| { | |
| "best_metric": 0.387269526720047, | |
| "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": 12.391196250915527, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1618, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006472491909385113, | |
| "eval_loss": 1.1013591289520264, | |
| "eval_runtime": 105.1712, | |
| "eval_samples_per_second": 24.75, | |
| "eval_steps_per_second": 3.1, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012944983818770227, | |
| "grad_norm": 10.685352325439453, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1263, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001941747572815534, | |
| "grad_norm": 7.642386436462402, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5872, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025889967637540453, | |
| "grad_norm": 12.233989715576172, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5568, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003236245954692557, | |
| "grad_norm": 6.16679048538208, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6063, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003883495145631068, | |
| "grad_norm": 5.216569423675537, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.3087, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004530744336569579, | |
| "grad_norm": 13.939298629760742, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.416, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005177993527508091, | |
| "grad_norm": 7.698254108428955, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.4695, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005825242718446602, | |
| "grad_norm": 4.788593292236328, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.2645, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006472491909385114, | |
| "grad_norm": 7.387963771820068, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.3205, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007119741100323625, | |
| "grad_norm": 5.369454860687256, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.3034, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007766990291262136, | |
| "grad_norm": 5.2790961265563965, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.1894, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008414239482200648, | |
| "grad_norm": 6.785725116729736, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.371, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009061488673139158, | |
| "grad_norm": 5.897602081298828, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.3022, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009708737864077669, | |
| "grad_norm": 6.494931697845459, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.3642, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010355987055016181, | |
| "grad_norm": 4.765385627746582, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.2676, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011003236245954692, | |
| "grad_norm": 5.174181938171387, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.4054, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011650485436893204, | |
| "grad_norm": 4.145316123962402, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.1391, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012297734627831715, | |
| "grad_norm": 5.084649085998535, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.2942, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012944983818770227, | |
| "grad_norm": 4.862823009490967, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1627, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013592233009708738, | |
| "grad_norm": 4.962240695953369, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.1816, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01423948220064725, | |
| "grad_norm": 4.77435827255249, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.2001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01488673139158576, | |
| "grad_norm": 5.3655242919921875, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.3343, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015533980582524271, | |
| "grad_norm": 5.315501689910889, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.3153, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016181229773462782, | |
| "grad_norm": 5.242373943328857, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.2928, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016181229773462782, | |
| "eval_loss": 0.387269526720047, | |
| "eval_runtime": 107.3282, | |
| "eval_samples_per_second": 24.253, | |
| "eval_steps_per_second": 3.037, | |
| "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 | |
| } | |