| { | |
| "best_metric": 0.13006852567195892, | |
| "best_model_checkpoint": "/project/home/p_babro/p_babel/v4_slant/checkpoint-34902", | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 34902, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.1385393142700195, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.1773, | |
| "step": 11634 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8172519018352172, | |
| "eval_f1": 0.8177504983784618, | |
| "eval_loss": 0.14184926450252533, | |
| "eval_precision": 0.8189176699515038, | |
| "eval_recall": 0.8172519018352172, | |
| "eval_runtime": 60.5693, | |
| "eval_samples_per_second": 384.138, | |
| "eval_steps_per_second": 24.022, | |
| "step": 11634 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 6.301619052886963, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1345, | |
| "step": 23268 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8301027205913956, | |
| "eval_f1": 0.8302797870565826, | |
| "eval_loss": 0.13333828747272491, | |
| "eval_precision": 0.8306761234771176, | |
| "eval_recall": 0.8301027205913956, | |
| "eval_runtime": 59.9815, | |
| "eval_samples_per_second": 387.903, | |
| "eval_steps_per_second": 24.257, | |
| "step": 23268 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.983363151550293, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.1201, | |
| "step": 34902 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8342287359779946, | |
| "eval_f1": 0.8333415258252606, | |
| "eval_loss": 0.13006852567195892, | |
| "eval_precision": 0.8345277590208003, | |
| "eval_recall": 0.8342287359779946, | |
| "eval_runtime": 56.7072, | |
| "eval_samples_per_second": 410.301, | |
| "eval_steps_per_second": 25.658, | |
| "step": 34902 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 116340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.673234605593549e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |