training_config.json

{
  "dataset_name": "PoolC/1-fold-clone-detection-600k-5fold",
  "train_split": "train",
  "heldout_split": "val",
  "test_group_fraction": 0.5,
  "max_train_samples": 50000,
  "max_eval_samples": 20000,
  "max_test_samples": 20000,
  "balance_subsamples": true,
  "model_name_or_path": "microsoft/graphcodebert-base",
  "code_length": 512,
  "data_flow_length": 128,
  "attn_implementation": "sdpa",
  "learning_rate": 2e-05,
  "num_train_epochs": 3.0,
  "per_device_train_batch_size": 16,
  "per_device_eval_batch_size": 32,
  "gradient_accumulation_steps": 1,
  "weight_decay": 0.01,
  "warmup_ratio": 0.1,
  "max_grad_norm": 1.0,
  "fp16": true,
  "bf16": false,
  "gradient_checkpointing": false,
  "optim": "adamw_torch",
  "lr_scheduler_type": "linear",
  "class_weighting": "auto",
  "class_weight_threshold": 0.6,
  "eval_strategy": "steps",
  "eval_steps": 1000,
  "save_strategy": "steps",
  "save_steps": 1000,
  "save_total_limit": 2,
  "logging_steps": 100,
  "metric_for_best_model": "f1",
  "greater_is_better": true,
  "load_best_model_at_end": true,
  "seed": 42,
  "full_determinism": false,
  "dataloader_num_workers": 4,
  "preprocessing_num_workers": 8,
  "output_dir": "./outputs",
  "model_dir": "./models/graphcodebert-clone-detection",
  "logging_dir": "./logs",
  "cache_dir": "./outputs/feature_cache",
  "report_to": "none",
  "run_sanity_check": true,
  "sanity_check_samples": 64,
  "total_sequence_length": 640,
  "effective_batch_size": 16
}