|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.9310344827586206, |
|
"eval_steps": 500, |
|
"global_step": 14, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.3793103448275863, |
|
"grad_norm": 6.256957425043139, |
|
"learning_rate": 5.000000000000002e-07, |
|
"loss": 1.2508, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 1.9310344827586206, |
|
"step": 14, |
|
"total_flos": 923429584896.0, |
|
"train_loss": 1.1873634883335658, |
|
"train_runtime": 3416.1853, |
|
"train_samples_per_second": 0.135, |
|
"train_steps_per_second": 0.004 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 14, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 923429584896.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|