| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.409090909090909, | |
| "eval_steps": 25, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 13.995810508728027, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 5.9656, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "eval_loss": 4.640727519989014, | |
| "eval_runtime": 3.9673, | |
| "eval_samples_per_second": 12.603, | |
| "eval_steps_per_second": 3.277, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 9.464171409606934, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 4.3631, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.1363636363636362, | |
| "grad_norm": 10.678471565246582, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.1543, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 5.6354475021362305, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 2.4264, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.8636363636363638, | |
| "grad_norm": 7.748903274536133, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 3.0526, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 6.438746452331543, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.2736, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.6363636363636362, | |
| "grad_norm": 3.6028335094451904, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 1.8927, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 3.0454545454545454, | |
| "grad_norm": 4.209403991699219, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 2.3577, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 3.409090909090909, | |
| "grad_norm": 3.089271068572998, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8169, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 9, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1114062820042342e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |