{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.857142857142857,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 6.298107624053955,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.9661,
      "step": 1
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 6.799452781677246,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.0251,
      "step": 2
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 6.040467262268066,
      "learning_rate": 1e-05,
      "loss": 1.0203,
      "step": 3
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.6806766986846924,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.9212,
      "step": 4
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 4.156323432922363,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.9261,
      "step": 5
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 4.021306037902832,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.8958,
      "step": 6
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 4.254787445068359,
      "learning_rate": 9.468163201617063e-06,
      "loss": 0.8737,
      "step": 7
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 3.553865671157837,
      "learning_rate": 9.177439057064684e-06,
      "loss": 0.8658,
      "step": 8
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 2.7045857906341553,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.8563,
      "step": 9
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.7606794834136963,
      "learning_rate": 8.43120818934367e-06,
      "loss": 0.8275,
      "step": 10
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 2.06550669670105,
      "learning_rate": 7.985792958513932e-06,
      "loss": 1.1942,
      "step": 11
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.4385194778442383,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.811,
      "step": 12
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 1.2831889390945435,
      "learning_rate": 6.980398830195785e-06,
      "loss": 0.8426,
      "step": 13
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.9029828310012817,
      "learning_rate": 6.434016163555452e-06,
      "loss": 0.7755,
      "step": 14
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.7501031160354614,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.6729,
      "step": 15
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.7512649893760681,
      "learning_rate": 5.290724144552379e-06,
      "loss": 0.757,
      "step": 16
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.7660739421844482,
      "learning_rate": 4.7092758554476215e-06,
      "loss": 0.7638,
      "step": 17
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.7301563620567322,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.6996,
      "step": 18
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.7749718427658081,
      "learning_rate": 3.5659838364445505e-06,
      "loss": 0.7709,
      "step": 19
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.6608964204788208,
      "learning_rate": 3.019601169804216e-06,
      "loss": 0.7915,
      "step": 20
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8035533428192139,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 1.045,
      "step": 21
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.5167558193206787,
      "learning_rate": 2.0142070414860704e-06,
      "loss": 0.7284,
      "step": 22
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.5187545418739319,
      "learning_rate": 1.5687918106563326e-06,
      "loss": 0.7311,
      "step": 23
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.49208584427833557,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.7283,
      "step": 24
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.4248793125152588,
      "learning_rate": 8.225609429353187e-07,
      "loss": 0.7379,
      "step": 25
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.45104220509529114,
      "learning_rate": 5.318367983829393e-07,
      "loss": 0.7063,
      "step": 26
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.4235578179359436,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.695,
      "step": 27
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.398269385099411,
      "learning_rate": 1.3477564710088097e-07,
      "loss": 0.7153,
      "step": 28
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.39391636848449707,
      "learning_rate": 3.3808211290284886e-08,
      "loss": 0.7307,
      "step": 29
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.4196050465106964,
      "learning_rate": 0.0,
      "loss": 0.7391,
      "step": 30
    },
    {
      "epoch": 2.857142857142857,
      "step": 30,
      "total_flos": 41955250929664.0,
      "train_loss": 0.8271350403626759,
      "train_runtime": 2095.9807,
      "train_samples_per_second": 1.431,
      "train_steps_per_second": 0.014
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 41955250929664.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}