{
  "adapter_config": {
    "alora_invocation_tokens": null,
    "alpha_pattern": {},
    "arrow_config": null,
    "auto_mapping": null,
    "base_model_name_or_path": "/kaggle/input/models/metaresearch/llama-3.2/transformers/3b-instruct/1",
    "bias": "none",
    "corda_config": null,
    "ensure_weight_tying": false,
    "eva_config": null,
    "exclude_modules": null,
    "fan_in_fan_out": false,
    "inference_mode": true,
    "init_lora_weights": true,
    "kasa_config": null,
    "layer_replication": null,
    "layers_pattern": null,
    "layers_to_transform": null,
    "loftq_config": {},
    "lora_alpha": 32,
    "lora_bias": false,
    "lora_dropout": 0.05,
    "lora_ga_config": null,
    "megatron_config": null,
    "megatron_core": "megatron.core",
    "modules_to_save": null,
    "monteclora_config": null,
    "peft_type": "LORA",
    "peft_version": "0.21.2",
    "qalora_group_size": 16,
    "r": 16,
    "rank_pattern": {},
    "revision": null,
    "target_modules": [
      "q_proj",
      "o_proj",
      "up_proj",
      "gate_proj",
      "v_proj",
      "k_proj",
      "down_proj"
    ],
    "target_parameters": null,
    "task_type": "CAUSAL_LM",
    "trainable_token_indices": null,
    "use_bdlora": null,
    "use_dora": false,
    "use_qalora": false,
    "use_rslora": false,
    "velora_config": null
  },
  "adapter_key": "retriever_1600",
  "base_probe_loss": 1.30984,
  "dpo_steps": 0,
  "files": {
    "adapter_config.json": {
      "bytes": 1226,
      "sha256": "9b8c1be09b50308e61b386695bbc4c53e243ed2f421fa6ae861d113353e57697"
    },
    "adapter_model.safetensors": {
      "bytes": 97307544,
      "sha256": "567596a253fad7ec6cba8ec796a8bc7de33aa28d6513609a83b1714c28c4cc86"
    }
  },
  "final_loss": 0.35491,
  "initial_loss": 1.40856,
  "kind": "sft",
  "max_abs_diff_disabled_vs_base": 0.0,
  "max_abs_diff_tuned_vs_base": 21.47266,
  "persisted_in_working": true,
  "public_name": "lora.shim-retriever",
  "role": "retriever",
  "saved_dir": "/kaggle/working/adapters/retriever_1600",
  "scale": 1600,
  "sft_steps": 44,
  "skipped_steps": 0,
  "tokens_per_s": 173.9,
  "tokens_processed": 201112,
  "train_rows": 500,
  "train_seconds": 1156.7,
  "trainable_params": 24313856,
  "tuned_probe_loss": 1.88547
}