|
{ |
|
"best_metric": 2.2135026454925537, |
|
"best_model_checkpoint": "dq158/pingusPongus/checkpoint-1581", |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 1581, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0008497772211805019, |
|
"loss": 2.4966, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.0009445572420019074, |
|
"loss": 2.3574, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.0009999999999999998, |
|
"loss": 2.3094, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_bleu": 1.0, |
|
"eval_brevity_penalty": 1.0, |
|
"eval_length_ratio": 1.0, |
|
"eval_loss": 2.2135026454925537, |
|
"eval_precisions": [ |
|
1.0, |
|
1.0, |
|
1.0, |
|
1.0 |
|
], |
|
"eval_reference_length": 53394, |
|
"eval_runtime": 2937.3471, |
|
"eval_samples_per_second": 0.957, |
|
"eval_steps_per_second": 0.12, |
|
"eval_translation_length": 53394, |
|
"step": 1581 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 15810, |
|
"num_train_epochs": 10, |
|
"save_steps": 500, |
|
"total_flos": 771945142419456.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|