| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0030321289043518823, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.77468949833816e-05, | |
| "eval_loss": 11.250130653381348, | |
| "eval_runtime": 373.7477, | |
| "eval_samples_per_second": 14.491, | |
| "eval_steps_per_second": 7.246, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000388734474916908, | |
| "grad_norm": 8.994977951049805, | |
| "learning_rate": 5e-05, | |
| "loss": 11.772, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000777468949833816, | |
| "grad_norm": 14.662769317626953, | |
| "learning_rate": 0.0001, | |
| "loss": 9.4834, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000777468949833816, | |
| "eval_loss": 6.440606594085693, | |
| "eval_runtime": 375.437, | |
| "eval_samples_per_second": 14.426, | |
| "eval_steps_per_second": 7.213, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001166203424750724, | |
| "grad_norm": 12.160930633544922, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0745, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001554937899667632, | |
| "grad_norm": 2.438434600830078, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2511, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001554937899667632, | |
| "eval_loss": 0.8021523952484131, | |
| "eval_runtime": 374.7912, | |
| "eval_samples_per_second": 14.451, | |
| "eval_steps_per_second": 7.225, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00194367237458454, | |
| "grad_norm": 6.623475551605225, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8868, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002332406849501448, | |
| "grad_norm": 11.61430835723877, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7983, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002332406849501448, | |
| "eval_loss": 0.6091293096542358, | |
| "eval_runtime": 374.8842, | |
| "eval_samples_per_second": 14.447, | |
| "eval_steps_per_second": 7.224, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002721141324418356, | |
| "grad_norm": 9.522652626037598, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6328, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7305778780176384.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |