{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.7267080745341614,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 4.998766400914329e-05,
      "loss": 0.6951,
      "step": 2
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.995066821070679e-05,
      "loss": 0.5589,
      "step": 4
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.9889049115077005e-05,
      "loss": 0.5485,
      "step": 6
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.980286753286195e-05,
      "loss": 0.5392,
      "step": 8
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 0.5347,
      "step": 10
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.9557181268217227e-05,
      "loss": 0.5261,
      "step": 12
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.939791904846869e-05,
      "loss": 0.5298,
      "step": 14
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.9214579028215776e-05,
      "loss": 0.536,
      "step": 16
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.900734214192358e-05,
      "loss": 0.5012,
      "step": 18
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.5342,
      "step": 20
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.852201922385564e-05,
      "loss": 0.5324,
      "step": 22
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.8244412147206284e-05,
      "loss": 0.4863,
      "step": 24
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.794386564209953e-05,
      "loss": 0.4774,
      "step": 26
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.762067631165049e-05,
      "loss": 0.4957,
      "step": 28
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.72751631047092e-05,
      "loss": 0.4531,
      "step": 30
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.72751631047092e-05,
      "loss": 0.5678,
      "step": 32
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.72751631047092e-05,
      "loss": 0.5456,
      "step": 34
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.690766700109659e-05,
      "loss": 0.541,
      "step": 36
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.65185506750986e-05,
      "loss": 0.5035,
      "step": 38
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.610819813755038e-05,
      "loss": 0.4901,
      "step": 40
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.567701435686404e-05,
      "loss": 0.3193,
      "step": 42
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.3019,
      "step": 44
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.4753875309392266e-05,
      "loss": 0.2869,
      "step": 46
    },
    {
      "epoch": 1.19,
      "learning_rate": 4.426283106939474e-05,
      "loss": 0.2998,
      "step": 48
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.375277674076149e-05,
      "loss": 0.2784,
      "step": 50
    },
    {
      "epoch": 1.29,
      "learning_rate": 4.3224215685535294e-05,
      "loss": 0.3551,
      "step": 52
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.3224,
      "step": 54
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.211367764821722e-05,
      "loss": 0.2901,
      "step": 56
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.1532796633091296e-05,
      "loss": 0.2776,
      "step": 58
    },
    {
      "epoch": 1.49,
      "learning_rate": 4.093559974371725e-05,
      "loss": 0.2993,
      "step": 60
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.0322676341324415e-05,
      "loss": 0.2978,
      "step": 62
    },
    {
      "epoch": 1.59,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.2895,
      "step": 64
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.905208444630327e-05,
      "loss": 0.3016,
      "step": 66
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.8395669874474915e-05,
      "loss": 0.2613,
      "step": 68
    },
    {
      "epoch": 1.74,
      "learning_rate": 3.7726035393759285e-05,
      "loss": 0.2993,
      "step": 70
    },
    {
      "epoch": 1.79,
      "learning_rate": 3.704384185254288e-05,
      "loss": 0.2853,
      "step": 72
    },
    {
      "epoch": 1.84,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.2578,
      "step": 74
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.564448228912682e-05,
      "loss": 0.2845,
      "step": 76
    },
    {
      "epoch": 1.94,
      "learning_rate": 3.4928697265869515e-05,
      "loss": 0.2931,
      "step": 78
    },
    {
      "epoch": 1.99,
      "learning_rate": 3.4203113817116957e-05,
      "loss": 0.3093,
      "step": 80
    },
    {
      "epoch": 2.04,
      "learning_rate": 3.346844800613229e-05,
      "loss": 0.1741,
      "step": 82
    },
    {
      "epoch": 2.09,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.1583,
      "step": 84
    },
    {
      "epoch": 2.14,
      "learning_rate": 3.1974777650980735e-05,
      "loss": 0.135,
      "step": 86
    },
    {
      "epoch": 2.19,
      "learning_rate": 3.121724717912138e-05,
      "loss": 0.1423,
      "step": 88
    },
    {
      "epoch": 2.24,
      "learning_rate": 3.045358103491357e-05,
      "loss": 0.1372,
      "step": 90
    },
    {
      "epoch": 2.29,
      "learning_rate": 2.9684532864643122e-05,
      "loss": 0.1249,
      "step": 92
    },
    {
      "epoch": 2.34,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 0.1222,
      "step": 94
    },
    {
      "epoch": 2.39,
      "learning_rate": 2.8133330839107608e-05,
      "loss": 0.1607,
      "step": 96
    },
    {
      "epoch": 2.43,
      "learning_rate": 2.7352707832962865e-05,
      "loss": 0.1427,
      "step": 98
    },
    {
      "epoch": 2.48,
      "learning_rate": 2.656976298823284e-05,
      "loss": 0.12,
      "step": 100
    },
    {
      "epoch": 2.53,
      "learning_rate": 2.578526897695321e-05,
      "loss": 0.1309,
      "step": 102
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.5e-05,
      "loss": 0.1332,
      "step": 104
    },
    {
      "epoch": 2.63,
      "learning_rate": 2.4214731023046793e-05,
      "loss": 0.1256,
      "step": 106
    },
    {
      "epoch": 2.68,
      "learning_rate": 2.3430237011767167e-05,
      "loss": 0.1258,
      "step": 108
    },
    {
      "epoch": 2.73,
      "learning_rate": 2.2647292167037144e-05,
      "loss": 0.1498,
      "step": 110
    },
    {
      "epoch": 2.78,
      "learning_rate": 2.186666916089239e-05,
      "loss": 0.1417,
      "step": 112
    },
    {
      "epoch": 2.83,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 0.1287,
      "step": 114
    },
    {
      "epoch": 2.88,
      "learning_rate": 2.031546713535688e-05,
      "loss": 0.1152,
      "step": 116
    },
    {
      "epoch": 2.93,
      "learning_rate": 1.9546418965086442e-05,
      "loss": 0.1352,
      "step": 118
    },
    {
      "epoch": 2.98,
      "learning_rate": 1.8782752820878634e-05,
      "loss": 0.1149,
      "step": 120
    },
    {
      "epoch": 3.03,
      "learning_rate": 1.802522234901927e-05,
      "loss": 0.0871,
      "step": 122
    },
    {
      "epoch": 3.08,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.0679,
      "step": 124
    },
    {
      "epoch": 3.13,
      "learning_rate": 1.6531551993867717e-05,
      "loss": 0.0616,
      "step": 126
    },
    {
      "epoch": 3.18,
      "learning_rate": 1.5796886182883053e-05,
      "loss": 0.0677,
      "step": 128
    },
    {
      "epoch": 3.23,
      "learning_rate": 1.5071302734130489e-05,
      "loss": 0.0636,
      "step": 130
    },
    {
      "epoch": 3.28,
      "learning_rate": 1.4355517710873184e-05,
      "loss": 0.0612,
      "step": 132
    },
    {
      "epoch": 3.33,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 0.0574,
      "step": 134
    },
    {
      "epoch": 3.38,
      "learning_rate": 1.2956158147457115e-05,
      "loss": 0.0467,
      "step": 136
    },
    {
      "epoch": 3.43,
      "learning_rate": 1.2273964606240718e-05,
      "loss": 0.0611,
      "step": 138
    },
    {
      "epoch": 3.48,
      "learning_rate": 1.1604330125525079e-05,
      "loss": 0.0655,
      "step": 140
    },
    {
      "epoch": 3.53,
      "learning_rate": 1.0947915553696742e-05,
      "loss": 0.069,
      "step": 142
    },
    {
      "epoch": 3.58,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.0573,
      "step": 144
    },
    {
      "epoch": 3.63,
      "learning_rate": 9.677323658675594e-06,
      "loss": 0.047,
      "step": 146
    },
    {
      "epoch": 3.68,
      "learning_rate": 9.064400256282757e-06,
      "loss": 0.0443,
      "step": 148
    },
    {
      "epoch": 3.73,
      "learning_rate": 8.467203366908707e-06,
      "loss": 0.0595,
      "step": 150
    }
  ],
  "logging_steps": 2,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 25,
  "total_flos": 2.021958544038822e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}