{
  "seed": 42,
  "model": {
    "name": "HuggingFaceTB/SmolLM2-360M-Instruct",
    "chat_template_path": "configs/chat_template_smollm2.jinja",
    "attn_implementation": "sdpa",
    "dtype": "bfloat16"
  },
  "data": {
    "dataset_id": "chimbiwide/NPC-Dialogue_v2",
    "dataset_config": "dialogue",
    "source_split": "train",
    "raw_dir": "data/raw",
    "processed_dir": "data/processed",
    "max_seq_length": 2048,
    "candidate_max_lengths": [
      512,
      1024,
      1536,
      2048,
      3072,
      4096
    ],
    "max_system_tokens": 1536,
    "min_assistant_tokens": 4,
    "max_chunks_per_conversation": 2,
    "validation_character_ratio": 0.1,
    "split_strategy": "character",
    "stratify_by_variant": true,
    "filter_explicit": false,
    "drop_duplicates": true
  },
  "lora": {
    "enabled": true,
    "r": 16,
    "lora_alpha": 32,
    "lora_dropout": 0.05,
    "bias": "none",
    "task_type": "CAUSAL_LM",
    "target_modules": [],
    "auto_target_modules": true,
    "exclude_modules": [
      "lm_head",
      "embed_tokens"
    ]
  },
  "train": {
    "output_dir": "outputs/checkpoints/npc-lora",
    "run_name": "smollm2-360m-npc-lora",
    "num_train_epochs": 3,
    "per_device_train_batch_size": 8,
    "per_device_eval_batch_size": 8,
    "gradient_accumulation_steps": 2,
    "auto_batch_size": true,
    "learning_rate": 0.0002,
    "lr_scheduler_type": "cosine",
    "warmup_ratio": 0.05,
    "weight_decay": 0.01,
    "max_grad_norm": 1.0,
    "optim": "adamw_torch_fused",
    "bf16": "auto",
    "gradient_checkpointing": true,
    "packing": false,
    "assistant_only_loss": true,
    "logging_steps": 5,
    "eval_strategy": "steps",
    "eval_steps": 250,
    "save_strategy": "steps",
    "save_steps": 250,
    "auto_eval_steps": true,
    "target_evaluations": 6,
    "save_total_limit": 3,
    "load_best_model_at_end": true,
    "metric_for_best_model": "eval_loss",
    "greater_is_better": false,
    "report_to": [
      "tensorboard"
    ],
    "dataloader_num_workers": 4,
    "max_train_samples": 0,
    "max_eval_samples": 1000
  },
  "full_finetune": {
    "learning_rate": 2e-05,
    "per_device_train_batch_size": 4,
    "gradient_accumulation_steps": 8,
    "gradient_checkpointing": true,
    "output_dir": "outputs/checkpoints/npc-full"
  },
  "generation": {
    "do_sample": true,
    "temperature": 0.8,
    "top_p": 0.9,
    "top_k": 50,
    "max_new_tokens": 160,
    "repetition_penalty": 1.1
  },
  "evaluation": {
    "output_dir": "outputs/evaluation",
    "num_comparison_examples": 60,
    "scenarios_path": "configs/eval_scenarios.yaml",
    "qualitative_turns": 4,
    "compute_rouge": true,
    "compute_bleu": true,
    "semantic_model": "sentence-transformers/all-MiniLM-L6-v2",
    "compute_semantic_similarity": true
  },
  "hub": {
    "repo_id": "",
    "private": false,
    "push_merged_model": true,
    "commit_message": "Add SmolLM2-360M NPC roleplay model"
  }
}