{
  "model_type": "llama",
  "hidden_size": 4096,
  "num_attention_heads": 16,
  "num_hidden_layers": 32,
  "intermediate_size": 11008,
  "hidden_act": "gelu",
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-5,
  "max_position_embeddings": 2048,
  "vocab_size": 32000,
  "model_name": "LlamaForSequenceClassification",
  "pipeline_tag": "text-generation",
  "peft_config": {
    "r": 16,
    "target_modules": [
      "q_proj", "k_proj", "v_proj", "o_proj",
      "gate_proj", "up_proj", "down_proj",
      "embed_tokens", "lm_head"
    ],
    "lora_alpha": 16,
    "lora_dropout": 0,
    "bias": "none",
    "use_gradient_checkpointing": "unsloth",
    "random_state": 3407,
    "use_rslora": false,
    "loftq_config": null
  },
  "training_args": {
    "per_device_train_batch_size": 2,
    "gradient_accumulation_steps": 4,
    "warmup_steps": 5,
    "max_steps": 60,
    "learning_rate": 2e-4,
    "fp16": true,
    "bf16": false,
    "logging_steps": 1,
    "optim": "adamw_8bit",
    "weight_decay": 0.01,
    "lr_scheduler_type": "linear",
    "seed": 3407,
    "output_dir": "outputs"
  }
}