|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 6.25, |
|
"eval_steps": 500, |
|
"global_step": 500, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.0070967741935483875, |
|
"eval_loss": NaN, |
|
"eval_runtime": 1.0747, |
|
"eval_samples_per_second": 2884.4, |
|
"eval_steps_per_second": 15.818, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 1.0647, |
|
"eval_samples_per_second": 2911.579, |
|
"eval_steps_per_second": 15.967, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 1.0875, |
|
"eval_samples_per_second": 2850.521, |
|
"eval_steps_per_second": 15.632, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 1.0794, |
|
"eval_samples_per_second": 2872.013, |
|
"eval_steps_per_second": 15.75, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 1.084, |
|
"eval_samples_per_second": 2859.658, |
|
"eval_steps_per_second": 15.682, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 1.0658, |
|
"eval_samples_per_second": 2908.484, |
|
"eval_steps_per_second": 15.95, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 6.25, |
|
"learning_rate": 2.1428571428571427e-06, |
|
"loss": 0.0, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 560, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 7, |
|
"save_steps": 500, |
|
"total_flos": 591309336775836.0, |
|
"train_batch_size": 192, |
|
"trial_name": null, |
|
"trial_params": { |
|
"alpha": 0.4032778497126247, |
|
"num_train_epochs": 7, |
|
"temperature": 5 |
|
} |
|
} |
|
|