|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 11.0, |
|
"eval_steps": 5, |
|
"global_step": 15, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 3.3333333333333335, |
|
"grad_norm": 53.851408552101205, |
|
"learning_rate": 8.742553740855507e-06, |
|
"loss": 2.183, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 3.3333333333333335, |
|
"eval_loss": 2.0213818550109863, |
|
"eval_runtime": 1.8825, |
|
"eval_samples_per_second": 21.248, |
|
"eval_steps_per_second": 1.062, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"grad_norm": 25.416084824405427, |
|
"learning_rate": 3.226975564787322e-06, |
|
"loss": 1.2705, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 1.5252158641815186, |
|
"eval_runtime": 1.4074, |
|
"eval_samples_per_second": 28.421, |
|
"eval_steps_per_second": 1.421, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"grad_norm": 15.615170883744815, |
|
"learning_rate": 0.0, |
|
"loss": 1.1255, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"eval_loss": 1.4653947353363037, |
|
"eval_runtime": 1.4084, |
|
"eval_samples_per_second": 28.401, |
|
"eval_steps_per_second": 1.42, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"step": 15, |
|
"total_flos": 1945315508224.0, |
|
"train_loss": 1.5263661384582519, |
|
"train_runtime": 474.6281, |
|
"train_samples_per_second": 11.377, |
|
"train_steps_per_second": 0.032 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 15, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 15, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1945315508224.0, |
|
"train_batch_size": 5, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|