vision_base_h0_lm/args.json

{
  "regime": "vision",
  "data_path": "data/training/splits_510k/train_arrow",
  "output_dir": "outputs/production_vision_base_lm_20251123_003859",
  "objective": "lm",
  "val_data_path": "data/training/splits_510k/val_arrow",
  "max_samples": null,
  "vision_mode": "base",
  "text_context_tokens": null,
  "hybrid_text_tokens": 0,
  "vision_prompt": "\nFree OCR.",
  "train_encoder": true,
  "encoder_lr": 1e-05,
  "compression_window_size": 9,
  "compression_stride": 9,
  "subsample_strategy": "regular",
  "subsample_count": null,
  "projection_dim": null,
  "train_projection": true,
  "compression_target": null,
  "conv_kernel": 5,
  "timestamp": "20251123_003859",
  "batch_size": 8,
  "gradient_accumulation_steps": 6,
  "learning_rate": 0.0001,
  "weight_decay": 0.01,
  "num_epochs": 1,
  "warmup_ratio": 0.1,
  "max_grad_norm": 1.0,
  "log_steps": 10,
  "save_steps": 0,
  "eval_steps": 2000,
  "initial_validation": false,
  "validation_only": false,
  "no_checkpoints": false,
  "num_qualitative_samples": 5,
  "max_generation_tokens": 200,
  "use_wandb": true,
  "wandb_project": "vision-compression-2",
  "wandb_run_name": "production_vision_base_lm_20251123_003859",
  "resume_from_checkpoint": "outputs/production_vision_base_lm_20251123_003859/best_checkpoint.pt",
  "resume": "outputs/production_vision_base_lm_20251123_003859/best_checkpoint.pt",
  "init_from_checkpoint": null,
  "allow_objective_switch": false,
  "aux_loss_weight": 0.5,
  "num_workers": 16,
  "prefetch_factor": 4,
  "seed": 42,
  "eval_seed": 42,
  "debug_log_sample_ids": false,
  "device": "cuda",
  "compile": false,
  "compile_mode": "default",
  "use_optimized_model": true,
  "use_encoder_checkpointing": true,
  "use_decoder_checkpointing": true,
  "use_8bit_optimizer": false
}