| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 171, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.4910585768520832, |
| "epoch": 0.14700477765527378, |
| "grad_norm": 0.0242919921875, |
| "learning_rate": 0.00019418443636395248, |
| "loss": 1.5326654052734374, |
| "mean_token_accuracy": 0.6706722094118596, |
| "num_tokens": 304280.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 0.750638470617123, |
| "epoch": 0.29400955531054757, |
| "grad_norm": 0.0322265625, |
| "learning_rate": 0.00016831579129369346, |
| "loss": 0.709859619140625, |
| "mean_token_accuracy": 0.8301207780092955, |
| "num_tokens": 606254.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.3453210424515419, |
| "epoch": 0.4410143329658214, |
| "grad_norm": 0.033447265625, |
| "learning_rate": 0.0001272585576455398, |
| "loss": 0.31636102676391603, |
| "mean_token_accuracy": 0.9236685149371624, |
| "num_tokens": 906841.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 0.27239121608203276, |
| "epoch": 0.5880191106210951, |
| "grad_norm": 0.030517578125, |
| "learning_rate": 8.014095333542548e-05, |
| "loss": 0.24910541534423827, |
| "mean_token_accuracy": 0.9407559935003519, |
| "num_tokens": 1210327.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.23772386389784514, |
| "epoch": 0.735023888276369, |
| "grad_norm": 0.019287109375, |
| "learning_rate": 3.7438593050527845e-05, |
| "loss": 0.21553144454956055, |
| "mean_token_accuracy": 0.9497649263590574, |
| "num_tokens": 1511549.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 0.19384966955753044, |
| "epoch": 0.8820286659316428, |
| "grad_norm": 0.0228271484375, |
| "learning_rate": 8.645454235739903e-06, |
| "loss": 0.1665646743774414, |
| "mean_token_accuracy": 0.9595617589354515, |
| "num_tokens": 1815980.0, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 171, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 8.763830690536858e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
