{ | |
"data_path": "autotrain-z9wst-apic1/autotrain-data", | |
"model": "microsoft/deberta-v3-base", | |
"lr": 5e-05, | |
"epochs": 1, | |
"max_seq_length": 256, | |
"batch_size": 32, | |
"warmup_ratio": 0.1, | |
"gradient_accumulation": 1, | |
"optimizer": "adamw_torch", | |
"scheduler": "cosine", | |
"weight_decay": 0.0, | |
"max_grad_norm": 1.0, | |
"seed": 42, | |
"train_split": "train", | |
"valid_split": "validation", | |
"text_column": "autotrain_text", | |
"target_column": "autotrain_label", | |
"logging_steps": -1, | |
"project_name": "autotrain-z9wst-apic1", | |
"auto_find_batch_size": false, | |
"mixed_precision": "fp16", | |
"save_total_limit": 1, | |
"push_to_hub": true, | |
"eval_strategy": "epoch", | |
"username": "assaflehr", | |
"log": "tensorboard", | |
"early_stopping_patience": 5, | |
"early_stopping_threshold": 0.01 | |
} |