|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.8, |
|
"eval_steps": 25, |
|
"global_step": 1, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": Infinity, |
|
"learning_rate": 0.0002, |
|
"loss": 10.1236, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"step": 1, |
|
"total_flos": 3295460764752.0, |
|
"train_loss": 10.123604774475098, |
|
"train_runtime": 9.4139, |
|
"train_samples_per_second": 2.125, |
|
"train_steps_per_second": 0.106 |
|
} |
|
], |
|
"logging_steps": 1.0, |
|
"max_steps": 1, |
|
"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": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 3295460764752.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|