{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.024,
  "eval_steps": 1000,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.3598,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.1113,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.0722,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019863945578231293,
      "loss": 2.1798,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019727891156462587,
      "loss": 1.9333,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001959183673469388,
      "loss": 2.4093,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001945578231292517,
      "loss": 2.6837,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019319727891156462,
      "loss": 1.5956,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019183673469387756,
      "loss": 2.02,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019047619047619048,
      "loss": 2.0534,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018911564625850343,
      "loss": 1.804,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018775510204081634,
      "loss": 2.0297,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018639455782312926,
      "loss": 1.8164,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001850340136054422,
      "loss": 1.8929,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018367346938775512,
      "loss": 1.7967,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018231292517006804,
      "loss": 1.5366,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018095238095238095,
      "loss": 1.7421,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001795918367346939,
      "loss": 2.5308,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017823129251700681,
      "loss": 1.5277,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017687074829931973,
      "loss": 1.9084,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017551020408163265,
      "loss": 1.9708,
      "step": 21
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001741496598639456,
      "loss": 1.8567,
      "step": 22
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001727891156462585,
      "loss": 1.5694,
      "step": 23
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.8519,
      "step": 24
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017006802721088434,
      "loss": 1.663,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016870748299319729,
      "loss": 1.9309,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016734693877551023,
      "loss": 1.551,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016598639455782315,
      "loss": 1.4782,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016462585034013606,
      "loss": 1.6643,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016326530612244898,
      "loss": 1.5571,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016190476190476192,
      "loss": 1.6747,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016054421768707484,
      "loss": 1.3539,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015918367346938776,
      "loss": 2.0579,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015782312925170067,
      "loss": 1.5418,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015646258503401362,
      "loss": 1.8159,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015510204081632654,
      "loss": 1.6081,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015374149659863945,
      "loss": 1.5529,
      "step": 37
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015238095238095237,
      "loss": 1.5456,
      "step": 38
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001510204081632653,
      "loss": 2.1016,
      "step": 39
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014965986394557826,
      "loss": 1.4394,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014829931972789117,
      "loss": 1.4033,
      "step": 41
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001469387755102041,
      "loss": 1.5887,
      "step": 42
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000145578231292517,
      "loss": 1.8761,
      "step": 43
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014421768707482995,
      "loss": 1.67,
      "step": 44
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.8064,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014149659863945578,
      "loss": 1.4283,
      "step": 46
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001401360544217687,
      "loss": 1.8028,
      "step": 47
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013877551020408165,
      "loss": 1.5101,
      "step": 48
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013741496598639456,
      "loss": 1.7825,
      "step": 49
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013605442176870748,
      "loss": 1.3797,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001346938775510204,
      "loss": 1.7408,
      "step": 51
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.6008,
      "step": 52
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013197278911564626,
      "loss": 1.5121,
      "step": 53
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013061224489795917,
      "loss": 1.3599,
      "step": 54
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012925170068027212,
      "loss": 1.4465,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012789115646258506,
      "loss": 1.6332,
      "step": 56
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012653061224489798,
      "loss": 1.6305,
      "step": 57
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001251700680272109,
      "loss": 1.5599,
      "step": 58
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001238095238095238,
      "loss": 1.8265,
      "step": 59
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012244897959183676,
      "loss": 1.7149,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_train_epochs": 1,
  "save_steps": 5,
  "total_flos": 6638833090068480.0,
  "trial_name": null,
  "trial_params": null
}