|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.00032123353678124, |
|
"eval_steps": 3, |
|
"global_step": 3, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00010707784559374665, |
|
"grad_norm": 0.5286692380905151, |
|
"learning_rate": 2e-05, |
|
"loss": 1.0893, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00010707784559374665, |
|
"eval_loss": 1.2124216556549072, |
|
"eval_runtime": 186.8738, |
|
"eval_samples_per_second": 10.526, |
|
"eval_steps_per_second": 10.526, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0002141556911874933, |
|
"grad_norm": 0.6973130106925964, |
|
"learning_rate": 4e-05, |
|
"loss": 1.1445, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00032123353678124, |
|
"grad_norm": 0.8045721054077148, |
|
"learning_rate": 6e-05, |
|
"loss": 1.2625, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00032123353678124, |
|
"eval_loss": 1.1848317384719849, |
|
"eval_runtime": 183.2207, |
|
"eval_samples_per_second": 10.736, |
|
"eval_steps_per_second": 10.736, |
|
"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": 936521553149952.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|