pszemraj's picture
manual upload with upload_folder.py
8561eb8
raw
history blame
67 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.784623217922607,
"eval_steps": 491,
"global_step": 5310,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"eval_loss": 2.4941999912261963,
"eval_runtime": 2.652,
"eval_samples_per_second": 915.917,
"eval_steps_per_second": 114.631,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 8.771929824561403e-06,
"loss": 1.6371,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 1.7543859649122806e-05,
"loss": 1.5433,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 2.6315789473684212e-05,
"loss": 1.4686,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 3.508771929824561e-05,
"loss": 1.4179,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 4.3859649122807014e-05,
"loss": 1.4009,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 5.2631578947368424e-05,
"loss": 1.3749,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 6.140350877192983e-05,
"loss": 1.385,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 7.017543859649122e-05,
"loss": 1.3324,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 7.894736842105263e-05,
"loss": 1.3405,
"step": 90
},
{
"epoch": 0.03,
"learning_rate": 8.771929824561403e-05,
"loss": 1.343,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 9.649122807017544e-05,
"loss": 1.292,
"step": 110
},
{
"epoch": 0.04,
"learning_rate": 0.00010526315789473685,
"loss": 1.2815,
"step": 120
},
{
"epoch": 0.04,
"learning_rate": 0.00011403508771929824,
"loss": 1.3075,
"step": 130
},
{
"epoch": 0.05,
"learning_rate": 0.00012280701754385965,
"loss": 1.3112,
"step": 140
},
{
"epoch": 0.05,
"learning_rate": 0.00013157894736842108,
"loss": 1.2992,
"step": 150
},
{
"epoch": 0.05,
"learning_rate": 0.00014035087719298245,
"loss": 1.2765,
"step": 160
},
{
"epoch": 0.06,
"learning_rate": 0.00014912280701754387,
"loss": 1.2929,
"step": 170
},
{
"epoch": 0.06,
"learning_rate": 0.00015789473684210527,
"loss": 1.3165,
"step": 180
},
{
"epoch": 0.06,
"learning_rate": 0.0001666666666666667,
"loss": 1.2967,
"step": 190
},
{
"epoch": 0.07,
"learning_rate": 0.00017543859649122806,
"loss": 1.2985,
"step": 200
},
{
"epoch": 0.07,
"learning_rate": 0.00018421052631578948,
"loss": 1.2911,
"step": 210
},
{
"epoch": 0.07,
"learning_rate": 0.00019298245614035088,
"loss": 1.2855,
"step": 220
},
{
"epoch": 0.08,
"learning_rate": 0.00019999993847052535,
"loss": 1.3145,
"step": 230
},
{
"epoch": 0.08,
"learning_rate": 0.00019999778494686225,
"loss": 1.3182,
"step": 240
},
{
"epoch": 0.08,
"learning_rate": 0.00019999255502518282,
"loss": 1.3009,
"step": 250
},
{
"epoch": 0.09,
"learning_rate": 0.0001999842488663838,
"loss": 1.2914,
"step": 260
},
{
"epoch": 0.09,
"learning_rate": 0.00019997286672600138,
"loss": 1.3277,
"step": 270
},
{
"epoch": 0.1,
"learning_rate": 0.0001999584089542032,
"loss": 1.3203,
"step": 280
},
{
"epoch": 0.1,
"learning_rate": 0.00019994087599577783,
"loss": 1.2884,
"step": 290
},
{
"epoch": 0.1,
"learning_rate": 0.00019992026839012067,
"loss": 1.2917,
"step": 300
},
{
"epoch": 0.11,
"learning_rate": 0.00019989658677121785,
"loss": 1.2794,
"step": 310
},
{
"epoch": 0.11,
"learning_rate": 0.00019986983186762628,
"loss": 1.2987,
"step": 320
},
{
"epoch": 0.11,
"learning_rate": 0.00019984000450245156,
"loss": 1.2775,
"step": 330
},
{
"epoch": 0.12,
"learning_rate": 0.00019980710559332248,
"loss": 1.2878,
"step": 340
},
{
"epoch": 0.12,
"learning_rate": 0.00019977113615236283,
"loss": 1.2705,
"step": 350
},
{
"epoch": 0.12,
"learning_rate": 0.00019973209728616032,
"loss": 1.2717,
"step": 360
},
{
"epoch": 0.13,
"learning_rate": 0.0001996899901957324,
"loss": 1.2748,
"step": 370
},
{
"epoch": 0.13,
"learning_rate": 0.00019964481617648953,
"loss": 1.2804,
"step": 380
},
{
"epoch": 0.13,
"learning_rate": 0.00019959657661819508,
"loss": 1.2697,
"step": 390
},
{
"epoch": 0.14,
"learning_rate": 0.00019954527300492276,
"loss": 1.2716,
"step": 400
},
{
"epoch": 0.14,
"learning_rate": 0.00019949090691501084,
"loss": 1.27,
"step": 410
},
{
"epoch": 0.14,
"learning_rate": 0.00019943348002101371,
"loss": 1.2659,
"step": 420
},
{
"epoch": 0.15,
"learning_rate": 0.00019937299408965035,
"loss": 1.2765,
"step": 430
},
{
"epoch": 0.15,
"learning_rate": 0.0001993094509817499,
"loss": 1.2886,
"step": 440
},
{
"epoch": 0.15,
"learning_rate": 0.00019924285265219467,
"loss": 1.2459,
"step": 450
},
{
"epoch": 0.16,
"learning_rate": 0.00019917320114985965,
"loss": 1.2433,
"step": 460
},
{
"epoch": 0.16,
"learning_rate": 0.00019910049861754977,
"loss": 1.2468,
"step": 470
},
{
"epoch": 0.16,
"learning_rate": 0.00019902474729193386,
"loss": 1.239,
"step": 480
},
{
"epoch": 0.17,
"learning_rate": 0.00019894594950347575,
"loss": 1.2391,
"step": 490
},
{
"epoch": 0.17,
"eval_loss": 1.329033374786377,
"eval_runtime": 2.5491,
"eval_samples_per_second": 952.867,
"eval_steps_per_second": 119.255,
"step": 491
},
{
"epoch": 0.17,
"learning_rate": 0.00019886410767636282,
"loss": 1.2567,
"step": 500
},
{
"epoch": 0.17,
"learning_rate": 0.00019877922432843116,
"loss": 1.2706,
"step": 510
},
{
"epoch": 0.18,
"learning_rate": 0.0001986913020710882,
"loss": 1.2458,
"step": 520
},
{
"epoch": 0.18,
"learning_rate": 0.0001986003436092325,
"loss": 1.2401,
"step": 530
},
{
"epoch": 0.18,
"learning_rate": 0.00019850635174117033,
"loss": 1.2642,
"step": 540
},
{
"epoch": 0.19,
"learning_rate": 0.00019840932935852968,
"loss": 1.2225,
"step": 550
},
{
"epoch": 0.19,
"learning_rate": 0.0001983092794461714,
"loss": 1.2084,
"step": 560
},
{
"epoch": 0.19,
"learning_rate": 0.00019820620508209712,
"loss": 1.2257,
"step": 570
},
{
"epoch": 0.2,
"learning_rate": 0.00019810010943735479,
"loss": 1.2629,
"step": 580
},
{
"epoch": 0.2,
"learning_rate": 0.00019799099577594097,
"loss": 1.2333,
"step": 590
},
{
"epoch": 0.2,
"learning_rate": 0.00019787886745470065,
"loss": 1.2591,
"step": 600
},
{
"epoch": 0.21,
"learning_rate": 0.00019776372792322357,
"loss": 1.2474,
"step": 610
},
{
"epoch": 0.21,
"learning_rate": 0.00019764558072373856,
"loss": 1.2386,
"step": 620
},
{
"epoch": 0.21,
"learning_rate": 0.00019752442949100415,
"loss": 1.2251,
"step": 630
},
{
"epoch": 0.22,
"learning_rate": 0.00019740027795219707,
"loss": 1.2031,
"step": 640
},
{
"epoch": 0.22,
"learning_rate": 0.00019727312992679733,
"loss": 1.2242,
"step": 650
},
{
"epoch": 0.22,
"learning_rate": 0.00019714298932647098,
"loss": 1.2364,
"step": 660
},
{
"epoch": 0.23,
"learning_rate": 0.00019700986015494957,
"loss": 1.2115,
"step": 670
},
{
"epoch": 0.23,
"learning_rate": 0.00019687374650790692,
"loss": 1.1958,
"step": 680
},
{
"epoch": 0.23,
"learning_rate": 0.00019673465257283342,
"loss": 1.2332,
"step": 690
},
{
"epoch": 0.24,
"learning_rate": 0.00019659258262890683,
"loss": 1.2024,
"step": 700
},
{
"epoch": 0.24,
"learning_rate": 0.00019644754104686097,
"loss": 1.2209,
"step": 710
},
{
"epoch": 0.24,
"learning_rate": 0.00019629953228885098,
"loss": 1.2114,
"step": 720
},
{
"epoch": 0.25,
"learning_rate": 0.00019614856090831626,
"loss": 1.1819,
"step": 730
},
{
"epoch": 0.25,
"learning_rate": 0.0001959946315498402,
"loss": 1.1833,
"step": 740
},
{
"epoch": 0.25,
"learning_rate": 0.00019583774894900747,
"loss": 1.2144,
"step": 750
},
{
"epoch": 0.26,
"learning_rate": 0.00019567791793225818,
"loss": 1.2038,
"step": 760
},
{
"epoch": 0.26,
"learning_rate": 0.00019551514341673948,
"loss": 1.2166,
"step": 770
},
{
"epoch": 0.26,
"learning_rate": 0.00019534943041015423,
"loss": 1.1866,
"step": 780
},
{
"epoch": 0.27,
"learning_rate": 0.00019518078401060707,
"loss": 1.2352,
"step": 790
},
{
"epoch": 0.27,
"learning_rate": 0.00019500920940644734,
"loss": 1.1941,
"step": 800
},
{
"epoch": 0.27,
"learning_rate": 0.00019483471187610972,
"loss": 1.176,
"step": 810
},
{
"epoch": 0.28,
"learning_rate": 0.00019465729678795168,
"loss": 1.1938,
"step": 820
},
{
"epoch": 0.28,
"learning_rate": 0.00019447696960008838,
"loss": 1.2077,
"step": 830
},
{
"epoch": 0.29,
"learning_rate": 0.00019429373586022473,
"loss": 1.1884,
"step": 840
},
{
"epoch": 0.29,
"learning_rate": 0.00019410760120548473,
"loss": 1.2051,
"step": 850
},
{
"epoch": 0.29,
"learning_rate": 0.00019391857136223802,
"loss": 1.1529,
"step": 860
},
{
"epoch": 0.3,
"learning_rate": 0.00019372665214592382,
"loss": 1.1833,
"step": 870
},
{
"epoch": 0.3,
"learning_rate": 0.00019353184946087183,
"loss": 1.1731,
"step": 880
},
{
"epoch": 0.3,
"learning_rate": 0.00019333416930012077,
"loss": 1.1893,
"step": 890
},
{
"epoch": 0.31,
"learning_rate": 0.00019313361774523385,
"loss": 1.1804,
"step": 900
},
{
"epoch": 0.31,
"learning_rate": 0.00019293020096611185,
"loss": 1.1439,
"step": 910
},
{
"epoch": 0.31,
"learning_rate": 0.0001927239252208031,
"loss": 1.1609,
"step": 920
},
{
"epoch": 0.32,
"learning_rate": 0.00019251479685531114,
"loss": 1.1852,
"step": 930
},
{
"epoch": 0.32,
"learning_rate": 0.00019230282230339935,
"loss": 1.1543,
"step": 940
},
{
"epoch": 0.32,
"learning_rate": 0.00019208800808639308,
"loss": 1.1703,
"step": 950
},
{
"epoch": 0.33,
"learning_rate": 0.00019187036081297907,
"loss": 1.1608,
"step": 960
},
{
"epoch": 0.33,
"learning_rate": 0.00019164988717900198,
"loss": 1.1504,
"step": 970
},
{
"epoch": 0.33,
"learning_rate": 0.0001914265939672586,
"loss": 1.1867,
"step": 980
},
{
"epoch": 0.33,
"eval_loss": 1.2649266719818115,
"eval_runtime": 2.5506,
"eval_samples_per_second": 952.326,
"eval_steps_per_second": 119.188,
"step": 982
},
{
"epoch": 0.34,
"learning_rate": 0.000191200488047289,
"loss": 1.1861,
"step": 990
},
{
"epoch": 0.34,
"learning_rate": 0.00019097157637516533,
"loss": 1.2134,
"step": 1000
},
{
"epoch": 0.34,
"learning_rate": 0.00019073986599327768,
"loss": 1.1595,
"step": 1010
},
{
"epoch": 0.35,
"learning_rate": 0.0001905053640301176,
"loss": 1.2316,
"step": 1020
},
{
"epoch": 0.35,
"learning_rate": 0.00019026807770005857,
"loss": 1.1175,
"step": 1030
},
{
"epoch": 0.35,
"learning_rate": 0.00019002801430313427,
"loss": 1.1671,
"step": 1040
},
{
"epoch": 0.36,
"learning_rate": 0.0001897851812248139,
"loss": 1.1988,
"step": 1050
},
{
"epoch": 0.36,
"learning_rate": 0.00018953958593577493,
"loss": 1.1415,
"step": 1060
},
{
"epoch": 0.36,
"learning_rate": 0.0001892912359916733,
"loss": 1.1851,
"step": 1070
},
{
"epoch": 0.37,
"learning_rate": 0.000189040139032911,
"loss": 1.1746,
"step": 1080
},
{
"epoch": 0.37,
"learning_rate": 0.00018878630278440102,
"loss": 1.201,
"step": 1090
},
{
"epoch": 0.37,
"learning_rate": 0.00018852973505532962,
"loss": 1.1623,
"step": 1100
},
{
"epoch": 0.38,
"learning_rate": 0.00018827044373891623,
"loss": 1.153,
"step": 1110
},
{
"epoch": 0.38,
"learning_rate": 0.0001880084368121704,
"loss": 1.17,
"step": 1120
},
{
"epoch": 0.38,
"learning_rate": 0.0001877437223356466,
"loss": 1.1549,
"step": 1130
},
{
"epoch": 0.39,
"learning_rate": 0.00018747630845319612,
"loss": 1.1541,
"step": 1140
},
{
"epoch": 0.39,
"learning_rate": 0.00018720620339171656,
"loss": 1.1692,
"step": 1150
},
{
"epoch": 0.39,
"learning_rate": 0.00018693341546089878,
"loss": 1.1707,
"step": 1160
},
{
"epoch": 0.4,
"learning_rate": 0.0001866579530529711,
"loss": 1.1899,
"step": 1170
},
{
"epoch": 0.4,
"learning_rate": 0.0001863798246424413,
"loss": 1.165,
"step": 1180
},
{
"epoch": 0.4,
"learning_rate": 0.00018609903878583585,
"loss": 1.1669,
"step": 1190
},
{
"epoch": 0.41,
"learning_rate": 0.00018581560412143661,
"loss": 1.1309,
"step": 1200
},
{
"epoch": 0.41,
"learning_rate": 0.0001855295293690151,
"loss": 1.1622,
"step": 1210
},
{
"epoch": 0.41,
"learning_rate": 0.00018524082332956428,
"loss": 1.1471,
"step": 1220
},
{
"epoch": 0.42,
"learning_rate": 0.00018494949488502774,
"loss": 1.1352,
"step": 1230
},
{
"epoch": 0.42,
"learning_rate": 0.00018465555299802656,
"loss": 1.1646,
"step": 1240
},
{
"epoch": 0.42,
"learning_rate": 0.00018435900671158334,
"loss": 1.1649,
"step": 1250
},
{
"epoch": 0.43,
"learning_rate": 0.00018405986514884434,
"loss": 1.1693,
"step": 1260
},
{
"epoch": 0.43,
"learning_rate": 0.0001837581375127984,
"loss": 1.1341,
"step": 1270
},
{
"epoch": 0.43,
"learning_rate": 0.00018345383308599424,
"loss": 1.1467,
"step": 1280
},
{
"epoch": 0.44,
"learning_rate": 0.00018314696123025454,
"loss": 1.1563,
"step": 1290
},
{
"epoch": 0.44,
"learning_rate": 0.00018283753138638808,
"loss": 1.1624,
"step": 1300
},
{
"epoch": 0.44,
"learning_rate": 0.00018252555307389935,
"loss": 1.1402,
"step": 1310
},
{
"epoch": 0.45,
"learning_rate": 0.00018221103589069552,
"loss": 1.122,
"step": 1320
},
{
"epoch": 0.45,
"learning_rate": 0.00018189398951279134,
"loss": 1.1523,
"step": 1330
},
{
"epoch": 0.45,
"learning_rate": 0.0001815744236940113,
"loss": 1.1174,
"step": 1340
},
{
"epoch": 0.46,
"learning_rate": 0.00018125234826568972,
"loss": 1.1418,
"step": 1350
},
{
"epoch": 0.46,
"learning_rate": 0.00018092777313636813,
"loss": 1.1447,
"step": 1360
},
{
"epoch": 0.47,
"learning_rate": 0.0001806007082914906,
"loss": 1.1358,
"step": 1370
},
{
"epoch": 0.47,
"learning_rate": 0.00018027116379309638,
"loss": 1.1245,
"step": 1380
},
{
"epoch": 0.47,
"learning_rate": 0.00017993914977951046,
"loss": 1.1407,
"step": 1390
},
{
"epoch": 0.48,
"learning_rate": 0.0001796046764650316,
"loss": 1.1243,
"step": 1400
},
{
"epoch": 0.48,
"learning_rate": 0.00017926775413961815,
"loss": 1.129,
"step": 1410
},
{
"epoch": 0.48,
"learning_rate": 0.00017892839316857145,
"loss": 1.1337,
"step": 1420
},
{
"epoch": 0.49,
"learning_rate": 0.00017858660399221697,
"loss": 1.1148,
"step": 1430
},
{
"epoch": 0.49,
"learning_rate": 0.00017824239712558302,
"loss": 1.0814,
"step": 1440
},
{
"epoch": 0.49,
"learning_rate": 0.0001778957831580774,
"loss": 1.1489,
"step": 1450
},
{
"epoch": 0.5,
"learning_rate": 0.0001775467727531615,
"loss": 1.1341,
"step": 1460
},
{
"epoch": 0.5,
"learning_rate": 0.00017719537664802234,
"loss": 1.1031,
"step": 1470
},
{
"epoch": 0.5,
"eval_loss": 1.2352267503738403,
"eval_runtime": 2.5573,
"eval_samples_per_second": 949.821,
"eval_steps_per_second": 118.874,
"step": 1473
},
{
"epoch": 0.5,
"learning_rate": 0.00017684160565324222,
"loss": 1.1272,
"step": 1480
},
{
"epoch": 0.51,
"learning_rate": 0.00017648547065246607,
"loss": 1.1159,
"step": 1490
},
{
"epoch": 0.51,
"learning_rate": 0.00017612698260206666,
"loss": 1.1203,
"step": 1500
},
{
"epoch": 0.51,
"learning_rate": 0.0001757661525308076,
"loss": 1.0934,
"step": 1510
},
{
"epoch": 0.52,
"learning_rate": 0.00017540299153950386,
"loss": 1.0958,
"step": 1520
},
{
"epoch": 0.52,
"learning_rate": 0.00017503751080068052,
"loss": 1.1486,
"step": 1530
},
{
"epoch": 0.52,
"learning_rate": 0.0001746697215582288,
"loss": 1.1456,
"step": 1540
},
{
"epoch": 0.53,
"learning_rate": 0.00017429963512706026,
"loss": 1.1408,
"step": 1550
},
{
"epoch": 0.53,
"learning_rate": 0.0001739272628927588,
"loss": 1.0965,
"step": 1560
},
{
"epoch": 0.53,
"learning_rate": 0.00017355261631123015,
"loss": 1.1339,
"step": 1570
},
{
"epoch": 0.54,
"learning_rate": 0.00017317570690834967,
"loss": 1.1235,
"step": 1580
},
{
"epoch": 0.54,
"learning_rate": 0.00017279654627960756,
"loss": 1.1254,
"step": 1590
},
{
"epoch": 0.54,
"learning_rate": 0.00017241514608975223,
"loss": 1.1341,
"step": 1600
},
{
"epoch": 0.55,
"learning_rate": 0.0001720315180724315,
"loss": 1.1417,
"step": 1610
},
{
"epoch": 0.55,
"learning_rate": 0.00017164567402983152,
"loss": 1.1376,
"step": 1620
},
{
"epoch": 0.55,
"learning_rate": 0.0001712576258323137,
"loss": 1.1065,
"step": 1630
},
{
"epoch": 0.56,
"learning_rate": 0.00017086738541804947,
"loss": 1.1081,
"step": 1640
},
{
"epoch": 0.56,
"learning_rate": 0.00017047496479265318,
"loss": 1.1324,
"step": 1650
},
{
"epoch": 0.56,
"learning_rate": 0.0001700803760288126,
"loss": 1.1182,
"step": 1660
},
{
"epoch": 0.57,
"learning_rate": 0.00016968363126591748,
"loss": 1.1284,
"step": 1670
},
{
"epoch": 0.57,
"learning_rate": 0.0001692847427096862,
"loss": 1.1011,
"step": 1680
},
{
"epoch": 0.57,
"learning_rate": 0.00016888372263179022,
"loss": 1.1196,
"step": 1690
},
{
"epoch": 0.58,
"learning_rate": 0.00016848058336947657,
"loss": 1.1012,
"step": 1700
},
{
"epoch": 0.58,
"learning_rate": 0.00016807533732518821,
"loss": 1.1076,
"step": 1710
},
{
"epoch": 0.58,
"learning_rate": 0.00016766799696618255,
"loss": 1.1175,
"step": 1720
},
{
"epoch": 0.59,
"learning_rate": 0.00016725857482414796,
"loss": 1.0902,
"step": 1730
},
{
"epoch": 0.59,
"learning_rate": 0.00016684708349481804,
"loss": 1.1322,
"step": 1740
},
{
"epoch": 0.59,
"learning_rate": 0.0001664335356375843,
"loss": 1.1016,
"step": 1750
},
{
"epoch": 0.6,
"learning_rate": 0.00016601794397510665,
"loss": 1.1073,
"step": 1760
},
{
"epoch": 0.6,
"learning_rate": 0.00016560032129292197,
"loss": 1.1127,
"step": 1770
},
{
"epoch": 0.6,
"learning_rate": 0.00016518068043905074,
"loss": 1.0561,
"step": 1780
},
{
"epoch": 0.61,
"learning_rate": 0.0001647590343236018,
"loss": 1.0951,
"step": 1790
},
{
"epoch": 0.61,
"learning_rate": 0.00016433539591837525,
"loss": 1.1138,
"step": 1800
},
{
"epoch": 0.61,
"learning_rate": 0.00016390977825646327,
"loss": 1.0807,
"step": 1810
},
{
"epoch": 0.62,
"learning_rate": 0.00016348219443184923,
"loss": 1.1041,
"step": 1820
},
{
"epoch": 0.62,
"learning_rate": 0.00016305265759900477,
"loss": 1.0948,
"step": 1830
},
{
"epoch": 0.62,
"learning_rate": 0.0001626211809724852,
"loss": 1.1167,
"step": 1840
},
{
"epoch": 0.63,
"learning_rate": 0.000162187777826523,
"loss": 1.1128,
"step": 1850
},
{
"epoch": 0.63,
"learning_rate": 0.0001617524614946192,
"loss": 1.124,
"step": 1860
},
{
"epoch": 0.63,
"learning_rate": 0.00016131524536913352,
"loss": 1.0904,
"step": 1870
},
{
"epoch": 0.64,
"learning_rate": 0.00016087614290087208,
"loss": 1.0797,
"step": 1880
},
{
"epoch": 0.64,
"learning_rate": 0.00016043516759867374,
"loss": 1.1135,
"step": 1890
},
{
"epoch": 0.64,
"learning_rate": 0.00015999233302899443,
"loss": 1.0823,
"step": 1900
},
{
"epoch": 0.65,
"learning_rate": 0.0001595476528154899,
"loss": 1.1011,
"step": 1910
},
{
"epoch": 0.65,
"learning_rate": 0.0001591011406385964,
"loss": 1.0804,
"step": 1920
},
{
"epoch": 0.66,
"learning_rate": 0.00015865281023510997,
"loss": 1.0908,
"step": 1930
},
{
"epoch": 0.66,
"learning_rate": 0.00015820267539776376,
"loss": 1.1049,
"step": 1940
},
{
"epoch": 0.66,
"learning_rate": 0.00015775074997480374,
"loss": 1.0597,
"step": 1950
},
{
"epoch": 0.67,
"learning_rate": 0.0001572970478695626,
"loss": 1.0856,
"step": 1960
},
{
"epoch": 0.67,
"eval_loss": 1.2079788446426392,
"eval_runtime": 2.5537,
"eval_samples_per_second": 951.168,
"eval_steps_per_second": 119.043,
"step": 1964
},
{
"epoch": 0.67,
"learning_rate": 0.00015684158304003215,
"loss": 1.092,
"step": 1970
},
{
"epoch": 0.67,
"learning_rate": 0.0001563843694984336,
"loss": 1.1,
"step": 1980
},
{
"epoch": 0.68,
"learning_rate": 0.000155925421310787,
"loss": 1.0925,
"step": 1990
},
{
"epoch": 0.68,
"learning_rate": 0.00015546475259647794,
"loss": 1.0717,
"step": 2000
},
{
"epoch": 0.68,
"learning_rate": 0.00015500237752782362,
"loss": 1.0865,
"step": 2010
},
{
"epoch": 0.69,
"learning_rate": 0.0001545383103296365,
"loss": 1.0816,
"step": 2020
},
{
"epoch": 0.69,
"learning_rate": 0.0001540725652787869,
"loss": 1.0913,
"step": 2030
},
{
"epoch": 0.69,
"learning_rate": 0.00015360515670376375,
"loss": 1.0932,
"step": 2040
},
{
"epoch": 0.7,
"learning_rate": 0.00015313609898423366,
"loss": 1.0835,
"step": 2050
},
{
"epoch": 0.7,
"learning_rate": 0.0001526654065505987,
"loss": 1.1036,
"step": 2060
},
{
"epoch": 0.7,
"learning_rate": 0.00015219309388355226,
"loss": 1.0698,
"step": 2070
},
{
"epoch": 0.71,
"learning_rate": 0.00015171917551363374,
"loss": 1.0814,
"step": 2080
},
{
"epoch": 0.71,
"learning_rate": 0.00015124366602078146,
"loss": 1.0823,
"step": 2090
},
{
"epoch": 0.71,
"learning_rate": 0.000150766580033884,
"loss": 1.0964,
"step": 2100
},
{
"epoch": 0.72,
"learning_rate": 0.00015028793223033037,
"loss": 1.0968,
"step": 2110
},
{
"epoch": 0.72,
"learning_rate": 0.0001498077373355582,
"loss": 1.0848,
"step": 2120
},
{
"epoch": 0.72,
"learning_rate": 0.00014932601012260105,
"loss": 1.0647,
"step": 2130
},
{
"epoch": 0.73,
"learning_rate": 0.0001488427654116335,
"loss": 1.0795,
"step": 2140
},
{
"epoch": 0.73,
"learning_rate": 0.00014835801806951566,
"loss": 1.0949,
"step": 2150
},
{
"epoch": 0.73,
"learning_rate": 0.00014787178300933542,
"loss": 1.0942,
"step": 2160
},
{
"epoch": 0.74,
"learning_rate": 0.0001473840751899499,
"loss": 1.0799,
"step": 2170
},
{
"epoch": 0.74,
"learning_rate": 0.00014689490961552513,
"loss": 1.0883,
"step": 2180
},
{
"epoch": 0.74,
"learning_rate": 0.00014640430133507445,
"loss": 1.0913,
"step": 2190
},
{
"epoch": 0.75,
"learning_rate": 0.00014591226544199564,
"loss": 1.0884,
"step": 2200
},
{
"epoch": 0.75,
"learning_rate": 0.00014541881707360642,
"loss": 1.0917,
"step": 2210
},
{
"epoch": 0.75,
"learning_rate": 0.00014492397141067887,
"loss": 1.0883,
"step": 2220
},
{
"epoch": 0.76,
"learning_rate": 0.0001444277436769724,
"loss": 1.1236,
"step": 2230
},
{
"epoch": 0.76,
"learning_rate": 0.0001439301491387653,
"loss": 1.0542,
"step": 2240
},
{
"epoch": 0.76,
"learning_rate": 0.00014343120310438513,
"loss": 1.0335,
"step": 2250
},
{
"epoch": 0.77,
"learning_rate": 0.00014293092092373786,
"loss": 1.0561,
"step": 2260
},
{
"epoch": 0.77,
"learning_rate": 0.00014242931798783546,
"loss": 1.0721,
"step": 2270
},
{
"epoch": 0.77,
"learning_rate": 0.0001419264097283225,
"loss": 1.0415,
"step": 2280
},
{
"epoch": 0.78,
"learning_rate": 0.00014142221161700142,
"loss": 1.0871,
"step": 2290
},
{
"epoch": 0.78,
"learning_rate": 0.00014091673916535654,
"loss": 1.044,
"step": 2300
},
{
"epoch": 0.78,
"learning_rate": 0.00014041000792407675,
"loss": 1.0579,
"step": 2310
},
{
"epoch": 0.79,
"learning_rate": 0.00013990203348257721,
"loss": 1.052,
"step": 2320
},
{
"epoch": 0.79,
"learning_rate": 0.0001393928314685198,
"loss": 1.0641,
"step": 2330
},
{
"epoch": 0.79,
"learning_rate": 0.00013888241754733208,
"loss": 1.0662,
"step": 2340
},
{
"epoch": 0.8,
"learning_rate": 0.0001383708074217257,
"loss": 1.0359,
"step": 2350
},
{
"epoch": 0.8,
"learning_rate": 0.00013785801683121294,
"loss": 1.0764,
"step": 2360
},
{
"epoch": 0.8,
"learning_rate": 0.00013734406155162292,
"loss": 1.044,
"step": 2370
},
{
"epoch": 0.81,
"learning_rate": 0.00013682895739461587,
"loss": 1.049,
"step": 2380
},
{
"epoch": 0.81,
"learning_rate": 0.00013631272020719686,
"loss": 1.0523,
"step": 2390
},
{
"epoch": 0.81,
"learning_rate": 0.00013579536587122828,
"loss": 1.0728,
"step": 2400
},
{
"epoch": 0.82,
"learning_rate": 0.0001352769103029412,
"loss": 1.0209,
"step": 2410
},
{
"epoch": 0.82,
"learning_rate": 0.00013475736945244574,
"loss": 1.0455,
"step": 2420
},
{
"epoch": 0.82,
"learning_rate": 0.0001342367593032404,
"loss": 1.0341,
"step": 2430
},
{
"epoch": 0.83,
"learning_rate": 0.00013371509587172022,
"loss": 1.0626,
"step": 2440
},
{
"epoch": 0.83,
"learning_rate": 0.00013319239520668416,
"loss": 1.0602,
"step": 2450
},
{
"epoch": 0.83,
"eval_loss": 1.1820294857025146,
"eval_runtime": 2.5668,
"eval_samples_per_second": 946.308,
"eval_steps_per_second": 118.435,
"step": 2455
},
{
"epoch": 0.84,
"learning_rate": 0.0001326686733888413,
"loss": 1.048,
"step": 2460
},
{
"epoch": 0.84,
"learning_rate": 0.00013214394653031616,
"loss": 1.0772,
"step": 2470
},
{
"epoch": 0.84,
"learning_rate": 0.00013161823077415297,
"loss": 1.0481,
"step": 2480
},
{
"epoch": 0.85,
"learning_rate": 0.0001310915422938191,
"loss": 1.0333,
"step": 2490
},
{
"epoch": 0.85,
"learning_rate": 0.00013056389729270738,
"loss": 1.0429,
"step": 2500
},
{
"epoch": 0.85,
"learning_rate": 0.0001300353120036378,
"loss": 1.012,
"step": 2510
},
{
"epoch": 0.86,
"learning_rate": 0.00012950580268835784,
"loss": 1.0759,
"step": 2520
},
{
"epoch": 0.86,
"learning_rate": 0.0001289753856370424,
"loss": 1.0514,
"step": 2530
},
{
"epoch": 0.86,
"learning_rate": 0.00012844407716779266,
"loss": 1.0419,
"step": 2540
},
{
"epoch": 0.87,
"learning_rate": 0.0001279118936261338,
"loss": 1.0373,
"step": 2550
},
{
"epoch": 0.87,
"learning_rate": 0.00012737885138451246,
"loss": 1.0306,
"step": 2560
},
{
"epoch": 0.87,
"learning_rate": 0.0001268449668417928,
"loss": 1.0389,
"step": 2570
},
{
"epoch": 0.88,
"learning_rate": 0.00012631025642275212,
"loss": 1.0332,
"step": 2580
},
{
"epoch": 0.88,
"learning_rate": 0.00012577473657757556,
"loss": 1.0231,
"step": 2590
},
{
"epoch": 0.88,
"learning_rate": 0.00012523842378134992,
"loss": 1.0648,
"step": 2600
},
{
"epoch": 0.89,
"learning_rate": 0.0001247013345335569,
"loss": 1.0809,
"step": 2610
},
{
"epoch": 0.89,
"learning_rate": 0.00012416348535756544,
"loss": 1.0716,
"step": 2620
},
{
"epoch": 0.89,
"learning_rate": 0.00012362489280012348,
"loss": 1.0139,
"step": 2630
},
{
"epoch": 0.9,
"learning_rate": 0.0001230855734308488,
"loss": 1.0637,
"step": 2640
},
{
"epoch": 0.9,
"learning_rate": 0.00012254554384171924,
"loss": 1.0393,
"step": 2650
},
{
"epoch": 0.9,
"learning_rate": 0.00012200482064656248,
"loss": 1.0292,
"step": 2660
},
{
"epoch": 0.91,
"learning_rate": 0.00012146342048054453,
"loss": 1.04,
"step": 2670
},
{
"epoch": 0.91,
"learning_rate": 0.0001209213599996584,
"loss": 1.0494,
"step": 2680
},
{
"epoch": 0.91,
"learning_rate": 0.00012037865588021127,
"loss": 1.021,
"step": 2690
},
{
"epoch": 0.92,
"learning_rate": 0.0001198353248183118,
"loss": 1.0079,
"step": 2700
},
{
"epoch": 0.92,
"learning_rate": 0.00011929138352935623,
"loss": 1.0282,
"step": 2710
},
{
"epoch": 0.92,
"learning_rate": 0.00011874684874751421,
"loss": 1.0061,
"step": 2720
},
{
"epoch": 0.93,
"learning_rate": 0.00011820173722521413,
"loss": 1.0071,
"step": 2730
},
{
"epoch": 0.93,
"learning_rate": 0.00011765606573262744,
"loss": 0.9862,
"step": 2740
},
{
"epoch": 0.93,
"learning_rate": 0.00011710985105715302,
"loss": 1.0342,
"step": 2750
},
{
"epoch": 0.94,
"learning_rate": 0.0001165631100029005,
"loss": 1.0448,
"step": 2760
},
{
"epoch": 0.94,
"learning_rate": 0.00011601585939017344,
"loss": 1.037,
"step": 2770
},
{
"epoch": 0.94,
"learning_rate": 0.00011546811605495169,
"loss": 1.0428,
"step": 2780
},
{
"epoch": 0.95,
"learning_rate": 0.00011491989684837366,
"loss": 1.0409,
"step": 2790
},
{
"epoch": 0.95,
"learning_rate": 0.00011437121863621775,
"loss": 1.0337,
"step": 2800
},
{
"epoch": 0.95,
"learning_rate": 0.00011382209829838347,
"loss": 1.0188,
"step": 2810
},
{
"epoch": 0.96,
"learning_rate": 0.00011327255272837221,
"loss": 1.0313,
"step": 2820
},
{
"epoch": 0.96,
"learning_rate": 0.00011272259883276745,
"loss": 1.0414,
"step": 2830
},
{
"epoch": 0.96,
"learning_rate": 0.00011217225353071472,
"loss": 1.0126,
"step": 2840
},
{
"epoch": 0.97,
"learning_rate": 0.00011162153375340101,
"loss": 1.0258,
"step": 2850
},
{
"epoch": 0.97,
"learning_rate": 0.00011107045644353387,
"loss": 1.0141,
"step": 2860
},
{
"epoch": 0.97,
"learning_rate": 0.00011051903855482034,
"loss": 1.022,
"step": 2870
},
{
"epoch": 0.98,
"learning_rate": 0.0001099672970514451,
"loss": 1.0469,
"step": 2880
},
{
"epoch": 0.98,
"learning_rate": 0.00010941524890754884,
"loss": 1.0254,
"step": 2890
},
{
"epoch": 0.98,
"learning_rate": 0.00010886291110670593,
"loss": 1.0386,
"step": 2900
},
{
"epoch": 0.99,
"learning_rate": 0.00010831030064140184,
"loss": 1.0029,
"step": 2910
},
{
"epoch": 0.99,
"learning_rate": 0.00010775743451251059,
"loss": 1.0349,
"step": 2920
},
{
"epoch": 0.99,
"learning_rate": 0.00010720432972877155,
"loss": 1.0296,
"step": 2930
},
{
"epoch": 1.0,
"learning_rate": 0.00010665100330626625,
"loss": 1.0105,
"step": 2940
},
{
"epoch": 1.0,
"eval_loss": 1.1566660404205322,
"eval_runtime": 2.5517,
"eval_samples_per_second": 951.906,
"eval_steps_per_second": 119.135,
"step": 2946
},
{
"epoch": 1.0,
"learning_rate": 0.00010609747226789476,
"loss": 1.0512,
"step": 2950
},
{
"epoch": 1.0,
"learning_rate": 0.0001055437536428523,
"loss": 0.9893,
"step": 2960
},
{
"epoch": 1.01,
"learning_rate": 0.00010498986446610488,
"loss": 0.9981,
"step": 2970
},
{
"epoch": 1.01,
"learning_rate": 0.00010443582177786564,
"loss": 1.0188,
"step": 2980
},
{
"epoch": 1.01,
"learning_rate": 0.00010388164262307046,
"loss": 0.9988,
"step": 2990
},
{
"epoch": 1.0,
"learning_rate": 0.00010332734405085342,
"loss": 1.0102,
"step": 3000
},
{
"epoch": 1.0,
"learning_rate": 0.00010277294311402259,
"loss": 0.9336,
"step": 3010
},
{
"epoch": 1.01,
"learning_rate": 0.00010221845686853517,
"loss": 0.8864,
"step": 3020
},
{
"epoch": 1.01,
"learning_rate": 0.00010166390237297287,
"loss": 0.8955,
"step": 3030
},
{
"epoch": 1.01,
"learning_rate": 0.00010110929668801711,
"loss": 0.9231,
"step": 3040
},
{
"epoch": 1.02,
"learning_rate": 0.00010055465687592411,
"loss": 0.9006,
"step": 3050
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.9126,
"step": 3060
},
{
"epoch": 1.02,
"learning_rate": 9.944534312407591e-05,
"loss": 0.8792,
"step": 3070
},
{
"epoch": 1.03,
"learning_rate": 9.889070331198292e-05,
"loss": 0.8911,
"step": 3080
},
{
"epoch": 1.03,
"learning_rate": 9.833609762702714e-05,
"loss": 0.8952,
"step": 3090
},
{
"epoch": 1.03,
"learning_rate": 9.778154313146484e-05,
"loss": 0.9196,
"step": 3100
},
{
"epoch": 1.04,
"learning_rate": 9.722705688597744e-05,
"loss": 0.9232,
"step": 3110
},
{
"epoch": 1.04,
"learning_rate": 9.667265594914662e-05,
"loss": 0.8986,
"step": 3120
},
{
"epoch": 1.04,
"learning_rate": 9.611835737692958e-05,
"loss": 0.8852,
"step": 3130
},
{
"epoch": 1.05,
"learning_rate": 9.556417822213435e-05,
"loss": 0.8771,
"step": 3140
},
{
"epoch": 1.05,
"learning_rate": 9.501013553389516e-05,
"loss": 0.8751,
"step": 3150
},
{
"epoch": 1.05,
"learning_rate": 9.445624635714773e-05,
"loss": 0.949,
"step": 3160
},
{
"epoch": 1.06,
"learning_rate": 9.390252773210524e-05,
"loss": 0.9212,
"step": 3170
},
{
"epoch": 1.06,
"learning_rate": 9.334899669373379e-05,
"loss": 0.9122,
"step": 3180
},
{
"epoch": 1.07,
"learning_rate": 9.279567027122845e-05,
"loss": 0.8839,
"step": 3190
},
{
"epoch": 1.07,
"learning_rate": 9.224256548748942e-05,
"loss": 0.894,
"step": 3200
},
{
"epoch": 1.07,
"learning_rate": 9.16896993585982e-05,
"loss": 0.8844,
"step": 3210
},
{
"epoch": 1.08,
"learning_rate": 9.113708889329413e-05,
"loss": 0.854,
"step": 3220
},
{
"epoch": 1.08,
"learning_rate": 9.058475109245116e-05,
"loss": 0.8669,
"step": 3230
},
{
"epoch": 1.08,
"learning_rate": 9.003270294855491e-05,
"loss": 0.9132,
"step": 3240
},
{
"epoch": 1.09,
"learning_rate": 8.94809614451797e-05,
"loss": 0.9012,
"step": 3250
},
{
"epoch": 1.09,
"learning_rate": 8.892954355646616e-05,
"loss": 0.884,
"step": 3260
},
{
"epoch": 1.09,
"learning_rate": 8.837846624659904e-05,
"loss": 0.8963,
"step": 3270
},
{
"epoch": 1.1,
"learning_rate": 8.78277464692853e-05,
"loss": 0.9208,
"step": 3280
},
{
"epoch": 1.1,
"learning_rate": 8.727740116723257e-05,
"loss": 0.8954,
"step": 3290
},
{
"epoch": 1.1,
"learning_rate": 8.672744727162781e-05,
"loss": 0.8794,
"step": 3300
},
{
"epoch": 1.11,
"learning_rate": 8.617790170161656e-05,
"loss": 0.898,
"step": 3310
},
{
"epoch": 1.11,
"learning_rate": 8.562878136378226e-05,
"loss": 0.9053,
"step": 3320
},
{
"epoch": 1.11,
"learning_rate": 8.508010315162634e-05,
"loss": 0.9039,
"step": 3330
},
{
"epoch": 1.12,
"learning_rate": 8.453188394504834e-05,
"loss": 0.8774,
"step": 3340
},
{
"epoch": 1.12,
"learning_rate": 8.398414060982659e-05,
"loss": 0.9022,
"step": 3350
},
{
"epoch": 1.12,
"learning_rate": 8.343688999709952e-05,
"loss": 0.8809,
"step": 3360
},
{
"epoch": 1.13,
"learning_rate": 8.289014894284702e-05,
"loss": 0.919,
"step": 3370
},
{
"epoch": 1.13,
"learning_rate": 8.234393426737258e-05,
"loss": 0.8623,
"step": 3380
},
{
"epoch": 1.13,
"learning_rate": 8.179826277478589e-05,
"loss": 0.923,
"step": 3390
},
{
"epoch": 1.14,
"learning_rate": 8.12531512524858e-05,
"loss": 0.8968,
"step": 3400
},
{
"epoch": 1.14,
"learning_rate": 8.070861647064383e-05,
"loss": 0.9099,
"step": 3410
},
{
"epoch": 1.14,
"learning_rate": 8.016467518168821e-05,
"loss": 0.9087,
"step": 3420
},
{
"epoch": 1.15,
"learning_rate": 7.962134411978874e-05,
"loss": 0.9047,
"step": 3430
},
{
"epoch": 1.15,
"eval_loss": 1.1462568044662476,
"eval_runtime": 2.5537,
"eval_samples_per_second": 951.181,
"eval_steps_per_second": 119.044,
"step": 3437
},
{
"epoch": 1.15,
"learning_rate": 7.907864000034163e-05,
"loss": 0.8912,
"step": 3440
},
{
"epoch": 1.15,
"learning_rate": 7.853657951945548e-05,
"loss": 0.8925,
"step": 3450
},
{
"epoch": 1.16,
"learning_rate": 7.799517935343757e-05,
"loss": 0.8751,
"step": 3460
},
{
"epoch": 1.16,
"learning_rate": 7.745445615828073e-05,
"loss": 0.9157,
"step": 3470
},
{
"epoch": 1.16,
"learning_rate": 7.69144265691512e-05,
"loss": 0.8971,
"step": 3480
},
{
"epoch": 1.17,
"learning_rate": 7.637510719987653e-05,
"loss": 0.8905,
"step": 3490
},
{
"epoch": 1.17,
"learning_rate": 7.583651464243458e-05,
"loss": 0.8786,
"step": 3500
},
{
"epoch": 1.17,
"learning_rate": 7.529866546644315e-05,
"loss": 0.8687,
"step": 3510
},
{
"epoch": 1.18,
"learning_rate": 7.476157621865009e-05,
"loss": 0.8842,
"step": 3520
},
{
"epoch": 1.18,
"learning_rate": 7.422526342242445e-05,
"loss": 0.9067,
"step": 3530
},
{
"epoch": 1.18,
"learning_rate": 7.368974357724789e-05,
"loss": 0.8755,
"step": 3540
},
{
"epoch": 1.19,
"learning_rate": 7.315503315820722e-05,
"loss": 0.8982,
"step": 3550
},
{
"epoch": 1.19,
"learning_rate": 7.262114861548759e-05,
"loss": 0.8743,
"step": 3560
},
{
"epoch": 1.19,
"learning_rate": 7.208810637386622e-05,
"loss": 0.8612,
"step": 3570
},
{
"epoch": 1.2,
"learning_rate": 7.155592283220738e-05,
"loss": 0.9104,
"step": 3580
},
{
"epoch": 1.2,
"learning_rate": 7.102461436295762e-05,
"loss": 0.8638,
"step": 3590
},
{
"epoch": 1.2,
"learning_rate": 7.049419731164221e-05,
"loss": 0.8811,
"step": 3600
},
{
"epoch": 1.21,
"learning_rate": 6.996468799636224e-05,
"loss": 0.8819,
"step": 3610
},
{
"epoch": 1.21,
"learning_rate": 6.94361027072926e-05,
"loss": 0.9108,
"step": 3620
},
{
"epoch": 1.21,
"learning_rate": 6.890845770618091e-05,
"loss": 0.8328,
"step": 3630
},
{
"epoch": 1.22,
"learning_rate": 6.838176922584705e-05,
"loss": 0.898,
"step": 3640
},
{
"epoch": 1.22,
"learning_rate": 6.785605346968386e-05,
"loss": 0.8752,
"step": 3650
},
{
"epoch": 1.22,
"learning_rate": 6.73313266111587e-05,
"loss": 0.8823,
"step": 3660
},
{
"epoch": 1.23,
"learning_rate": 6.680760479331585e-05,
"loss": 0.8907,
"step": 3670
},
{
"epoch": 1.23,
"learning_rate": 6.62849041282798e-05,
"loss": 0.9016,
"step": 3680
},
{
"epoch": 1.23,
"learning_rate": 6.576324069675963e-05,
"loss": 0.8745,
"step": 3690
},
{
"epoch": 1.24,
"learning_rate": 6.52426305475543e-05,
"loss": 0.8954,
"step": 3700
},
{
"epoch": 1.24,
"learning_rate": 6.472308969705882e-05,
"loss": 0.8873,
"step": 3710
},
{
"epoch": 1.24,
"learning_rate": 6.420463412877176e-05,
"loss": 0.8926,
"step": 3720
},
{
"epoch": 1.25,
"learning_rate": 6.368727979280317e-05,
"loss": 0.8842,
"step": 3730
},
{
"epoch": 1.25,
"learning_rate": 6.317104260538414e-05,
"loss": 0.8959,
"step": 3740
},
{
"epoch": 1.26,
"learning_rate": 6.265593844837709e-05,
"loss": 0.8738,
"step": 3750
},
{
"epoch": 1.26,
"learning_rate": 6.214198316878707e-05,
"loss": 0.8721,
"step": 3760
},
{
"epoch": 1.26,
"learning_rate": 6.162919257827435e-05,
"loss": 0.8922,
"step": 3770
},
{
"epoch": 1.27,
"learning_rate": 6.111758245266794e-05,
"loss": 0.8858,
"step": 3780
},
{
"epoch": 1.27,
"learning_rate": 6.060716853148024e-05,
"loss": 0.8973,
"step": 3790
},
{
"epoch": 1.27,
"learning_rate": 6.009796651742281e-05,
"loss": 0.896,
"step": 3800
},
{
"epoch": 1.28,
"learning_rate": 5.9589992075923265e-05,
"loss": 0.8763,
"step": 3810
},
{
"epoch": 1.28,
"learning_rate": 5.9083260834643486e-05,
"loss": 0.892,
"step": 3820
},
{
"epoch": 1.28,
"learning_rate": 5.8577788382998585e-05,
"loss": 0.8727,
"step": 3830
},
{
"epoch": 1.29,
"learning_rate": 5.8073590271677536e-05,
"loss": 0.8751,
"step": 3840
},
{
"epoch": 1.29,
"learning_rate": 5.757068201216456e-05,
"loss": 0.869,
"step": 3850
},
{
"epoch": 1.29,
"learning_rate": 5.706907907626215e-05,
"loss": 0.8727,
"step": 3860
},
{
"epoch": 1.3,
"learning_rate": 5.656879689561487e-05,
"loss": 0.8937,
"step": 3870
},
{
"epoch": 1.3,
"learning_rate": 5.606985086123473e-05,
"loss": 0.87,
"step": 3880
},
{
"epoch": 1.3,
"learning_rate": 5.5572256323027625e-05,
"loss": 0.8837,
"step": 3890
},
{
"epoch": 1.31,
"learning_rate": 5.507602858932113e-05,
"loss": 0.8804,
"step": 3900
},
{
"epoch": 1.31,
"learning_rate": 5.45811829263936e-05,
"loss": 0.9172,
"step": 3910
},
{
"epoch": 1.31,
"learning_rate": 5.40877345580044e-05,
"loss": 0.8849,
"step": 3920
},
{
"epoch": 1.32,
"eval_loss": 1.1395624876022339,
"eval_runtime": 2.5544,
"eval_samples_per_second": 950.915,
"eval_steps_per_second": 119.011,
"step": 3928
},
{
"epoch": 1.32,
"learning_rate": 5.3595698664925573e-05,
"loss": 0.8883,
"step": 3930
},
{
"epoch": 1.32,
"learning_rate": 5.310509038447492e-05,
"loss": 0.8841,
"step": 3940
},
{
"epoch": 1.32,
"learning_rate": 5.261592481005011e-05,
"loss": 0.8565,
"step": 3950
},
{
"epoch": 1.33,
"learning_rate": 5.212821699066459e-05,
"loss": 0.8722,
"step": 3960
},
{
"epoch": 1.33,
"learning_rate": 5.1641981930484374e-05,
"loss": 0.9014,
"step": 3970
},
{
"epoch": 1.33,
"learning_rate": 5.115723458836652e-05,
"loss": 0.8695,
"step": 3980
},
{
"epoch": 1.34,
"learning_rate": 5.067398987739901e-05,
"loss": 0.8876,
"step": 3990
},
{
"epoch": 1.34,
"learning_rate": 5.01922626644418e-05,
"loss": 0.8721,
"step": 4000
},
{
"epoch": 1.34,
"learning_rate": 4.9712067769669665e-05,
"loss": 0.867,
"step": 4010
},
{
"epoch": 1.35,
"learning_rate": 4.9233419966116036e-05,
"loss": 0.8673,
"step": 4020
},
{
"epoch": 1.35,
"learning_rate": 4.875633397921855e-05,
"loss": 0.8854,
"step": 4030
},
{
"epoch": 1.35,
"learning_rate": 4.828082448636626e-05,
"loss": 0.8818,
"step": 4040
},
{
"epoch": 1.36,
"learning_rate": 4.780690611644776e-05,
"loss": 0.8916,
"step": 4050
},
{
"epoch": 1.36,
"learning_rate": 4.73345934494013e-05,
"loss": 0.8962,
"step": 4060
},
{
"epoch": 1.36,
"learning_rate": 4.686390101576633e-05,
"loss": 0.9049,
"step": 4070
},
{
"epoch": 1.37,
"learning_rate": 4.639484329623627e-05,
"loss": 0.868,
"step": 4080
},
{
"epoch": 1.37,
"learning_rate": 4.592743472121309e-05,
"loss": 0.8673,
"step": 4090
},
{
"epoch": 1.37,
"learning_rate": 4.546168967036351e-05,
"loss": 0.8602,
"step": 4100
},
{
"epoch": 1.38,
"learning_rate": 4.499762247217639e-05,
"loss": 0.8695,
"step": 4110
},
{
"epoch": 1.38,
"learning_rate": 4.453524740352206e-05,
"loss": 0.8698,
"step": 4120
},
{
"epoch": 1.38,
"learning_rate": 4.407457868921303e-05,
"loss": 0.9047,
"step": 4130
},
{
"epoch": 1.39,
"learning_rate": 4.3615630501566384e-05,
"loss": 0.8802,
"step": 4140
},
{
"epoch": 1.39,
"learning_rate": 4.3158416959967884e-05,
"loss": 0.8553,
"step": 4150
},
{
"epoch": 1.39,
"learning_rate": 4.27029521304374e-05,
"loss": 0.8767,
"step": 4160
},
{
"epoch": 1.4,
"learning_rate": 4.2249250025196274e-05,
"loss": 0.8774,
"step": 4170
},
{
"epoch": 1.4,
"learning_rate": 4.179732460223626e-05,
"loss": 0.885,
"step": 4180
},
{
"epoch": 1.4,
"learning_rate": 4.1347189764890016e-05,
"loss": 0.8937,
"step": 4190
},
{
"epoch": 1.41,
"learning_rate": 4.08988593614036e-05,
"loss": 0.9031,
"step": 4200
},
{
"epoch": 1.41,
"learning_rate": 4.045234718451011e-05,
"loss": 0.8615,
"step": 4210
},
{
"epoch": 1.41,
"learning_rate": 4.000766697100558e-05,
"loss": 0.8887,
"step": 4220
},
{
"epoch": 1.42,
"learning_rate": 3.95648324013263e-05,
"loss": 0.892,
"step": 4230
},
{
"epoch": 1.42,
"learning_rate": 3.9123857099127936e-05,
"loss": 0.8536,
"step": 4240
},
{
"epoch": 1.42,
"learning_rate": 3.868475463086651e-05,
"loss": 0.8937,
"step": 4250
},
{
"epoch": 1.43,
"learning_rate": 3.824753850538082e-05,
"loss": 0.8575,
"step": 4260
},
{
"epoch": 1.43,
"learning_rate": 3.781222217347704e-05,
"loss": 0.8774,
"step": 4270
},
{
"epoch": 1.43,
"learning_rate": 3.737881902751479e-05,
"loss": 0.8906,
"step": 4280
},
{
"epoch": 1.44,
"learning_rate": 3.694734240099524e-05,
"loss": 0.8901,
"step": 4290
},
{
"epoch": 1.44,
"learning_rate": 3.651780556815079e-05,
"loss": 0.8603,
"step": 4300
},
{
"epoch": 1.45,
"learning_rate": 3.609022174353674e-05,
"loss": 0.8865,
"step": 4310
},
{
"epoch": 1.45,
"learning_rate": 3.5664604081624786e-05,
"loss": 0.864,
"step": 4320
},
{
"epoch": 1.45,
"learning_rate": 3.5240965676398215e-05,
"loss": 0.8863,
"step": 4330
},
{
"epoch": 1.46,
"learning_rate": 3.48193195609493e-05,
"loss": 0.8841,
"step": 4340
},
{
"epoch": 1.46,
"learning_rate": 3.439967870707807e-05,
"loss": 0.8755,
"step": 4350
},
{
"epoch": 1.46,
"learning_rate": 3.398205602489337e-05,
"loss": 0.8844,
"step": 4360
},
{
"epoch": 1.47,
"learning_rate": 3.356646436241573e-05,
"loss": 0.9026,
"step": 4370
},
{
"epoch": 1.47,
"learning_rate": 3.315291650518197e-05,
"loss": 0.877,
"step": 4380
},
{
"epoch": 1.47,
"learning_rate": 3.2741425175852056e-05,
"loss": 0.8969,
"step": 4390
},
{
"epoch": 1.48,
"learning_rate": 3.233200303381746e-05,
"loss": 0.8719,
"step": 4400
},
{
"epoch": 1.48,
"learning_rate": 3.1924662674811836e-05,
"loss": 0.8522,
"step": 4410
},
{
"epoch": 1.48,
"eval_loss": 1.1344659328460693,
"eval_runtime": 2.6026,
"eval_samples_per_second": 933.308,
"eval_steps_per_second": 116.808,
"step": 4419
},
{
"epoch": 1.48,
"learning_rate": 3.1519416630523444e-05,
"loss": 0.8861,
"step": 4420
},
{
"epoch": 1.49,
"learning_rate": 3.111627736820979e-05,
"loss": 0.8813,
"step": 4430
},
{
"epoch": 1.49,
"learning_rate": 3.071525729031384e-05,
"loss": 0.8727,
"step": 4440
},
{
"epoch": 1.49,
"learning_rate": 3.0316368734082533e-05,
"loss": 0.8966,
"step": 4450
},
{
"epoch": 1.5,
"learning_rate": 2.9919623971187415e-05,
"loss": 0.8636,
"step": 4460
},
{
"epoch": 1.5,
"learning_rate": 2.952503520734682e-05,
"loss": 0.8779,
"step": 4470
},
{
"epoch": 1.5,
"learning_rate": 2.913261458195051e-05,
"loss": 0.8666,
"step": 4480
},
{
"epoch": 1.51,
"learning_rate": 2.8742374167686313e-05,
"loss": 0.8625,
"step": 4490
},
{
"epoch": 1.51,
"learning_rate": 2.8354325970168484e-05,
"loss": 0.8835,
"step": 4500
},
{
"epoch": 1.51,
"learning_rate": 2.7968481927568514e-05,
"loss": 0.8778,
"step": 4510
},
{
"epoch": 1.52,
"learning_rate": 2.7584853910247767e-05,
"loss": 0.8682,
"step": 4520
},
{
"epoch": 1.52,
"learning_rate": 2.7203453720392458e-05,
"loss": 0.858,
"step": 4530
},
{
"epoch": 1.52,
"learning_rate": 2.682429309165033e-05,
"loss": 0.8964,
"step": 4540
},
{
"epoch": 1.53,
"learning_rate": 2.6447383688769846e-05,
"loss": 0.8856,
"step": 4550
},
{
"epoch": 1.53,
"learning_rate": 2.6072737107241208e-05,
"loss": 0.8832,
"step": 4560
},
{
"epoch": 1.53,
"learning_rate": 2.5700364872939718e-05,
"loss": 0.8549,
"step": 4570
},
{
"epoch": 1.54,
"learning_rate": 2.5330278441771226e-05,
"loss": 0.836,
"step": 4580
},
{
"epoch": 1.54,
"learning_rate": 2.4962489199319504e-05,
"loss": 0.8541,
"step": 4590
},
{
"epoch": 1.54,
"learning_rate": 2.4597008460496164e-05,
"loss": 0.8889,
"step": 4600
},
{
"epoch": 1.55,
"learning_rate": 2.4233847469192438e-05,
"loss": 0.8512,
"step": 4610
},
{
"epoch": 1.55,
"learning_rate": 2.3873017397933327e-05,
"loss": 0.8525,
"step": 4620
},
{
"epoch": 1.55,
"learning_rate": 2.351452934753394e-05,
"loss": 0.8887,
"step": 4630
},
{
"epoch": 1.56,
"learning_rate": 2.3158394346757784e-05,
"loss": 0.8911,
"step": 4640
},
{
"epoch": 1.56,
"learning_rate": 2.280462335197767e-05,
"loss": 0.905,
"step": 4650
},
{
"epoch": 1.56,
"learning_rate": 2.2453227246838538e-05,
"loss": 0.8785,
"step": 4660
},
{
"epoch": 1.57,
"learning_rate": 2.2104216841922633e-05,
"loss": 0.8762,
"step": 4670
},
{
"epoch": 1.57,
"learning_rate": 2.1757602874416993e-05,
"loss": 0.8723,
"step": 4680
},
{
"epoch": 1.57,
"learning_rate": 2.141339600778305e-05,
"loss": 0.8541,
"step": 4690
},
{
"epoch": 1.58,
"learning_rate": 2.1071606831428557e-05,
"loss": 0.8762,
"step": 4700
},
{
"epoch": 1.58,
"learning_rate": 2.0732245860381872e-05,
"loss": 0.8654,
"step": 4710
},
{
"epoch": 1.58,
"learning_rate": 2.0395323534968412e-05,
"loss": 0.8362,
"step": 4720
},
{
"epoch": 1.59,
"learning_rate": 2.0060850220489567e-05,
"loss": 0.8711,
"step": 4730
},
{
"epoch": 1.59,
"learning_rate": 1.9728836206903656e-05,
"loss": 0.8564,
"step": 4740
},
{
"epoch": 1.59,
"learning_rate": 1.9399291708509438e-05,
"loss": 0.8733,
"step": 4750
},
{
"epoch": 1.6,
"learning_rate": 1.907222686363188e-05,
"loss": 0.8519,
"step": 4760
},
{
"epoch": 1.6,
"learning_rate": 1.8747651734310314e-05,
"loss": 0.8923,
"step": 4770
},
{
"epoch": 1.6,
"learning_rate": 1.8425576305988734e-05,
"loss": 0.8662,
"step": 4780
},
{
"epoch": 1.61,
"learning_rate": 1.8106010487208713e-05,
"loss": 0.856,
"step": 4790
},
{
"epoch": 1.61,
"learning_rate": 1.7788964109304496e-05,
"loss": 0.8734,
"step": 4800
},
{
"epoch": 1.61,
"learning_rate": 1.7474446926100673e-05,
"loss": 0.8542,
"step": 4810
},
{
"epoch": 1.62,
"learning_rate": 1.7162468613611937e-05,
"loss": 0.8638,
"step": 4820
},
{
"epoch": 1.62,
"learning_rate": 1.6853038769745467e-05,
"loss": 0.8949,
"step": 4830
},
{
"epoch": 1.63,
"learning_rate": 1.6546166914005767e-05,
"loss": 0.861,
"step": 4840
},
{
"epoch": 1.63,
"learning_rate": 1.62418624872016e-05,
"loss": 0.8437,
"step": 4850
},
{
"epoch": 1.63,
"learning_rate": 1.5940134851155697e-05,
"loss": 0.8584,
"step": 4860
},
{
"epoch": 1.64,
"learning_rate": 1.564099328841665e-05,
"loss": 0.8736,
"step": 4870
},
{
"epoch": 1.64,
"learning_rate": 1.534444700197346e-05,
"loss": 0.8591,
"step": 4880
},
{
"epoch": 1.64,
"learning_rate": 1.505050511497227e-05,
"loss": 0.8684,
"step": 4890
},
{
"epoch": 1.65,
"learning_rate": 1.4759176670435748e-05,
"loss": 0.9093,
"step": 4900
},
{
"epoch": 1.65,
"learning_rate": 1.4470470630984911e-05,
"loss": 0.871,
"step": 4910
},
{
"epoch": 1.65,
"eval_loss": 1.1315988302230835,
"eval_runtime": 2.6531,
"eval_samples_per_second": 915.533,
"eval_steps_per_second": 114.583,
"step": 4910
},
{
"epoch": 1.65,
"learning_rate": 1.4184395878563395e-05,
"loss": 0.8653,
"step": 4920
},
{
"epoch": 1.66,
"learning_rate": 1.3900961214164144e-05,
"loss": 0.8912,
"step": 4930
},
{
"epoch": 1.66,
"learning_rate": 1.3620175357558706e-05,
"loss": 0.8725,
"step": 4940
},
{
"epoch": 1.66,
"learning_rate": 1.3342046947028896e-05,
"loss": 0.9122,
"step": 4950
},
{
"epoch": 1.67,
"learning_rate": 1.3066584539101223e-05,
"loss": 0.8874,
"step": 4960
},
{
"epoch": 1.67,
"learning_rate": 1.2793796608283426e-05,
"loss": 0.8628,
"step": 4970
},
{
"epoch": 1.67,
"learning_rate": 1.2523691546803873e-05,
"loss": 0.8751,
"step": 4980
},
{
"epoch": 1.68,
"learning_rate": 1.2256277664353411e-05,
"loss": 0.8485,
"step": 4990
},
{
"epoch": 1.68,
"learning_rate": 1.1991563187829591e-05,
"loss": 0.8741,
"step": 5000
},
{
"epoch": 1.68,
"learning_rate": 1.1729556261083784e-05,
"loss": 0.8194,
"step": 5010
},
{
"epoch": 1.69,
"learning_rate": 1.1470264944670383e-05,
"loss": 0.8649,
"step": 5020
},
{
"epoch": 1.69,
"learning_rate": 1.1213697215599017e-05,
"loss": 0.887,
"step": 5030
},
{
"epoch": 1.69,
"learning_rate": 1.0959860967089041e-05,
"loss": 0.8359,
"step": 5040
},
{
"epoch": 1.7,
"learning_rate": 1.0708764008326733e-05,
"loss": 0.8837,
"step": 5050
},
{
"epoch": 1.7,
"learning_rate": 1.04604140642251e-05,
"loss": 0.8914,
"step": 5060
},
{
"epoch": 1.7,
"learning_rate": 1.0214818775186108e-05,
"loss": 0.9028,
"step": 5070
},
{
"epoch": 1.71,
"learning_rate": 9.971985696865738e-06,
"loss": 0.8887,
"step": 5080
},
{
"epoch": 1.71,
"learning_rate": 9.731922299941454e-06,
"loss": 0.8613,
"step": 5090
},
{
"epoch": 1.71,
"learning_rate": 9.494635969882426e-06,
"loss": 0.8656,
"step": 5100
},
{
"epoch": 1.72,
"learning_rate": 9.260134006722332e-06,
"loss": 0.879,
"step": 5110
},
{
"epoch": 1.72,
"learning_rate": 9.028423624834704e-06,
"loss": 0.862,
"step": 5120
},
{
"epoch": 1.72,
"learning_rate": 8.799511952711025e-06,
"loss": 0.8987,
"step": 5130
},
{
"epoch": 1.73,
"learning_rate": 8.573406032741438e-06,
"loss": 0.8483,
"step": 5140
},
{
"epoch": 1.73,
"learning_rate": 8.350112820998035e-06,
"loss": 0.8875,
"step": 5150
},
{
"epoch": 1.73,
"learning_rate": 8.129639187020954e-06,
"loss": 0.8512,
"step": 5160
},
{
"epoch": 1.74,
"learning_rate": 7.911991913606932e-06,
"loss": 0.8735,
"step": 5170
},
{
"epoch": 1.74,
"learning_rate": 7.697177696600677e-06,
"loss": 0.8544,
"step": 5180
},
{
"epoch": 1.74,
"learning_rate": 7.4852031446888685e-06,
"loss": 0.8834,
"step": 5190
},
{
"epoch": 1.75,
"learning_rate": 7.276074779196906e-06,
"loss": 0.8757,
"step": 5200
},
{
"epoch": 1.75,
"learning_rate": 7.06979903388818e-06,
"loss": 0.8711,
"step": 5210
},
{
"epoch": 1.75,
"learning_rate": 6.866382254766157e-06,
"loss": 0.869,
"step": 5220
},
{
"epoch": 1.76,
"learning_rate": 6.665830699879261e-06,
"loss": 0.8468,
"step": 5230
},
{
"epoch": 1.76,
"learning_rate": 6.468150539128193e-06,
"loss": 0.8703,
"step": 5240
},
{
"epoch": 1.76,
"learning_rate": 6.273347854076195e-06,
"loss": 0.8728,
"step": 5250
},
{
"epoch": 1.77,
"learning_rate": 6.081428637761977e-06,
"loss": 0.8635,
"step": 5260
},
{
"epoch": 1.77,
"learning_rate": 5.892398794515286e-06,
"loss": 0.8632,
"step": 5270
},
{
"epoch": 1.77,
"learning_rate": 5.706264139775286e-06,
"loss": 0.8723,
"step": 5280
},
{
"epoch": 1.78,
"learning_rate": 5.523030399911611e-06,
"loss": 0.8804,
"step": 5290
},
{
"epoch": 1.78,
"learning_rate": 5.342703212048305e-06,
"loss": 0.855,
"step": 5300
},
{
"epoch": 1.78,
"learning_rate": 5.165288123890277e-06,
"loss": 0.8741,
"step": 5310
}
],
"logging_steps": 10,
"max_steps": 5892,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 590,
"total_flos": 1.865860038912901e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}