|
{ |
|
"best_metric": 1.1072543859481812, |
|
"best_model_checkpoint": "/kaggle/output/checkpoint-4000", |
|
"epoch": 64.0, |
|
"eval_steps": 1000, |
|
"global_step": 4000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.7777777777777777e-11, |
|
"loss": 1.5477, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"learning_rate": 2.7750000000000004e-08, |
|
"loss": 1.2028, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"eval_accuracy": 0.3387225548902196, |
|
"eval_loss": 1.1078879833221436, |
|
"eval_runtime": 54.1057, |
|
"eval_samples_per_second": 92.596, |
|
"eval_steps_per_second": 11.588, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 32.0, |
|
"learning_rate": 5.5527777777777784e-08, |
|
"loss": 1.1152, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 32.0, |
|
"eval_accuracy": 0.3349301397205589, |
|
"eval_loss": 1.1080944538116455, |
|
"eval_runtime": 54.2029, |
|
"eval_samples_per_second": 92.43, |
|
"eval_steps_per_second": 11.568, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 48.0, |
|
"learning_rate": 8.327777777777778e-08, |
|
"loss": 1.1036, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 48.0, |
|
"eval_accuracy": 0.3377245508982036, |
|
"eval_loss": 1.1081210374832153, |
|
"eval_runtime": 54.0467, |
|
"eval_samples_per_second": 92.698, |
|
"eval_steps_per_second": 11.601, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 64.0, |
|
"learning_rate": 1.1105555555555557e-07, |
|
"loss": 1.0895, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 64.0, |
|
"eval_accuracy": 0.33912175648702597, |
|
"eval_loss": 1.1072543859481812, |
|
"eval_runtime": 54.1318, |
|
"eval_samples_per_second": 92.552, |
|
"eval_steps_per_second": 11.583, |
|
"step": 4000 |
|
} |
|
], |
|
"logging_steps": 1000, |
|
"max_steps": 10000000, |
|
"num_train_epochs": 161291, |
|
"save_steps": 1000, |
|
"total_flos": 8361420521472000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|