|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.003356760725899507, |
|
"eval_steps": 5, |
|
"global_step": 5, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0006713521451799014, |
|
"grad_norm": 0.3204704225063324, |
|
"learning_rate": 1e-05, |
|
"loss": 0.2534, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0006713521451799014, |
|
"eval_loss": 0.34151291847229004, |
|
"eval_runtime": 410.3846, |
|
"eval_samples_per_second": 24.453, |
|
"eval_steps_per_second": 6.114, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0013427042903598027, |
|
"grad_norm": 0.36491429805755615, |
|
"learning_rate": 2e-05, |
|
"loss": 0.2745, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0020140564355397043, |
|
"grad_norm": 0.3138849139213562, |
|
"learning_rate": 3e-05, |
|
"loss": 0.2594, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0026854085807196055, |
|
"grad_norm": 0.3455110788345337, |
|
"learning_rate": 4e-05, |
|
"loss": 0.2766, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.003356760725899507, |
|
"grad_norm": 0.3628172278404236, |
|
"learning_rate": 5e-05, |
|
"loss": 0.2775, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.003356760725899507, |
|
"eval_loss": 0.31641557812690735, |
|
"eval_runtime": 408.4107, |
|
"eval_samples_per_second": 24.571, |
|
"eval_steps_per_second": 6.143, |
|
"step": 5 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 20, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 5, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.090030138916864e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|