|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.00010475866223188329, |
|
"eval_steps": 3, |
|
"global_step": 3, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 3.491955407729443e-05, |
|
"grad_norm": 1.5854488611221313, |
|
"learning_rate": 2e-05, |
|
"loss": 2.0741, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 3.491955407729443e-05, |
|
"eval_loss": 2.1542773246765137, |
|
"eval_runtime": 357.8677, |
|
"eval_samples_per_second": 16.847, |
|
"eval_steps_per_second": 16.847, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 6.983910815458886e-05, |
|
"grad_norm": 1.4733368158340454, |
|
"learning_rate": 4e-05, |
|
"loss": 1.5595, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00010475866223188329, |
|
"grad_norm": 2.865410804748535, |
|
"learning_rate": 6e-05, |
|
"loss": 1.7822, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00010475866223188329, |
|
"eval_loss": 2.1372852325439453, |
|
"eval_runtime": 356.9492, |
|
"eval_samples_per_second": 16.89, |
|
"eval_steps_per_second": 16.89, |
|
"step": 3 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 108143145123840.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|