{
  "name": "ladder-3b-kaggle",
  "data": {
    "dataset": "open-r1/codeforces-cots",
    "config_name": "solutions_py_decontaminated",
    "split": "train",
    "max_tokens": 8192,
    "min_tokens": 256,
    "min_rating": null,
    "max_rating": null,
    "require_finish_reason": "stop",
    "dedup_by_problem": true,
    "verify_solutions": true,
    "verify_max_tests": 4,
    "verify_timeout": 5.0,
    "verify_memory_limit_mb": 1024,
    "verify_workers": 8,
    "verify_keep_unverifiable": true,
    "val_fraction": 0.04,
    "seed": 17,
    "max_samples": 0
  },
  "model": {
    "base_model": "unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit",
    "max_seq_length": 8192,
    "load_in_4bit": true,
    "lora_r": 32,
    "lora_alpha": 32,
    "lora_dropout": 0.0,
    "target_modules": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj",
      "gate_proj",
      "up_proj",
      "down_proj"
    ],
    "use_gradient_checkpointing": "unsloth"
  },
  "train": {
    "output_dir": "/kaggle/working/outputs/ladder-3b-kaggle",
    "per_device_train_batch_size": 1,
    "gradient_accumulation_steps": 16,
    "num_train_epochs": 1.0,
    "max_steps": 150,
    "learning_rate": 0.0001,
    "warmup_ratio": 0.03,
    "lr_scheduler_type": "cosine",
    "weight_decay": 0.01,
    "optim": "adamw_8bit",
    "max_grad_norm": 0.5,
    "logging_steps": 5,
    "save_steps": 75,
    "save_total_limit": 2,
    "eval_steps": 100,
    "seed": 17,
    "train_on_completions_only": true,
    "hub_model_id": null,
    "push_to_hub": false
  },
  "eval": {
    "dataset": "open-r1/codeforces-cots",
    "config_name": "solutions_py_decontaminated",
    "split": "train",
    "num_problems": 40,
    "samples_per_problem": 1,
    "problem_types": [
      "diff"
    ],
    "max_new_tokens": 4096,
    "temperature": 0.0,
    "top_p": 0.95,
    "seed": 17,
    "timeout_seconds": 8.0,
    "memory_limit_mb": 1024,
    "max_tests_per_problem": 12,
    "case_sensitive": false,
    "results_path": "/kaggle/working/outputs/eval/results.json"
  }
}