{
  "best_metric": 0.8696024900350746,
  "best_model_checkpoint": "result/bert-large-uncased-bs512-lr1e-5",
  "epoch": 3.0,
  "global_step": 1617,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 9.938157081014226e-06,
      "loss": 5.2117,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.876314162028449e-06,
      "loss": 2.7303,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.814471243042673e-06,
      "loss": 1.8126,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.752628324056896e-06,
      "loss": 1.482,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.690785405071121e-06,
      "loss": 1.3545,
      "step": 50
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.628942486085344e-06,
      "loss": 1.2558,
      "step": 60
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.567099567099569e-06,
      "loss": 1.1597,
      "step": 70
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.505256648113792e-06,
      "loss": 1.0949,
      "step": 80
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.443413729128017e-06,
      "loss": 1.1096,
      "step": 90
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.38157081014224e-06,
      "loss": 1.0072,
      "step": 100
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.319727891156464e-06,
      "loss": 1.0697,
      "step": 110
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.257884972170687e-06,
      "loss": 1.0235,
      "step": 120
    },
    {
      "epoch": 0.23,
      "eval_avg_sts": 0.835670676836703,
      "eval_sickr_spearman": 0.8174356477052697,
      "eval_stsb_spearman": 0.8539057059681365,
      "step": 125
    },
    {
      "epoch": 0.24,
      "learning_rate": 9.196042053184912e-06,
      "loss": 1.0064,
      "step": 130
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.134199134199135e-06,
      "loss": 0.9805,
      "step": 140
    },
    {
      "epoch": 0.28,
      "learning_rate": 9.07235621521336e-06,
      "loss": 0.9327,
      "step": 150
    },
    {
      "epoch": 0.3,
      "learning_rate": 9.010513296227583e-06,
      "loss": 0.9818,
      "step": 160
    },
    {
      "epoch": 0.32,
      "learning_rate": 8.948670377241808e-06,
      "loss": 0.9391,
      "step": 170
    },
    {
      "epoch": 0.33,
      "learning_rate": 8.88682745825603e-06,
      "loss": 0.9709,
      "step": 180
    },
    {
      "epoch": 0.35,
      "learning_rate": 8.824984539270254e-06,
      "loss": 0.8995,
      "step": 190
    },
    {
      "epoch": 0.37,
      "learning_rate": 8.763141620284478e-06,
      "loss": 0.9076,
      "step": 200
    },
    {
      "epoch": 0.39,
      "learning_rate": 8.701298701298701e-06,
      "loss": 0.9185,
      "step": 210
    },
    {
      "epoch": 0.41,
      "learning_rate": 8.639455782312926e-06,
      "loss": 0.9286,
      "step": 220
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.577612863327149e-06,
      "loss": 0.9184,
      "step": 230
    },
    {
      "epoch": 0.45,
      "learning_rate": 8.515769944341374e-06,
      "loss": 0.9211,
      "step": 240
    },
    {
      "epoch": 0.46,
      "learning_rate": 8.453927025355597e-06,
      "loss": 0.9251,
      "step": 250
    },
    {
      "epoch": 0.46,
      "eval_avg_sts": 0.8411396152471846,
      "eval_sickr_spearman": 0.8226138807513125,
      "eval_stsb_spearman": 0.8596653497430569,
      "step": 250
    },
    {
      "epoch": 0.48,
      "learning_rate": 8.392084106369822e-06,
      "loss": 0.8951,
      "step": 260
    },
    {
      "epoch": 0.5,
      "learning_rate": 8.330241187384045e-06,
      "loss": 0.8781,
      "step": 270
    },
    {
      "epoch": 0.52,
      "learning_rate": 8.26839826839827e-06,
      "loss": 0.8797,
      "step": 280
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.206555349412492e-06,
      "loss": 0.8636,
      "step": 290
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.144712430426717e-06,
      "loss": 0.8805,
      "step": 300
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.08286951144094e-06,
      "loss": 0.8727,
      "step": 310
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.021026592455165e-06,
      "loss": 0.8553,
      "step": 320
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.959183673469388e-06,
      "loss": 0.8563,
      "step": 330
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.897340754483613e-06,
      "loss": 0.8791,
      "step": 340
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.835497835497836e-06,
      "loss": 0.8768,
      "step": 350
    },
    {
      "epoch": 0.67,
      "learning_rate": 7.77365491651206e-06,
      "loss": 0.9132,
      "step": 360
    },
    {
      "epoch": 0.69,
      "learning_rate": 7.711811997526283e-06,
      "loss": 0.8531,
      "step": 370
    },
    {
      "epoch": 0.7,
      "eval_avg_sts": 0.8443297683636638,
      "eval_sickr_spearman": 0.8256352291561755,
      "eval_stsb_spearman": 0.8630243075711521,
      "step": 375
    },
    {
      "epoch": 0.71,
      "learning_rate": 7.649969078540508e-06,
      "loss": 0.8604,
      "step": 380
    },
    {
      "epoch": 0.72,
      "learning_rate": 7.588126159554732e-06,
      "loss": 0.8272,
      "step": 390
    },
    {
      "epoch": 0.74,
      "learning_rate": 7.526283240568956e-06,
      "loss": 0.8352,
      "step": 400
    },
    {
      "epoch": 0.76,
      "learning_rate": 7.46444032158318e-06,
      "loss": 0.8819,
      "step": 410
    },
    {
      "epoch": 0.78,
      "learning_rate": 7.402597402597404e-06,
      "loss": 0.8073,
      "step": 420
    },
    {
      "epoch": 0.8,
      "learning_rate": 7.3407544836116275e-06,
      "loss": 0.8457,
      "step": 430
    },
    {
      "epoch": 0.82,
      "learning_rate": 7.278911564625851e-06,
      "loss": 0.8393,
      "step": 440
    },
    {
      "epoch": 0.83,
      "learning_rate": 7.217068645640075e-06,
      "loss": 0.81,
      "step": 450
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.155225726654299e-06,
      "loss": 0.8133,
      "step": 460
    },
    {
      "epoch": 0.87,
      "learning_rate": 7.093382807668523e-06,
      "loss": 0.8193,
      "step": 470
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.031539888682747e-06,
      "loss": 0.7912,
      "step": 480
    },
    {
      "epoch": 0.91,
      "learning_rate": 6.969696969696971e-06,
      "loss": 0.7821,
      "step": 490
    },
    {
      "epoch": 0.93,
      "learning_rate": 6.907854050711195e-06,
      "loss": 0.7864,
      "step": 500
    },
    {
      "epoch": 0.93,
      "eval_avg_sts": 0.8462257647791973,
      "eval_sickr_spearman": 0.8268360547232299,
      "eval_stsb_spearman": 0.8656154748351649,
      "step": 500
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.8460111317254185e-06,
      "loss": 0.8478,
      "step": 510
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.7841682127396415e-06,
      "loss": 0.7763,
      "step": 520
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.722325293753865e-06,
      "loss": 0.8213,
      "step": 530
    },
    {
      "epoch": 1.0,
      "learning_rate": 6.660482374768089e-06,
      "loss": 0.7716,
      "step": 540
    },
    {
      "epoch": 1.02,
      "learning_rate": 6.598639455782313e-06,
      "loss": 0.7478,
      "step": 550
    },
    {
      "epoch": 1.04,
      "learning_rate": 6.536796536796537e-06,
      "loss": 0.7475,
      "step": 560
    },
    {
      "epoch": 1.06,
      "learning_rate": 6.474953617810761e-06,
      "loss": 0.7442,
      "step": 570
    },
    {
      "epoch": 1.08,
      "learning_rate": 6.413110698824985e-06,
      "loss": 0.7604,
      "step": 580
    },
    {
      "epoch": 1.09,
      "learning_rate": 6.351267779839209e-06,
      "loss": 0.742,
      "step": 590
    },
    {
      "epoch": 1.11,
      "learning_rate": 6.2894248608534325e-06,
      "loss": 0.7343,
      "step": 600
    },
    {
      "epoch": 1.13,
      "learning_rate": 6.227581941867656e-06,
      "loss": 0.734,
      "step": 610
    },
    {
      "epoch": 1.15,
      "learning_rate": 6.16573902288188e-06,
      "loss": 0.7441,
      "step": 620
    },
    {
      "epoch": 1.16,
      "eval_avg_sts": 0.8465997739356157,
      "eval_sickr_spearman": 0.8266303855468717,
      "eval_stsb_spearman": 0.8665691623243595,
      "step": 625
    },
    {
      "epoch": 1.17,
      "learning_rate": 6.103896103896104e-06,
      "loss": 0.7822,
      "step": 630
    },
    {
      "epoch": 1.19,
      "learning_rate": 6.042053184910328e-06,
      "loss": 0.7358,
      "step": 640
    },
    {
      "epoch": 1.21,
      "learning_rate": 5.980210265924552e-06,
      "loss": 0.749,
      "step": 650
    },
    {
      "epoch": 1.22,
      "learning_rate": 5.918367346938776e-06,
      "loss": 0.7475,
      "step": 660
    },
    {
      "epoch": 1.24,
      "learning_rate": 5.856524427953e-06,
      "loss": 0.7897,
      "step": 670
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.7946815089672236e-06,
      "loss": 0.7362,
      "step": 680
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.7328385899814474e-06,
      "loss": 0.7563,
      "step": 690
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.670995670995671e-06,
      "loss": 0.7491,
      "step": 700
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.609152752009895e-06,
      "loss": 0.7776,
      "step": 710
    },
    {
      "epoch": 1.34,
      "learning_rate": 5.547309833024119e-06,
      "loss": 0.7346,
      "step": 720
    },
    {
      "epoch": 1.35,
      "learning_rate": 5.485466914038343e-06,
      "loss": 0.737,
      "step": 730
    },
    {
      "epoch": 1.37,
      "learning_rate": 5.423623995052567e-06,
      "loss": 0.7341,
      "step": 740
    },
    {
      "epoch": 1.39,
      "learning_rate": 5.361781076066791e-06,
      "loss": 0.7293,
      "step": 750
    },
    {
      "epoch": 1.39,
      "eval_avg_sts": 0.8490029126462879,
      "eval_sickr_spearman": 0.8293255067107672,
      "eval_stsb_spearman": 0.8686803185818085,
      "step": 750
    },
    {
      "epoch": 1.41,
      "learning_rate": 5.2999381570810146e-06,
      "loss": 0.7347,
      "step": 760
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.2380952380952384e-06,
      "loss": 0.742,
      "step": 770
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.176252319109462e-06,
      "loss": 0.7423,
      "step": 780
    },
    {
      "epoch": 1.47,
      "learning_rate": 5.114409400123686e-06,
      "loss": 0.7141,
      "step": 790
    },
    {
      "epoch": 1.48,
      "learning_rate": 5.05256648113791e-06,
      "loss": 0.75,
      "step": 800
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.990723562152134e-06,
      "loss": 0.7373,
      "step": 810
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.928880643166358e-06,
      "loss": 0.7547,
      "step": 820
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.867037724180582e-06,
      "loss": 0.7347,
      "step": 830
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.805194805194806e-06,
      "loss": 0.7323,
      "step": 840
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.7433518862090295e-06,
      "loss": 0.762,
      "step": 850
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.681508967223253e-06,
      "loss": 0.763,
      "step": 860
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.619666048237477e-06,
      "loss": 0.7183,
      "step": 870
    },
    {
      "epoch": 1.62,
      "eval_avg_sts": 0.8478878233181263,
      "eval_sickr_spearman": 0.8271554615477934,
      "eval_stsb_spearman": 0.8686201850884592,
      "step": 875
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.557823129251701e-06,
      "loss": 0.7052,
      "step": 880
    },
    {
      "epoch": 1.65,
      "learning_rate": 4.495980210265925e-06,
      "loss": 0.7586,
      "step": 890
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.434137291280149e-06,
      "loss": 0.7303,
      "step": 900
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.372294372294373e-06,
      "loss": 0.711,
      "step": 910
    },
    {
      "epoch": 1.71,
      "learning_rate": 4.310451453308597e-06,
      "loss": 0.7505,
      "step": 920
    },
    {
      "epoch": 1.73,
      "learning_rate": 4.2486085343228205e-06,
      "loss": 0.7287,
      "step": 930
    },
    {
      "epoch": 1.74,
      "learning_rate": 4.186765615337044e-06,
      "loss": 0.7288,
      "step": 940
    },
    {
      "epoch": 1.76,
      "learning_rate": 4.124922696351268e-06,
      "loss": 0.7317,
      "step": 950
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.063079777365492e-06,
      "loss": 0.7456,
      "step": 960
    },
    {
      "epoch": 1.8,
      "learning_rate": 4.001236858379716e-06,
      "loss": 0.7247,
      "step": 970
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.93939393939394e-06,
      "loss": 0.7423,
      "step": 980
    },
    {
      "epoch": 1.84,
      "learning_rate": 3.877551020408164e-06,
      "loss": 0.7257,
      "step": 990
    },
    {
      "epoch": 1.86,
      "learning_rate": 3.815708101422388e-06,
      "loss": 0.7655,
      "step": 1000
    },
    {
      "epoch": 1.86,
      "eval_avg_sts": 0.8485790233693684,
      "eval_sickr_spearman": 0.8282474486389888,
      "eval_stsb_spearman": 0.868910598099748,
      "step": 1000
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.753865182436611e-06,
      "loss": 0.6967,
      "step": 1010
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.6920222634508353e-06,
      "loss": 0.6964,
      "step": 1020
    },
    {
      "epoch": 1.91,
      "learning_rate": 3.6301793444650592e-06,
      "loss": 0.6989,
      "step": 1030
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.568336425479283e-06,
      "loss": 0.7278,
      "step": 1040
    },
    {
      "epoch": 1.95,
      "learning_rate": 3.506493506493507e-06,
      "loss": 0.7235,
      "step": 1050
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.444650587507731e-06,
      "loss": 0.7041,
      "step": 1060
    },
    {
      "epoch": 1.99,
      "learning_rate": 3.3828076685219547e-06,
      "loss": 0.7118,
      "step": 1070
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.3209647495361786e-06,
      "loss": 0.6951,
      "step": 1080
    },
    {
      "epoch": 2.02,
      "learning_rate": 3.2591218305504025e-06,
      "loss": 0.6957,
      "step": 1090
    },
    {
      "epoch": 2.04,
      "learning_rate": 3.1972789115646264e-06,
      "loss": 0.7068,
      "step": 1100
    },
    {
      "epoch": 2.06,
      "learning_rate": 3.1354359925788502e-06,
      "loss": 0.6662,
      "step": 1110
    },
    {
      "epoch": 2.08,
      "learning_rate": 3.0735930735930737e-06,
      "loss": 0.7002,
      "step": 1120
    },
    {
      "epoch": 2.09,
      "eval_avg_sts": 0.847001402508377,
      "eval_sickr_spearman": 0.8256772563699338,
      "eval_stsb_spearman": 0.86832554864682,
      "step": 1125
    },
    {
      "epoch": 2.1,
      "learning_rate": 3.0117501546072976e-06,
      "loss": 0.6668,
      "step": 1130
    },
    {
      "epoch": 2.12,
      "learning_rate": 2.9499072356215214e-06,
      "loss": 0.695,
      "step": 1140
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.8880643166357453e-06,
      "loss": 0.718,
      "step": 1150
    },
    {
      "epoch": 2.15,
      "learning_rate": 2.826221397649969e-06,
      "loss": 0.6953,
      "step": 1160
    },
    {
      "epoch": 2.17,
      "learning_rate": 2.764378478664193e-06,
      "loss": 0.6716,
      "step": 1170
    },
    {
      "epoch": 2.19,
      "learning_rate": 2.702535559678417e-06,
      "loss": 0.6765,
      "step": 1180
    },
    {
      "epoch": 2.21,
      "learning_rate": 2.640692640692641e-06,
      "loss": 0.6645,
      "step": 1190
    },
    {
      "epoch": 2.23,
      "learning_rate": 2.5788497217068647e-06,
      "loss": 0.6946,
      "step": 1200
    },
    {
      "epoch": 2.24,
      "learning_rate": 2.5170068027210886e-06,
      "loss": 0.6971,
      "step": 1210
    },
    {
      "epoch": 2.26,
      "learning_rate": 2.4551638837353125e-06,
      "loss": 0.7074,
      "step": 1220
    },
    {
      "epoch": 2.28,
      "learning_rate": 2.3933209647495363e-06,
      "loss": 0.6894,
      "step": 1230
    },
    {
      "epoch": 2.3,
      "learning_rate": 2.33147804576376e-06,
      "loss": 0.6821,
      "step": 1240
    },
    {
      "epoch": 2.32,
      "learning_rate": 2.269635126777984e-06,
      "loss": 0.6948,
      "step": 1250
    },
    {
      "epoch": 2.32,
      "eval_avg_sts": 0.8472029429037058,
      "eval_sickr_spearman": 0.8261643397696178,
      "eval_stsb_spearman": 0.8682415460377939,
      "step": 1250
    },
    {
      "epoch": 2.34,
      "learning_rate": 2.207792207792208e-06,
      "loss": 0.7039,
      "step": 1260
    },
    {
      "epoch": 2.36,
      "learning_rate": 2.145949288806432e-06,
      "loss": 0.6647,
      "step": 1270
    },
    {
      "epoch": 2.37,
      "learning_rate": 2.0841063698206557e-06,
      "loss": 0.6775,
      "step": 1280
    },
    {
      "epoch": 2.39,
      "learning_rate": 2.0222634508348796e-06,
      "loss": 0.6639,
      "step": 1290
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.9604205318491035e-06,
      "loss": 0.6936,
      "step": 1300
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.8985776128633273e-06,
      "loss": 0.6936,
      "step": 1310
    },
    {
      "epoch": 2.45,
      "learning_rate": 1.8367346938775512e-06,
      "loss": 0.6833,
      "step": 1320
    },
    {
      "epoch": 2.47,
      "learning_rate": 1.774891774891775e-06,
      "loss": 0.6785,
      "step": 1330
    },
    {
      "epoch": 2.49,
      "learning_rate": 1.7130488559059988e-06,
      "loss": 0.6837,
      "step": 1340
    },
    {
      "epoch": 2.5,
      "learning_rate": 1.6512059369202226e-06,
      "loss": 0.6743,
      "step": 1350
    },
    {
      "epoch": 2.52,
      "learning_rate": 1.5893630179344465e-06,
      "loss": 0.6912,
      "step": 1360
    },
    {
      "epoch": 2.54,
      "learning_rate": 1.5275200989486704e-06,
      "loss": 0.6798,
      "step": 1370
    },
    {
      "epoch": 2.55,
      "eval_avg_sts": 0.8477483274295515,
      "eval_sickr_spearman": 0.8258941648240284,
      "eval_stsb_spearman": 0.8696024900350746,
      "step": 1375
    },
    {
      "epoch": 2.56,
      "learning_rate": 1.4656771799628945e-06,
      "loss": 0.697,
      "step": 1380
    },
    {
      "epoch": 2.58,
      "learning_rate": 1.4038342609771183e-06,
      "loss": 0.6815,
      "step": 1390
    },
    {
      "epoch": 2.6,
      "learning_rate": 1.3419913419913422e-06,
      "loss": 0.6678,
      "step": 1400
    },
    {
      "epoch": 2.62,
      "learning_rate": 1.280148423005566e-06,
      "loss": 0.6709,
      "step": 1410
    },
    {
      "epoch": 2.63,
      "learning_rate": 1.2183055040197898e-06,
      "loss": 0.661,
      "step": 1420
    },
    {
      "epoch": 2.65,
      "learning_rate": 1.1564625850340136e-06,
      "loss": 0.6829,
      "step": 1430
    },
    {
      "epoch": 2.67,
      "learning_rate": 1.0946196660482377e-06,
      "loss": 0.6987,
      "step": 1440
    },
    {
      "epoch": 2.69,
      "learning_rate": 1.0327767470624614e-06,
      "loss": 0.696,
      "step": 1450
    },
    {
      "epoch": 2.71,
      "learning_rate": 9.709338280766853e-07,
      "loss": 0.7002,
      "step": 1460
    },
    {
      "epoch": 2.73,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.709,
      "step": 1470
    },
    {
      "epoch": 2.75,
      "learning_rate": 8.472479901051331e-07,
      "loss": 0.6794,
      "step": 1480
    },
    {
      "epoch": 2.76,
      "learning_rate": 7.854050711193569e-07,
      "loss": 0.6784,
      "step": 1490
    },
    {
      "epoch": 2.78,
      "learning_rate": 7.235621521335808e-07,
      "loss": 0.6644,
      "step": 1500
    },
    {
      "epoch": 2.78,
      "eval_avg_sts": 0.8478596119891653,
      "eval_sickr_spearman": 0.8263944087455064,
      "eval_stsb_spearman": 0.8693248152328242,
      "step": 1500
    },
    {
      "epoch": 2.8,
      "learning_rate": 6.617192331478047e-07,
      "loss": 0.6888,
      "step": 1510
    },
    {
      "epoch": 2.82,
      "learning_rate": 5.998763141620285e-07,
      "loss": 0.6594,
      "step": 1520
    },
    {
      "epoch": 2.84,
      "learning_rate": 5.380333951762524e-07,
      "loss": 0.6909,
      "step": 1530
    },
    {
      "epoch": 2.86,
      "learning_rate": 4.7619047619047623e-07,
      "loss": 0.6693,
      "step": 1540
    },
    {
      "epoch": 2.88,
      "learning_rate": 4.143475572047001e-07,
      "loss": 0.6671,
      "step": 1550
    },
    {
      "epoch": 2.89,
      "learning_rate": 3.5250463821892393e-07,
      "loss": 0.6589,
      "step": 1560
    },
    {
      "epoch": 2.91,
      "learning_rate": 2.9066171923314786e-07,
      "loss": 0.6687,
      "step": 1570
    },
    {
      "epoch": 2.93,
      "learning_rate": 2.288188002473717e-07,
      "loss": 0.659,
      "step": 1580
    },
    {
      "epoch": 2.95,
      "learning_rate": 1.6697588126159556e-07,
      "loss": 0.6724,
      "step": 1590
    },
    {
      "epoch": 2.97,
      "learning_rate": 1.0513296227581942e-07,
      "loss": 0.6762,
      "step": 1600
    },
    {
      "epoch": 2.99,
      "learning_rate": 4.3290043290043295e-08,
      "loss": 0.7098,
      "step": 1610
    },
    {
      "epoch": 3.0,
      "step": 1617,
      "train_runtime": 1994.4448,
      "train_samples_per_second": 0.811
    }
  ],
  "max_steps": 1617,
  "num_train_epochs": 3,
  "total_flos": 160111061011021824,
  "trial_name": null,
  "trial_params": null
}