|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.860215053763441, |
|
"eval_steps": 500, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.17204301075268819, |
|
"grad_norm": 1.0915554685185225, |
|
"learning_rate": 4.980286753286196e-06, |
|
"loss": 1.0963, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.8602150537634409, |
|
"grad_norm": 0.7585504456177423, |
|
"learning_rate": 4.522542485937369e-06, |
|
"loss": 0.6549, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 1.860215053763441, |
|
"grad_norm": 0.12095147610663935, |
|
"learning_rate": 3.272542485937369e-06, |
|
"loss": 0.4408, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 2.860215053763441, |
|
"grad_norm": 0.06518471954206857, |
|
"learning_rate": 1.7274575140626318e-06, |
|
"loss": 0.3797, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 3.860215053763441, |
|
"grad_norm": 0.04484583649573071, |
|
"learning_rate": 4.774575140626317e-07, |
|
"loss": 0.3665, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 4.860215053763441, |
|
"grad_norm": 0.03680134596304473, |
|
"learning_rate": 0.0, |
|
"loss": 0.3604, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 4.860215053763441, |
|
"step": 25, |
|
"total_flos": 1.5863473089439334e+17, |
|
"train_loss": 0.4581123924255371, |
|
"train_runtime": 560.5063, |
|
"train_samples_per_second": 6.637, |
|
"train_steps_per_second": 0.045 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 25, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"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": 1.5863473089439334e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|