|
{ |
|
"best_metric": 0.8876146788990825, |
|
"best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-8/checkpoint-421", |
|
"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": 0.8876146788990825, |
|
"eval_loss": 0.2878369987010956, |
|
"eval_runtime": 2.3568, |
|
"eval_samples_per_second": 369.996, |
|
"eval_steps_per_second": 23.337, |
|
"step": 421 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.8864678899082569, |
|
"eval_loss": 0.2797411382198334, |
|
"eval_runtime": 2.3688, |
|
"eval_samples_per_second": 368.112, |
|
"eval_steps_per_second": 23.218, |
|
"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": 1.3007555473187744e-05, |
|
"num_train_epochs": 2, |
|
"per_device_train_batch_size": 16, |
|
"seed": 10, |
|
"weight_decay": 0.3516798909755618 |
|
} |
|
} |
|
|