|
{ |
|
"best_metric": 0.7387755102040816, |
|
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-0\\checkpoint-70", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 70, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.5142857142857142, |
|
"eval_loss": 1.8266521692276, |
|
"eval_runtime": 1.249, |
|
"eval_samples_per_second": 196.157, |
|
"eval_steps_per_second": 12.81, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.7387755102040816, |
|
"eval_loss": 1.3899593353271484, |
|
"eval_runtime": 1.192, |
|
"eval_samples_per_second": 205.538, |
|
"eval_steps_per_second": 13.423, |
|
"step": 70 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 175, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 5.723967938193154e-05, |
|
"num_train_epochs": 5, |
|
"per_device_train_batch_size": 64, |
|
"seed": 40 |
|
} |
|
} |
|
|