|
{ |
|
"best_metric": 0.05648113414645195, |
|
"best_model_checkpoint": "doc-topic-model_eval-01_train-04/checkpoint-3000", |
|
"epoch": 1.4785608674223756, |
|
"eval_steps": 1000, |
|
"global_step": 3000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.2464268112370626, |
|
"grad_norm": 0.36145079135894775, |
|
"learning_rate": 1.9950714637752587e-05, |
|
"loss": 0.1655, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.4928536224741252, |
|
"grad_norm": 0.3764462471008301, |
|
"learning_rate": 1.990142927550518e-05, |
|
"loss": 0.0934, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.4928536224741252, |
|
"eval_accuracy": 0.981383845685049, |
|
"eval_f1": 0.0, |
|
"eval_loss": 0.09022163599729538, |
|
"eval_precision": 0.0, |
|
"eval_recall": 0.0, |
|
"eval_runtime": 12.1169, |
|
"eval_samples_per_second": 669.315, |
|
"eval_steps_per_second": 2.641, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.7392804337111878, |
|
"grad_norm": 0.3353608548641205, |
|
"learning_rate": 1.9852143913257764e-05, |
|
"loss": 0.0875, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.9857072449482503, |
|
"grad_norm": 0.3118976652622223, |
|
"learning_rate": 1.980285855101035e-05, |
|
"loss": 0.0778, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.9857072449482503, |
|
"eval_accuracy": 0.981383845685049, |
|
"eval_f1": 0.0, |
|
"eval_loss": 0.07012662291526794, |
|
"eval_precision": 0.0, |
|
"eval_recall": 0.0, |
|
"eval_runtime": 12.1219, |
|
"eval_samples_per_second": 669.036, |
|
"eval_steps_per_second": 2.64, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 1.232134056185313, |
|
"grad_norm": 0.36931222677230835, |
|
"learning_rate": 1.975357318876294e-05, |
|
"loss": 0.0682, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 1.4785608674223756, |
|
"grad_norm": 0.3769352436065674, |
|
"learning_rate": 1.9704287826515527e-05, |
|
"loss": 0.0618, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.4785608674223756, |
|
"eval_accuracy": 0.9828110605609649, |
|
"eval_f1": 0.1748537215947748, |
|
"eval_loss": 0.05648113414645195, |
|
"eval_precision": 0.8221369161868202, |
|
"eval_recall": 0.09783022459078797, |
|
"eval_runtime": 14.4938, |
|
"eval_samples_per_second": 559.549, |
|
"eval_steps_per_second": 2.208, |
|
"step": 3000 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 202900, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 100, |
|
"save_steps": 1000, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 5, |
|
"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": 68043845709666.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|