vit-base-cats-vs-dogs / trainer_state.json
{
"best_metric": 0.036893460899591446,
"best_model_checkpoint": "./cats_vs_dogs_outputs/checkpoint-2488",
"epoch": 1.0,
"global_step": 2488,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.00019919614147909968,
"loss": 0.4243,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 0.00019839228295819936,
"loss": 0.2515,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 0.00019758842443729903,
"loss": 0.2728,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 0.00019678456591639874,
"loss": 0.2011,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 0.0001959807073954984,
"loss": 0.1596,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 0.00019517684887459809,
"loss": 0.2641,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 0.00019437299035369776,
"loss": 0.2891,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 0.00019356913183279743,
"loss": 0.1983,
"step": 80
},
{
"epoch": 0.04,
"learning_rate": 0.0001927652733118971,
"loss": 0.1355,
"step": 90
},
{
"epoch": 0.04,
"learning_rate": 0.00019196141479099678,
"loss": 0.1282,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 0.00019115755627009649,
"loss": 0.1681,
"step": 110
},
{
"epoch": 0.05,
"learning_rate": 0.00019035369774919616,
"loss": 0.4071,
"step": 120
},
{
"epoch": 0.05,
"learning_rate": 0.00018954983922829584,
"loss": 0.467,
"step": 130
},
{
"epoch": 0.06,
"learning_rate": 0.0001887459807073955,
"loss": 0.1196,
"step": 140
},
{
"epoch": 0.06,
"learning_rate": 0.00018794212218649519,
"loss": 0.2998,
"step": 150
},
{
"epoch": 0.06,
"learning_rate": 0.00018713826366559486,
"loss": 0.2774,
"step": 160
},
{
"epoch": 0.07,
"learning_rate": 0.00018633440514469454,
"loss": 0.3209,
"step": 170
},
{
"epoch": 0.07,
"learning_rate": 0.0001855305466237942,
"loss": 0.1764,
"step": 180
},
{
"epoch": 0.08,
"learning_rate": 0.0001847266881028939,
"loss": 0.3375,
"step": 190
},
{
"epoch": 0.08,
"learning_rate": 0.0001839228295819936,
"loss": 0.2445,
"step": 200
},
{
"epoch": 0.08,
"learning_rate": 0.00018311897106109326,
"loss": 0.2098,
"step": 210
},
{
"epoch": 0.09,
"learning_rate": 0.00018231511254019294,
"loss": 0.1775,
"step": 220
},
{
"epoch": 0.09,
"learning_rate": 0.0001815112540192926,
"loss": 0.2583,
"step": 230
},
{
"epoch": 0.1,
"learning_rate": 0.00018070739549839229,
"loss": 0.1765,
"step": 240
},
{
"epoch": 0.1,
"learning_rate": 0.00017990353697749196,
"loss": 0.1831,
"step": 250
},
{
"epoch": 0.1,
"learning_rate": 0.00017909967845659166,
"loss": 0.1802,
"step": 260
},
{
"epoch": 0.11,
"learning_rate": 0.00017829581993569134,
"loss": 0.283,
"step": 270
},
{
"epoch": 0.11,
"learning_rate": 0.000177491961414791,
"loss": 0.2873,
"step": 280
},
{
"epoch": 0.12,
"learning_rate": 0.0001766881028938907,
"loss": 0.2789,
"step": 290
},
{
"epoch": 0.12,
"learning_rate": 0.00017588424437299036,
"loss": 0.4105,
"step": 300
},
{
"epoch": 0.12,
"learning_rate": 0.00017508038585209004,
"loss": 0.2762,
"step": 310
},
{
"epoch": 0.13,
"learning_rate": 0.0001742765273311897,
"loss": 0.1414,
"step": 320
},
{
"epoch": 0.13,
"learning_rate": 0.0001734726688102894,
"loss": 0.2126,
"step": 330
},
{
"epoch": 0.14,
"learning_rate": 0.0001726688102893891,
"loss": 0.3115,
"step": 340
},
{
"epoch": 0.14,
"learning_rate": 0.00017186495176848876,
"loss": 0.2029,
"step": 350
},
{
"epoch": 0.14,
"learning_rate": 0.00017106109324758844,
"loss": 0.0867,
"step": 360
},
{
"epoch": 0.15,
"learning_rate": 0.0001702572347266881,
"loss": 0.1312,
"step": 370
},
{
"epoch": 0.15,
"learning_rate": 0.0001694533762057878,
"loss": 0.5391,
"step": 380
},
{
"epoch": 0.16,
"learning_rate": 0.00016864951768488746,
"loss": 0.2131,
"step": 390
},
{
"epoch": 0.16,
"learning_rate": 0.00016784565916398716,
"loss": 0.2431,
"step": 400
},
{
"epoch": 0.16,
"learning_rate": 0.00016704180064308684,
"loss": 0.2088,
"step": 410
},
{
"epoch": 0.17,
"learning_rate": 0.0001662379421221865,
"loss": 0.1451,
"step": 420
},
{
"epoch": 0.17,
"learning_rate": 0.0001654340836012862,
"loss": 0.1635,
"step": 430
},
{
"epoch": 0.18,
"learning_rate": 0.00016463022508038586,
"loss": 0.2134,
"step": 440
},
{
"epoch": 0.18,
"learning_rate": 0.00016382636655948554,
"loss": 0.3112,
"step": 450
},
{
"epoch": 0.18,
"learning_rate": 0.0001630225080385852,
"loss": 0.2105,
"step": 460
},
{
"epoch": 0.19,
"learning_rate": 0.0001622186495176849,
"loss": 0.1925,
"step": 470
},
{
"epoch": 0.19,
"learning_rate": 0.0001614147909967846,
"loss": 0.0771,
"step": 480
},
{
"epoch": 0.2,
"learning_rate": 0.00016061093247588426,
"loss": 0.1727,
"step": 490
},
{
"epoch": 0.2,
"learning_rate": 0.00015980707395498394,
"loss": 0.1623,
"step": 500
},
{
"epoch": 0.2,
"learning_rate": 0.0001590032154340836,
"loss": 0.3692,
"step": 510
},
{
"epoch": 0.21,
"learning_rate": 0.0001581993569131833,
"loss": 0.0848,
"step": 520
},
{
"epoch": 0.21,
"learning_rate": 0.00015739549839228296,
"loss": 0.1735,
"step": 530
},
{
"epoch": 0.22,
"learning_rate": 0.00015659163987138264,
"loss": 0.2304,
"step": 540
},
{
"epoch": 0.22,
"learning_rate": 0.00015578778135048234,
"loss": 0.1427,
"step": 550
},
{
"epoch": 0.23,
"learning_rate": 0.00015498392282958201,
"loss": 0.11,
"step": 560
},
{
"epoch": 0.23,
"learning_rate": 0.0001541800643086817,
"loss": 0.1318,
"step": 570
},
{
"epoch": 0.23,
"learning_rate": 0.00015337620578778136,
"loss": 0.3012,
"step": 580
},
{
"epoch": 0.24,
"learning_rate": 0.00015257234726688104,
"loss": 0.1292,
"step": 590
},
{
"epoch": 0.24,
"learning_rate": 0.0001517684887459807,
"loss": 0.0977,
"step": 600
},
{
"epoch": 0.25,
"learning_rate": 0.0001509646302250804,
"loss": 0.121,
"step": 610
},
{
"epoch": 0.25,
"learning_rate": 0.0001501607717041801,
"loss": 0.1502,
"step": 620
},
{
"epoch": 0.25,
"learning_rate": 0.00014935691318327976,
"loss": 0.0814,
"step": 630
},
{
"epoch": 0.26,
"learning_rate": 0.00014855305466237944,
"loss": 0.2753,
"step": 640
},
{
"epoch": 0.26,
"learning_rate": 0.00014774919614147911,
"loss": 0.1735,
"step": 650
},
{
"epoch": 0.27,
"learning_rate": 0.0001469453376205788,
"loss": 0.065,
"step": 660
},
{
"epoch": 0.27,
"learning_rate": 0.00014614147909967846,
"loss": 0.1937,
"step": 670
},
{
"epoch": 0.27,
"learning_rate": 0.00014533762057877814,
"loss": 0.1878,
"step": 680
},
{
"epoch": 0.28,
"learning_rate": 0.00014453376205787784,
"loss": 0.2737,
"step": 690
},
{
"epoch": 0.28,
"learning_rate": 0.00014372990353697752,
"loss": 0.08,
"step": 700
},
{
"epoch": 0.29,
"learning_rate": 0.0001429260450160772,
"loss": 0.2417,
"step": 710
},
{
"epoch": 0.29,
"learning_rate": 0.00014212218649517686,
"loss": 0.1485,
"step": 720
},
{
"epoch": 0.29,
"learning_rate": 0.00014131832797427654,
"loss": 0.1943,
"step": 730
},
{
"epoch": 0.3,
"learning_rate": 0.00014051446945337621,
"loss": 0.1168,
"step": 740
},
{
"epoch": 0.3,
"learning_rate": 0.0001397106109324759,
"loss": 0.271,
"step": 750
},
{
"epoch": 0.31,
"learning_rate": 0.0001389067524115756,
"loss": 0.1807,
"step": 760
},
{
"epoch": 0.31,
"learning_rate": 0.00013810289389067527,
"loss": 0.2312,
"step": 770
},
{
"epoch": 0.31,
"learning_rate": 0.00013729903536977494,
"loss": 0.2052,
"step": 780
},
{
"epoch": 0.32,
"learning_rate": 0.00013649517684887462,
"loss": 0.2927,
"step": 790
},
{
"epoch": 0.32,
"learning_rate": 0.0001356913183279743,
"loss": 0.2083,
"step": 800
},
{
"epoch": 0.33,
"learning_rate": 0.00013488745980707396,
"loss": 0.1997,
"step": 810
},
{
"epoch": 0.33,
"learning_rate": 0.00013408360128617364,
"loss": 0.0869,
"step": 820
},
{
"epoch": 0.33,
"learning_rate": 0.00013327974276527331,
"loss": 0.1731,
"step": 830
},
{
"epoch": 0.34,
"learning_rate": 0.00013247588424437302,
"loss": 0.2085,
"step": 840
},
{
"epoch": 0.34,
"learning_rate": 0.0001316720257234727,
"loss": 0.0884,
"step": 850
},
{
"epoch": 0.35,
"learning_rate": 0.00013086816720257237,
"loss": 0.1051,
"step": 860
},
{
"epoch": 0.35,
"learning_rate": 0.00013006430868167204,
"loss": 0.2395,
"step": 870
},
{
"epoch": 0.35,
"learning_rate": 0.00012926045016077172,
"loss": 0.1216,
"step": 880
},
{
"epoch": 0.36,
"learning_rate": 0.0001284565916398714,
"loss": 0.234,
"step": 890
},
{
"epoch": 0.36,
"learning_rate": 0.00012765273311897106,
"loss": 0.1559,
"step": 900
},
{
"epoch": 0.37,
"learning_rate": 0.00012684887459807077,
"loss": 0.2665,
"step": 910
},
{
"epoch": 0.37,
"learning_rate": 0.00012604501607717044,
"loss": 0.0772,
"step": 920
},
{
"epoch": 0.37,
"learning_rate": 0.00012524115755627012,
"loss": 0.1792,
"step": 930
},
{
"epoch": 0.38,
"learning_rate": 0.0001244372990353698,
"loss": 0.1338,
"step": 940
},
{
"epoch": 0.38,
"learning_rate": 0.00012363344051446947,
"loss": 0.1326,
"step": 950
},
{
"epoch": 0.39,
"learning_rate": 0.00012282958199356914,
"loss": 0.1114,
"step": 960
},
{
"epoch": 0.39,
"learning_rate": 0.0001220257234726688,
"loss": 0.1606,
"step": 970
},
{
"epoch": 0.39,
"learning_rate": 0.0001212218649517685,
"loss": 0.0651,
"step": 980
},
{
"epoch": 0.4,
"learning_rate": 0.00012041800643086818,
"loss": 0.1518,
"step": 990
},
{
"epoch": 0.4,
"learning_rate": 0.00011961414790996785,
"loss": 0.2242,
"step": 1000
},
{
"epoch": 0.41,
"learning_rate": 0.00011881028938906753,
"loss": 0.2432,
"step": 1010
},
{
"epoch": 0.41,
"learning_rate": 0.0001180064308681672,
"loss": 0.2233,
"step": 1020
},
{
"epoch": 0.41,
"learning_rate": 0.00011720257234726688,
"loss": 0.2343,
"step": 1030
},
{
"epoch": 0.42,
"learning_rate": 0.00011639871382636655,
"loss": 0.1798,
"step": 1040
},
{
"epoch": 0.42,
"learning_rate": 0.00011559485530546625,
"loss": 0.2162,
"step": 1050
},
{
"epoch": 0.43,
"learning_rate": 0.00011479099678456593,
"loss": 0.178,
"step": 1060
},
{
"epoch": 0.43,
"learning_rate": 0.0001139871382636656,
"loss": 0.1113,
"step": 1070
},
{
"epoch": 0.43,
"learning_rate": 0.00011318327974276528,
"loss": 0.1912,
"step": 1080
},
{
"epoch": 0.44,
"learning_rate": 0.00011237942122186495,
"loss": 0.1249,
"step": 1090
},
{
"epoch": 0.44,
"learning_rate": 0.00011157556270096463,
"loss": 0.1505,
"step": 1100
},
{
"epoch": 0.45,
"learning_rate": 0.0001107717041800643,
"loss": 0.2325,
"step": 1110
},
{
"epoch": 0.45,
"learning_rate": 0.00010996784565916398,
"loss": 0.1284,
"step": 1120
},
{
"epoch": 0.45,
"learning_rate": 0.00010916398713826368,
"loss": 0.0767,
"step": 1130
},
{
"epoch": 0.46,
"learning_rate": 0.00010836012861736335,
"loss": 0.0773,
"step": 1140
},
{
"epoch": 0.46,
"learning_rate": 0.00010755627009646303,
"loss": 0.1112,
"step": 1150
},
{
"epoch": 0.47,
"learning_rate": 0.0001067524115755627,
"loss": 0.0873,
"step": 1160
},
{
"epoch": 0.47,
"learning_rate": 0.00010594855305466238,
"loss": 0.1782,
"step": 1170
},
{
"epoch": 0.47,
"learning_rate": 0.00010514469453376205,
"loss": 0.1493,
"step": 1180
},
{
"epoch": 0.48,
"learning_rate": 0.00010434083601286173,
"loss": 0.2793,
"step": 1190
},
{
"epoch": 0.48,
"learning_rate": 0.00010353697749196143,
"loss": 0.1563,
"step": 1200
},
{
"epoch": 0.49,
"learning_rate": 0.0001027331189710611,
"loss": 0.1311,
"step": 1210
},
{
"epoch": 0.49,
"learning_rate": 0.00010192926045016078,
"loss": 0.2596,
"step": 1220
},
{
"epoch": 0.49,
"learning_rate": 0.00010112540192926045,
"loss": 0.0822,
"step": 1230
},
{
"epoch": 0.5,
"learning_rate": 0.00010032154340836013,
"loss": 0.1717,
"step": 1240
},
{
"epoch": 0.5,
"learning_rate": 9.951768488745982e-05,
"loss": 0.1029,
"step": 1250
},
{
"epoch": 0.51,
"learning_rate": 9.871382636655949e-05,
"loss": 0.068,
"step": 1260
},
{
"epoch": 0.51,
"learning_rate": 9.790996784565917e-05,
"loss": 0.2052,
"step": 1270
},
{
"epoch": 0.51,
"learning_rate": 9.710610932475884e-05,
"loss": 0.1236,
"step": 1280
},
{
"epoch": 0.52,
"learning_rate": 9.630225080385853e-05,
"loss": 0.1484,
"step": 1290
},
{
"epoch": 0.52,
"learning_rate": 9.54983922829582e-05,
"loss": 0.2226,
"step": 1300
},
{
"epoch": 0.53,
"learning_rate": 9.469453376205788e-05,
"loss": 0.0759,
"step": 1310
},
{
"epoch": 0.53,
"learning_rate": 9.389067524115757e-05,
"loss": 0.0796,
"step": 1320
},
{
"epoch": 0.53,
"learning_rate": 9.308681672025724e-05,
"loss": 0.15,
"step": 1330
},
{
"epoch": 0.54,
"learning_rate": 9.228295819935692e-05,
"loss": 0.1217,
"step": 1340
},
{
"epoch": 0.54,
"learning_rate": 9.147909967845659e-05,
"loss": 0.1487,
"step": 1350
},
{
"epoch": 0.55,
"learning_rate": 9.067524115755628e-05,
"loss": 0.178,
"step": 1360
},
{
"epoch": 0.55,
"learning_rate": 8.987138263665596e-05,
"loss": 0.0732,
"step": 1370
},
{
"epoch": 0.55,
"learning_rate": 8.906752411575563e-05,
"loss": 0.1639,
"step": 1380
},
{
"epoch": 0.56,
"learning_rate": 8.82636655948553e-05,
"loss": 0.1026,
"step": 1390
},
{
"epoch": 0.56,
"learning_rate": 8.7459807073955e-05,
"loss": 0.0329,
"step": 1400
},
{
"epoch": 0.57,
"learning_rate": 8.665594855305467e-05,
"loss": 0.2264,
"step": 1410
},
{
"epoch": 0.57,
"learning_rate": 8.585209003215434e-05,
"loss": 0.0799,
"step": 1420
},
{
"epoch": 0.57,
"learning_rate": 8.504823151125403e-05,
"loss": 0.0258,
"step": 1430
},
{
"epoch": 0.58,
"learning_rate": 8.42443729903537e-05,
"loss": 0.1056,
"step": 1440
},
{
"epoch": 0.58,
"learning_rate": 8.344051446945338e-05,
"loss": 0.0807,
"step": 1450
},
{
"epoch": 0.59,
"learning_rate": 8.263665594855306e-05,
"loss": 0.1491,
"step": 1460
},
{
"epoch": 0.59,
"learning_rate": 8.183279742765274e-05,
"loss": 0.1216,
"step": 1470
},
{
"epoch": 0.59,
"learning_rate": 8.102893890675242e-05,
"loss": 0.1722,
"step": 1480
},
{
"epoch": 0.6,
"learning_rate": 8.02250803858521e-05,
"loss": 0.0542,
"step": 1490
},
{
"epoch": 0.6,
"learning_rate": 7.942122186495177e-05,
"loss": 0.1965,
"step": 1500
},
{
"epoch": 0.61,
"learning_rate": 7.861736334405146e-05,
"loss": 0.1252,
"step": 1510
},
{
"epoch": 0.61,
"learning_rate": 7.781350482315113e-05,
"loss": 0.0457,
"step": 1520
},
{
"epoch": 0.61,
"learning_rate": 7.70096463022508e-05,
"loss": 0.1899,
"step": 1530
},
{
"epoch": 0.62,
"learning_rate": 7.62057877813505e-05,
"loss": 0.1058,
"step": 1540
},
{
"epoch": 0.62,
"learning_rate": 7.540192926045017e-05,
"loss": 0.1748,
"step": 1550
},
{
"epoch": 0.63,
"learning_rate": 7.459807073954984e-05,
"loss": 0.078,
"step": 1560
},
{
"epoch": 0.63,
"learning_rate": 7.379421221864952e-05,
"loss": 0.2113,
"step": 1570
},
{
"epoch": 0.64,
"learning_rate": 7.299035369774921e-05,
"loss": 0.101,
"step": 1580
},
{
"epoch": 0.64,
"learning_rate": 7.218649517684888e-05,
"loss": 0.0684,
"step": 1590
},
{
"epoch": 0.64,
"learning_rate": 7.138263665594856e-05,
"loss": 0.3001,
"step": 1600
},
{
"epoch": 0.65,
"learning_rate": 7.057877813504825e-05,
"loss": 0.1088,
"step": 1610
},
{
"epoch": 0.65,
"learning_rate": 6.977491961414792e-05,
"loss": 0.0099,
"step": 1620
},
{
"epoch": 0.66,
"learning_rate": 6.89710610932476e-05,
"loss": 0.0918,
"step": 1630
},
{
"epoch": 0.66,
"learning_rate": 6.816720257234727e-05,
"loss": 0.0402,
"step": 1640
},
{
"epoch": 0.66,
"learning_rate": 6.736334405144696e-05,
"loss": 0.0505,
"step": 1650
},
{
"epoch": 0.67,
"learning_rate": 6.655948553054663e-05,
"loss": 0.1337,
"step": 1660
},
{
"epoch": 0.67,
"learning_rate": 6.575562700964631e-05,
"loss": 0.0712,
"step": 1670
},
{
"epoch": 0.68,
"learning_rate": 6.495176848874598e-05,
"loss": 0.0177,
"step": 1680
},
{
"epoch": 0.68,
"learning_rate": 6.414790996784567e-05,
"loss": 0.2133,
"step": 1690
},
{
"epoch": 0.68,
"learning_rate": 6.334405144694535e-05,
"loss": 0.0598,
"step": 1700
},
{
"epoch": 0.69,
"learning_rate": 6.254019292604502e-05,
"loss": 0.1066,
"step": 1710
},
{
"epoch": 0.69,
"learning_rate": 6.173633440514471e-05,
"loss": 0.1304,
"step": 1720
},
{
"epoch": 0.7,
"learning_rate": 6.0932475884244377e-05,
"loss": 0.2402,
"step": 1730
},
{
"epoch": 0.7,
"learning_rate": 6.012861736334405e-05,
"loss": 0.0907,
"step": 1740
},
{
"epoch": 0.7,
"learning_rate": 5.9324758842443726e-05,
"loss": 0.1261,
"step": 1750
},
{
"epoch": 0.71,
"learning_rate": 5.8520900321543414e-05,
"loss": 0.0255,
"step": 1760
},
{
"epoch": 0.71,
"learning_rate": 5.771704180064309e-05,
"loss": 0.1224,
"step": 1770
},
{
"epoch": 0.72,
"learning_rate": 5.6913183279742764e-05,
"loss": 0.1896,
"step": 1780
},
{
"epoch": 0.72,
"learning_rate": 5.610932475884244e-05,
"loss": 0.1877,
"step": 1790
},
{
"epoch": 0.72,
"learning_rate": 5.530546623794213e-05,
"loss": 0.1275,
"step": 1800
},
{
"epoch": 0.73,
"learning_rate": 5.45016077170418e-05,
"loss": 0.1746,
"step": 1810
},
{
"epoch": 0.73,
"learning_rate": 5.369774919614148e-05,
"loss": 0.0513,
"step": 1820
},
{
"epoch": 0.74,
"learning_rate": 5.2893890675241165e-05,
"loss": 0.1638,
"step": 1830
},
{
"epoch": 0.74,
"learning_rate": 5.209003215434084e-05,
"loss": 0.0546,
"step": 1840
},
{
"epoch": 0.74,
"learning_rate": 5.1286173633440515e-05,
"loss": 0.0156,
"step": 1850
},
{
"epoch": 0.75,
"learning_rate": 5.048231511254019e-05,
"loss": 0.0511,
"step": 1860
},
{
"epoch": 0.75,
"learning_rate": 4.967845659163987e-05,
"loss": 0.1748,
"step": 1870
},
{
"epoch": 0.76,
"learning_rate": 4.887459807073955e-05,
"loss": 0.087,
"step": 1880
},
{
"epoch": 0.76,
"learning_rate": 4.8070739549839234e-05,
"loss": 0.1595,
"step": 1890
},
{
"epoch": 0.76,
"learning_rate": 4.726688102893891e-05,
"loss": 0.1603,
"step": 1900
},
{
"epoch": 0.77,
"learning_rate": 4.646302250803859e-05,
"loss": 0.0242,
"step": 1910
},
{
"epoch": 0.77,
"learning_rate": 4.5659163987138265e-05,
"loss": 0.1388,
"step": 1920
},
{
"epoch": 0.78,
"learning_rate": 4.485530546623795e-05,
"loss": 0.1766,
"step": 1930
},
{
"epoch": 0.78,
"learning_rate": 4.405144694533762e-05,
"loss": 0.1017,
"step": 1940
},
{
"epoch": 0.78,
"learning_rate": 4.32475884244373e-05,
"loss": 0.0819,
"step": 1950
},
{
"epoch": 0.79,
"learning_rate": 4.244372990353698e-05,
"loss": 0.0785,
"step": 1960
},
{
"epoch": 0.79,
"learning_rate": 4.163987138263666e-05,
"loss": 0.0906,
"step": 1970
},
{
"epoch": 0.8,
"learning_rate": 4.083601286173634e-05,
"loss": 0.0545,
"step": 1980
},
{
"epoch": 0.8,
"learning_rate": 4.0032154340836016e-05,
"loss": 0.0917,
"step": 1990
},
{
"epoch": 0.8,
"learning_rate": 3.92282958199357e-05,
"loss": 0.1921,
"step": 2000
},
{
"epoch": 0.81,
"learning_rate": 3.842443729903537e-05,
"loss": 0.1346,
"step": 2010
},
{
"epoch": 0.81,
"learning_rate": 3.7620578778135054e-05,
"loss": 0.0455,
"step": 2020
},
{
"epoch": 0.82,
"learning_rate": 3.681672025723473e-05,
"loss": 0.0267,
"step": 2030
},
{
"epoch": 0.82,
"learning_rate": 3.601286173633441e-05,
"loss": 0.0781,
"step": 2040
},
{
"epoch": 0.82,
"learning_rate": 3.5209003215434085e-05,
"loss": 0.0123,
"step": 2050
},
{
"epoch": 0.83,
"learning_rate": 3.4405144694533766e-05,
"loss": 0.0145,
"step": 2060
},
{
"epoch": 0.83,
"learning_rate": 3.360128617363344e-05,
"loss": 0.0802,
"step": 2070
},
{
"epoch": 0.84,
"learning_rate": 3.279742765273312e-05,
"loss": 0.0797,
"step": 2080
},
{
"epoch": 0.84,
"learning_rate": 3.1993569131832804e-05,
"loss": 0.2245,
"step": 2090
},
{
"epoch": 0.84,
"learning_rate": 3.118971061093248e-05,
"loss": 0.0771,
"step": 2100
},
{
"epoch": 0.85,
"learning_rate": 3.0385852090032157e-05,
"loss": 0.0732,
"step": 2110
},
{
"epoch": 0.85,
"learning_rate": 2.9581993569131832e-05,
"loss": 0.1055,
"step": 2120
},
{
"epoch": 0.86,
"learning_rate": 2.8778135048231513e-05,
"loss": 0.0194,
"step": 2130
},
{
"epoch": 0.86,
"learning_rate": 2.7974276527331188e-05,
"loss": 0.1721,
"step": 2140
},
{
"epoch": 0.86,
"learning_rate": 2.717041800643087e-05,
"loss": 0.0708,
"step": 2150
},
{
"epoch": 0.87,
"learning_rate": 2.6366559485530545e-05,
"loss": 0.0392,
"step": 2160
},
{
"epoch": 0.87,
"learning_rate": 2.5562700964630226e-05,
"loss": 0.0824,
"step": 2170
},
{
"epoch": 0.88,
"learning_rate": 2.4758842443729904e-05,
"loss": 0.0319,
"step": 2180
},
{
"epoch": 0.88,
"learning_rate": 2.3954983922829582e-05,
"loss": 0.1465,
"step": 2190
},
{
"epoch": 0.88,
"learning_rate": 2.315112540192926e-05,
"loss": 0.0373,
"step": 2200
},
{
"epoch": 0.89,
"learning_rate": 2.234726688102894e-05,
"loss": 0.0872,
"step": 2210
},
{
"epoch": 0.89,
"learning_rate": 2.154340836012862e-05,
"loss": 0.0213,
"step": 2220
},
{
"epoch": 0.9,
"learning_rate": 2.07395498392283e-05,
"loss": 0.0919,
"step": 2230
},
{
"epoch": 0.9,
"learning_rate": 1.9935691318327977e-05,
"loss": 0.0234,
"step": 2240
},
{
"epoch": 0.9,
"learning_rate": 1.9131832797427655e-05,
"loss": 0.0677,
"step": 2250
},
{
"epoch": 0.91,
"learning_rate": 1.8327974276527333e-05,
"loss": 0.0754,
"step": 2260
},
{
"epoch": 0.91,
"learning_rate": 1.752411575562701e-05,
"loss": 0.0257,
"step": 2270
},
{
"epoch": 0.92,
"learning_rate": 1.672025723472669e-05,
"loss": 0.1474,
"step": 2280
},
{
"epoch": 0.92,
"learning_rate": 1.5916398713826368e-05,
"loss": 0.3303,
"step": 2290
},
{
"epoch": 0.92,
"learning_rate": 1.5112540192926044e-05,
"loss": 0.1173,
"step": 2300
},
{
"epoch": 0.93,
"learning_rate": 1.4308681672025726e-05,
"loss": 0.0271,
"step": 2310
},
{
"epoch": 0.93,
"learning_rate": 1.3504823151125404e-05,
"loss": 0.0182,
"step": 2320
},
{
"epoch": 0.94,
"learning_rate": 1.2700964630225082e-05,
"loss": 0.1104,
"step": 2330
},
{
"epoch": 0.94,
"learning_rate": 1.189710610932476e-05,
"loss": 0.0909,
"step": 2340
},
{
"epoch": 0.94,
"learning_rate": 1.1093247588424438e-05,
"loss": 0.0389,
"step": 2350
},
{
"epoch": 0.95,
"learning_rate": 1.0289389067524116e-05,
"loss": 0.067,
"step": 2360
},
{
"epoch": 0.95,
"learning_rate": 9.485530546623795e-06,
"loss": 0.07,
"step": 2370
},
{
"epoch": 0.96,
"learning_rate": 8.681672025723474e-06,
"loss": 0.0457,
"step": 2380
},
{
"epoch": 0.96,
"learning_rate": 7.877813504823153e-06,
"loss": 0.1058,
"step": 2390
},
{
"epoch": 0.96,
"learning_rate": 7.07395498392283e-06,
"loss": 0.0225,
"step": 2400
},
{
"epoch": 0.97,
"learning_rate": 6.270096463022508e-06,
"loss": 0.1176,
"step": 2410
},
{
"epoch": 0.97,
"learning_rate": 5.466237942122187e-06,
"loss": 0.0267,
"step": 2420
},
{
"epoch": 0.98,
"learning_rate": 4.662379421221865e-06,
"loss": 0.0751,
"step": 2430
},
{
"epoch": 0.98,
"learning_rate": 3.858520900321544e-06,
"loss": 0.0904,
"step": 2440
},
{
"epoch": 0.98,
"learning_rate": 3.054662379421222e-06,
"loss": 0.0607,
"step": 2450
},
{
"epoch": 0.99,
"learning_rate": 2.2508038585209006e-06,
"loss": 0.1344,
"step": 2460
},
{
"epoch": 0.99,
"learning_rate": 1.4469453376205788e-06,
"loss": 0.0816,
"step": 2470
},
{
"epoch": 1.0,
"learning_rate": 6.430868167202573e-07,
"loss": 0.0949,
"step": 2480
},
{
"epoch": 1.0,
"eval_accuracy": 0.9883257403189066,
"eval_loss": 0.036893460899591446,
"eval_runtime": 109.7581,
"eval_samples_per_second": 31.998,
"eval_steps_per_second": 4.0,
"step": 2488
},
{
"epoch": 1.0,
"step": 2488,
"total_flos": 0.0,
"train_loss": 0.1489328353447163,
"train_runtime": 1701.4159,
"train_samples_per_second": 11.695,
"train_steps_per_second": 1.462
}
],
"max_steps": 2488,
"num_train_epochs": 1,
"total_flos": 0.0,
"trial_name": null,
"trial_params": null
}