| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.945010183299389, |
| "eval_steps": 500, |
| "global_step": 29, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1629327902240326, |
| "grad_norm": 3.2831389904022217, |
| "learning_rate": 4.917142857142858e-06, |
| "loss": 1.1958, |
| "mean_token_accuracy": 0.7120350122451782, |
| "num_tokens": 1976903.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.3258655804480652, |
| "grad_norm": 0.6579073667526245, |
| "learning_rate": 1.106357142857143e-05, |
| "loss": 0.9781, |
| "mean_token_accuracy": 0.7306134402751923, |
| "num_tokens": 3997965.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.48879837067209775, |
| "grad_norm": 0.43862125277519226, |
| "learning_rate": 1.7210000000000003e-05, |
| "loss": 0.8603, |
| "mean_token_accuracy": 0.7505308024585247, |
| "num_tokens": 6048529.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6517311608961304, |
| "grad_norm": 0.28088220953941345, |
| "learning_rate": 2.3356428571428574e-05, |
| "loss": 0.8169, |
| "mean_token_accuracy": 0.7589591950178146, |
| "num_tokens": 8047186.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.814663951120163, |
| "grad_norm": 0.26158055663108826, |
| "learning_rate": 2.950285714285715e-05, |
| "loss": 0.7313, |
| "mean_token_accuracy": 0.7809609144926071, |
| "num_tokens": 9981253.0, |
| "step": 25 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 62, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.472975169857004e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
