|
{ |
|
"best_metric": 1.100860357284546, |
|
"best_model_checkpoint": "/kaggle/output/checkpoint-4000", |
|
"epoch": 0.16297262059973924, |
|
"eval_steps": 1000, |
|
"global_step": 4000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2.7777777777777777e-11, |
|
"loss": 1.1506, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.7750000000000004e-08, |
|
"loss": 1.1326, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"eval_accuracy": 0.3331337325349301, |
|
"eval_loss": 1.1057127714157104, |
|
"eval_runtime": 61.3538, |
|
"eval_samples_per_second": 81.657, |
|
"eval_steps_per_second": 10.219, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 5.5527777777777784e-08, |
|
"loss": 1.1238, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"eval_accuracy": 0.33812375249501, |
|
"eval_loss": 1.1044437885284424, |
|
"eval_runtime": 61.256, |
|
"eval_samples_per_second": 81.788, |
|
"eval_steps_per_second": 10.236, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 8.327777777777778e-08, |
|
"loss": 1.1251, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"eval_accuracy": 0.3407185628742515, |
|
"eval_loss": 1.1043975353240967, |
|
"eval_runtime": 61.2433, |
|
"eval_samples_per_second": 81.805, |
|
"eval_steps_per_second": 10.238, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.1105555555555557e-07, |
|
"loss": 1.1205, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"eval_accuracy": 0.3387225548902196, |
|
"eval_loss": 1.100860357284546, |
|
"eval_runtime": 61.4457, |
|
"eval_samples_per_second": 81.535, |
|
"eval_steps_per_second": 10.204, |
|
"step": 4000 |
|
} |
|
], |
|
"logging_steps": 1000, |
|
"max_steps": 10000000, |
|
"num_train_epochs": 408, |
|
"save_steps": 1000, |
|
"total_flos": 8361420521472000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|