{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8032128514056225,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01606425702811245,
      "eval_loss": 6.64418363571167,
      "eval_runtime": 0.6161,
      "eval_samples_per_second": 170.42,
      "eval_steps_per_second": 22.723,
      "step": 1
    },
    {
      "epoch": 0.04819277108433735,
      "grad_norm": 6.182103633880615,
      "learning_rate": 3e-05,
      "loss": 6.1901,
      "step": 3
    },
    {
      "epoch": 0.08032128514056225,
      "eval_loss": 6.533019065856934,
      "eval_runtime": 0.6137,
      "eval_samples_per_second": 171.087,
      "eval_steps_per_second": 22.812,
      "step": 5
    },
    {
      "epoch": 0.0963855421686747,
      "grad_norm": 5.5103912353515625,
      "learning_rate": 6e-05,
      "loss": 6.1677,
      "step": 6
    },
    {
      "epoch": 0.14457831325301204,
      "grad_norm": 5.758279323577881,
      "learning_rate": 9e-05,
      "loss": 6.1421,
      "step": 9
    },
    {
      "epoch": 0.1606425702811245,
      "eval_loss": 6.087296009063721,
      "eval_runtime": 0.612,
      "eval_samples_per_second": 171.564,
      "eval_steps_per_second": 22.875,
      "step": 10
    },
    {
      "epoch": 0.1927710843373494,
      "grad_norm": 6.739719390869141,
      "learning_rate": 9.938441702975689e-05,
      "loss": 5.7648,
      "step": 12
    },
    {
      "epoch": 0.24096385542168675,
      "grad_norm": 4.701174259185791,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.9243,
      "step": 15
    },
    {
      "epoch": 0.24096385542168675,
      "eval_loss": 5.733823299407959,
      "eval_runtime": 0.6162,
      "eval_samples_per_second": 170.403,
      "eval_steps_per_second": 22.72,
      "step": 15
    },
    {
      "epoch": 0.2891566265060241,
      "grad_norm": 5.849489688873291,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.448,
      "step": 18
    },
    {
      "epoch": 0.321285140562249,
      "eval_loss": 5.51096248626709,
      "eval_runtime": 0.6135,
      "eval_samples_per_second": 171.16,
      "eval_steps_per_second": 22.821,
      "step": 20
    },
    {
      "epoch": 0.3373493975903614,
      "grad_norm": 5.229000091552734,
      "learning_rate": 8.247240241650918e-05,
      "loss": 5.6213,
      "step": 21
    },
    {
      "epoch": 0.3855421686746988,
      "grad_norm": 5.692105770111084,
      "learning_rate": 7.269952498697734e-05,
      "loss": 5.3913,
      "step": 24
    },
    {
      "epoch": 0.40160642570281124,
      "eval_loss": 5.345283508300781,
      "eval_runtime": 0.6101,
      "eval_samples_per_second": 172.09,
      "eval_steps_per_second": 22.945,
      "step": 25
    },
    {
      "epoch": 0.43373493975903615,
      "grad_norm": 5.2464704513549805,
      "learning_rate": 6.167226819279528e-05,
      "loss": 5.5785,
      "step": 27
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 5.426384925842285,
      "learning_rate": 5e-05,
      "loss": 5.2095,
      "step": 30
    },
    {
      "epoch": 0.4819277108433735,
      "eval_loss": 5.21764612197876,
      "eval_runtime": 0.6151,
      "eval_samples_per_second": 170.698,
      "eval_steps_per_second": 22.76,
      "step": 30
    },
    {
      "epoch": 0.5301204819277109,
      "grad_norm": 4.646877765655518,
      "learning_rate": 3.832773180720475e-05,
      "loss": 5.1446,
      "step": 33
    },
    {
      "epoch": 0.5622489959839357,
      "eval_loss": 5.134397506713867,
      "eval_runtime": 0.6146,
      "eval_samples_per_second": 170.839,
      "eval_steps_per_second": 22.778,
      "step": 35
    },
    {
      "epoch": 0.5783132530120482,
      "grad_norm": 4.9829936027526855,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 5.1313,
      "step": 36
    },
    {
      "epoch": 0.6265060240963856,
      "grad_norm": 6.772069454193115,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 5.0577,
      "step": 39
    },
    {
      "epoch": 0.642570281124498,
      "eval_loss": 5.084665298461914,
      "eval_runtime": 0.6128,
      "eval_samples_per_second": 171.356,
      "eval_steps_per_second": 22.848,
      "step": 40
    },
    {
      "epoch": 0.6746987951807228,
      "grad_norm": 6.180466651916504,
      "learning_rate": 9.549150281252633e-06,
      "loss": 5.132,
      "step": 42
    },
    {
      "epoch": 0.7228915662650602,
      "grad_norm": 4.479893207550049,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 5.2261,
      "step": 45
    },
    {
      "epoch": 0.7228915662650602,
      "eval_loss": 5.069843292236328,
      "eval_runtime": 0.6128,
      "eval_samples_per_second": 171.356,
      "eval_steps_per_second": 22.847,
      "step": 45
    },
    {
      "epoch": 0.7710843373493976,
      "grad_norm": 5.148656845092773,
      "learning_rate": 6.15582970243117e-07,
      "loss": 4.825,
      "step": 48
    },
    {
      "epoch": 0.8032128514056225,
      "eval_loss": 5.06525182723999,
      "eval_runtime": 0.6142,
      "eval_samples_per_second": 170.963,
      "eval_steps_per_second": 22.795,
      "step": 50
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 32706134016000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}