training_config.json

{
  "data_dir": "/nfsd/voce/machine_learning/experiments/artifacts/processed",
  "tokenizer_path": "/nfsd/voce/machine_learning/experiments/artifacts/tokenizer",
  "output_dir": "/nfsd/voce/machine_learning/experiments/cb-pdmx-bm",
  "model_architecture": "microsoft/codebert-base",
  "random_init": false,
  "hidden_size": 768,
  "num_hidden_layers": 12,
  "num_attention_heads": 12,
  "intermediate_size": 3072,
  "max_position_embeddings": 514,
  "max_length": 512,
  "mlm_probability": 0.15,
  "per_device_train_batch_size": 72,
  "per_device_eval_batch_size": 72,
  "num_train_epochs": 10,
  "learning_rate": 0.0002,
  "lr_scheduler_type": "cosine",
  "max_grad_norm": 1.0,
  "weight_decay": 0.01,
  "warmup_ratio": 0.1,
  "max_steps": -1,
  "logging_steps": 50,
  "eval_steps": 1000,
  "save_steps": 1000,
  "seed": 42,
  "pretokenized_shards_dir": "/nfsd/voce/machine_learning/experiments/codebert/baroque-music-shards/mlm",
  "resume_from_checkpoint": null,
  "dataloader_num_workers": 8,
  "early_stopping": true,
  "early_stopping_patience": 5,
  "early_stopping_threshold": 0.0,
  "bf16": true,
  "gradient_accumulation_steps": 2,
  "optim": "adamw_torch_fused",
  "dataloader_pin_memory": true,
  "dataloader_prefetch_factor": 4,
  "save_total_limit": 3,
  "torch_compile": false,
  "ddp_find_unused_parameters": false,
  "wandb_enabled": true,
  "wandb_project": "lilybert",
  "wandb_entity": null,
  "wandb_mode": "online",
  "wandb_run_name": "cb-pdmx-baroquemusic",
  "tensorboard_enabled": true,
  "tensorboard_log_dir": "/nfsd/voce/machine_learning/experiments/cb-pdmx-bm/tensorboard"
}