|
{ |
|
"adam_epsilon": 1e-08, |
|
"cache_dir": "", |
|
"config_name": "", |
|
"data_dir": "/content/data/glue/MNLI", |
|
"dev": null, |
|
"device": "cuda", |
|
"do_eval": true, |
|
"do_lower_case": true, |
|
"do_test": false, |
|
"do_train": true, |
|
"eval_all_checkpoints": false, |
|
"evaluate_during_training": true, |
|
"evaluate_during_training_epoch": false, |
|
"features_cache_dir": "/content/data/glue/MNLI/cache_36891", |
|
"fp16": false, |
|
"fp16_opt_level": "01", |
|
"gradient_accumulation_steps": 1, |
|
"learning_rate": 1.0993071205018916e-05, |
|
"local_rank": -1, |
|
"logging_steps": 1000, |
|
"max_grad_norm": 1.0, |
|
"max_seq_length": 128, |
|
"max_steps": -1, |
|
"model_name_or_path": "roberta-base", |
|
"model_type": "roberta", |
|
"n_gpu": 1, |
|
"no_cuda": false, |
|
"num_train_epochs": 6, |
|
"output_dir": "/content/results", |
|
"output_mode": "classification", |
|
"overwrite_cache": false, |
|
"overwrite_output_dir": false, |
|
"patience": 3, |
|
"per_gpu_eval_batch_size": 96, |
|
"per_gpu_train_batch_size": 64, |
|
"save_steps": 0, |
|
"seed": 36891, |
|
"server_ip": "", |
|
"server_port": "", |
|
"task_name": "mnli", |
|
"test": null, |
|
"tokenizer_name": "", |
|
"train": null, |
|
"warmup_steps": 0, |
|
"weight_decay": 0.0 |
|
} |
|
|