{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.395973154362416,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.7916,
      "step": 10
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.7906,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 3e-06,
      "loss": 1.7887,
      "step": 30
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.7891,
      "step": 40
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-06,
      "loss": 1.7873,
      "step": 50
    },
    {
      "epoch": 0.4,
      "learning_rate": 6e-06,
      "loss": 1.7828,
      "step": 60
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.000000000000001e-06,
      "loss": 1.7828,
      "step": 70
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.7809,
      "step": 80
    },
    {
      "epoch": 0.6,
      "learning_rate": 9e-06,
      "loss": 1.7793,
      "step": 90
    },
    {
      "epoch": 0.67,
      "learning_rate": 1e-05,
      "loss": 1.7742,
      "step": 100
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.7633,
      "step": 110
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2e-05,
      "loss": 1.7617,
      "step": 120
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.7601,
      "step": 130
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.7457,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3411764705882353,
      "eval_loss": 1.6935209035873413,
      "eval_runtime": 22.6549,
      "eval_samples_per_second": 26.264,
      "eval_steps_per_second": 3.311,
      "step": 149
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.5e-05,
      "loss": 1.7224,
      "step": 150
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.6744,
      "step": 160
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 1.6978,
      "step": 170
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.8e-05,
      "loss": 1.6583,
      "step": 180
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.9e-05,
      "loss": 1.5927,
      "step": 190
    },
    {
      "epoch": 1.34,
      "learning_rate": 2e-05,
      "loss": 1.6234,
      "step": 200
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.1e-05,
      "loss": 1.577,
      "step": 210
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.5456,
      "step": 220
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 1.4884,
      "step": 230
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.4e-05,
      "loss": 1.5366,
      "step": 240
    },
    {
      "epoch": 1.68,
      "learning_rate": 2.5e-05,
      "loss": 1.5622,
      "step": 250
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.5054,
      "step": 260
    },
    {
      "epoch": 1.81,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 1.5265,
      "step": 270
    },
    {
      "epoch": 1.88,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.4786,
      "step": 280
    },
    {
      "epoch": 1.95,
      "learning_rate": 2.9e-05,
      "loss": 1.45,
      "step": 290
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.43529411764705883,
      "eval_loss": 1.4212191104888916,
      "eval_runtime": 22.0113,
      "eval_samples_per_second": 27.032,
      "eval_steps_per_second": 3.407,
      "step": 298
    },
    {
      "epoch": 2.01,
      "learning_rate": 3e-05,
      "loss": 1.5353,
      "step": 300
    },
    {
      "epoch": 2.08,
      "learning_rate": 3.1e-05,
      "loss": 1.4117,
      "step": 310
    },
    {
      "epoch": 2.15,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.4371,
      "step": 320
    },
    {
      "epoch": 2.21,
      "learning_rate": 3.3e-05,
      "loss": 1.475,
      "step": 330
    },
    {
      "epoch": 2.28,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.4499,
      "step": 340
    },
    {
      "epoch": 2.35,
      "learning_rate": 3.5e-05,
      "loss": 1.4489,
      "step": 350
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.6e-05,
      "loss": 1.4577,
      "step": 360
    },
    {
      "epoch": 2.48,
      "learning_rate": 3.7e-05,
      "loss": 1.3862,
      "step": 370
    },
    {
      "epoch": 2.55,
      "learning_rate": 3.8e-05,
      "loss": 1.3997,
      "step": 380
    },
    {
      "epoch": 2.62,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 1.408,
      "step": 390
    },
    {
      "epoch": 2.68,
      "learning_rate": 4e-05,
      "loss": 1.3716,
      "step": 400
    },
    {
      "epoch": 2.75,
      "learning_rate": 4.1e-05,
      "loss": 1.3804,
      "step": 410
    },
    {
      "epoch": 2.82,
      "learning_rate": 4.2e-05,
      "loss": 1.3478,
      "step": 420
    },
    {
      "epoch": 2.89,
      "learning_rate": 4.3e-05,
      "loss": 1.3447,
      "step": 430
    },
    {
      "epoch": 2.95,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.3691,
      "step": 440
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5563025210084034,
      "eval_loss": 1.1688096523284912,
      "eval_runtime": 21.4253,
      "eval_samples_per_second": 27.771,
      "eval_steps_per_second": 3.501,
      "step": 447
    },
    {
      "epoch": 3.02,
      "learning_rate": 4.5e-05,
      "loss": 1.3441,
      "step": 450
    },
    {
      "epoch": 3.09,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.2688,
      "step": 460
    },
    {
      "epoch": 3.15,
      "learning_rate": 4.7e-05,
      "loss": 1.1629,
      "step": 470
    },
    {
      "epoch": 3.22,
      "learning_rate": 4.8e-05,
      "loss": 1.225,
      "step": 480
    },
    {
      "epoch": 3.29,
      "learning_rate": 4.9e-05,
      "loss": 1.2406,
      "step": 490
    },
    {
      "epoch": 3.36,
      "learning_rate": 5e-05,
      "loss": 1.1661,
      "step": 500
    },
    {
      "epoch": 3.42,
      "learning_rate": 4.94949494949495e-05,
      "loss": 1.2401,
      "step": 510
    },
    {
      "epoch": 3.49,
      "learning_rate": 4.898989898989899e-05,
      "loss": 1.1792,
      "step": 520
    },
    {
      "epoch": 3.56,
      "learning_rate": 4.848484848484849e-05,
      "loss": 1.2781,
      "step": 530
    },
    {
      "epoch": 3.62,
      "learning_rate": 4.797979797979798e-05,
      "loss": 1.1531,
      "step": 540
    },
    {
      "epoch": 3.69,
      "learning_rate": 4.7474747474747476e-05,
      "loss": 1.1768,
      "step": 550
    },
    {
      "epoch": 3.76,
      "learning_rate": 4.696969696969697e-05,
      "loss": 1.1918,
      "step": 560
    },
    {
      "epoch": 3.83,
      "learning_rate": 4.6464646464646464e-05,
      "loss": 1.164,
      "step": 570
    },
    {
      "epoch": 3.89,
      "learning_rate": 4.595959595959596e-05,
      "loss": 1.1254,
      "step": 580
    },
    {
      "epoch": 3.96,
      "learning_rate": 4.545454545454546e-05,
      "loss": 1.1553,
      "step": 590
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6084033613445378,
      "eval_loss": 1.0190620422363281,
      "eval_runtime": 21.3507,
      "eval_samples_per_second": 27.868,
      "eval_steps_per_second": 3.513,
      "step": 596
    },
    {
      "epoch": 4.03,
      "learning_rate": 4.494949494949495e-05,
      "loss": 1.1626,
      "step": 600
    },
    {
      "epoch": 4.09,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.1336,
      "step": 610
    },
    {
      "epoch": 4.16,
      "learning_rate": 4.3939393939393944e-05,
      "loss": 1.1021,
      "step": 620
    },
    {
      "epoch": 4.23,
      "learning_rate": 4.343434343434344e-05,
      "loss": 1.1986,
      "step": 630
    },
    {
      "epoch": 4.3,
      "learning_rate": 4.292929292929293e-05,
      "loss": 1.1517,
      "step": 640
    },
    {
      "epoch": 4.36,
      "learning_rate": 4.242424242424243e-05,
      "loss": 1.0188,
      "step": 650
    },
    {
      "epoch": 4.43,
      "learning_rate": 4.191919191919192e-05,
      "loss": 1.0938,
      "step": 660
    },
    {
      "epoch": 4.5,
      "learning_rate": 4.141414141414142e-05,
      "loss": 1.1621,
      "step": 670
    },
    {
      "epoch": 4.56,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 1.0986,
      "step": 680
    },
    {
      "epoch": 4.63,
      "learning_rate": 4.0404040404040405e-05,
      "loss": 1.1434,
      "step": 690
    },
    {
      "epoch": 4.7,
      "learning_rate": 3.98989898989899e-05,
      "loss": 1.0971,
      "step": 700
    },
    {
      "epoch": 4.77,
      "learning_rate": 3.939393939393939e-05,
      "loss": 0.9853,
      "step": 710
    },
    {
      "epoch": 4.83,
      "learning_rate": 3.888888888888889e-05,
      "loss": 1.1469,
      "step": 720
    },
    {
      "epoch": 4.9,
      "learning_rate": 3.838383838383838e-05,
      "loss": 1.0782,
      "step": 730
    },
    {
      "epoch": 4.97,
      "learning_rate": 3.787878787878788e-05,
      "loss": 0.9854,
      "step": 740
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.653781512605042,
      "eval_loss": 0.9426462650299072,
      "eval_runtime": 22.7302,
      "eval_samples_per_second": 26.177,
      "eval_steps_per_second": 3.3,
      "step": 745
    },
    {
      "epoch": 5.03,
      "learning_rate": 3.7373737373737376e-05,
      "loss": 1.07,
      "step": 750
    },
    {
      "epoch": 5.1,
      "learning_rate": 3.686868686868687e-05,
      "loss": 1.054,
      "step": 760
    },
    {
      "epoch": 5.17,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.9113,
      "step": 770
    },
    {
      "epoch": 5.23,
      "learning_rate": 3.5858585858585855e-05,
      "loss": 1.0446,
      "step": 780
    },
    {
      "epoch": 5.3,
      "learning_rate": 3.535353535353535e-05,
      "loss": 1.074,
      "step": 790
    },
    {
      "epoch": 5.37,
      "learning_rate": 3.484848484848485e-05,
      "loss": 1.0417,
      "step": 800
    },
    {
      "epoch": 5.44,
      "learning_rate": 3.434343434343435e-05,
      "loss": 1.1119,
      "step": 810
    },
    {
      "epoch": 5.5,
      "learning_rate": 3.3838383838383844e-05,
      "loss": 1.056,
      "step": 820
    },
    {
      "epoch": 5.57,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.0155,
      "step": 830
    },
    {
      "epoch": 5.64,
      "learning_rate": 3.282828282828283e-05,
      "loss": 1.0486,
      "step": 840
    },
    {
      "epoch": 5.7,
      "learning_rate": 3.232323232323233e-05,
      "loss": 1.1064,
      "step": 850
    },
    {
      "epoch": 5.77,
      "learning_rate": 3.181818181818182e-05,
      "loss": 0.9373,
      "step": 860
    },
    {
      "epoch": 5.84,
      "learning_rate": 3.131313131313132e-05,
      "loss": 0.9218,
      "step": 870
    },
    {
      "epoch": 5.91,
      "learning_rate": 3.080808080808081e-05,
      "loss": 0.9732,
      "step": 880
    },
    {
      "epoch": 5.97,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 1.088,
      "step": 890
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6756302521008404,
      "eval_loss": 0.9188197255134583,
      "eval_runtime": 22.0566,
      "eval_samples_per_second": 26.976,
      "eval_steps_per_second": 3.4,
      "step": 894
    },
    {
      "epoch": 6.04,
      "learning_rate": 2.9797979797979796e-05,
      "loss": 0.9063,
      "step": 900
    },
    {
      "epoch": 6.11,
      "learning_rate": 2.9292929292929294e-05,
      "loss": 1.0027,
      "step": 910
    },
    {
      "epoch": 6.17,
      "learning_rate": 2.878787878787879e-05,
      "loss": 1.122,
      "step": 920
    },
    {
      "epoch": 6.24,
      "learning_rate": 2.8282828282828282e-05,
      "loss": 0.9835,
      "step": 930
    },
    {
      "epoch": 6.31,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.9308,
      "step": 940
    },
    {
      "epoch": 6.38,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 1.0989,
      "step": 950
    },
    {
      "epoch": 6.44,
      "learning_rate": 2.676767676767677e-05,
      "loss": 0.9864,
      "step": 960
    },
    {
      "epoch": 6.51,
      "learning_rate": 2.6262626262626268e-05,
      "loss": 1.0551,
      "step": 970
    },
    {
      "epoch": 6.58,
      "learning_rate": 2.575757575757576e-05,
      "loss": 1.0034,
      "step": 980
    },
    {
      "epoch": 6.64,
      "learning_rate": 2.5252525252525256e-05,
      "loss": 0.9375,
      "step": 990
    },
    {
      "epoch": 6.71,
      "learning_rate": 2.474747474747475e-05,
      "loss": 1.0388,
      "step": 1000
    },
    {
      "epoch": 6.78,
      "learning_rate": 2.4242424242424244e-05,
      "loss": 0.9212,
      "step": 1010
    },
    {
      "epoch": 6.85,
      "learning_rate": 2.3737373737373738e-05,
      "loss": 1.0113,
      "step": 1020
    },
    {
      "epoch": 6.91,
      "learning_rate": 2.3232323232323232e-05,
      "loss": 0.9493,
      "step": 1030
    },
    {
      "epoch": 6.98,
      "learning_rate": 2.272727272727273e-05,
      "loss": 0.9801,
      "step": 1040
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6789915966386555,
      "eval_loss": 0.9123912453651428,
      "eval_runtime": 21.4548,
      "eval_samples_per_second": 27.733,
      "eval_steps_per_second": 3.496,
      "step": 1043
    },
    {
      "epoch": 7.05,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.9011,
      "step": 1050
    },
    {
      "epoch": 7.11,
      "learning_rate": 2.171717171717172e-05,
      "loss": 0.96,
      "step": 1060
    },
    {
      "epoch": 7.18,
      "learning_rate": 2.1212121212121215e-05,
      "loss": 0.9343,
      "step": 1070
    },
    {
      "epoch": 7.25,
      "learning_rate": 2.070707070707071e-05,
      "loss": 0.9807,
      "step": 1080
    },
    {
      "epoch": 7.32,
      "learning_rate": 2.0202020202020203e-05,
      "loss": 0.9954,
      "step": 1090
    },
    {
      "epoch": 7.38,
      "learning_rate": 1.9696969696969697e-05,
      "loss": 0.8943,
      "step": 1100
    },
    {
      "epoch": 7.45,
      "learning_rate": 1.919191919191919e-05,
      "loss": 1.004,
      "step": 1110
    },
    {
      "epoch": 7.52,
      "learning_rate": 1.8686868686868688e-05,
      "loss": 0.9443,
      "step": 1120
    },
    {
      "epoch": 7.58,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.9772,
      "step": 1130
    },
    {
      "epoch": 7.65,
      "learning_rate": 1.7676767676767676e-05,
      "loss": 0.9806,
      "step": 1140
    },
    {
      "epoch": 7.72,
      "learning_rate": 1.7171717171717173e-05,
      "loss": 0.8561,
      "step": 1150
    },
    {
      "epoch": 7.79,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.9052,
      "step": 1160
    },
    {
      "epoch": 7.85,
      "learning_rate": 1.6161616161616165e-05,
      "loss": 0.9653,
      "step": 1170
    },
    {
      "epoch": 7.92,
      "learning_rate": 1.565656565656566e-05,
      "loss": 1.0037,
      "step": 1180
    },
    {
      "epoch": 7.99,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 0.9003,
      "step": 1190
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6941176470588235,
      "eval_loss": 0.8562597036361694,
      "eval_runtime": 21.0406,
      "eval_samples_per_second": 28.279,
      "eval_steps_per_second": 3.565,
      "step": 1192
    },
    {
      "epoch": 8.05,
      "learning_rate": 1.4646464646464647e-05,
      "loss": 0.9756,
      "step": 1200
    },
    {
      "epoch": 8.12,
      "learning_rate": 1.4141414141414141e-05,
      "loss": 1.0478,
      "step": 1210
    },
    {
      "epoch": 8.19,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 0.8094,
      "step": 1220
    },
    {
      "epoch": 8.26,
      "learning_rate": 1.3131313131313134e-05,
      "loss": 0.9645,
      "step": 1230
    },
    {
      "epoch": 8.32,
      "learning_rate": 1.2626262626262628e-05,
      "loss": 0.9773,
      "step": 1240
    },
    {
      "epoch": 8.39,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 1.0006,
      "step": 1250
    },
    {
      "epoch": 8.46,
      "learning_rate": 1.1616161616161616e-05,
      "loss": 0.9612,
      "step": 1260
    },
    {
      "epoch": 8.52,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.9107,
      "step": 1270
    },
    {
      "epoch": 8.59,
      "learning_rate": 1.0606060606060607e-05,
      "loss": 0.876,
      "step": 1280
    },
    {
      "epoch": 8.66,
      "learning_rate": 1.0101010101010101e-05,
      "loss": 0.8718,
      "step": 1290
    },
    {
      "epoch": 8.72,
      "learning_rate": 9.595959595959595e-06,
      "loss": 0.8687,
      "step": 1300
    },
    {
      "epoch": 8.79,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.9235,
      "step": 1310
    },
    {
      "epoch": 8.86,
      "learning_rate": 8.585858585858587e-06,
      "loss": 0.9192,
      "step": 1320
    },
    {
      "epoch": 8.93,
      "learning_rate": 8.080808080808082e-06,
      "loss": 0.9701,
      "step": 1330
    },
    {
      "epoch": 8.99,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 0.9199,
      "step": 1340
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7025210084033613,
      "eval_loss": 0.8486049771308899,
      "eval_runtime": 21.6062,
      "eval_samples_per_second": 27.538,
      "eval_steps_per_second": 3.471,
      "step": 1341
    },
    {
      "epoch": 9.06,
      "learning_rate": 7.0707070707070704e-06,
      "loss": 0.8483,
      "step": 1350
    },
    {
      "epoch": 9.13,
      "learning_rate": 6.565656565656567e-06,
      "loss": 0.8321,
      "step": 1360
    },
    {
      "epoch": 9.19,
      "learning_rate": 6.060606060606061e-06,
      "loss": 1.006,
      "step": 1370
    },
    {
      "epoch": 9.26,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.9249,
      "step": 1380
    },
    {
      "epoch": 9.33,
      "learning_rate": 5.050505050505051e-06,
      "loss": 0.8196,
      "step": 1390
    },
    {
      "epoch": 9.4,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.8964,
      "step": 1400
    }
  ],
  "max_steps": 1490,
  "num_train_epochs": 10,
  "total_flos": 1.3539817231250708e+18,
  "trial_name": null,
  "trial_params": null
}