{"dataset": ["tner/conll2003"], "dataset_split": "train", "dataset_name": null, "local_dataset": null, "model": "microsoft/deberta-v3-large", "crf": false, "max_length": 128, "epoch": 15, "batch_size": 16, "lr": 1e-05, "random_seed": 42, "gradient_accumulation_steps": 4, "weight_decay": null, "lr_warmup_step_ratio": 0.1, "max_grad_norm": 10.0} |