{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.996875,
  "eval_steps": 500,
  "global_step": 1599,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 9.896907216494846e-05,
      "loss": 1.5529,
      "step": 64
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.484536082474227e-05,
      "loss": 0.9276,
      "step": 128
    },
    {
      "epoch": 0.6,
      "learning_rate": 9.072164948453609e-05,
      "loss": 0.879,
      "step": 192
    },
    {
      "epoch": 0.8,
      "learning_rate": 8.65979381443299e-05,
      "loss": 0.8731,
      "step": 256
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.247422680412371e-05,
      "loss": 0.8242,
      "step": 320
    },
    {
      "epoch": 1.2,
      "learning_rate": 7.835051546391753e-05,
      "loss": 0.7293,
      "step": 384
    },
    {
      "epoch": 1.4,
      "learning_rate": 7.422680412371135e-05,
      "loss": 0.7194,
      "step": 448
    },
    {
      "epoch": 1.6,
      "learning_rate": 7.010309278350515e-05,
      "loss": 0.6864,
      "step": 512
    },
    {
      "epoch": 1.8,
      "learning_rate": 6.597938144329897e-05,
      "loss": 0.7096,
      "step": 576
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.185567010309279e-05,
      "loss": 0.6913,
      "step": 640
    },
    {
      "epoch": 2.2,
      "learning_rate": 5.7731958762886594e-05,
      "loss": 0.5724,
      "step": 704
    },
    {
      "epoch": 2.4,
      "learning_rate": 5.360824742268041e-05,
      "loss": 0.5465,
      "step": 768
    },
    {
      "epoch": 2.6,
      "learning_rate": 4.948453608247423e-05,
      "loss": 0.5307,
      "step": 832
    },
    {
      "epoch": 2.8,
      "learning_rate": 4.536082474226804e-05,
      "loss": 0.5446,
      "step": 896
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.1237113402061855e-05,
      "loss": 0.5501,
      "step": 960
    },
    {
      "epoch": 3.2,
      "learning_rate": 3.7113402061855674e-05,
      "loss": 0.4308,
      "step": 1024
    },
    {
      "epoch": 3.4,
      "learning_rate": 3.2989690721649485e-05,
      "loss": 0.4082,
      "step": 1088
    },
    {
      "epoch": 3.6,
      "learning_rate": 2.8865979381443297e-05,
      "loss": 0.4158,
      "step": 1152
    },
    {
      "epoch": 3.8,
      "learning_rate": 2.4742268041237116e-05,
      "loss": 0.4281,
      "step": 1216
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.0618556701030927e-05,
      "loss": 0.4065,
      "step": 1280
    },
    {
      "epoch": 4.2,
      "learning_rate": 1.6494845360824743e-05,
      "loss": 0.3311,
      "step": 1344
    },
    {
      "epoch": 4.4,
      "learning_rate": 1.2371134020618558e-05,
      "loss": 0.3239,
      "step": 1408
    },
    {
      "epoch": 4.6,
      "learning_rate": 8.247422680412371e-06,
      "loss": 0.322,
      "step": 1472
    },
    {
      "epoch": 4.8,
      "learning_rate": 4.123711340206186e-06,
      "loss": 0.3261,
      "step": 1536
    }
  ],
  "logging_steps": 64,
  "max_steps": 1600,
  "num_train_epochs": 5,
  "save_steps": 1599,
  "total_flos": 1.2482695900296806e+17,
  "trial_name": null,
  "trial_params": null
}