Diplomovka/aya_300k_lr_experiments/benchmarks/skbench/configs/model_config.json
Jakub 67061cf373 Add Aya 300k learning-rate study and benchmark results
Document six completed LR runs as preparation for full Aya training on Perun. Record selection of LR 0.00010 by lowest final validation loss, selected-model lm-eval and partial SK-bench results, reproducible provenance, and dataset-access/context-truncation limitations. Preserve existing 30k and Titan material.
2026-10-25 00:33:24 +02:00

60 lines
1.7 KiB
JSON

{
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"max_samples": null,
"job_id": "0",
"start_time": 796668.90423246,
"end_time": 807588.555648873,
"total_evaluation_time_secondes": "10919.65141641302",
"model_config": {
"model_name": "/home/schwarc/diplomovka/skbench_evaluation/models/aya_300k_lr_0p00010",
"generation_parameters": {
"num_blocks": null,
"block_size": null,
"early_stopping": null,
"repetition_penalty": null,
"frequency_penalty": null,
"length_penalty": null,
"presence_penalty": null,
"max_new_tokens": null,
"min_new_tokens": null,
"seed": null,
"stop_tokens": null,
"temperature": 0,
"top_k": null,
"min_p": null,
"top_p": null,
"truncate_prompt": null,
"cache_implementation": null,
"response_format": null,
"skip_special_tokens": true
},
"system_prompt": null,
"cache_dir": "~/.cache/huggingface/lighteval",
"tokenizer": null,
"revision": "main",
"dtype": "bfloat16",
"tensor_parallel_size": 1,
"data_parallel_size": 1,
"pipeline_parallel_size": 1,
"gpu_memory_utilization": 0.85,
"enable_prefix_caching": null,
"max_model_length": 32768,
"quantization": null,
"load_format": null,
"swap_space": 4,
"seed": 1234,
"trust_remote_code": false,
"add_special_tokens": true,
"multichoice_continuations_start_space": true,
"pairwise_tokenization": false,
"max_num_seqs": 128,
"max_num_batched_tokens": 2048,
"subfolder": null,
"is_async": false,
"override_chat_template": null,
"enforce_eager": true
},
"model_name": "/home/schwarc/diplomovka/skbench_evaluation/models/aya_300k_lr_0p00010"
}