| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.870264064293915, | |
| "eval_steps": 500, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2870264064293915, | |
| "grad_norm": 42880.98828125, | |
| "learning_rate": 5e-05, | |
| "loss": 3172.427, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.574052812858783, | |
| "grad_norm": 16434.26171875, | |
| "learning_rate": 4.4710114261531955e-05, | |
| "loss": 575.8997, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8610792192881745, | |
| "grad_norm": 45976.1640625, | |
| "learning_rate": 3.94202285230639e-05, | |
| "loss": 192.3109, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.3062288305872897, | |
| "eval_f1": 0.32511442518995726, | |
| "eval_loss": 91.62698364257812, | |
| "eval_precision": 0.35349985153895397, | |
| "eval_recall": 0.3062288305872897, | |
| "eval_runtime": 575.7714, | |
| "eval_samples_per_second": 151.267, | |
| "eval_steps_per_second": 1.513, | |
| "step": 1742 | |
| }, | |
| { | |
| "epoch": 1.148105625717566, | |
| "grad_norm": 41129.7421875, | |
| "learning_rate": 3.4130342784595854e-05, | |
| "loss": 88.8144, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.4351320321469574, | |
| "grad_norm": 47626.203125, | |
| "learning_rate": 2.8840457046127807e-05, | |
| "loss": 55.8473, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.7221584385763489, | |
| "grad_norm": 41772.453125, | |
| "learning_rate": 2.3550571307659756e-05, | |
| "loss": 41.8575, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4196911418565934, | |
| "eval_f1": 0.3957631489816371, | |
| "eval_loss": 29.51061248779297, | |
| "eval_precision": 0.40305455818867747, | |
| "eval_recall": 0.4196911418565934, | |
| "eval_runtime": 577.8048, | |
| "eval_samples_per_second": 150.734, | |
| "eval_steps_per_second": 1.507, | |
| "step": 3484 | |
| }, | |
| { | |
| "epoch": 2.0091848450057403, | |
| "grad_norm": 15703.599609375, | |
| "learning_rate": 1.8260685569191706e-05, | |
| "loss": 34.2812, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.296211251435132, | |
| "grad_norm": 30644.392578125, | |
| "learning_rate": 1.2970799830723657e-05, | |
| "loss": 27.0696, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.5832376578645233, | |
| "grad_norm": 37150.8671875, | |
| "learning_rate": 7.680914092255608e-06, | |
| "loss": 24.7918, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.870264064293915, | |
| "grad_norm": 31945.640625, | |
| "learning_rate": 2.3910283537875584e-06, | |
| "loss": 22.9924, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5226, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 50, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |