{
  "best_metric": 108.29063415527344,
  "best_model_checkpoint": "./ViT_ordinary/checkpoint-2500",
  "epoch": 2.2893772893772892,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.1452785890167783e-06,
      "loss": 1143.4345,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.2905571780335565e-06,
      "loss": 1227.331,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.435835767050335e-06,
      "loss": 1257.7006,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.581114356067113e-06,
      "loss": 1220.7573,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.726392945083892e-06,
      "loss": 1314.9278,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.87167153410067e-06,
      "loss": 1161.0052,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.016950123117448e-06,
      "loss": 1195.8272,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.162228712134226e-06,
      "loss": 1135.2035,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.0307507301151004e-05,
      "loss": 1105.4266,
      "step": 90
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.1452785890167784e-05,
      "loss": 1138.5144,
      "step": 100
    },
    {
      "epoch": 0.09,
      "eval_RMSE": 45.47388458251953,
      "eval_loss": 2676.440673828125,
      "eval_runtime": 88.8721,
      "eval_samples_per_second": 91.941,
      "eval_steps_per_second": 2.881,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.259806447918456e-05,
      "loss": 936.6518,
      "step": 110
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.374334306820134e-05,
      "loss": 1003.3095,
      "step": 120
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.4888621657218118e-05,
      "loss": 994.7256,
      "step": 130
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.6033900246234896e-05,
      "loss": 962.0123,
      "step": 140
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.7179178835251674e-05,
      "loss": 1012.3558,
      "step": 150
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.8324457424268452e-05,
      "loss": 923.0986,
      "step": 160
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.946973601328523e-05,
      "loss": 1055.8317,
      "step": 170
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.0615014602302008e-05,
      "loss": 1189.4732,
      "step": 180
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.1760293191318786e-05,
      "loss": 998.1689,
      "step": 190
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.2905571780335568e-05,
      "loss": 940.4191,
      "step": 200
    },
    {
      "epoch": 0.18,
      "eval_RMSE": 44.35804748535156,
      "eval_loss": 2574.700927734375,
      "eval_runtime": 88.6183,
      "eval_samples_per_second": 92.204,
      "eval_steps_per_second": 2.889,
      "step": 200
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.4050850369352342e-05,
      "loss": 1081.1541,
      "step": 210
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.519612895836912e-05,
      "loss": 953.7207,
      "step": 220
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.63414075473859e-05,
      "loss": 920.4622,
      "step": 230
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.748668613640268e-05,
      "loss": 1037.0487,
      "step": 240
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.8631964725419458e-05,
      "loss": 991.3824,
      "step": 250
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.9777243314436236e-05,
      "loss": 1079.5839,
      "step": 260
    },
    {
      "epoch": 0.25,
      "learning_rate": 3.092252190345301e-05,
      "loss": 989.4474,
      "step": 270
    },
    {
      "epoch": 0.26,
      "learning_rate": 3.206780049246979e-05,
      "loss": 987.4904,
      "step": 280
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.321307908148657e-05,
      "loss": 1038.7738,
      "step": 290
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.435835767050335e-05,
      "loss": 921.6753,
      "step": 300
    },
    {
      "epoch": 0.27,
      "eval_RMSE": 43.82501220703125,
      "eval_loss": 2526.614501953125,
      "eval_runtime": 89.1648,
      "eval_samples_per_second": 91.639,
      "eval_steps_per_second": 2.871,
      "step": 300
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.550363625952013e-05,
      "loss": 909.3841,
      "step": 310
    },
    {
      "epoch": 0.29,
      "learning_rate": 3.6648914848536904e-05,
      "loss": 931.0681,
      "step": 320
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.7794193437553686e-05,
      "loss": 969.0332,
      "step": 330
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.893947202657046e-05,
      "loss": 1054.9324,
      "step": 340
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.008475061558724e-05,
      "loss": 989.6485,
      "step": 350
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.1230029204604016e-05,
      "loss": 940.8793,
      "step": 360
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.237530779362079e-05,
      "loss": 935.6209,
      "step": 370
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.352058638263757e-05,
      "loss": 1083.344,
      "step": 380
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.4665864971654354e-05,
      "loss": 918.0279,
      "step": 390
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.5811143560671135e-05,
      "loss": 938.6592,
      "step": 400
    },
    {
      "epoch": 0.37,
      "eval_RMSE": 43.11045837402344,
      "eval_loss": 2458.26171875,
      "eval_runtime": 89.3306,
      "eval_samples_per_second": 91.469,
      "eval_steps_per_second": 2.866,
      "step": 400
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.69564221496879e-05,
      "loss": 980.8854,
      "step": 410
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.8101700738704685e-05,
      "loss": 1039.0189,
      "step": 420
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.9246979327721466e-05,
      "loss": 876.2118,
      "step": 430
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.039225791673824e-05,
      "loss": 922.5582,
      "step": 440
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.153753650575502e-05,
      "loss": 918.9763,
      "step": 450
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.26828150947718e-05,
      "loss": 967.343,
      "step": 460
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.3828093683788585e-05,
      "loss": 866.294,
      "step": 470
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.497337227280536e-05,
      "loss": 866.6839,
      "step": 480
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.611865086182213e-05,
      "loss": 839.3744,
      "step": 490
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.7263929450838916e-05,
      "loss": 904.052,
      "step": 500
    },
    {
      "epoch": 0.46,
      "eval_RMSE": 42.12101364135742,
      "eval_loss": 2360.75439453125,
      "eval_runtime": 82.5537,
      "eval_samples_per_second": 98.978,
      "eval_steps_per_second": 3.101,
      "step": 500
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.840920803985569e-05,
      "loss": 770.1921,
      "step": 510
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.955448662887247e-05,
      "loss": 867.2703,
      "step": 520
    },
    {
      "epoch": 0.49,
      "learning_rate": 6.0699765217889246e-05,
      "loss": 803.1129,
      "step": 530
    },
    {
      "epoch": 0.49,
      "learning_rate": 6.184504380690602e-05,
      "loss": 838.8234,
      "step": 540
    },
    {
      "epoch": 0.5,
      "learning_rate": 6.29903223959228e-05,
      "loss": 854.0321,
      "step": 550
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.413560098493958e-05,
      "loss": 843.9535,
      "step": 560
    },
    {
      "epoch": 0.52,
      "learning_rate": 6.528087957395637e-05,
      "loss": 819.4999,
      "step": 570
    },
    {
      "epoch": 0.53,
      "learning_rate": 6.642615816297315e-05,
      "loss": 833.5234,
      "step": 580
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.757143675198991e-05,
      "loss": 919.277,
      "step": 590
    },
    {
      "epoch": 0.55,
      "learning_rate": 6.87167153410067e-05,
      "loss": 852.848,
      "step": 600
    },
    {
      "epoch": 0.55,
      "eval_RMSE": 40.79917526245117,
      "eval_loss": 2225.54150390625,
      "eval_runtime": 90.1848,
      "eval_samples_per_second": 90.603,
      "eval_steps_per_second": 2.839,
      "step": 600
    },
    {
      "epoch": 0.56,
      "learning_rate": 6.986199393002348e-05,
      "loss": 750.3481,
      "step": 610
    },
    {
      "epoch": 0.57,
      "learning_rate": 7.100727251904026e-05,
      "loss": 879.5618,
      "step": 620
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.215255110805703e-05,
      "loss": 797.6468,
      "step": 630
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.329782969707381e-05,
      "loss": 835.0447,
      "step": 640
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.444310828609059e-05,
      "loss": 755.9302,
      "step": 650
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.558838687510737e-05,
      "loss": 749.4049,
      "step": 660
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.673366546412415e-05,
      "loss": 727.4822,
      "step": 670
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.787894405314092e-05,
      "loss": 664.3502,
      "step": 680
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.90242226421577e-05,
      "loss": 737.5342,
      "step": 690
    },
    {
      "epoch": 0.64,
      "learning_rate": 8.016950123117448e-05,
      "loss": 685.9979,
      "step": 700
    },
    {
      "epoch": 0.64,
      "eval_RMSE": 39.182891845703125,
      "eval_loss": 2045.955322265625,
      "eval_runtime": 86.8947,
      "eval_samples_per_second": 94.033,
      "eval_steps_per_second": 2.946,
      "step": 700
    },
    {
      "epoch": 0.65,
      "learning_rate": 8.131477982019125e-05,
      "loss": 818.1389,
      "step": 710
    },
    {
      "epoch": 0.66,
      "learning_rate": 8.246005840920803e-05,
      "loss": 679.9854,
      "step": 720
    },
    {
      "epoch": 0.67,
      "learning_rate": 8.360533699822481e-05,
      "loss": 696.1048,
      "step": 730
    },
    {
      "epoch": 0.68,
      "learning_rate": 8.475061558724158e-05,
      "loss": 694.8774,
      "step": 740
    },
    {
      "epoch": 0.69,
      "learning_rate": 8.589589417625838e-05,
      "loss": 673.0095,
      "step": 750
    },
    {
      "epoch": 0.7,
      "learning_rate": 8.704117276527514e-05,
      "loss": 638.9566,
      "step": 760
    },
    {
      "epoch": 0.71,
      "learning_rate": 8.818645135429193e-05,
      "loss": 660.6367,
      "step": 770
    },
    {
      "epoch": 0.71,
      "learning_rate": 8.933172994330871e-05,
      "loss": 622.8923,
      "step": 780
    },
    {
      "epoch": 0.72,
      "learning_rate": 9.047700853232548e-05,
      "loss": 570.6501,
      "step": 790
    },
    {
      "epoch": 0.73,
      "learning_rate": 9.162228712134227e-05,
      "loss": 612.6461,
      "step": 800
    },
    {
      "epoch": 0.73,
      "eval_RMSE": 37.14878845214844,
      "eval_loss": 1821.157958984375,
      "eval_runtime": 90.6758,
      "eval_samples_per_second": 90.112,
      "eval_steps_per_second": 2.823,
      "step": 800
    },
    {
      "epoch": 0.74,
      "learning_rate": 9.276756571035904e-05,
      "loss": 632.5693,
      "step": 810
    },
    {
      "epoch": 0.75,
      "learning_rate": 9.39128442993758e-05,
      "loss": 633.8072,
      "step": 820
    },
    {
      "epoch": 0.76,
      "learning_rate": 9.50581228883926e-05,
      "loss": 625.9993,
      "step": 830
    },
    {
      "epoch": 0.77,
      "learning_rate": 9.620340147740937e-05,
      "loss": 616.1023,
      "step": 840
    },
    {
      "epoch": 0.78,
      "learning_rate": 9.734868006642615e-05,
      "loss": 542.3134,
      "step": 850
    },
    {
      "epoch": 0.79,
      "learning_rate": 9.849395865544293e-05,
      "loss": 510.9979,
      "step": 860
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.96392372444597e-05,
      "loss": 527.1517,
      "step": 870
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00010078451583347648,
      "loss": 595.9219,
      "step": 880
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00010192979442249326,
      "loss": 480.4347,
      "step": 890
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00010307507301151004,
      "loss": 487.5384,
      "step": 900
    },
    {
      "epoch": 0.82,
      "eval_RMSE": 34.58900833129883,
      "eval_loss": 1558.3662109375,
      "eval_runtime": 89.9793,
      "eval_samples_per_second": 90.81,
      "eval_steps_per_second": 2.845,
      "step": 900
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00010422035160052684,
      "loss": 538.8044,
      "step": 910
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001053656301895436,
      "loss": 438.5807,
      "step": 920
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00010651090877856037,
      "loss": 492.5742,
      "step": 930
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010765618736757717,
      "loss": 368.3077,
      "step": 940
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00010880146595659392,
      "loss": 374.0631,
      "step": 950
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00010994674454561072,
      "loss": 505.5752,
      "step": 960
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001110920231346275,
      "loss": 392.0846,
      "step": 970
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011223730172364425,
      "loss": 348.8105,
      "step": 980
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00011338258031266105,
      "loss": 351.132,
      "step": 990
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00011452785890167783,
      "loss": 363.1367,
      "step": 1000
    },
    {
      "epoch": 0.92,
      "eval_RMSE": 31.56056785583496,
      "eval_loss": 1274.2431640625,
      "eval_runtime": 89.8821,
      "eval_samples_per_second": 90.908,
      "eval_steps_per_second": 2.848,
      "step": 1000
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001156731374906946,
      "loss": 296.5691,
      "step": 1010
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011681841607971138,
      "loss": 357.6329,
      "step": 1020
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011796369466872816,
      "loss": 361.3535,
      "step": 1030
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00011910897325774494,
      "loss": 322.6138,
      "step": 1040
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00012025425184676171,
      "loss": 405.8568,
      "step": 1050
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00012139953043577849,
      "loss": 352.4393,
      "step": 1060
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00012254480902479527,
      "loss": 367.3307,
      "step": 1070
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00012369008761381204,
      "loss": 300.1264,
      "step": 1080
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00012483536620282884,
      "loss": 344.8634,
      "step": 1090
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001259806447918456,
      "loss": 275.3597,
      "step": 1100
    },
    {
      "epoch": 1.01,
      "eval_RMSE": 28.991735458374023,
      "eval_loss": 1044.326416015625,
      "eval_runtime": 90.499,
      "eval_samples_per_second": 90.288,
      "eval_steps_per_second": 2.829,
      "step": 1100
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00012712592338086237,
      "loss": 354.2523,
      "step": 1110
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00012827120196987917,
      "loss": 283.569,
      "step": 1120
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00012941648055889594,
      "loss": 248.2783,
      "step": 1130
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013056175914791273,
      "loss": 262.5986,
      "step": 1140
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001317070377369295,
      "loss": 294.735,
      "step": 1150
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001328523163259463,
      "loss": 301.2489,
      "step": 1160
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00013399759491496306,
      "loss": 252.3795,
      "step": 1170
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00013514287350397983,
      "loss": 247.8596,
      "step": 1180
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00013628815209299662,
      "loss": 253.8303,
      "step": 1190
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001374334306820134,
      "loss": 251.5496,
      "step": 1200
    },
    {
      "epoch": 1.1,
      "eval_RMSE": 27.961669921875,
      "eval_loss": 858.2109985351562,
      "eval_runtime": 90.7351,
      "eval_samples_per_second": 90.053,
      "eval_steps_per_second": 2.821,
      "step": 1200
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00013857870927103016,
      "loss": 207.0559,
      "step": 1210
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00013972398786004695,
      "loss": 231.4458,
      "step": 1220
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014086926644906372,
      "loss": 252.8603,
      "step": 1230
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00014201454503808052,
      "loss": 204.8269,
      "step": 1240
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00014315982362709729,
      "loss": 230.3754,
      "step": 1250
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00014430510221611405,
      "loss": 170.1902,
      "step": 1260
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00014545038080513085,
      "loss": 207.8812,
      "step": 1270
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00014659565939414762,
      "loss": 250.5713,
      "step": 1280
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00014774093798316438,
      "loss": 210.8263,
      "step": 1290
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00014888621657218118,
      "loss": 232.956,
      "step": 1300
    },
    {
      "epoch": 1.19,
      "eval_RMSE": 28.184946060180664,
      "eval_loss": 733.7390747070312,
      "eval_runtime": 89.6232,
      "eval_samples_per_second": 91.171,
      "eval_steps_per_second": 2.856,
      "step": 1300
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00015003149516119795,
      "loss": 209.1999,
      "step": 1310
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00015117677375021474,
      "loss": 219.4115,
      "step": 1320
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001523220523392315,
      "loss": 142.051,
      "step": 1330
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001534673309282483,
      "loss": 182.2509,
      "step": 1340
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00015461260951726507,
      "loss": 168.6032,
      "step": 1350
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00015575788810628184,
      "loss": 171.8442,
      "step": 1360
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00015690316669529864,
      "loss": 171.8282,
      "step": 1370
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001580484452843154,
      "loss": 186.681,
      "step": 1380
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00015919372387333217,
      "loss": 173.0698,
      "step": 1390
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00016033900246234897,
      "loss": 148.5199,
      "step": 1400
    },
    {
      "epoch": 1.28,
      "eval_RMSE": 27.53377914428711,
      "eval_loss": 608.1200561523438,
      "eval_runtime": 87.4424,
      "eval_samples_per_second": 93.444,
      "eval_steps_per_second": 2.928,
      "step": 1400
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00016148428105136573,
      "loss": 195.879,
      "step": 1410
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001626295596403825,
      "loss": 161.7053,
      "step": 1420
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001637748382293993,
      "loss": 144.2296,
      "step": 1430
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00016492011681841607,
      "loss": 146.4364,
      "step": 1440
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00016606539540743283,
      "loss": 144.3109,
      "step": 1450
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00016721067399644963,
      "loss": 184.0622,
      "step": 1460
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00016835595258546642,
      "loss": 127.7919,
      "step": 1470
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00016950123117448316,
      "loss": 133.7518,
      "step": 1480
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017064650976349996,
      "loss": 112.2735,
      "step": 1490
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017179178835251675,
      "loss": 126.9139,
      "step": 1500
    },
    {
      "epoch": 1.37,
      "eval_RMSE": 26.30722999572754,
      "eval_loss": 453.3481750488281,
      "eval_runtime": 88.0738,
      "eval_samples_per_second": 92.774,
      "eval_steps_per_second": 2.907,
      "step": 1500
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00017293706694153352,
      "loss": 134.5855,
      "step": 1510
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001740823455305503,
      "loss": 124.9829,
      "step": 1520
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00017522762411956708,
      "loss": 111.1943,
      "step": 1530
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00017637290270858385,
      "loss": 124.6046,
      "step": 1540
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00017751818129760062,
      "loss": 97.5316,
      "step": 1550
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00017866345988661742,
      "loss": 130.0623,
      "step": 1560
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001798087384756342,
      "loss": 140.2047,
      "step": 1570
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00018095401706465095,
      "loss": 111.0409,
      "step": 1580
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00018209929565366775,
      "loss": 112.2171,
      "step": 1590
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00018324457424268454,
      "loss": 113.2355,
      "step": 1600
    },
    {
      "epoch": 1.47,
      "eval_RMSE": 26.593936920166016,
      "eval_loss": 397.5113220214844,
      "eval_runtime": 89.5143,
      "eval_samples_per_second": 91.282,
      "eval_steps_per_second": 2.86,
      "step": 1600
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00018438985283170128,
      "loss": 121.8388,
      "step": 1610
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00018553513142071808,
      "loss": 116.3681,
      "step": 1620
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00018668041000973487,
      "loss": 113.7981,
      "step": 1630
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001878256885987516,
      "loss": 119.2628,
      "step": 1640
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001889709671877684,
      "loss": 93.8756,
      "step": 1650
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0001901162457767852,
      "loss": 118.5608,
      "step": 1660
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00019126152436580197,
      "loss": 101.4624,
      "step": 1670
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00019240680295481874,
      "loss": 96.8405,
      "step": 1680
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00019355208154383553,
      "loss": 93.3038,
      "step": 1690
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001946973601328523,
      "loss": 99.5798,
      "step": 1700
    },
    {
      "epoch": 1.56,
      "eval_RMSE": 25.650577545166016,
      "eval_loss": 304.5827331542969,
      "eval_runtime": 88.1891,
      "eval_samples_per_second": 92.653,
      "eval_steps_per_second": 2.903,
      "step": 1700
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00019584263872186907,
      "loss": 116.748,
      "step": 1710
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00019698791731088586,
      "loss": 87.1141,
      "step": 1720
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00019813319589990266,
      "loss": 97.8321,
      "step": 1730
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001992784744889194,
      "loss": 79.7827,
      "step": 1740
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019995291632467376,
      "loss": 98.2981,
      "step": 1750
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00019982566314811633,
      "loss": 68.1837,
      "step": 1760
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001996984099715589,
      "loss": 88.1333,
      "step": 1770
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001995711567950015,
      "loss": 84.4777,
      "step": 1780
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00019944390361844406,
      "loss": 75.6494,
      "step": 1790
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00019931665044188666,
      "loss": 101.6581,
      "step": 1800
    },
    {
      "epoch": 1.65,
      "eval_RMSE": 24.347003936767578,
      "eval_loss": 246.870849609375,
      "eval_runtime": 91.7415,
      "eval_samples_per_second": 89.066,
      "eval_steps_per_second": 2.79,
      "step": 1800
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00019918939726532923,
      "loss": 79.9642,
      "step": 1810
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00019906214408877182,
      "loss": 67.1507,
      "step": 1820
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001989348909122144,
      "loss": 78.1831,
      "step": 1830
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.000198807637735657,
      "loss": 72.3693,
      "step": 1840
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00019868038455909956,
      "loss": 73.2772,
      "step": 1850
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00019855313138254216,
      "loss": 73.4863,
      "step": 1860
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00019842587820598472,
      "loss": 68.861,
      "step": 1870
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001982986250294273,
      "loss": 70.2734,
      "step": 1880
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00019817137185286986,
      "loss": 80.5998,
      "step": 1890
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00019804411867631246,
      "loss": 74.3472,
      "step": 1900
    },
    {
      "epoch": 1.74,
      "eval_RMSE": 25.971708297729492,
      "eval_loss": 242.7896270751953,
      "eval_runtime": 89.3685,
      "eval_samples_per_second": 91.43,
      "eval_steps_per_second": 2.865,
      "step": 1900
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00019791686549975503,
      "loss": 88.6437,
      "step": 1910
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00019778961232319763,
      "loss": 95.2708,
      "step": 1920
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001976623591466402,
      "loss": 114.3341,
      "step": 1930
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001975351059700828,
      "loss": 67.5784,
      "step": 1940
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00019740785279352536,
      "loss": 73.2939,
      "step": 1950
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00019728059961696793,
      "loss": 68.14,
      "step": 1960
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00019715334644041053,
      "loss": 69.5453,
      "step": 1970
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001970260932638531,
      "loss": 81.5987,
      "step": 1980
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001968988400872957,
      "loss": 71.576,
      "step": 1990
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00019677158691073826,
      "loss": 77.3393,
      "step": 2000
    },
    {
      "epoch": 1.83,
      "eval_RMSE": 25.02290153503418,
      "eval_loss": 158.2856903076172,
      "eval_runtime": 91.421,
      "eval_samples_per_second": 89.378,
      "eval_steps_per_second": 2.8,
      "step": 2000
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00019664433373418083,
      "loss": 71.151,
      "step": 2010
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001965170805576234,
      "loss": 57.0214,
      "step": 2020
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.000196389827381066,
      "loss": 60.4723,
      "step": 2030
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00019626257420450857,
      "loss": 61.1471,
      "step": 2040
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00019613532102795116,
      "loss": 64.6843,
      "step": 2050
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00019600806785139373,
      "loss": 80.3143,
      "step": 2060
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00019588081467483633,
      "loss": 61.2826,
      "step": 2070
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001957535614982789,
      "loss": 87.4192,
      "step": 2080
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001956263083217215,
      "loss": 80.7123,
      "step": 2090
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00019549905514516406,
      "loss": 69.8205,
      "step": 2100
    },
    {
      "epoch": 1.92,
      "eval_RMSE": 26.108875274658203,
      "eval_loss": 163.57669067382812,
      "eval_runtime": 88.3567,
      "eval_samples_per_second": 92.477,
      "eval_steps_per_second": 2.897,
      "step": 2100
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00019537180196860666,
      "loss": 68.615,
      "step": 2110
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00019524454879204923,
      "loss": 66.9629,
      "step": 2120
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00019511729561549182,
      "loss": 66.9707,
      "step": 2130
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00019499004243893437,
      "loss": 61.8375,
      "step": 2140
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00019486278926237696,
      "loss": 86.5031,
      "step": 2150
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00019473553608581953,
      "loss": 59.317,
      "step": 2160
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00019460828290926213,
      "loss": 46.4391,
      "step": 2170
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001944810297327047,
      "loss": 66.9274,
      "step": 2180
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001943537765561473,
      "loss": 60.0429,
      "step": 2190
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00019422652337958986,
      "loss": 49.6239,
      "step": 2200
    },
    {
      "epoch": 2.01,
      "eval_RMSE": 25.317358016967773,
      "eval_loss": 155.91978454589844,
      "eval_runtime": 89.937,
      "eval_samples_per_second": 90.852,
      "eval_steps_per_second": 2.846,
      "step": 2200
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00019409927020303243,
      "loss": 48.8787,
      "step": 2210
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00019397201702647503,
      "loss": 54.4583,
      "step": 2220
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001938447638499176,
      "loss": 51.7232,
      "step": 2230
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001937175106733602,
      "loss": 55.3078,
      "step": 2240
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00019359025749680276,
      "loss": 52.4878,
      "step": 2250
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00019346300432024533,
      "loss": 51.498,
      "step": 2260
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001933357511436879,
      "loss": 55.693,
      "step": 2270
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0001932084979671305,
      "loss": 60.7052,
      "step": 2280
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00019308124479057307,
      "loss": 57.5329,
      "step": 2290
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00019295399161401567,
      "loss": 49.7357,
      "step": 2300
    },
    {
      "epoch": 2.11,
      "eval_RMSE": 25.681665420532227,
      "eval_loss": 113.43367004394531,
      "eval_runtime": 88.8092,
      "eval_samples_per_second": 92.006,
      "eval_steps_per_second": 2.883,
      "step": 2300
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00019282673843745823,
      "loss": 40.8768,
      "step": 2310
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00019269948526090083,
      "loss": 51.1638,
      "step": 2320
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001925722320843434,
      "loss": 53.8347,
      "step": 2330
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.000192444978907786,
      "loss": 61.9818,
      "step": 2340
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00019231772573122857,
      "loss": 65.0766,
      "step": 2350
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00019219047255467116,
      "loss": 54.4025,
      "step": 2360
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00019206321937811373,
      "loss": 43.9705,
      "step": 2370
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00019193596620155633,
      "loss": 58.1021,
      "step": 2380
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00019180871302499887,
      "loss": 41.1698,
      "step": 2390
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00019168145984844147,
      "loss": 60.9505,
      "step": 2400
    },
    {
      "epoch": 2.2,
      "eval_RMSE": 25.213809967041016,
      "eval_loss": 128.33050537109375,
      "eval_runtime": 89.5513,
      "eval_samples_per_second": 91.244,
      "eval_steps_per_second": 2.859,
      "step": 2400
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00019155420667188404,
      "loss": 50.3419,
      "step": 2410
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00019142695349532663,
      "loss": 34.2566,
      "step": 2420
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001912997003187692,
      "loss": 45.824,
      "step": 2430
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001911724471422118,
      "loss": 51.5597,
      "step": 2440
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00019104519396565437,
      "loss": 63.5468,
      "step": 2450
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00019091794078909694,
      "loss": 47.8715,
      "step": 2460
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00019079068761253953,
      "loss": 56.6548,
      "step": 2470
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001906634344359821,
      "loss": 46.0047,
      "step": 2480
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0001905361812594247,
      "loss": 55.3212,
      "step": 2490
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00019040892808286727,
      "loss": 49.0666,
      "step": 2500
    },
    {
      "epoch": 2.29,
      "eval_RMSE": 26.342649459838867,
      "eval_loss": 108.29063415527344,
      "eval_runtime": 89.6891,
      "eval_samples_per_second": 91.104,
      "eval_steps_per_second": 2.854,
      "step": 2500
    }
  ],
  "max_steps": 4368,
  "num_train_epochs": 4,
  "total_flos": 9.294770879473766e+18,
  "trial_name": null,
  "trial_params": null
}