|
{ |
|
"best_metric": 1.1012382507324219, |
|
"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": 1.1078, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.7750000000000004e-08, |
|
"loss": 1.128, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"eval_accuracy": 0.330938123752495, |
|
"eval_loss": 1.1083118915557861, |
|
"eval_runtime": 12.3979, |
|
"eval_samples_per_second": 404.1, |
|
"eval_steps_per_second": 50.573, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 5.5527777777777784e-08, |
|
"loss": 1.1164, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"eval_accuracy": 0.3323353293413174, |
|
"eval_loss": 1.102672815322876, |
|
"eval_runtime": 12.2861, |
|
"eval_samples_per_second": 407.778, |
|
"eval_steps_per_second": 51.033, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 8.327777777777778e-08, |
|
"loss": 1.1158, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"eval_accuracy": 0.34211576846307384, |
|
"eval_loss": 1.1024774312973022, |
|
"eval_runtime": 12.3746, |
|
"eval_samples_per_second": 404.863, |
|
"eval_steps_per_second": 50.668, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.1105555555555557e-07, |
|
"loss": 1.1115, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"eval_accuracy": 0.34890219560878244, |
|
"eval_loss": 1.1012382507324219, |
|
"eval_runtime": 12.5405, |
|
"eval_samples_per_second": 399.505, |
|
"eval_steps_per_second": 49.998, |
|
"step": 4000 |
|
} |
|
], |
|
"logging_steps": 1000, |
|
"max_steps": 10000000, |
|
"num_train_epochs": 408, |
|
"save_steps": 1000, |
|
"total_flos": 1393758830592000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|