{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16181229773462782,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003236245954692557,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.003236245954692557,
      "eval_loss": NaN,
      "eval_runtime": 37.1065,
      "eval_samples_per_second": 7.007,
      "eval_steps_per_second": 0.889,
      "step": 1
    },
    {
      "epoch": 0.006472491909385114,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.009708737864077669,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.012944983818770227,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.016181229773462782,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.016181229773462782,
      "eval_loss": NaN,
      "eval_runtime": 36.6369,
      "eval_samples_per_second": 7.097,
      "eval_steps_per_second": 0.901,
      "step": 5
    },
    {
      "epoch": 0.019417475728155338,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.022653721682847898,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.025889967637540454,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.02912621359223301,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.032362459546925564,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.032362459546925564,
      "eval_loss": NaN,
      "eval_runtime": 36.6305,
      "eval_samples_per_second": 7.098,
      "eval_steps_per_second": 0.901,
      "step": 10
    },
    {
      "epoch": 0.03559870550161812,
      "grad_norm": NaN,
      "learning_rate": 9.98458666866564e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.038834951456310676,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.042071197411003236,
      "grad_norm": NaN,
      "learning_rate": 9.861849601988383e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.045307443365695796,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.04854368932038835,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.04854368932038835,
      "eval_loss": NaN,
      "eval_runtime": 36.6277,
      "eval_samples_per_second": 7.098,
      "eval_steps_per_second": 0.901,
      "step": 15
    },
    {
      "epoch": 0.05177993527508091,
      "grad_norm": NaN,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.05501618122977346,
      "grad_norm": NaN,
      "learning_rate": 9.263200821770461e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.05825242718446602,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.061488673139158574,
      "grad_norm": NaN,
      "learning_rate": 8.802029828000156e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.06472491909385113,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.06472491909385113,
      "eval_loss": NaN,
      "eval_runtime": 36.6202,
      "eval_samples_per_second": 7.1,
      "eval_steps_per_second": 0.901,
      "step": 20
    },
    {
      "epoch": 0.06796116504854369,
      "grad_norm": NaN,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.07119741100323625,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0744336569579288,
      "grad_norm": NaN,
      "learning_rate": 7.612492823579745e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.07766990291262135,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.08090614886731391,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.08090614886731391,
      "eval_loss": NaN,
      "eval_runtime": 36.6414,
      "eval_samples_per_second": 7.096,
      "eval_steps_per_second": 0.901,
      "step": 25
    },
    {
      "epoch": 0.08414239482200647,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.08737864077669903,
      "grad_norm": NaN,
      "learning_rate": 6.167226819279528e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.09061488673139159,
      "grad_norm": NaN,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.09385113268608414,
      "grad_norm": NaN,
      "learning_rate": 5.392295478639225e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.0970873786407767,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0970873786407767,
      "eval_loss": NaN,
      "eval_runtime": 36.6148,
      "eval_samples_per_second": 7.101,
      "eval_steps_per_second": 0.901,
      "step": 30
    },
    {
      "epoch": 0.10032362459546926,
      "grad_norm": NaN,
      "learning_rate": 4.607704521360776e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.10355987055016182,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.10679611650485436,
      "grad_norm": NaN,
      "learning_rate": 3.832773180720475e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.11003236245954692,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.11326860841423948,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.11326860841423948,
      "eval_loss": NaN,
      "eval_runtime": 36.6108,
      "eval_samples_per_second": 7.102,
      "eval_steps_per_second": 0.901,
      "step": 35
    },
    {
      "epoch": 0.11650485436893204,
      "grad_norm": NaN,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.11974110032362459,
      "grad_norm": NaN,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.12297734627831715,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.1262135922330097,
      "grad_norm": NaN,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.12944983818770225,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.12944983818770225,
      "eval_loss": NaN,
      "eval_runtime": 36.6108,
      "eval_samples_per_second": 7.102,
      "eval_steps_per_second": 0.901,
      "step": 40
    },
    {
      "epoch": 0.13268608414239483,
      "grad_norm": NaN,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.13592233009708737,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.13915857605177995,
      "grad_norm": NaN,
      "learning_rate": 7.367991782295391e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.1423948220064725,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.14563106796116504,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.14563106796116504,
      "eval_loss": NaN,
      "eval_runtime": 36.6201,
      "eval_samples_per_second": 7.1,
      "eval_steps_per_second": 0.901,
      "step": 45
    },
    {
      "epoch": 0.1488673139158576,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.15210355987055016,
      "grad_norm": NaN,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.1553398058252427,
      "grad_norm": NaN,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.15857605177993528,
      "grad_norm": NaN,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.16181229773462782,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.16181229773462782,
      "eval_loss": NaN,
      "eval_runtime": 36.6159,
      "eval_samples_per_second": 7.101,
      "eval_steps_per_second": 0.901,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.6888215814144e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}