{
  "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",
      "down_proj",
      "o_proj",
      "gate_proj",
      "v_proj",
      "k_proj",
      "up_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": "monolithic_1600",
  "base_probe_loss": 1.30984,
  "dpo_steps": 0,
  "files": {
    "adapter_config.json": {
      "bytes": 1226,
      "sha256": "0f93046676d1a5d9c1a5efa0bd5ee344e81c870431f1611e570eab4037001f1d"
    },
    "adapter_model.safetensors": {
      "bytes": 97307544,
      "sha256": "4dd4ed96ec0a2f835405ca03d95179b238dbc6a4eaea6e65d7fd13d1c9111ccf"
    }
  },
  "final_loss": 0.42555,
  "initial_loss": 1.30531,
  "kind": "sft",
  "max_abs_diff_disabled_vs_base": 0.0,
  "max_abs_diff_tuned_vs_base": 30.14209,
  "persisted_in_working": true,
  "public_name": "lora.monolithic-mixed",
  "role": "monolithic_mixed",
  "saved_dir": "/kaggle/working/adapters/monolithic_1600",
  "scale": 1600,
  "sft_steps": 56,
  "skipped_steps": 0,
  "tokens_per_s": 135.4,
  "tokens_processed": 284121,
  "train_rows": 1600,
  "train_seconds": 2098.05,
  "trainable_params": 24313856,
  "tuned_probe_loss": 0.36392
}