{
  "run_name": "llama32-3B-rte-nf4-lora-seed43",
  "model_size": "3B",
  "model_id": "meta-llama/Llama-3.2-3B",
  "task": "rte",
  "glue_config": "rte",
  "n_classes": 2,
  "bitwidth": "nf4",
  "seed": 43,
  "lora_init_source": "shared:lora_init_3B_seed43.pt:224tensors",
  "trainable_params": 9175040,
  "total_params": 1812638720,
  "train": {
    "steps": 105,
    "epochs": 2.9411764705882355,
    "train_runtime_sec": 385.316321849823,
    "train_loss": 0.476223771912711,
    "n_train_examples": 2241,
    "n_train_tokens_per_epoch": 219447,
    "throughput_samples_per_sec": 17.105884430084295,
    "throughput_tokens_per_sec": 1675.071405858415
  },
  "peak_gpu_mem_gib": {
    "allocated": 5.5141496658325195,
    "reserved": 9.181640625
  },
  "validation": {
    "accuracy": 0.8433734939759037,
    "macro_f1": 0.8428767899037295,
    "loss": 0.36798715854744357,
    "n": 249,
    "n_classes": 2,
    "majority_baseline": 0.5140562248995983,
    "pred_dist": {
      "A": 142,
      "B": 107
    },
    "true_dist": {
      "A": 121,
      "B": 128
    }
  },
  "test": {
    "accuracy": 0.8483754512635379,
    "macro_f1": 0.8471302428256071,
    "loss": 0.44474018362454987,
    "n": 277,
    "n_classes": 2,
    "majority_baseline": 0.5270758122743683,
    "pred_dist": {
      "A": 156,
      "B": 121
    },
    "true_dist": {
      "A": 146,
      "B": 131
    }
  },
  "hyperparams": {
    "num_train_epochs": 3,
    "learning_rate": 0.0002,
    "max_length": 256,
    "per_device_train_batch_size": 4,
    "per_device_eval_batch_size": 8,
    "gradient_accumulation_steps": 16,
    "warmup_ratio": 0.03,
    "lr_scheduler_type": "cosine",
    "gradient_checkpointing": true
  },
  "lora": {
    "r": 16,
    "alpha": 32,
    "dropout": 0.0,
    "bias": "none",
    "target_modules": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj"
    ]
  },
  "env": {
    "torch": "2.4.1+cu121",
    "cuda": "12.1",
    "gpu": "NVIDIA GeForce RTX 4090",
    "slurm_job": "1932942",
    "node": "node39"
  },
  "debug_caps": {
    "max_train": null,
    "max_eval": null,
    "max_steps": -1
  }
}