|
{ |
|
"best_metric": 1.1000434160232544, |
|
"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": 1.2076, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.7750000000000004e-08, |
|
"loss": 1.1301, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"eval_accuracy": 0.3321357285429142, |
|
"eval_loss": 1.1047232151031494, |
|
"eval_runtime": 50.8344, |
|
"eval_samples_per_second": 98.555, |
|
"eval_steps_per_second": 12.334, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 5.5527777777777784e-08, |
|
"loss": 1.1286, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"eval_accuracy": 0.3377245508982036, |
|
"eval_loss": 1.1038333177566528, |
|
"eval_runtime": 50.8114, |
|
"eval_samples_per_second": 98.6, |
|
"eval_steps_per_second": 12.34, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 8.327777777777778e-08, |
|
"loss": 1.1214, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"eval_accuracy": 0.3409181636726547, |
|
"eval_loss": 1.103529930114746, |
|
"eval_runtime": 50.8258, |
|
"eval_samples_per_second": 98.572, |
|
"eval_steps_per_second": 12.336, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.1105555555555557e-07, |
|
"loss": 1.1249, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"eval_accuracy": 0.3469061876247505, |
|
"eval_loss": 1.1000434160232544, |
|
"eval_runtime": 50.6414, |
|
"eval_samples_per_second": 98.931, |
|
"eval_steps_per_second": 12.381, |
|
"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 |
|
} |
|
|