args.json

{"data_dir": "data/", "model_type": "distilroberta", "model_name": "distilroberta-base", "task_name": "binary", "output_dir": "outputs/", "cache_dir": "cache/", "do_train": true, "do_eval": true, "fp16": false, "fp16_opt_level": "O1", "max_seq_length": 128, "output_mode": "classification", "train_batch_size": 12, "eval_batch_size": 12, "gradient_accumulation_steps": 1, "num_train_epochs": 1, "weight_decay": 0, "learning_rate": 4e-05, "adam_epsilon": 1e-08, "warmup_ratio": 0.06, "warmup_steps": 0, "max_grad_norm": 1.0, "logging_steps": 50, "evaluate_during_training": false, "save_steps": 2000, "eval_all_checkpoints": true, "overwrite_output_dir": false, "reprocess_input_data": true, "notes": "Using twitter dataset"}