| { |
| "data_path": "Paraphrase-v3/autotrain-data", |
| "model": "google-t5/t5-base", |
| "username": "edithram23", |
| "seed": 42, |
| "train_split": "train", |
| "valid_split": "validation", |
| "project_name": "Paraphrase-v3", |
| "push_to_hub": true, |
| "text_column": "autotrain_text", |
| "target_column": "autotrain_label", |
| "lr": 5e-05, |
| "epochs": 15, |
| "max_seq_length": 128, |
| "max_target_length": 128, |
| "batch_size": 16, |
| "warmup_ratio": 0.1, |
| "gradient_accumulation": 1, |
| "optimizer": "adamw_torch", |
| "scheduler": "linear", |
| "weight_decay": 0.0, |
| "max_grad_norm": 1.0, |
| "logging_steps": -1, |
| "eval_strategy": "epoch", |
| "auto_find_batch_size": false, |
| "mixed_precision": "fp16", |
| "save_total_limit": 1, |
| "peft": false, |
| "quantization": "int4", |
| "lora_r": 16, |
| "lora_alpha": 32, |
| "lora_dropout": 0.05, |
| "target_modules": "all-linear", |
| "log": "tensorboard", |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.01 |
| } |
