| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 2964, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.7750787224471436e-05, | |
| "loss": 0.2516, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.550157444894287e-05, | |
| "loss": 0.1893, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9572655742438461, | |
| "eval_f1": 0.5739710789766408, | |
| "eval_loss": 0.11261405795812607, | |
| "eval_precision": 0.5113974231912785, | |
| "eval_recall": 0.6539923954372624, | |
| "eval_runtime": 94.9871, | |
| "eval_samples_per_second": 12.486, | |
| "eval_steps_per_second": 3.127, | |
| "step": 1482 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.3252361673414307e-05, | |
| "loss": 0.1719, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.100314889788574e-05, | |
| "loss": 0.1202, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.753936122357177e-06, | |
| "loss": 0.1117, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9754806419788734, | |
| "eval_f1": 0.725097218067604, | |
| "eval_loss": 0.06848359107971191, | |
| "eval_precision": 0.686685552407932, | |
| "eval_recall": 0.7680608365019012, | |
| "eval_runtime": 101.9581, | |
| "eval_samples_per_second": 11.632, | |
| "eval_steps_per_second": 2.913, | |
| "step": 2964 | |
| } | |
| ], | |
| "max_steps": 4446, | |
| "num_train_epochs": 3, | |
| "total_flos": 1287500616115188.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |