|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0, |
|
"eval_steps": 500, |
|
"global_step": 0, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0, |
|
"step": 0, |
|
"total_flos": 2632449197568.0, |
|
"train_loss": 8966.395378112793, |
|
"train_runtime": 8.6949, |
|
"train_samples_per_second": 4.6, |
|
"train_steps_per_second": 0.46 |
|
} |
|
], |
|
"logging_steps": 2, |
|
"max_steps": 4, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"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": 2632449197568.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|