{
  "base_model": "/iopsstor/scratch/cscs/nmuendler/hf-cache/hub/models--deepseek-ai--DeepSeek-R1-Distill-Qwen-7B/snapshots/916b56a44061fd5cd7d6a8fb632557ed4f724f60",
  "train_file": "datasets/training_set_filtered_code_max.jsonl",
  "validation_file": "datasets/rust_dataset_true_passed_test750_max.jsonl",
  "task": "rust",
  "reasoning": false,
  "reasoning_format": "think",
  "target_mode": "standard",
  "rust_prompt_variant": "current",
  "learning_rate": 0.0002,
  "epochs": 5,
  "batch_size": 2,
  "gradient_accumulation_steps": 8,
  "effective_batch_size": 16,
  "max_length": 3000,
  "lora_r": 64,
  "lora_alpha": 128,
  "lora_dropout": 0.05,
  "target_modules": [
    "q_proj",
    "k_proj",
    "v_proj",
    "o_proj",
    "gate_proj",
    "up_proj",
    "down_proj"
  ],
  "full_finetune": false,
  "eval_step_fraction": 0.01,
  "eval_steps": 4,
  "validation_size": 100,
  "stop_reasoning_below": 90.0,
  "reasoning_probe_tokens": 20,
  "reasoning_probe_num_prompts": 100,
  "kl_coefficient": 0.0,
  "kl_temperature": 1.0,
  "kl_mask_mode": "full",
  "mask_end_think_labels": false,
  "gradient_checkpointing": false,
  "seed": 42,
  "pre_model_seed": null,
  "raw_training_examples": 6761,
  "filtered_training_examples": 6761,
  "optimizer_steps_per_epoch": 423,
  "train_file_sha256": "6c6fc896b9e48de81cce63881f5bab2497ab4bf6e212aec4202a38d0a7766450",
  "transformers_version": "5.16.1",
  "peft_version": "0.20.0",
  "torch_version": "2.13.0+cu130",
  "resolved_training_arguments": {
    "optim": "adamw_torch_fused",
    "lr_scheduler_type": "linear",
    "weight_decay": 0.0,
    "adam_beta1": 0.9,
    "adam_beta2": 0.999,
    "adam_epsilon": 1e-08,
    "max_grad_norm": 1.0,
    "warmup_ratio": null,
    "warmup_steps": 0,
    "seed": 42,
    "data_seed": 42
  }
}