|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.8626609442060085, |
|
"eval_steps": 300, |
|
"global_step": 900, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.2875536480686696, |
|
"grad_norm": 0.001025281846523285, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 0.0089, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.2875536480686696, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0007540204096585512, |
|
"eval_runtime": 2.866, |
|
"eval_samples_per_second": 289.256, |
|
"eval_steps_per_second": 9.072, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.575107296137339, |
|
"grad_norm": 0.0004946357221342623, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 0.0001, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 2.575107296137339, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.00020219432190060616, |
|
"eval_runtime": 2.8542, |
|
"eval_samples_per_second": 290.45, |
|
"eval_steps_per_second": 9.109, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 3.8626609442060085, |
|
"grad_norm": 0.00040382734732702374, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 3.8626609442060085, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0003535090072546154, |
|
"eval_runtime": 2.8648, |
|
"eval_samples_per_second": 289.378, |
|
"eval_steps_per_second": 9.076, |
|
"step": 900 |
|
} |
|
], |
|
"logging_steps": 300, |
|
"max_steps": 900, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 300, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 0.0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|