|
{ |
|
"best_metric": 0.6399082568807339, |
|
"best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-7/checkpoint-842", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 842, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.5470183486238532, |
|
"eval_loss": 0.626240611076355, |
|
"eval_runtime": 2.3487, |
|
"eval_samples_per_second": 371.275, |
|
"eval_steps_per_second": 23.418, |
|
"step": 421 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.6399082568807339, |
|
"eval_loss": 0.5675538182258606, |
|
"eval_runtime": 2.3621, |
|
"eval_samples_per_second": 369.157, |
|
"eval_steps_per_second": 23.284, |
|
"step": 842 |
|
} |
|
], |
|
"logging_steps": 4209, |
|
"max_steps": 842, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 2.4428340050458666e-06, |
|
"num_train_epochs": 2, |
|
"per_device_train_batch_size": 16, |
|
"seed": 36, |
|
"weight_decay": 0.14229812099502392 |
|
} |
|
} |
|
|