| { | |
| "best_metric": 0.38691768050193787, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.016181229773462782, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006472491909385113, | |
| "grad_norm": 12.386811256408691, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1618, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006472491909385113, | |
| "eval_loss": 1.1013591289520264, | |
| "eval_runtime": 105.9515, | |
| "eval_samples_per_second": 24.568, | |
| "eval_steps_per_second": 3.077, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012944983818770227, | |
| "grad_norm": 10.682132720947266, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1263, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001941747572815534, | |
| "grad_norm": 7.8965067863464355, | |
| "learning_rate": 6e-05, | |
| "loss": 1.588, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025889967637540453, | |
| "grad_norm": 12.606889724731445, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5629, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003236245954692557, | |
| "grad_norm": 6.1731276512146, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6082, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003883495145631068, | |
| "grad_norm": 5.269734859466553, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.3069, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004530744336569579, | |
| "grad_norm": 15.008581161499023, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.4322, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005177993527508091, | |
| "grad_norm": 7.973099708557129, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.4821, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005825242718446602, | |
| "grad_norm": 4.92938756942749, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.2722, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006472491909385114, | |
| "grad_norm": 7.114321708679199, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.3121, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007119741100323625, | |
| "grad_norm": 5.484792709350586, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.3083, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007766990291262136, | |
| "grad_norm": 5.332705974578857, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.19, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008414239482200648, | |
| "grad_norm": 6.66576623916626, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.3733, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009061488673139158, | |
| "grad_norm": 5.858701229095459, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.3019, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009708737864077669, | |
| "grad_norm": 6.463413715362549, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.356, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010355987055016181, | |
| "grad_norm": 4.812952995300293, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.2641, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011003236245954692, | |
| "grad_norm": 5.166619300842285, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.4067, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011650485436893204, | |
| "grad_norm": 4.101341724395752, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.1359, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012297734627831715, | |
| "grad_norm": 5.182929039001465, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.2996, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012944983818770227, | |
| "grad_norm": 4.8671464920043945, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1693, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013592233009708738, | |
| "grad_norm": 4.907355308532715, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.1906, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01423948220064725, | |
| "grad_norm": 4.77469539642334, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.203, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01488673139158576, | |
| "grad_norm": 5.339026927947998, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.3357, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015533980582524271, | |
| "grad_norm": 5.2934370040893555, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.3286, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016181229773462782, | |
| "grad_norm": 5.244269847869873, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.2954, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016181229773462782, | |
| "eval_loss": 0.38691768050193787, | |
| "eval_runtime": 107.8238, | |
| "eval_samples_per_second": 24.141, | |
| "eval_steps_per_second": 3.023, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.128611934155571e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |