|
{ |
|
"best_metric": 0.889795918367347, |
|
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-10\\checkpoint-276", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 276, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.8571428571428571, |
|
"eval_loss": 0.7101830244064331, |
|
"eval_runtime": 1.1461, |
|
"eval_samples_per_second": 213.774, |
|
"eval_steps_per_second": 13.961, |
|
"step": 138 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.889795918367347, |
|
"eval_loss": 0.43645206093788147, |
|
"eval_runtime": 1.148, |
|
"eval_samples_per_second": 213.415, |
|
"eval_steps_per_second": 13.937, |
|
"step": 276 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 690, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 8.797006170440622e-05, |
|
"num_train_epochs": 5, |
|
"per_device_train_batch_size": 16, |
|
"seed": 40 |
|
} |
|
} |
|
|