|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.56, |
|
"eval_steps": 1, |
|
"global_step": 2, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.64, |
|
"grad_norm": 0.02430405095219612, |
|
"learning_rate": 1e-05, |
|
"loss": 11.9224, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"eval_loss": 11.915824890136719, |
|
"eval_runtime": 29.5719, |
|
"eval_samples_per_second": 0.101, |
|
"eval_steps_per_second": 0.068, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"grad_norm": 0.04462896287441254, |
|
"learning_rate": 2e-05, |
|
"loss": 22.4912, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"eval_loss": 11.915820121765137, |
|
"eval_runtime": 0.0312, |
|
"eval_samples_per_second": 96.043, |
|
"eval_steps_per_second": 64.029, |
|
"step": 2 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 2, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 1, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1565638656.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|