| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 565, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.8574724197387695, |
| "learning_rate": 0.0002, |
| "loss": 1.6569, |
| "mean_token_accuracy": 0.7738864991517194, |
| "num_tokens": 141431.0, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.7945952415466309, |
| "learning_rate": 0.0002, |
| "loss": 1.294, |
| "mean_token_accuracy": 0.8045228189599197, |
| "num_tokens": 280529.0, |
| "step": 226 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.8255439400672913, |
| "learning_rate": 0.0002, |
| "loss": 1.2564, |
| "mean_token_accuracy": 0.8090212698531362, |
| "num_tokens": 420250.0, |
| "step": 339 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.8216926455497742, |
| "learning_rate": 0.0002, |
| "loss": 1.1816, |
| "mean_token_accuracy": 0.8187902234824358, |
| "num_tokens": 562214.0, |
| "step": 452 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.7376641035079956, |
| "learning_rate": 0.0002, |
| "loss": 1.172, |
| "mean_token_accuracy": 0.8204494675176334, |
| "num_tokens": 705929.0, |
| "step": 565 |
| } |
| ], |
| "logging_steps": 113, |
| "max_steps": 565, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 113, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.612353485483008e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
