{
  "run_id": "20260512_190433",
  "model_id": "google/gemma-4-E4B-it",
  "dataset_id": "ise-uiuc/Magicoder-Evol-Instruct-110K",
  "adapter_repo": "josephmayo/gemma-4-E4B-it-coding-lora",
  "merged_repo": "josephmayo/gemma-4-E4B-it-coding-merged",
  "stage": "after_eval",
  "errors": [],
  "cuda_available": true,
  "cuda_device_count": 2,
  "devices": [
    "Tesla T4",
    "Tesla T4"
  ],
  "torch_version_initial": "2.10.0+cu128",
  "hf_token_present": false,
  "max_train_samples": 1024,
  "max_steps": 200,
  "max_seq_length": 512,
  "eval_count": 8,
  "lora_r": 16,
  "lora_alpha": 32,
  "lr": 0.0001,
  "grad_accum": 8,
  "push_to_hf": true,
  "merge_and_push": false,
  "load_in_4bit": true,
  "memory_after_load": [
    0,
    9302143488
  ],
  "eval_source": "openai/openai_humaneval:8",
  "baseline_avg_score": 0.76875,
  "safe_train_rows": 1024,
  "trainable_parameters": {
    "trainable": 50499584,
    "total": 7991600416
  },
  "log_history_tail": [
    {
      "loss": 1.0154043197631837,
      "grad_norm": 0.37521687150001526,
      "learning_rate": 4.51495073572676e-05,
      "epoch": 1.71875
    },
    {
      "loss": 0.9917967796325684,
      "grad_norm": 0.42887604236602783,
      "learning_rate": 4.114045042103887e-05,
      "epoch": 1.796875
    },
    {
      "loss": 1.1146905899047852,
      "grad_norm": 0.4208148717880249,
      "learning_rate": 3.718944461187138e-05,
      "epoch": 1.875
    },
    {
      "loss": 0.9283761978149414,
      "grad_norm": 0.3849687874317169,
      "learning_rate": 3.332237841745898e-05,
      "epoch": 1.953125
    },
    {
      "loss": 1.113053035736084,
      "grad_norm": 0.4142734110355377,
      "learning_rate": 2.9564590321322207e-05,
      "epoch": 2.03125
    },
    {
      "loss": 0.9842248916625976,
      "grad_norm": 0.44529953598976135,
      "learning_rate": 2.5940702775459747e-05,
      "epoch": 2.109375
    },
    {
      "loss": 0.9449721336364746,
      "grad_norm": 0.3756776750087738,
      "learning_rate": 2.2474460864709824e-05,
      "epoch": 2.1875
    },
    {
      "loss": 1.0590093612670899,
      "grad_norm": 0.4192875325679779,
      "learning_rate": 1.9188576719953633e-05,
      "epoch": 2.265625
    },
    {
      "loss": 0.9768091201782226,
      "grad_norm": 0.5095818638801575,
      "learning_rate": 1.6104580699624837e-05,
      "epoch": 2.34375
    },
    {
      "loss": 1.038302516937256,
      "grad_norm": 0.41709497570991516,
      "learning_rate": 1.3242680314639993e-05,
      "epoch": 2.421875
    },
    {
      "loss": 0.9975608825683594,
      "grad_norm": 0.5563586354255676,
      "learning_rate": 1.0621627821127289e-05,
      "epoch": 2.5
    },
    {
      "loss": 0.9714397430419922,
      "grad_norm": 0.8915637135505676,
      "learning_rate": 8.25859734853645e-06,
      "epoch": 2.578125
    },
    {
      "loss": 0.9948483467102051,
      "grad_norm": 0.4391196370124817,
      "learning_rate": 6.16907236823262e-06,
      "epoch": 2.65625
    },
    {
      "loss": 0.9389057159423828,
      "grad_norm": 0.4650712311267853,
      "learning_rate": 4.366744239922998e-06,
      "epoch": 2.734375
    },
    {
      "loss": 1.06390380859375,
      "grad_norm": 0.4836062788963318,
      "learning_rate": 2.8634225006782865e-06,
      "epoch": 2.8125
    },
    {
      "loss": 1.008359718322754,
      "grad_norm": 0.45215511322021484,
      "learning_rate": 1.6689574843694433e-06,
      "epoch": 2.890625
    },
    {
      "loss": 1.0110493659973145,
      "grad_norm": 0.5408219695091248,
      "learning_rate": 7.911757785462881e-07,
      "epoch": 2.96875
    },
    {
      "loss": 0.911649227142334,
      "grad_norm": 0.4599083364009857,
      "learning_rate": 2.3582894166930268e-07,
      "epoch": 3.046875
    },
    {
      "loss": 0.9673548698425293,
      "grad_norm": 0.43304941058158875,
      "learning_rate": 6.5558167183898955e-09,
      "epoch": 3.125
    },
    {
      "train_runtime": 4256.6409,
      "train_samples_per_second": 0.752,
      "train_steps_per_second": 0.047,
      "total_flos": 4.259313762009523e+16,
      "train_loss": 1.142699921131134,
      "epoch": 3.125
    }
  ],
  "train_metrics": {
    "train_runtime": 4256.6409,
    "train_samples_per_second": 0.752,
    "train_steps_per_second": 0.047,
    "total_flos": 4.259313762009523e+16,
    "train_loss": 1.142699921131134,
    "epoch": 3.125
  },
  "after_avg_score": 0.76875,
  "score_delta": 0.0,
  "adapter_dir": "/kaggle/working/gemma4_e4b_coding_lora",
  "release_gate_pass": true
}