EssayGPT / trainer_state.json
AngoHF's picture
first commit
fbcb102 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.0,
"eval_steps": 500,
"global_step": 1960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 0.0004999678864499828,
"loss": 1.9845,
"step": 10
},
{
"epoch": 0.08,
"learning_rate": 0.000499871554050172,
"loss": 1.8444,
"step": 20
},
{
"epoch": 0.12,
"learning_rate": 0.0004997110275491702,
"loss": 1.721,
"step": 30
},
{
"epoch": 0.16,
"learning_rate": 0.0004994863481875841,
"loss": 1.6755,
"step": 40
},
{
"epoch": 0.2,
"learning_rate": 0.0004991975736874289,
"loss": 1.7248,
"step": 50
},
{
"epoch": 0.24,
"learning_rate": 0.0004988447782372996,
"loss": 1.6803,
"step": 60
},
{
"epoch": 0.29,
"learning_rate": 0.0004984280524733107,
"loss": 1.7063,
"step": 70
},
{
"epoch": 0.33,
"learning_rate": 0.0004979475034558115,
"loss": 1.6724,
"step": 80
},
{
"epoch": 0.37,
"learning_rate": 0.0004974032546418815,
"loss": 1.6933,
"step": 90
},
{
"epoch": 0.41,
"learning_rate": 0.0004967954458536126,
"loss": 1.6243,
"step": 100
},
{
"epoch": 0.45,
"learning_rate": 0.0004961242332421882,
"loss": 1.639,
"step": 110
},
{
"epoch": 0.49,
"learning_rate": 0.0004953897892477664,
"loss": 1.6545,
"step": 120
},
{
"epoch": 0.53,
"learning_rate": 0.0004945923025551788,
"loss": 1.6017,
"step": 130
},
{
"epoch": 0.57,
"learning_rate": 0.0004937319780454559,
"loss": 1.6522,
"step": 140
},
{
"epoch": 0.61,
"learning_rate": 0.000492809036743191,
"loss": 1.5948,
"step": 150
},
{
"epoch": 0.65,
"learning_rate": 0.0004918237157597574,
"loss": 1.5385,
"step": 160
},
{
"epoch": 0.69,
"learning_rate": 0.0004907762682323926,
"loss": 1.6132,
"step": 170
},
{
"epoch": 0.73,
"learning_rate": 0.0004896669632591652,
"loss": 1.5396,
"step": 180
},
{
"epoch": 0.78,
"learning_rate": 0.000488496085829841,
"loss": 1.5023,
"step": 190
},
{
"epoch": 0.82,
"learning_rate": 0.0004872639367526672,
"loss": 1.4937,
"step": 200
},
{
"epoch": 0.86,
"learning_rate": 0.0004859708325770919,
"loss": 1.4824,
"step": 210
},
{
"epoch": 0.9,
"learning_rate": 0.0004846171055124401,
"loss": 1.5506,
"step": 220
},
{
"epoch": 0.94,
"learning_rate": 0.00048320310334256625,
"loss": 1.5709,
"step": 230
},
{
"epoch": 0.98,
"learning_rate": 0.0004817291893365054,
"loss": 1.5531,
"step": 240
},
{
"epoch": 1.02,
"learning_rate": 0.00048019574215514706,
"loss": 1.4546,
"step": 250
},
{
"epoch": 1.06,
"learning_rate": 0.0004786031557539531,
"loss": 1.4281,
"step": 260
},
{
"epoch": 1.1,
"learning_rate": 0.00047695183928174803,
"loss": 1.4339,
"step": 270
},
{
"epoch": 1.14,
"learning_rate": 0.00047524221697560476,
"loss": 1.3993,
"step": 280
},
{
"epoch": 1.18,
"learning_rate": 0.0004734747280518549,
"loss": 1.3786,
"step": 290
},
{
"epoch": 1.22,
"learning_rate": 0.00047164982659325005,
"loss": 1.458,
"step": 300
},
{
"epoch": 1.27,
"learning_rate": 0.0004697679814323043,
"loss": 1.3692,
"step": 310
},
{
"epoch": 1.31,
"learning_rate": 0.00046782967603084736,
"loss": 1.491,
"step": 320
},
{
"epoch": 1.35,
"learning_rate": 0.00046583540835581883,
"loss": 1.3637,
"step": 330
},
{
"epoch": 1.39,
"learning_rate": 0.0004637856907513366,
"loss": 1.4276,
"step": 340
},
{
"epoch": 1.43,
"learning_rate": 0.00046168104980707104,
"loss": 1.3943,
"step": 350
},
{
"epoch": 1.47,
"learning_rate": 0.00045952202622296013,
"loss": 1.4274,
"step": 360
},
{
"epoch": 1.51,
"learning_rate": 0.00045730917467029877,
"loss": 1.4829,
"step": 370
},
{
"epoch": 1.55,
"learning_rate": 0.00045504306364923896,
"loss": 1.3585,
"step": 380
},
{
"epoch": 1.59,
"learning_rate": 0.00045272427534273776,
"loss": 1.4194,
"step": 390
},
{
"epoch": 1.63,
"learning_rate": 0.00045035340546698916,
"loss": 1.3924,
"step": 400
},
{
"epoch": 1.67,
"learning_rate": 0.0004479310631183799,
"loss": 1.4117,
"step": 410
},
{
"epoch": 1.71,
"learning_rate": 0.0004454578706170075,
"loss": 1.3849,
"step": 420
},
{
"epoch": 1.76,
"learning_rate": 0.0004429344633468004,
"loss": 1.3857,
"step": 430
},
{
"epoch": 1.8,
"learning_rate": 0.0004403614895922836,
"loss": 1.4772,
"step": 440
},
{
"epoch": 1.84,
"learning_rate": 0.0004377396103720278,
"loss": 1.4021,
"step": 450
},
{
"epoch": 1.88,
"learning_rate": 0.00043506949926882887,
"loss": 1.3589,
"step": 460
},
{
"epoch": 1.92,
"learning_rate": 0.0004323518422566586,
"loss": 1.45,
"step": 470
},
{
"epoch": 1.96,
"learning_rate": 0.0004295873375244319,
"loss": 1.2784,
"step": 480
},
{
"epoch": 2.0,
"learning_rate": 0.00042677669529663686,
"loss": 1.4127,
"step": 490
},
{
"epoch": 2.04,
"learning_rate": 0.0004239206376508716,
"loss": 1.2777,
"step": 500
},
{
"epoch": 2.08,
"learning_rate": 0.00042101989833233654,
"loss": 1.1873,
"step": 510
},
{
"epoch": 2.12,
"learning_rate": 0.0004180752225653292,
"loss": 1.2746,
"step": 520
},
{
"epoch": 2.16,
"learning_rate": 0.0004150873668617898,
"loss": 1.308,
"step": 530
},
{
"epoch": 2.2,
"learning_rate": 0.00041205709882694713,
"loss": 1.2431,
"step": 540
},
{
"epoch": 2.24,
"learning_rate": 0.0004089851969621138,
"loss": 1.3411,
"step": 550
},
{
"epoch": 2.29,
"learning_rate": 0.0004058724504646834,
"loss": 1.2369,
"step": 560
},
{
"epoch": 2.33,
"learning_rate": 0.0004027196590253786,
"loss": 1.303,
"step": 570
},
{
"epoch": 2.37,
"learning_rate": 0.000399527632622804,
"loss": 1.2011,
"step": 580
},
{
"epoch": 2.41,
"learning_rate": 0.0003962971913153559,
"loss": 1.2239,
"step": 590
},
{
"epoch": 2.45,
"learning_rate": 0.00039302916503054243,
"loss": 1.2133,
"step": 600
},
{
"epoch": 2.49,
"learning_rate": 0.0003897243933517679,
"loss": 1.2108,
"step": 610
},
{
"epoch": 2.53,
"learning_rate": 0.00038638372530263714,
"loss": 1.3095,
"step": 620
},
{
"epoch": 2.57,
"learning_rate": 0.00038300801912883415,
"loss": 1.2392,
"step": 630
},
{
"epoch": 2.61,
"learning_rate": 0.0003795981420776313,
"loss": 1.1789,
"step": 640
},
{
"epoch": 2.65,
"learning_rate": 0.0003761549701750865,
"loss": 1.2285,
"step": 650
},
{
"epoch": 2.69,
"learning_rate": 0.0003726793880009845,
"loss": 1.2101,
"step": 660
},
{
"epoch": 2.73,
"learning_rate": 0.00036917228846158136,
"loss": 1.1973,
"step": 670
},
{
"epoch": 2.78,
"learning_rate": 0.00036563457256020887,
"loss": 1.2238,
"step": 680
},
{
"epoch": 2.82,
"learning_rate": 0.0003620671491657992,
"loss": 1.2249,
"step": 690
},
{
"epoch": 2.86,
"learning_rate": 0.00035847093477938953,
"loss": 1.2314,
"step": 700
},
{
"epoch": 2.9,
"learning_rate": 0.00035484685329866423,
"loss": 1.2987,
"step": 710
},
{
"epoch": 2.94,
"learning_rate": 0.00035119583578059843,
"loss": 1.2416,
"step": 720
},
{
"epoch": 2.98,
"learning_rate": 0.00034751882020226174,
"loss": 1.175,
"step": 730
},
{
"epoch": 3.02,
"learning_rate": 0.0003438167512198436,
"loss": 1.2123,
"step": 740
},
{
"epoch": 3.06,
"learning_rate": 0.00034009057992596335,
"loss": 1.0257,
"step": 750
},
{
"epoch": 3.1,
"learning_rate": 0.0003363412636053269,
"loss": 1.118,
"step": 760
},
{
"epoch": 3.14,
"learning_rate": 0.00033256976548879183,
"loss": 1.1586,
"step": 770
},
{
"epoch": 3.18,
"learning_rate": 0.0003287770545059052,
"loss": 1.0559,
"step": 780
},
{
"epoch": 3.22,
"learning_rate": 0.0003249641050359779,
"loss": 1.0775,
"step": 790
},
{
"epoch": 3.27,
"learning_rate": 0.0003211318966577581,
"loss": 1.0905,
"step": 800
},
{
"epoch": 3.31,
"learning_rate": 0.00031728141389776923,
"loss": 1.088,
"step": 810
},
{
"epoch": 3.35,
"learning_rate": 0.0003134136459773768,
"loss": 1.0395,
"step": 820
},
{
"epoch": 3.39,
"learning_rate": 0.00030952958655864954,
"loss": 1.1064,
"step": 830
},
{
"epoch": 3.43,
"learning_rate": 0.0003056302334890786,
"loss": 1.0662,
"step": 840
},
{
"epoch": 3.47,
"learning_rate": 0.0003017165885452227,
"loss": 1.0627,
"step": 850
},
{
"epoch": 3.51,
"learning_rate": 0.00029778965717534313,
"loss": 0.9968,
"step": 860
},
{
"epoch": 3.55,
"learning_rate": 0.0002938504482410954,
"loss": 1.1237,
"step": 870
},
{
"epoch": 3.59,
"learning_rate": 0.00028989997375834483,
"loss": 1.0432,
"step": 880
},
{
"epoch": 3.63,
"learning_rate": 0.00028593924863717045,
"loss": 1.1197,
"step": 890
},
{
"epoch": 3.67,
"learning_rate": 0.0002819692904211265,
"loss": 1.0016,
"step": 900
},
{
"epoch": 3.71,
"learning_rate": 0.00027799111902582696,
"loss": 1.0956,
"step": 910
},
{
"epoch": 3.76,
"learning_rate": 0.00027400575647692046,
"loss": 1.0878,
"step": 920
},
{
"epoch": 3.8,
"learning_rate": 0.00027001422664752335,
"loss": 1.0838,
"step": 930
},
{
"epoch": 3.84,
"learning_rate": 0.00026601755499517824,
"loss": 1.0587,
"step": 940
},
{
"epoch": 3.88,
"learning_rate": 0.0002620167682984052,
"loss": 1.0857,
"step": 950
},
{
"epoch": 3.92,
"learning_rate": 0.00025801289439291385,
"loss": 1.0107,
"step": 960
},
{
"epoch": 3.96,
"learning_rate": 0.00025400696190754345,
"loss": 1.1491,
"step": 970
},
{
"epoch": 4.0,
"learning_rate": 0.00025,
"loss": 1.0726,
"step": 980
},
{
"epoch": 4.04,
"learning_rate": 0.0002459930380924566,
"loss": 0.9856,
"step": 990
},
{
"epoch": 4.08,
"learning_rate": 0.0002419871056070862,
"loss": 0.9726,
"step": 1000
},
{
"epoch": 4.12,
"learning_rate": 0.00023798323170159486,
"loss": 0.9675,
"step": 1010
},
{
"epoch": 4.16,
"learning_rate": 0.0002339824450048218,
"loss": 0.9831,
"step": 1020
},
{
"epoch": 4.2,
"learning_rate": 0.0002299857733524767,
"loss": 0.9082,
"step": 1030
},
{
"epoch": 4.24,
"learning_rate": 0.00022599424352307955,
"loss": 1.04,
"step": 1040
},
{
"epoch": 4.29,
"learning_rate": 0.00022200888097417305,
"loss": 0.9608,
"step": 1050
},
{
"epoch": 4.33,
"learning_rate": 0.00021803070957887347,
"loss": 1.0405,
"step": 1060
},
{
"epoch": 4.37,
"learning_rate": 0.0002140607513628296,
"loss": 0.9635,
"step": 1070
},
{
"epoch": 4.41,
"learning_rate": 0.00021010002624165526,
"loss": 0.8787,
"step": 1080
},
{
"epoch": 4.45,
"learning_rate": 0.00020614955175890463,
"loss": 0.9367,
"step": 1090
},
{
"epoch": 4.49,
"learning_rate": 0.00020221034282465699,
"loss": 1.0206,
"step": 1100
},
{
"epoch": 4.53,
"learning_rate": 0.00019828341145477728,
"loss": 0.962,
"step": 1110
},
{
"epoch": 4.57,
"learning_rate": 0.00019436976651092142,
"loss": 0.8907,
"step": 1120
},
{
"epoch": 4.61,
"learning_rate": 0.00019047041344135045,
"loss": 0.932,
"step": 1130
},
{
"epoch": 4.65,
"learning_rate": 0.0001865863540226232,
"loss": 0.957,
"step": 1140
},
{
"epoch": 4.69,
"learning_rate": 0.0001827185861022308,
"loss": 0.9121,
"step": 1150
},
{
"epoch": 4.73,
"learning_rate": 0.0001788681033422419,
"loss": 0.9817,
"step": 1160
},
{
"epoch": 4.78,
"learning_rate": 0.0001750358949640221,
"loss": 0.9116,
"step": 1170
},
{
"epoch": 4.82,
"learning_rate": 0.00017122294549409484,
"loss": 0.8627,
"step": 1180
},
{
"epoch": 4.86,
"learning_rate": 0.00016743023451120832,
"loss": 0.8922,
"step": 1190
},
{
"epoch": 4.9,
"learning_rate": 0.00016365873639467314,
"loss": 0.9926,
"step": 1200
},
{
"epoch": 4.94,
"learning_rate": 0.0001599094200740367,
"loss": 1.0046,
"step": 1210
},
{
"epoch": 4.98,
"learning_rate": 0.0001561832487801565,
"loss": 0.927,
"step": 1220
},
{
"epoch": 5.02,
"learning_rate": 0.0001524811797977383,
"loss": 0.8946,
"step": 1230
},
{
"epoch": 5.06,
"learning_rate": 0.00014880416421940155,
"loss": 0.9484,
"step": 1240
},
{
"epoch": 5.1,
"learning_rate": 0.0001451531467013358,
"loss": 0.7806,
"step": 1250
},
{
"epoch": 5.14,
"learning_rate": 0.00014152906522061048,
"loss": 0.8487,
"step": 1260
},
{
"epoch": 5.18,
"learning_rate": 0.00013793285083420076,
"loss": 0.7939,
"step": 1270
},
{
"epoch": 5.22,
"learning_rate": 0.00013436542743979125,
"loss": 0.9054,
"step": 1280
},
{
"epoch": 5.27,
"learning_rate": 0.0001308277115384187,
"loss": 0.8808,
"step": 1290
},
{
"epoch": 5.31,
"learning_rate": 0.00012732061199901561,
"loss": 0.8748,
"step": 1300
},
{
"epoch": 5.35,
"learning_rate": 0.00012384502982491357,
"loss": 0.9054,
"step": 1310
},
{
"epoch": 5.39,
"learning_rate": 0.00012040185792236874,
"loss": 0.8023,
"step": 1320
},
{
"epoch": 5.43,
"learning_rate": 0.00011699198087116588,
"loss": 0.9195,
"step": 1330
},
{
"epoch": 5.47,
"learning_rate": 0.00011361627469736286,
"loss": 0.8406,
"step": 1340
},
{
"epoch": 5.51,
"learning_rate": 0.00011027560664823208,
"loss": 0.8873,
"step": 1350
},
{
"epoch": 5.55,
"learning_rate": 0.00010697083496945764,
"loss": 0.8811,
"step": 1360
},
{
"epoch": 5.59,
"learning_rate": 0.00010370280868464405,
"loss": 0.9164,
"step": 1370
},
{
"epoch": 5.63,
"learning_rate": 0.000100472367377196,
"loss": 0.9604,
"step": 1380
},
{
"epoch": 5.67,
"learning_rate": 9.728034097462144e-05,
"loss": 0.9027,
"step": 1390
},
{
"epoch": 5.71,
"learning_rate": 9.412754953531663e-05,
"loss": 0.857,
"step": 1400
},
{
"epoch": 5.76,
"learning_rate": 9.101480303788623e-05,
"loss": 0.8198,
"step": 1410
},
{
"epoch": 5.8,
"learning_rate": 8.794290117305295e-05,
"loss": 0.866,
"step": 1420
},
{
"epoch": 5.84,
"learning_rate": 8.491263313821021e-05,
"loss": 0.8422,
"step": 1430
},
{
"epoch": 5.88,
"learning_rate": 8.192477743467078e-05,
"loss": 0.8921,
"step": 1440
},
{
"epoch": 5.92,
"learning_rate": 7.898010166766348e-05,
"loss": 0.8429,
"step": 1450
},
{
"epoch": 5.96,
"learning_rate": 7.60793623491284e-05,
"loss": 0.8728,
"step": 1460
},
{
"epoch": 6.0,
"learning_rate": 7.322330470336314e-05,
"loss": 0.8335,
"step": 1470
},
{
"epoch": 6.04,
"learning_rate": 7.041266247556813e-05,
"loss": 0.8213,
"step": 1480
},
{
"epoch": 6.08,
"learning_rate": 6.764815774334149e-05,
"loss": 0.8509,
"step": 1490
},
{
"epoch": 6.12,
"learning_rate": 6.493050073117116e-05,
"loss": 0.7348,
"step": 1500
},
{
"epoch": 6.16,
"learning_rate": 6.226038962797217e-05,
"loss": 0.8422,
"step": 1510
},
{
"epoch": 6.2,
"learning_rate": 5.96385104077164e-05,
"loss": 0.896,
"step": 1520
},
{
"epoch": 6.24,
"learning_rate": 5.706553665319955e-05,
"loss": 0.7791,
"step": 1530
},
{
"epoch": 6.29,
"learning_rate": 5.454212938299255e-05,
"loss": 0.8045,
"step": 1540
},
{
"epoch": 6.33,
"learning_rate": 5.206893688162009e-05,
"loss": 0.8531,
"step": 1550
},
{
"epoch": 6.37,
"learning_rate": 4.9646594533010875e-05,
"loss": 0.8444,
"step": 1560
},
{
"epoch": 6.41,
"learning_rate": 4.7275724657262294e-05,
"loss": 0.7966,
"step": 1570
},
{
"epoch": 6.45,
"learning_rate": 4.495693635076101e-05,
"loss": 0.7895,
"step": 1580
},
{
"epoch": 6.49,
"learning_rate": 4.269082532970131e-05,
"loss": 0.7409,
"step": 1590
},
{
"epoch": 6.53,
"learning_rate": 4.047797377703985e-05,
"loss": 0.875,
"step": 1600
},
{
"epoch": 6.57,
"learning_rate": 3.831895019292897e-05,
"loss": 0.8869,
"step": 1610
},
{
"epoch": 6.61,
"learning_rate": 3.621430924866348e-05,
"loss": 0.8159,
"step": 1620
},
{
"epoch": 6.65,
"learning_rate": 3.416459164418123e-05,
"loss": 0.7707,
"step": 1630
},
{
"epoch": 6.69,
"learning_rate": 3.217032396915265e-05,
"loss": 0.8724,
"step": 1640
},
{
"epoch": 6.73,
"learning_rate": 3.0232018567695695e-05,
"loss": 0.7733,
"step": 1650
},
{
"epoch": 6.78,
"learning_rate": 2.8350173406749973e-05,
"loss": 0.8311,
"step": 1660
},
{
"epoch": 6.82,
"learning_rate": 2.652527194814511e-05,
"loss": 0.8356,
"step": 1670
},
{
"epoch": 6.86,
"learning_rate": 2.4757783024395242e-05,
"loss": 0.8144,
"step": 1680
},
{
"epoch": 6.9,
"learning_rate": 2.3048160718251997e-05,
"loss": 0.7767,
"step": 1690
},
{
"epoch": 6.94,
"learning_rate": 2.1396844246046905e-05,
"loss": 0.8402,
"step": 1700
},
{
"epoch": 6.98,
"learning_rate": 1.980425784485293e-05,
"loss": 0.8576,
"step": 1710
},
{
"epoch": 7.02,
"learning_rate": 1.827081066349459e-05,
"loss": 0.7797,
"step": 1720
},
{
"epoch": 7.06,
"learning_rate": 1.6796896657433808e-05,
"loss": 0.8409,
"step": 1730
},
{
"epoch": 7.1,
"learning_rate": 1.538289448755989e-05,
"loss": 0.7642,
"step": 1740
},
{
"epoch": 7.14,
"learning_rate": 1.4029167422908107e-05,
"loss": 0.8464,
"step": 1750
},
{
"epoch": 7.18,
"learning_rate": 1.273606324733284e-05,
"loss": 0.7975,
"step": 1760
},
{
"epoch": 7.22,
"learning_rate": 1.1503914170159058e-05,
"loss": 0.7577,
"step": 1770
},
{
"epoch": 7.27,
"learning_rate": 1.0333036740834856e-05,
"loss": 0.8085,
"step": 1780
},
{
"epoch": 7.31,
"learning_rate": 9.223731767607434e-06,
"loss": 0.7511,
"step": 1790
},
{
"epoch": 7.35,
"learning_rate": 8.176284240242638e-06,
"loss": 0.845,
"step": 1800
},
{
"epoch": 7.39,
"learning_rate": 7.190963256809069e-06,
"loss": 0.865,
"step": 1810
},
{
"epoch": 7.43,
"learning_rate": 6.268021954544096e-06,
"loss": 0.8486,
"step": 1820
},
{
"epoch": 7.47,
"learning_rate": 5.407697444821169e-06,
"loss": 0.7099,
"step": 1830
},
{
"epoch": 7.51,
"learning_rate": 4.61021075223364e-06,
"loss": 0.8223,
"step": 1840
},
{
"epoch": 7.55,
"learning_rate": 3.8757667578118995e-06,
"loss": 0.8753,
"step": 1850
},
{
"epoch": 7.59,
"learning_rate": 3.2045541463874563e-06,
"loss": 0.8835,
"step": 1860
},
{
"epoch": 7.63,
"learning_rate": 2.5967453581185186e-06,
"loss": 0.7877,
"step": 1870
},
{
"epoch": 7.67,
"learning_rate": 2.052496544188487e-06,
"loss": 0.8828,
"step": 1880
},
{
"epoch": 7.71,
"learning_rate": 1.571947526689349e-06,
"loss": 0.7658,
"step": 1890
},
{
"epoch": 7.76,
"learning_rate": 1.1552217627004424e-06,
"loss": 0.8952,
"step": 1900
},
{
"epoch": 7.8,
"learning_rate": 8.024263125710751e-07,
"loss": 0.8118,
"step": 1910
},
{
"epoch": 7.84,
"learning_rate": 5.136518124159162e-07,
"loss": 0.8503,
"step": 1920
},
{
"epoch": 7.88,
"learning_rate": 2.8897245082978865e-07,
"loss": 0.8248,
"step": 1930
},
{
"epoch": 7.92,
"learning_rate": 1.284459498280266e-07,
"loss": 0.8515,
"step": 1940
},
{
"epoch": 7.96,
"learning_rate": 3.2113550017198734e-08,
"loss": 0.8274,
"step": 1950
},
{
"epoch": 8.0,
"learning_rate": 0.0,
"loss": 0.7359,
"step": 1960
},
{
"epoch": 8.0,
"step": 1960,
"total_flos": 7.457847416862474e+17,
"train_loss": 1.1027992168251348,
"train_runtime": 31447.7257,
"train_samples_per_second": 0.997,
"train_steps_per_second": 0.062
}
],
"logging_steps": 10,
"max_steps": 1960,
"num_input_tokens_seen": 0,
"num_train_epochs": 8,
"save_steps": 100,
"total_flos": 7.457847416862474e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}