training_params.json

{
    "data_path": "rajpurkar/squad_v2",
    "model": "Wonder-Griffin/TraXLMistral",
    "lr": 3e-05,
    "epochs": 3,
    "max_seq_length": 128,
    "batch_size": 8,
    "warmup_ratio": 0.1,
    "gradient_accumulation": 1,
    "optimizer": "adamw_torch",
    "scheduler": "linear",
    "weight_decay": 0.0,
    "max_grad_norm": 1.0,
    "seed": 42,
    "train_split": "train",
    "valid_split": null,
    "logging_steps": -1,
    "project_name": "squadtrainTraXL",
    "auto_find_batch_size": true,
    "mixed_precision": "fp16",
    "save_total_limit": 1,
    "push_to_hub": true,
    "eval_strategy": "steps",
    "username": "Wonder-Griffin",
    "log": "tensorboard",
    "early_stopping_patience": 5,
    "early_stopping_threshold": 0.01,
    "trainer": "qa",
    "sentence1_column": "question",
    "sentence2_column": "answers",
    "sentence3_column": "sentence3",
    "target_column": "target"
}