{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 852.0,
      "learning_rate": 2.222222222222222e-07,
      "loss": 4.3787,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 972.0,
      "learning_rate": 4.444444444444444e-07,
      "loss": 4.7261,
      "step": 20
    },
    {
      "epoch": 0.06,
      "grad_norm": 1128.0,
      "learning_rate": 6.666666666666666e-07,
      "loss": 3.5648,
      "step": 30
    },
    {
      "epoch": 0.08,
      "grad_norm": 1128.0,
      "learning_rate": 8.888888888888888e-07,
      "loss": 2.7698,
      "step": 40
    },
    {
      "epoch": 0.1,
      "grad_norm": 700.0,
      "learning_rate": 9.965635738831615e-07,
      "loss": 1.9925,
      "step": 50
    },
    {
      "epoch": 0.12,
      "grad_norm": 211.0,
      "learning_rate": 9.896907216494845e-07,
      "loss": 0.5663,
      "step": 60
    },
    {
      "epoch": 0.14,
      "grad_norm": 43.75,
      "learning_rate": 9.828178694158075e-07,
      "loss": 0.3221,
      "step": 70
    },
    {
      "epoch": 0.16,
      "grad_norm": 23.375,
      "learning_rate": 9.759450171821305e-07,
      "loss": 0.168,
      "step": 80
    },
    {
      "epoch": 0.18,
      "grad_norm": 10.125,
      "learning_rate": 9.690721649484535e-07,
      "loss": 0.3897,
      "step": 90
    },
    {
      "epoch": 0.2,
      "grad_norm": 334.0,
      "learning_rate": 9.621993127147767e-07,
      "loss": 0.1535,
      "step": 100
    },
    {
      "epoch": 0.22,
      "grad_norm": 8.0,
      "learning_rate": 9.553264604810997e-07,
      "loss": 0.3741,
      "step": 110
    },
    {
      "epoch": 0.24,
      "grad_norm": 18.375,
      "learning_rate": 9.484536082474226e-07,
      "loss": 0.2235,
      "step": 120
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.0,
      "learning_rate": 9.415807560137456e-07,
      "loss": 0.3256,
      "step": 130
    },
    {
      "epoch": 0.28,
      "grad_norm": 98.5,
      "learning_rate": 9.347079037800687e-07,
      "loss": 0.3158,
      "step": 140
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.796875,
      "learning_rate": 9.278350515463918e-07,
      "loss": 0.8076,
      "step": 150
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.0078125,
      "learning_rate": 9.209621993127147e-07,
      "loss": 0.2682,
      "step": 160
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.1484375,
      "learning_rate": 9.140893470790378e-07,
      "loss": 0.4375,
      "step": 170
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.404296875,
      "learning_rate": 9.072164948453608e-07,
      "loss": 0.4296,
      "step": 180
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.396484375,
      "learning_rate": 9.003436426116838e-07,
      "loss": 0.046,
      "step": 190
    },
    {
      "epoch": 0.4,
      "grad_norm": 196.0,
      "learning_rate": 8.934707903780069e-07,
      "loss": 0.3079,
      "step": 200
    },
    {
      "epoch": 0.42,
      "grad_norm": 20.5,
      "learning_rate": 8.865979381443298e-07,
      "loss": 0.5322,
      "step": 210
    },
    {
      "epoch": 0.44,
      "grad_norm": 169.0,
      "learning_rate": 8.797250859106528e-07,
      "loss": 0.4256,
      "step": 220
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.609375,
      "learning_rate": 8.728522336769759e-07,
      "loss": 0.192,
      "step": 230
    },
    {
      "epoch": 0.48,
      "grad_norm": 159.0,
      "learning_rate": 8.659793814432989e-07,
      "loss": 0.4527,
      "step": 240
    },
    {
      "epoch": 0.5,
      "grad_norm": 9.125,
      "learning_rate": 8.591065292096219e-07,
      "loss": 0.3642,
      "step": 250
    },
    {
      "epoch": 0.52,
      "grad_norm": 284.0,
      "learning_rate": 8.52233676975945e-07,
      "loss": 0.1506,
      "step": 260
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.57421875,
      "learning_rate": 8.45360824742268e-07,
      "loss": 0.1674,
      "step": 270
    },
    {
      "epoch": 0.56,
      "grad_norm": 360.0,
      "learning_rate": 8.384879725085911e-07,
      "loss": 0.239,
      "step": 280
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.408203125,
      "learning_rate": 8.316151202749141e-07,
      "loss": 0.1217,
      "step": 290
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.90625,
      "learning_rate": 8.24742268041237e-07,
      "loss": 0.0678,
      "step": 300
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.52734375,
      "learning_rate": 8.178694158075601e-07,
      "loss": 0.2232,
      "step": 310
    },
    {
      "epoch": 0.64,
      "grad_norm": 8.4375,
      "learning_rate": 8.109965635738831e-07,
      "loss": 0.257,
      "step": 320
    },
    {
      "epoch": 0.66,
      "grad_norm": 348.0,
      "learning_rate": 8.041237113402062e-07,
      "loss": 0.5143,
      "step": 330
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.1279296875,
      "learning_rate": 7.972508591065292e-07,
      "loss": 0.1554,
      "step": 340
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.8203125,
      "learning_rate": 7.903780068728521e-07,
      "loss": 0.1433,
      "step": 350
    },
    {
      "epoch": 0.72,
      "grad_norm": 11.5625,
      "learning_rate": 7.835051546391752e-07,
      "loss": 0.1622,
      "step": 360
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.53125,
      "learning_rate": 7.766323024054983e-07,
      "loss": 0.1386,
      "step": 370
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.765625,
      "learning_rate": 7.697594501718213e-07,
      "loss": 0.206,
      "step": 380
    },
    {
      "epoch": 0.78,
      "grad_norm": 242.0,
      "learning_rate": 7.628865979381443e-07,
      "loss": 0.2306,
      "step": 390
    },
    {
      "epoch": 0.8,
      "grad_norm": 180.0,
      "learning_rate": 7.560137457044673e-07,
      "loss": 0.3283,
      "step": 400
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.7265625,
      "learning_rate": 7.491408934707904e-07,
      "loss": 0.1725,
      "step": 410
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.279296875,
      "learning_rate": 7.422680412371134e-07,
      "loss": 0.2467,
      "step": 420
    },
    {
      "epoch": 0.86,
      "grad_norm": 61.25,
      "learning_rate": 7.353951890034364e-07,
      "loss": 0.3496,
      "step": 430
    },
    {
      "epoch": 0.88,
      "grad_norm": 430.0,
      "learning_rate": 7.285223367697594e-07,
      "loss": 0.235,
      "step": 440
    },
    {
      "epoch": 0.9,
      "grad_norm": 39.0,
      "learning_rate": 7.216494845360824e-07,
      "loss": 0.3074,
      "step": 450
    },
    {
      "epoch": 0.92,
      "grad_norm": 126.0,
      "learning_rate": 7.147766323024054e-07,
      "loss": 0.2102,
      "step": 460
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.349609375,
      "learning_rate": 7.079037800687286e-07,
      "loss": 0.128,
      "step": 470
    },
    {
      "epoch": 0.96,
      "grad_norm": 9.8125,
      "learning_rate": 7.010309278350515e-07,
      "loss": 0.2278,
      "step": 480
    },
    {
      "epoch": 0.98,
      "grad_norm": 3.359375,
      "learning_rate": 6.941580756013746e-07,
      "loss": 0.1644,
      "step": 490
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.244140625,
      "learning_rate": 6.872852233676976e-07,
      "loss": 0.3245,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.2981492877006531,
      "eval_model_preparation_time": 0.0055,
      "eval_runtime": 90.7988,
      "eval_samples_per_second": 9.923,
      "eval_steps_per_second": 2.489,
      "step": 500
    },
    {
      "epoch": 1.02,
      "grad_norm": 1.4765625,
      "learning_rate": 6.804123711340206e-07,
      "loss": 0.2128,
      "step": 510
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.07958984375,
      "learning_rate": 6.735395189003437e-07,
      "loss": 0.0455,
      "step": 520
    },
    {
      "epoch": 1.06,
      "grad_norm": 175.0,
      "learning_rate": 6.666666666666666e-07,
      "loss": 0.2633,
      "step": 530
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.1328125,
      "learning_rate": 6.597938144329896e-07,
      "loss": 0.1368,
      "step": 540
    },
    {
      "epoch": 1.1,
      "grad_norm": 42.0,
      "learning_rate": 6.529209621993127e-07,
      "loss": 0.3963,
      "step": 550
    },
    {
      "epoch": 1.12,
      "grad_norm": 248.0,
      "learning_rate": 6.460481099656357e-07,
      "loss": 0.1807,
      "step": 560
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 230.0,
      "learning_rate": 6.391752577319586e-07,
      "loss": 0.1865,
      "step": 570
    },
    {
      "epoch": 1.16,
      "grad_norm": 175.0,
      "learning_rate": 6.323024054982817e-07,
      "loss": 0.2382,
      "step": 580
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.671875,
      "learning_rate": 6.254295532646048e-07,
      "loss": 0.1976,
      "step": 590
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.326171875,
      "learning_rate": 6.185567010309279e-07,
      "loss": 0.0799,
      "step": 600
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.69921875,
      "learning_rate": 6.116838487972509e-07,
      "loss": 0.252,
      "step": 610
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.1494140625,
      "learning_rate": 6.048109965635738e-07,
      "loss": 0.1807,
      "step": 620
    },
    {
      "epoch": 1.26,
      "grad_norm": 140.0,
      "learning_rate": 5.979381443298969e-07,
      "loss": 0.2544,
      "step": 630
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.107421875,
      "learning_rate": 5.910652920962199e-07,
      "loss": 0.2119,
      "step": 640
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.51171875,
      "learning_rate": 5.841924398625429e-07,
      "loss": 0.2212,
      "step": 650
    },
    {
      "epoch": 1.32,
      "grad_norm": 100.5,
      "learning_rate": 5.773195876288659e-07,
      "loss": 0.2884,
      "step": 660
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.51171875,
      "learning_rate": 5.704467353951889e-07,
      "loss": 0.2897,
      "step": 670
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.53515625,
      "learning_rate": 5.63573883161512e-07,
      "loss": 0.2315,
      "step": 680
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.52734375,
      "learning_rate": 5.56701030927835e-07,
      "loss": 0.1976,
      "step": 690
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.27734375,
      "learning_rate": 5.498281786941581e-07,
      "loss": 0.0962,
      "step": 700
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.52734375,
      "learning_rate": 5.429553264604811e-07,
      "loss": 0.1074,
      "step": 710
    },
    {
      "epoch": 1.44,
      "grad_norm": 212.0,
      "learning_rate": 5.360824742268041e-07,
      "loss": 0.2251,
      "step": 720
    },
    {
      "epoch": 1.46,
      "grad_norm": 146.0,
      "learning_rate": 5.292096219931271e-07,
      "loss": 0.198,
      "step": 730
    },
    {
      "epoch": 1.48,
      "grad_norm": 8.375,
      "learning_rate": 5.223367697594502e-07,
      "loss": 0.2187,
      "step": 740
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.322265625,
      "learning_rate": 5.154639175257731e-07,
      "loss": 0.1811,
      "step": 750
    },
    {
      "epoch": 1.52,
      "grad_norm": 1.609375,
      "learning_rate": 5.085910652920962e-07,
      "loss": 0.114,
      "step": 760
    },
    {
      "epoch": 1.54,
      "grad_norm": 126.0,
      "learning_rate": 5.017182130584192e-07,
      "loss": 0.0166,
      "step": 770
    },
    {
      "epoch": 1.56,
      "grad_norm": 170.0,
      "learning_rate": 4.948453608247422e-07,
      "loss": 0.0905,
      "step": 780
    },
    {
      "epoch": 1.58,
      "grad_norm": 27.875,
      "learning_rate": 4.879725085910652e-07,
      "loss": 0.1969,
      "step": 790
    },
    {
      "epoch": 1.6,
      "grad_norm": 210.0,
      "learning_rate": 4.810996563573884e-07,
      "loss": 0.1211,
      "step": 800
    },
    {
      "epoch": 1.62,
      "grad_norm": 246.0,
      "learning_rate": 4.742268041237113e-07,
      "loss": 0.2062,
      "step": 810
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.546875,
      "learning_rate": 4.6735395189003437e-07,
      "loss": 0.1751,
      "step": 820
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.310546875,
      "learning_rate": 4.6048109965635733e-07,
      "loss": 0.21,
      "step": 830
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.205078125,
      "learning_rate": 4.536082474226804e-07,
      "loss": 0.1722,
      "step": 840
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.31640625,
      "learning_rate": 4.4673539518900345e-07,
      "loss": 0.2915,
      "step": 850
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.1943359375,
      "learning_rate": 4.398625429553264e-07,
      "loss": 0.0555,
      "step": 860
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.72265625,
      "learning_rate": 4.3298969072164947e-07,
      "loss": 0.0485,
      "step": 870
    },
    {
      "epoch": 1.76,
      "grad_norm": 1.3046875,
      "learning_rate": 4.261168384879725e-07,
      "loss": 0.0254,
      "step": 880
    },
    {
      "epoch": 1.78,
      "grad_norm": 143.0,
      "learning_rate": 4.1924398625429554e-07,
      "loss": 0.1165,
      "step": 890
    },
    {
      "epoch": 1.8,
      "grad_norm": 196.0,
      "learning_rate": 4.123711340206185e-07,
      "loss": 0.2069,
      "step": 900
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.1796875,
      "learning_rate": 4.0549828178694155e-07,
      "loss": 0.2645,
      "step": 910
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 213.0,
      "learning_rate": 3.986254295532646e-07,
      "loss": 0.0918,
      "step": 920
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 338.0,
      "learning_rate": 3.917525773195876e-07,
      "loss": 0.2423,
      "step": 930
    },
    {
      "epoch": 1.88,
      "grad_norm": 280.0,
      "learning_rate": 3.8487972508591063e-07,
      "loss": 0.2567,
      "step": 940
    },
    {
      "epoch": 1.9,
      "grad_norm": 4.5,
      "learning_rate": 3.7800687285223364e-07,
      "loss": 0.0007,
      "step": 950
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.40625,
      "learning_rate": 3.711340206185567e-07,
      "loss": 0.2774,
      "step": 960
    },
    {
      "epoch": 1.94,
      "grad_norm": 196.0,
      "learning_rate": 3.642611683848797e-07,
      "loss": 0.1821,
      "step": 970
    },
    {
      "epoch": 1.96,
      "grad_norm": 95.0,
      "learning_rate": 3.573883161512027e-07,
      "loss": 0.333,
      "step": 980
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.2177734375,
      "learning_rate": 3.5051546391752573e-07,
      "loss": 0.1336,
      "step": 990
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.314453125,
      "learning_rate": 3.436426116838488e-07,
      "loss": 0.1321,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.2803506553173065,
      "eval_model_preparation_time": 0.0055,
      "eval_runtime": 90.8543,
      "eval_samples_per_second": 9.917,
      "eval_steps_per_second": 2.487,
      "step": 1000
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.365234375,
      "learning_rate": 3.3676975945017185e-07,
      "loss": 0.2451,
      "step": 1010
    },
    {
      "epoch": 2.04,
      "grad_norm": 3.890625,
      "learning_rate": 3.298969072164948e-07,
      "loss": 0.2094,
      "step": 1020
    },
    {
      "epoch": 2.06,
      "grad_norm": 115.5,
      "learning_rate": 3.2302405498281787e-07,
      "loss": 0.3415,
      "step": 1030
    },
    {
      "epoch": 2.08,
      "grad_norm": 242.0,
      "learning_rate": 3.161512027491409e-07,
      "loss": 0.2187,
      "step": 1040
    },
    {
      "epoch": 2.1,
      "grad_norm": 158.0,
      "learning_rate": 3.0927835051546394e-07,
      "loss": 0.2182,
      "step": 1050
    },
    {
      "epoch": 2.12,
      "grad_norm": 24.625,
      "learning_rate": 3.024054982817869e-07,
      "loss": 0.0973,
      "step": 1060
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.70703125,
      "learning_rate": 2.9553264604810995e-07,
      "loss": 0.1385,
      "step": 1070
    },
    {
      "epoch": 2.16,
      "grad_norm": 175.0,
      "learning_rate": 2.8865979381443296e-07,
      "loss": 0.1739,
      "step": 1080
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.73828125,
      "learning_rate": 2.81786941580756e-07,
      "loss": 0.0563,
      "step": 1090
    },
    {
      "epoch": 2.2,
      "grad_norm": 308.0,
      "learning_rate": 2.7491408934707903e-07,
      "loss": 0.4428,
      "step": 1100
    },
    {
      "epoch": 2.22,
      "grad_norm": 2.984375,
      "learning_rate": 2.6804123711340204e-07,
      "loss": 0.1983,
      "step": 1110
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.9765625,
      "learning_rate": 2.611683848797251e-07,
      "loss": 0.1572,
      "step": 1120
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.234375,
      "learning_rate": 2.542955326460481e-07,
      "loss": 0.2067,
      "step": 1130
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 246.0,
      "learning_rate": 2.474226804123711e-07,
      "loss": 0.3285,
      "step": 1140
    },
    {
      "epoch": 2.3,
      "grad_norm": 125.5,
      "learning_rate": 2.405498281786942e-07,
      "loss": 0.2141,
      "step": 1150
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.4140625,
      "learning_rate": 2.3367697594501719e-07,
      "loss": 0.045,
      "step": 1160
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.271484375,
      "learning_rate": 2.268041237113402e-07,
      "loss": 0.1434,
      "step": 1170
    },
    {
      "epoch": 2.36,
      "grad_norm": 120.0,
      "learning_rate": 2.199312714776632e-07,
      "loss": 0.2549,
      "step": 1180
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.58203125,
      "learning_rate": 2.1305841924398624e-07,
      "loss": 0.1642,
      "step": 1190
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.26953125,
      "learning_rate": 2.0618556701030925e-07,
      "loss": 0.1319,
      "step": 1200
    },
    {
      "epoch": 2.42,
      "grad_norm": 4.65625,
      "learning_rate": 1.993127147766323e-07,
      "loss": 0.0939,
      "step": 1210
    },
    {
      "epoch": 2.44,
      "grad_norm": 7.40625,
      "learning_rate": 1.9243986254295532e-07,
      "loss": 0.0408,
      "step": 1220
    },
    {
      "epoch": 2.46,
      "grad_norm": 158.0,
      "learning_rate": 1.8556701030927835e-07,
      "loss": 0.0666,
      "step": 1230
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.59765625,
      "learning_rate": 1.7869415807560136e-07,
      "loss": 0.1051,
      "step": 1240
    },
    {
      "epoch": 2.5,
      "grad_norm": 2.046875,
      "learning_rate": 1.718213058419244e-07,
      "loss": 0.1325,
      "step": 1250
    },
    {
      "epoch": 2.52,
      "grad_norm": 196.0,
      "learning_rate": 1.649484536082474e-07,
      "loss": 0.1399,
      "step": 1260
    },
    {
      "epoch": 2.54,
      "grad_norm": 1.2265625,
      "learning_rate": 1.5807560137457044e-07,
      "loss": 0.1376,
      "step": 1270
    },
    {
      "epoch": 2.56,
      "grad_norm": 382.0,
      "learning_rate": 1.5120274914089345e-07,
      "loss": 0.4664,
      "step": 1280
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.203125,
      "learning_rate": 1.4432989690721648e-07,
      "loss": 0.0066,
      "step": 1290
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.232421875,
      "learning_rate": 1.3745704467353952e-07,
      "loss": 0.1785,
      "step": 1300
    },
    {
      "epoch": 2.62,
      "grad_norm": 150.0,
      "learning_rate": 1.3058419243986255e-07,
      "loss": 0.215,
      "step": 1310
    },
    {
      "epoch": 2.64,
      "grad_norm": 176.0,
      "learning_rate": 1.2371134020618556e-07,
      "loss": 0.2701,
      "step": 1320
    },
    {
      "epoch": 2.66,
      "grad_norm": 60.25,
      "learning_rate": 1.1683848797250859e-07,
      "loss": 0.1865,
      "step": 1330
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.55859375,
      "learning_rate": 1.099656357388316e-07,
      "loss": 0.0705,
      "step": 1340
    },
    {
      "epoch": 2.7,
      "grad_norm": 11.5625,
      "learning_rate": 1.0309278350515462e-07,
      "loss": 0.1022,
      "step": 1350
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 130.0,
      "learning_rate": 9.621993127147766e-08,
      "loss": 0.1533,
      "step": 1360
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.19140625,
      "learning_rate": 8.934707903780068e-08,
      "loss": 0.2216,
      "step": 1370
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.107421875,
      "learning_rate": 8.24742268041237e-08,
      "loss": 0.1827,
      "step": 1380
    },
    {
      "epoch": 2.7800000000000002,
      "grad_norm": 144.0,
      "learning_rate": 7.560137457044672e-08,
      "loss": 0.1647,
      "step": 1390
    },
    {
      "epoch": 2.8,
      "grad_norm": 2.71875,
      "learning_rate": 6.872852233676976e-08,
      "loss": 0.2745,
      "step": 1400
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.5390625,
      "learning_rate": 6.185567010309278e-08,
      "loss": 0.2536,
      "step": 1410
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.10693359375,
      "learning_rate": 5.49828178694158e-08,
      "loss": 0.1457,
      "step": 1420
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.1328125,
      "learning_rate": 4.810996563573883e-08,
      "loss": 0.1346,
      "step": 1430
    },
    {
      "epoch": 2.88,
      "grad_norm": 1.28125,
      "learning_rate": 4.123711340206185e-08,
      "loss": 0.0228,
      "step": 1440
    },
    {
      "epoch": 2.9,
      "grad_norm": 37.25,
      "learning_rate": 3.436426116838488e-08,
      "loss": 0.1333,
      "step": 1450
    },
    {
      "epoch": 2.92,
      "grad_norm": 203.0,
      "learning_rate": 2.74914089347079e-08,
      "loss": 0.0583,
      "step": 1460
    },
    {
      "epoch": 2.94,
      "grad_norm": 162.0,
      "learning_rate": 2.0618556701030925e-08,
      "loss": 0.0219,
      "step": 1470
    },
    {
      "epoch": 2.96,
      "grad_norm": 180.0,
      "learning_rate": 1.374570446735395e-08,
      "loss": 0.0781,
      "step": 1480
    },
    {
      "epoch": 2.98,
      "grad_norm": 147.0,
      "learning_rate": 6.872852233676975e-09,
      "loss": 0.0778,
      "step": 1490
    },
    {
      "epoch": 3.0,
      "grad_norm": 179.0,
      "learning_rate": 0.0,
      "loss": 0.1859,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.2740519940853119,
      "eval_model_preparation_time": 0.0055,
      "eval_runtime": 90.7126,
      "eval_samples_per_second": 9.932,
      "eval_steps_per_second": 2.491,
      "step": 1500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0457851977728e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}