{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.558846453624318,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.9726,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000197979797979798,
      "loss": 1.3188,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019595959595959596,
      "loss": 1.1313,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019393939393939395,
      "loss": 1.0928,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019191919191919191,
      "loss": 1.0552,
      "step": 25
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001898989898989899,
      "loss": 1.0644,
      "step": 30
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001878787878787879,
      "loss": 1.0013,
      "step": 35
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00018585858585858586,
      "loss": 1.0065,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018383838383838384,
      "loss": 1.0054,
      "step": 45
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9734,
      "step": 50
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001797979797979798,
      "loss": 0.9654,
      "step": 55
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.9673,
      "step": 60
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00017575757575757578,
      "loss": 0.9584,
      "step": 65
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00017373737373737377,
      "loss": 0.9694,
      "step": 70
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017171717171717173,
      "loss": 0.9773,
      "step": 75
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00016969696969696972,
      "loss": 0.9531,
      "step": 80
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00016767676767676768,
      "loss": 0.9775,
      "step": 85
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016565656565656567,
      "loss": 0.9261,
      "step": 90
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9715,
      "step": 95
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016161616161616162,
      "loss": 0.9392,
      "step": 100
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001595959595959596,
      "loss": 0.9722,
      "step": 105
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015757575757575757,
      "loss": 0.9546,
      "step": 110
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.9177,
      "step": 115
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015353535353535353,
      "loss": 0.8817,
      "step": 120
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015151515151515152,
      "loss": 0.9303,
      "step": 125
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001494949494949495,
      "loss": 0.9237,
      "step": 130
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014747474747474747,
      "loss": 0.9136,
      "step": 135
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.9011,
      "step": 140
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00014343434343434342,
      "loss": 0.9071,
      "step": 145
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001414141414141414,
      "loss": 0.9315,
      "step": 150
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001393939393939394,
      "loss": 0.8887,
      "step": 155
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001373737373737374,
      "loss": 0.9104,
      "step": 160
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00013535353535353538,
      "loss": 0.9178,
      "step": 165
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.9236,
      "step": 170
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00013131313131313133,
      "loss": 0.908,
      "step": 175
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00012929292929292932,
      "loss": 0.9268,
      "step": 180
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.8726,
      "step": 185
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00012525252525252527,
      "loss": 0.9305,
      "step": 190
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00012323232323232323,
      "loss": 0.9196,
      "step": 195
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00012121212121212122,
      "loss": 0.8803,
      "step": 200
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00011919191919191919,
      "loss": 0.8714,
      "step": 205
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00011717171717171717,
      "loss": 0.903,
      "step": 210
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00011515151515151516,
      "loss": 0.8812,
      "step": 215
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00011313131313131313,
      "loss": 0.8887,
      "step": 220
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.8708,
      "step": 225
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.8859,
      "step": 230
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00010707070707070708,
      "loss": 0.922,
      "step": 235
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00010505050505050507,
      "loss": 0.8849,
      "step": 240
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00010303030303030303,
      "loss": 0.8729,
      "step": 245
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00010101010101010102,
      "loss": 0.8851,
      "step": 250
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.8989898989899e-05,
      "loss": 0.9178,
      "step": 255
    },
    {
      "epoch": 0.81,
      "learning_rate": 9.696969696969698e-05,
      "loss": 0.8472,
      "step": 260
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.494949494949495e-05,
      "loss": 0.8691,
      "step": 265
    },
    {
      "epoch": 0.84,
      "learning_rate": 9.292929292929293e-05,
      "loss": 0.8663,
      "step": 270
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.8658,
      "step": 275
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.8641,
      "step": 280
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.686868686868688e-05,
      "loss": 0.8331,
      "step": 285
    },
    {
      "epoch": 0.9,
      "learning_rate": 8.484848484848486e-05,
      "loss": 0.8843,
      "step": 290
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.282828282828283e-05,
      "loss": 0.8753,
      "step": 295
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.080808080808081e-05,
      "loss": 0.8589,
      "step": 300
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.878787878787879e-05,
      "loss": 0.8395,
      "step": 305
    },
    {
      "epoch": 0.97,
      "learning_rate": 7.676767676767676e-05,
      "loss": 0.852,
      "step": 310
    },
    {
      "epoch": 0.98,
      "learning_rate": 7.474747474747475e-05,
      "loss": 0.8413,
      "step": 315
    },
    {
      "epoch": 1.0,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.866,
      "step": 320
    },
    {
      "epoch": 1.01,
      "learning_rate": 7.07070707070707e-05,
      "loss": 0.8244,
      "step": 325
    },
    {
      "epoch": 1.03,
      "learning_rate": 6.86868686868687e-05,
      "loss": 0.79,
      "step": 330
    },
    {
      "epoch": 1.04,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.7924,
      "step": 335
    },
    {
      "epoch": 1.06,
      "learning_rate": 6.464646464646466e-05,
      "loss": 0.8056,
      "step": 340
    },
    {
      "epoch": 1.08,
      "learning_rate": 6.262626262626264e-05,
      "loss": 0.7935,
      "step": 345
    },
    {
      "epoch": 1.09,
      "learning_rate": 6.060606060606061e-05,
      "loss": 0.8212,
      "step": 350
    },
    {
      "epoch": 1.11,
      "learning_rate": 5.858585858585859e-05,
      "loss": 0.7993,
      "step": 355
    },
    {
      "epoch": 1.12,
      "learning_rate": 5.6565656565656563e-05,
      "loss": 0.8074,
      "step": 360
    },
    {
      "epoch": 1.14,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.8426,
      "step": 365
    },
    {
      "epoch": 1.15,
      "learning_rate": 5.2525252525252536e-05,
      "loss": 0.796,
      "step": 370
    },
    {
      "epoch": 1.17,
      "learning_rate": 5.050505050505051e-05,
      "loss": 0.783,
      "step": 375
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.848484848484849e-05,
      "loss": 0.801,
      "step": 380
    },
    {
      "epoch": 1.2,
      "learning_rate": 4.6464646464646464e-05,
      "loss": 0.8028,
      "step": 385
    },
    {
      "epoch": 1.22,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.7935,
      "step": 390
    },
    {
      "epoch": 1.23,
      "learning_rate": 4.242424242424243e-05,
      "loss": 0.7957,
      "step": 395
    },
    {
      "epoch": 1.25,
      "learning_rate": 4.0404040404040405e-05,
      "loss": 0.8139,
      "step": 400
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.838383838383838e-05,
      "loss": 0.7718,
      "step": 405
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.8142,
      "step": 410
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.434343434343435e-05,
      "loss": 0.8083,
      "step": 415
    },
    {
      "epoch": 1.31,
      "learning_rate": 3.232323232323233e-05,
      "loss": 0.7984,
      "step": 420
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 0.7968,
      "step": 425
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.8282828282828282e-05,
      "loss": 0.7945,
      "step": 430
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.6262626262626268e-05,
      "loss": 0.803,
      "step": 435
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.4242424242424244e-05,
      "loss": 0.8167,
      "step": 440
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.7801,
      "step": 445
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.0202020202020203e-05,
      "loss": 0.8059,
      "step": 450
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.7927,
      "step": 455
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.6161616161616165e-05,
      "loss": 0.7962,
      "step": 460
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.4141414141414141e-05,
      "loss": 0.7893,
      "step": 465
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 0.7965,
      "step": 470
    },
    {
      "epoch": 1.48,
      "learning_rate": 1.0101010101010101e-05,
      "loss": 0.7817,
      "step": 475
    },
    {
      "epoch": 1.5,
      "learning_rate": 8.080808080808082e-06,
      "loss": 0.8159,
      "step": 480
    },
    {
      "epoch": 1.51,
      "learning_rate": 6.060606060606061e-06,
      "loss": 0.7822,
      "step": 485
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.040404040404041e-06,
      "loss": 0.7937,
      "step": 490
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.0202020202020206e-06,
      "loss": 0.8044,
      "step": 495
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0,
      "loss": 0.8113,
      "step": 500
    },
    {
      "epoch": 1.56,
      "step": 500,
      "total_flos": 1.3764276825690931e+17,
      "train_loss": 0.8930109763145446,
      "train_runtime": 25972.5576,
      "train_samples_per_second": 1.232,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 5,
  "max_steps": 500,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 1.3764276825690931e+17,
  "trial_name": null,
  "trial_params": null
}