|
{ |
|
"best_metric": 0.07017117738723755, |
|
"best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-2000", |
|
"epoch": 0.9861932938856016, |
|
"eval_steps": 1000, |
|
"global_step": 2000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.2465483234714004, |
|
"grad_norm": 0.3881610631942749, |
|
"learning_rate": 1.9950690335305722e-05, |
|
"loss": 0.1669, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.4930966469428008, |
|
"grad_norm": 0.3564796447753906, |
|
"learning_rate": 1.9901380670611442e-05, |
|
"loss": 0.0935, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.4930966469428008, |
|
"eval_accuracy": 0.981383845685049, |
|
"eval_f1": 0.0, |
|
"eval_loss": 0.08976549655199051, |
|
"eval_precision": 0.0, |
|
"eval_recall": 0.0, |
|
"eval_runtime": 12.0327, |
|
"eval_samples_per_second": 673.996, |
|
"eval_steps_per_second": 2.659, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.7396449704142012, |
|
"grad_norm": 0.4097365140914917, |
|
"learning_rate": 1.9852071005917162e-05, |
|
"loss": 0.0869, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.9861932938856016, |
|
"grad_norm": 0.3858756422996521, |
|
"learning_rate": 1.980276134122288e-05, |
|
"loss": 0.0764, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.9861932938856016, |
|
"eval_accuracy": 0.981383845685049, |
|
"eval_f1": 0.0, |
|
"eval_loss": 0.07017117738723755, |
|
"eval_precision": 0.0, |
|
"eval_recall": 0.0, |
|
"eval_runtime": 12.2763, |
|
"eval_samples_per_second": 660.624, |
|
"eval_steps_per_second": 2.607, |
|
"step": 2000 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 202800, |
|
"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": 45024835218264.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|