{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 39.388888888888886,
  "eval_steps": 500,
  "global_step": 280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.727,
      "step": 3
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.9644,
      "step": 6
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.5e-05,
      "loss": 1.8722,
      "step": 9
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.6195,
      "step": 12
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.8716,
      "step": 15
    },
    {
      "epoch": 2.22,
      "learning_rate": 5e-05,
      "loss": 1.5027,
      "step": 18
    },
    {
      "epoch": 2.39,
      "learning_rate": 5.833333333333334e-05,
      "loss": 1.6891,
      "step": 21
    },
    {
      "epoch": 3.17,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.5746,
      "step": 24
    },
    {
      "epoch": 3.33,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3677,
      "step": 27
    },
    {
      "epoch": 4.11,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.5316,
      "step": 30
    },
    {
      "epoch": 4.28,
      "learning_rate": 9.166666666666667e-05,
      "loss": 1.361,
      "step": 33
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.0001,
      "loss": 1.042,
      "step": 36
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.00010833333333333333,
      "loss": 1.2362,
      "step": 39
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.00011666666666666668,
      "loss": 1.1618,
      "step": 42
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.000125,
      "loss": 1.0433,
      "step": 45
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.0156,
      "step": 48
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.00014166666666666668,
      "loss": 0.794,
      "step": 51
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8204,
      "step": 54
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.00015833333333333332,
      "loss": 0.6787,
      "step": 57
    },
    {
      "epoch": 8.22,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.5017,
      "step": 60
    },
    {
      "epoch": 8.39,
      "learning_rate": 0.000175,
      "loss": 0.4836,
      "step": 63
    },
    {
      "epoch": 9.17,
      "learning_rate": 0.00018333333333333334,
      "loss": 0.3545,
      "step": 66
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.00019166666666666667,
      "loss": 0.5009,
      "step": 69
    },
    {
      "epoch": 10.11,
      "learning_rate": 0.0002,
      "loss": 0.3405,
      "step": 72
    },
    {
      "epoch": 10.28,
      "learning_rate": 0.0001990740740740741,
      "loss": 0.3549,
      "step": 75
    },
    {
      "epoch": 11.06,
      "learning_rate": 0.00019814814814814814,
      "loss": 0.2224,
      "step": 78
    },
    {
      "epoch": 11.22,
      "learning_rate": 0.00019722222222222225,
      "loss": 0.2505,
      "step": 81
    },
    {
      "epoch": 11.39,
      "learning_rate": 0.0001962962962962963,
      "loss": 0.2139,
      "step": 84
    },
    {
      "epoch": 12.17,
      "learning_rate": 0.00019537037037037038,
      "loss": 0.1912,
      "step": 87
    },
    {
      "epoch": 12.33,
      "learning_rate": 0.00019444444444444446,
      "loss": 0.1754,
      "step": 90
    },
    {
      "epoch": 13.11,
      "learning_rate": 0.0001935185185185185,
      "loss": 0.1442,
      "step": 93
    },
    {
      "epoch": 13.28,
      "learning_rate": 0.0001925925925925926,
      "loss": 0.1333,
      "step": 96
    },
    {
      "epoch": 14.06,
      "learning_rate": 0.00019166666666666667,
      "loss": 0.1117,
      "step": 99
    },
    {
      "epoch": 14.22,
      "learning_rate": 0.00019074074074074075,
      "loss": 0.0805,
      "step": 102
    },
    {
      "epoch": 14.39,
      "learning_rate": 0.00018981481481481483,
      "loss": 0.0944,
      "step": 105
    },
    {
      "epoch": 15.17,
      "learning_rate": 0.00018888888888888888,
      "loss": 0.0615,
      "step": 108
    },
    {
      "epoch": 15.33,
      "learning_rate": 0.00018796296296296296,
      "loss": 0.0458,
      "step": 111
    },
    {
      "epoch": 16.11,
      "learning_rate": 0.00018703703703703704,
      "loss": 0.0527,
      "step": 114
    },
    {
      "epoch": 16.28,
      "learning_rate": 0.00018611111111111112,
      "loss": 0.0355,
      "step": 117
    },
    {
      "epoch": 17.06,
      "learning_rate": 0.0001851851851851852,
      "loss": 0.0407,
      "step": 120
    },
    {
      "epoch": 17.22,
      "learning_rate": 0.00018425925925925926,
      "loss": 0.0283,
      "step": 123
    },
    {
      "epoch": 17.39,
      "learning_rate": 0.00018333333333333334,
      "loss": 0.0329,
      "step": 126
    },
    {
      "epoch": 18.17,
      "learning_rate": 0.00018240740740740742,
      "loss": 0.0239,
      "step": 129
    },
    {
      "epoch": 18.33,
      "learning_rate": 0.0001814814814814815,
      "loss": 0.0241,
      "step": 132
    },
    {
      "epoch": 19.11,
      "learning_rate": 0.00018055555555555557,
      "loss": 0.0138,
      "step": 135
    },
    {
      "epoch": 19.28,
      "learning_rate": 0.00017962962962962963,
      "loss": 0.0215,
      "step": 138
    },
    {
      "epoch": 20.06,
      "learning_rate": 0.0001787037037037037,
      "loss": 0.0198,
      "step": 141
    },
    {
      "epoch": 20.22,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.0164,
      "step": 144
    },
    {
      "epoch": 20.39,
      "learning_rate": 0.00017685185185185187,
      "loss": 0.0218,
      "step": 147
    },
    {
      "epoch": 21.17,
      "learning_rate": 0.00017592592592592595,
      "loss": 0.0139,
      "step": 150
    },
    {
      "epoch": 21.33,
      "learning_rate": 0.000175,
      "loss": 0.0191,
      "step": 153
    },
    {
      "epoch": 22.11,
      "learning_rate": 0.00017407407407407408,
      "loss": 0.0111,
      "step": 156
    },
    {
      "epoch": 22.28,
      "learning_rate": 0.00017314814814814816,
      "loss": 0.0134,
      "step": 159
    },
    {
      "epoch": 23.06,
      "learning_rate": 0.00017222222222222224,
      "loss": 0.0163,
      "step": 162
    },
    {
      "epoch": 23.22,
      "learning_rate": 0.00017129629629629632,
      "loss": 0.0097,
      "step": 165
    },
    {
      "epoch": 23.39,
      "learning_rate": 0.00017037037037037037,
      "loss": 0.0141,
      "step": 168
    },
    {
      "epoch": 24.17,
      "learning_rate": 0.00016944444444444445,
      "loss": 0.0122,
      "step": 171
    },
    {
      "epoch": 24.33,
      "learning_rate": 0.00016851851851851853,
      "loss": 0.0111,
      "step": 174
    },
    {
      "epoch": 25.11,
      "learning_rate": 0.00016759259259259258,
      "loss": 0.0105,
      "step": 177
    },
    {
      "epoch": 25.28,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.0087,
      "step": 180
    },
    {
      "epoch": 26.06,
      "learning_rate": 0.00016574074074074074,
      "loss": 0.0097,
      "step": 183
    },
    {
      "epoch": 26.22,
      "learning_rate": 0.00016481481481481482,
      "loss": 0.0099,
      "step": 186
    },
    {
      "epoch": 26.39,
      "learning_rate": 0.0001638888888888889,
      "loss": 0.009,
      "step": 189
    },
    {
      "epoch": 27.17,
      "learning_rate": 0.00016296296296296295,
      "loss": 0.0097,
      "step": 192
    },
    {
      "epoch": 27.33,
      "learning_rate": 0.00016203703703703706,
      "loss": 0.008,
      "step": 195
    },
    {
      "epoch": 28.11,
      "learning_rate": 0.0001611111111111111,
      "loss": 0.008,
      "step": 198
    },
    {
      "epoch": 28.28,
      "learning_rate": 0.0001601851851851852,
      "loss": 0.0055,
      "step": 201
    },
    {
      "epoch": 29.06,
      "learning_rate": 0.00015925925925925927,
      "loss": 0.0094,
      "step": 204
    },
    {
      "epoch": 29.22,
      "learning_rate": 0.00015833333333333332,
      "loss": 0.0052,
      "step": 207
    },
    {
      "epoch": 29.39,
      "learning_rate": 0.00015740740740740743,
      "loss": 0.0072,
      "step": 210
    },
    {
      "epoch": 30.17,
      "learning_rate": 0.00015648148148148148,
      "loss": 0.0066,
      "step": 213
    },
    {
      "epoch": 30.33,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.006,
      "step": 216
    },
    {
      "epoch": 31.11,
      "learning_rate": 0.00015462962962962964,
      "loss": 0.0078,
      "step": 219
    },
    {
      "epoch": 31.28,
      "learning_rate": 0.0001537037037037037,
      "loss": 0.0051,
      "step": 222
    },
    {
      "epoch": 32.06,
      "learning_rate": 0.00015277777777777777,
      "loss": 0.0042,
      "step": 225
    },
    {
      "epoch": 32.22,
      "learning_rate": 0.00015185185185185185,
      "loss": 0.0058,
      "step": 228
    },
    {
      "epoch": 32.39,
      "learning_rate": 0.00015092592592592593,
      "loss": 0.0059,
      "step": 231
    },
    {
      "epoch": 33.17,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0065,
      "step": 234
    },
    {
      "epoch": 33.33,
      "learning_rate": 0.00014907407407407407,
      "loss": 0.0047,
      "step": 237
    },
    {
      "epoch": 34.11,
      "learning_rate": 0.00014814814814814815,
      "loss": 0.0061,
      "step": 240
    },
    {
      "epoch": 34.28,
      "learning_rate": 0.00014722222222222223,
      "loss": 0.0031,
      "step": 243
    },
    {
      "epoch": 35.06,
      "learning_rate": 0.0001462962962962963,
      "loss": 0.0066,
      "step": 246
    },
    {
      "epoch": 35.22,
      "learning_rate": 0.00014537037037037039,
      "loss": 0.003,
      "step": 249
    },
    {
      "epoch": 35.39,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.0054,
      "step": 252
    },
    {
      "epoch": 36.17,
      "learning_rate": 0.00014351851851851852,
      "loss": 0.0029,
      "step": 255
    },
    {
      "epoch": 36.33,
      "learning_rate": 0.0001425925925925926,
      "loss": 0.0063,
      "step": 258
    },
    {
      "epoch": 37.11,
      "learning_rate": 0.00014166666666666668,
      "loss": 0.0039,
      "step": 261
    },
    {
      "epoch": 37.28,
      "learning_rate": 0.00014074074074074076,
      "loss": 0.0043,
      "step": 264
    },
    {
      "epoch": 38.06,
      "learning_rate": 0.0001398148148148148,
      "loss": 0.0063,
      "step": 267
    },
    {
      "epoch": 38.22,
      "learning_rate": 0.0001388888888888889,
      "loss": 0.003,
      "step": 270
    },
    {
      "epoch": 38.39,
      "learning_rate": 0.00013796296296296297,
      "loss": 0.005,
      "step": 273
    },
    {
      "epoch": 39.17,
      "learning_rate": 0.00013703703703703705,
      "loss": 0.005,
      "step": 276
    },
    {
      "epoch": 39.33,
      "learning_rate": 0.00013611111111111113,
      "loss": 0.0041,
      "step": 279
    }
  ],
  "logging_steps": 3,
  "max_steps": 720,
  "num_train_epochs": 40,
  "save_steps": 500,
  "total_flos": 2.27623670120448e+16,
  "trial_name": null,
  "trial_params": null
}