| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "global_step": 5860, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.43, |
| "learning_rate": 4.573378839590444e-05, |
| "loss": 0.1236, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 4.1467576791808876e-05, |
| "loss": 0.0826, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9701500564728661, |
| "eval_f1": 0.8742703188145488, |
| "eval_loss": 0.07586850225925446, |
| "eval_precision": 0.9289122137404581, |
| "eval_recall": 0.8256997455470738, |
| "eval_runtime": 3.6496, |
| "eval_samples_per_second": 285.24, |
| "eval_steps_per_second": 35.895, |
| "step": 1172 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 3.720136518771331e-05, |
| "loss": 0.0549, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 3.293515358361775e-05, |
| "loss": 0.0457, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9726241058462862, |
| "eval_f1": 0.8871037776812852, |
| "eval_loss": 0.09076694399118423, |
| "eval_precision": 0.9088078291814946, |
| "eval_recall": 0.8664122137404581, |
| "eval_runtime": 3.5668, |
| "eval_samples_per_second": 291.861, |
| "eval_steps_per_second": 36.728, |
| "step": 2344 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 2.8668941979522183e-05, |
| "loss": 0.0377, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 2.4402730375426623e-05, |
| "loss": 0.0204, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 2.013651877133106e-05, |
| "loss": 0.0198, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9724089711181627, |
| "eval_f1": 0.8868527594289368, |
| "eval_loss": 0.11024652421474457, |
| "eval_precision": 0.891220556745182, |
| "eval_recall": 0.8825275657336726, |
| "eval_runtime": 3.591, |
| "eval_samples_per_second": 289.895, |
| "eval_steps_per_second": 36.481, |
| "step": 3516 |
| }, |
| { |
| "epoch": 3.41, |
| "learning_rate": 1.5870307167235497e-05, |
| "loss": 0.0097, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 1.1604095563139932e-05, |
| "loss": 0.0092, |
| "step": 4500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9726241058462862, |
| "eval_f1": 0.8877923192447972, |
| "eval_loss": 0.13143494725227356, |
| "eval_precision": 0.8983933999131567, |
| "eval_recall": 0.8774385072094996, |
| "eval_runtime": 3.6011, |
| "eval_samples_per_second": 289.076, |
| "eval_steps_per_second": 36.377, |
| "step": 4688 |
| }, |
| { |
| "epoch": 4.27, |
| "learning_rate": 7.337883959044369e-06, |
| "loss": 0.0065, |
| "step": 5000 |
| }, |
| { |
| "epoch": 4.69, |
| "learning_rate": 3.0716723549488057e-06, |
| "loss": 0.0038, |
| "step": 5500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9724089711181627, |
| "eval_f1": 0.8878464818763325, |
| "eval_loss": 0.1649477779865265, |
| "eval_precision": 0.8927958833619211, |
| "eval_recall": 0.8829516539440203, |
| "eval_runtime": 3.5283, |
| "eval_samples_per_second": 295.043, |
| "eval_steps_per_second": 37.128, |
| "step": 5860 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 5860, |
| "total_flos": 1012549907373102.0, |
| "train_loss": 0.03548831426039491, |
| "train_runtime": 710.9927, |
| "train_samples_per_second": 65.901, |
| "train_steps_per_second": 8.242 |
| } |
| ], |
| "max_steps": 5860, |
| "num_train_epochs": 5, |
| "total_flos": 1012549907373102.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
