{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 3000,
  "global_step": 2700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.00019925925925925927,
      "loss": 2.1757,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019851851851851853,
      "loss": 1.9027,
      "step": 20
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019777777777777778,
      "loss": 1.7624,
      "step": 30
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019703703703703704,
      "loss": 1.6008,
      "step": 40
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001962962962962963,
      "loss": 1.3749,
      "step": 50
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019555555555555556,
      "loss": 1.494,
      "step": 60
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019481481481481482,
      "loss": 1.3449,
      "step": 70
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019407407407407408,
      "loss": 1.2193,
      "step": 80
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019333333333333333,
      "loss": 1.3163,
      "step": 90
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001925925925925926,
      "loss": 1.1955,
      "step": 100
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019185185185185185,
      "loss": 1.3643,
      "step": 110
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019111111111111114,
      "loss": 1.3792,
      "step": 120
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019037037037037037,
      "loss": 1.1842,
      "step": 130
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018962962962962965,
      "loss": 1.1366,
      "step": 140
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018888888888888888,
      "loss": 1.2302,
      "step": 150
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018814814814814817,
      "loss": 1.1672,
      "step": 160
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001874074074074074,
      "loss": 1.1124,
      "step": 170
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001866666666666667,
      "loss": 0.9382,
      "step": 180
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00018592592592592592,
      "loss": 0.9567,
      "step": 190
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001851851851851852,
      "loss": 0.9075,
      "step": 200
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00018444444444444446,
      "loss": 0.9064,
      "step": 210
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018370370370370372,
      "loss": 1.0113,
      "step": 220
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018296296296296298,
      "loss": 0.863,
      "step": 230
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018222222222222224,
      "loss": 0.83,
      "step": 240
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001814814814814815,
      "loss": 0.9212,
      "step": 250
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018074074074074075,
      "loss": 0.8929,
      "step": 260
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018,
      "loss": 1.09,
      "step": 270
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00017925925925925927,
      "loss": 0.7487,
      "step": 280
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00017851851851851853,
      "loss": 0.5648,
      "step": 290
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.8104,
      "step": 300
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017703703703703704,
      "loss": 0.8599,
      "step": 310
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001762962962962963,
      "loss": 0.6207,
      "step": 320
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017555555555555556,
      "loss": 0.6954,
      "step": 330
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017481481481481482,
      "loss": 0.6896,
      "step": 340
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00017407407407407408,
      "loss": 0.6426,
      "step": 350
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00017333333333333334,
      "loss": 0.6755,
      "step": 360
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001725925925925926,
      "loss": 0.5689,
      "step": 370
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00017185185185185185,
      "loss": 0.8554,
      "step": 380
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001711111111111111,
      "loss": 0.5816,
      "step": 390
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00017037037037037037,
      "loss": 0.71,
      "step": 400
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016962962962962963,
      "loss": 0.6038,
      "step": 410
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016888888888888889,
      "loss": 0.5442,
      "step": 420
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00016814814814814817,
      "loss": 0.6354,
      "step": 430
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001674074074074074,
      "loss": 0.8464,
      "step": 440
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.8248,
      "step": 450
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00016592592592592592,
      "loss": 0.6434,
      "step": 460
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001651851851851852,
      "loss": 0.6549,
      "step": 470
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00016444444444444444,
      "loss": 0.5651,
      "step": 480
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00016370370370370372,
      "loss": 0.4748,
      "step": 490
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00016296296296296295,
      "loss": 0.6189,
      "step": 500
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00016222222222222224,
      "loss": 0.4894,
      "step": 510
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001614814814814815,
      "loss": 0.6632,
      "step": 520
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00016074074074074075,
      "loss": 0.5738,
      "step": 530
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00016,
      "loss": 0.5349,
      "step": 540
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00015925925925925927,
      "loss": 0.3067,
      "step": 550
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00015851851851851853,
      "loss": 0.3444,
      "step": 560
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001577777777777778,
      "loss": 0.3304,
      "step": 570
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00015703703703703705,
      "loss": 0.5832,
      "step": 580
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0001562962962962963,
      "loss": 0.5208,
      "step": 590
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.3367,
      "step": 600
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00015481481481481482,
      "loss": 0.3564,
      "step": 610
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00015407407407407408,
      "loss": 0.5481,
      "step": 620
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00015333333333333334,
      "loss": 0.3271,
      "step": 630
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0001525925925925926,
      "loss": 0.3379,
      "step": 640
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00015185185185185185,
      "loss": 0.4362,
      "step": 650
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0001511111111111111,
      "loss": 0.4654,
      "step": 660
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00015037037037037037,
      "loss": 0.4666,
      "step": 670
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00014962962962962963,
      "loss": 0.2851,
      "step": 680
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0001488888888888889,
      "loss": 0.3229,
      "step": 690
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00014814814814814815,
      "loss": 0.4301,
      "step": 700
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0001474074074074074,
      "loss": 0.22,
      "step": 710
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00014666666666666666,
      "loss": 0.3819,
      "step": 720
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00014592592592592592,
      "loss": 0.4382,
      "step": 730
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0001451851851851852,
      "loss": 0.3389,
      "step": 740
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.392,
      "step": 750
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00014370370370370372,
      "loss": 0.5607,
      "step": 760
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00014296296296296295,
      "loss": 0.2621,
      "step": 770
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00014222222222222224,
      "loss": 0.4369,
      "step": 780
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00014148148148148147,
      "loss": 0.3211,
      "step": 790
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00014074074074074076,
      "loss": 0.3269,
      "step": 800
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00014,
      "loss": 0.2869,
      "step": 810
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.00013925925925925927,
      "loss": 0.2943,
      "step": 820
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0001385185185185185,
      "loss": 0.2445,
      "step": 830
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0001377777777777778,
      "loss": 0.1964,
      "step": 840
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00013703703703703705,
      "loss": 0.1399,
      "step": 850
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0001362962962962963,
      "loss": 0.1535,
      "step": 860
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.00013555555555555556,
      "loss": 0.2293,
      "step": 870
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.00013481481481481482,
      "loss": 0.2467,
      "step": 880
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.00013407407407407408,
      "loss": 0.2009,
      "step": 890
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.2182,
      "step": 900
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.0001325925925925926,
      "loss": 0.0813,
      "step": 910
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.00013185185185185186,
      "loss": 0.1104,
      "step": 920
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.00013111111111111111,
      "loss": 0.2386,
      "step": 930
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0001303703703703704,
      "loss": 0.228,
      "step": 940
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.00012962962962962963,
      "loss": 0.2143,
      "step": 950
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.00012888888888888892,
      "loss": 0.1438,
      "step": 960
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.00012814814814814815,
      "loss": 0.1099,
      "step": 970
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0001274074074074074,
      "loss": 0.1817,
      "step": 980
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.00012666666666666666,
      "loss": 0.1819,
      "step": 990
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.00012592592592592592,
      "loss": 0.0993,
      "step": 1000
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.00012518518518518518,
      "loss": 0.1726,
      "step": 1010
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.00012444444444444444,
      "loss": 0.0822,
      "step": 1020
    },
    {
      "epoch": 3.81,
      "learning_rate": 0.0001237037037037037,
      "loss": 0.158,
      "step": 1030
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.00012296296296296296,
      "loss": 0.1716,
      "step": 1040
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.00012222222222222224,
      "loss": 0.1157,
      "step": 1050
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.00012148148148148149,
      "loss": 0.1985,
      "step": 1060
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.00012074074074074076,
      "loss": 0.1466,
      "step": 1070
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00012,
      "loss": 0.1043,
      "step": 1080
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.00011925925925925927,
      "loss": 0.0642,
      "step": 1090
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.00011851851851851852,
      "loss": 0.0815,
      "step": 1100
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00011777777777777779,
      "loss": 0.1572,
      "step": 1110
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.00011703703703703704,
      "loss": 0.1935,
      "step": 1120
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.00011629629629629631,
      "loss": 0.183,
      "step": 1130
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.00011555555555555555,
      "loss": 0.0969,
      "step": 1140
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.00011481481481481482,
      "loss": 0.1347,
      "step": 1150
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.00011407407407407408,
      "loss": 0.0702,
      "step": 1160
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.00011333333333333334,
      "loss": 0.0834,
      "step": 1170
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0001125925925925926,
      "loss": 0.144,
      "step": 1180
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.00011185185185185186,
      "loss": 0.2074,
      "step": 1190
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.1733,
      "step": 1200
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.00011037037037037037,
      "loss": 0.1018,
      "step": 1210
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.00010962962962962963,
      "loss": 0.1497,
      "step": 1220
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.00010888888888888889,
      "loss": 0.1547,
      "step": 1230
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.00010814814814814815,
      "loss": 0.0763,
      "step": 1240
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.00010740740740740742,
      "loss": 0.0262,
      "step": 1250
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.00010666666666666667,
      "loss": 0.0448,
      "step": 1260
    },
    {
      "epoch": 4.7,
      "learning_rate": 0.00010592592592592594,
      "loss": 0.1568,
      "step": 1270
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.00010518518518518518,
      "loss": 0.0858,
      "step": 1280
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.00010444444444444445,
      "loss": 0.0615,
      "step": 1290
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0001037037037037037,
      "loss": 0.0791,
      "step": 1300
    },
    {
      "epoch": 4.85,
      "learning_rate": 0.00010296296296296297,
      "loss": 0.1502,
      "step": 1310
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.00010222222222222222,
      "loss": 0.0945,
      "step": 1320
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.00010148148148148149,
      "loss": 0.0217,
      "step": 1330
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.00010074074074074073,
      "loss": 0.0726,
      "step": 1340
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0001,
      "loss": 0.0872,
      "step": 1350
    },
    {
      "epoch": 5.04,
      "learning_rate": 9.925925925925926e-05,
      "loss": 0.0646,
      "step": 1360
    },
    {
      "epoch": 5.07,
      "learning_rate": 9.851851851851852e-05,
      "loss": 0.0929,
      "step": 1370
    },
    {
      "epoch": 5.11,
      "learning_rate": 9.777777777777778e-05,
      "loss": 0.0149,
      "step": 1380
    },
    {
      "epoch": 5.15,
      "learning_rate": 9.703703703703704e-05,
      "loss": 0.0757,
      "step": 1390
    },
    {
      "epoch": 5.19,
      "learning_rate": 9.62962962962963e-05,
      "loss": 0.021,
      "step": 1400
    },
    {
      "epoch": 5.22,
      "learning_rate": 9.555555555555557e-05,
      "loss": 0.0265,
      "step": 1410
    },
    {
      "epoch": 5.26,
      "learning_rate": 9.481481481481483e-05,
      "loss": 0.0923,
      "step": 1420
    },
    {
      "epoch": 5.3,
      "learning_rate": 9.407407407407408e-05,
      "loss": 0.0344,
      "step": 1430
    },
    {
      "epoch": 5.33,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.0725,
      "step": 1440
    },
    {
      "epoch": 5.37,
      "learning_rate": 9.25925925925926e-05,
      "loss": 0.0452,
      "step": 1450
    },
    {
      "epoch": 5.41,
      "learning_rate": 9.185185185185186e-05,
      "loss": 0.0904,
      "step": 1460
    },
    {
      "epoch": 5.44,
      "learning_rate": 9.111111111111112e-05,
      "loss": 0.0833,
      "step": 1470
    },
    {
      "epoch": 5.48,
      "learning_rate": 9.037037037037038e-05,
      "loss": 0.0235,
      "step": 1480
    },
    {
      "epoch": 5.52,
      "learning_rate": 8.962962962962963e-05,
      "loss": 0.0355,
      "step": 1490
    },
    {
      "epoch": 5.56,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.0139,
      "step": 1500
    },
    {
      "epoch": 5.59,
      "learning_rate": 8.814814814814815e-05,
      "loss": 0.0454,
      "step": 1510
    },
    {
      "epoch": 5.63,
      "learning_rate": 8.740740740740741e-05,
      "loss": 0.0556,
      "step": 1520
    },
    {
      "epoch": 5.67,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.0757,
      "step": 1530
    },
    {
      "epoch": 5.7,
      "learning_rate": 8.592592592592593e-05,
      "loss": 0.0382,
      "step": 1540
    },
    {
      "epoch": 5.74,
      "learning_rate": 8.518518518518518e-05,
      "loss": 0.0211,
      "step": 1550
    },
    {
      "epoch": 5.78,
      "learning_rate": 8.444444444444444e-05,
      "loss": 0.0542,
      "step": 1560
    },
    {
      "epoch": 5.81,
      "learning_rate": 8.37037037037037e-05,
      "loss": 0.0081,
      "step": 1570
    },
    {
      "epoch": 5.85,
      "learning_rate": 8.296296296296296e-05,
      "loss": 0.0543,
      "step": 1580
    },
    {
      "epoch": 5.89,
      "learning_rate": 8.222222222222222e-05,
      "loss": 0.0325,
      "step": 1590
    },
    {
      "epoch": 5.93,
      "learning_rate": 8.148148148148148e-05,
      "loss": 0.057,
      "step": 1600
    },
    {
      "epoch": 5.96,
      "learning_rate": 8.074074074074075e-05,
      "loss": 0.0534,
      "step": 1610
    },
    {
      "epoch": 6.0,
      "learning_rate": 8e-05,
      "loss": 0.057,
      "step": 1620
    },
    {
      "epoch": 6.04,
      "learning_rate": 7.925925925925926e-05,
      "loss": 0.0262,
      "step": 1630
    },
    {
      "epoch": 6.07,
      "learning_rate": 7.851851851851852e-05,
      "loss": 0.0527,
      "step": 1640
    },
    {
      "epoch": 6.11,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.0426,
      "step": 1650
    },
    {
      "epoch": 6.15,
      "learning_rate": 7.703703703703704e-05,
      "loss": 0.017,
      "step": 1660
    },
    {
      "epoch": 6.19,
      "learning_rate": 7.62962962962963e-05,
      "loss": 0.0428,
      "step": 1670
    },
    {
      "epoch": 6.22,
      "learning_rate": 7.555555555555556e-05,
      "loss": 0.0371,
      "step": 1680
    },
    {
      "epoch": 6.26,
      "learning_rate": 7.481481481481481e-05,
      "loss": 0.0119,
      "step": 1690
    },
    {
      "epoch": 6.3,
      "learning_rate": 7.407407407407407e-05,
      "loss": 0.0597,
      "step": 1700
    },
    {
      "epoch": 6.33,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.008,
      "step": 1710
    },
    {
      "epoch": 6.37,
      "learning_rate": 7.25925925925926e-05,
      "loss": 0.0173,
      "step": 1720
    },
    {
      "epoch": 6.41,
      "learning_rate": 7.185185185185186e-05,
      "loss": 0.0409,
      "step": 1730
    },
    {
      "epoch": 6.44,
      "learning_rate": 7.111111111111112e-05,
      "loss": 0.0346,
      "step": 1740
    },
    {
      "epoch": 6.48,
      "learning_rate": 7.037037037037038e-05,
      "loss": 0.0053,
      "step": 1750
    },
    {
      "epoch": 6.52,
      "learning_rate": 6.962962962962964e-05,
      "loss": 0.0202,
      "step": 1760
    },
    {
      "epoch": 6.56,
      "learning_rate": 6.88888888888889e-05,
      "loss": 0.0149,
      "step": 1770
    },
    {
      "epoch": 6.59,
      "learning_rate": 6.814814814814815e-05,
      "loss": 0.011,
      "step": 1780
    },
    {
      "epoch": 6.63,
      "learning_rate": 6.740740740740741e-05,
      "loss": 0.0407,
      "step": 1790
    },
    {
      "epoch": 6.67,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.022,
      "step": 1800
    },
    {
      "epoch": 6.7,
      "learning_rate": 6.592592592592593e-05,
      "loss": 0.0375,
      "step": 1810
    },
    {
      "epoch": 6.74,
      "learning_rate": 6.51851851851852e-05,
      "loss": 0.0043,
      "step": 1820
    },
    {
      "epoch": 6.78,
      "learning_rate": 6.444444444444446e-05,
      "loss": 0.0057,
      "step": 1830
    },
    {
      "epoch": 6.81,
      "learning_rate": 6.37037037037037e-05,
      "loss": 0.0176,
      "step": 1840
    },
    {
      "epoch": 6.85,
      "learning_rate": 6.296296296296296e-05,
      "loss": 0.0042,
      "step": 1850
    },
    {
      "epoch": 6.89,
      "learning_rate": 6.222222222222222e-05,
      "loss": 0.0059,
      "step": 1860
    },
    {
      "epoch": 6.93,
      "learning_rate": 6.148148148148148e-05,
      "loss": 0.0126,
      "step": 1870
    },
    {
      "epoch": 6.96,
      "learning_rate": 6.074074074074074e-05,
      "loss": 0.0049,
      "step": 1880
    },
    {
      "epoch": 7.0,
      "learning_rate": 6e-05,
      "loss": 0.0196,
      "step": 1890
    },
    {
      "epoch": 7.04,
      "learning_rate": 5.925925925925926e-05,
      "loss": 0.0064,
      "step": 1900
    },
    {
      "epoch": 7.07,
      "learning_rate": 5.851851851851852e-05,
      "loss": 0.006,
      "step": 1910
    },
    {
      "epoch": 7.11,
      "learning_rate": 5.7777777777777776e-05,
      "loss": 0.004,
      "step": 1920
    },
    {
      "epoch": 7.15,
      "learning_rate": 5.703703703703704e-05,
      "loss": 0.0075,
      "step": 1930
    },
    {
      "epoch": 7.19,
      "learning_rate": 5.62962962962963e-05,
      "loss": 0.059,
      "step": 1940
    },
    {
      "epoch": 7.22,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.004,
      "step": 1950
    },
    {
      "epoch": 7.26,
      "learning_rate": 5.4814814814814817e-05,
      "loss": 0.0039,
      "step": 1960
    },
    {
      "epoch": 7.3,
      "learning_rate": 5.4074074074074075e-05,
      "loss": 0.0078,
      "step": 1970
    },
    {
      "epoch": 7.33,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.0046,
      "step": 1980
    },
    {
      "epoch": 7.37,
      "learning_rate": 5.259259259259259e-05,
      "loss": 0.0135,
      "step": 1990
    },
    {
      "epoch": 7.41,
      "learning_rate": 5.185185185185185e-05,
      "loss": 0.0208,
      "step": 2000
    },
    {
      "epoch": 7.44,
      "learning_rate": 5.111111111111111e-05,
      "loss": 0.0124,
      "step": 2010
    },
    {
      "epoch": 7.48,
      "learning_rate": 5.0370370370370366e-05,
      "loss": 0.0039,
      "step": 2020
    },
    {
      "epoch": 7.52,
      "learning_rate": 4.962962962962963e-05,
      "loss": 0.0037,
      "step": 2030
    },
    {
      "epoch": 7.56,
      "learning_rate": 4.888888888888889e-05,
      "loss": 0.0042,
      "step": 2040
    },
    {
      "epoch": 7.59,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.0032,
      "step": 2050
    },
    {
      "epoch": 7.63,
      "learning_rate": 4.740740740740741e-05,
      "loss": 0.0037,
      "step": 2060
    },
    {
      "epoch": 7.67,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.0035,
      "step": 2070
    },
    {
      "epoch": 7.7,
      "learning_rate": 4.592592592592593e-05,
      "loss": 0.0033,
      "step": 2080
    },
    {
      "epoch": 7.74,
      "learning_rate": 4.518518518518519e-05,
      "loss": 0.0164,
      "step": 2090
    },
    {
      "epoch": 7.78,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.0036,
      "step": 2100
    },
    {
      "epoch": 7.81,
      "learning_rate": 4.3703703703703705e-05,
      "loss": 0.0033,
      "step": 2110
    },
    {
      "epoch": 7.85,
      "learning_rate": 4.296296296296296e-05,
      "loss": 0.0037,
      "step": 2120
    },
    {
      "epoch": 7.89,
      "learning_rate": 4.222222222222222e-05,
      "loss": 0.0321,
      "step": 2130
    },
    {
      "epoch": 7.93,
      "learning_rate": 4.148148148148148e-05,
      "loss": 0.0034,
      "step": 2140
    },
    {
      "epoch": 7.96,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.0034,
      "step": 2150
    },
    {
      "epoch": 8.0,
      "learning_rate": 4e-05,
      "loss": 0.013,
      "step": 2160
    },
    {
      "epoch": 8.04,
      "learning_rate": 3.925925925925926e-05,
      "loss": 0.0088,
      "step": 2170
    },
    {
      "epoch": 8.07,
      "learning_rate": 3.851851851851852e-05,
      "loss": 0.0033,
      "step": 2180
    },
    {
      "epoch": 8.11,
      "learning_rate": 3.777777777777778e-05,
      "loss": 0.0197,
      "step": 2190
    },
    {
      "epoch": 8.15,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.0033,
      "step": 2200
    },
    {
      "epoch": 8.19,
      "learning_rate": 3.62962962962963e-05,
      "loss": 0.0031,
      "step": 2210
    },
    {
      "epoch": 8.22,
      "learning_rate": 3.555555555555556e-05,
      "loss": 0.0031,
      "step": 2220
    },
    {
      "epoch": 8.26,
      "learning_rate": 3.481481481481482e-05,
      "loss": 0.003,
      "step": 2230
    },
    {
      "epoch": 8.3,
      "learning_rate": 3.4074074074074077e-05,
      "loss": 0.003,
      "step": 2240
    },
    {
      "epoch": 8.33,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0034,
      "step": 2250
    },
    {
      "epoch": 8.37,
      "learning_rate": 3.25925925925926e-05,
      "loss": 0.0135,
      "step": 2260
    },
    {
      "epoch": 8.41,
      "learning_rate": 3.185185185185185e-05,
      "loss": 0.0038,
      "step": 2270
    },
    {
      "epoch": 8.44,
      "learning_rate": 3.111111111111111e-05,
      "loss": 0.003,
      "step": 2280
    },
    {
      "epoch": 8.48,
      "learning_rate": 3.037037037037037e-05,
      "loss": 0.0028,
      "step": 2290
    },
    {
      "epoch": 8.52,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.0033,
      "step": 2300
    },
    {
      "epoch": 8.56,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 0.0028,
      "step": 2310
    },
    {
      "epoch": 8.59,
      "learning_rate": 2.814814814814815e-05,
      "loss": 0.0085,
      "step": 2320
    },
    {
      "epoch": 8.63,
      "learning_rate": 2.7407407407407408e-05,
      "loss": 0.0028,
      "step": 2330
    },
    {
      "epoch": 8.67,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.0134,
      "step": 2340
    },
    {
      "epoch": 8.7,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.0029,
      "step": 2350
    },
    {
      "epoch": 8.74,
      "learning_rate": 2.5185185185185183e-05,
      "loss": 0.003,
      "step": 2360
    },
    {
      "epoch": 8.78,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 0.0027,
      "step": 2370
    },
    {
      "epoch": 8.81,
      "learning_rate": 2.3703703703703707e-05,
      "loss": 0.0027,
      "step": 2380
    },
    {
      "epoch": 8.85,
      "learning_rate": 2.2962962962962965e-05,
      "loss": 0.0027,
      "step": 2390
    },
    {
      "epoch": 8.89,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0091,
      "step": 2400
    },
    {
      "epoch": 8.93,
      "learning_rate": 2.148148148148148e-05,
      "loss": 0.0028,
      "step": 2410
    },
    {
      "epoch": 8.96,
      "learning_rate": 2.074074074074074e-05,
      "loss": 0.0028,
      "step": 2420
    },
    {
      "epoch": 9.0,
      "learning_rate": 2e-05,
      "loss": 0.0028,
      "step": 2430
    },
    {
      "epoch": 9.04,
      "learning_rate": 1.925925925925926e-05,
      "loss": 0.003,
      "step": 2440
    },
    {
      "epoch": 9.07,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.0086,
      "step": 2450
    },
    {
      "epoch": 9.11,
      "learning_rate": 1.777777777777778e-05,
      "loss": 0.0096,
      "step": 2460
    },
    {
      "epoch": 9.15,
      "learning_rate": 1.7037037037037038e-05,
      "loss": 0.0027,
      "step": 2470
    },
    {
      "epoch": 9.19,
      "learning_rate": 1.62962962962963e-05,
      "loss": 0.0026,
      "step": 2480
    },
    {
      "epoch": 9.22,
      "learning_rate": 1.5555555555555555e-05,
      "loss": 0.0026,
      "step": 2490
    },
    {
      "epoch": 9.26,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.0026,
      "step": 2500
    },
    {
      "epoch": 9.3,
      "learning_rate": 1.4074074074074075e-05,
      "loss": 0.0027,
      "step": 2510
    },
    {
      "epoch": 9.33,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0026,
      "step": 2520
    },
    {
      "epoch": 9.37,
      "learning_rate": 1.2592592592592592e-05,
      "loss": 0.0025,
      "step": 2530
    },
    {
      "epoch": 9.41,
      "learning_rate": 1.1851851851851853e-05,
      "loss": 0.0027,
      "step": 2540
    },
    {
      "epoch": 9.44,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0024,
      "step": 2550
    },
    {
      "epoch": 9.48,
      "learning_rate": 1.037037037037037e-05,
      "loss": 0.0025,
      "step": 2560
    },
    {
      "epoch": 9.52,
      "learning_rate": 9.62962962962963e-06,
      "loss": 0.0077,
      "step": 2570
    },
    {
      "epoch": 9.56,
      "learning_rate": 8.88888888888889e-06,
      "loss": 0.0176,
      "step": 2580
    },
    {
      "epoch": 9.59,
      "learning_rate": 8.14814814814815e-06,
      "loss": 0.0026,
      "step": 2590
    },
    {
      "epoch": 9.63,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0024,
      "step": 2600
    },
    {
      "epoch": 9.67,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.0025,
      "step": 2610
    },
    {
      "epoch": 9.7,
      "learning_rate": 5.925925925925927e-06,
      "loss": 0.0025,
      "step": 2620
    },
    {
      "epoch": 9.74,
      "learning_rate": 5.185185185185185e-06,
      "loss": 0.0025,
      "step": 2630
    },
    {
      "epoch": 9.78,
      "learning_rate": 4.444444444444445e-06,
      "loss": 0.0026,
      "step": 2640
    },
    {
      "epoch": 9.81,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.0026,
      "step": 2650
    },
    {
      "epoch": 9.85,
      "learning_rate": 2.9629629629629633e-06,
      "loss": 0.0025,
      "step": 2660
    },
    {
      "epoch": 9.89,
      "learning_rate": 2.2222222222222225e-06,
      "loss": 0.0101,
      "step": 2670
    },
    {
      "epoch": 9.93,
      "learning_rate": 1.4814814814814817e-06,
      "loss": 0.0026,
      "step": 2680
    },
    {
      "epoch": 9.96,
      "learning_rate": 7.407407407407408e-07,
      "loss": 0.0026,
      "step": 2690
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 0.0025,
      "step": 2700
    },
    {
      "epoch": 10.0,
      "step": 2700,
      "total_flos": 3.347863979094835e+18,
      "train_loss": 0.2644773021671507,
      "train_runtime": 949.4602,
      "train_samples_per_second": 45.5,
      "train_steps_per_second": 2.844
    }
  ],
  "logging_steps": 10,
  "max_steps": 2700,
  "num_train_epochs": 10,
  "save_steps": 3000,
  "total_flos": 3.347863979094835e+18,
  "trial_name": null,
  "trial_params": null
}