| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 77, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.1682333001494407, |
| "epoch": 0.32786885245901637, |
| "grad_norm": 0.046142578125, |
| "learning_rate": 0.00016282199972956425, |
| "loss": 1.1654401397705079, |
| "mean_token_accuracy": 0.7184657980501652, |
| "num_tokens": 150039.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 0.807309385985136, |
| "epoch": 0.6557377049180327, |
| "grad_norm": 0.134765625, |
| "learning_rate": 6.271435222196916e-05, |
| "loss": 0.7393476867675781, |
| "mean_token_accuracy": 0.7940354010462761, |
| "num_tokens": 292991.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.5239431077986956, |
| "epoch": 0.9836065573770492, |
| "grad_norm": 0.09033203125, |
| "learning_rate": 8.099564741123166e-07, |
| "loss": 0.46052257537841795, |
| "mean_token_accuracy": 0.8671573248505592, |
| "num_tokens": 440288.0, |
| "step": 75 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 77, |
| "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": 3.771194546385101e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
