training_config.json

{
  "model_name": "microsoft/deberta-v3-large",
  "dataset_name": "jainsatyam26/guardrail-215k-splits",
  "max_length": 512,
  "epochs": 4,
  "batch_size": 8,
  "grad_accum": 4,
  "learning_rate": 1e-05,
  "weight_decay": 0.01,
  "warmup_ratio": 0.1,
  "use_llrd": true,
  "llrd_alpha": 0.9,
  "use_multisample_dropout": true,
  "num_dropout_samples": 5,
  "dropout_rate": 0.3,
  "use_label_smoothing": true,
  "label_smoothing": 0.1,
  "use_focal_loss": true,
  "focal_alpha": 0.7,
  "focal_gamma": 2.0,
  "use_hard_negative": true,
  "hard_negative_ratio": 0.3,
  "num_folds": 3,
  "optimize_thresholds": true,
  "output_dir": "./guardrail_model",
  "checkpoint_steps": 500,
  "logging_steps": 50,
  "eval_steps": 500,
  "hf_repo_id": "jainsatyam26/bertclassfier",
  "hf_token": "***REDACTED***",
  "deploy_every_minutes": 30,
  "deploy_every_steps": 400,
  "auto_deploy": true,
  "private_repo": false,
  "auto_resume": true,
  "resume_from_hf": true,
  "use_wandb": true,
  "wandb_project": "safety-classifier",
  "fp16": false,
  "bf16": true,
  "dataloader_num_workers": 4,
  "seed": 42
}