{
  "model": "CohereLabs/tiny-aya-global",
  "dataset_name": "unknown",
  "output_dir": "/tmp/out/adapter",
  "use_rollouts": false,
  "agentic_mode": false,
  "tools": [],
  "train_size": 306,
  "eval_size": 0,
  "final_loss": 0.534419200817744,
  "total_steps": 60,
  "training_history": [],
  "metrics": {
    "train_runtime": 911.9718,
    "train_samples_per_second": 1.007,
    "train_steps_per_second": 0.066,
    "total_flos": 0.0,
    "train_loss": 0.534419200817744,
    "epoch": 3.0
  },
  "config_kwargs": {
    "model": "CohereLabs/tiny-aya-global",
    "train_dataset": "Dataset({\n    features: ['prompt', 'completion', 'label'],\n    num_rows: 306\n})",
    "output_dir": "/tmp/out/adapter",
    "peft_config": {
      "r": 16,
      "lora_alpha": 32,
      "lora_dropout": 0.05,
      "task_type": "CAUSAL_LM",
      "target_modules": [
        "q_proj",
        "k_proj",
        "v_proj",
        "o_proj",
        "gate_proj",
        "up_proj",
        "down_proj"
      ]
    },
    "num_train_epochs": 3.0,
    "per_device_train_batch_size": 1,
    "gradient_accumulation_steps": 16,
    "learning_rate": 1e-05,
    "beta": 0.1,
    "seed": 42,
    "bf16": true,
    "logging_steps": 2,
    "save_strategy": "no",
    "report_to": "none",
    "gradient_checkpointing": true,
    "max_prompt_length": 2048,
    "max_length": 2176
  }
}