| { | |
| "data_path": "gizemgg/wiki-eng-summary-trial-gen0-transformed-instruction", | |
| "model": "google/t5-efficient-tiny-nh8", | |
| "username": "shorecode", | |
| "seed": 42, | |
| "train_split": "train", | |
| "valid_split": "test", | |
| "project_name": "autotrain-x906d-mvlef", | |
| "push_to_hub": true, | |
| "text_column": "text", | |
| "target_column": "summ", | |
| "lr": 0.0001, | |
| "epochs": 3, | |
| "max_seq_length": 128, | |
| "max_target_length": 128, | |
| "batch_size": 2, | |
| "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": "int8", | |
| "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 | |
| } |