|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.08056394763343404, |
|
"eval_steps": 2, |
|
"global_step": 5, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.016112789526686808, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.016112789526686808, |
|
"eval_loss": NaN, |
|
"eval_runtime": 77.1013, |
|
"eval_samples_per_second": 1.362, |
|
"eval_steps_per_second": 0.687, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.032225579053373615, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.032225579053373615, |
|
"eval_loss": NaN, |
|
"eval_runtime": 0.8984, |
|
"eval_samples_per_second": 116.881, |
|
"eval_steps_per_second": 58.997, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.04833836858006042, |
|
"grad_norm": NaN, |
|
"learning_rate": 3e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.06445115810674723, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.06445115810674723, |
|
"eval_loss": NaN, |
|
"eval_runtime": 0.902, |
|
"eval_samples_per_second": 116.405, |
|
"eval_steps_per_second": 58.757, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.08056394763343404, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 5, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 2, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 178076327608320.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|