{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8888888888888888,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 7.324110666020067,
      "learning_rate": 0.0,
      "loss": 1.1331,
      "step": 1
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 6.970093833551372,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.9839,
      "step": 2
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 6.533144881859678,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.1706,
      "step": 3
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 4.207071008660512,
      "learning_rate": 1e-05,
      "loss": 0.9681,
      "step": 4
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 2.642402710160962,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.8197,
      "step": 5
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.727792568855549,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.8382,
      "step": 6
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.9522935621615103,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.9836,
      "step": 7
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 2.5757668932590003,
      "learning_rate": 9.468163201617063e-06,
      "loss": 0.8731,
      "step": 8
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.0911823115100314,
      "learning_rate": 9.177439057064684e-06,
      "loss": 0.8753,
      "step": 9
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 1.8503711966182128,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.9582,
      "step": 10
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 1.9114302786839066,
      "learning_rate": 8.43120818934367e-06,
      "loss": 0.785,
      "step": 11
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 2.0324118014591397,
      "learning_rate": 7.985792958513932e-06,
      "loss": 0.8561,
      "step": 12
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 1.968052637757545,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.9083,
      "step": 13
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.7085596413443718,
      "learning_rate": 6.980398830195785e-06,
      "loss": 0.8333,
      "step": 14
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.8547754899514082,
      "learning_rate": 6.434016163555452e-06,
      "loss": 0.8507,
      "step": 15
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.8547754899514082,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.7102,
      "step": 16
    },
    {
      "epoch": 1.0634920634920635,
      "grad_norm": 1.7988647892176266,
      "learning_rate": 5.290724144552379e-06,
      "loss": 0.7307,
      "step": 17
    },
    {
      "epoch": 1.126984126984127,
      "grad_norm": 1.4701202322559601,
      "learning_rate": 4.7092758554476215e-06,
      "loss": 0.6586,
      "step": 18
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 1.4519462964010579,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.718,
      "step": 19
    },
    {
      "epoch": 1.253968253968254,
      "grad_norm": 1.4790600874234856,
      "learning_rate": 3.5659838364445505e-06,
      "loss": 0.7562,
      "step": 20
    },
    {
      "epoch": 1.3174603174603174,
      "grad_norm": 1.3709811120459832,
      "learning_rate": 3.019601169804216e-06,
      "loss": 0.6764,
      "step": 21
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 1.5845689530878082,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.8151,
      "step": 22
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 1.347763642806335,
      "learning_rate": 2.0142070414860704e-06,
      "loss": 0.6922,
      "step": 23
    },
    {
      "epoch": 1.507936507936508,
      "grad_norm": 1.3625248870214142,
      "learning_rate": 1.5687918106563326e-06,
      "loss": 0.7066,
      "step": 24
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 1.2655929657505138,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.6978,
      "step": 25
    },
    {
      "epoch": 1.6349206349206349,
      "grad_norm": 1.25066011858336,
      "learning_rate": 8.225609429353187e-07,
      "loss": 0.7835,
      "step": 26
    },
    {
      "epoch": 1.6984126984126984,
      "grad_norm": 1.416071207700581,
      "learning_rate": 5.318367983829393e-07,
      "loss": 0.6726,
      "step": 27
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 1.407662267783889,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.6786,
      "step": 28
    },
    {
      "epoch": 1.8253968253968254,
      "grad_norm": 1.145457608552001,
      "learning_rate": 1.3477564710088097e-07,
      "loss": 0.647,
      "step": 29
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 1.2631614021291049,
      "learning_rate": 3.3808211290284886e-08,
      "loss": 0.6099,
      "step": 30
    },
    {
      "epoch": 1.8888888888888888,
      "step": 30,
      "total_flos": 6383245138591744.0,
      "train_loss": 0.8130231420199077,
      "train_runtime": 322.1077,
      "train_samples_per_second": 4.694,
      "train_steps_per_second": 0.093
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6383245138591744.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}