|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 1000, |
|
"global_step": 125, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": 7.137415885925293, |
|
"learning_rate": 9.549150281252633e-07, |
|
"loss": 0.8592, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 125, |
|
"total_flos": 0.0, |
|
"train_loss": 0.8179722900390625, |
|
"train_runtime": 110.6784, |
|
"train_samples_per_second": 9.035, |
|
"train_steps_per_second": 1.129 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 125, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": false, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 0.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|