| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00029550063347948304, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.9100126695896606e-05, | |
| "grad_norm": 8.745173454284668, | |
| "learning_rate": 1e-05, | |
| "loss": 47.5169, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.9100126695896606e-05, | |
| "eval_loss": 2.81036639213562, | |
| "eval_runtime": 1539.8535, | |
| "eval_samples_per_second": 18.507, | |
| "eval_steps_per_second": 9.253, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011820025339179321, | |
| "grad_norm": 11.03530216217041, | |
| "learning_rate": 2e-05, | |
| "loss": 44.2999, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00011820025339179321, | |
| "eval_loss": 2.7735745906829834, | |
| "eval_runtime": 1486.8712, | |
| "eval_samples_per_second": 19.166, | |
| "eval_steps_per_second": 9.583, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001773003800876898, | |
| "grad_norm": 9.165048599243164, | |
| "learning_rate": 3e-05, | |
| "loss": 44.8764, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00023640050678358642, | |
| "grad_norm": 8.95555305480957, | |
| "learning_rate": 4e-05, | |
| "loss": 44.2531, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00023640050678358642, | |
| "eval_loss": 2.7517380714416504, | |
| "eval_runtime": 1562.0017, | |
| "eval_samples_per_second": 18.245, | |
| "eval_steps_per_second": 9.122, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00029550063347948304, | |
| "grad_norm": 9.540165901184082, | |
| "learning_rate": 5e-05, | |
| "loss": 42.6226, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6332448610713600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |