| { |
| "best_global_step": 171, |
| "best_metric": 0.916008305482059, |
| "best_model_checkpoint": "./results_model/checkpoint-171", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 228, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.8830022075055187, |
| "grad_norm": 6.72242546081543, |
| "learning_rate": 8.24561403508772e-06, |
| "loss": 1.8585, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7248618784530386, |
| "eval_f1": 0.719310914066912, |
| "eval_loss": 1.1899107694625854, |
| "eval_runtime": 3.4844, |
| "eval_samples_per_second": 259.729, |
| "eval_steps_per_second": 32.717, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.759381898454746, |
| "grad_norm": 12.256659507751465, |
| "learning_rate": 1.7017543859649125e-05, |
| "loss": 0.8167, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9005524861878453, |
| "eval_f1": 0.9000409168011964, |
| "eval_loss": 0.26897701621055603, |
| "eval_runtime": 4.3818, |
| "eval_samples_per_second": 206.538, |
| "eval_steps_per_second": 26.017, |
| "step": 114 |
| }, |
| { |
| "epoch": 2.6357615894039736, |
| "grad_norm": 5.979743480682373, |
| "learning_rate": 1.935672514619883e-05, |
| "loss": 0.2562, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9160220994475138, |
| "eval_f1": 0.916008305482059, |
| "eval_loss": 0.2404857724905014, |
| "eval_runtime": 3.5634, |
| "eval_samples_per_second": 253.968, |
| "eval_steps_per_second": 31.992, |
| "step": 171 |
| }, |
| { |
| "epoch": 3.512141280353201, |
| "grad_norm": 10.351480484008789, |
| "learning_rate": 1.8382066276803122e-05, |
| "loss": 0.1603, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9138121546961326, |
| "eval_f1": 0.9136192640631743, |
| "eval_loss": 0.2848789393901825, |
| "eval_runtime": 3.8136, |
| "eval_samples_per_second": 237.309, |
| "eval_steps_per_second": 29.893, |
| "step": 228 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1140, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.01 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 1 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 970662956884380.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
