 [01:43<00:33,  7.30it/s]

 76%|███████▌  | 761/1000 [01:43<00:27,  8.69it/s]

 76%|███████▋  | 763/1000 [01:43<00:30,  7.65it/s]

 76%|███████▋  | 764/1000 [01:43<00:35,  6.60it/s]

 77%|███████▋  | 766/1000 [01:44<00:36,  6.46it/s]

 77%|███████▋  | 768/1000 [01:44<00:29,  7.77it/s]

 77%|███████▋  | 769/1000 [01:44<00:34,  6.62it/s]

 77%|███████▋  | 770/1000 [01:44<00:35,  6.55it/s]

 77%|███████▋  | 772/1000 [01:44<00:28,  8.12it/s]

 77%|███████▋  | 773/1000 [01:45<00:35,  6.37it/s]

 77%|███████▋  | 774/1000 [01:45<00:33,  6.77it/s]

 78%|███████▊  | 776/1000 [01:45<00:28,  7.88it/s]

 78%|███████▊  | 778/1000 [01:45<00:23,  9.60it/s]

 78%|███████▊  | 780/1000 [01:46<00:31,  6.94it/s]

 78%|███████▊  | 782/1000 [01:46<00:26,  8.36it/s]

 78%|███████▊  | 784/1000 [01:46<00:30,  7.15it/s]

 79%|███████▊  | 786/1000 [01:46<00:28,  7.52it/s]

 79%|███████▉  | 788/1000 [01:46<00:25,  8.35it/s]

 79%|███████▉  | 790/1000 [01:47<00:23,  8.98it/s]

 79%|███████▉  | 791/1000 [01:47<00:25,  8.22it/s]

 79%|███████▉  | 792/1000 [01:47<00:26,  7.72it/s]

 79%|███████▉  | 793/1000 [01:47<00:25,  7.97it/s]

 80%|███████▉  | 795/1000 [01:47<00:28,  7.19it/s]

 80%|███████▉  | 797/1000 [01:48<00:29,  6.85it/s]

 80%|███████▉  | 798/1000 [01:48<00:33,  6.01it/s]

 80%|████████  | 800/1000 [01:48<00:29,  6.72it/s]

 80%|████████  | 802/1000 [01:48<00:25,  7.64it/s]

 80%|████████  | 804/1000 [01:49<00:25,  7.83it/s]

 81%|████████  | 806/1000 [01:49<00:21,  9.16it/s]

 81%|████████  | 807/1000 [01:49<00:21,  8.96it/s]

 81%|████████  | 809/1000 [01:49<00:18, 10.20it/s]

 81%|████████  | 811/1000 [01:49<00:16, 11.23it/s]

 81%|████████▏ | 813/1000 [01:49<00:20,  9.05it/s]

 82%|████████▏ | 815/1000 [01:50<00:19,  9.30it/s]

 82%|████████▏ | 817/1000 [01:50<00:22,  8.13it/s]

 82%|████████▏ | 819/1000 [01:50<00:19,  9.19it/s]

 82%|████████▏ | 821/1000 [01:50<00:22,  8.04it/s]

 82%|████████▏ | 823/1000 [01:51<00:22,  7.81it/s]

 82%|████████▏ | 824/1000 [01:51<00:26,  6.74it/s]

 82%|████████▎ | 825/1000 [01:51<00:25,  6.99it/s]

 83%|████████▎ | 826/1000 [01:51<00:30,  5.79it/s]

 83%|████████▎ | 828/1000 [01:52<00:32,  5.23it/s]

 83%|████████▎ | 829/1000 [01:52<00:29,  5.73it/s]

 83%|████████▎ | 831/1000 [01:52<00:24,  7.00it/s]

 83%|████████▎ | 832/1000 [01:52<00:29,  5.75it/s]

 83%|████████▎ | 833/1000 [01:53<00:26,  6.23it/s]

 83%|████████▎ | 834/1000 [01:53<00:27,  6.02it/s]

 84%|████████▎ | 835/1000 [01:53<00:25,  6.53it/s]

 84%|████████▎ | 836/1000 [01:53<00:26,  6.11it/s]

 84%|████████▍ | 838/1000 [01:53<00:21,  7.45it/s]

 84%|████████▍ | 840/1000 [01:54<00:24,  6.61it/s]

 84%|████████▍ | 842/1000 [01:54<00:19,  8.13it/s]

 84%|████████▍ | 844/1000 [01:54<00:24,  6.41it/s]

 84%|████████▍ | 845/1000 [01:54<00:26,  5.76it/s]

 85%|████████▍ | 847/1000 [01:55<00:24,  6.24it/s]

 85%|████████▍ | 849/1000 [01:55<00:20,  7.54it/s]

 85%|████████▌ | 850/1000 [01:55<00:23,  6.48it/s]

 85%|████████▌ | 851/1000 [01:55<00:21,  6.86it/s]

 85%|████████▌ | 853/1000 [01:55<00:17,  8.46it/s]

 86%|████████▌ | 855/1000 [01:55<00:14, 10.03it/s]

 86%|████████▌ | 857/1000 [01:56<00:14, 10.20it/s]

 86%|████████▌ | 859/1000 [01:56<00:16,  8.50it/s]

 86%|████████▌ | 861/1000 [01:56<00:14,  9.74it/s]

 86%|████████▋ | 863/1000 [01:56<00:12, 10.60it/s]

 86%|████████▋ | 865/1000 [01:56<00:11, 11.67it/s]

 87%|████████▋ | 867/1000 [01:57<00:14,  9.28it/s]

 87%|████████▋ | 869/1000 [01:57<00:12, 10.25it/s]

 87%|████████▋ | 871/1000 [01:57<00:11, 11.25it/s]

 87%|████████▋ | 873/1000 [01:57<00:16,  7.76it/s]

 88%|████████▊ | 875/1000 [01:58<00:16,  7.62it/s]

 88%|████████▊ | 877/1000 [01:58<00:13,  8.86it/s]

 88%|████████▊ | 879/1000 [01:58<00:17,  6.86it/s]

 88%|████████▊ | 881/1000 [01:58<00:15,  7.60it/s]

 88%|████████▊ | 882/1000 [01:59<00:18,  6.55it/s]

 88%|████████▊ | 884/1000 [01:59<00:14,  7.96it/s]

 89%|████████▊ | 886/1000 [01:59<00:12,  9.17it/s]

 89%|████████▉ | 888/1000 [01:59<00:10, 10.34it/s]

 89%|████████▉ | 890/1000 [01:59<00:11,  9.76it/s]

 89%|████████▉ | 892/1000 [02:00<00:10, 10.76it/s]

 89%|████████▉ | 894/1000 [02:00<00:13,  7.60it/s]

 90%|████████▉ | 896/1000 [02:00<00:11,  8.83it/s]

 90%|████████▉ | 898/1000 [02:01<00:15,  6.53it/s]

 90%|█████████ | 900/1000 [02:01<00:12,  7.69it/s]

 90%|█████████ | 902/1000 [02:01<00:12,  7.86it/s]

 90%|█████████ | 904/1000 [02:01<00:10,  9.06it/s]

 91%|█████████ | 906/1000 [02:02<00:13,  7.04it/s]

 91%|█████████ | 908/1000 [02:02<00:11,  8.30it/s]

 91%|█████████ | 910/1000 [02:02<00:11,  7.58it/s]

 91%|█████████ | 912/1000 [02:02<00:10,  8.76it/s]

 91%|█████████▏| 914/1000 [02:03<00:11,  7.39it/s]

 92%|█████████▏| 916/1000 [02:03<00:11,  7.08it/s]

 92%|█████████▏| 917/1000 [02:03<00:11,  7.37it/s]

 92%|█████████▏| 918/1000 [02:03<00:14,  5.60it/s]

 92%|█████████▏| 919/1000 [02:03<00:14,  5.72it/s]

 92%|█████████▏| 921/1000 [02:04<00:14,  5.58it/s]

 92%|█████████▏| 922/1000 [02:04<00:13,  5.94it/s]

 92%|█████████▏| 924/1000 [02:04<00:10,  7.17it/s]

 93%|█████████▎| 926/1000 [02:04<00:08,  8.65it/s]

 93%|█████████▎| 927/1000 [02:04<00:09,  8.10it/s]

 93%|█████████▎| 928/1000 [02:05<00:10,  6.65it/s]

 93%|█████████▎| 930/1000 [02:05<00:10,  6.47it/s]

 93%|█████████▎| 931/1000 [02:05<00:10,  6.82it/s]

 93%|█████████▎| 933/1000 [02:05<00:10,  6.61it/s]

 93%|█████████▎| 934/1000 [02:06<00:10,  6.18it/s]

 94%|█████████▎| 936/1000 [02:06<00:08,  7.31it/s]

 94%|█████████▍| 938/1000 [02:06<00:07,  8.83it/s]

 94%|█████████▍| 939/1000 [02:06<00:07,  8.04it/s]

 94%|█████████▍| 940/1000 [02:06<00:07,  8.13it/s]

 94%|█████████▍| 942/1000 [02:07<00:09,  6.34it/s]

 94%|█████████▍| 944/1000 [02:07<00:07,  7.08it/s]

 95%|█████████▍| 946/1000 [02:07<00:06,  8.38it/s]

 95%|█████████▍| 948/1000 [02:07<00:05,  9.70it/s]

 95%|█████████▌| 950/1000 [02:08<00:05,  8.82it/s]

 95%|█████████▌| 952/1000 [02:08<00:06,  7.41it/s]

 95%|█████████▌| 954/1000 [02:08<00:07,  6.16it/s]

 96%|█████████▌| 956/1000 [02:08<00:05,  7.40it/s]

 96%|█████████▌| 957/1000 [02:09<00:06,  6.40it/s]

 96%|█████████▌| 959/1000 [02:09<00:07,  5.78it/s]

 96%|█████████▌| 961/1000 [02:09<00:05,  6.81it/s]

 96%|█████████▌| 962/1000 [02:10<00:06,  6.04it/s]

 96%|█████████▋| 964/1000 [02:10<00:04,  7.49it/s]

 96%|█████████▋| 965/1000 [02:10<00:05,  6.44it/s]

 97%|█████████▋| 966/1000 [02:10<00:05,  6.34it/s]

 97%|█████████▋| 968/1000 [02:10<00:03,  8.01it/s]

 97%|█████████▋| 970/1000 [02:10<00:03,  9.41it/s]

 97%|█████████▋| 972/1000 [02:11<00:03,  8.01it/s]

 97%|█████████▋| 974/1000 [02:11<00:02,  9.20it/s]

 98%|█████████▊| 976/1000 [02:11<00:02,  9.80it/s]

 98%|█████████▊| 978/1000 [02:11<00:02, 10.82it/s]

 98%|█████████▊| 980/1000 [02:12<00:02,  8.43it/s]

 98%|█████████▊| 981/1000 [02:12<00:02,  7.06it/s]

 98%|█████████▊| 982/1000 [02:12<00:03,  5.44it/s]

 98%|█████████▊| 984/1000 [02:12<00:02,  6.92it/s]

 99%|█████████▊| 986/1000 [02:12<00:01,  8.36it/s]

 99%|█████████▉| 988/1000 [02:13<00:01,  6.73it/s]

 99%|█████████▉| 989/1000 [02:13<00:01,  5.99it/s]

 99%|█████████▉| 991/1000 [02:13<00:01,  6.15it/s]

 99%|█████████▉| 992/1000 [02:14<00:01,  4.98it/s]

 99%|█████████▉| 994/1000 [02:14<00:00,  6.54it/s]

100%|█████████▉| 995/1000 [02:14<00:00,  5.53it/s]

100%|█████████▉| 997/1000 [02:14<00:00,  7.05it/s]

100%|█████████▉| 999/1000 [02:15<00:00,  6.76it/s]

100%|██████████| 1000/1000 [02:15<00:00,  6.67it/s]
                                                       

                                                   
{'eval_loss': '0.7632', 'eval_runtime': '135.5', 'eval_samples_per_second': '7.381', 'eval_steps_per_second': '7.381', 'epoch': '0.6621', 'num_input_tokens_seen': 8055352}

 66%|██████▌   | 1200/1813 [2:14:04<1:05:05,  6.37s/it]

100%|██████████| 1000/1000 [02:15<00:00,  6.67it/s]

                                                   
 66%|██████▌   | 1201/1813 [2:14:09<7:57:02, 46.77s/it]
 66%|██████▋   | 1202/1813 [2:14:16<5:53:44, 34.74s/it]
 66%|██████▋   | 1203/1813 [2:14:22<4:27:14, 26.29s/it]
 66%|██████▋   | 1204/1813 [2:14:29<3:27:01, 20.40s/it]
 66%|██████▋   | 1205/1813 [2:14:36<2:44:32, 16.24s/it]
 67%|██████▋   | 1206/1813 [2:14:42<2:13:35, 13.21s/it]
 67%|██████▋   | 1207/1813 [2:14:48<1:52:07, 11.10s/it]
 67%|██████▋   | 1208/1813 [2:14:55<1:41:05, 10.03s/it]
 67%|██████▋   | 1209/1813 [2:15:02<1:30:57,  9.04s/it]
 67%|██████▋   | 1210/1813 [2:15:08<1:21:05,  8.07s/it]
                                                       
{'loss': '0.9283', 'grad_norm': '0.954', 'learning_rate': '2.917e-05', 'epoch': '0.6676', 'num_input_tokens_seen': 8125224, 'train_runtime': '8109', 'train_tokens_per_second': '1002'}

 67%|██████▋   | 1210/1813 [2:15:08<1:21:05,  8.07s/it]
 67%|██████▋   | 1211/1813 [2:15:15<1:17:22,  7.71s/it]
 67%|██████▋   | 1212/1813 [2:15:19<1:07:07,  6.70s/it]
 67%|██████▋   | 1213/1813 [2:15:26<1:06:21,  6.64s/it]
 67%|██████▋   | 1214/1813 [2:15:34<1:11:26,  7.16s/it]
 67%|██████▋   | 1215/1813 [2:15:40<1:08:28,  6.87s/it]
 67%|██████▋   | 1216/1813 [2:15:47<1:08:56,  6.93s/it]
 67%|██████▋   | 1217/1813 [2:15:53<1:05:52,  6.63s/it]
 67%|██████▋   | 1218/1813 [2:15:59<1:04:25,  6.50s/it]
 67%|██████▋   | 1219/1813 [2:16:05<1:01:02,  6.17s/it]
 67%|██████▋   | 1220/1813 [2:16:13<1:06:39,  6.74s/it]
                                                       
{'loss': '0.9578', 'grad_norm': '7.803', 'learning_rate': '2.831e-05', 'epoch': '0.6731', 'num_input_tokens_seen': 8197488, 'train_runtime': '8173', 'train_tokens_per_second': '1003'}

 67%|██████▋   | 1220/1813 [2:16:13<1:06:39,  6.74s/it]
 67%|██████▋   | 1221/1813 [2:16:18<1:02:13,  6.31s/it]
 67%|██████▋   | 1222/1813 [2:16:23<58:13,  5.91s/it]  
 67%|██████▋   | 1223/1813 [2:16:29<56:51,  5.78s/it]
 68%|██████▊   | 1224/1813 [2:16:34<54:17,  5.53s/it]
 68%|██████▊   | 1225/1813 [2:16:40<55:49,  5.70s/it]
 68%|██████▊   | 1226/1813 [2:16:46<56:44,  5.80s/it]
 68%|██████▊   | 1227/1813 [2:16:52<58:40,  6.01s/it]
 68%|██████▊   | 1228/1813 [2:16:58<56:37,  5.81s/it]
 68%|██████▊   | 1229/1813 [2:17:04<58:36,  6.02s/it]
 68%|██████▊   | 1230/1813 [2:17:10<58:44,  6.04s/it]
                                                     
{'loss': '0.8137', 'grad_norm': '0.7522', 'learning_rate': '2.746e-05', 'epoch': '0.6786', 'num_input_tokens_seen': 8257288, 'train_runtime': '8231', 'train_tokens_per_second': '1003'}

 68%|██████▊   | 1230/1813 [2:17:10<58:44,  6.04s/it]
 68%|██████▊   | 1231/1813 [2:17:18<1:03:19,  6.53s/it]
 68%|██████▊   | 1232/1813 [2:17:25<1:05:50,  6.80s/it]
 68%|██████▊   | 1233/1813 [2:17:32<1:04:29,  6.67s/it]
 68%|██████▊   | 1234/1813 [2:17:38<1:02:47,  6.51s/it]
 68%|██████▊   | 1235/1813 [2:17:44<1:01:59,  6.44s/it]
 68%|██████▊   | 1236/1813 [2:17:53<1:07:45,  7.05s/it]
 68%|██████▊   | 1237/1813 [2:17:59<1:05:36,  6.83s/it]
 68%|██████▊   | 1238/1813 [2:18:05<1:02:06,  6.48s/it]
 68%|██████▊   | 1239/1813 [2:18:10<58:56,  6.16s/it]  
 68%|██████▊   | 1240/1813 [2:18:15<56:33,  5.92s/it]
                                                     
{'loss': '0.819', 'grad_norm': '0.8135', 'learning_rate': '2.663e-05', 'epoch': '0.6841', 'num_input_tokens_seen': 8327600, 'train_runtime': '8296', 'train_tokens_per_second': '1004'}

 68%|██████▊   | 1240/1813 [2:18:15<56:33,  5.92s/it]
 68%|██████▊   | 1241/1813 [2:18:21<56:07,  5.89s/it]
 69%|██████▊   | 1242/1813 [2:18:27<56:38,  5.95s/it]
 69%|██████▊   | 1243/1813 [2:18:33<57:04,  6.01s/it]
 69%|██████▊   | 1244/1813 [2:18:40<59:26,  6.27s/it]
 69%|██████▊   | 1245/1813 [2:18:48<1:02:25,  6.59s/it]
 69%|██████▊   | 1246/1813 [2:18:53<1:00:13,  6.37s/it]
 69%|██████▉   | 1247/1813 [2:19:00<1:01:14,  6.49s/it]
 69%|██████▉   | 1248/1813 [2:19:07<1:01:52,  6.57s/it]
 69%|██████▉   | 1249/1813 [2:19:13<1:01:21,  6.53s/it]
 69%|██████▉   | 1250/1813 [2:19:18<56:30,  6.02s/it]  
                                                     
{'loss': '0.9586', 'grad_norm': '1.12', 'learning_rate': '2.579e-05', 'epoch': '0.6897', 'num_input_tokens_seen': 8394824, 'train_runtime': '8359', 'train_tokens_per_second': '1004'}

 69%|██████▉   | 1250/1813 [2:19:18<56:30,  6.02s/it]
 69%|██████▉   | 1251/1813 [2:19:24<56:35,  6.04s/it]
 69%|██████▉   | 1252/1813 [2:19:30<55:21,  5.92s/it]
 69%|██████▉   | 1253/1813 [2:19:36<55:17,  5.92s/it]
 69%|██████▉   | 1254/1813 [2:19:43<57:03,  6.12s/it]
 69%|██████▉   | 1255/1813 [2:19:49<57:20,  6.17s/it]
 69%|██████▉   | 1256/1813 [2:19:55<57:11,  6.16s/it]
 69%|██████▉   | 1257/1813 [2:20:01<56:05,  6.05s/it]
 69%|██████▉   | 1258/1813 [2:20:08<58:08,  6.29s/it]
 69%|██████▉   | 1259/1813 [2:20:14<58:41,  6.36s/it]
 69%|██████▉   | 1260/1813 [2:20:21<1:00:24,  6.55s/it]
                                                       
{'loss': '0.9177', 'grad_norm': '1.085', 'learning_rate': '2.497e-05', 'epoch': '0.6952', 'num_input_tokens_seen': 8461096, 'train_runtime': '8422', 'train_tokens_per_second': '1005'}

 69%|██████▉   | 1260/1813 [2:20:21<1:00:24,  6.55s/it]
 70%|██████▉   | 1261/1813 [2:20:29<1:04:27,  7.01s/it]
 70%|██████▉   | 1262/1813 [2:20:37<1:05:32,  7.14s/it]
 70%|██████▉   | 1263/1813 [2:20:44<1:05:41,  7.17s/it]
 70%|██████▉   | 1264/1813 [2:20:50<1:01:32,  6.73s/it]
 70%|██████▉   | 1265/1813 [2:20:55<56:58,  6.24s/it]  
 70%|██████▉   | 1266/1813 [2:21:02<1:00:37,  6.65s/it]
 70%|██████▉   | 1267/1813 [2:21:07<55:58,  6.15s/it]  
 70%|██████▉   | 1268/1813 [2:21:12<52:07,  5.74s/it]
 70%|██████▉   | 1269/1813 [2:21:17<50:28,  5.57s/it]
 70%|███████   | 1270/1813 [2:21:23<51:20,  5.67s/it]
                                                     
{'loss': '0.9102', 'grad_norm': '0.9747', 'learning_rate': '2.416e-05', 'epoch': '0.7007', 'num_input_tokens_seen': 8529224, 'train_runtime': '8484', 'train_tokens_per_second': '1005'}

 70%|███████   | 1270/1813 [2:21:23<51:20,  5.67s/it]
 70%|███████   | 1271/1813 [2:21:28<48:26,  5.36s/it]
 70%|███████   | 1272/1813 [2:21:35<52:24,  5.81s/it]
 70%|███████   | 1273/1813 [2:21:41<55:02,  6.11s/it]
 70%|███████   | 1274/1813 [2:21:49<57:58,  6.45s/it]
 70%|███████   | 1275/1813 [2:21:55<58:31,  6.53s/it]
 70%|███████   | 1276/1813 [2:22:01<55:50,  6.24s/it]
 70%|███████   | 1277/1813 [2:22:08<57:49,  6.47s/it]
 70%|███████   | 1278/1813 [2:22:14<55:20,  6.21s/it]
 71%|███████   | 1279/1813 [2:22:19<52:12,  5.87s/it]
 71%|███████   | 1280/1813 [2:22:26<55:26,  6.24s/it]
                                                     
{'loss': '0.9284', 'grad_norm': '1.056', 'learning_rate': '2.336e-05', 'epoch': '0.7062', 'num_input_tokens_seen': 8596456, 'train_runtime': '8546', 'train_tokens_per_second': '1006'}

 71%|███████   | 1280/1813 [2:22:26<55:26,  6.24s/it]
 71%|███████   | 1281/1813 [2:22:31<53:17,  6.01s/it]
 71%|███████   | 1282/1813 [2:22:38<53:59,  6.10s/it]
 71%|███████   | 1283/1813 [2:22:44<55:49,  6.32s/it]
 71%|███████   | 1284/1813 [2:22:50<54:41,  6.20s/it]
 71%|███████   | 1285/1813 [2:22:56<52:38,  5.98s/it]
 71%|███████   | 1286/1813 [2:23:03<55:55,  6.37s/it]
 71%|███████   | 1287/1813 [2:23:09<55:30,  6.33s/it]
 71%|███████   | 1288/1813 [2:23:15<53:04,  6.07s/it]
 71%|███████   | 1289/1813 [2:23:22<55:01,  6.30s/it]
 71%|███████   | 1290/1813 [2:23:29<57:36,  6.61s/it]
                                                     
{'loss': '0.9834', 'grad_norm': '0.6644', 'learning_rate': '2.256e-05', 'epoch': '0.7117', 'num_input_tokens_seen': 8662472, 'train_runtime': '8609', 'train_tokens_per_second': '1006'}

 71%|███████   | 1290/1813 [2:23:29<57:36,  6.61s/it]
 71%|███████   | 1291/1813 [2:23:35<56:48,  6.53s/it]
 71%|███████▏  | 1292/1813 [2:23:42<57:43,  6.65s/it]
 71%|███████▏  | 1293/1813 [2:23:49<58:27,  6.75s/it]
 71%|███████▏  | 1294/1813 [2:23:55<57:25,  6.64s/it]
 71%|███████▏  | 1295/1813 [2:24:02<55:54,  6.48s/it]
 71%|███████▏  | 1296/1813 [2:24:07<53:29,  6.21s/it]
 72%|███████▏  | 1297/1813 [2:24:13<51:16,  5.96s/it]
 72%|███████▏  | 1298/1813 [2:24:19<53:04,  6.18s/it]
 72%|███████▏  | 1299/1813 [2:24:26<54:51,  6.40s/it]
 72%|███████▏  | 1300/1813 [2:24:32<54:12,  6.34s/it]
                                                     
{'loss': '0.8826', 'grad_norm': '1.069', 'learning_rate': '2.178e-05', 'epoch': '0.7172', 'num_input_tokens_seen': 8730600, 'train_runtime': '8673', 'train_tokens_per_second': '1007'}

 72%|███████▏  | 1300/1813 [2:24:32<54:12,  6.34s/it]
 72%|███████▏  | 1301/1813 [2:24:38<53:11,  6.23s/it]
 72%|███████▏  | 1302/1813 [2:24:45<53:57,  6.34s/it]
 72%|███████▏  | 1303/1813 [2:24:53<57:42,  6.79s/it]
 72%|███████▏  | 1304/1813 [2:24:58<54:40,  6.44s/it]
 72%|███████▏  | 1305/1813 [2:25:06<57:14,  6.76s/it]
 72%|███████▏  | 1306/1813 [2:25:12<54:48,  6.49s/it]
 72%|███████▏  | 1307/1813 [2:25:18<53:59,  6.40s/it]
 72%|███████▏  | 1308/1813 [2:25:24<53:55,  6.41s/it]
 72%|███████▏  | 1309/1813 [2:25:31<53:22,  6.35s/it]
 72%|███████▏  | 1310/1813 [2:25:38<54:43,  6.53s/it]
                                                     
{'loss': '0.9633', 'grad_norm': '0.8692', 'learning_rate': '2.1e-05', 'epoch': '0.7228', 'num_input_tokens_seen': 8802000, 'train_runtime': '8738', 'train_tokens_per_second': '1007'}

 72%|███████▏  | 1310/1813 [2:25:38<54:43,  6.53s/it]
 72%|███████▏  | 1311/1813 [2:25:44<53:56,  6.45s/it]
 72%|███████▏  | 1312/1813 [2:25:50<51:59,  6.23s/it]
 72%|███████▏  | 1313/1813 [2:25:55<51:14,  6.15s/it]
 72%|███████▏  | 1314/1813 [2:26:02<51:26,  6.19s/it]
 73%|███████▎  | 1315/1813 [2:26:07<50:11,  6.05s/it]
 73%|███████▎  | 1316/1813 [2:26:13<50:01,  6.04s/it]
 73%|███████▎  | 1317/1813 [2:26:20<50:28,  6.11s/it]
 73%|███████▎  | 1318/1813 [2:26:26<49:31,  6.00s/it]
 73%|███████▎  | 1319/1813 [2:26:32<50:57,  6.19s/it]
 73%|███████▎  | 1320/1813 [2:26:39<52:33,  6.40s/it]
                                                     
{'loss': '0.9467', 'grad_norm': '0.7702', 'learning_rate': '2.024e-05', 'epoch': '0.7283', 'num_input_tokens_seen': 8866824, 'train_runtime': '8800', 'train_tokens_per_second': '1008'}

 73%|███████▎  | 1320/1813 [2:26:39<52:33,  6.40s/it]
 73%|███████▎  | 1321/1813 [2:26:46<52:55,  6.45s/it]
 73%|███████▎  | 1322/1813 [2:26:52<51:36,  6.31s/it]
 73%|███████▎  | 1323/1813 [2:26:58<52:21,  6.41s/it]
 73%|███████▎  | 1324/1813 [2:27:04<50:45,  6.23s/it]
 73%|███████▎  | 1325/1813 [2:27:10<49:24,  6.08s/it]
 73%|███████▎  | 1326/1813 [2:27:16<49:49,  6.14s/it]
 73%|███████▎  | 1327/1813 [2:27:24<53:41,  6.63s/it]
 73%|███████▎  | 1328/1813 [2:27:31<54:17,  6.72s/it]
 73%|███████▎  | 1329/1813 [2:27:37<52:57,  6.57s/it]
 73%|███████▎  | 1330/1813 [2:27:43<50:38,  6.29s/it]
                                                     
{'loss': '0.8939', 'grad_norm': '0.9541', 'learning_rate': '1.948e-05', 'epoch': '0.7338', 'num_input_tokens_seen': 8935584, 'train_runtime': '8863', 'train_tokens_per_second': '1008'}

 73%|███████▎  | 1330/1813 [2:27:43<50:38,  6.29s/it]
 73%|███████▎  | 1331/1813 [2:27:48<49:34,  6.17s/it]
 73%|███████▎  | 1332/1813 [2:27:54<48:56,  6.11s/it]
 74%|███████▎  | 1333/1813 [2:28:00<48:26,  6.06s/it]
 74%|███████▎  | 1334/1813 [2:28:06<47:10,  5.91s/it]
 74%|███████▎  | 1335/1813 [2:28:12<46:17,  5.81s/it]
 74%|███████▎  | 1336/1813 [2:28:18<47:12,  5.94s/it]
 74%|███████▎  | 1337/1813 [2:28:25<50:44,  6.40s/it]
 74%|███████▍  | 1338/1813 [2:28:33<52:51,  6.68s/it]
 74%|███████▍  | 1339/1813 [2:28:38<49:46,  6.30s/it]
 74%|███████▍  | 1340/1813 [2:28:45<51:18,  6.51s/it]
                                                     
{'loss': '0.9832', 'grad_norm': '0.8213', 'learning_rate': '1.874e-05', 'epoch': '0.7393', 'num_input_tokens_seen': 9000416, 'train_runtime': '8925', 'train_tokens_per_second': '1008'}

 74%|███████▍  | 1340/1813 [2:28:45<51:18,  6.51s/it]
 74%|███████▍  | 1341/1813 [2:28:52<51:26,  6.54s/it]
 74%|███████▍  | 1342/1813 [2:28:57<48:55,  6.23s/it]
 74%|███████▍  | 1343/1813 [2:29:03<47:31,  6.07s/it]
 74%|███████▍  | 1344/1813 [2:29:09<47:06,  6.03s/it]
 74%|███████▍  | 1345/1813 [2:29:16<50:42,  6.50s/it]
 74%|███████▍  | 1346/1813 [2:29:23<50:22,  6.47s/it]
 74%|███████▍  | 1347/1813 [2:29:28<48:28,  6.24s/it]
 74%|███████▍  | 1348/1813 [2:29:35<48:20,  6.24s/it]
 74%|███████▍  | 1349/1813 [2:29:41<48:59,  6.34s/it]
 74%|███████▍  | 1350/1813 [2:29:47<47:17,  6.13s/it]
                                                     
{'loss': '0.9344', 'grad_norm': '1.063', 'learning_rate': '1.801e-05', 'epoch': '0.7448', 'num_input_tokens_seen': 9066864, 'train_runtime': '8987', 'train_tokens_per_second': '1009'}

 74%|███████▍  | 1350/1813 [2:29:47<47:17,  6.13s/it]
 75%|███████▍  | 1351/1813 [2:29:55<51:13,  6.65s/it]
 75%|███████▍  | 1352/1813 [2:30:01<50:10,  6.53s/it]
 75%|███████▍  | 1353/1813 [2:30:08<50:43,  6.62s/it]
 75%|███████▍  | 1354/1813 [2:30:15<51:01,  6.67s/it]
 75%|███████▍  | 1355/1813 [2:30:23<55:03,  7.21s/it]
 75%|███████▍  | 1356/1813 [2:30:29<51:31,  6.76s/it]
 75%|███████▍  | 1357/1813 [2:30:35<49:39,  6.53s/it]
 75%|███████▍  | 1358/1813 [2:30:41<49:42,  6.56s/it]
 75%|███████▍  | 1359/1813 [2:30:47<48:02,  6.35s/it]
 75%|███████▌  | 1360/1813 [2:30:53<46:58,  6.22s/it]
                                                     
{'loss': '0.8969', 'grad_norm': '1.113', 'learning_rate': '1.729e-05', 'epoch': '0.7503', 'num_input_tokens_seen': 9140520, 'train_runtime': '9054', 'train_tokens_per_second': '1010'}

 75%|███████▌  | 1360/1813 [2:30:53<46:58,  6.22s/it]
 75%|███████▌  | 1361/1813 [2:31:00<47:50,  6.35s/it]
 75%|███████▌  | 1362/1813 [2:31:06<47:38,  6.34s/it]
 75%|███████▌  | 1363/1813 [2:31:14<49:53,  6.65s/it]
 75%|███████▌  | 1364/1813 [2:31:19<48:13,  6.44s/it]
 75%|███████▌  | 1365/1813 [2:31:27<50:25,  6.75s/it]
 75%|███████▌  | 1366/1813 [2:31:33<48:28,  6.51s/it]
 75%|███████▌  | 1367/1813 [2:31:39<48:28,  6.52s/it]
 75%|███████▌  | 1368/1813 [2:31:44<45:02,  6.07s/it]
 76%|███████▌  | 1369/1813 [2:31:53<49:17,  6.66s/it]
 76%|███████▌  | 1370/1813 [2:31:58<47:37,  6.45s/it]
                                                     
{'loss': '0.8836', 'grad_norm': '0.8735', 'learning_rate': '1.658e-05', 'epoch': '0.7559', 'num_input_tokens_seen': 9213048, 'train_runtime': '9119', 'train_tokens_per_second': '1010'}

 76%|███████▌  | 1370/1813 [2:31:58<47:37,  6.45s/it]
 76%|███████▌  | 1371/1813 [2:32:06<50:57,  6.92s/it]
 76%|███████▌  | 1372/1813 [2:32:12<47:03,  6.40s/it]
 76%|███████▌  | 1373/1813 [2:32:18<46:10,  6.30s/it]
 76%|███████▌  | 1374/1813 [2:32:24<45:10,  6.18s/it]
 76%|███████▌  | 1375/1813 [2:32:30<44:35,  6.11s/it]
 76%|███████▌  | 1376/1813 [2:32:35<43:16,  5.94s/it]
 76%|███████▌  | 1377/1813 [2:32:41<44:03,  6.06s/it]
 76%|███████▌  | 1378/1813 [2:32:47<43:15,  5.97s/it]
 76%|███████▌  | 1379/1813 [2:32:53<43:27,  6.01s/it]
 76%|███████▌  | 1380/1813 [2:33:00<45:47,  6.35s/it]
                                                     
{'loss': '0.8775', 'grad_norm': '1.015', 'learning_rate': '1.588e-05', 'epoch': '0.7614', 'num_input_tokens_seen': 9279088, 'train_runtime': '9181', 'train_tokens_per_second': '1011'}

 76%|███████▌  | 1380/1813 [2:33:00<45:47,  6.35s/it]
 76%|███████▌  | 1381/1813 [2:33:08<47:18,  6.57s/it]
 76%|███████▌  | 1382/1813 [2:33:13<45:06,  6.28s/it]
 76%|███████▋  | 1383/1813 [2:33:19<44:42,  6.24s/it]
 76%|███████▋  | 1384/1813 [2:33:25<43:57,  6.15s/it]
 76%|███████▋  | 1385/1813 [2:33:32<45:24,  6.36s/it]
 76%|███████▋  | 1386/1813 [2:33:39<45:37,  6.41s/it]
 77%|███████▋  | 1387/1813 [2:33:46<47:10,  6.64s/it]
 77%|███████▋  | 1388/1813 [2:33:51<44:33,  6.29s/it]
 77%|███████▋  | 1389/1813 [2:33:56<40:13,  5.69s/it]
 77%|███████▋  | 1390/1813 [2:34:02<42:12,  5.99s/it]
                                                     
{'loss': '0.9474', 'grad_norm': '0.9559', 'learning_rate': '1.52e-05', 'epoch': '0.7669', 'num_input_tokens_seen': 9344880, 'train_runtime': '9243', 'train_tokens_per_second': '1011'}

 77%|███████▋  | 1390/1813 [2:34:02<42:12,  5.99s/it]
 77%|███████▋  | 1391/1813 [2:34:07<40:27,  5.75s/it]
 77%|███████▋  | 1392/1813 [2:34:14<42:15,  6.02s/it]
 77%|███████▋  | 1393/1813 [2:34:20<40:59,  5.86s/it]
 77%|███████▋  | 1394/1813 [2:34:26<42:53,  6.14s/it]
 77%|███████▋  | 1395/1813 [2:34:33<43:16,  6.21s/it]
 77%|███████▋  | 1396/1813 [2:34:39<43:17,  6.23s/it]
 77%|███████▋  | 1397/1813 [2:34:46<44:41,  6.44s/it]
 77%|███████▋  | 1398/1813 [2:34:51<41:28,  6.00s/it]
 77%|███████▋  | 1399/1813 [2:34:56<39:22,  5.71s/it]
 77%|███████▋  | 1400/1813 [2:35:03<41:28,  6.03s/it]
                                                     
{'loss': '0.8827', 'grad_norm': '0.7981', 'learning_rate': '1.453e-05', 'epoch': '0.7724', 'num_input_tokens_seen': 9408280, 'train_runtime': '9303', 'train_tokens_per_second': '1011'}

 77%|███████▋  | 1400/1813 [2:35:03<41:28,  6.03s/it]
 77%|███████▋  | 1401/1813 [2:35:08<40:18,  5.87s/it]
 77%|███████▋  | 1402/1813 [2:35:14<40:45,  5.95s/it]
 77%|███████▋  | 1403/1813 [2:35:21<42:13,  6.18s/it]
 77%|███████▋  | 1404/1813 [2:35:27<42:35,  6.25s/it]
 77%|███████▋  | 1405/1813 [2:35:32<39:52,  5.86s/it]
 78%|███████▊  | 1406/1813 [2:35:38<39:34,  5.83s/it]
 78%|███████▊  | 1407/1813 [2:35:45<40:50,  6.04s/it]
 78%|███████▊  | 1408/1813 [2:35:50<38:52,  5.76s/it]
 78%|███████▊  | 1409/1813 [2:35:54<36:21,  5.40s/it]
 78%|███████▊  | 1410/1813 [2:36:00<37:00,  5.51s/it]
                                                     
{'loss': '0.9374', 'grad_norm': '1.029', 'learning_rate': '1.387e-05', 'epoch': '0.7779', 'num_input_tokens_seen': 9467408, 'train_runtime': '9361', 'train_tokens_per_second': '1011'}

 78%|███████▊  | 1410/1813 [2:36:00<37:00,  5.51s/it]
 78%|███████▊  | 1411/1813 [2:36:05<36:28,  5.44s/it]
 78%|███████▊  | 1412/1813 [2:36:12<38:09,  5.71s/it]
 78%|███████▊  | 1413/1813 [2:36:17<37:51,  5.68s/it]
 78%|███████▊  | 1414/1813 [2:36:24<38:49,  5.84s/it]
 78%|███████▊  | 1415/1813 [2:36:31<41:20,  6.23s/it]
 78%|███████▊  | 1416/1813 [2:36:37<41:07,  6.21s/it]
 78%|███████▊  | 1417/1813 [2:36:42<39:20,  5.96s/it]
 78%|███████▊  | 1418/1813 [2:36:48<38:54,  5.91s/it]
 78%|███████▊  | 1419/1813 [2:36:57<44:11,  6.73s/it]
 78%|███████▊  | 1420/1813 [2:37:01<40:08,  6.13s/it]
                                                     
{'loss': '0.8896', 'grad_norm': '0.9979', 'learning_rate': '1.322e-05', 'epoch': '0.7834', 'num_input_tokens_seen': 9532720, 'train_runtime': '9422', 'train_tokens_per_second': '1012'}

 78%|███████▊  | 1420/1813 [2:37:01<40:08,  6.13s/it]
 78%|███████▊  | 1421/1813 [2:37:08<41:37,  6.37s/it]
 78%|███████▊  | 1422/1813 [2:37:14<39:58,  6.13s/it]
 78%|███████▊  | 1423/1813 [2:37:20<38:48,  5.97s/it]
 79%|███████▊  | 1424/1813 [2:37:27<41:40,  6.43s/it]
 79%|███████▊  | 1425/1813 [2:37:32<38:32,  5.96s/it]
 79%|███████▊  | 1426/1813 [2:37:41<43:33,  6.75s/it]
 79%|███████▊  | 1427/1813 [2:37:46<41:01,  6.38s/it]
 79%|███████▉  | 1428/1813 [2:37:53<41:36,  6.48s/it]
 79%|███████▉  | 1429/1813 [2:37:59<40:57,  6.40s/it]
 79%|███████▉  | 1430/1813 [2:38:06<41:40,  6.53s/it]
                                                     
{'loss': '0.8718', 'grad_norm': '0.9045', 'learning_rate': '1.259e-05', 'epoch': '0.789', 'num_input_tokens_seen': 9602112, 'train_runtime': '9486', 'train_tokens_per_second': '1012'}

 79%|███████▉  | 1430/1813 [2:38:06<41:40,  6.53s/it]
 79%|███████▉  | 1431/1813 [2:38:12<40:31,  6.36s/it]
 79%|███████▉  | 1432/1813 [2:38:18<39:34,  6.23s/it]
 79%|███████▉  | 1433/1813 [2:38:24<39:50,  6.29s/it]
 79%|███████▉  | 1434/1813 [2:38:31<40:02,  6.34s/it]
 79%|███████▉  | 1435/1813 [2:38:36<38:32,  6.12s/it]
 79%|███████▉  | 1436/1813 [2:38:43<40:03,  6.38s/it]
 79%|███████▉  | 1437/1813 [2:38:49<38:50,  6.20s/it]
 79%|███████▉  | 1438/1813 [2:38:56<40:42,  6.51s/it]
 79%|███████▉  | 1439/1813 [2:39:02<38:32,  6.18s/it]
 79%|███████▉  | 1440/1813 [2:39:07<36:12,  5.82s/it]
                                                     
{'loss': '0.8798', 'grad_norm': '0.9689', 'learning_rate': '1.197e-05', 'epoch': '0.7945', 'num_input_tokens_seen': 9667112, 'train_runtime': '9547', 'train_tokens_per_second': '1013'}

 79%|███████▉  | 1440/1813 [2:39:07<36:12,  5.82s/it]
 79%|███████▉  | 1441/1813 [2:39:13<37:06,  5.99s/it]
 80%|███████▉  | 1442/1813 [2:39:18<35:46,  5.78s/it]
 80%|███████▉  | 1443/1813 [2:39:24<34:39,  5.62s/it]
 80%|███████▉  | 1444/1813 [2:39:30<36:37,  5.95s/it]
 80%|███████▉  | 1445/1813 [2:39:36<35:52,  5.85s/it]
 80%|███████▉  | 1446/1813 [2:39:42<35:28,  5.80s/it]
 80%|███████▉  | 1447/1813 [2:39:50<39:45,  6.52s/it]
 80%|███████▉  | 1448/1813 [2:39:57<41:11,  6.77s/it]
 80%|███████▉  | 1449/1813 [2:40:04<40:52,  6.74s/it]
 80%|███████▉  | 1450/1813 [2:40:10<40:33,  6.70s/it]
                                                     
{'loss': '0.9669', 'grad_norm': '0.9346', 'learning_rate': '1.136e-05', 'epoch': '0.8', 'num_input_tokens_seen': 9735792, 'train_runtime': '9611', 'train_tokens_per_second': '1013'}

 80%|███████▉  | 1450/1813 [2:40:10<40:33,  6.70s/it]
 80%|████████  | 1451/1813 [2:40:17<40:55,  6.78s/it]
 80%|████████  | 1452/1813 [2:40:22<36:42,  6.10s/it]
 80%|████████  | 1453/1813 [2:40:30<40:46,  6.80s/it]
 80%|████████  | 1454/1813 [2:40:36<38:30,  6.43s/it]
 80%|████████  | 1455/1813 [2:40:42<37:58,  6.36s/it]
 80%|████████  | 1456/1813 [2:40:49<39:25,  6.63s/it]
 80%|████████  | 1457/1813 [2:40:53<34:41,  5.85s/it]
 80%|████████  | 1458/1813 [2:40:59<34:28,  5.83s/it]
 80%|████████  | 1459/1813 [2:41:06<36:41,  6.22s/it]
 81%|████████  | 1460/1813 [2:41:13<38:15,  6.50s/it]
                                                     
{'loss': '0.9149', 'grad_norm': '0.947', 'learning_rate': '1.077e-05', 'epoch': '0.8055', 'num_input_tokens_seen': 9802968, 'train_runtime': '9674', 'train_tokens_per_second': '1013'}

 81%|████████  | 1460/1813 [2:41:13<38:15,  6.50s/it]
 81%|████████  | 1461/1813 [2:41:19<37:04,  6.32s/it]
 81%|████████  | 1462/1813 [2:41:24<34:54,  5.97s/it]
 81%|████████  | 1463/1813 [2:41:32<37:17,  6.39s/it]
 81%|████████  | 1464/1813 [2:41:38<37:31,  6.45s/it]
 81%|████████  | 1465/1813 [2:41:47<40:29,  6.98s/it]
 81%|████████  | 1466/1813 [2:41:52<37:37,  6.51s/it]
 81%|████████  | 1467/1813 [2:41:59<38:56,  6.75s/it]
 81%|████████  | 1468/1813 [2:42:06<38:29,  6.69s/it]
 81%|████████  | 1469/1813 [2:42:15<41:50,  7.30s/it]
 81%|████████  | 1470/1813 [2:42:21<40:22,  7.06s/it]
                                                     
{'loss': '0.913', 'grad_norm': '0.9012', 'learning_rate': '1.019e-05', 'epoch': '0.811', 'num_input_tokens_seen': 9879232, 'train_runtime': '9742', 'train_tokens_per_second': '1014'}

 81%|████████  | 1470/1813 [2:42:21<40:22,  7.06s/it]
 81%|████████  | 1471/1813 [2:42:27<38:38,  6.78s/it]
 81%|████████  | 1472/1813 [2:42:34<38:14,  6.73s/it]
 81%|████████  | 1473/1813 [2:42:40<36:22,  6.42s/it]
 81%|████████▏ | 1474/1813 [2:42:46<36:31,  6.46s/it]
 81%|████████▏ | 1475/1813 [2:42:52<35:55,  6.38s/it]
 81%|████████▏ | 1476/1813 [2:42:59<35:34,  6.33s/it]
 81%|████████▏ | 1477/1813 [2:43:05<35:22,  6.32s/it]
 82%|████████▏ | 1478/1813 [2:43:10<34:04,  6.10s/it]
 82%|████████▏ | 1479/1813 [2:43:17<33:56,  6.10s/it]
 82%|████████▏ | 1480/1813 [2:43:24<35:26,  6.38s/it]
                                                     
{'loss': '0.8914', 'grad_norm': '0.7256', 'learning_rate': '9.627e-06', 'epoch': '0.8166', 'num_input_tokens_seen': 9948032, 'train_runtime': '9804', 'train_tokens_per_second': '1015'}

 82%|████████▏ | 1480/1813 [2:43:24<35:26,  6.38s/it]
 82%|████████▏ | 1481/1813 [2:43:30<35:43,  6.46s/it]
 82%|████████▏ | 1482/1813 [2:43:36<34:20,  6.22s/it]
 82%|████████▏ | 1483/1813 [2:43:43<35:08,  6.39s/it]
 82%|████████▏ | 1484/1813 [2:43:49<35:04,  6.40s/it]
 82%|████████▏ | 1485/1813 [2:43:56<35:18,  6.46s/it]
 82%|████████▏ | 1486/1813 [2:44:01<33:08,  6.08s/it]
 82%|████████▏ | 1487/1813 [2:44:09<36:09,  6.66s/it]
 82%|████████▏ | 1488/1813 [2:44:15<35:27,  6.54s/it]
 82%|████████▏ | 1489/1813 [2:44:23<36:40,  6.79s/it]
 82%|████████▏ | 1490/1813 [2:44:30<36:53,  6.85s/it]
                                                     
{'loss': '0.9309', 'grad_norm': '0.9664', 'learning_rate': '9.077e-06', 'epoch': '0.8221', 'num_input_tokens_seen': 10021400, 'train_runtime': '9870', 'train_tokens_per_second': '1015'}

 82%|████████▏ | 1490/1813 [2:44:30<36:53,  6.85s/it]
 82%|████████▏ | 1491/1813 [2:44:36<35:31,  6.62s/it]
 82%|████████▏ | 1492/1813 [2:44:44<38:10,  7.13s/it]
 82%|████████▏ | 1493/1813 [2:44:50<36:15,  6.80s/it]
 82%|████████▏ | 1494/1813 [2:44:56<34:48,  6.55s/it]
 82%|████████▏ | 1495/1813 [2:45:04<36:59,  6.98s/it]
 83%|████████▎ | 1496/1813 [2:45:09<33:51,  6.41s/it]
 83%|████████▎ | 1497/1813 [2:45:14<31:40,  6.01s/it]
 83%|████████▎ | 1498/1813 [2:45:20<32:14,  6.14s/it]
 83%|████████▎ | 1499/1813 [2:45:25<30:00,  5.73s/it]
 83%|████████▎ | 1500/1813 [2:45:33<32:51,  6.30s/it]
                                                     
{'loss': '0.8627', 'grad_norm': '0.9089', 'learning_rate': '8.542e-06', 'epoch': '0.8276', 'num_input_tokens_seen': 10089904, 'train_runtime': '9933', 'train_tokens_per_second': '1016'}

 83%|████████▎ | 1500/1813 [2:45:33<32:51,  6.30s/it]
***** Running Evaluation *****
  Num examples = 1000
  Batch size = 1


  0%|          | 0/1000 [00:00<?, ?it/s]

  0%|          | 3/1000 [00:00<01:03, 15.77it/s]

  0%|          | 5/1000 [00:00<02:17,  7.22it/s]

  1%|          | 7/1000 [00:00<01:59,  8.31it/s]

  1%|          | 9/1000 [00:01<02:33,  6.47it/s]

  1%|          | 11/1000 [00:01<02:02,  8.06it/s]

  1%|▏         | 13/1000 [00:01<02:21,  6.99it/s]

  1%|▏         | 14/1000 [00:01<02:24,  6.82it/s]

  2%|▏         | 15/1000 [00:02<02:45,  5.96it/s]

  2%|▏         | 16/1000 [00:02<02:51,  5.72it/s]

  2%|▏         | 18/1000 [00:02<02:42,  6.04it/s]

  2%|▏         | 19/1000 [00:02<03:10,  5.14it/s]

  2%|▏         | 20/1000 [00:03<03:33,  4.59it/s]

  2%|▏         | 22/1000 [00:03<02:36,  6.24it/s]

  2%|▏         | 23/1000 [00:03<02:55,  5.58it/s]

  2%|▎         | 25/1000 [00:03<02:12,  7.35it/s]

  3%|▎         | 26/1000 [00:04<02:35,  6.25it/s]

  3%|▎         | 28/1000 [00:04<02:42,  5.99it/s]

  3%|▎         | 29/1000 [00:04<02:32,  6.36it/s]

  3%|▎         | 30/1000 [00:04<02:42,  5.96it/s]

  3%|▎         | 31/1000 [00:04<03:01,  5.34it/s]

  3%|▎         | 32/1000 [00:05<02:41,  5.98it/s]

  3%|▎         | 33/1000 [00:05<02:48,  5.75it/s]

  4%|▎         | 35/1000 [00:05<02:06,  7.66it/s]

  4%|▎         | 37/1000 [00:05<01:45,  9.10it/s]

  4%|▍         | 39/1000 [00:05<02:06,  7.57it/s]

  4%|▍         | 40/1000 [00:06<02:04,  7.74it/s]

  4%|▍         | 42/1000 [00:06<01:45,  9.09it/s]

  4%|▍         | 44/1000 [00:06<01:32, 10.30it/s]

  5%|▍         | 46/1000 [00:06<01:45,  9.04it/s]

  5%|▍         | 47/1000 [00:06<02:09,  7.34it/s]

  5%|▍         | 49/1000 [00:06<01:48,  8.73it/s]

  5%|▌         | 51/1000 [00:07<01:35,  9.89it/s]

  5%|▌         | 53/1000 [00:07<01:26, 10.91it/s]

  6%|▌         | 55/1000 [00:07<01:28, 10.73it/s]

  6%|▌         | 57/1000 [00:07<01:41,  9.28it/s]

  6%|▌         | 59/1000 [00:08<01:54,  8.19it/s]

  6%|▌         | 61/1000 [00:08<01:40,  9.33it/s]

  6%|▋         | 63/1000 [00:08<01:36,  9.74it/s]

  6%|▋         | 65/1000 [00:08<01:51,  8.36it/s]

  7%|▋         | 67/1000 [00:09<02:03,  7.57it/s]

  7%|▋         | 69/1000 [00:09<01:52,  8.25it/s]

  7%|▋         | 70/1000 [00:09<02:13,  6.99it/s]

  7%|▋         | 72/1000 [00:09<02:18,  6.71it/s]

  7%|▋         | 74/1000 [00:09<01:54,  8.12it/s]

  8%|▊         | 75/1000 [00:10<02:14,  6.86it/s]

  8%|▊         | 76/1000 [00:10<02:18,  6.67it/s]

  8%|▊         | 78/1000 [00:10<02:25,  6.32it/s]

  8%|▊         | 80/1000 [00:10<01:57,  7.85it/s]

  8%|▊         | 82/1000 [00:10<01:39,  9.19it/s]

  8%|▊         | 84/1000 [00:11<01:54,  8.03it/s]

  8%|▊         | 85/1000 [00:11<02:14,  6.78it/s]

  9%|▊         | 86/1000 [00:11<02:33,  5.94it/s]

  9%|▊         | 87/1000 [00:12<02:49,  5.38it/s]

  9%|▉         | 89/1000 [00:12<02:10,  7.00it/s]

  9%|▉         | 90/1000 [00:12<02:05,  7.25it/s]

  9%|▉         | 91/1000 [00:12<02:29,  6.07it/s]

  9%|▉         | 92/1000 [00:12<02:27,  6.17it/s]

  9%|▉         | 93/1000 [00:12<02:37,  5.77it/s]

 10%|▉         | 95/1000 [00:13<02:44,  5.51it/s]

 10%|▉         | 97/1000 [00:13<02:13,  6.77it/s]

 10%|▉         | 99/1000 [00:13<01:47,  8.35it/s]

 10%|█         | 101/1000 [00:13<01:33,  9.62it/s]

 10%|█         | 103/1000 [00:14<01:56,  7.73it/s]

 10%|█         | 104/1000 [00:14<01:54,  7.81it/s]

 11%|█         | 106/1000 [00:14<01:36,  9.30it/s]

 11%|█         | 108/1000 [00:14<01:25, 10.43it/s]

 11%|█         | 110/1000 [00:14<01:19, 11.19it/s]

 11%|█         | 112/1000 [00:14<01:13, 12.00it/s]

 11%|█▏        | 114/1000 [00:14<01:11, 12.48it/s]

 12%|█▏        | 116/1000 [00:15<01:09, 12.77it/s]

 12%|█▏        | 118/1000 [00:15<01:06, 13.21it/s]

 12%|█▏        | 120/1000 [00:15<02:07,  6.90it/s]

 12%|█▏        | 122/1000 [00:15<01:48,  8.07it/s]

 12%|█▏        | 124/1000 [00:16<01:57,  7.42it/s]

 12%|█▎        | 125/1000 [00:16<02:32,  5.72it/s]

 13%|█▎        | 126/1000 [00:16<02:22,  6.14it/s]

 13%|█▎        | 127/1000 [00:17<02:30,  5.79it/s]

 13%|█▎        | 128/1000 [00:17<02:45,  5.28it/s]

 13%|█▎        | 130/1000 [00:17<02:02,  7.09it/s]

 13%|█▎        | 132/1000 [00:17<01:39,  8.70it/s]

 13%|█▎        | 134/1000 [00:17<01:25, 10.14it/s]

 14%|█▎        | 136/1000 [00:17<01:29,  9.64it/s]

 14%|█▍        | 138/1000 [00:18<01:27,  9.88it/s]

 14%|█▍        | 140/1000 [00:18<01:26,  9.96it/s]

 14%|█▍        | 142/1000 [00:18<01:35,  9.03it/s]

 14%|█▍        | 143/1000 [00:18<01:36,  8.89it/s]

 14%|█▍        | 145/1000 [00:18<01:24, 10.06it/s]

 15%|█▍        | 147/1000 [00:19<01:41,  8.43it/s]

 15%|█▍        | 148/1000 [00:19<01:40,  8.49it/s]

 15%|█▌        | 150/1000 [00:19<01:25,  9.90it/s]

 15%|█▌        | 152/1000 [00:19<01:16, 11.02it/s]

 15%|█▌        | 154/1000 [00:19<01:21, 10.37it/s]

 16%|█▌        | 156/1000 [00:20<02:07,  6.64it/s]

 16%|█▌        | 158/1000 [00:20<01:45,  7.96it/s]

 16%|█▌        | 160/1000 [00:20<01:37,  8.59it/s]

 16%|█▌        | 162/1000 [00:20<01:47,  7.80it/s]

 16%|█▋        | 163/1000 [00:21<01:51,  7.49it/s]

 16%|█▋        | 164/1000 [00:21<02:10,  6.40it/s]

 16%|█▋        | 165/1000 [00:21<02:28,  5.64it/s]

 17%|█▋        | 166/1000 [00:21<02:41,  5.16it/s]

 17%|█▋        | 167/1000 [00:21<02:24,  5.76it/s]

 17%|█▋        | 169/1000 [00:22<01:46,  7.80it/s]

 17%|█▋        | 171/1000 [00:22<01:56,  7.13it/s]

 17%|█▋        | 172/1000 [00:22<02:14,  6.14it/s]

 17%|█▋        | 173/1000 [00:22<02:13,  6.20it/s]

 17%|█▋        | 174/1000 [00:22<02:02,  6.72it/s]

 18%|█▊        | 176/1000 [00:23<01:37,  8.42it/s]

 18%|█▊        | 177/1000 [00:23<02:01,  6.80it/s]

 18%|█▊        | 179/1000 [00:23<01:35,  8.56it/s]

 18%|█▊        | 180/1000 [00:23<01:36,  8.50it/s]

 18%|█▊        | 181/1000 [00:23<02:01,  6.75it/s]

 18%|█▊        | 182/1000 [00:24<02:23,  5.72it/s]

 18%|█▊        | 183/1000 [00:24<02:21,  5.79it/s]

 18%|█▊        | 185/1000 [00:24<01:45,  7.74it/s]

 19%|█▊        | 186/1000 [00:24<01:43,  7.90it/s]

 19%|█▊        | 187/1000 [00:24<02:07,  6.39it/s]

 19%|█▉        | 189/1000 [00:24<01:40,  8.10it/s]

 19%|█▉        | 190/1000 [00:25<02:02,  6.62it/s]

 19%|█▉        | 192/1000 [00:25<02:04,  6.48it/s]

 19%|█▉        | 194/1000 [00:25<02:06,  6.38it/s]

 20%|█▉        | 196/1000 [00:25<01:43,  7.75it/s]

 20%|█▉        | 198/1000 [00:26<01:27,  9.20it/s]

 20%|██        | 200/1000 [00:26<01:15, 10.65it/s]

 20%|██        | 202/1000 [00:26<01:31,  8.74it/s]

 20%|██        | 204/1000 [00:26<01:32,  8.62it/s]

 21%|██        | 206/1000 [00:26<01:20,  9.92it/s]

 21%|██        | 208/1000 [00:27<01:32,  8.52it/s]

 21%|██        | 210/1000 [00:27<01:33,  8.47it/s]

 21%|██        | 212/1000 [00:27<01:21,  9.66it/s]

 21%|██▏       | 214/1000 [00:27<01:30,  8.73it/s]

 22%|██▏       | 216/1000 [00:28<01:25,  9.14it/s]

 22%|██▏       | 217/1000 [00:28<01:44,  7.50it/s]

 22%|██▏       | 219/1000 [00:28<01:28,  8.79it/s]

 22%|██▏       | 220/1000 [00:28<02:03,  6.31it/s]

 22%|██▏       | 221/1000 [00:28<02:03,  6.29it/s]

 22%|██▏       | 223/1000 [00:29<02:19,  5.55it/s]

 22%|██▏       | 224/1000 [00:29<02:08,  6.05it/s]

 22%|██▎       | 225/1000 [00:29<02:07,  6.09it/s]

 23%|██▎       | 226/1000 [00:29<02:22,  5.42it/s]

 23%|██▎       | 228/1000 [00:30<01:53,  6.82it/s]

 23%|██▎       | 229/1000 [00:30<02:10,  5.91it/s]

 23%|██▎       | 230/1000 [00:30<02:00,  6.37it/s]

 23%|██▎       | 232/1000 [00:30<01:35,  8.02it/s]

 23%|██▎       | 233/1000 [00:30<01:33,  8.20it/s]

 24%|██▎       | 235/1000 [00:30<01:16,  9.96it/s]

 24%|██▎       | 237/1000 [00:31<01:20,  9.46it/s]

 24%|██▍       | 239/1000 [00:31<01:24,  8.97it/s]

 24%|██▍       | 241/1000 [00:31<01:30,  8.37it/s]

 24%|██▍       | 242/1000 [00:31<02:05,  6.03it/s]

 24%|██▍       | 243/1000 [00:32<02:18,  5.47it/s]

 24%|██▍       | 245/1000 [00:32<01:53,  6.66it/s]

 25%|██▍       | 247/1000 [00:32<01:31,  8.26it/s]

 25%|██▍       | 248/1000 [00:32<01:49,  6.86it/s]

 25%|██▍       | 249/1000 [00:33<02:06,  5.95it/s]

 25%|██▌       | 250/1000 [00:33<02:07,  5.86it/s]

 25%|██▌       | 252/1000 [00:33<02:04,  6.02it/s]

 25%|██▌       | 253/1000 [00:33<02:10,  5.74it/s]

 26%|██▌       | 255/1000 [00:33<01:41,  7.35it/s]

 26%|██▌       | 256/1000 [00:33<01:36,  7.68it/s]

 26%|██▌       | 258/1000 [00:34<01:24,  8.73it/s]

 26%|██▌       | 260/1000 [00:34<01:36,  7.67it/s]

 26%|██▌       | 261/1000 [00:34<01:53,  6.51it/s]

 26%|██▌       | 262/1000 [00:34<01:54,  6.42it/s]

 26%|██▋       | 264/1000 [00:35<01:56,  6.33it/s]

 26%|██▋       | 265/1000 [00:35<01:51,  6.59it/s]

 27%|██▋       | 266/1000 [00:35<01:46,  6.90it/s]

 27%|██▋       | 268/1000 [00:35<01:37,  7.53it/s]

 27%|██▋       | 270/1000 [00:36<01:43,  7.03it/s]

 27%|██▋       | 271/1000 [00:36<02:14,  5.44it/s]

 27%|██▋       | 273/1000 [00:36<02:07,  5.69it/s]

 28%|██▊       | 275/1000 [00:36<01:48,  6.70it/s]

 28%|██▊       | 277/1000 [00:37<01:29,  8.06it/s]

 28%|██▊       | 278/1000 [00:37<01:45,  6.81it/s]

 28%|██▊       | 280/1000 [00:37<01:48,  6.61it/s]

 28%|██▊       | 282/1000 [00:37<01:29,  8.02it/s]

 28%|██▊       | 283/1000 [00:38<02:02,  5.85it/s]

 28%|██▊       | 284/1000 [00:38<02:05,  5.71it/s]

 29%|██▊       | 286/1000 [00:38<01:36,  7.44it/s]

 29%|██▉       | 288/1000 [00:38<01:21,  8.74it/s]

 29%|██▉       | 290/1000 [00:38<01:31,  7.77it/s]

 29%|██▉       | 291/1000 [00:39<01:41,  7.00it/s]

 29%|██▉       | 292/1000 [00:39<01:56,  6.08it/s]

 29%|██▉       | 294/1000 [00:39<01:38,  7.18it/s]

 30%|██▉       | 296/1000 [00:39<01:42,  6.88it/s]

 30%|██▉       | 298/1000 [00:39<01:25,  8.19it/s]

 30%|██▉       | 299/1000 [00:40<01:48,  6.47it/s]

 30%|███       | 300/1000 [00:40<01:42,  6.85it/s]

 30%|███       | 301/1000 [00:40<01:38,  7.11it/s]

 30%|███       | 303/1000 [00:40<01:19,  8.74it/s]

 30%|███       | 304/1000 [00:40<01:26,  8.07it/s]

 30%|███       | 305/1000 [00:40<01:25,  8.14it/s]

 31%|███       | 306/1000 [00:41<01:39,  6.94it/s]

 31%|███       | 307/1000 [00:41<01:42,  6.78it/s]

 31%|███       | 309/1000 [00:41<01:18,  8.79it/s]

 31%|███       | 311/1000 [00:41<01:07, 10.20it/s]

 31%|███▏      | 313/1000 [00:41<01:00, 11.26it/s]

 32%|███▏      | 315/1000 [00:41<01:06, 10.25it/s]

 32%|███▏      | 317/1000 [00:42<01:11,  9.56it/s]

 32%|███▏      | 319/1000 [00:42<01:34,  7.24it/s]

 32%|███▏      | 321/1000 [00:42<01:38,  6.89it/s]

 32%|███▏      | 322/1000 [00:43<01:45,  6.43it/s]

 32%|███▏      | 324/1000 [00:43<01:27,  7.74it/s]

 32%|███▎      | 325/1000 [00:43<01:58,  5.69it/s]

 33%|███▎      | 327/1000 [00:43<01:30,  7.40it/s]

 33%|███▎      | 328/1000 [00:43<01:33,  7.16it/s]

 33%|███▎      | 330/1000 [00:44<01:38,  6.77it/s]

 33%|███▎      | 332/1000 [00:44<01:41,  6.58it/s]

 33%|███▎      | 333/1000 [00:44<01:35,  6.95it/s]

 33%|███▎      | 334/1000 [00:44<01:44,  6.37it/s]

 34%|███▎      | 336/1000 [00:45<01:22,  8.03it/s]

 34%|███▍      | 338/1000 [00:45<01:15,  8.80it/s]

 34%|███▍      | 340/1000 [00:45<01:05, 10.02it/s]

 34%|███▍      | 342/1000 [00:45<01:00, 10.86it/s]

 34%|███▍      | 344/1000 [00:45<01:26,  7.61it/s]

 34%|███▍      | 345/1000 [00:46<01:24,  7.72it/s]

 35%|███▍      | 346/1000 [00:46<01:30,  7.22it/s]

 35%|███▍      | 347/1000 [00:46<01:28,  7.41it/s]

 35%|███▍      | 349/1000 [00:46<01:34,  6.92it/s]

 35%|███▌      | 350/1000 [00:46<01:48,  5.96it/s]

 35%|███▌      | 352/1000 [00:47<01:24,  7.65it/s]

 35%|███▌      | 354/1000 [00:47<01:25,  7.55it/s]

 36%|███▌      | 355/1000 [00:47<01:27,  7.36it/s]

 36%|███▌      | 357/1000 [00:47<01:11,  8.95it/s]

 36%|███▌      | 359/1000 [00:47<01:00, 10.60it/s]

 36%|███▌      | 361/1000 [00:48<01:07,  9.43it/s]

 36%|███▋      | 363/1000 [00:48<01:28,  7.19it/s]

 36%|███▋      | 364/1000 [00:48<01:41,  6.28it/s]

 36%|███▋      | 365/1000 [00:49<02:09,  4.92it/s]

 37%|███▋      | 367/1000 [00:49<01:57,  5.37it/s]

 37%|███▋      | 368/1000 [00:49<02:05,  5.02it/s]

 37%|███▋      | 369/1000 [00:49<01:52,  5.60it/s]

 37%|███▋      | 371/1000 [00:49<01:23,  7.55it/s]

 37%|███▋      | 372/1000 [00:50<01:21,  7.72it/s]

 37%|███▋      | 374/1000 [00:50<01:17,  8.09it/s]

 38%|███▊      | 375/1000 [00:50<01:40,  6.22it/s]

 38%|███▊      | 376/1000 [00:50<01:53,  5.48it/s]

 38%|███▊      | 378/1000 [00:50<01:29,  6.92it/s]

 38%|███▊      | 380/1000 [00:51<01:10,  8.75it/s]

 38%|███▊      | 382/1000 [00:51<01:18,  7.88it/s]

 38%|███▊      | 384/1000 [00:51<01:07,  9.18it/s]

 39%|███▊      | 386/1000 [00:51<01:06,  9.18it/s]

 39%|███▉      | 388/1000 [00:52<01:25,  7.14it/s]

 39%|███▉      | 390/1000 [00:52<01:19,  7.64it/s]

 39%|███▉      | 391/1000 [00:52<01:22,  7.37it/s]

 39%|███▉      | 393/1000 [00:52<01:09,  8.77it/s]

 40%|███▉      | 395/1000 [00:53<01:21,  7.46it/s]

 40%|███▉      | 397/1000 [00:53<01:09,  8.65it/s]

 40%|███▉      | 398/1000 [00:53<01:23,  7.18it/s]

 40%|███▉      | 399/1000 [00:53<01:41,  5.93it/s]

 40%|████      | 400/1000 [00:53<01:51,  5.37it/s]

 40%|████      | 402/1000 [00:54<01:44,  5.73it/s]

 40%|████      | 404/1000 [00:54<01:22,  7.21it/s]

 41%|████      | 406/1000 [00:54<01:09,  8.56it/s]

 41%|████      | 407/1000 [00:54<01:24,  7.04it/s]

 41%|████      | 408/1000 [00:55<01:36,  6.14it/s]

 41%|████      | 410/1000 [00:55<01:33,  6.30it/s]

 41%|████      | 411/1000 [00:55<01:44,  5.64it/s]

 41%|████      | 412/1000 [00:55<01:53,  5.17it/s]

 41%|████▏     | 414/1000 [00:55<01:23,  7.06it/s]

 42%|████▏     | 416/1000 [00:56<01:25,  6.81it/s]

 42%|████▏     | 418/1000 [00:56<01:09,  8.33it/s]

 42%|████▏     | 420/1000 [00:56<01:08,  8.50it/s]

 42%|████▏     | 421/1000 [00:56<01:17,  7.50it/s]

 42%|████▏     | 423/1000 [00:57<01:26,  6.69it/s]

 42%|████▏     | 424/1000 [00:57<01:37,  5.93it/s]

 42%|████▎     | 425/1000 [00:57<01:30,  6.38it/s]

 43%|████▎     | 427/1000 [00:57<01:12,  7.91it/s]

 43%|████▎     | 428/1000 [00:57<01:16,  7.50it/s]

 43%|████▎     | 429/1000 [00:57<01:13,  7.82it/s]

 43%|████▎     | 431/1000 [00:58<00:59,  9.52it/s]

 43%|████▎     | 433/1000 [00:58<00:51, 11.02it/s]

 44%|████▎     | 435/1000 [00:58<00:47, 11.79it/s]

 44%|████▎     | 437/1000 [00:58<00:53, 10.52it/s]

 44%|████▍     | 439/1000 [00:59<01:09,  8.08it/s]

 44%|████▍     | 441/1000 [00:59<01:00,  9.29it/s]

 44%|████▍     | 443/1000 [00:59<01:08,  8.09it/s]

 44%|████▍     | 444/1000 [00:59<01:16,  7.25it/s]

 45%|████▍     | 446/1000 [00:59<01:03,  8.71it/s]

 45%|████▍     | 448/1000 [01:00<01:13,  7.47it/s]

 45%|████▌     | 450/1000 [01:00<01:18,  7.02it/s]

 45%|████▌     | 451/1000 [01:00<01:28,  6.18it/s]

 45%|████▌     | 452/1000 [01:00<01:38,  5.58it/s]

 45%|████▌     | 454/1000 [01:01<01:16,  7.18it/s]

 46%|████▌     | 456/1000 [01:01<01:04,  8.50it/s]

 46%|████▌     | 457/1000 [01:01<01:09,  7.81it/s]

 46%|████▌     | 459/1000 [01:01<00:58,  9.27it/s]

 46%|████▌     | 461/1000 [01:01<00:49, 10.84it/s]

 46%|████▋     | 463/1000 [01:02<01:10,  7.62it/s]

 46%|████▋     | 465/1000 [01:02<01:19,  6.75it/s]

 47%|████▋     | 466/1000 [01:02<01:28,  6.01it/s]

 47%|████▋     | 467/1000 [01:03<01:50,  4.82it/s]

 47%|████▋     | 469/1000 [01:03<01:24,  6.31it/s]

 47%|████▋     | 471/1000 [01:03<01:07,  7.85it/s]

 47%|████▋     | 473/1000 [01:03<01:09,  7.57it/s]

 47%|████▋     | 474/1000 [01:03<01:20,  6.50it/s]

 48%|████▊     | 476/1000 [01:04<01:22,  6.39it/s]

 48%|████▊     | 477/1000 [01:04<01:35,  5.49it/s]

 48%|████▊     | 479/1000 [01:04<01:13,  7.13it/s]

 48%|████▊     | 480/1000 [01:04<01:19,  6.54it/s]

 48%|████▊     | 482/1000 [01:05<01:04,  8.01it/s]

 48%|████▊     | 484/1000 [01:05<01:10,  7.29it/s]

 48%|████▊     | 485/1000 [01:05<01:21,  6.29it/s]

 49%|████▊     | 486/1000 [01:05<01:21,  6.28it/s]

 49%|████▉     | 488/1000 [01:05<01:04,  7.98it/s]

 49%|████▉     | 489/1000 [01:06<01:17,  6.62it/s]

 49%|████▉     | 491/1000 [01:06<01:01,  8.21it/s]

 49%|████▉     | 492/1000 [01:06<01:01,  8.27it/s]

 49%|████▉     | 494/1000 [01:06<00:50,  9.97it/s]

 50%|████▉     | 496/1000 [01:06<01:00,  8.40it/s]

 50%|████▉     | 498/1000 [01:07<00:59,  8.43it/s]

 50%|████▉     | 499/1000 [01:07<01:15,  6.65it/s]

 50%|█████     | 500/1000 [01:07<01:24,  5.93it/s]

 50%|█████     | 502/1000 [01:07<01:05,  7.55it/s]

 50%|█████     | 503/1000 [01:07<01:13,  6.81it/s]

 50%|█████     | 505/1000 [01:08<01:15,  6.55it/s]

 51%|█████     | 506/1000 [01:08<01:25,  5.80it/s]

 51%|█████     | 508/1000 [01:08<01:06,  7.43it/s]

 51%|█████     | 510/1000 [01:08<00:54,  8.96it/s]

 51%|█████     | 512/1000 [01:08<00:48,  9.97it/s]

 51%|█████▏    | 514/1000 [01:09<01:06,  7.28it/s]

 52%|█████▏    | 515/1000 [01:09<01:04,  7.53it/s]

 52%|█████▏    | 516/1000 [01:09<01:08,  7.10it/s]

 52%|█████▏    | 518/1000 [01:09<00:59,  8.07it/s]

 52%|█████▏    | 519/1000 [01:10<01:15,  6.37it/s]

 52%|█████▏    | 521/1000 [01:10<00:59,  8.01it/s]

 52%|█████▏    | 522/1000 [01:10<01:11,  6.67it/s]

 52%|█████▏    | 523/1000 [01:10<01:22,  5.80it/s]

 52%|█████▏    | 524/1000 [01:10<01:25,  5.55it/s]

 53%|█████▎    | 526/1000 [01:11<01:12,  6.57it/s]

 53%|█████▎    | 528/1000 [01:11<01:12,  6.53it/s]

 53%|█████▎    | 529/1000 [01:11<01:13,  6.40it/s]

 53%|█████▎    | 531/1000 [01:11<00:57,  8.13it/s]

 53%|█████▎    | 533/1000 [01:11<00:48,  9.72it/s]

 54%|█████▎    | 535/1000 [01:12<01:09,  6.68it/s]

 54%|█████▎    | 536/1000 [01:12<01:13,  6.36it/s]

 54%|█████▎    | 537/1000 [01:12<01:21,  5.66it/s]

 54%|█████▍    | 539/1000 [01:13<01:17,  5.93it/s]

 54%|█████▍    | 540/1000 [01:13<01:19,  5.75it/s]

 54%|█████▍    | 541/1000 [01:13<01:27,  5.25it/s]

 54%|█████▍    | 543/1000 [01:13<01:05,  6.93it/s]

 55%|█████▍    | 545/1000 [01:14<01:04,  7.07it/s]

 55%|█████▍    | 546/1000 [01:14<01:09,  6.50it/s]

 55%|█████▍    | 547/1000 [01:14<01:19,  5.70it/s]

 55%|█████▍    | 549/1000 [01:14<01:16,  5.92it/s]

 55%|█████▌    | 551/1000 [01:14<00:59,  7.50it/s]

 55%|█████▌    | 552/1000 [01:15<01:01,  7.25it/s]

 55%|█████▌    | 553/1000 [01:15<01:12,  6.18it/s]

 55%|█████▌    | 554/1000 [01:15<01:15,  5.94it/s]

 56%|█████▌    | 556/1000 [01:15<00:57,  7.75it/s]

 56%|█████▌    | 557/1000 [01:15<01:03,  7.02it/s]

 56%|█████▌    | 559/1000 [01:16<00:49,  8.85it/s]

 56%|█████▌    | 561/1000 [01:16<00:43, 10.05it/s]

 56%|█████▋    | 563/1000 [01:16<00:52,  8.37it/s]

 56%|█████▋    | 565/1000 [01:16<00:54,  7.97it/s]

 57%|█████▋    | 566/1000 [01:17<01:04,  6.74it/s]

 57%|█████▋    | 568/1000 [01:17<01:05,  6.55it/s]

 57%|█████▋    | 569/1000 [01:17<01:06,  6.44it/s]

 57%|█████▋    | 571/1000 [01:17<01:06,  6.44it/s]

 57%|█████▋    | 572/1000 [01:17<01:07,  6.30it/s]

 57%|█████▋    | 574/1000 [01:18<01:07,  6.34it/s]

 58%|█████▊    | 576/1000 [01:18<00:54,  7.83it/s]

 58%|█████▊    | 577/1000 [01:18<01:13,  5.73it/s]

 58%|█████▊    | 578/1000 [01:19<01:20,  5.25it/s]

 58%|█████▊    | 580/1000 [01:19<01:00,  6.96it/s]

 58%|█████▊    | 582/1000 [01:19<00:48,  8.55it/s]

 58%|█████▊    | 584/1000 [01:19<00:54,  7.59it/s]

 58%|█████▊    | 585/1000 [01:19<01:00,  6.91it/s]

 59%|█████▊    | 587/1000 [01:20<00:57,  7.15it/s]

 59%|█████▉    | 589/1000 [01:20<00:48,  8.54it/s]

 59%|█████▉    | 590/1000 [01:20<01:00,  6.75it/s]

 59%|█████▉    | 592/1000 [01:20<00:49,  8.16it/s]

 59%|█████▉    | 593/1000 [01:20<00:59,  6.79it/s]

 60%|█████▉    | 595/1000 [01:21<00:48,  8.38it/s]

 60%|█████▉    | 596/1000 [01:21<00:58,  6.87it/s]

 60%|█████▉    | 597/1000 [01:21<01:00,  6.66it/s]

 60%|█████▉    | 599/1000 [01:21<01:01,  6.47it/s]

 60%|██████    | 601/1000 [01:22<01:02,  6.39it/s]

 60%|██████    | 602/1000 [01:22<00:59,  6.71it/s]

 60%|██████    | 604/1000 [01:22<01:09,  5.68it/s]

 61%|██████    | 606/1000 [01:22<00:55,  7.10it/s]

 61%|██████    | 608/1000 [01:23<00:50,  7.84it/s]

 61%|██████    | 610/1000 [01:23<00:46,  8.47it/s]

 61%|██████    | 612/1000 [01:23<00:39,  9.73it/s]

 61%|██████▏   | 614/1000 [01:23<00:35, 10.79it/s]

 62%|██████▏   | 616/1000 [01:23<00:50,  7.60it/s]

 62%|██████▏   | 617/1000 [01:24<00:49,  7.75it/s]

 62%|██████▏   | 619/1000 [01:24<00:41,  9.10it/s]

 62%|██████▏   | 621/1000 [01:24<00:47,  8.02it/s]

 62%|██████▏   | 623/1000 [01:24<00:45,  8.20it/s]

 62%|██████▏   | 624/1000 [01:24<00:44,  8.46it/s]

 62%|██████▎   | 625/1000 [01:25<00:53,  6.96it/s]

 63%|██████▎   | 627/1000 [01:25<00:43,  8.49it/s]

 63%|██████▎   | 628/1000 [01:25<00:53,  6.91it/s]

 63%|██████▎   | 629/1000 [01:25<01:02,  5.95it/s]

 63%|██████▎   | 631/1000 [01:25<00:47,  7.72it/s]

 63%|██████▎   | 633/1000 [01:26<00:39,  9.36it/s]

 64%|██████▎   | 635/1000 [01:26<00:54,  6.64it/s]

 64%|██████▎   | 636/1000 [01:26<00:51,  7.02it/s]

 64%|██████▍   | 638/1000 [01:26<00:45,  7.91it/s]

 64%|██████▍   | 640/1000 [01:26<00:39,  9.13it/s]

 64%|██████▍   | 642/1000 [01:27<00:45,  7.94it/s]

 64%|██████▍   | 643/1000 [01:27<00:47,  7.57it/s]

 64%|██████▍   | 645/1000 [01:27<00:50,  7.09it/s]

 65%|██████▍   | 647/1000 [01:27<00:46,  7.58it/s]

 65%|██████▍   | 648/1000 [01:28<00:53,  6.52it/s]

 65%|██████▌   | 650/1000 [01:28<00:53,  6.56it/s]

 65%|██████▌   | 652/1000 [01:28<00:55,  6.32it/s]

 65%|██████▌   | 654/1000 [01:28<00:44,  7.69it/s]

 66%|██████▌   | 656/1000 [01:29<00:38,  8.91it/s]

 66%|██████▌   | 658/1000 [01:29<00:42,  8.09it/s]

 66%|██████▌   | 659/1000 [01:29<00:56,  5.99it/s]

 66%|██████▌   | 661/1000 [01:29<00:44,  7.55it/s]

 66%|██████▌   | 662/1000 [01:30<00:52,  6.47it/s]

 66%|██████▋   | 664/1000 [01:30<00:58,  5.77it/s]

 66%|██████▋   | 665/1000 [01:30<01:02,  5.32it/s]

 67%|██████▋   | 667/1000 [01:31<00:59,  5.60it/s]

 67%|██████▋   | 668/1000 [01:31<01:03,  5.19it/s]

 67%|██████▋   | 669/1000 [01:31<00:58,  5.69it/s]

 67%|██████▋   | 671/1000 [01:31<00:56,  5.87it/s]

 67%|██████▋   | 673/1000 [01:32<00:49,  6.63it/s]

 68%|██████▊   | 675/1000 [01:32<00:44,  7.27it/s]

 68%|██████▊   | 677/1000 [01:32<00:37,  8.66it/s]

 68%|██████▊   | 679/1000 [01:32<00:33,  9.68it/s]

 68%|██████▊   | 681/1000 [01:32<00:29, 10.90it/s]

 68%|██████▊   | 683/1000 [01:33<00:35,  8.89it/s]

 68%|██████▊   | 685/1000 [01:33<00:31,  9.86it/s]

 69%|██████▊   | 687/1000 [01:33<00:45,  6.85it/s]

 69%|██████▉   | 688/1000 [01:33<00:43,  7.15it/s]

 69%|██████▉   | 690/1000 [01:34<00:45,  6.80it/s]

 69%|██████▉   | 692/1000 [01:34<00:39,  7.83it/s]

 69%|██████▉   | 694/1000 [01:34<00:42,  7.25it/s]

 70%|██████▉   | 695/1000 [01:34<00:41,  7.41it/s]

 70%|██████▉   | 696/1000 [01:34<00:48,  6.33it/s]

 70%|██████▉   | 698/1000 [01:35<00:43,  6.94it/s]

 70%|██████▉   | 699/1000 [01:35<00:49,  6.04it/s]

 70%|███████   | 701/1000 [01:35<00:39,  7.59it/s]

 70%|███████   | 702/1000 [01:35<00:53,  5.61it/s]

 70%|███████   | 704/1000 [01:36<00:41,  7.22it/s]

 70%|███████   | 705/1000 [01:36<00:54,  5.42it/s]

 71%|███████   | 707/1000 [01:36<00:41,  7.01it/s]

 71%|███████   | 709/1000 [01:36<00:38,  7.62it/s]

 71%|███████   | 710/1000 [01:37<00:44,  6.50it/s]

 71%|███████   | 712/1000 [01:37<00:37,  7.71it/s]

 71%|███████▏  | 713/1000 [01:37<00:36,  7.86it/s]

 72%|███████▏  | 715/1000 [01:37<00:30,  9.36it/s]

 72%|███████▏  | 717/1000 [01:37<00:35,  8.06it/s]

 72%|███████▏  | 718/1000 [01:38<00:41,  6.80it/s]

 72%|███████▏  | 719/1000 [01:38<00:47,  5.94it/s]

 72%|███████▏  | 720/1000 [01:38<00:43,  6.47it/s]

 72%|███████▏  | 722/1000 [01:38<00:34,  8.17it/s]

 72%|███████▏  | 723/1000 [01:38<00:33,  8.24it/s]

 72%|███████▏  | 724/1000 [01:38<00:33,  8.24it/s]

 72%|███████▎  | 725/1000 [01:38<00:33,  8.30it/s]

 73%|███████▎  | 727/1000 [01:39<00:26, 10.12it/s]

 73%|███████▎  | 729/1000 [01:39<00:23, 11.61it/s]

 73%|███████▎  | 731/1000 [01:39<00:32,  8.32it/s]

 73%|███████▎  | 733/1000 [01:39<00:28,  9.53it/s]

 74%|███████▎  | 735/1000 [01:39<00:26,  9.88it/s]

 74%|███████▎  | 737/1000 [01:40<00:27,  9.51it/s]

 74%|███████▍  | 739/1000 [01:40<00:26,  9.77it/s]

 74%|███████▍  | 741/1000 [01:40<00:31,  8.30it/s]

 74%|███████▍  | 743/1000 [01:40<00:30,  8.36it/s]

 74%|███████▍  | 745/1000 [01:41<00:26,  9.61it/s]

 75%|███████▍  | 747/1000 [01:41<00:24, 10.45it/s]

 75%|███████▍  | 749/1000 [01:41<00:29,  8.65it/s]

 75%|███████▌  | 750/1000 [01:41<00:32,  7.69it/s]

 75%|███████▌  | 751/1000 [01:41<00:40,  6.17it/s]

 75%|███████▌  | 753/1000 [01:42<00:34,  7.23it/s]

 75%|███████▌  | 754/1000 [01:42<00:39,  6.22it/s]

 76%|███████▌  | 756/1000 [01:42<00:38,  6.41it/s]

 76%|███████▌  | 758/1000 [01:42<00:31,  7.61it/s]

 76%|███████▌  | 759/1000 [01:43<00:32,  7.32it/s]

 76%|███████▌  | 761/1000 [01:43<00:27,  8.69it/s]

 76%|███████▋  | 763/1000 [01:43<00:31,  7.64it/s]

 76%|███████▋  | 764/1000 [01:43<00:35,  6.60it/s]

 77%|███████▋  | 766/1000 [01:44<00:36,  6.47it/s]

 77%|███████▋  | 768/1000 [01:44<00:29,  7.79it/s]

 77%|███████▋  | 769/1000 [01:44<00:34,  6.63it/s]

 77%|███████▋  | 770/1000 [01:44<00:35,  6.55it/s]

 77%|███████▋  | 772/1000 [01:44<00:28,  8.11it/s]

 77%|███████▋  | 773/1000 [01:45<00:35,  6.38it/s]

 77%|███████▋  | 774/1000 [01:45<00:33,  6.78it/s]

 78%|███████▊  | 776/1000 [01:45<00:28,  7.89it/s]

 78%|███████▊  | 778/1000 [01:45<00:23,  9.61it/s]

 78%|███████▊  | 780/1000 [01:45<00:31,  6.95it/s]

 78%|███████▊  | 782/1000 [01:46<00:26,  8.37it/s]

 78%|███████▊  | 784/1000 [01:46<00:30,  7.16it/s]

 79%|███████▊  | 786/1000 [01:46<00:28,  7.53it/s]

 79%|███████▉  | 788/1000 [01:46<00:25,  8.37it/s]

 79%|███████▉  | 790/1000 [01:47<00:23,  8.98it/s]

 79%|███████▉  | 791/1000 [01:47<00:25,  8.22it/s]

 79%|███████▉  | 792/1000 [01:47<00:26,  7.73it/s]

 79%|███████▉  | 793/1000 [01:47<00:25,  7.97it/s]

 80%|███████▉  | 795/1000 [01:47<00:28,  7.19it/s]

 80%|███████▉  | 797/1000 [01:48<00:29,  6.85it/s]

 80%|███████▉  | 798/1000 [01:48<00:33,  6.02it/s]

 80%|████████  | 800/1000 [01:48<00:29,  6.72it/s]

 80%|████████  | 802/1000 [01:48<00:25,  7.64it/s]

 80%|████████  | 804/1000 [01:49<00:25,  7.82it/s]

 81%|████████  | 806/1000 [01:49<00:21,  9.16it/s]

 81%|████████  | 807/1000 [01:49<00:21,  8.97it/s]

 81%|████████  | 809/1000 [01:49<00:18, 10.21it/s]

 81%|████████  | 811/1000 [01:49<00:16, 11.23it/s]

 81%|████████▏ | 813/1000 [01:49<00:20,  9.04it/s]

 82%|████████▏ | 815/1000 [01:50<00:19,  9.30it/s]

 82%|████████▏ | 817/1000 [01:50<00:22,  8.14it/s]

 82%|████████▏ | 819/1000 [01:50<00:19,  9.20it/s]

 82%|████████▏ | 821/1000 [01:50<00:22,  8.04it/s]

 82%|████████▏ | 823/1000 [01:51<00:22,  7.81it/s]

 82%|████████▏ | 824/1000 [01:51<00:26,  6.75it/s]

 82%|████████▎ | 825/1000 [01:51<00:25,  7.00it/s]

 83%|████████▎ | 826/1000 [01:51<00:30,  5.80it/s]

 83%|████████▎ | 828/1000 [01:52<00:32,  5.24it/s]

 83%|████████▎ | 829/1000 [01:52<00:29,  5.73it/s]

 83%|████████▎ | 831/1000 [01:52<00:24,  7.00it/s]

 83%|████████▎ | 832/1000 [01:52<00:29,  5.75it/s]

 83%|████████▎ | 833/1000 [01:52<00:26,  6.22it/s]

 83%|████████▎ | 834/1000 [01:53<00:27,  6.01it/s]

 84%|████████▎ | 835/1000 [01:53<00:25,  6.52it/s]

 84%|████████▎ | 836/1000 [01:53<00:26,  6.11it/s]

 84%|████████▍ | 838/1000 [01:53<00:21,  7.45it/s]

 84%|████████▍ | 840/1000 [01:54<00:24,  6.63it/s]

 84%|████████▍ | 842/1000 [01:54<00:19,  8.16it/s]

 84%|████████▍ | 844/1000 [01:54<00:24,  6.41it/s]

 84%|████████▍ | 845/1000 [01:54<00:26,  5.77it/s]

 85%|████████▍ | 847/1000 [01:55<00:24,  6.25it/s]

 85%|████████▍ | 849/1000 [01:55<00:20,  7.54it/s]

 85%|████████▌ | 850/1000 [01:55<00:23,  6.48it/s]

 85%|████████▌ | 851/1000 [01:55<00:21,  6.87it/s]

 85%|████████▌ | 853/1000 [01:55<00:17,  8.47it/s]

 86%|████████▌ | 855/1000 [01:55<00:14, 10.05it/s]

 86%|████████▌ | 857/1000 [01:56<00:14, 10.21it/s]

 86%|████████▌ | 859/1000 [01:56<00:16,  8.52it/s]

 86%|████████▌ | 861/1000 [01:56<00:14,  9.76it/s]

 86%|████████▋ | 863/1000 [01:56<00:12, 10.64it/s]

 86%|████████▋ | 865/1000 [01:56<00:11, 11.72it/s]

 87%|████████▋ | 867/1000 [01:57<00:14,  9.32it/s]

 87%|████████▋ | 869/1000 [01:57<00:12, 10.28it/s]

 87%|████████▋ | 871/1000 [01:57<00:11, 11.28it/s]

 87%|████████▋ | 873/1000 [01:57<00:16,  7.77it/s]

 88%|████████▊ | 875/1000 [01:58<00:16,  7.63it/s]

 88%|████████▊ | 877/1000 [01:58<00:13,  8.88it/s]

 88%|████████▊ | 879/1000 [01:58<00:17,  6.86it/s]

 88%|████████▊ | 881/1000 [01:58<00:15,  7.60it/s]

 88%|████████▊ | 882/1000 [01:59<00:18,  6.54it/s]

 88%|████████▊ | 884/1000 [01:59<00:14,  7.96it/s]

 89%|████████▊ | 886/1000 [01:59<00:12,  9.17it/s]

 89%|████████▉ | 888/1000 [01:59<00:10, 10.34it/s]

 89%|████████▉ | 890/1000 [01:59<00:11,  9.76it/s]

 89%|████████▉ | 892/1000 [01:59<00:10, 10.76it/s]

 89%|████████▉ | 894/1000 [02:00<00:13,  7.61it/s]

 90%|████████▉ | 896/1000 [02:00<00:11,  8.84it/s]

 90%|████████▉ | 898/1000 [02:01<00:15,  6.53it/s]

 90%|█████████ | 900/1000 [02:01<00:13,  7.69it/s]

 90%|█████████ | 902/1000 [02:01<00:12,  7.86it/s]

 90%|█████████ | 904/1000 [02:01<00:10,  9.06it/s]

 91%|█████████ | 906/1000 [02:02<00:13,  7.05it/s]

 91%|█████████ | 908/1000 [02:02<00:11,  8.32it/s]

 91%|█████████ | 910/1000 [02:02<00:11,  7.59it/s]

 91%|█████████ | 912/1000 [02:02<00:10,  8.78it/s]

 91%|█████████▏| 914/1000 [02:02<00:11,  7.39it/s]

 92%|█████████▏| 916/1000 [02:03<00:11,  7.08it/s]

 92%|█████████▏| 917/1000 [02:03<00:11,  7.36it/s]

 92%|█████████▏| 918/1000 [02:03<00:14,  5.59it/s]

 92%|█████████▏| 919/1000 [02:03<00:14,  5.71it/s]

 92%|█████████▏| 921/1000 [02:04<00:14,  5.58it/s]

 92%|█████████▏| 922/1000 [02:04<00:13,  5.93it/s]

 92%|█████████▏| 924/1000 [02:04<00:10,  7.16it/s]

 93%|█████████▎| 926/1000 [02:04<00:08,  8.62it/s]

 93%|█████████▎| 927/1000 [02:04<00:09,  8.07it/s]

 93%|█████████▎| 928/1000 [02:05<00:10,  6.64it/s]

 93%|█████████▎| 930/1000 [02:05<00:10,  6.46it/s]

 93%|█████████▎| 931/1000 [02:05<00:10,  6.82it/s]

 93%|█████████▎| 933/1000 [02:05<00:10,  6.60it/s]

 93%|█████████▎| 934/1000 [02:06<00:10,  6.17it/s]

 94%|█████████▎| 936/1000 [02:06<00:08,  7.31it/s]

 94%|█████████▍| 938/1000 [02:06<00:07,  8.83it/s]

 94%|█████████▍| 939/1000 [02:06<00:07,  8.04it/s]

 94%|█████████▍| 940/1000 [02:06<00:07,  8.13it/s]

 94%|█████████▍| 942/1000 [02:07<00:09,  6.33it/s]

 94%|█████████▍| 944/1000 [02:07<00:07,  7.08it/s]

 95%|█████████▍| 946/1000 [02:07<00:06,  8.39it/s]

 95%|█████████▍| 948/1000 [02:07<00:05,  9.72it/s]

 95%|█████████▌| 950/1000 [02:07<00:05,  8.82it/s]

 95%|█████████▌| 952/1000 [02:08<00:06,  7.41it/s]

 95%|█████████▌| 954/1000 [02:08<00:07,  6.16it/s]

 96%|█████████▌| 956/1000 [02:08<00:05,  7.39it/s]

 96%|█████████▌| 957/1000 [02:09<00:06,  6.39it/s]

 96%|█████████▌| 959/1000 [02:09<00:07,  5.77it/s]

 96%|█████████▌| 961/1000 [02:09<00:05,  6.81it/s]

 96%|█████████▌| 962/1000 [02:10<00:06,  6.04it/s]

 96%|█████████▋| 964/1000 [02:10<00:04,  7.49it/s]

 96%|█████████▋| 965/1000 [02:10<00:05,  6.44it/s]

 97%|█████████▋| 966/1000 [02:10<00:05,  6.33it/s]

 97%|█████████▋| 968/1000 [02:10<00:03,  8.01it/s]

 97%|█████████▋| 970/1000 [02:10<00:03,  9.40it/s]

 97%|█████████▋| 972/1000 [02:11<00:03,  8.01it/s]

 97%|█████████▋| 974/1000 [02:11<00:02,  9.19it/s]

 98%|█████████▊| 976/1000 [02:11<00:02,  9.79it/s]

 98%|█████████▊| 978/1000 [02:11<00:02, 10.82it/s]

 98%|█████████▊| 980/1000 [02:12<00:02,  8.42it/s]

 98%|█████████▊| 981/1000 [02:12<00:02,  7.06it/s]

 98%|█████████▊| 982/1000 [02:12<00:03,  5.44it/s]

 98%|█████████▊| 984/1000 [02:12<00:02,  6.93it/s]

 99%|█████████▊| 986/1000 [02:12<00:01,  8.36it/s]

 99%|█████████▉| 988/1000 [02:13<00:01,  6.72it/s]

 99%|█████████▉| 989/1000 [02:13<00:01,  5.99it/s]

 99%|█████████▉| 991/1000 [02:13<00:01,  6.14it/s]

 99%|█████████▉| 992/1000 [02:14<00:01,  4.97it/s]

 99%|█████████▉| 994/1000 [02:14<00:00,  6.54it/s]

100%|█████████▉| 995/1000 [02:14<00:00,  5.53it/s]

100%|█████████▉| 997/1000 [02:14<00:00,  7.05it/s]

100%|█████████▉| 999/1000 [02:15<00:00,  6.76it/s]

100%|██████████| 1000/1000 [02:15<00:00,  6.66it/s]
                                                     

                                                   
{'eval_loss': '0.7545', 'eval_runtime': '135.4', 'eval_samples_per_second': '7.383', 'eval_steps_per_second': '7.383', 'epoch': '0.8276', 'num_input_tokens_seen': 10089904}

 83%|████████▎ | 1500/1813 [2:47:48<32:51,  6.30s/it]

100%|██████████| 1000/1000 [02:15<00:00,  6.66it/s]

                                                   
 83%|████████▎ | 1501/1813 [2:47:55<4:04:05, 46.94s/it]
 83%|████████▎ | 1502/1813 [2:47:59<2:57:09, 34.18s/it]
 83%|████████▎ | 1503/1813 [2:48:05<2:13:12, 25.78s/it]
 83%|████████▎ | 1504/1813 [2:48:10<1:40:41, 19.55s/it]
 83%|████████▎ | 1505/1813 [2:48:16<1:18:23, 15.27s/it]
 83%|████████▎ | 1506/1813 [2:48:22<1:05:17, 12.76s/it]
 83%|████████▎ | 1507/1813 [2:48:27<53:04, 10.41s/it]  
 83%|████████▎ | 1508/1813 [2:48:34<47:39,  9.38s/it]
 83%|████████▎ | 1509/1813 [2:48:40<42:22,  8.36s/it]
 83%|████████▎ | 1510/1813 [2:48:47<38:56,  7.71s/it]
                                                     
{'loss': '0.8551', 'grad_norm': '1.092', 'learning_rate': '8.021e-06', 'epoch': '0.8331', 'num_input_tokens_seen': 10151928, 'train_runtime': '1.013e+04', 'train_tokens_per_second': '1002'}

 83%|████████▎ | 1510/1813 [2:48:47<38:56,  7.71s/it]
 83%|████████▎ | 1511/1813 [2:48:53<36:52,  7.33s/it]
 83%|████████▎ | 1512/1813 [2:48:59<34:25,  6.86s/it]
 83%|████████▎ | 1513/1813 [2:49:04<32:15,  6.45s/it]
 84%|████████▎ | 1514/1813 [2:49:11<32:17,  6.48s/it]
 84%|████████▎ | 1515/1813 [2:49:18<33:33,  6.76s/it]
 84%|████████▎ | 1516/1813 [2:49:25<33:36,  6.79s/it]
 84%|████████▎ | 1517/1813 [2:49:32<33:20,  6.76s/it]
 84%|████████▎ | 1518/1813 [2:49:39<34:26,  7.01s/it]
 84%|████████▍ | 1519/1813 [2:49:46<34:30,  7.04s/it]
 84%|████████▍ | 1520/1813 [2:49:53<33:07,  6.78s/it]
                                                     
{'loss': '0.8822', 'grad_norm': '1.069', 'learning_rate': '7.515e-06', 'epoch': '0.8386', 'num_input_tokens_seen': 10225024, 'train_runtime': '1.019e+04', 'train_tokens_per_second': '1003'}

 84%|████████▍ | 1520/1813 [2:49:53<33:07,  6.78s/it]
 84%|████████▍ | 1521/1813 [2:49:59<33:06,  6.80s/it]
 84%|████████▍ | 1522/1813 [2:50:06<32:08,  6.63s/it]
 84%|████████▍ | 1523/1813 [2:50:13<32:58,  6.82s/it]
 84%|████████▍ | 1524/1813 [2:50:19<32:06,  6.67s/it]
 84%|████████▍ | 1525/1813 [2:50:24<29:15,  6.09s/it]
 84%|████████▍ | 1526/1813 [2:50:30<29:31,  6.17s/it]
 84%|████████▍ | 1527/1813 [2:50:37<30:03,  6.31s/it]
 84%|████████▍ | 1528/1813 [2:50:44<30:18,  6.38s/it]
 84%|████████▍ | 1529/1813 [2:50:51<31:10,  6.59s/it]
 84%|████████▍ | 1530/1813 [2:50:56<29:58,  6.36s/it]
                                                     
{'loss': '0.9278', 'grad_norm': '0.7647', 'learning_rate': '7.025e-06', 'epoch': '0.8441', 'num_input_tokens_seen': 10294368, 'train_runtime': '1.026e+04', 'train_tokens_per_second': '1004'}

 84%|████████▍ | 1530/1813 [2:50:56<29:58,  6.36s/it]
 84%|████████▍ | 1531/1813 [2:51:02<28:11,  6.00s/it]
 85%|████████▍ | 1532/1813 [2:51:09<29:23,  6.28s/it]
 85%|████████▍ | 1533/1813 [2:51:14<27:30,  5.89s/it]
 85%|████████▍ | 1534/1813 [2:51:22<30:26,  6.55s/it]
 85%|████████▍ | 1535/1813 [2:51:27<28:43,  6.20s/it]
 85%|████████▍ | 1536/1813 [2:51:34<30:26,  6.59s/it]
 85%|████████▍ | 1537/1813 [2:51:41<30:29,  6.63s/it]
 85%|████████▍ | 1538/1813 [2:51:46<27:39,  6.04s/it]
 85%|████████▍ | 1539/1813 [2:51:51<26:53,  5.89s/it]
 85%|████████▍ | 1540/1813 [2:51:57<26:13,  5.76s/it]
                                                     
{'loss': '0.9113', 'grad_norm': '1.176', 'learning_rate': '6.55e-06', 'epoch': '0.8497', 'num_input_tokens_seen': 10359416, 'train_runtime': '1.032e+04', 'train_tokens_per_second': '1004'}

 85%|████████▍ | 1540/1813 [2:51:57<26:13,  5.76s/it]
 85%|████████▍ | 1541/1813 [2:52:03<27:12,  6.00s/it]
 85%|████████▌ | 1542/1813 [2:52:10<27:23,  6.06s/it]
 85%|████████▌ | 1543/1813 [2:52:15<25:40,  5.71s/it]
 85%|████████▌ | 1544/1813 [2:52:19<24:28,  5.46s/it]
 85%|████████▌ | 1545/1813 [2:52:27<27:29,  6.16s/it]
 85%|████████▌ | 1546/1813 [2:52:33<27:05,  6.09s/it]
 85%|████████▌ | 1547/1813 [2:52:38<25:58,  5.86s/it]
 85%|████████▌ | 1548/1813 [2:52:47<29:13,  6.62s/it]
 85%|████████▌ | 1549/1813 [2:52:52<27:36,  6.27s/it]
 85%|████████▌ | 1550/1813 [2:53:00<29:01,  6.62s/it]
                                                     
{'loss': '0.9997', 'grad_norm': '0.8834', 'learning_rate': '6.09e-06', 'epoch': '0.8552', 'num_input_tokens_seen': 10427368, 'train_runtime': '1.038e+04', 'train_tokens_per_second': '1005'}

 85%|████████▌ | 1550/1813 [2:53:00<29:01,  6.62s/it]
 86%|████████▌ | 1551/1813 [2:53:07<30:15,  6.93s/it]
 86%|████████▌ | 1552/1813 [2:53:14<29:12,  6.71s/it]
 86%|████████▌ | 1553/1813 [2:53:20<28:08,  6.49s/it]
 86%|████████▌ | 1554/1813 [2:53:26<28:13,  6.54s/it]
 86%|████████▌ | 1555/1813 [2:53:33<28:18,  6.58s/it]
 86%|████████▌ | 1556/1813 [2:53:39<27:51,  6.50s/it]
 86%|████████▌ | 1557/1813 [2:53:47<29:23,  6.89s/it]
 86%|████████▌ | 1558/1813 [2:53:53<28:00,  6.59s/it]
 86%|████████▌ | 1559/1813 [2:53:59<27:25,  6.48s/it]
 86%|████████▌ | 1560/1813 [2:54:04<25:36,  6.07s/it]
                                                     
{'loss': '0.9878', 'grad_norm': '0.7696', 'learning_rate': '5.646e-06', 'epoch': '0.8607', 'num_input_tokens_seen': 10497472, 'train_runtime': '1.044e+04', 'train_tokens_per_second': '1005'}

 86%|████████▌ | 1560/1813 [2:54:04<25:36,  6.07s/it]
 86%|████████▌ | 1561/1813 [2:54:11<26:33,  6.32s/it]
 86%|████████▌ | 1562/1813 [2:54:17<26:24,  6.31s/it]
 86%|████████▌ | 1563/1813 [2:54:24<26:12,  6.29s/it]
 86%|████████▋ | 1564/1813 [2:54:30<26:14,  6.32s/it]
 86%|████████▋ | 1565/1813 [2:54:35<24:06,  5.83s/it]
 86%|████████▋ | 1566/1813 [2:54:41<24:27,  5.94s/it]
 86%|████████▋ | 1567/1813 [2:54:47<24:45,  6.04s/it]
 86%|████████▋ | 1568/1813 [2:54:52<23:24,  5.73s/it]
 87%|████████▋ | 1569/1813 [2:55:00<25:24,  6.25s/it]
 87%|████████▋ | 1570/1813 [2:55:07<26:32,  6.56s/it]
                                                     
{'loss': '0.8288', 'grad_norm': '0.941', 'learning_rate': '5.218e-06', 'epoch': '0.8662', 'num_input_tokens_seen': 10564336, 'train_runtime': '1.051e+04', 'train_tokens_per_second': '1005'}

 87%|████████▋ | 1570/1813 [2:55:07<26:32,  6.56s/it]
 87%|████████▋ | 1571/1813 [2:55:12<24:58,  6.19s/it]
 87%|████████▋ | 1572/1813 [2:55:18<24:15,  6.04s/it]
 87%|████████▋ | 1573/1813 [2:55:24<23:58,  5.99s/it]
 87%|████████▋ | 1574/1813 [2:55:30<24:38,  6.18s/it]
 87%|████████▋ | 1575/1813 [2:55:36<24:03,  6.06s/it]
 87%|████████▋ | 1576/1813 [2:55:44<25:46,  6.52s/it]
 87%|████████▋ | 1577/1813 [2:55:51<26:11,  6.66s/it]
 87%|████████▋ | 1578/1813 [2:55:57<25:34,  6.53s/it]
 87%|████████▋ | 1579/1813 [2:56:03<25:04,  6.43s/it]
 87%|████████▋ | 1580/1813 [2:56:08<23:07,  5.96s/it]
                                                     
{'loss': '0.9389', 'grad_norm': '1.107', 'learning_rate': '4.806e-06', 'epoch': '0.8717', 'num_input_tokens_seen': 10628400, 'train_runtime': '1.057e+04', 'train_tokens_per_second': '1006'}

 87%|████████▋ | 1580/1813 [2:56:08<23:07,  5.96s/it]
 87%|████████▋ | 1581/1813 [2:56:14<22:46,  5.89s/it]
 87%|████████▋ | 1582/1813 [2:56:18<20:42,  5.38s/it]
 87%|████████▋ | 1583/1813 [2:56:24<21:34,  5.63s/it]
 87%|████████▋ | 1584/1813 [2:56:31<22:24,  5.87s/it]
 87%|████████▋ | 1585/1813 [2:56:38<24:03,  6.33s/it]
 87%|████████▋ | 1586/1813 [2:56:46<25:15,  6.67s/it]
 88%|████████▊ | 1587/1813 [2:56:53<26:11,  6.95s/it]
 88%|████████▊ | 1588/1813 [2:56:59<24:52,  6.63s/it]
 88%|████████▊ | 1589/1813 [2:57:04<23:11,  6.21s/it]
 88%|████████▊ | 1590/1813 [2:57:11<23:40,  6.37s/it]
                                                     
{'loss': '0.8877', 'grad_norm': '0.9404', 'learning_rate': '4.41e-06', 'epoch': '0.8772', 'num_input_tokens_seen': 10695288, 'train_runtime': '1.063e+04', 'train_tokens_per_second': '1006'}

 88%|████████▊ | 1590/1813 [2:57:11<23:40,  6.37s/it]
 88%|████████▊ | 1591/1813 [2:57:17<23:31,  6.36s/it]
 88%|████████▊ | 1592/1813 [2:57:24<23:39,  6.42s/it]
 88%|████████▊ | 1593/1813 [2:57:31<23:58,  6.54s/it]
 88%|████████▊ | 1594/1813 [2:57:38<24:11,  6.63s/it]
 88%|████████▊ | 1595/1813 [2:57:45<24:55,  6.86s/it]
 88%|████████▊ | 1596/1813 [2:57:54<26:55,  7.44s/it]
 88%|████████▊ | 1597/1813 [2:58:01<26:10,  7.27s/it]
 88%|████████▊ | 1598/1813 [2:58:07<25:09,  7.02s/it]
 88%|████████▊ | 1599/1813 [2:58:13<23:22,  6.56s/it]
 88%|████████▊ | 1600/1813 [2:58:17<21:11,  5.97s/it]
                                                     
{'loss': '0.9118', 'grad_norm': '0.8956', 'learning_rate': '4.031e-06', 'epoch': '0.8828', 'num_input_tokens_seen': 10767512, 'train_runtime': '1.07e+04', 'train_tokens_per_second': '1007'}

 88%|████████▊ | 1600/1813 [2:58:17<21:11,  5.97s/it]
 88%|████████▊ | 1601/1813 [2:58:25<23:08,  6.55s/it]
 88%|████████▊ | 1602/1813 [2:58:31<22:23,  6.37s/it]
 88%|████████▊ | 1603/1813 [2:58:38<22:44,  6.50s/it]
 88%|████████▊ | 1604/1813 [2:58:45<23:02,  6.62s/it]
 89%|████████▊ | 1605/1813 [2:58:53<24:43,  7.13s/it]
 89%|████████▊ | 1606/1813 [2:58:58<22:28,  6.51s/it]
 89%|████████▊ | 1607/1813 [2:59:05<22:31,  6.56s/it]
 89%|████████▊ | 1608/1813 [2:59:12<23:08,  6.78s/it]
 89%|████████▊ | 1609/1813 [2:59:17<21:26,  6.31s/it]
 89%|████████▉ | 1610/1813 [2:59:23<20:53,  6.18s/it]
                                                     
{'loss': '0.9112', 'grad_norm': '1.199', 'learning_rate': '3.667e-06', 'epoch': '0.8883', 'num_input_tokens_seen': 10840800, 'train_runtime': '1.076e+04', 'train_tokens_per_second': '1007'}

 89%|████████▉ | 1610/1813 [2:59:23<20:53,  6.18s/it]
 89%|████████▉ | 1611/1813 [2:59:28<19:30,  5.79s/it]
 89%|████████▉ | 1612/1813 [2:59:34<19:21,  5.78s/it]
 89%|████████▉ | 1613/1813 [2:59:38<17:57,  5.39s/it]
 89%|████████▉ | 1614/1813 [2:59:44<18:14,  5.50s/it]
 89%|████████▉ | 1615/1813 [2:59:50<19:05,  5.78s/it]
 89%|████████▉ | 1616/1813 [2:59:57<19:41,  6.00s/it]
 89%|████████▉ | 1617/1813 [3:00:04<20:09,  6.17s/it]
 89%|████████▉ | 1618/1813 [3:00:09<18:59,  5.84s/it]
 89%|████████▉ | 1619/1813 [3:00:14<18:38,  5.77s/it]
 89%|████████▉ | 1620/1813 [3:00:19<17:49,  5.54s/it]
                                                     
{'loss': '0.9181', 'grad_norm': '0.9562', 'learning_rate': '3.32e-06', 'epoch': '0.8938', 'num_input_tokens_seen': 10899640, 'train_runtime': '1.082e+04', 'train_tokens_per_second': '1007'}

 89%|████████▉ | 1620/1813 [3:00:19<17:49,  5.54s/it]
 89%|████████▉ | 1621/1813 [3:00:25<17:51,  5.58s/it]
 89%|████████▉ | 1622/1813 [3:00:33<19:48,  6.22s/it]
 90%|████████▉ | 1623/1813 [3:00:40<20:23,  6.44s/it]
 90%|████████▉ | 1624/1813 [3:00:46<19:54,  6.32s/it]
 90%|████████▉ | 1625/1813 [3:00:53<20:50,  6.65s/it]
 90%|████████▉ | 1626/1813 [3:00:59<20:06,  6.45s/it]
 90%|████████▉ | 1627/1813 [3:01:05<19:24,  6.26s/it]
 90%|████████▉ | 1628/1813 [3:01:11<18:46,  6.09s/it]
 90%|████████▉ | 1629/1813 [3:01:18<19:40,  6.41s/it]
 90%|████████▉ | 1630/1813 [3:01:23<18:46,  6.15s/it]
                                                     
{'loss': '0.9185', 'grad_norm': '1.372', 'learning_rate': '2.99e-06', 'epoch': '0.8993', 'num_input_tokens_seen': 10968528, 'train_runtime': '1.088e+04', 'train_tokens_per_second': '1008'}

 90%|████████▉ | 1630/1813 [3:01:23<18:46,  6.15s/it]
 90%|████████▉ | 1631/1813 [3:01:29<18:13,  6.01s/it]
 90%|█████████ | 1632/1813 [3:01:34<16:59,  5.63s/it]
 90%|█████████ | 1633/1813 [3:01:41<18:27,  6.15s/it]
 90%|█████████ | 1634/1813 [3:01:46<17:25,  5.84s/it]
 90%|█████████ | 1635/1813 [3:01:53<18:20,  6.18s/it]
 90%|█████████ | 1636/1813 [3:01:59<17:48,  6.04s/it]
 90%|█████████ | 1637/1813 [3:02:05<18:02,  6.15s/it]
 90%|█████████ | 1638/1813 [3:02:11<17:21,  5.95s/it]
 90%|█████████ | 1639/1813 [3:02:18<18:08,  6.26s/it]
 90%|█████████ | 1640/1813 [3:02:23<17:04,  5.92s/it]
                                                     
{'loss': '0.9227', 'grad_norm': '0.7844', 'learning_rate': '2.677e-06', 'epoch': '0.9048', 'num_input_tokens_seen': 11030048, 'train_runtime': '1.094e+04', 'train_tokens_per_second': '1008'}

 90%|█████████ | 1640/1813 [3:02:23<17:04,  5.92s/it]
 91%|█████████ | 1641/1813 [3:02:29<16:50,  5.87s/it]
 91%|█████████ | 1642/1813 [3:02:35<17:18,  6.07s/it]
 91%|█████████ | 1643/1813 [3:02:41<17:10,  6.06s/it]
 91%|█████████ | 1644/1813 [3:02:48<17:36,  6.25s/it]
 91%|█████████ | 1645/1813 [3:02:57<20:13,  7.22s/it]
 91%|█████████ | 1646/1813 [3:03:04<19:32,  7.02s/it]
 91%|█████████ | 1647/1813 [3:03:10<18:34,  6.71s/it]
 91%|█████████ | 1648/1813 [3:03:17<18:28,  6.72s/it]
 91%|█████████ | 1649/1813 [3:03:22<17:08,  6.27s/it]
 91%|█████████ | 1650/1813 [3:03:27<16:05,  5.92s/it]
                                                     
{'loss': '0.8873', 'grad_norm': '0.8632', 'learning_rate': '2.38e-06', 'epoch': '0.9103', 'num_input_tokens_seen': 11098768, 'train_runtime': '1.101e+04', 'train_tokens_per_second': '1008'}

 91%|█████████ | 1650/1813 [3:03:27<16:05,  5.92s/it]
 91%|█████████ | 1651/1813 [3:03:33<16:22,  6.06s/it]
 91%|█████████ | 1652/1813 [3:03:40<16:34,  6.18s/it]
 91%|█████████ | 1653/1813 [3:03:47<16:54,  6.34s/it]
 91%|█████████ | 1654/1813 [3:03:52<16:21,  6.18s/it]
 91%|█████████▏| 1655/1813 [3:03:59<16:25,  6.24s/it]
 91%|█████████▏| 1656/1813 [3:04:05<16:02,  6.13s/it]
 91%|█████████▏| 1657/1813 [3:04:12<17:09,  6.60s/it]
 91%|█████████▏| 1658/1813 [3:04:19<17:04,  6.61s/it]
 92%|█████████▏| 1659/1813 [3:04:26<17:16,  6.73s/it]
 92%|█████████▏| 1660/1813 [3:04:32<16:49,  6.60s/it]
                                                     
{'loss': '0.9432', 'grad_norm': '0.9487', 'learning_rate': '2.101e-06', 'epoch': '0.9159', 'num_input_tokens_seen': 11168848, 'train_runtime': '1.107e+04', 'train_tokens_per_second': '1009'}

 92%|█████████▏| 1660/1813 [3:04:32<16:49,  6.60s/it]
 92%|█████████▏| 1661/1813 [3:04:39<17:08,  6.76s/it]
 92%|█████████▏| 1662/1813 [3:04:46<16:54,  6.72s/it]
 92%|█████████▏| 1663/1813 [3:04:53<16:57,  6.78s/it]
 92%|█████████▏| 1664/1813 [3:05:00<16:53,  6.80s/it]
 92%|█████████▏| 1665/1813 [3:05:07<17:22,  7.04s/it]
 92%|█████████▏| 1666/1813 [3:05:12<15:19,  6.25s/it]
 92%|█████████▏| 1667/1813 [3:05:18<15:27,  6.35s/it]
 92%|█████████▏| 1668/1813 [3:05:25<15:16,  6.32s/it]
 92%|█████████▏| 1669/1813 [3:05:35<17:46,  7.41s/it]
 92%|█████████▏| 1670/1813 [3:05:40<16:17,  6.84s/it]
                                                     
{'loss': '0.9028', 'grad_norm': '1.006', 'learning_rate': '1.839e-06', 'epoch': '0.9214', 'num_input_tokens_seen': 11244288, 'train_runtime': '1.114e+04', 'train_tokens_per_second': '1009'}

 92%|█████████▏| 1670/1813 [3:05:40<16:17,  6.84s/it]
 92%|█████████▏| 1671/1813 [3:05:45<15:09,  6.40s/it]
 92%|█████████▏| 1672/1813 [3:05:51<14:34,  6.20s/it]
 92%|█████████▏| 1673/1813 [3:05:57<14:11,  6.08s/it]
 92%|█████████▏| 1674/1813 [3:06:04<14:39,  6.32s/it]
 92%|█████████▏| 1675/1813 [3:06:11<15:04,  6.56s/it]
 92%|█████████▏| 1676/1813 [3:06:18<15:29,  6.78s/it]
 92%|█████████▏| 1677/1813 [3:06:25<15:04,  6.65s/it]
 93%|█████████▎| 1678/1813 [3:06:31<14:44,  6.56s/it]
 93%|█████████▎| 1679/1813 [3:06:37<14:09,  6.34s/it]
 93%|█████████▎| 1680/1813 [3:06:46<15:42,  7.09s/it]
                                                     
{'loss': '0.9648', 'grad_norm': '0.8387', 'learning_rate': '1.593e-06', 'epoch': '0.9269', 'num_input_tokens_seen': 11317056, 'train_runtime': '1.121e+04', 'train_tokens_per_second': '1010'}

 93%|█████████▎| 1680/1813 [3:06:46<15:42,  7.09s/it]
 93%|█████████▎| 1681/1813 [3:06:51<14:17,  6.50s/it]
 93%|█████████▎| 1682/1813 [3:06:56<13:20,  6.11s/it]
 93%|█████████▎| 1683/1813 [3:07:01<12:16,  5.66s/it]
 93%|█████████▎| 1684/1813 [3:07:07<12:57,  6.03s/it]
 93%|█████████▎| 1685/1813 [3:07:14<13:13,  6.20s/it]
 93%|█████████▎| 1686/1813 [3:07:21<13:32,  6.40s/it]
 93%|█████████▎| 1687/1813 [3:07:27<13:24,  6.39s/it]
 93%|█████████▎| 1688/1813 [3:07:34<13:33,  6.51s/it]
 93%|█████████▎| 1689/1813 [3:07:39<12:19,  5.96s/it]
 93%|█████████▎| 1690/1813 [3:07:45<12:32,  6.12s/it]
                                                     
{'loss': '0.8905', 'grad_norm': '0.7818', 'learning_rate': '1.366e-06', 'epoch': '0.9324', 'num_input_tokens_seen': 11380560, 'train_runtime': '1.127e+04', 'train_tokens_per_second': '1010'}

 93%|█████████▎| 1690/1813 [3:07:45<12:32,  6.12s/it]
 93%|█████████▎| 1691/1813 [3:07:51<12:27,  6.12s/it]
 93%|█████████▎| 1692/1813 [3:07:59<13:12,  6.55s/it]
 93%|█████████▎| 1693/1813 [3:08:05<12:48,  6.40s/it]
 93%|█████████▎| 1694/1813 [3:08:13<13:47,  6.96s/it]
 93%|█████████▎| 1695/1813 [3:08:19<13:05,  6.66s/it]
 94%|█████████▎| 1696/1813 [3:08:25<12:23,  6.36s/it]
 94%|█████████▎| 1697/1813 [3:08:31<12:16,  6.35s/it]
 94%|█████████▎| 1698/1813 [3:08:36<11:28,  5.99s/it]
 94%|█████████▎| 1699/1813 [3:08:43<11:32,  6.07s/it]
 94%|█████████▍| 1700/1813 [3:08:49<11:32,  6.13s/it]
                                                     
{'loss': '0.8874', 'grad_norm': '1.025', 'learning_rate': '1.155e-06', 'epoch': '0.9379', 'num_input_tokens_seen': 11450712, 'train_runtime': '1.133e+04', 'train_tokens_per_second': '1011'}

 94%|█████████▍| 1700/1813 [3:08:49<11:32,  6.13s/it]
 94%|█████████▍| 1701/1813 [3:08:54<10:45,  5.77s/it]
 94%|█████████▍| 1702/1813 [3:08:59<10:29,  5.67s/it]
 94%|█████████▍| 1703/1813 [3:09:05<10:29,  5.72s/it]
 94%|█████████▍| 1704/1813 [3:09:13<11:28,  6.32s/it]
 94%|█████████▍| 1705/1813 [3:09:19<11:33,  6.42s/it]
 94%|█████████▍| 1706/1813 [3:09:26<11:25,  6.41s/it]
 94%|█████████▍| 1707/1813 [3:09:31<10:50,  6.14s/it]
 94%|█████████▍| 1708/1813 [3:09:36<10:01,  5.73s/it]
 94%|█████████▍| 1709/1813 [3:09:42<10:07,  5.84s/it]
 94%|█████████▍| 1710/1813 [3:09:48<09:54,  5.77s/it]
                                                     
{'loss': '0.9414', 'grad_norm': '1.104', 'learning_rate': '9.619e-07', 'epoch': '0.9434', 'num_input_tokens_seen': 11511984, 'train_runtime': '1.139e+04', 'train_tokens_per_second': '1011'}

 94%|█████████▍| 1710/1813 [3:09:48<09:54,  5.77s/it]
 94%|█████████▍| 1711/1813 [3:09:53<09:31,  5.61s/it]
 94%|█████████▍| 1712/1813 [3:09:59<09:27,  5.62s/it]
 94%|█████████▍| 1713/1813 [3:10:05<09:30,  5.70s/it]
 95%|█████████▍| 1714/1813 [3:10:10<09:28,  5.74s/it]
 95%|█████████▍| 1715/1813 [3:10:16<09:14,  5.66s/it]
 95%|█████████▍| 1716/1813 [3:10:21<08:50,  5.47s/it]
 95%|█████████▍| 1717/1813 [3:10:26<08:37,  5.39s/it]
 95%|█████████▍| 1718/1813 [3:10:32<08:53,  5.62s/it]
 95%|█████████▍| 1719/1813 [3:10:38<09:06,  5.81s/it]
 95%|█████████▍| 1720/1813 [3:10:44<09:04,  5.85s/it]
                                                     
{'loss': '0.8947', 'grad_norm': '0.8582', 'learning_rate': '7.863e-07', 'epoch': '0.949', 'num_input_tokens_seen': 11571368, 'train_runtime': '1.144e+04', 'train_tokens_per_second': '1011'}

 95%|█████████▍| 1720/1813 [3:10:44<09:04,  5.85s/it]
 95%|█████████▍| 1721/1813 [3:10:52<09:37,  6.28s/it]
 95%|█████████▍| 1722/1813 [3:10:58<09:24,  6.20s/it]
 95%|█████████▌| 1723/1813 [3:11:04<09:13,  6.15s/it]
 95%|█████████▌| 1724/1813 [3:11:10<09:00,  6.07s/it]
 95%|█████████▌| 1725/1813 [3:11:17<09:24,  6.41s/it]
 95%|█████████▌| 1726/1813 [3:11:24<09:40,  6.68s/it]
 95%|█████████▌| 1727/1813 [3:11:30<09:13,  6.44s/it]
 95%|█████████▌| 1728/1813 [3:11:35<08:28,  5.98s/it]
 95%|█████████▌| 1729/1813 [3:11:40<08:02,  5.74s/it]
 95%|█████████▌| 1730/1813 [3:11:47<08:16,  5.99s/it]
                                                     
{'loss': '0.932', 'grad_norm': '0.734', 'learning_rate': '6.282e-07', 'epoch': '0.9545', 'num_input_tokens_seen': 11640392, 'train_runtime': '1.151e+04', 'train_tokens_per_second': '1012'}

 95%|█████████▌| 1730/1813 [3:11:47<08:16,  5.99s/it]
 95%|█████████▌| 1731/1813 [3:11:53<08:14,  6.02s/it]
 96%|█████████▌| 1732/1813 [3:12:00<08:29,  6.29s/it]
 96%|█████████▌| 1733/1813 [3:12:05<07:54,  5.93s/it]
 96%|█████████▌| 1734/1813 [3:12:11<07:45,  5.90s/it]
 96%|█████████▌| 1735/1813 [3:12:17<07:58,  6.13s/it]
 96%|█████████▌| 1736/1813 [3:12:24<08:09,  6.36s/it]
 96%|█████████▌| 1737/1813 [3:12:30<07:59,  6.31s/it]
 96%|█████████▌| 1738/1813 [3:12:36<07:28,  5.98s/it]
 96%|█████████▌| 1739/1813 [3:12:44<08:07,  6.59s/it]
 96%|█████████▌| 1740/1813 [3:12:50<08:00,  6.58s/it]
                                                     
{'loss': '0.9223', 'grad_norm': '0.9856', 'learning_rate': '4.878e-07', 'epoch': '0.96', 'num_input_tokens_seen': 11709120, 'train_runtime': '1.157e+04', 'train_tokens_per_second': '1012'}

 96%|█████████▌| 1740/1813 [3:12:50<08:00,  6.58s/it]
 96%|█████████▌| 1741/1813 [3:12:56<07:35,  6.32s/it]
 96%|█████████▌| 1742/1813 [3:13:03<07:37,  6.45s/it]
 96%|█████████▌| 1743/1813 [3:13:10<07:42,  6.61s/it]
 96%|█████████▌| 1744/1813 [3:13:17<07:45,  6.74s/it]
 96%|█████████▌| 1745/1813 [3:13:23<07:21,  6.49s/it]
 96%|█████████▋| 1746/1813 [3:13:30<07:31,  6.74s/it]
 96%|█████████▋| 1747/1813 [3:13:35<06:49,  6.20s/it]
 96%|█████████▋| 1748/1813 [3:13:42<07:08,  6.60s/it]
 96%|█████████▋| 1749/1813 [3:13:48<06:43,  6.31s/it]
 97%|█████████▋| 1750/1813 [3:13:54<06:24,  6.11s/it]
                                                     
{'loss': '0.8874', 'grad_norm': '0.7923', 'learning_rate': '3.65e-07', 'epoch': '0.9655', 'num_input_tokens_seen': 11777768, 'train_runtime': '1.163e+04', 'train_tokens_per_second': '1012'}

 97%|█████████▋| 1750/1813 [3:13:54<06:24,  6.11s/it]
 97%|█████████▋| 1751/1813 [3:14:00<06:19,  6.13s/it]
 97%|█████████▋| 1752/1813 [3:14:06<06:14,  6.15s/it]
 97%|█████████▋| 1753/1813 [3:14:14<06:37,  6.63s/it]
 97%|█████████▋| 1754/1813 [3:14:21<06:45,  6.88s/it]
 97%|█████████▋| 1755/1813 [3:14:28<06:34,  6.80s/it]
 97%|█████████▋| 1756/1813 [3:14:33<06:02,  6.35s/it]
 97%|█████████▋| 1757/1813 [3:14:39<05:46,  6.19s/it]
 97%|█████████▋| 1758/1813 [3:14:45<05:33,  6.07s/it]
 97%|█████████▋| 1759/1813 [3:14:51<05:28,  6.08s/it]
 97%|█████████▋| 1760/1813 [3:14:56<05:13,  5.92s/it]
                                                     
{'loss': '0.9006', 'grad_norm': '0.9911', 'learning_rate': '2.599e-07', 'epoch': '0.971', 'num_input_tokens_seen': 11843192, 'train_runtime': '1.17e+04', 'train_tokens_per_second': '1013'}

 97%|█████████▋| 1760/1813 [3:14:56<05:13,  5.92s/it]
 97%|█████████▋| 1761/1813 [3:15:02<05:03,  5.83s/it]
 97%|█████████▋| 1762/1813 [3:15:07<04:43,  5.57s/it]
 97%|█████████▋| 1763/1813 [3:15:15<05:11,  6.23s/it]
 97%|█████████▋| 1764/1813 [3:15:20<04:51,  5.94s/it]
 97%|█████████▋| 1765/1813 [3:15:25<04:37,  5.78s/it]
 97%|█████████▋| 1766/1813 [3:15:31<04:30,  5.75s/it]
 97%|█████████▋| 1767/1813 [3:15:37<04:25,  5.76s/it]
 98%|█████████▊| 1768/1813 [3:15:43<04:19,  5.77s/it]
 98%|█████████▊| 1769/1813 [3:15:49<04:15,  5.81s/it]
 98%|█████████▊| 1770/1813 [3:15:55<04:23,  6.13s/it]
                                                     
{'loss': '0.9144', 'grad_norm': '0.8835', 'learning_rate': '1.726e-07', 'epoch': '0.9766', 'num_input_tokens_seen': 11903728, 'train_runtime': '1.176e+04', 'train_tokens_per_second': '1013'}

 98%|█████████▊| 1770/1813 [3:15:55<04:23,  6.13s/it]
 98%|█████████▊| 1771/1813 [3:16:02<04:19,  6.18s/it]
 98%|█████████▊| 1772/1813 [3:16:08<04:15,  6.22s/it]
 98%|█████████▊| 1773/1813 [3:16:15<04:18,  6.45s/it]
 98%|█████████▊| 1774/1813 [3:16:20<03:51,  5.94s/it]
 98%|█████████▊| 1775/1813 [3:16:27<04:04,  6.42s/it]
 98%|█████████▊| 1776/1813 [3:16:35<04:09,  6.74s/it]
 98%|█████████▊| 1777/1813 [3:16:42<04:11,  6.99s/it]
 98%|█████████▊| 1778/1813 [3:16:48<03:52,  6.63s/it]
 98%|█████████▊| 1779/1813 [3:16:54<03:34,  6.31s/it]
 98%|█████████▊| 1780/1813 [3:17:00<03:23,  6.16s/it]
                                                     
{'loss': '0.9059', 'grad_norm': '0.7636', 'learning_rate': '1.031e-07', 'epoch': '0.9821', 'num_input_tokens_seen': 11972864, 'train_runtime': '1.182e+04', 'train_tokens_per_second': '1013'}

 98%|█████████▊| 1780/1813 [3:17:00<03:23,  6.16s/it]
 98%|█████████▊| 1781/1813 [3:17:06<03:16,  6.15s/it]
 98%|█████████▊| 1782/1813 [3:17:12<03:07,  6.06s/it]
 98%|█████████▊| 1783/1813 [3:17:17<02:59,  5.99s/it]
 98%|█████████▊| 1784/1813 [3:17:24<02:59,  6.18s/it]
 98%|█████████▊| 1785/1813 [3:17:30<02:50,  6.11s/it]
 99%|█████████▊| 1786/1813 [3:17:36<02:45,  6.14s/it]
 99%|█████████▊| 1787/1813 [3:17:41<02:32,  5.88s/it]
 99%|█████████▊| 1788/1813 [3:17:48<02:32,  6.09s/it]
 99%|█████████▊| 1789/1813 [3:17:56<02:43,  6.81s/it]
 99%|█████████▊| 1790/1813 [3:18:04<02:38,  6.89s/it]
                                                     
{'loss': '0.9073', 'grad_norm': '0.7609', 'learning_rate': '5.138e-08', 'epoch': '0.9876', 'num_input_tokens_seen': 12043496, 'train_runtime': '1.188e+04', 'train_tokens_per_second': '1013'}

 99%|█████████▊| 1790/1813 [3:18:04<02:38,  6.89s/it]
 99%|█████████▉| 1791/1813 [3:18:09<02:20,  6.40s/it]
 99%|█████████▉| 1792/1813 [3:18:15<02:12,  6.31s/it]
 99%|█████████▉| 1793/1813 [3:18:22<02:09,  6.46s/it]
 99%|█████████▉| 1794/1813 [3:18:29<02:05,  6.62s/it]
 99%|█████████▉| 1795/1813 [3:18:35<01:59,  6.65s/it]
 99%|█████████▉| 1796/1813 [3:18:42<01:53,  6.67s/it]
 99%|█████████▉| 1797/1813 [3:18:48<01:44,  6.55s/it]
 99%|█████████▉| 1798/1813 [3:18:58<01:50,  7.36s/it]
 99%|█████████▉| 1799/1813 [3:19:04<01:38,  7.07s/it]
 99%|█████████▉| 1800/1813 [3:19:09<01:21,  6.28s/it]
                                                     
{'loss': '0.8827', 'grad_norm': '0.8935', 'learning_rate': '1.749e-08', 'epoch': '0.9931', 'num_input_tokens_seen': 12115448, 'train_runtime': '1.195e+04', 'train_tokens_per_second': '1014'}

 99%|█████████▉| 1800/1813 [3:19:09<01:21,  6.28s/it]
***** Running Evaluation *****
  Num examples = 1000
  Batch size = 1


  0%|          | 0/1000 [00:00<?, ?it/s]

  0%|          | 3/1000 [00:00<01:03, 15.72it/s]

  0%|          | 5/1000 [00:00<02:18,  7.21it/s]

  1%|          | 7/1000 [00:00<01:59,  8.31it/s]

  1%|          | 9/1000 [00:01<02:33,  6.46it/s]

  1%|          | 11/1000 [00:01<02:02,  8.04it/s]

  1%|▏         | 13/1000 [00:01<02:21,  6.98it/s]

  1%|▏         | 14/1000 [00:01<02:24,  6.81it/s]

  2%|▏         | 15/1000 [00:02<02:45,  5.95it/s]

  2%|▏         | 16/1000 [00:02<02:52,  5.71it/s]

  2%|▏         | 18/1000 [00:02<02:42,  6.03it/s]

  2%|▏         | 19/1000 [00:02<03:11,  5.13it/s]

  2%|▏         | 20/1000 [00:03<03:33,  4.59it/s]

  2%|▏         | 22/1000 [00:03<02:36,  6.23it/s]

  2%|▏         | 23/1000 [00:03<02:55,  5.58it/s]

  2%|▎         | 25/1000 [00:03<02:12,  7.35it/s]

  3%|▎         | 26/1000 [00:04<02:35,  6.25it/s]

  3%|▎         | 28/1000 [00:04<02:42,  5.99it/s]

  3%|▎         | 29/1000 [00:04<02:32,  6.35it/s]

  3%|▎         | 30/1000 [00:04<02:42,  5.96it/s]

  3%|▎         | 31/1000 [00:04<03:01,  5.34it/s]

  3%|▎         | 32/1000 [00:05<02:41,  5.98it/s]

  3%|▎         | 33/1000 [00:05<02:48,  5.75it/s]

  4%|▎         | 35/1000 [00:05<02:06,  7.66it/s]

  4%|▎         | 37/1000 [00:05<01:45,  9.10it/s]

  4%|▍         | 39/1000 [00:05<02:06,  7.58it/s]

  4%|▍         | 40/1000 [00:06<02:04,  7.73it/s]

  4%|▍         | 42/1000 [00:06<01:45,  9.09it/s]

  4%|▍         | 44/1000 [00:06<01:32, 10.30it/s]

  5%|▍         | 46/1000 [00:06<01:45,  9.04it/s]

  5%|▍         | 47/1000 [00:06<02:09,  7.36it/s]

  5%|▍         | 49/1000 [00:06<01:48,  8.74it/s]

  5%|▌         | 51/1000 [00:07<01:35,  9.89it/s]

  5%|▌         | 53/1000 [00:07<01:26, 10.91it/s]

  6%|▌         | 55/1000 [00:07<01:28, 10.72it/s]

  6%|▌         | 57/1000 [00:07<01:41,  9.29it/s]

  6%|▌         | 59/1000 [00:08<01:54,  8.20it/s]

  6%|▌         | 61/1000 [00:08<01:40,  9.33it/s]

  6%|▋         | 63/1000 [00:08<01:36,  9.75it/s]

  6%|▋         | 65/1000 [00:08<01:51,  8.36it/s]

  7%|▋         | 67/1000 [00:09<02:03,  7.57it/s]

  7%|▋         | 69/1000 [00:09<01:52,  8.25it/s]

  7%|▋         | 70/1000 [00:09<02:13,  6.99it/s]

  7%|▋         | 72/1000 [00:09<02:18,  6.71it/s]

  7%|▋         | 74/1000 [00:09<01:54,  8.12it/s]

  8%|▊         | 75/1000 [00:10<02:14,  6.86it/s]

  8%|▊         | 76/1000 [00:10<02:18,  6.67it/s]

  8%|▊         | 78/1000 [00:10<02:25,  6.33it/s]

  8%|▊         | 80/1000 [00:10<01:56,  7.87it/s]

  8%|▊         | 82/1000 [00:10<01:39,  9.20it/s]

  8%|▊         | 84/1000 [00:11<01:54,  8.02it/s]

  8%|▊         | 85/1000 [00:11<02:14,  6.78it/s]

  9%|▊         | 86/1000 [00:11<02:33,  5.95it/s]

  9%|▊         | 87/1000 [00:12<02:49,  5.38it/s]

  9%|▉         | 89/1000 [00:12<02:10,  7.00it/s]

  9%|▉         | 90/1000 [00:12<02:05,  7.25it/s]

  9%|▉         | 91/1000 [00:12<02:29,  6.07it/s]

  9%|▉         | 92/1000 [00:12<02:27,  6.18it/s]

  9%|▉         | 93/1000 [00:12<02:36,  5.79it/s]

 10%|▉         | 95/1000 [00:13<02:43,  5.52it/s]

 10%|▉         | 97/1000 [00:13<02:13,  6.78it/s]

 10%|▉         | 99/1000 [00:13<01:47,  8.36it/s]

 10%|█         | 101/1000 [00:13<01:33,  9.62it/s]

 10%|█         | 103/1000 [00:14<01:55,  7.74it/s]

 10%|█         | 104/1000 [00:14<01:54,  7.82it/s]

 11%|█         | 106/1000 [00:14<01:36,  9.29it/s]

 11%|█         | 108/1000 [00:14<01:25, 10.41it/s]

 11%|█         | 110/1000 [00:14<01:19, 11.19it/s]

 11%|█         | 112/1000 [00:14<01:13, 12.01it/s]

 11%|█▏        | 114/1000 [00:14<01:10, 12.48it/s]

 12%|█▏        | 116/1000 [00:15<01:09, 12.78it/s]

 12%|█▏        | 118/1000 [00:15<01:06, 13.21it/s]

 12%|█▏        | 120/1000 [00:15<02:07,  6.90it/s]

 12%|█▏        | 122/1000 [00:15<01:48,  8.08it/s]

 12%|█▏        | 124/1000 [00:16<01:57,  7.43it/s]

 12%|█▎        | 125/1000 [00:16<02:33,  5.72it/s]

 13%|█▎        | 126/1000 [00:16<02:22,  6.13it/s]

 13%|█▎        | 127/1000 [00:17<02:30,  5.79it/s]

 13%|█▎        | 128/1000 [00:17<02:45,  5.27it/s]

 13%|█▎        | 130/1000 [00:17<02:02,  7.09it/s]

 13%|█▎        | 132/1000 [00:17<01:39,  8.69it/s]

 13%|█▎        | 134/1000 [00:17<01:25, 10.13it/s]

 14%|█▎        | 136/1000 [00:17<01:29,  9.64it/s]

 14%|█▍        | 138/1000 [00:18<01:27,  9.88it/s]

 14%|█▍        | 140/1000 [00:18<01:26,  9.96it/s]

 14%|█▍        | 142/1000 [00:18<01:34,  9.04it/s]

 14%|█▍        | 143/1000 [00:18<01:36,  8.89it/s]

 14%|█▍        | 145/1000 [00:18<01:24, 10.08it/s]

 15%|█▍        | 147/1000 [00:19<01:41,  8.39it/s]

 15%|█▍        | 148/1000 [00:19<01:40,  8.45it/s]

 15%|█▌        | 150/1000 [00:19<01:26,  9.88it/s]

 15%|█▌        | 152/1000 [00:19<01:17, 11.00it/s]

 15%|█▌        | 154/1000 [00:19<01:21, 10.39it/s]

 16%|█▌        | 156/1000 [00:20<02:07,  6.64it/s]

 16%|█▌        | 158/1000 [00:20<01:45,  7.97it/s]

 16%|█▌        | 160/1000 [00:20<01:37,  8.61it/s]

 16%|█▌        | 162/1000 [00:20<01:47,  7.81it/s]

 16%|█▋        | 163/1000 [00:21<01:51,  7.50it/s]

 16%|█▋        | 164/1000 [00:21<02:10,  6.40it/s]

 16%|█▋        | 165/1000 [00:21<02:27,  5.67it/s]

 17%|█▋        | 166/1000 [00:21<02:40,  5.19it/s]

 17%|█▋        | 167/1000 [00:21<02:24,  5.78it/s]

 17%|█▋        | 169/1000 [00:22<01:46,  7.83it/s]

 17%|█▋        | 171/1000 [00:22<01:57,  7.05it/s]

 17%|█▋        | 172/1000 [00:22<02:16,  6.09it/s]

 17%|█▋        | 173/1000 [00:22<02:13,  6.18it/s]

 17%|█▋        | 174/1000 [00:22<02:03,  6.70it/s]

 18%|█▊        | 176/1000 [00:23<01:38,  8.40it/s]

 18%|█▊        | 177/1000 [00:23<02:01,  6.78it/s]

 18%|█▊        | 179/1000 [00:23<01:35,  8.56it/s]

 18%|█▊        | 180/1000 [00:23<01:36,  8.48it/s]

 18%|█▊        | 181/1000 [00:23<02:01,  6.74it/s]

 18%|█▊        | 182/1000 [00:24<02:23,  5.70it/s]

 18%|█▊        | 183/1000 [00:24<02:21,  5.78it/s]

 18%|█▊        | 185/1000 [00:24<01:45,  7.74it/s]

 19%|█▊        | 186/1000 [00:24<01:43,  7.88it/s]

 19%|█▊        | 187/1000 [00:24<02:07,  6.37it/s]

 19%|█▉        | 189/1000 [00:24<01:40,  8.09it/s]

 19%|█▉        | 190/1000 [00:25<02:02,  6.61it/s]

 19%|█▉        | 192/1000 [00:25<02:04,  6.47it/s]

 19%|█▉        | 194/1000 [00:25<02:06,  6.37it/s]

 20%|█▉        | 196/1000 [00:25<01:43,  7.75it/s]

 20%|█▉        | 198/1000 [00:26<01:27,  9.19it/s]

 20%|██        | 200/1000 [00:26<01:18, 10.14it/s]

 20%|██        | 202/1000 [00:26<01:33,  8.54it/s]

 20%|██        | 204/1000 [00:26<01:33,  8.50it/s]

 21%|██        | 206/1000 [00:26<01:20,  9.81it/s]

 21%|██        | 208/1000 [00:27<01:34,  8.43it/s]

 21%|██        | 210/1000 [00:27<01:33,  8.41it/s]

 21%|██        | 212/1000 [00:27<01:22,  9.60it/s]

 21%|██▏       | 214/1000 [00:27<01:30,  8.72it/s]

 22%|██▏       | 216/1000 [00:28<01:25,  9.12it/s]

 22%|██▏       | 217/1000 [00:28<01:44,  7.49it/s]

 22%|██▏       | 219/1000 [00:28<01:28,  8.78it/s]

 22%|██▏       | 220/1000 [00:28<02:03,  6.31it/s]

 22%|██▏       | 221/1000 [00:28<02:03,  6.30it/s]

 22%|██▏       | 223/1000 [00:29<02:20,  5.55it/s]

 22%|██▏       | 224/1000 [00:29<02:08,  6.04it/s]

 22%|██▎       | 225/1000 [00:29<02:07,  6.10it/s]

 23%|██▎       | 226/1000 [00:29<02:22,  5.42it/s]

 23%|██▎       | 228/1000 [00:30<01:53,  6.82it/s]

 23%|██▎       | 229/1000 [00:30<02:10,  5.90it/s]

 23%|██▎       | 230/1000 [00:30<02:00,  6.37it/s]

 23%|██▎       | 232/1000 [00:30<01:35,  8.02it/s]

 23%|██▎       | 233/1000 [00:30<01:33,  8.21it/s]

 24%|██▎       | 235/1000 [00:30<01:16,  9.97it/s]

 24%|██▎       | 237/1000 [00:31<01:20,  9.47it/s]

 24%|██▍       | 239/1000 [00:31<01:24,  8.97it/s]

 24%|██▍       | 241/1000 [00:31<01:30,  8.36it/s]

 24%|██▍       | 242/1000 [00:31<02:05,  6.02it/s]

 24%|██▍       | 243/1000 [00:32<02:18,  5.47it/s]

 24%|██▍       | 245/1000 [00:32<01:53,  6.65it/s]

 25%|██▍       | 247/1000 [00:32<01:31,  8.25it/s]

 25%|██▍       | 248/1000 [00:32<01:49,  6.85it/s]

 25%|██▍       | 249/1000 [00:33<02:06,  5.95it/s]

 25%|██▌       | 250/1000 [00:33<02:07,  5.86it/s]

 25%|██▌       | 252/1000 [00:33<02:04,  6.02it/s]

 25%|██▌       | 253/1000 [00:33<02:10,  5.74it/s]

 26%|██▌       | 255/1000 [00:33<01:41,  7.35it/s]

 26%|██▌       | 256/1000 [00:34<01:36,  7.69it/s]

 26%|██▌       | 258/1000 [00:34<01:24,  8.74it/s]

 26%|██▌       | 260/1000 [00:34<01:36,  7.69it/s]

 26%|██▌       | 261/1000 [00:34<01:53,  6.51it/s]

 26%|██▌       | 262/1000 [00:34<01:54,  6.42it/s]

 26%|██▋       | 264/1000 [00:35<01:56,  6.33it/s]

 26%|██▋       | 265/1000 [00:35<01:51,  6.59it/s]

 27%|██▋       | 266/1000 [00:35<01:46,  6.91it/s]

 27%|██▋       | 268/1000 [00:35<01:37,  7.53it/s]

 27%|██▋       | 270/1000 [00:36<01:43,  7.03it/s]

 27%|██▋       | 271/1000 [00:36<02:14,  5.44it/s]

 27%|██▋       | 273/1000 [00:36<02:07,  5.70it/s]

 28%|██▊       | 275/1000 [00:36<01:48,  6.70it/s]

 28%|██▊       | 277/1000 [00:37<01:29,  8.06it/s]

 28%|██▊       | 278/1000 [00:37<01:46,  6.80it/s]

 28%|██▊       | 280/1000 [00:37<01:48,  6.61it/s]

 28%|██▊       | 282/1000 [00:37<01:29,  8.02it/s]

 28%|██▊       | 283/1000 [00:38<02:02,  5.85it/s]

 28%|██▊       | 284/1000 [00:38<02:05,  5.70it/s]

 29%|██▊       | 286/1000 [00:38<01:36,  7.43it/s]

 29%|██▉       | 288/1000 [00:38<01:21,  8.72it/s]

 29%|██▉       | 290/1000 [00:38<01:31,  7.74it/s]

 29%|██▉       | 291/1000 [00:39<01:41,  6.98it/s]

 29%|██▉       | 292/1000 [00:39<01:56,  6.06it/s]

 29%|██▉       | 294/1000 [00:39<01:38,  7.18it/s]

 30%|██▉       | 296/1000 [00:39<01:42,  6.89it/s]

 30%|██▉       | 298/1000 [00:40<01:25,  8.18it/s]

 30%|██▉       | 299/1000 [00:40<01:48,  6.46it/s]

 30%|███       | 300/1000 [00:40<01:42,  6.85it/s]

 30%|███       | 301/1000 [00:40<01:38,  7.12it/s]

 30%|███       | 303/1000 [00:40<01:19,  8.76it/s]

 30%|███       | 304/1000 [00:40<01:26,  8.08it/s]

 30%|███       | 305/1000 [00:40<01:25,  8.15it/s]

 31%|███       | 306/1000 [00:41<01:39,  6.95it/s]

 31%|███       | 307/1000 [00:41<01:42,  6.79it/s]

 31%|███       | 309/1000 [00:41<01:18,  8.79it/s]

 31%|███       | 311/1000 [00:41<01:07, 10.20it/s]

 31%|███▏      | 313/1000 [00:41<01:00, 11.27it/s]

 32%|███▏      | 315/1000 [00:42<01:06, 10.26it/s]

 32%|███▏      | 317/1000 [00:42<01:11,  9.58it/s]

 32%|███▏      | 319/1000 [00:42<01:34,  7.24it/s]

 32%|███▏      | 321/1000 [00:42<01:38,  6.90it/s]

 32%|███▏      | 322/1000 [00:43<01:45,  6.44it/s]

 32%|███▏      | 324/1000 [00:43<01:27,  7.74it/s]

 32%|███▎      | 325/1000 [00:43<01:58,  5.69it/s]

 33%|███▎      | 327/1000 [00:43<01:30,  7.40it/s]

 33%|███▎      | 328/1000 [00:43<01:33,  7.16it/s]

 33%|███▎      | 330/1000 [00:44<01:38,  6.79it/s]

 33%|███▎      | 332/1000 [00:44<01:41,  6.57it/s]

 33%|███▎      | 333/1000 [00:44<01:35,  6.95it/s]

 33%|███▎      | 334/1000 [00:44<01:44,  6.38it/s]

 34%|███▎      | 336/1000 [00:45<01:22,  8.04it/s]

 34%|███▍      | 338/1000 [00:45<01:15,  8.81it/s]

 34%|███▍      | 340/1000 [00:45<01:05, 10.02it/s]

 34%|███▍      | 342/1000 [00:45<01:00, 10.87it/s]

 34%|███▍      | 344/1000 [00:46<01:26,  7.60it/s]

 34%|███▍      | 345/1000 [00:46<01:24,  7.72it/s]

 35%|███▍      | 346/1000 [00:46<01:30,  7.22it/s]

 35%|███▍      | 347/1000 [00:46<01:28,  7.41it/s]

 35%|███▍      | 349/1000 [00:46<01:34,  6.90it/s]

 35%|███▌      | 350/1000 [00:46<01:49,  5.96it/s]

 35%|███▌      | 352/1000 [00:47<01:24,  7.63it/s]

 35%|███▌      | 354/1000 [00:47<01:25,  7.55it/s]

 36%|███▌      | 355/1000 [00:47<01:27,  7.35it/s]

 36%|███▌      | 357/1000 [00:47<01:11,  8.95it/s]

 36%|███▌      | 359/1000 [00:47<01:00, 10.57it/s]

 36%|███▌      | 361/1000 [00:48<01:07,  9.43it/s]

 36%|███▋      | 363/1000 [00:48<01:28,  7.18it/s]

 36%|███▋      | 364/1000 [00:48<01:41,  6.27it/s]

 36%|███▋      | 365/1000 [00:49<02:09,  4.92it/s]

 37%|███▋      | 367/1000 [00:49<01:58,  5.36it/s]

 37%|███▋      | 368/1000 [00:49<02:05,  5.02it/s]

 37%|███▋      | 369/1000 [00:49<01:52,  5.60it/s]

 37%|███▋      | 371/1000 [00:49<01:23,  7.54it/s]

 37%|███▋      | 372/1000 [00:50<01:21,  7.72it/s]

 37%|███▋      | 374/1000 [00:50<01:17,  8.08it/s]

 38%|███▊      | 375/1000 [00:50<01:40,  6.22it/s]

 38%|███▊      | 376/1000 [00:50<01:53,  5.49it/s]

 38%|███▊      | 378/1000 [00:50<01:29,  6.92it/s]

 38%|███▊      | 380/1000 [00:51<01:10,  8.78it/s]

 38%|███▊      | 382/1000 [00:51<01:18,  7.91it/s]

 38%|███▊      | 384/1000 [00:51<01:06,  9.21it/s]

 39%|███▊      | 386/1000 [00:51<01:06,  9.17it/s]

 39%|███▉      | 388/1000 [00:52<01:25,  7.14it/s]

 39%|███▉      | 390/1000 [00:52<01:19,  7.66it/s]

 39%|███▉      | 391/1000 [00:52<01:22,  7.38it/s]

 39%|███▉      | 393/1000 [00:52<01:09,  8.80it/s]

 40%|███▉      | 395/1000 [00:53<01:20,  7.47it/s]

 40%|███▉      | 397/1000 [00:53<01:08,  8.76it/s]

 40%|███▉      | 399/1000 [00:53<01:36,  6.23it/s]

 40%|████      | 400/1000 [00:53<01:45,  5.68it/s]

 40%|████      | 402/1000 [00:54<01:41,  5.92it/s]

 40%|████      | 404/1000 [00:54<01:22,  7.24it/s]

 41%|████      | 406/1000 [00:54<01:09,  8.50it/s]

 41%|████      | 408/1000 [00:55<01:32,  6.39it/s]

 41%|████      | 410/1000 [00:55<01:31,  6.44it/s]

 41%|████      | 411/1000 [00:55<01:41,  5.83it/s]

 41%|████      | 412/1000 [00:55<01:49,  5.35it/s]

 41%|████▏     | 414/1000 [00:55<01:23,  7.05it/s]

 42%|████▏     | 416/1000 [00:56<01:25,  6.81it/s]

 42%|████▏     | 418/1000 [00:56<01:10,  8.26it/s]

 42%|████▏     | 420/1000 [00:56<01:08,  8.45it/s]

 42%|████▏     | 421/1000 [00:56<01:17,  7.49it/s]

 42%|████▏     | 423/1000 [00:57<01:26,  6.69it/s]

 42%|████▏     | 424/1000 [00:57<01:37,  5.93it/s]

 42%|████▎     | 425/1000 [00:57<01:30,  6.37it/s]

 43%|████▎     | 427/1000 [00:57<01:12,  7.95it/s]

 43%|████▎     | 428/1000 [00:57<01:15,  7.54it/s]

 43%|████▎     | 429/1000 [00:58<01:12,  7.83it/s]

 43%|████▎     | 431/1000 [00:58<00:59,  9.53it/s]

 43%|████▎     | 433/1000 [00:58<00:51, 11.02it/s]

 44%|████▎     | 435/1000 [00:58<00:47, 11.79it/s]

 44%|████▎     | 437/1000 [00:58<00:53, 10.52it/s]

 44%|████▍     | 439/1000 [00:59<01:09,  8.08it/s]

 44%|████▍     | 441/1000 [00:59<01:00,  9.29it/s]

 44%|████▍     | 443/1000 [00:59<01:08,  8.09it/s]

 44%|████▍     | 444/1000 [00:59<01:16,  7.24it/s]

 45%|████▍     | 446/1000 [00:59<01:03,  8.72it/s]

 45%|████▍     | 448/1000 [01:00<01:13,  7.48it/s]

 45%|████▌     | 450/1000 [01:00<01:18,  7.01it/s]

 45%|████▌     | 451/1000 [01:00<01:28,  6.18it/s]

 45%|████▌     | 452/1000 [01:01<01:38,  5.58it/s]

 45%|████▌     | 454/1000 [01:01<01:16,  7.18it/s]

 46%|████▌     | 456/1000 [01:01<01:03,  8.50it/s]

 46%|████▌     | 457/1000 [01:01<01:09,  7.80it/s]

 46%|████▌     | 459/1000 [01:01<00:58,  9.26it/s]

 46%|████▌     | 461/1000 [01:01<00:49, 10.82it/s]

 46%|████▋     | 463/1000 [01:02<01:10,  7.63it/s]

 46%|████▋     | 465/1000 [01:02<01:19,  6.75it/s]

 47%|████▋     | 466/1000 [01:02<01:28,  6.01it/s]

 47%|████▋     | 467/1000 [01:03<01:50,  4.82it/s]

 47%|████▋     | 469/1000 [01:03<01:24,  6.31it/s]

 47%|████▋     | 471/1000 [01:03<01:07,  7.86it/s]

 47%|████▋     | 472/1000 [01:03<01:04,  8.20it/s]

 47%|████▋     | 473/1000 [01:03<01:11,  7.37it/s]

 47%|████▋     | 474/1000 [01:03<01:25,  6.17it/s]

 48%|████▊     | 476/1000 [01:04<01:24,  6.19it/s]

 48%|████▊     | 477/1000 [01:04<01:38,  5.29it/s]

 48%|████▊     | 479/1000 [01:04<01:13,  7.08it/s]

 48%|████▊     | 480/1000 [01:04<01:20,  6.50it/s]

 48%|████▊     | 482/1000 [01:05<01:04,  8.03it/s]

 48%|████▊     | 484/1000 [01:05<01:10,  7.29it/s]

 48%|████▊     | 485/1000 [01:05<01:21,  6.29it/s]

 49%|████▊     | 486/1000 [01:05<01:22,  6.26it/s]

 49%|████▉     | 488/1000 [01:05<01:04,  7.98it/s]

 49%|████▉     | 489/1000 [01:06<01:17,  6.62it/s]

 49%|████▉     | 491/1000 [01:06<01:01,  8.21it/s]

 49%|████▉     | 492/1000 [01:06<01:01,  8.28it/s]

 49%|████▉     | 494/1000 [01:06<00:50, 10.00it/s]

 50%|████▉     | 496/1000 [01:06<00:59,  8.41it/s]

 50%|████▉     | 498/1000 [01:07<00:59,  8.43it/s]

 50%|████▉     | 499/1000 [01:07<01:15,  6.65it/s]

 50%|█████     | 500/1000 [01:07<01:24,  5.93it/s]

 50%|█████     | 502/1000 [01:07<01:06,  7.54it/s]

 50%|█████     | 503/1000 [01:07<01:13,  6.80it/s]

 50%|█████     | 505/1000 [01:08<01:15,  6.56it/s]

 51%|█████     | 506/1000 [01:08<01:25,  5.81it/s]

 51%|█████     | 508/1000 [01:08<01:06,  7.43it/s]

 51%|█████     | 510/1000 [01:08<00:54,  8.96it/s]

 51%|█████     | 512/1000 [01:08<00:48,  9.98it/s]

 51%|█████▏    | 514/1000 [01:09<01:06,  7.28it/s]

 52%|█████▏    | 515/1000 [01:09<01:04,  7.53it/s]

 52%|█████▏    | 516/1000 [01:09<01:08,  7.11it/s]

 52%|█████▏    | 518/1000 [01:09<00:59,  8.06it/s]

 52%|█████▏    | 519/1000 [01:10<01:15,  6.37it/s]

 52%|█████▏    | 521/1000 [01:10<00:59,  8.02it/s]

 52%|█████▏    | 522/1000 [01:10<01:11,  6.67it/s]

 52%|█████▏    | 523/1000 [01:10<01:22,  5.81it/s]

 52%|█████▏    | 524/1000 [01:11<01:25,  5.56it/s]

 53%|█████▎    | 526/1000 [01:11<01:11,  6.59it/s]

 53%|█████▎    | 528/1000 [01:11<01:12,  6.54it/s]

 53%|█████▎    | 529/1000 [01:11<01:13,  6.40it/s]

 53%|█████▎    | 531/1000 [01:11<00:58,  7.97it/s]

 53%|█████▎    | 533/1000 [01:11<00:48,  9.56it/s]

 54%|█████▎    | 535/1000 [01:12<01:09,  6.65it/s]

 54%|█████▎    | 536/1000 [01:12<01:13,  6.32it/s]

 54%|█████▎    | 537/1000 [01:12<01:22,  5.63it/s]

 54%|█████▍    | 539/1000 [01:13<01:17,  5.92it/s]

 54%|█████▍    | 540/1000 [01:13<01:20,  5.75it/s]

 54%|█████▍    | 541/1000 [01:13<01:27,  5.25it/s]

 54%|█████▍    | 543/1000 [01:13<01:06,  6.92it/s]

 55%|█████▍    | 545/1000 [01:14<01:04,  7.06it/s]

 55%|█████▍    | 546/1000 [01:14<01:09,  6.49it/s]

 55%|█████▍    | 547/1000 [01:14<01:19,  5.70it/s]

 55%|█████▍    | 549/1000 [01:14<01:16,  5.91it/s]

 55%|█████▌    | 551/1000 [01:14<00:59,  7.50it/s]

 55%|█████▌    | 552/1000 [01:15<01:01,  7.25it/s]

 55%|█████▌    | 553/1000 [01:15<01:12,  6.17it/s]

 55%|█████▌    | 554/1000 [01:15<01:15,  5.94it/s]

 56%|█████▌    | 556/1000 [01:15<00:57,  7.75it/s]

 56%|█████▌    | 557/1000 [01:15<01:03,  7.02it/s]

 56%|█████▌    | 559/1000 [01:16<00:49,  8.85it/s]

 56%|█████▌    | 561/1000 [01:16<00:43, 10.06it/s]

 56%|█████▋    | 563/1000 [01:16<00:52,  8.37it/s]

 56%|█████▋    | 565/1000 [01:16<00:54,  7.97it/s]

 57%|█████▋    | 566/1000 [01:17<01:04,  6.75it/s]

 57%|█████▋    | 568/1000 [01:17<01:05,  6.55it/s]

 57%|█████▋    | 569/1000 [01:17<01:06,  6.44it/s]

 57%|█████▋    | 571/1000 [01:17<01:06,  6.43it/s]

 57%|█████▋    | 572/1000 [01:18<01:07,  6.30it/s]

 57%|█████▋    | 574/1000 [01:18<01:07,  6.35it/s]

 58%|█████▊    | 576/1000 [01:18<00:54,  7.83it/s]

 58%|█████▊    | 577/1000 [01:18<01:13,  5.72it/s]

 58%|█████▊    | 578/1000 [01:19<01:20,  5.25it/s]

 58%|█████▊    | 580/1000 [01:19<01:00,  6.97it/s]

 58%|█████▊    | 582/1000 [01:19<00:48,  8.56it/s]

 58%|█████▊    | 584/1000 [01:19<00:54,  7.59it/s]

 58%|█████▊    | 585/1000 [01:19<01:00,  6.91it/s]

 59%|█████▊    | 587/1000 [01:20<00:57,  7.15it/s]

 59%|█████▉    | 589/1000 [01:20<00:48,  8.53it/s]

 59%|█████▉    | 590/1000 [01:20<01:00,  6.75it/s]

 59%|█████▉    | 592/1000 [01:20<00:49,  8.17it/s]

 59%|█████▉    | 593/1000 [01:20<00:59,  6.79it/s]

 60%|█████▉    | 595/1000 [01:21<00:48,  8.38it/s]

 60%|█████▉    | 596/1000 [01:21<00:58,  6.87it/s]

 60%|█████▉    | 597/1000 [01:21<01:00,  6.66it/s]

 60%|█████▉    | 599/1000 [01:21<01:01,  6.47it/s]

 60%|██████    | 601/1000 [01:22<01:02,  6.39it/s]

 60%|██████    | 602/1000 [01:22<00:59,  6.70it/s]

 60%|██████    | 604/1000 [01:22<01:09,  5.68it/s]

 61%|██████    | 606/1000 [01:22<00:55,  7.10it/s]

 61%|██████    | 608/1000 [01:23<00:50,  7.77it/s]

 61%|██████    | 610/1000 [01:23<00:46,  8.41it/s]

 61%|██████    | 612/1000 [01:23<00:40,  9.68it/s]

 61%|██████▏   | 614/1000 [01:23<00:35, 10.75it/s]

 62%|██████▏   | 616/1000 [01:23<00:50,  7.60it/s]

 62%|██████▏   | 617/1000 [01:24<00:49,  7.73it/s]

 62%|██████▏   | 619/1000 [01:24<00:41,  9.08it/s]

 62%|██████▏   | 621/1000 [01:24<00:47,  8.02it/s]

 62%|██████▏   | 623/1000 [01:24<00:45,  8.20it/s]

 62%|██████▎   | 625/1000 [01:25<00:50,  7.44it/s]

 63%|██████▎   | 627/1000 [01:25<00:43,  8.62it/s]

 63%|██████▎   | 628/1000 [01:25<00:51,  7.18it/s]

 63%|██████▎   | 629/1000 [01:25<00:59,  6.21it/s]

 63%|██████▎   | 631/1000 [01:25<00:47,  7.85it/s]

 63%|██████▎   | 633/1000 [01:26<00:39,  9.40it/s]

 64%|██████▎   | 635/1000 [01:26<00:54,  6.71it/s]

 64%|██████▎   | 636/1000 [01:26<00:51,  7.06it/s]

 64%|██████▍   | 638/1000 [01:26<00:45,  7.95it/s]

 64%|██████▍   | 640/1000 [01:26<00:39,  9.17it/s]

 64%|██████▍   | 642/1000 [01:27<00:45,  7.95it/s]

 64%|██████▍   | 643/1000 [01:27<00:47,  7.58it/s]

 64%|██████▍   | 645/1000 [01:27<00:49,  7.10it/s]

 65%|██████▍   | 647/1000 [01:27<00:46,  7.58it/s]

 65%|██████▍   | 648/1000 [01:28<00:54,  6.52it/s]

 65%|██████▌   | 650/1000 [01:28<00:53,  6.56it/s]

 65%|██████▌   | 652/1000 [01:28<00:55,  6.32it/s]

 65%|██████▌   | 654/1000 [01:29<00:45,  7.57it/s]

 66%|██████▌   | 656/1000 [01:29<00:39,  8.79it/s]

 66%|██████▌   | 657/1000 [01:29<00:46,  7.35it/s]

 66%|██████▌   | 659/1000 [01:29<00:55,  6.17it/s]

 66%|██████▌   | 661/1000 [01:29<00:44,  7.66it/s]

 66%|██████▌   | 662/1000 [01:30<00:51,  6.57it/s]

 66%|██████▋   | 664/1000 [01:30<00:57,  5.83it/s]

 66%|██████▋   | 665/1000 [01:30<01:02,  5.37it/s]

 67%|██████▋   | 667/1000 [01:31<00:59,  5.64it/s]

 67%|██████▋   | 668/1000 [01:31<01:03,  5.22it/s]

 67%|██████▋   | 669/1000 [01:31<00:57,  5.71it/s]

 67%|██████▋   | 671/1000 [01:31<00:55,  5.89it/s]

 67%|██████▋   | 673/1000 [01:32<00:49,  6.65it/s]

 68%|██████▊   | 675/1000 [01:32<00:44,  7.28it/s]

 68%|██████▊   | 677/1000 [01:32<00:37,  8.57it/s]

 68%|██████▊   | 679/1000 [01:32<00:33,  9.63it/s]

 68%|██████▊   | 681/1000 [01:32<00:29, 10.91it/s]

 68%|██████▊   | 683/1000 [01:33<00:35,  8.90it/s]

 68%|██████▊   | 685/1000 [01:33<00:31,  9.88it/s]

 69%|██████▊   | 687/1000 [01:33<00:45,  6.86it/s]

 69%|██████▉   | 688/1000 [01:33<00:43,  7.15it/s]

 69%|██████▉   | 690/1000 [01:34<00:45,  6.81it/s]

 69%|██████▉   | 692/1000 [01:34<00:39,  7.84it/s]

 69%|██████▉   | 694/1000 [01:34<00:42,  7.26it/s]

 70%|██████▉   | 695/1000 [01:34<00:41,  7.42it/s]

 70%|██████▉   | 696/1000 [01:35<00:47,  6.33it/s]

 70%|██████▉   | 698/1000 [01:35<00:43,  6.94it/s]

 70%|██████▉   | 699/1000 [01:35<00:49,  6.02it/s]

 70%|███████   | 701/1000 [01:35<00:39,  7.57it/s]

 70%|███████   | 702/1000 [01:36<00:53,  5.60it/s]

 70%|███████   | 704/1000 [01:36<00:41,  7.20it/s]

 70%|███████   | 705/1000 [01:36<00:54,  5.41it/s]

 71%|███████   | 707/1000 [01:36<00:41,  7.01it/s]

 71%|███████   | 709/1000 [01:36<00:38,  7.62it/s]

 71%|███████   | 710/1000 [01:37<00:44,  6.49it/s]

 71%|███████   | 712/1000 [01:37<00:37,  7.67it/s]

 71%|███████▏  | 713/1000 [01:37<00:36,  7.83it/s]

 72%|███████▏  | 715/1000 [01:37<00:30,  9.35it/s]

 72%|███████▏  | 717/1000 [01:37<00:35,  8.05it/s]

 72%|███████▏  | 718/1000 [01:38<00:41,  6.79it/s]

 72%|███████▏  | 719/1000 [01:38<00:47,  5.92it/s]

 72%|███████▏  | 720/1000 [01:38<00:43,  6.46it/s]

 72%|███████▏  | 722/1000 [01:38<00:34,  8.15it/s]

 72%|███████▏  | 723/1000 [01:38<00:33,  8.24it/s]

 72%|███████▏  | 724/1000 [01:38<00:33,  8.25it/s]

 72%|███████▎  | 725/1000 [01:38<00:33,  8.32it/s]

 73%|███████▎  | 727/1000 [01:39<00:26, 10.13it/s]

 73%|███████▎  | 729/1000 [01:39<00:23, 11.60it/s]

 73%|███████▎  | 731/1000 [01:39<00:32,  8.31it/s]

 73%|███████▎  | 733/1000 [01:39<00:28,  9.51it/s]

 74%|███████▎  | 735/1000 [01:39<00:26,  9.87it/s]

 74%|███████▎  | 737/1000 [01:40<00:27,  9.53it/s]

 74%|███████▍  | 739/1000 [01:40<00:26,  9.77it/s]

 74%|███████▍  | 741/1000 [01:40<00:31,  8.31it/s]

 74%|███████▍  | 743/1000 [01:40<00:30,  8.36it/s]

 74%|███████▍  | 745/1000 [01:41<00:26,  9.62it/s]

 75%|███████▍  | 747/1000 [01:41<00:24, 10.45it/s]

 75%|███████▍  | 749/1000 [01:41<00:29,  8.63it/s]

 75%|███████▌  | 750/1000 [01:41<00:32,  7.67it/s]

 75%|███████▌  | 751/1000 [01:42<00:40,  6.16it/s]

 75%|███████▌  | 753/1000 [01:42<00:34,  7.23it/s]

 75%|███████▌  | 754/1000 [01:42<00:39,  6.22it/s]

 76%|███████▌  | 756/1000 [01:42<00:38,  6.40it/s]

 76%|███████▌  | 758/1000 [01:42<00:31,  7.61it/s]

 76%|███████▌  | 759/1000 [01:43<00:32,  7.32it/s]

 76%|███████▌  | 761/1000 [01:43<00:27,  8.71it/s]

 76%|███████▋  | 763/1000 [01:43<00:30,  7.65it/s]

 76%|███████▋  | 764/1000 [01:43<00:35,  6.60it/s]

 77%|███████▋  | 766/1000 [01:44<00:36,  6.47it/s]

 77%|███████▋  | 768/1000 [01:44<00:29,  7.79it/s]

 77%|███████▋  | 769/1000 [01:44<00:34,  6.63it/s]

 77%|███████▋  | 770/1000 [01:44<00:35,  6.56it/s]

 77%|███████▋  | 772/1000 [01:44<00:28,  8.13it/s]

 77%|███████▋  | 773/1000 [01:45<00:35,  6.38it/s]

 77%|███████▋  | 774/1000 [01:45<00:33,  6.78it/s]

 78%|███████▊  | 776/1000 [01:45<00:28,  7.89it/s]

 78%|███████▊  | 778/1000 [01:45<00:23,  9.60it/s]

 78%|███████▊  | 780/1000 [01:45<00:31,  6.94it/s]

 78%|███████▊  | 782/1000 [01:46<00:26,  8.37it/s]

 78%|███████▊  | 784/1000 [01:46<00:30,  7.16it/s]

 79%|███████▊  | 786/1000 [01:46<00:28,  7.53it/s]

 79%|███████▉  | 788/1000 [01:46<00:25,  8.35it/s]

 79%|███████▉  | 790/1000 [01:47<00:23,  8.96it/s]

 79%|███████▉  | 791/1000 [01:47<00:25,  8.21it/s]

 79%|███████▉  | 792/1000 [01:47<00:26,  7.72it/s]

 79%|███████▉  | 793/1000 [01:47<00:25,  7.97it/s]

 80%|███████▉  | 795/1000 [01:47<00:28,  7.18it/s]

 80%|███████▉  | 797/1000 [01:48<00:29,  6.85it/s]

 80%|███████▉  | 798/1000 [01:48<00:33,  6.02it/s]

 80%|████████  | 800/1000 [01:48<00:29,  6.71it/s]

 80%|████████  | 802/1000 [01:48<00:25,  7.63it/s]

 80%|████████  | 804/1000 [01:49<00:25,  7.82it/s]

 81%|████████  | 806/1000 [01:49<00:21,  9.15it/s]

 81%|████████  | 807/1000 [01:49<00:21,  8.96it/s]

 81%|████████  | 809/1000 [01:49<00:18, 10.21it/s]

 81%|████████  | 811/1000 [01:49<00:16, 11.24it/s]

 81%|████████▏ | 813/1000 [01:49<00:20,  9.05it/s]

 82%|████████▏ | 815/1000 [01:50<00:19,  9.30it/s]

 82%|████████▏ | 817/1000 [01:50<00:22,  8.13it/s]

 82%|████████▏ | 819/1000 [01:50<00:19,  9.20it/s]

 82%|████████▏ | 821/1000 [01:50<00:22,  8.04it/s]

 82%|████████▏ | 823/1000 [01:51<00:22,  7.82it/s]

 82%|████████▏ | 824/1000 [01:51<00:26,  6.75it/s]

 82%|████████▎ | 825/1000 [01:51<00:24,  7.00it/s]

 83%|████████▎ | 826/1000 [01:51<00:30,  5.79it/s]

 83%|████████▎ | 828/1000 [01:52<00:32,  5.23it/s]

 83%|████████▎ | 829/1000 [01:52<00:29,  5.73it/s]

 83%|████████▎ | 831/1000 [01:52<00:24,  7.01it/s]

 83%|████████▎ | 832/1000 [01:52<00:29,  5.75it/s]

 83%|████████▎ | 833/1000 [01:53<00:26,  6.23it/s]

 83%|████████▎ | 834/1000 [01:53<00:27,  6.01it/s]

 84%|████████▎ | 835/1000 [01:53<00:25,  6.52it/s]

 84%|████████▎ | 836/1000 [01:53<00:26,  6.10it/s]

 84%|████████▍ | 838/1000 [01:53<00:21,  7.45it/s]

 84%|████████▍ | 840/1000 [01:54<00:24,  6.62it/s]

 84%|████████▍ | 842/1000 [01:54<00:19,  8.15it/s]

 84%|████████▍ | 844/1000 [01:54<00:24,  6.41it/s]

 84%|████████▍ | 845/1000 [01:54<00:26,  5.77it/s]

 85%|████████▍ | 847/1000 [01:55<00:24,  6.24it/s]

 85%|████████▍ | 849/1000 [01:55<00:20,  7.54it/s]

 85%|████████▌ | 850/1000 [01:55<00:23,  6.49it/s]

 85%|████████▌ | 851/1000 [01:55<00:21,  6.87it/s]

 85%|████████▌ | 853/1000 [01:55<00:17,  8.47it/s]

 86%|████████▌ | 855/1000 [01:55<00:14, 10.04it/s]

 86%|████████▌ | 857/1000 [01:56<00:14, 10.20it/s]

 86%|████████▌ | 859/1000 [01:56<00:16,  8.50it/s]

 86%|████████▌ | 861/1000 [01:56<00:14,  9.77it/s]

 86%|████████▋ | 863/1000 [01:56<00:12, 10.64it/s]

 86%|████████▋ | 865/1000 [01:56<00:11, 11.70it/s]

 87%|████████▋ | 867/1000 [01:57<00:14,  9.30it/s]

 87%|████████▋ | 869/1000 [01:57<00:12, 10.25it/s]

 87%|████████▋ | 871/1000 [01:57<00:11, 11.24it/s]

 87%|████████▋ | 873/1000 [01:57<00:16,  7.77it/s]

 88%|████████▊ | 875/1000 [01:58<00:16,  7.62it/s]

 88%|████████▊ | 877/1000 [01:58<00:13,  8.87it/s]

 88%|████████▊ | 879/1000 [01:58<00:17,  6.87it/s]

 88%|████████▊ | 881/1000 [01:58<00:15,  7.60it/s]

 88%|████████▊ | 882/1000 [01:59<00:18,  6.53it/s]

 88%|████████▊ | 884/1000 [01:59<00:14,  7.95it/s]

 89%|████████▊ | 886/1000 [01:59<00:12,  9.16it/s]

 89%|████████▉ | 888/1000 [01:59<00:10, 10.35it/s]

 89%|████████▉ | 890/1000 [01:59<00:11,  9.77it/s]

 89%|████████▉ | 892/1000 [02:00<00:10, 10.76it/s]

 89%|████████▉ | 894/1000 [02:00<00:13,  7.60it/s]

 90%|████████▉ | 896/1000 [02:00<00:11,  8.84it/s]

 90%|████████▉ | 898/1000 [02:01<00:15,  6.53it/s]

 90%|█████████ | 900/1000 [02:01<00:12,  7.70it/s]

 90%|█████████ | 902/1000 [02:01<00:12,  7.86it/s]

 90%|█████████ | 904/1000 [02:01<00:10,  9.06it/s]

 91%|█████████ | 906/1000 [02:02<00:13,  7.05it/s]

 91%|█████████ | 908/1000 [02:02<00:11,  8.31it/s]

 91%|█████████ | 910/1000 [02:02<00:11,  7.59it/s]

 91%|█████████ | 912/1000 [02:02<00:10,  8.77it/s]

 91%|█████████▏| 914/1000 [02:03<00:11,  7.39it/s]

 92%|█████████▏| 916/1000 [02:03<00:11,  7.08it/s]

 92%|█████████▏| 917/1000 [02:03<00:11,  7.37it/s]

 92%|█████████▏| 918/1000 [02:03<00:14,  5.59it/s]

 92%|█████████▏| 919/1000 [02:03<00:14,  5.71it/s]

 92%|█████████▏| 921/1000 [02:04<00:14,  5.58it/s]

 92%|█████████▏| 922/1000 [02:04<00:13,  5.94it/s]

 92%|█████████▏| 924/1000 [02:04<00:10,  7.16it/s]

 93%|█████████▎| 926/1000 [02:04<00:08,  8.63it/s]

 93%|█████████▎| 927/1000 [02:04<00:09,  8.08it/s]

 93%|█████████▎| 928/1000 [02:05<00:10,  6.64it/s]

 93%|█████████▎| 930/1000 [02:05<00:10,  6.47it/s]

 93%|█████████▎| 931/1000 [02:05<00:10,  6.82it/s]

 93%|█████████▎| 933/1000 [02:05<00:10,  6.61it/s]

 93%|█████████▎| 934/1000 [02:06<00:10,  6.17it/s]

 94%|█████████▎| 936/1000 [02:06<00:08,  7.30it/s]

 94%|█████████▍| 938/1000 [02:06<00:07,  8.83it/s]

 94%|█████████▍| 939/1000 [02:06<00:07,  8.03it/s]

 94%|█████████▍| 940/1000 [02:06<00:07,  8.13it/s]

 94%|█████████▍| 942/1000 [02:07<00:09,  6.34it/s]

 94%|█████████▍| 944/1000 [02:07<00:07,  7.08it/s]

 95%|█████████▍| 946/1000 [02:07<00:06,  8.39it/s]

 95%|█████████▍| 948/1000 [02:07<00:05,  9.72it/s]

 95%|█████████▌| 950/1000 [02:07<00:05,  8.83it/s]

 95%|█████████▌| 952/1000 [02:08<00:06,  7.40it/s]

 95%|█████████▌| 954/1000 [02:08<00:07,  6.16it/s]

 96%|█████████▌| 956/1000 [02:08<00:05,  7.40it/s]

 96%|█████████▌| 957/1000 [02:09<00:06,  6.39it/s]

 96%|█████████▌| 959/1000 [02:09<00:07,  5.77it/s]

 96%|█████████▌| 961/1000 [02:09<00:05,  6.81it/s]

 96%|█████████▌| 962/1000 [02:10<00:06,  6.04it/s]

 96%|█████████▋| 964/1000 [02:10<00:04,  7.49it/s]

 96%|█████████▋| 965/1000 [02:10<00:05,  6.44it/s]

 97%|█████████▋| 966/1000 [02:10<00:05,  6.34it/s]

 97%|█████████▋| 968/1000 [02:10<00:03,  8.02it/s]

 97%|█████████▋| 970/1000 [02:10<00:03,  9.42it/s]

 97%|█████████▋| 972/1000 [02:11<00:03,  8.02it/s]

 97%|█████████▋| 974/1000 [02:11<00:02,  9.20it/s]

 98%|█████████▊| 976/1000 [02:11<00:02,  9.78it/s]

 98%|█████████▊| 978/1000 [02:11<00:02, 10.80it/s]

 98%|█████████▊| 980/1000 [02:12<00:02,  8.41it/s]

 98%|█████████▊| 981/1000 [02:12<00:02,  7.04it/s]

 98%|█████████▊| 982/1000 [02:12<00:03,  5.43it/s]

 98%|█████████▊| 984/1000 [02:12<00:02,  6.91it/s]

 99%|█████████▊| 986/1000 [02:12<00:01,  8.34it/s]

 99%|█████████▉| 988/1000 [02:13<00:01,  6.72it/s]

 99%|█████████▉| 989/1000 [02:13<00:01,  5.98it/s]

 99%|█████████▉| 991/1000 [02:13<00:01,  6.13it/s]

 99%|█████████▉| 992/1000 [02:14<00:01,  4.96it/s]

 99%|█████████▉| 994/1000 [02:14<00:00,  6.52it/s]

100%|█████████▉| 995/1000 [02:14<00:00,  5.51it/s]

100%|█████████▉| 997/1000 [02:14<00:00,  7.01it/s]

100%|█████████▉| 999/1000 [02:15<00:00,  6.72it/s]

100%|██████████| 1000/1000 [02:15<00:00,  6.63it/s]
                                                     

                                                   
{'eval_loss': '0.7529', 'eval_runtime': '135.5', 'eval_samples_per_second': '7.381', 'eval_steps_per_second': '7.381', 'epoch': '0.9931', 'num_input_tokens_seen': 12115448}

 99%|█████████▉| 1800/1813 [3:21:24<01:21,  6.28s/it]

100%|██████████| 1000/1000 [02:15<00:00,  6.63it/s]

                                                   Saving model checkpoint to /home/schwarc/diplomovka/optuna_lr_hpo_1gpu/trials/trial_002_lr_1.000e-04/checkpoint-1800
loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}


 99%|█████████▉| 1801/1813 [3:21:33<09:32, 47.67s/it]
 99%|█████████▉| 1802/1813 [3:21:38<06:24, 34.94s/it]
 99%|█████████▉| 1803/1813 [3:21:44<04:21, 26.13s/it]
100%|█████████▉| 1804/1813 [3:21:51<03:05, 20.56s/it]
100%|█████████▉| 1805/1813 [3:21:57<02:09, 16.18s/it]
100%|█████████▉| 1806/1813 [3:22:04<01:32, 13.26s/it]
100%|█████████▉| 1807/1813 [3:22:11<01:08, 11.39s/it]
100%|█████████▉| 1808/1813 [3:22:18<00:51, 10.20s/it]
100%|█████████▉| 1809/1813 [3:22:24<00:36,  9.05s/it]
100%|█████████▉| 1810/1813 [3:22:30<00:24,  8.06s/it]
                                                     
{'loss': '0.8685', 'grad_norm': '0.8519', 'learning_rate': '1.427e-09', 'epoch': '0.9986', 'num_input_tokens_seen': 12187432, 'train_runtime': '1.215e+04', 'train_tokens_per_second': '1003'}

100%|█████████▉| 1810/1813 [3:22:30<00:24,  8.06s/it]
100%|█████████▉| 1811/1813 [3:22:36<00:14,  7.33s/it]
100%|█████████▉| 1812/1813 [3:22:41<00:06,  6.72s/it]
100%|██████████| 1813/1813 [3:22:44<00:00,  5.64s/it]
***** Running Evaluation *****
  Num examples = 1000
  Batch size = 1
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:71: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:281: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:172: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:202: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:254: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)


  0%|          | 0/1000 [00:00<?, ?it/s]

  0%|          | 3/1000 [00:00<01:03, 15.73it/s]

  0%|          | 5/1000 [00:00<02:17,  7.23it/s]

  1%|          | 7/1000 [00:00<01:59,  8.33it/s]

  1%|          | 9/1000 [00:01<02:33,  6.47it/s]

  1%|          | 11/1000 [00:01<02:02,  8.08it/s]

  1%|▏         | 13/1000 [00:01<02:21,  7.00it/s]

  1%|▏         | 14/1000 [00:01<02:24,  6.82it/s]

  2%|▏         | 15/1000 [00:02<02:45,  5.96it/s]

  2%|▏         | 16/1000 [00:02<02:52,  5.72it/s]

  2%|▏         | 18/1000 [00:02<02:46,  5.91it/s]

  2%|▏         | 19/1000 [00:02<03:13,  5.07it/s]

  2%|▏         | 20/1000 [00:03<03:35,  4.55it/s]

  2%|▏         | 22/1000 [00:03<02:38,  6.18it/s]

  2%|▏         | 23/1000 [00:03<02:56,  5.55it/s]

  2%|▎         | 25/1000 [00:03<02:13,  7.31it/s]

  3%|▎         | 26/1000 [00:04<02:36,  6.24it/s]

  3%|▎         | 28/1000 [00:04<02:42,  5.97it/s]

  3%|▎         | 29/1000 [00:04<02:33,  6.34it/s]

  3%|▎         | 30/1000 [00:04<02:43,  5.95it/s]

  3%|▎         | 31/1000 [00:04<03:01,  5.34it/s]

  3%|▎         | 32/1000 [00:05<02:41,  5.99it/s]

  3%|▎         | 33/1000 [00:05<02:48,  5.75it/s]

  4%|▎         | 35/1000 [00:05<02:05,  7.67it/s]

  4%|▎         | 37/1000 [00:05<01:46,  9.08it/s]

  4%|▍         | 39/1000 [00:05<02:06,  7.58it/s]

  4%|▍         | 40/1000 [00:06<02:03,  7.74it/s]

  4%|▍         | 42/1000 [00:06<01:45,  9.10it/s]

  4%|▍         | 44/1000 [00:06<01:32, 10.33it/s]

  5%|▍         | 46/1000 [00:06<01:45,  9.03it/s]

  5%|▍         | 47/1000 [00:06<02:09,  7.36it/s]

  5%|▍         | 49/1000 [00:06<01:48,  8.74it/s]

  5%|▌         | 51/1000 [00:07<01:35,  9.90it/s]

  5%|▌         | 53/1000 [00:07<01:26, 10.92it/s]

  6%|▌         | 55/1000 [00:07<01:28, 10.73it/s]

  6%|▌         | 57/1000 [00:07<01:41,  9.28it/s]

  6%|▌         | 59/1000 [00:08<01:54,  8.19it/s]

  6%|▌         | 61/1000 [00:08<01:40,  9.32it/s]

  6%|▋         | 63/1000 [00:08<01:36,  9.74it/s]

  6%|▋         | 65/1000 [00:08<01:51,  8.35it/s]

  7%|▋         | 67/1000 [00:09<02:03,  7.57it/s]

  7%|▋         | 69/1000 [00:09<01:52,  8.25it/s]

  7%|▋         | 70/1000 [00:09<02:13,  6.98it/s]

  7%|▋         | 72/1000 [00:09<02:18,  6.71it/s]

  7%|▋         | 74/1000 [00:09<01:54,  8.11it/s]

  8%|▊         | 75/1000 [00:10<02:15,  6.85it/s]

  8%|▊         | 76/1000 [00:10<02:18,  6.66it/s]

  8%|▊         | 78/1000 [00:10<02:26,  6.30it/s]

  8%|▊         | 80/1000 [00:10<01:57,  7.83it/s]

  8%|▊         | 82/1000 [00:10<01:40,  9.18it/s]

  8%|▊         | 84/1000 [00:11<01:54,  8.03it/s]

  8%|▊         | 85/1000 [00:11<02:14,  6.78it/s]

  9%|▊         | 86/1000 [00:11<02:33,  5.94it/s]

  9%|▊         | 87/1000 [00:12<02:50,  5.37it/s]

  9%|▉         | 89/1000 [00:12<02:10,  6.99it/s]

  9%|▉         | 90/1000 [00:12<02:05,  7.25it/s]

  9%|▉         | 91/1000 [00:12<02:29,  6.08it/s]

  9%|▉         | 92/1000 [00:12<02:27,  6.17it/s]

  9%|▉         | 93/1000 [00:12<02:37,  5.77it/s]

 10%|▉         | 95/1000 [00:13<02:44,  5.52it/s]

 10%|▉         | 97/1000 [00:13<02:13,  6.78it/s]

 10%|▉         | 99/1000 [00:13<01:47,  8.35it/s]

 10%|█         | 101/1000 [00:13<01:33,  9.61it/s]

 10%|█         | 103/1000 [00:14<01:55,  7.74it/s]

 10%|█         | 104/1000 [00:14<01:54,  7.81it/s]

 11%|█         | 106/1000 [00:14<01:36,  9.30it/s]

 11%|█         | 108/1000 [00:14<01:25, 10.42it/s]

 11%|█         | 110/1000 [00:14<01:19, 11.18it/s]

 11%|█         | 112/1000 [00:14<01:13, 12.03it/s]

 11%|█▏        | 114/1000 [00:14<01:10, 12.52it/s]

 12%|█▏        | 116/1000 [00:15<01:09, 12.80it/s]

 12%|█▏        | 118/1000 [00:15<01:06, 13.22it/s]

 12%|█▏        | 120/1000 [00:15<02:07,  6.91it/s]

 12%|█▏        | 122/1000 [00:16<01:48,  8.07it/s]

 12%|█▏        | 124/1000 [00:16<01:57,  7.42it/s]

 12%|█▎        | 125/1000 [00:16<02:33,  5.72it/s]

 13%|█▎        | 126/1000 [00:16<02:22,  6.14it/s]

 13%|█▎        | 127/1000 [00:17<02:30,  5.80it/s]

 13%|█▎        | 128/1000 [00:17<02:45,  5.28it/s]

 13%|█▎        | 130/1000 [00:17<02:02,  7.10it/s]

 13%|█▎        | 132/1000 [00:17<01:39,  8.70it/s]

 13%|█▎        | 134/1000 [00:17<01:25, 10.14it/s]

 14%|█▎        | 136/1000 [00:17<01:29,  9.64it/s]

 14%|█▍        | 138/1000 [00:18<01:27,  9.88it/s]

 14%|█▍        | 140/1000 [00:18<01:26,  9.93it/s]

 14%|█▍        | 142/1000 [00:18<01:35,  9.00it/s]

 14%|█▍        | 143/1000 [00:18<01:36,  8.87it/s]

 14%|█▍        | 145/1000 [00:18<01:25, 10.05it/s]

 15%|█▍        | 147/1000 [00:19<01:41,  8.41it/s]

 15%|█▍        | 148/1000 [00:19<01:40,  8.46it/s]

 15%|█▌        | 150/1000 [00:19<01:26,  9.88it/s]

 15%|█▌        | 152/1000 [00:19<01:17, 11.00it/s]

 15%|█▌        | 154/1000 [00:19<01:21, 10.39it/s]

 16%|█▌        | 156/1000 [00:20<02:07,  6.64it/s]

 16%|█▌        | 158/1000 [00:20<01:45,  7.96it/s]

 16%|█▌        | 160/1000 [00:20<01:37,  8.61it/s]

 16%|█▌        | 162/1000 [00:20<01:47,  7.81it/s]

 16%|█▋        | 163/1000 [00:21<01:51,  7.50it/s]

 16%|█▋        | 164/1000 [00:21<02:10,  6.39it/s]

 16%|█▋        | 165/1000 [00:21<02:27,  5.66it/s]

 17%|█▋        | 166/1000 [00:21<02:41,  5.18it/s]

 17%|█▋        | 167/1000 [00:21<02:24,  5.77it/s]

 17%|█▋        | 169/1000 [00:22<01:46,  7.83it/s]

 17%|█▋        | 171/1000 [00:22<01:56,  7.14it/s]

 17%|█▋        | 172/1000 [00:22<02:14,  6.15it/s]

 17%|█▋        | 173/1000 [00:22<02:12,  6.22it/s]

 17%|█▋        | 174/1000 [00:22<02:02,  6.74it/s]

 18%|█▊        | 176/1000 [00:23<01:37,  8.44it/s]

 18%|█▊        | 177/1000 [00:23<02:00,  6.80it/s]

 18%|█▊        | 179/1000 [00:23<01:35,  8.57it/s]

 18%|█▊        | 180/1000 [00:23<01:36,  8.49it/s]

 18%|█▊        | 181/1000 [00:23<02:01,  6.74it/s]

 18%|█▊        | 182/1000 [00:24<02:23,  5.71it/s]

 18%|█▊        | 183/1000 [00:24<02:21,  5.78it/s]

 18%|█▊        | 185/1000 [00:24<01:45,  7.73it/s]

 19%|█▊        | 186/1000 [00:24<01:43,  7.89it/s]

 19%|█▊        | 187/1000 [00:24<02:07,  6.38it/s]

 19%|█▉        | 189/1000 [00:24<01:40,  8.11it/s]

 19%|█▉        | 190/1000 [00:25<02:02,  6.63it/s]

 19%|█▉        | 192/1000 [00:25<02:04,  6.48it/s]

 19%|█▉        | 194/1000 [00:25<02:06,  6.38it/s]

 20%|█▉        | 196/1000 [00:25<01:43,  7.75it/s]

 20%|█▉        | 198/1000 [00:26<01:27,  9.19it/s]

 20%|██        | 200/1000 [00:26<01:14, 10.67it/s]

 20%|██        | 202/1000 [00:26<01:30,  8.77it/s]

 20%|██        | 204/1000 [00:26<01:32,  8.63it/s]

 21%|██        | 206/1000 [00:26<01:20,  9.92it/s]

 21%|██        | 208/1000 [00:27<01:33,  8.51it/s]

 21%|██        | 210/1000 [00:27<01:33,  8.48it/s]

 21%|██        | 212/1000 [00:27<01:21,  9.68it/s]

 21%|██▏       | 214/1000 [00:27<01:30,  8.73it/s]

 22%|██▏       | 216/1000 [00:28<01:25,  9.14it/s]

 22%|██▏       | 217/1000 [00:28<01:44,  7.49it/s]

 22%|██▏       | 219/1000 [00:28<01:28,  8.78it/s]

 22%|██▏       | 220/1000 [00:28<02:03,  6.30it/s]

 22%|██▏       | 221/1000 [00:28<02:03,  6.29it/s]

 22%|██▏       | 223/1000 [00:29<02:20,  5.54it/s]

 22%|██▏       | 224/1000 [00:29<02:08,  6.04it/s]

 22%|██▎       | 225/1000 [00:29<02:07,  6.09it/s]

 23%|██▎       | 226/1000 [00:29<02:23,  5.41it/s]

 23%|██▎       | 228/1000 [00:30<01:53,  6.81it/s]

 23%|██▎       | 229/1000 [00:30<02:10,  5.89it/s]

 23%|██▎       | 230/1000 [00:30<02:01,  6.36it/s]

 23%|██▎       | 232/1000 [00:30<01:35,  8.01it/s]

 23%|██▎       | 233/1000 [00:30<01:33,  8.20it/s]

 24%|██▎       | 235/1000 [00:30<01:17,  9.91it/s]

 24%|██▎       | 237/1000 [00:31<01:20,  9.43it/s]

 24%|██▍       | 239/1000 [00:31<01:24,  8.96it/s]

 24%|██▍       | 241/1000 [00:31<01:31,  8.28it/s]

 24%|██▍       | 242/1000 [00:31<02:06,  5.98it/s]

 24%|██▍       | 243/1000 [00:32<02:19,  5.44it/s]

 24%|██▍       | 245/1000 [00:32<01:53,  6.63it/s]

 25%|██▍       | 247/1000 [00:32<01:31,  8.23it/s]

 25%|██▍       | 248/1000 [00:32<01:49,  6.84it/s]

 25%|██▍       | 249/1000 [00:33<02:06,  5.95it/s]

 25%|██▌       | 250/1000 [00:33<02:07,  5.86it/s]

 25%|██▌       | 252/1000 [00:33<02:04,  6.02it/s]

 25%|██▌       | 253/1000 [00:33<02:10,  5.73it/s]

 26%|██▌       | 255/1000 [00:33<01:41,  7.35it/s]

 26%|██▌       | 256/1000 [00:34<01:36,  7.68it/s]

 26%|██▌       | 258/1000 [00:34<01:25,  8.73it/s]

 26%|██▌       | 260/1000 [00:34<01:37,  7.63it/s]

 26%|██▌       | 261/1000 [00:34<01:53,  6.49it/s]

 26%|██▌       | 262/1000 [00:34<01:56,  6.35it/s]

 26%|██▋       | 264/1000 [00:35<01:57,  6.28it/s]

 26%|██▋       | 265/1000 [00:35<01:52,  6.55it/s]

 27%|██▋       | 266/1000 [00:35<01:46,  6.87it/s]

 27%|██▋       | 268/1000 [00:35<01:37,  7.50it/s]

 27%|██▋       | 270/1000 [00:36<01:43,  7.02it/s]

 27%|██▋       | 271/1000 [00:36<02:14,  5.43it/s]

 27%|██▋       | 273/1000 [00:36<02:07,  5.69it/s]

 28%|██▊       | 275/1000 [00:36<01:48,  6.69it/s]

 28%|██▊       | 277/1000 [00:37<01:29,  8.06it/s]

 28%|██▊       | 278/1000 [00:37<01:46,  6.80it/s]

 28%|██▊       | 280/1000 [00:37<01:49,  6.61it/s]

 28%|██▊       | 282/1000 [00:37<01:29,  8.01it/s]

 28%|██▊       | 283/1000 [00:38<02:02,  5.85it/s]

 28%|██▊       | 284/1000 [00:38<02:05,  5.70it/s]

 29%|██▊       | 286/1000 [00:38<01:36,  7.42it/s]

 29%|██▉       | 288/1000 [00:38<01:21,  8.73it/s]

 29%|██▉       | 290/1000 [00:38<01:31,  7.76it/s]

 29%|██▉       | 291/1000 [00:39<01:41,  6.98it/s]

 29%|██▉       | 292/1000 [00:39<01:57,  6.03it/s]

 29%|██▉       | 294/1000 [00:39<01:38,  7.15it/s]

 30%|██▉       | 296/1000 [00:39<01:42,  6.86it/s]

 30%|██▉       | 298/1000 [00:40<01:26,  8.16it/s]

 30%|██▉       | 299/1000 [00:40<01:48,  6.45it/s]

 30%|███       | 300/1000 [00:40<01:42,  6.83it/s]

 30%|███       | 301/1000 [00:40<01:38,  7.10it/s]

 30%|███       | 303/1000 [00:40<01:19,  8.74it/s]

 30%|███       | 304/1000 [00:40<01:26,  8.06it/s]

 30%|███       | 305/1000 [00:40<01:25,  8.14it/s]

 31%|███       | 306/1000 [00:41<01:39,  6.95it/s]

 31%|███       | 307/1000 [00:41<01:42,  6.79it/s]

 31%|███       | 309/1000 [00:41<01:18,  8.77it/s]

 31%|███       | 311/1000 [00:41<01:07, 10.17it/s]

 31%|███▏      | 313/1000 [00:41<01:01, 11.24it/s]

 32%|███▏      | 315/1000 [00:42<01:06, 10.24it/s]

 32%|███▏      | 317/1000 [00:42<01:11,  9.58it/s]

 32%|███▏      | 319/1000 [00:42<01:34,  7.22it/s]

 32%|███▏      | 321/1000 [00:42<01:38,  6.88it/s]

 32%|███▏      | 322/1000 [00:43<01:45,  6.44it/s]

 32%|███▏      | 324/1000 [00:43<01:27,  7.75it/s]

 32%|███▎      | 325/1000 [00:43<01:58,  5.69it/s]

 33%|███▎      | 327/1000 [00:43<01:30,  7.40it/s]

 33%|███▎      | 328/1000 [00:44<01:33,  7.16it/s]

 33%|███▎      | 330/1000 [00:44<01:38,  6.79it/s]

 33%|███▎      | 332/1000 [00:44<01:41,  6.57it/s]

 33%|███▎      | 333/1000 [00:44<01:35,  6.95it/s]

 33%|███▎      | 334/1000 [00:44<01:44,  6.37it/s]

 34%|███▎      | 336/1000 [00:45<01:22,  8.02it/s]

 34%|███▍      | 338/1000 [00:45<01:15,  8.81it/s]

 34%|███▍      | 340/1000 [00:45<01:05, 10.02it/s]

 34%|███▍      | 342/1000 [00:45<01:00, 10.87it/s]

 34%|███▍      | 344/1000 [00:46<01:26,  7.59it/s]

 34%|███▍      | 345/1000 [00:46<01:24,  7.71it/s]

 35%|███▍      | 346/1000 [00:46<01:30,  7.22it/s]

 35%|███▍      | 347/1000 [00:46<01:28,  7.41it/s]

 35%|███▍      | 349/1000 [00:46<01:34,  6.91it/s]

 35%|███▌      | 350/1000 [00:47<01:49,  5.95it/s]

 35%|███▌      | 352/1000 [00:47<01:24,  7.62it/s]

 35%|███▌      | 354/1000 [00:47<01:25,  7.55it/s]

 36%|███▌      | 355/1000 [00:47<01:27,  7.35it/s]

 36%|███▌      | 357/1000 [00:47<01:11,  8.94it/s]

 36%|███▌      | 359/1000 [00:47<01:00, 10.52it/s]

 36%|███▌      | 361/1000 [00:48<01:08,  9.38it/s]

 36%|███▋      | 363/1000 [00:48<01:28,  7.17it/s]

 36%|███▋      | 364/1000 [00:48<01:41,  6.26it/s]

 36%|███▋      | 365/1000 [00:49<02:09,  4.91it/s]

 37%|███▋      | 367/1000 [00:49<01:58,  5.36it/s]

 37%|███▋      | 368/1000 [00:49<02:05,  5.02it/s]

 37%|███▋      | 369/1000 [00:49<01:52,  5.59it/s]

 37%|███▋      | 371/1000 [00:49<01:23,  7.54it/s]

 37%|███▋      | 372/1000 [00:50<01:21,  7.71it/s]

 37%|███▋      | 374/1000 [00:50<01:17,  8.07it/s]

 38%|███▊      | 375/1000 [00:50<01:40,  6.20it/s]

 38%|███▊      | 376/1000 [00:50<01:54,  5.47it/s]

 38%|███▊      | 378/1000 [00:51<01:30,  6.91it/s]

 38%|███▊      | 380/1000 [00:51<01:10,  8.75it/s]

 38%|███▊      | 382/1000 [00:51<01:18,  7.89it/s]

 38%|███▊      | 384/1000 [00:51<01:07,  9.17it/s]

 39%|███▊      | 386/1000 [00:51<01:06,  9.16it/s]

 39%|███▉      | 388/1000 [00:52<01:25,  7.14it/s]

 39%|███▉      | 390/1000 [00:52<01:19,  7.63it/s]

 39%|███▉      | 391/1000 [00:52<01:22,  7.36it/s]

 39%|███▉      | 393/1000 [00:52<01:09,  8.78it/s]

 40%|███▉      | 395/1000 [00:53<01:21,  7.46it/s]

 40%|███▉      | 397/1000 [00:53<01:08,  8.74it/s]

 40%|███▉      | 399/1000 [00:53<01:36,  6.23it/s]

 40%|████      | 400/1000 [00:54<01:45,  5.68it/s]

 40%|████      | 402/1000 [00:54<01:41,  5.91it/s]

 40%|████      | 404/1000 [00:54<01:22,  7.23it/s]

 41%|████      | 406/1000 [00:54<01:09,  8.49it/s]

 41%|████      | 408/1000 [00:55<01:32,  6.39it/s]

 41%|████      | 410/1000 [00:55<01:31,  6.44it/s]

 41%|████      | 411/1000 [00:55<01:40,  5.83it/s]

 41%|████      | 412/1000 [00:55<01:49,  5.35it/s]

 41%|████▏     | 414/1000 [00:56<01:23,  7.05it/s]

 42%|████▏     | 416/1000 [00:56<01:25,  6.81it/s]

 42%|████▏     | 418/1000 [00:56<01:10,  8.25it/s]

 42%|████▏     | 420/1000 [00:56<01:08,  8.44it/s]

 42%|████▏     | 421/1000 [00:56<01:17,  7.50it/s]

 42%|████▏     | 423/1000 [00:57<01:26,  6.69it/s]

 42%|████▏     | 424/1000 [00:57<01:37,  5.93it/s]

 42%|████▎     | 425/1000 [00:57<01:30,  6.36it/s]

 43%|████▎     | 427/1000 [00:57<01:12,  7.95it/s]

 43%|████▎     | 428/1000 [00:57<01:15,  7.54it/s]

 43%|████▎     | 429/1000 [00:58<01:12,  7.84it/s]

 43%|████▎     | 431/1000 [00:58<00:59,  9.53it/s]

 43%|████▎     | 433/1000 [00:58<00:51, 11.01it/s]

 44%|████▎     | 435/1000 [00:58<00:47, 11.78it/s]

 44%|████▎     | 437/1000 [00:58<00:53, 10.50it/s]

 44%|████▍     | 439/1000 [00:59<01:09,  8.08it/s]

 44%|████▍     | 441/1000 [00:59<01:00,  9.17it/s]

 44%|████▍     | 443/1000 [00:59<01:11,  7.78it/s]

 44%|████▍     | 444/1000 [00:59<01:18,  7.05it/s]

 45%|████▍     | 446/1000 [00:59<01:04,  8.53it/s]

 45%|████▍     | 448/1000 [01:00<01:14,  7.40it/s]

 45%|████▌     | 450/1000 [01:00<01:19,  6.95it/s]

 45%|████▌     | 451/1000 [01:00<01:29,  6.14it/s]

 45%|████▌     | 452/1000 [01:01<01:38,  5.55it/s]

 45%|████▌     | 454/1000 [01:01<01:16,  7.15it/s]

 46%|████▌     | 456/1000 [01:01<01:04,  8.47it/s]

 46%|████▌     | 457/1000 [01:01<01:09,  7.78it/s]

 46%|████▌     | 459/1000 [01:01<00:58,  9.23it/s]

 46%|████▌     | 461/1000 [01:01<00:49, 10.79it/s]

 46%|████▋     | 463/1000 [01:02<01:10,  7.61it/s]

 46%|████▋     | 465/1000 [01:02<01:19,  6.73it/s]

 47%|████▋     | 466/1000 [01:02<01:28,  6.00it/s]

 47%|████▋     | 467/1000 [01:03<01:50,  4.82it/s]

 47%|████▋     | 469/1000 [01:03<01:24,  6.25it/s]

 47%|████▋     | 471/1000 [01:03<01:07,  7.80it/s]

 47%|████▋     | 473/1000 [01:03<01:09,  7.53it/s]

 47%|████▋     | 474/1000 [01:04<01:21,  6.49it/s]

 48%|████▊     | 476/1000 [01:04<01:22,  6.38it/s]

 48%|████▊     | 477/1000 [01:04<01:35,  5.48it/s]

 48%|████▊     | 479/1000 [01:04<01:12,  7.14it/s]

 48%|████▊     | 480/1000 [01:04<01:19,  6.57it/s]

 48%|████▊     | 482/1000 [01:05<01:04,  8.05it/s]

 48%|████▊     | 484/1000 [01:05<01:10,  7.30it/s]

 48%|████▊     | 485/1000 [01:05<01:21,  6.31it/s]

 49%|████▊     | 486/1000 [01:05<01:21,  6.30it/s]

 49%|████▉     | 488/1000 [01:05<01:04,  8.00it/s]

 49%|████▉     | 489/1000 [01:06<01:17,  6.62it/s]

 49%|████▉     | 491/1000 [01:06<01:02,  8.20it/s]

 49%|████▉     | 492/1000 [01:06<01:01,  8.25it/s]

 49%|████▉     | 494/1000 [01:06<00:50,  9.96it/s]

 50%|████▉     | 496/1000 [01:06<00:59,  8.40it/s]

 50%|████▉     | 498/1000 [01:07<00:59,  8.43it/s]

 50%|████▉     | 499/1000 [01:07<01:15,  6.66it/s]

 50%|█████     | 500/1000 [01:07<01:24,  5.92it/s]

 50%|█████     | 502/1000 [01:07<01:06,  7.54it/s]

 50%|█████     | 503/1000 [01:08<01:13,  6.80it/s]

 50%|█████     | 505/1000 [01:08<01:15,  6.55it/s]

 51%|█████     | 506/1000 [01:08<01:25,  5.80it/s]

 51%|█████     | 508/1000 [01:08<01:06,  7.42it/s]

 51%|█████     | 510/1000 [01:08<00:54,  8.95it/s]

 51%|█████     | 512/1000 [01:09<00:48,  9.97it/s]

 51%|█████▏    | 514/1000 [01:09<01:06,  7.28it/s]

 52%|█████▏    | 515/1000 [01:09<01:04,  7.53it/s]

 52%|█████▏    | 516/1000 [01:09<01:08,  7.10it/s]

 52%|█████▏    | 518/1000 [01:09<00:59,  8.07it/s]

 52%|█████▏    | 519/1000 [01:10<01:15,  6.37it/s]

 52%|█████▏    | 521/1000 [01:10<00:59,  8.02it/s]

 52%|█████▏    | 522/1000 [01:10<01:11,  6.68it/s]

 52%|█████▏    | 523/1000 [01:10<01:22,  5.81it/s]

 52%|█████▏    | 524/1000 [01:11<01:25,  5.56it/s]

 53%|█████▎    | 526/1000 [01:11<01:12,  6.58it/s]

 53%|█████▎    | 528/1000 [01:11<01:12,  6.52it/s]

 53%|█████▎    | 529/1000 [01:11<01:13,  6.40it/s]

 53%|█████▎    | 531/1000 [01:11<00:57,  8.11it/s]

 53%|█████▎    | 533/1000 [01:12<00:48,  9.68it/s]

 54%|█████▎    | 535/1000 [01:12<01:09,  6.67it/s]

 54%|█████▎    | 536/1000 [01:12<01:13,  6.34it/s]

 54%|█████▎    | 537/1000 [01:12<01:21,  5.65it/s]

 54%|█████▍    | 539/1000 [01:13<01:17,  5.91it/s]

 54%|█████▍    | 540/1000 [01:13<01:20,  5.74it/s]

 54%|█████▍    | 541/1000 [01:13<01:27,  5.25it/s]

 54%|█████▍    | 543/1000 [01:13<01:06,  6.92it/s]

 55%|█████▍    | 545/1000 [01:14<01:04,  7.05it/s]

 55%|█████▍    | 546/1000 [01:14<01:10,  6.48it/s]

 55%|█████▍    | 547/1000 [01:14<01:19,  5.67it/s]

 55%|█████▍    | 549/1000 [01:14<01:16,  5.90it/s]

 55%|█████▌    | 551/1000 [01:15<01:00,  7.48it/s]

 55%|█████▌    | 552/1000 [01:15<01:01,  7.23it/s]

 55%|█████▌    | 553/1000 [01:15<01:12,  6.13it/s]

 55%|█████▌    | 554/1000 [01:15<01:15,  5.92it/s]

 56%|█████▌    | 556/1000 [01:15<00:57,  7.73it/s]

 56%|█████▌    | 557/1000 [01:15<01:03,  6.99it/s]

 56%|█████▌    | 559/1000 [01:16<00:50,  8.81it/s]

 56%|█████▌    | 561/1000 [01:16<00:43, 10.01it/s]

 56%|█████▋    | 563/1000 [01:16<00:52,  8.34it/s]

 56%|█████▋    | 565/1000 [01:16<00:54,  7.95it/s]

 57%|█████▋    | 566/1000 [01:17<01:04,  6.72it/s]

 57%|█████▋    | 568/1000 [01:17<01:06,  6.53it/s]

 57%|█████▋    | 569/1000 [01:17<01:07,  6.42it/s]

 57%|█████▋    | 571/1000 [01:17<01:06,  6.42it/s]

 57%|█████▋    | 572/1000 [01:18<01:08,  6.28it/s]

 57%|█████▋    | 574/1000 [01:18<01:07,  6.32it/s]

 58%|█████▊    | 576/1000 [01:18<00:55,  7.59it/s]

 58%|█████▊    | 577/1000 [01:18<01:15,  5.62it/s]

 58%|█████▊    | 578/1000 [01:19<01:21,  5.19it/s]

 58%|█████▊    | 580/1000 [01:19<01:00,  6.90it/s]

 58%|█████▊    | 582/1000 [01:19<00:49,  8.46it/s]

 58%|█████▊    | 584/1000 [01:19<00:55,  7.53it/s]

 58%|█████▊    | 585/1000 [01:19<01:00,  6.87it/s]

 59%|█████▊    | 587/1000 [01:20<00:57,  7.14it/s]

 59%|█████▉    | 589/1000 [01:20<00:48,  8.52it/s]

 59%|█████▉    | 590/1000 [01:20<01:00,  6.74it/s]

 59%|█████▉    | 592/1000 [01:20<00:50,  8.15it/s]

 59%|█████▉    | 593/1000 [01:21<00:59,  6.79it/s]

 60%|█████▉    | 595/1000 [01:21<00:48,  8.39it/s]

 60%|█████▉    | 596/1000 [01:21<00:58,  6.87it/s]

 60%|█████▉    | 597/1000 [01:21<01:00,  6.65it/s]

 60%|█████▉    | 599/1000 [01:21<01:02,  6.46it/s]

 60%|██████    | 601/1000 [01:22<01:02,  6.38it/s]

 60%|██████    | 602/1000 [01:22<00:59,  6.69it/s]

 60%|██████    | 604/1000 [01:22<01:09,  5.68it/s]

 61%|██████    | 606/1000 [01:22<00:55,  7.08it/s]

 61%|██████    | 608/1000 [01:23<00:49,  7.85it/s]

 61%|██████    | 610/1000 [01:23<00:46,  8.47it/s]

 61%|██████    | 612/1000 [01:23<00:40,  9.54it/s]

 61%|██████▏   | 614/1000 [01:23<00:36, 10.64it/s]

 62%|██████▏   | 616/1000 [01:24<00:50,  7.56it/s]

 62%|██████▏   | 617/1000 [01:24<00:49,  7.71it/s]

 62%|██████▏   | 619/1000 [01:24<00:42,  9.05it/s]

 62%|██████▏   | 621/1000 [01:24<00:47,  8.01it/s]

 62%|██████▏   | 623/1000 [01:24<00:46,  8.19it/s]

 62%|██████▎   | 625/1000 [01:25<00:50,  7.45it/s]

 63%|██████▎   | 627/1000 [01:25<00:43,  8.62it/s]

 63%|██████▎   | 628/1000 [01:25<00:51,  7.18it/s]

 63%|██████▎   | 629/1000 [01:25<00:59,  6.21it/s]

 63%|██████▎   | 631/1000 [01:26<00:46,  7.86it/s]

 63%|██████▎   | 633/1000 [01:26<00:38,  9.41it/s]

 64%|██████▎   | 635/1000 [01:26<00:54,  6.71it/s]

 64%|██████▎   | 636/1000 [01:26<00:51,  7.06it/s]

 64%|██████▍   | 638/1000 [01:26<00:45,  7.95it/s]

 64%|██████▍   | 640/1000 [01:27<00:39,  9.16it/s]

 64%|██████▍   | 642/1000 [01:27<00:45,  7.94it/s]

 64%|██████▍   | 643/1000 [01:27<00:47,  7.57it/s]

 64%|██████▍   | 645/1000 [01:27<00:50,  7.09it/s]

 65%|██████▍   | 647/1000 [01:28<00:46,  7.58it/s]

 65%|██████▍   | 648/1000 [01:28<00:54,  6.51it/s]

 65%|██████▌   | 650/1000 [01:28<00:53,  6.53it/s]

 65%|██████▌   | 652/1000 [01:28<00:55,  6.31it/s]

 65%|██████▌   | 654/1000 [01:29<00:45,  7.69it/s]

 66%|██████▌   | 656/1000 [01:29<00:38,  8.89it/s]

 66%|██████▌   | 658/1000 [01:29<00:42,  8.08it/s]

 66%|██████▌   | 659/1000 [01:29<00:56,  5.98it/s]

 66%|██████▌   | 661/1000 [01:30<00:44,  7.55it/s]

 66%|██████▌   | 662/1000 [01:30<00:52,  6.48it/s]

 66%|██████▋   | 664/1000 [01:30<00:58,  5.77it/s]

 66%|██████▋   | 665/1000 [01:30<01:02,  5.32it/s]

 67%|██████▋   | 667/1000 [01:31<00:59,  5.61it/s]

 67%|██████▋   | 668/1000 [01:31<01:03,  5.20it/s]

 67%|██████▋   | 669/1000 [01:31<00:58,  5.70it/s]

 67%|██████▋   | 671/1000 [01:31<00:55,  5.88it/s]

 67%|██████▋   | 673/1000 [01:32<00:49,  6.63it/s]

 68%|██████▊   | 675/1000 [01:32<00:44,  7.26it/s]

 68%|██████▊   | 677/1000 [01:32<00:37,  8.65it/s]

 68%|██████▊   | 679/1000 [01:32<00:33,  9.68it/s]

 68%|██████▊   | 681/1000 [01:32<00:29, 10.91it/s]

 68%|██████▊   | 683/1000 [01:33<00:35,  8.89it/s]

 68%|██████▊   | 685/1000 [01:33<00:31,  9.86it/s]

 69%|██████▊   | 687/1000 [01:33<00:45,  6.85it/s]

 69%|██████▉   | 688/1000 [01:33<00:43,  7.15it/s]

 69%|██████▉   | 690/1000 [01:34<00:45,  6.80it/s]

 69%|██████▉   | 692/1000 [01:34<00:39,  7.82it/s]

 69%|██████▉   | 694/1000 [01:34<00:42,  7.25it/s]

 70%|██████▉   | 695/1000 [01:34<00:41,  7.41it/s]

 70%|██████▉   | 696/1000 [01:35<00:48,  6.33it/s]

 70%|██████▉   | 698/1000 [01:35<00:43,  6.94it/s]

 70%|██████▉   | 699/1000 [01:35<00:49,  6.04it/s]

 70%|███████   | 701/1000 [01:35<00:39,  7.59it/s]

 70%|███████   | 702/1000 [01:36<00:53,  5.61it/s]

 70%|███████   | 704/1000 [01:36<00:41,  7.22it/s]

 70%|███████   | 705/1000 [01:36<00:54,  5.41it/s]

 71%|███████   | 707/1000 [01:36<00:41,  7.02it/s]

 71%|███████   | 709/1000 [01:36<00:38,  7.62it/s]

 71%|███████   | 710/1000 [01:37<00:44,  6.50it/s]

 71%|███████   | 712/1000 [01:37<00:37,  7.70it/s]

 71%|███████▏  | 713/1000 [01:37<00:36,  7.85it/s]

 72%|███████▏  | 715/1000 [01:37<00:30,  9.35it/s]

 72%|███████▏  | 717/1000 [01:37<00:35,  8.05it/s]

 72%|███████▏  | 718/1000 [01:38<00:41,  6.79it/s]

 72%|███████▏  | 719/1000 [01:38<00:47,  5.93it/s]

 72%|███████▏  | 720/1000 [01:38<00:43,  6.45it/s]

 72%|███████▏  | 722/1000 [01:38<00:34,  8.11it/s]

 72%|███████▏  | 723/1000 [01:38<00:33,  8.17it/s]

 72%|███████▏  | 724/1000 [01:38<00:33,  8.20it/s]

 72%|███████▎  | 725/1000 [01:39<00:33,  8.28it/s]

 73%|███████▎  | 727/1000 [01:39<00:27, 10.07it/s]

 73%|███████▎  | 729/1000 [01:39<00:23, 11.54it/s]

 73%|███████▎  | 731/1000 [01:39<00:32,  8.30it/s]

 73%|███████▎  | 733/1000 [01:39<00:28,  9.50it/s]

 74%|███████▎  | 735/1000 [01:40<00:26,  9.87it/s]

 74%|███████▎  | 737/1000 [01:40<00:28,  9.22it/s]

 74%|███████▍  | 739/1000 [01:40<00:27,  9.57it/s]

 74%|███████▍  | 741/1000 [01:40<00:31,  8.21it/s]

 74%|███████▍  | 743/1000 [01:41<00:30,  8.29it/s]

 74%|███████▍  | 745/1000 [01:41<00:26,  9.52it/s]

 75%|███████▍  | 747/1000 [01:41<00:24, 10.36it/s]

 75%|███████▍  | 749/1000 [01:41<00:29,  8.60it/s]

 75%|███████▌  | 750/1000 [01:41<00:32,  7.66it/s]

 75%|███████▌  | 751/1000 [01:42<00:40,  6.15it/s]

 75%|███████▌  | 753/1000 [01:42<00:34,  7.21it/s]

 75%|███████▌  | 754/1000 [01:42<00:39,  6.22it/s]

 76%|███████▌  | 756/1000 [01:42<00:38,  6.39it/s]

 76%|███████▌  | 758/1000 [01:43<00:31,  7.59it/s]

 76%|███████▌  | 759/1000 [01:43<00:33,  7.26it/s]

 76%|███████▌  | 761/1000 [01:43<00:27,  8.60it/s]

 76%|███████▋  | 763/1000 [01:43<00:31,  7.60it/s]

 76%|███████▋  | 764/1000 [01:43<00:35,  6.57it/s]

 77%|███████▋  | 766/1000 [01:44<00:36,  6.34it/s]

 77%|███████▋  | 768/1000 [01:44<00:30,  7.66it/s]

 77%|███████▋  | 769/1000 [01:44<00:35,  6.56it/s]

 77%|███████▋  | 770/1000 [01:44<00:35,  6.50it/s]

 77%|███████▋  | 772/1000 [01:44<00:28,  8.04it/s]

 77%|███████▋  | 773/1000 [01:45<00:35,  6.35it/s]

 77%|███████▋  | 774/1000 [01:45<00:33,  6.76it/s]

 78%|███████▊  | 776/1000 [01:45<00:28,  7.88it/s]

 78%|███████▊  | 778/1000 [01:45<00:23,  9.56it/s]

 78%|███████▊  | 780/1000 [01:46<00:31,  6.92it/s]

 78%|███████▊  | 782/1000 [01:46<00:26,  8.34it/s]

 78%|███████▊  | 784/1000 [01:46<00:30,  7.15it/s]

 79%|███████▊  | 786/1000 [01:46<00:28,  7.52it/s]

 79%|███████▉  | 788/1000 [01:47<00:25,  8.35it/s]

 79%|███████▉  | 790/1000 [01:47<00:23,  8.97it/s]

 79%|███████▉  | 791/1000 [01:47<00:25,  8.20it/s]

 79%|███████▉  | 792/1000 [01:47<00:26,  7.72it/s]

 79%|███████▉  | 793/1000 [01:47<00:25,  7.96it/s]

 80%|███████▉  | 795/1000 [01:48<00:28,  7.18it/s]

 80%|███████▉  | 797/1000 [01:48<00:29,  6.85it/s]

 80%|███████▉  | 798/1000 [01:48<00:33,  6.00it/s]

 80%|████████  | 800/1000 [01:48<00:29,  6.70it/s]

 80%|████████  | 802/1000 [01:49<00:25,  7.63it/s]

 80%|████████  | 804/1000 [01:49<00:25,  7.81it/s]

 81%|████████  | 806/1000 [01:49<00:21,  9.14it/s]

 81%|████████  | 807/1000 [01:49<00:21,  8.94it/s]

 81%|████████  | 809/1000 [01:49<00:18, 10.18it/s]

 81%|████████  | 811/1000 [01:49<00:16, 11.20it/s]

 81%|████████▏ | 813/1000 [01:50<00:20,  9.04it/s]

 82%|████████▏ | 815/1000 [01:50<00:19,  9.28it/s]

 82%|████████▏ | 817/1000 [01:50<00:22,  8.11it/s]

 82%|████████▏ | 819/1000 [01:50<00:19,  9.17it/s]

 82%|████████▏ | 821/1000 [01:51<00:22,  8.02it/s]

 82%|████████▏ | 823/1000 [01:51<00:22,  7.80it/s]

 82%|████████▏ | 824/1000 [01:51<00:26,  6.73it/s]

 82%|████████▎ | 825/1000 [01:51<00:25,  6.98it/s]

 83%|████████▎ | 826/1000 [01:52<00:30,  5.79it/s]

 83%|████████▎ | 828/1000 [01:52<00:32,  5.23it/s]

 83%|████████▎ | 829/1000 [01:52<00:29,  5.72it/s]

 83%|████████▎ | 831/1000 [01:52<00:24,  7.00it/s]

 83%|████████▎ | 832/1000 [01:53<00:29,  5.75it/s]

 83%|████████▎ | 833/1000 [01:53<00:26,  6.23it/s]

 83%|████████▎ | 834/1000 [01:53<00:27,  6.01it/s]

 84%|████████▎ | 835/1000 [01:53<00:25,  6.52it/s]

 84%|████████▎ | 836/1000 [01:53<00:26,  6.09it/s]

 84%|████████▍ | 838/1000 [01:53<00:21,  7.43it/s]

 84%|████████▍ | 840/1000 [01:54<00:24,  6.60it/s]

 84%|████████▍ | 842/1000 [01:54<00:19,  8.13it/s]

 84%|████████▍ | 844/1000 [01:54<00:24,  6.40it/s]

 84%|████████▍ | 845/1000 [01:55<00:26,  5.76it/s]

 85%|████████▍ | 847/1000 [01:55<00:24,  6.24it/s]

 85%|████████▍ | 849/1000 [01:55<00:20,  7.53it/s]

 85%|████████▌ | 850/1000 [01:55<00:23,  6.48it/s]

 85%|████████▌ | 851/1000 [01:55<00:21,  6.86it/s]

 85%|████████▌ | 853/1000 [01:55<00:17,  8.45it/s]

 86%|████████▌ | 855/1000 [01:56<00:14, 10.03it/s]

 86%|████████▌ | 857/1000 [01:56<00:14, 10.19it/s]

 86%|████████▌ | 859/1000 [01:56<00:16,  8.50it/s]

 86%|████████▌ | 861/1000 [01:56<00:14,  9.70it/s]

 86%|████████▋ | 863/1000 [01:56<00:13, 10.52it/s]

 86%|████████▋ | 865/1000 [01:57<00:11, 11.58it/s]

 87%|████████▋ | 867/1000 [01:57<00:14,  9.27it/s]

 87%|████████▋ | 869/1000 [01:57<00:12, 10.23it/s]

 87%|████████▋ | 871/1000 [01:57<00:11, 11.23it/s]

 87%|████████▋ | 873/1000 [01:58<00:16,  7.74it/s]

 88%|████████▊ | 875/1000 [01:58<00:16,  7.60it/s]

 88%|████████▊ | 877/1000 [01:58<00:13,  8.85it/s]

 88%|████████▊ | 879/1000 [01:58<00:17,  6.85it/s]

 88%|████████▊ | 881/1000 [01:59<00:15,  7.58it/s]

 88%|████████▊ | 882/1000 [01:59<00:18,  6.53it/s]

 88%|████████▊ | 884/1000 [01:59<00:14,  7.94it/s]

 89%|████████▊ | 886/1000 [01:59<00:12,  9.15it/s]

 89%|████████▉ | 888/1000 [01:59<00:10, 10.32it/s]

 89%|████████▉ | 890/1000 [02:00<00:11,  9.75it/s]

 89%|████████▉ | 892/1000 [02:00<00:10, 10.73it/s]

 89%|████████▉ | 894/1000 [02:00<00:13,  7.60it/s]

 90%|████████▉ | 896/1000 [02:00<00:11,  8.83it/s]

 90%|████████▉ | 898/1000 [02:01<00:15,  6.53it/s]

 90%|█████████ | 900/1000 [02:01<00:13,  7.69it/s]

 90%|█████████ | 902/1000 [02:01<00:12,  7.85it/s]

 90%|█████████ | 904/1000 [02:01<00:10,  9.05it/s]

 91%|█████████ | 906/1000 [02:02<00:13,  7.04it/s]

 91%|█████████ | 908/1000 [02:02<00:11,  8.30it/s]

 91%|█████████ | 910/1000 [02:02<00:11,  7.58it/s]

 91%|█████████ | 912/1000 [02:02<00:10,  8.77it/s]

 91%|█████████▏| 914/1000 [02:03<00:11,  7.38it/s]

 92%|█████████▏| 916/1000 [02:03<00:11,  7.08it/s]

 92%|█████████▏| 917/1000 [02:03<00:11,  7.36it/s]

 92%|█████████▏| 918/1000 [02:03<00:14,  5.59it/s]

 92%|█████████▏| 919/1000 [02:04<00:14,  5.71it/s]

 92%|█████████▏| 921/1000 [02:04<00:14,  5.58it/s]

 92%|█████████▏| 922/1000 [02:04<00:13,  5.93it/s]

 92%|█████████▏| 924/1000 [02:04<00:10,  7.16it/s]

 93%|█████████▎| 926/1000 [02:04<00:08,  8.64it/s]

 93%|█████████▎| 927/1000 [02:05<00:09,  8.08it/s]

 93%|█████████▎| 928/1000 [02:05<00:10,  6.64it/s]

 93%|█████████▎| 930/1000 [02:05<00:10,  6.47it/s]

 93%|█████████▎| 931/1000 [02:05<00:10,  6.82it/s]

 93%|█████████▎| 933/1000 [02:06<00:10,  6.60it/s]

 93%|█████████▎| 934/1000 [02:06<00:10,  6.16it/s]

 94%|█████████▎| 936/1000 [02:06<00:08,  7.29it/s]

 94%|█████████▍| 938/1000 [02:06<00:07,  8.83it/s]

 94%|█████████▍| 939/1000 [02:06<00:07,  8.05it/s]

 94%|█████████▍| 940/1000 [02:06<00:07,  8.14it/s]

 94%|█████████▍| 942/1000 [02:07<00:09,  6.33it/s]

 94%|█████████▍| 944/1000 [02:07<00:07,  7.07it/s]

 95%|█████████▍| 946/1000 [02:07<00:06,  8.39it/s]

 95%|█████████▍| 948/1000 [02:07<00:05,  9.72it/s]

 95%|█████████▌| 950/1000 [02:08<00:05,  8.83it/s]

 95%|█████████▌| 952/1000 [02:08<00:06,  7.40it/s]

 95%|█████████▌| 954/1000 [02:08<00:07,  6.16it/s]

 96%|█████████▌| 956/1000 [02:09<00:06,  7.28it/s]

 96%|█████████▌| 957/1000 [02:09<00:06,  6.33it/s]

 96%|█████████▌| 959/1000 [02:09<00:07,  5.74it/s]

 96%|█████████▌| 961/1000 [02:09<00:05,  6.77it/s]

 96%|█████████▌| 962/1000 [02:10<00:06,  6.01it/s]

 96%|█████████▋| 964/1000 [02:10<00:04,  7.45it/s]

 96%|█████████▋| 965/1000 [02:10<00:05,  6.42it/s]

 97%|█████████▋| 966/1000 [02:10<00:05,  6.33it/s]

 97%|█████████▋| 968/1000 [02:10<00:03,  8.01it/s]

 97%|█████████▋| 970/1000 [02:11<00:03,  9.41it/s]

 97%|█████████▋| 972/1000 [02:11<00:03,  8.00it/s]

 97%|█████████▋| 974/1000 [02:11<00:02,  9.17it/s]

 98%|█████████▊| 976/1000 [02:11<00:02,  9.77it/s]

 98%|█████████▊| 978/1000 [02:11<00:02, 10.80it/s]

 98%|█████████▊| 980/1000 [02:12<00:02,  8.43it/s]

 98%|█████████▊| 981/1000 [02:12<00:02,  7.05it/s]

 98%|█████████▊| 982/1000 [02:12<00:03,  5.44it/s]

 98%|█████████▊| 984/1000 [02:12<00:02,  6.93it/s]

 99%|█████████▊| 986/1000 [02:13<00:01,  8.37it/s]

 99%|█████████▉| 988/1000 [02:13<00:01,  6.73it/s]

 99%|█████████▉| 989/1000 [02:13<00:01,  5.99it/s]

 99%|█████████▉| 991/1000 [02:14<00:01,  6.14it/s]

 99%|█████████▉| 992/1000 [02:14<00:01,  4.98it/s]

 99%|█████████▉| 994/1000 [02:14<00:00,  6.54it/s]

100%|█████████▉| 995/1000 [02:14<00:00,  5.53it/s]

100%|█████████▉| 997/1000 [02:15<00:00,  7.05it/s]

100%|█████████▉| 999/1000 [02:15<00:00,  6.75it/s]

100%|██████████| 1000/1000 [02:15<00:00,  6.66it/s]
                                                     

                                                   
{'eval_loss': '0.7529', 'eval_runtime': '135.7', 'eval_samples_per_second': '7.371', 'eval_steps_per_second': '7.371', 'epoch': '1', 'num_input_tokens_seen': 12201816}

100%|██████████| 1813/1813 [3:25:00<00:00,  5.64s/it]

100%|██████████| 1000/1000 [02:15<00:00,  6.66it/s]

                                                   Saving model checkpoint to /home/schwarc/diplomovka/optuna_lr_hpo_1gpu/trials/trial_002_lr_1.000e-04/checkpoint-1813
loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}



Training completed. Do not forget to share your model on huggingface.co/models =)



                                                     
{'train_runtime': '1.23e+04', 'train_samples_per_second': '2.357', 'train_steps_per_second': '0.147', 'train_loss': '0.9647', 'epoch': '1', 'num_input_tokens_seen': 12201816}

100%|██████████| 1813/1813 [3:25:01<00:00,  5.64s/it]
100%|██████████| 1813/1813 [3:25:01<00:00,  6.79s/it]
Saving model checkpoint to /home/schwarc/diplomovka/optuna_lr_hpo_1gpu/trials/trial_002_lr_1.000e-04
loading configuration file config.json from cache at /home/schwarc/.cache/huggingface/hub/models--slovak-nlp--mistral-sk-7b/snapshots/089497ae0d72018e9591895c54f774bf0b4a83a4/config.json
Model config MistralConfig {
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.0",
  "use_cache": true,
  "vocab_size": 32000
}

***** train metrics *****
  epoch                    =         1.0
  num_input_tokens_seen    =    12201816
  total_flos               = 487685654GF
  train_loss               =      0.9647
  train_runtime            =  3:25:01.28
  train_samples_per_second =       2.357
  train_steps_per_second   =       0.147
Figure saved at: /home/schwarc/diplomovka/optuna_lr_hpo_1gpu/trials/trial_002_lr_1.000e-04/training_loss.png
Figure saved at: /home/schwarc/diplomovka/optuna_lr_hpo_1gpu/trials/trial_002_lr_1.000e-04/training_eval_loss.png
[WARNING|2026-10-13 06:21:48] llamafactory.extras.ploting:149 >> No metric eval_accuracy to plot.

***** Running Evaluation *****
  Num examples = 1000
  Batch size = 1
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:71: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:281: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:172: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:202: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)
/home/schwarc/miniconda3/envs/llama_factory_unsloth/lib/python3.11/site-packages/transformers/modeling_attn_mask_utils.py:254: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.
  warnings.warn(DEPRECATION_MESSAGE, FutureWarning)

  0%|          | 0/1000 [00:00<?, ?it/s]
  0%|          | 3/1000 [00:00<01:03, 15.82it/s]
  0%|          | 5/1000 [00:00<02:17,  7.24it/s]
  1%|          | 7/1000 [00:00<01:59,  8.33it/s]
  1%|          | 9/1000 [00:01<02:33,  6.47it/s]
  1%|          | 11/1000 [00:01<02:02,  8.07it/s]
  1%|▏         | 13/1000 [00:01<02:20,  7.01it/s]
  1%|▏         | 14/1000 [00:01<02:24,  6.84it/s]
  2%|▏         | 15/1000 [00:02<02:45,  5.96it/s]
  2%|▏         | 16/1000 [00:02<02:51,  5.72it/s]
  2%|▏         | 18/1000 [00:02<02:42,  6.05it/s]
  2%|▏         | 19/1000 [00:02<03:10,  5.15it/s]
  2%|▏         | 20/1000 [00:03<03:33,  4.60it/s]
  2%|▏         | 22/1000 [00:03<02:36,  6.24it/s]
  2%|▏         | 23/1000 [00:03<02:54,  5.58it/s]
  2%|▎         | 25/1000 [00:03<02:12,  7.36it/s]
  3%|▎         | 26/1000 [00:04<02:35,  6.26it/s]
  3%|▎         | 28/1000 [00:04<02:42,  5.99it/s]
  3%|▎         | 29/1000 [00:04<02:32,  6.36it/s]
  3%|▎         | 30/1000 [00:04<02:42,  5.97it/s]
  3%|▎         | 31/1000 [00:04<03:01,  5.35it/s]
  3%|▎         | 32/1000 [00:05<02:41,  5.99it/s]
  3%|▎         | 33/1000 [00:05<02:47,  5.76it/s]
  4%|▎         | 35/1000 [00:05<02:05,  7.67it/s]
  4%|▎         | 37/1000 [00:05<01:45,  9.11it/s]
  4%|▍         | 39/1000 [00:05<02:06,  7.59it/s]
  4%|▍         | 40/1000 [00:05<02:03,  7.76it/s]
  4%|▍         | 42/1000 [00:06<01:45,  9.12it/s]
  4%|▍         | 44/1000 [00:06<01:32, 10.32it/s]
  5%|▍         | 46/1000 [00:06<01:45,  9.04it/s]
  5%|▍         | 47/1000 [00:06<02:09,  7.37it/s]
  5%|▍         | 49/1000 [00:06<01:48,  8.75it/s]
  5%|▌         | 51/1000 [00:07<01:35,  9.91it/s]
  5%|▌         | 53/1000 [00:07<01:26, 10.93it/s]
  6%|▌         | 55/1000 [00:07<01:28, 10.73it/s]
  6%|▌         | 57/1000 [00:07<01:41,  9.29it/s]
  6%|▌         | 59/1000 [00:08<01:54,  8.21it/s]
  6%|▌         | 61/1000 [00:08<01:40,  9.35it/s]
  6%|▋         | 63/1000 [00:08<01:36,  9.75it/s]
  6%|▋         | 65/1000 [00:08<01:51,  8.35it/s]
  7%|▋         | 67/1000 [00:09<02:03,  7.58it/s]
  7%|▋         | 69/1000 [00:09<01:52,  8.26it/s]
  7%|▋         | 70/1000 [00:09<02:13,  6.99it/s]
  7%|▋         | 72/1000 [00:09<02:18,  6.71it/s]
  7%|▋         | 74/1000 [00:09<01:54,  8.12it/s]
  8%|▊         | 75/1000 [00:10<02:14,  6.86it/s]
  8%|▊         | 76/1000 [00:10<02:18,  6.67it/s]
  8%|▊         | 78/1000 [00:10<02:25,  6.32it/s]
  8%|▊         | 80/1000 [00:10<01:57,  7.86it/s]
  8%|▊         | 82/1000 [00:10<01:39,  9.20it/s]
  8%|▊         | 84/1000 [00:11<01:54,  8.02it/s]
  8%|▊         | 85/1000 [00:11<02:14,  6.78it/s]
  9%|▊         | 86/1000 [00:11<02:33,  5.94it/s]
  9%|▊         | 87/1000 [00:11<02:49,  5.38it/s]
  9%|▉         | 89/1000 [00:12<02:10,  7.00it/s]
  9%|▉         | 90/1000 [00:12<02:05,  7.25it/s]
  9%|▉         | 91/1000 [00:12<02:29,  6.07it/s]
  9%|▉         | 92/1000 [00:12<02:27,  6.16it/s]
  9%|▉         | 93/1000 [00:12<02:36,  5.78it/s]
 10%|▉         | 95/1000 [00:13<02:43,  5.52it/s]
 10%|▉         | 97/1000 [00:13<02:13,  6.78it/s]
 10%|▉         | 99/1000 [00:13<01:47,  8.36it/s]
 10%|█         | 101/1000 [00:13<01:33,  9.61it/s]
 10%|█         | 103/1000 [00:14<01:55,  7.74it/s]
 10%|█         | 104/1000 [00:14<01:54,  7.81it/s]
 11%|█         | 106/1000 [00:14<01:36,  9.31it/s]
 11%|█         | 108/1000 [00:14<01:25, 10.43it/s]
 11%|█         | 110/1000 [00:14<01:19, 11.20it/s]
 11%|█         | 112/1000 [00:14<01:13, 12.03it/s]
 11%|█▏        | 114/1000 [00:14<01:10, 12.51it/s]
 12%|█▏        | 116/1000 [00:15<01:08, 12.81it/s]
 12%|█▏        | 118/1000 [00:15<01:06, 13.23it/s]
 12%|█▏        | 120/1000 [00:15<02:07,  6.91it/s]
 12%|█▏        | 122/1000 [00:15<01:48,  8.08it/s]
 12%|█▏        | 124/1000 [00:16<01:57,  7.43it/s]
 12%|█▎        | 125/1000 [00:16<02:32,  5.72it/s]
 13%|█▎        | 126/1000 [00:16<02:22,  6.14it/s]
 13%|█▎        | 127/1000 [00:16<02:30,  5.80it/s]
 13%|█▎        | 128/1000 [00:17<02:45,  5.28it/s]
 13%|█▎        | 130/1000 [00:17<02:02,  7.10it/s]
 13%|█▎        | 132/1000 [00:17<01:39,  8.70it/s]
 13%|█▎        | 134/1000 [00:17<01:25, 10.15it/s]
 14%|█▎        | 136/1000 [00:17<01:29,  9.65it/s]
 14%|█▍        | 138/1000 [00:18<01:27,  9.88it/s]
 14%|█▍        | 140/1000 [00:18<01:26,  9.96it/s]
 14%|█▍        | 142/1000 [00:18<01:35,  9.03it/s]
 14%|█▍        | 143/1000 [00:18<01:36,  8.89it/s]
 14%|█▍        | 145/1000 [00:18<01:24, 10.06it/s]
 15%|█▍        | 147/1000 [00:19<01:41,  8.42it/s]
 15%|█▍        | 148/1000 [00:19<01:40,  8.48it/s]
 15%|█▌        | 150/1000 [00:19<01:25,  9.90it/s]
 15%|█▌        | 152/1000 [00:19<01:16, 11.03it/s]
 15%|█▌        | 154/1000 [00:19<01:21, 10.38it/s]
 16%|█▌        | 156/1000 [00:20<02:07,  6.64it/s]
 16%|█▌        | 158/1000 [00:20<01:45,  7.96it/s]
 16%|█▌        | 160/1000 [00:20<01:37,  8.61it/s]
 16%|█▌        | 162/1000 [00:20<01:47,  7.80it/s]
 16%|█▋        | 163/1000 [00:21<01:51,  7.49it/s]
 16%|█▋        | 164/1000 [00:21<02:10,  6.40it/s]
 16%|█▋        | 165/1000 [00:21<02:27,  5.67it/s]
 17%|█▋        | 166/1000 [00:21<02:41,  5.18it/s]
 17%|█▋        | 167/1000 [00:21<02:24,  5.77it/s]
 17%|█▋        | 169/1000 [00:22<01:46,  7.82it/s]
 17%|█▋        | 171/1000 [00:22<01:56,  7.14it/s]
 17%|█▋        | 172/1000 [00:22<02:14,  6.15it/s]
 17%|█▋        | 173/1000 [00:22<02:12,  6.22it/s]
 17%|█▋        | 174/1000 [00:22<02:02,  6.73it/s]
 18%|█▊        | 176/1000 [00:23<01:37,  8.43it/s]
 18%|█▊        | 177/1000 [00:23<02:01,  6.79it/s]
 18%|█▊        | 179/1000 [00:23<01:35,  8.57it/s]
 18%|█▊        | 180/1000 [00:23<01:36,  8.50it/s]
 18%|█▊        | 181/1000 [00:23<02:01,  6.75it/s]
 18%|█▊        | 182/1000 [00:24<02:23,  5.72it/s]
 18%|█▊        | 183/1000 [00:24<02:21,  5.78it/s]
 18%|█▊        | 185/1000 [00:24<01:47,  7.60it/s]
 19%|█▊        | 186/1000 [00:24<01:44,  7.76it/s]
 19%|█▊        | 187/1000 [00:24<02:08,  6.31it/s]
 19%|█▉        | 189/1000 [00:24<01:40,  8.06it/s]
 19%|█▉        | 190/1000 [00:25<02:02,  6.59it/s]
 19%|█▉        | 192/1000 [00:25<02:05,  6.45it/s]
 19%|█▉        | 194/1000 [00:25<02:06,  6.37it/s]
 20%|█▉        | 196/1000 [00:25<01:43,  7.74it/s]
 20%|█▉        | 198/1000 [00:26<01:27,  9.18it/s]
 20%|██        | 200/1000 [00:26<01:15, 10.61it/s]
 20%|██        | 202/1000 [00:26<01:31,  8.74it/s]
 20%|██        | 204/1000 [00:26<01:32,  8.61it/s]
 21%|██        | 206/1000 [00:26<01:20,  9.88it/s]
 21%|██        | 208/1000 [00:27<01:33,  8.49it/s]
 21%|██        | 210/1000 [00:27<01:33,  8.47it/s]
 21%|██        | 212/1000 [00:27<01:21,  9.67it/s]
 21%|██▏       | 214/1000 [00:27<01:30,  8.72it/s]
 22%|██▏       | 216/1000 [00:28<01:25,  9.14it/s]
 22%|██▏       | 217/1000 [00:28<01:44,  7.50it/s]
 22%|██▏       | 219/1000 [00:28<01:28,  8.78it/s]
 22%|██▏       | 220/1000 [00:28<02:03,  6.30it/s]
 22%|██▏       | 221/1000 [00:28<02:03,  6.29it/s]
 22%|██▏       | 223/1000 [00:29<02:20,  5.54it/s]
 22%|██▏       | 224/1000 [00:29<02:08,  6.04it/s]
 22%|██▎       | 225/1000 [00:29<02:07,  6.09it/s]
 23%|██▎       | 226/1000 [00:29<02:23,  5.41it/s]
 23%|██▎       | 228/1000 [00:30<01:53,  6.81it/s]
 23%|██▎       | 229/1000 [00:30<02:10,  5.90it/s]
 23%|██▎       | 230/1000 [00:30<02:01,  6.36it/s]
 23%|██▎       | 232/1000 [00:30<01:35,  8.02it/s]
 23%|██▎       | 233/1000 [00:30<01:33,  8.20it/s]
 24%|██▎       | 235/1000 [00:30<01:17,  9.91it/s]
 24%|██▎       | 237/1000 [00:31<01:20,  9.42it/s]
 24%|██▍       | 239/1000 [00:31<01:25,  8.94it/s]
 24%|██▍       | 241/1000 [00:31<01:30,  8.34it/s]
 24%|██▍       | 242/1000 [00:31<02:06,  6.01it/s]
 24%|██▍       | 243/1000 [00:32<02:18,  5.46it/s]
 24%|██▍       | 245/1000 [00:32<01:53,  6.65it/s]
 25%|██▍       | 247/1000 [00:32<01:31,  8.25it/s]
 25%|██▍       | 248/1000 [00:32<01:49,  6.85it/s]
 25%|██▍       | 249/1000 [00:33<02:06,  5.95it/s]
 25%|██▌       | 250/1000 [00:33<02:08,  5.86it/s]
 25%|██▌       | 252/1000 [00:33<02:04,  6.02it/s]
 25%|██▌       | 253/1000 [00:33<02:10,  5.74it/s]
 26%|██▌       | 255/1000 [00:33<01:41,  7.35it/s]
 26%|██▌       | 256/1000 [00:33<01:36,  7.68it/s]
 26%|██▌       | 258/1000 [00:34<01:24,  8.73it/s]
 26%|██▌       | 260/1000 [00:34<01:36,  7.68it/s]
 26%|██▌       | 261/1000 [00:34<01:54,  6.48it/s]
 26%|██▌       | 262/1000 [00:34<01:55,  6.39it/s]
 26%|██▋       | 264/1000 [00:35<01:56,  6.30it/s]
 26%|██▋       | 265/1000 [00:35<01:51,  6.57it/s]
 27%|██▋       | 266/1000 [00:35<01:46,  6.88it/s]
 27%|██▋       | 268/1000 [00:35<01:37,  7.50it/s]
 27%|██▋       | 270/1000 [00:36<01:43,  7.02it/s]
 27%|██▋       | 271/1000 [00:36<02:14,  5.43it/s]
 27%|██▋       | 273/1000 [00:36<02:07,  5.69it/s]
 28%|██▊       | 275/1000 [00:36<01:48,  6.68it/s]
 28%|██▊       | 277/1000 [00:37<01:29,  8.05it/s]
 28%|██▊       | 278/1000 [00:37<01:46,  6.80it/s]
 28%|██▊       | 280/1000 [00:37<01:48,  6.61it/s]
 28%|██▊       | 282/1000 [00:37<01:29,  8.02it/s]
 28%|██▊       | 283/1000 [00:38<02:02,  5.85it/s]
 28%|██▊       | 284/1000 [00:38<02:05,  5.70it/s]
 29%|██▊       | 286/1000 [00:38<01:36,  7.43it/s]
 29%|██▉       | 288/1000 [00:38<01:21,  8.72it/s]
 29%|██▉       | 290/1000 [00:38<01:31,  7.76it/s]
 29%|██▉       | 291/1000 [00:39<01:41,  6.99it/s]
 29%|██▉       | 292/1000 [00:39<01:56,  6.06it/s]
 29%|██▉       | 294/1000 [00:39<01:38,  7.18it/s]
 30%|██▉       | 296/1000 [00:39<01:42,  6.88it/s]
 30%|██▉       | 298/1000 [00:40<01:25,  8.18it/s]
 30%|██▉       | 299/1000 [00:40<01:48,  6.46it/s]
 30%|███       | 300/1000 [00:40<01:42,  6.84it/s]
 30%|███       | 301/1000 [00:40<01:38,  7.10it/s]
 30%|███       | 303/1000 [00:40<01:19,  8.74it/s]
 30%|███       | 304/1000 [00:40<01:26,  8.06it/s]
 30%|███       | 305/1000 [00:40<01:25,  8.13it/s]
 31%|███       | 306/1000 [00:41<01:39,  6.94it/s]
 31%|███       | 307/1000 [00:41<01:42,  6.77it/s]
 31%|███       | 309/1000 [00:41<01:18,  8.78it/s]
 31%|███       | 311/1000 [00:41<01:07, 10.18it/s]
 31%|███▏      | 313/1000 [00:41<01:01, 11.24it/s]
 32%|███▏      | 315/1000 [00:41<01:07, 10.22it/s]
 32%|███▏      | 317/1000 [00:42<01:11,  9.56it/s]
 32%|███▏      | 319/1000 [00:42<01:34,  7.23it/s]
 32%|███▏      | 321/1000 [00:42<01:38,  6.88it/s]
 32%|███▏      | 322/1000 [00:43<01:45,  6.43it/s]
 32%|███▏      | 324/1000 [00:43<01:27,  7.73it/s]
 32%|███▎      | 325/1000 [00:43<01:58,  5.69it/s]
 33%|███▎      | 327/1000 [00:43<01:30,  7.40it/s]
 33%|███▎      | 328/1000 [00:43<01:33,  7.16it/s]
 33%|███▎      | 330/1000 [00:44<01:38,  6.78it/s]
 33%|███▎      | 332/1000 [00:44<01:41,  6.57it/s]
 33%|███▎      | 333/1000 [00:44<01:35,  6.95it/s]
 33%|███▎      | 334/1000 [00:44<01:44,  6.37it/s]
 34%|███▎      | 336/1000 [00:45<01:22,  8.03it/s]
 34%|███▍      | 338/1000 [00:45<01:15,  8.81it/s]
 34%|███▍      | 340/1000 [00:45<01:05, 10.02it/s]
 34%|███▍      | 342/1000 [00:45<01:00, 10.84it/s]
 34%|███▍      | 344/1000 [00:45<01:26,  7.59it/s]
 34%|███▍      | 345/1000 [00:46<01:24,  7.71it/s]
 35%|███▍      | 346/1000 [00:46<01:30,  7.20it/s]
 35%|███▍      | 347/1000 [00:46<01:28,  7.40it/s]
 35%|███▍      | 349/1000 [00:46<01:34,  6.90it/s]
 35%|███▌      | 350/1000 [00:46<01:49,  5.95it/s]
 35%|███▌      | 352/1000 [00:47<01:24,  7.63it/s]
 35%|███▌      | 354/1000 [00:47<01:25,  7.54it/s]
 36%|███▌      | 355/1000 [00:47<01:27,  7.34it/s]
 36%|███▌      | 357/1000 [00:47<01:11,  8.93it/s]
 36%|███▌      | 359/1000 [00:47<01:00, 10.55it/s]
 36%|███▌      | 361/1000 [00:48<01:07,  9.40it/s]
 36%|███▋      | 363/1000 [00:48<01:28,  7.18it/s]
 36%|███▋      | 364/1000 [00:48<01:41,  6.27it/s]
 36%|███▋      | 365/1000 [00:49<02:09,  4.92it/s]
 37%|███▋      | 367/1000 [00:49<01:57,  5.37it/s]
 37%|███▋      | 368/1000 [00:49<02:05,  5.02it/s]
 37%|███▋      | 369/1000 [00:49<01:52,  5.60it/s]
 37%|███▋      | 371/1000 [00:49<01:23,  7.53it/s]
 37%|███▋      | 372/1000 [00:50<01:21,  7.70it/s]
 37%|███▋      | 374/1000 [00:50<01:17,  8.06it/s]
 38%|███▊      | 375/1000 [00:50<01:40,  6.21it/s]
 38%|███▊      | 376/1000 [00:50<01:53,  5.48it/s]
 38%|███▊      | 377/1000 [00:50<01:40,  6.18it/s]
 38%|███▊      | 379/1000 [00:51<01:16,  8.14it/s]
 38%|███▊      | 381/1000 [00:51<01:07,  9.16it/s]
 38%|███▊      | 383/1000 [00:51<01:12,  8.54it/s]
 38%|███▊      | 385/1000 [00:51<01:07,  9.06it/s]
 39%|███▊      | 387/1000 [00:52<01:21,  7.55it/s]
 39%|███▉      | 388/1000 [00:52<01:23,  7.29it/s]
 39%|███▉      | 390/1000 [00:52<01:17,  7.82it/s]
 39%|███▉      | 391/1000 [00:52<01:21,  7.48it/s]
 39%|███▉      | 393/1000 [00:52<01:07,  8.99it/s]
 40%|███▉      | 395/1000 [00:53<01:20,  7.51it/s]
 40%|███▉      | 397/1000 [00:53<01:08,  8.83it/s]
 40%|███▉      | 399/1000 [00:53<01:36,  6.23it/s]
 40%|████      | 400/1000 [00:53<01:45,  5.67it/s]
 40%|████      | 402/1000 [00:54<01:41,  5.91it/s]
 40%|████      | 404/1000 [00:54<01:22,  7.24it/s]
 41%|████      | 406/1000 [00:54<01:09,  8.49it/s]
 41%|████      | 408/1000 [00:55<01:32,  6.38it/s]
 41%|████      | 410/1000 [00:55<01:31,  6.44it/s]
 41%|████      | 411/1000 [00:55<01:41,  5.82it/s]
 41%|████      | 412/1000 [00:55<01:49,  5.35it/s]
 41%|████▏     | 414/1000 [00:55<01:23,  7.05it/s]
 42%|████▏     | 416/1000 [00:56<01:25,  6.81it/s]
 42%|████▏     | 418/1000 [00:56<01:10,  8.24it/s]
 42%|████▏     | 420/1000 [00:56<01:08,  8.43it/s]
 42%|████▏     | 421/1000 [00:56<01:17,  7.49it/s]
 42%|████▏     | 423/1000 [00:57<01:26,  6.68it/s]
 42%|████▏     | 424/1000 [00:57<01:37,  5.92it/s]
 42%|████▎     | 425/1000 [00:57<01:30,  6.35it/s]
 43%|████▎     | 427/1000 [00:57<01:12,  7.94it/s]
 43%|████▎     | 428/1000 [00:57<01:16,  7.52it/s]
 43%|████▎     | 429/1000 [00:58<01:12,  7.82it/s]
 43%|████▎     | 431/1000 [00:58<00:59,  9.53it/s]
 43%|████▎     | 433/1000 [00:58<00:51, 11.01it/s]
 44%|████▎     | 435/1000 [00:58<00:47, 11.77it/s]
 44%|████▎     | 437/1000 [00:58<00:53, 10.49it/s]
 44%|████▍     | 439/1000 [00:59<01:09,  8.08it/s]
 44%|████▍     | 441/1000 [00:59<01:00,  9.30it/s]
 44%|████▍     | 443/1000 [00:59<01:08,  8.08it/s]
 44%|████▍     | 444/1000 [00:59<01:16,  7.24it/s]
 45%|████▍     | 446/1000 [00:59<01:03,  8.71it/s]
 45%|████▍     | 448/1000 [01:00<01:13,  7.48it/s]
 45%|████▌     | 450/1000 [01:00<01:18,  7.01it/s]
 45%|████▌     | 451/1000 [01:00<01:28,  6.17it/s]
 45%|████▌     | 452/1000 [01:01<01:38,  5.58it/s]
 45%|████▌     | 454/1000 [01:01<01:16,  7.18it/s]
 46%|████▌     | 456/1000 [01:01<01:04,  8.50it/s]
 46%|████▌     | 457/1000 [01:01<01:09,  7.79it/s]
 46%|████▌     | 459/1000 [01:01<00:58,  9.23it/s]
 46%|████▌     | 461/1000 [01:01<00:49, 10.79it/s]
 46%|████▋     | 463/1000 [01:02<01:10,  7.62it/s]
 46%|████▋     | 465/1000 [01:02<01:19,  6.74it/s]
 47%|████▋     | 466/1000 [01:02<01:28,  6.00it/s]
 47%|████▋     | 467/1000 [01:03<01:50,  4.82it/s]
 47%|████▋     | 469/1000 [01:03<01:24,  6.31it/s]
 47%|████▋     | 471/1000 [01:03<01:07,  7.84it/s]
 47%|████▋     | 473/1000 [01:03<01:09,  7.56it/s]
 47%|████▋     | 474/1000 [01:03<01:20,  6.51it/s]
 48%|████▊     | 476/1000 [01:04<01:22,  6.38it/s]
 48%|████▊     | 477/1000 [01:04<01:35,  5.49it/s]
 48%|████▊     | 479/1000 [01:04<01:12,  7.15it/s]
 48%|████▊     | 480/1000 [01:04<01:19,  6.58it/s]
 48%|████▊     | 482/1000 [01:05<01:04,  8.04it/s]
 48%|████▊     | 484/1000 [01:05<01:10,  7.30it/s]
 48%|████▊     | 485/1000 [01:05<01:21,  6.31it/s]
 49%|████▊     | 486/1000 [01:05<01:21,  6.30it/s]
 49%|████▉     | 488/1000 [01:05<01:04,  7.98it/s]
 49%|████▉     | 489/1000 [01:06<01:17,  6.62it/s]
 49%|████▉     | 491/1000 [01:06<01:02,  8.21it/s]
 49%|████▉     | 492/1000 [01:06<01:01,  8.26it/s]
 49%|████▉     | 494/1000 [01:06<00:50,  9.96it/s]
 50%|████▉     | 496/1000 [01:06<01:00,  8.39it/s]
 50%|████▉     | 498/1000 [01:07<00:59,  8.41it/s]
 50%|████▉     | 499/1000 [01:07<01:15,  6.66it/s]
 50%|█████     | 500/1000 [01:07<01:24,  5.92it/s]
 50%|█████     | 502/1000 [01:07<01:06,  7.53it/s]
 50%|█████     | 503/1000 [01:07<01:13,  6.78it/s]
 50%|█████     | 505/1000 [01:08<01:15,  6.56it/s]
 51%|█████     | 506/1000 [01:08<01:25,  5.80it/s]
 51%|█████     | 508/1000 [01:08<01:06,  7.42it/s]
 51%|█████     | 510/1000 [01:08<00:54,  8.94it/s]
 51%|█████     | 512/1000 [01:08<00:49,  9.95it/s]
 51%|█████▏    | 514/1000 [01:09<01:06,  7.28it/s]
 52%|█████▏    | 515/1000 [01:09<01:04,  7.52it/s]
 52%|█████▏    | 516/1000 [01:09<01:08,  7.09it/s]
 52%|█████▏    | 518/1000 [01:09<00:59,  8.06it/s]
 52%|█████▏    | 519/1000 [01:10<01:15,  6.37it/s]
 52%|█████▏    | 521/1000 [01:10<00:59,  8.01it/s]
 52%|█████▏    | 522/1000 [01:10<01:11,  6.68it/s]
 52%|█████▏    | 523/1000 [01:10<01:22,  5.80it/s]
 52%|█████▏    | 524/1000 [01:11<01:25,  5.55it/s]
 53%|█████▎    | 526/1000 [01:11<01:12,  6.57it/s]
 53%|█████▎    | 528/1000 [01:11<01:12,  6.53it/s]
 53%|█████▎    | 529/1000 [01:11<01:13,  6.39it/s]
 53%|█████▎    | 531/1000 [01:11<00:57,  8.10it/s]
 53%|█████▎    | 533/1000 [01:11<00:48,  9.66it/s]
 54%|█████▎    | 535/1000 [01:12<01:09,  6.67it/s]
 54%|█████▎    | 536/1000 [01:12<01:13,  6.35it/s]
 54%|█████▎    | 537/1000 [01:12<01:22,  5.64it/s]
 54%|█████▍    | 539/1000 [01:13<01:17,  5.92it/s]
 54%|█████▍    | 540/1000 [01:13<01:20,  5.74it/s]
 54%|█████▍    | 541/1000 [01:13<01:27,  5.25it/s]
 54%|█████▍    | 543/1000 [01:13<01:05,  6.92it/s]
 55%|█████▍    | 545/1000 [01:14<01:04,  7.06it/s]
 55%|█████▍    | 546/1000 [01:14<01:09,  6.49it/s]
 55%|█████▍    | 547/1000 [01:14<01:19,  5.69it/s]
 55%|█████▍    | 549/1000 [01:14<01:16,  5.91it/s]
 55%|█████▌    | 551/1000 [01:14<00:59,  7.50it/s]
 55%|█████▌    | 552/1000 [01:15<01:01,  7.25it/s]
 55%|█████▌    | 553/1000 [01:15<01:12,  6.17it/s]
 55%|█████▌    | 554/1000 [01:15<01:15,  5.94it/s]
 56%|█████▌    | 556/1000 [01:15<00:57,  7.75it/s]
 56%|█████▌    | 557/1000 [01:15<01:03,  7.02it/s]
 56%|█████▌    | 559/1000 [01:16<00:49,  8.83it/s]
 56%|█████▌    | 561/1000 [01:16<00:43, 10.02it/s]
 56%|█████▋    | 563/1000 [01:16<00:52,  8.35it/s]
 56%|█████▋    | 565/1000 [01:16<00:54,  7.97it/s]
 57%|█████▋    | 566/1000 [01:17<01:04,  6.75it/s]
 57%|█████▋    | 568/1000 [01:17<01:06,  6.54it/s]
 57%|█████▋    | 569/1000 [01:17<01:06,  6.43it/s]
 57%|█████▋    | 571/1000 [01:17<01:06,  6.43it/s]
 57%|█████▋    | 572/1000 [01:18<01:07,  6.30it/s]
 57%|█████▋    | 574/1000 [01:18<01:07,  6.34it/s]
 58%|█████▊    | 576/1000 [01:18<00:54,  7.82it/s]
 58%|█████▊    | 577/1000 [01:18<01:13,  5.73it/s]
 58%|█████▊    | 578/1000 [01:19<01:20,  5.25it/s]
 58%|█████▊    | 580/1000 [01:19<01:00,  6.96it/s]
 58%|█████▊    | 582/1000 [01:19<00:48,  8.54it/s]
 58%|█████▊    | 584/1000 [01:19<00:54,  7.58it/s]
 58%|█████▊    | 585/1000 [01:19<01:00,  6.91it/s]
 59%|█████▊    | 587/1000 [01:20<00:57,  7.14it/s]
 59%|█████▉    | 589/1000 [01:20<00:48,  8.52it/s]
 59%|█████▉    | 590/1000 [01:20<01:00,  6.74it/s]
 59%|█████▉    | 592/1000 [01:20<00:49,  8.17it/s]
 59%|█████▉    | 593/1000 [01:20<00:59,  6.80it/s]
 60%|█████▉    | 595/1000 [01:21<00:48,  8.38it/s]
 60%|█████▉    | 596/1000 [01:21<00:58,  6.86it/s]
 60%|█████▉    | 597/1000 [01:21<01:00,  6.65it/s]
 60%|█████▉    | 599/1000 [01:21<01:02,  6.46it/s]
 60%|██████    | 601/1000 [01:22<01:02,  6.38it/s]
 60%|██████    | 602/1000 [01:22<00:59,  6.69it/s]
 60%|██████    | 604/1000 [01:22<01:09,  5.67it/s]
 61%|██████    | 606/1000 [01:22<00:56,  6.99it/s]
 61%|██████    | 608/1000 [01:23<00:50,  7.77it/s]
 61%|██████    | 610/1000 [01:23<00:46,  8.41it/s]
 61%|██████    | 612/1000 [01:23<00:40,  9.67it/s]
 61%|██████▏   | 614/1000 [01:23<00:35, 10.74it/s]
 62%|██████▏   | 616/1000 [01:24<00:50,  7.57it/s]
 62%|██████▏   | 617/1000 [01:24<00:49,  7.72it/s]
 62%|██████▏   | 619/1000 [01:24<00:41,  9.07it/s]
 62%|██████▏   | 621/1000 [01:24<00:47,  8.01it/s]
 62%|██████▏   | 623/1000 [01:24<00:46,  8.19it/s]
 62%|██████▎   | 625/1000 [01:25<00:50,  7.44it/s]
 63%|██████▎   | 627/1000 [01:25<00:43,  8.62it/s]
 63%|██████▎   | 628/1000 [01:25<00:51,  7.18it/s]
 63%|██████▎   | 629/1000 [01:25<00:59,  6.20it/s]
 63%|██████▎   | 631/1000 [01:25<00:47,  7.83it/s]
 63%|██████▎   | 633/1000 [01:26<00:39,  9.40it/s]
 64%|██████▎   | 635/1000 [01:26<00:54,  6.71it/s]
 64%|██████▎   | 636/1000 [01:26<00:51,  7.06it/s]
 64%|██████▍   | 638/1000 [01:26<00:45,  7.93it/s]
 64%|██████▍   | 640/1000 [01:26<00:39,  9.16it/s]
 64%|██████▍   | 642/1000 [01:27<00:45,  7.95it/s]
 64%|██████▍   | 643/1000 [01:27<00:47,  7.58it/s]
 64%|██████▍   | 645/1000 [01:27<00:50,  7.10it/s]
 65%|██████▍   | 647/1000 [01:27<00:46,  7.57it/s]
 65%|██████▍   | 648/1000 [01:28<00:54,  6.51it/s]
 65%|██████▌   | 650/1000 [01:28<00:53,  6.54it/s]
 65%|██████▌   | 652/1000 [01:28<00:55,  6.31it/s]
 65%|██████▌   | 654/1000 [01:29<00:44,  7.70it/s]
 66%|██████▌   | 656/1000 [01:29<00:38,  8.90it/s]
 66%|██████▌   | 658/1000 [01:29<00:42,  8.10it/s]
 66%|██████▌   | 659/1000 [01:29<00:56,  5.99it/s]
 66%|██████▌   | 661/1000 [01:29<00:44,  7.56it/s]
 66%|██████▌   | 662/1000 [01:30<00:52,  6.48it/s]
 66%|██████▋   | 664/1000 [01:30<00:58,  5.77it/s]
 66%|██████▋   | 665/1000 [01:30<01:02,  5.32it/s]
 67%|██████▋   | 667/1000 [01:31<00:59,  5.60it/s]
 67%|██████▋   | 668/1000 [01:31<01:03,  5.19it/s]
 67%|██████▋   | 669/1000 [01:31<00:58,  5.70it/s]
 67%|██████▋   | 671/1000 [01:31<00:55,  5.88it/s]
 67%|██████▋   | 673/1000 [01:32<00:49,  6.63it/s]
 68%|██████▊   | 675/1000 [01:32<00:44,  7.25it/s]
 68%|██████▊   | 677/1000 [01:32<00:37,  8.64it/s]
 68%|██████▊   | 679/1000 [01:32<00:33,  9.69it/s]
 68%|██████▊   | 681/1000 [01:32<00:29, 10.97it/s]
 68%|██████▊   | 683/1000 [01:33<00:35,  8.91it/s]
 68%|██████▊   | 685/1000 [01:33<00:31,  9.86it/s]
 69%|██████▊   | 687/1000 [01:33<00:45,  6.86it/s]
 69%|██████▉   | 688/1000 [01:33<00:43,  7.16it/s]
 69%|██████▉   | 690/1000 [01:34<00:45,  6.80it/s]
 69%|██████▉   | 692/1000 [01:34<00:39,  7.82it/s]
 69%|██████▉   | 694/1000 [01:34<00:42,  7.26it/s]
 70%|██████▉   | 695/1000 [01:34<00:41,  7.42it/s]
 70%|██████▉   | 696/1000 [01:35<00:47,  6.34it/s]
 70%|██████▉   | 698/1000 [01:35<00:43,  6.94it/s]
 70%|██████▉   | 699/1000 [01:35<00:49,  6.04it/s]
 70%|███████   | 701/1000 [01:35<00:39,  7.60it/s]
 70%|███████   | 702/1000 [01:36<00:53,  5.62it/s]
 70%|███████   | 704/1000 [01:36<00:41,  7.22it/s]
 70%|███████   | 705/1000 [01:36<00:54,  5.41it/s]
 71%|███████   | 707/1000 [01:36<00:41,  7.02it/s]
 71%|███████   | 709/1000 [01:36<00:38,  7.63it/s]
 71%|███████   | 710/1000 [01:37<00:44,  6.49it/s]
 71%|███████   | 712/1000 [01:37<00:37,  7.71it/s]
 71%|███████▏  | 713/1000 [01:37<00:36,  7.85it/s]
 72%|███████▏  | 715/1000 [01:37<00:30,  9.35it/s]
 72%|███████▏  | 717/1000 [01:37<00:35,  8.06it/s]
 72%|███████▏  | 718/1000 [01:38<00:41,  6.79it/s]
 72%|███████▏  | 719/1000 [01:38<00:47,  5.93it/s]
 72%|███████▏  | 720/1000 [01:38<00:43,  6.46it/s]
 72%|███████▏  | 722/1000 [01:38<00:34,  8.14it/s]
 72%|███████▏  | 723/1000 [01:38<00:33,  8.23it/s]
 72%|███████▏  | 724/1000 [01:38<00:33,  8.24it/s]
 72%|███████▎  | 725/1000 [01:38<00:33,  8.30it/s]
 73%|███████▎  | 727/1000 [01:39<00:28,  9.71it/s]
 73%|███████▎  | 729/1000 [01:39<00:24, 11.27it/s]
 73%|███████▎  | 731/1000 [01:39<00:32,  8.22it/s]
 73%|███████▎  | 733/1000 [01:39<00:28,  9.42it/s]
 74%|███████▎  | 735/1000 [01:39<00:27,  9.79it/s]
 74%|███████▎  | 737/1000 [01:40<00:27,  9.46it/s]
 74%|███████▍  | 739/1000 [01:40<00:26,  9.73it/s]
 74%|███████▍  | 741/1000 [01:40<00:31,  8.29it/s]
 74%|███████▍  | 743/1000 [01:40<00:30,  8.34it/s]
 74%|███████▍  | 745/1000 [01:41<00:26,  9.59it/s]
 75%|███████▍  | 747/1000 [01:41<00:24, 10.42it/s]
 75%|███████▍  | 749/1000 [01:41<00:29,  8.63it/s]
 75%|███████▌  | 750/1000 [01:41<00:32,  7.63it/s]
 75%|███████▌  | 751/1000 [01:42<00:40,  6.14it/s]
 75%|███████▌  | 753/1000 [01:42<00:34,  7.21it/s]
 75%|███████▌  | 754/1000 [01:42<00:39,  6.20it/s]
 76%|███████▌  | 756/1000 [01:42<00:38,  6.40it/s]
 76%|███████▌  | 758/1000 [01:42<00:31,  7.60it/s]
 76%|███████▌  | 759/1000 [01:43<00:32,  7.31it/s]
 76%|███████▌  | 761/1000 [01:43<00:27,  8.72it/s]
 76%|███████▋  | 763/1000 [01:43<00:30,  7.65it/s]
 76%|███████▋  | 764/1000 [01:43<00:35,  6.61it/s]
 77%|███████▋  | 766/1000 [01:44<00:36,  6.46it/s]
 77%|███████▋  | 768/1000 [01:44<00:29,  7.77it/s]
 77%|███████▋  | 769/1000 [01:44<00:34,  6.62it/s]
 77%|███████▋  | 770/1000 [01:44<00:35,  6.55it/s]
 77%|███████▋  | 772/1000 [01:44<00:28,  8.11it/s]
 77%|███████▋  | 773/1000 [01:45<00:35,  6.38it/s]
 77%|███████▋  | 774/1000 [01:45<00:33,  6.78it/s]
 78%|███████▊  | 776/1000 [01:45<00:28,  7.90it/s]
 78%|███████▊  | 778/1000 [01:45<00:23,  9.59it/s]
 78%|███████▊  | 780/1000 [01:46<00:31,  6.93it/s]
 78%|███████▊  | 782/1000 [01:46<00:26,  8.36it/s]
 78%|███████▊  | 784/1000 [01:46<00:30,  7.16it/s]
 79%|███████▊  | 786/1000 [01:46<00:28,  7.53it/s]
 79%|███████▉  | 788/1000 [01:46<00:25,  8.36it/s]
 79%|███████▉  | 790/1000 [01:47<00:23,  8.99it/s]
 79%|███████▉  | 791/1000 [01:47<00:25,  8.22it/s]
 79%|███████▉  | 792/1000 [01:47<00:26,  7.73it/s]
 79%|███████▉  | 793/1000 [01:47<00:25,  7.97it/s]
 80%|███████▉  | 795/1000 [01:47<00:28,  7.18it/s]
 80%|███████▉  | 797/1000 [01:48<00:29,  6.85it/s]
 80%|███████▉  | 798/1000 [01:48<00:33,  6.02it/s]
 80%|████████  | 800/1000 [01:48<00:29,  6.71it/s]
 80%|████████  | 802/1000 [01:48<00:25,  7.64it/s]
 80%|████████  | 804/1000 [01:49<00:25,  7.83it/s]
 81%|████████  | 806/1000 [01:49<00:21,  9.16it/s]
 81%|████████  | 807/1000 [01:49<00:21,  8.96it/s]
 81%|████████  | 809/1000 [01:49<00:18, 10.20it/s]
 81%|████████  | 811/1000 [01:49<00:16, 11.22it/s]
 81%|████████▏ | 813/1000 [01:49<00:20,  9.04it/s]
 82%|████████▏ | 815/1000 [01:50<00:19,  9.31it/s]
 82%|████████▏ | 817/1000 [01:50<00:22,  8.13it/s]
 82%|████████▏ | 819/1000 [01:50<00:19,  9.20it/s]
 82%|████████▏ | 821/1000 [01:50<00:22,  8.04it/s]
 82%|████████▏ | 823/1000 [01:51<00:22,  7.82it/s]
 82%|████████▏ | 824/1000 [01:51<00:26,  6.75it/s]
 82%|████████▎ | 825/1000 [01:51<00:24,  7.00it/s]
 83%|████████▎ | 826/1000 [01:51<00:30,  5.80it/s]
 83%|████████▎ | 828/1000 [01:52<00:32,  5.23it/s]
 83%|████████▎ | 829/1000 [01:52<00:29,  5.73it/s]
 83%|████████▎ | 831/1000 [01:52<00:24,  7.01it/s]
 83%|████████▎ | 832/1000 [01:52<00:29,  5.75it/s]
 83%|████████▎ | 833/1000 [01:53<00:26,  6.22it/s]
 83%|████████▎ | 834/1000 [01:53<00:27,  6.01it/s]
 84%|████████▎ | 835/1000 [01:53<00:25,  6.53it/s]
 84%|████████▎ | 836/1000 [01:53<00:26,  6.11it/s]
 84%|████████▍ | 838/1000 [01:53<00:21,  7.45it/s]
 84%|████████▍ | 840/1000 [01:54<00:24,  6.61it/s]
 84%|████████▍ | 842/1000 [01:54<00:19,  8.14it/s]
 84%|████████▍ | 844/1000 [01:54<00:24,  6.40it/s]
 84%|████████▍ | 845/1000 [01:54<00:26,  5.76it/s]
 85%|████████▍ | 847/1000 [01:55<00:24,  6.24it/s]
 85%|████████▍ | 849/1000 [01:55<00:20,  7.54it/s]
 85%|████████▌ | 850/1000 [01:55<00:23,  6.48it/s]
 85%|████████▌ | 851/1000 [01:55<00:21,  6.85it/s]
 85%|████████▌ | 853/1000 [01:55<00:17,  8.45it/s]
 86%|████████▌ | 855/1000 [01:55<00:14, 10.03it/s]
 86%|████████▌ | 857/1000 [01:56<00:14, 10.17it/s]
 86%|████████▌ | 859/1000 [01:56<00:16,  8.49it/s]
 86%|████████▌ | 861/1000 [01:56<00:14,  9.75it/s]
 86%|████████▋ | 863/1000 [01:56<00:12, 10.60it/s]
 86%|████████▋ | 865/1000 [01:56<00:11, 11.65it/s]
 87%|████████▋ | 867/1000 [01:57<00:14,  9.30it/s]
 87%|████████▋ | 869/1000 [01:57<00:12, 10.25it/s]
 87%|████████▋ | 871/1000 [01:57<00:11, 11.26it/s]
 87%|████████▋ | 873/1000 [01:57<00:16,  7.77it/s]
 88%|████████▊ | 875/1000 [01:58<00:16,  7.62it/s]
 88%|████████▊ | 877/1000 [01:58<00:13,  8.86it/s]
 88%|████████▊ | 879/1000 [01:58<00:17,  6.86it/s]
 88%|████████▊ | 881/1000 [01:59<00:15,  7.59it/s]
 88%|████████▊ | 882/1000 [01:59<00:18,  6.53it/s]
 88%|████████▊ | 884/1000 [01:59<00:14,  7.94it/s]
 89%|████████▊ | 886/1000 [01:59<00:12,  8.94it/s]
 89%|████████▉ | 888/1000 [01:59<00:11, 10.16it/s]
 89%|████████▉ | 890/1000 [01:59<00:11,  9.66it/s]
 89%|████████▉ | 892/1000 [02:00<00:10, 10.68it/s]
 89%|████████▉ | 894/1000 [02:00<00:14,  7.55it/s]
 90%|████████▉ | 896/1000 [02:00<00:11,  8.79it/s]
 90%|████████▉ | 898/1000 [02:01<00:15,  6.52it/s]
 90%|█████████ | 900/1000 [02:01<00:13,  7.68it/s]
 90%|█████████ | 902/1000 [02:01<00:12,  7.83it/s]
 90%|█████████ | 904/1000 [02:01<00:10,  9.03it/s]
 91%|█████████ | 906/1000 [02:02<00:13,  7.04it/s]
 91%|█████████ | 908/1000 [02:02<00:11,  8.30it/s]
 91%|█████████ | 910/1000 [02:02<00:11,  7.56it/s]
 91%|█████████ | 912/1000 [02:02<00:10,  8.75it/s]
 91%|█████████▏| 914/1000 [02:03<00:11,  7.38it/s]
 92%|█████████▏| 916/1000 [02:03<00:11,  7.08it/s]
 92%|█████████▏| 917/1000 [02:03<00:11,  7.36it/s]
 92%|█████████▏| 918/1000 [02:03<00:14,  5.59it/s]
 92%|█████████▏| 919/1000 [02:04<00:14,  5.71it/s]
 92%|█████████▏| 921/1000 [02:04<00:14,  5.58it/s]
 92%|█████████▏| 922/1000 [02:04<00:13,  5.93it/s]
 92%|█████████▏| 924/1000 [02:04<00:10,  7.16it/s]
 93%|█████████▎| 926/1000 [02:04<00:08,  8.64it/s]
 93%|█████████▎| 927/1000 [02:05<00:09,  8.07it/s]
 93%|█████████▎| 928/1000 [02:05<00:10,  6.64it/s]
 93%|█████████▎| 930/1000 [02:05<00:10,  6.46it/s]
 93%|█████████▎| 931/1000 [02:05<00:10,  6.81it/s]
 93%|█████████▎| 933/1000 [02:06<00:10,  6.60it/s]
 93%|█████████▎| 934/1000 [02:06<00:10,  6.16it/s]
 94%|█████████▎| 936/1000 [02:06<00:08,  7.29it/s]
 94%|█████████▍| 938/1000 [02:06<00:07,  8.81it/s]
 94%|█████████▍| 939/1000 [02:06<00:07,  8.03it/s]
 94%|█████████▍| 940/1000 [02:06<00:07,  8.12it/s]
 94%|█████████▍| 942/1000 [02:07<00:09,  6.32it/s]
 94%|█████████▍| 944/1000 [02:07<00:07,  7.06it/s]
 95%|█████████▍| 946/1000 [02:07<00:06,  8.37it/s]
 95%|█████████▍| 948/1000 [02:07<00:05,  9.69it/s]
 95%|█████████▌| 950/1000 [02:08<00:05,  8.82it/s]
 95%|█████████▌| 952/1000 [02:08<00:06,  7.40it/s]
 95%|█████████▌| 954/1000 [02:08<00:07,  6.16it/s]
 96%|█████████▌| 956/1000 [02:09<00:05,  7.40it/s]
 96%|█████████▌| 957/1000 [02:09<00:06,  6.40it/s]
 96%|█████████▌| 959/1000 [02:09<00:07,  5.76it/s]
 96%|█████████▌| 961/1000 [02:09<00:05,  6.81it/s]
 96%|█████████▌| 962/1000 [02:10<00:06,  6.04it/s]
 96%|█████████▋| 964/1000 [02:10<00:04,  7.49it/s]
 96%|█████████▋| 965/1000 [02:10<00:05,  6.43it/s]
 97%|█████████▋| 966/1000 [02:10<00:05,  6.33it/s]
 97%|█████████▋| 968/1000 [02:10<00:03,  8.01it/s]
 97%|█████████▋| 970/1000 [02:10<00:03,  9.41it/s]
 97%|█████████▋| 972/1000 [02:11<00:03,  8.01it/s]
 97%|█████████▋| 974/1000 [02:11<00:02,  9.19it/s]
 98%|█████████▊| 976/1000 [02:11<00:02,  9.78it/s]
 98%|█████████▊| 978/1000 [02:11<00:02, 10.80it/s]
 98%|█████████▊| 980/1000 [02:12<00:02,  8.41it/s]
 98%|█████████▊| 981/1000 [02:12<00:02,  7.05it/s]
 98%|█████████▊| 982/1000 [02:12<00:03,  5.43it/s]
 98%|█████████▊| 984/1000 [02:12<00:02,  6.92it/s]
 99%|█████████▊| 986/1000 [02:12<00:01,  8.36it/s]
 99%|█████████▉| 988/1000 [02:13<00:01,  6.73it/s]
 99%|█████████▉| 989/1000 [02:13<00:01,  5.99it/s]
 99%|█████████▉| 991/1000 [02:13<00:01,  6.15it/s]
 99%|█████████▉| 992/1000 [02:14<00:01,  4.98it/s]
 99%|█████████▉| 994/1000 [02:14<00:00,  6.54it/s]
100%|█████████▉| 995/1000 [02:14<00:00,  5.52it/s]
100%|█████████▉| 997/1000 [02:14<00:00,  7.05it/s]
100%|█████████▉| 999/1000 [02:15<00:00,  6.76it/s]
100%|██████████| 1000/1000 [02:15<00:00,  6.66it/s]
100%|██████████| 1000/1000 [02:15<00:00,  7.39it/s]
***** eval metrics *****
  epoch                   =        1.0
  eval_loss               =     0.7529
  eval_runtime            = 0:02:15.53
  eval_samples_per_second =      7.378
  eval_steps_per_second   =      7.378
  num_input_tokens_seen   =   12201816
Dropping the following result as it does not have all the necessary fields:
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}