gemma7b-gpt4o_100k_summarize-k / trainer_state.json
chansung's picture
Model save
fa9e110 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9996810207336523,
"eval_steps": 500,
"global_step": 1567,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006379585326953748,
"grad_norm": 210.7223358154297,
"learning_rate": 1.910828025477707e-06,
"loss": 45.3725,
"step": 1
},
{
"epoch": 0.003189792663476874,
"grad_norm": 226.75299072265625,
"learning_rate": 9.554140127388534e-06,
"loss": 48.3317,
"step": 5
},
{
"epoch": 0.006379585326953748,
"grad_norm": 153.64804077148438,
"learning_rate": 1.9108280254777068e-05,
"loss": 46.1831,
"step": 10
},
{
"epoch": 0.009569377990430622,
"grad_norm": 100.49105072021484,
"learning_rate": 2.8662420382165606e-05,
"loss": 35.4306,
"step": 15
},
{
"epoch": 0.012759170653907496,
"grad_norm": 76.70584106445312,
"learning_rate": 3.8216560509554137e-05,
"loss": 29.7582,
"step": 20
},
{
"epoch": 0.01594896331738437,
"grad_norm": 18.13677215576172,
"learning_rate": 4.777070063694267e-05,
"loss": 24.9798,
"step": 25
},
{
"epoch": 0.019138755980861243,
"grad_norm": 14.398043632507324,
"learning_rate": 5.732484076433121e-05,
"loss": 22.6081,
"step": 30
},
{
"epoch": 0.022328548644338118,
"grad_norm": 10.421934127807617,
"learning_rate": 6.687898089171974e-05,
"loss": 20.6468,
"step": 35
},
{
"epoch": 0.025518341307814992,
"grad_norm": 6.249530792236328,
"learning_rate": 7.643312101910827e-05,
"loss": 20.6855,
"step": 40
},
{
"epoch": 0.028708133971291867,
"grad_norm": 4.4145917892456055,
"learning_rate": 8.59872611464968e-05,
"loss": 18.4075,
"step": 45
},
{
"epoch": 0.03189792663476874,
"grad_norm": 4.664849281311035,
"learning_rate": 9.554140127388533e-05,
"loss": 18.931,
"step": 50
},
{
"epoch": 0.03508771929824561,
"grad_norm": 5.491772174835205,
"learning_rate": 0.00010509554140127387,
"loss": 18.2993,
"step": 55
},
{
"epoch": 0.03827751196172249,
"grad_norm": 11.026978492736816,
"learning_rate": 0.00011464968152866242,
"loss": 17.9978,
"step": 60
},
{
"epoch": 0.04146730462519936,
"grad_norm": 16.8328914642334,
"learning_rate": 0.00012420382165605095,
"loss": 16.1541,
"step": 65
},
{
"epoch": 0.044657097288676235,
"grad_norm": 24.968544006347656,
"learning_rate": 0.00013375796178343948,
"loss": 13.5497,
"step": 70
},
{
"epoch": 0.04784688995215311,
"grad_norm": 34.1843147277832,
"learning_rate": 0.00014331210191082802,
"loss": 10.0932,
"step": 75
},
{
"epoch": 0.051036682615629984,
"grad_norm": 26.95475196838379,
"learning_rate": 0.00015286624203821655,
"loss": 6.0162,
"step": 80
},
{
"epoch": 0.05422647527910686,
"grad_norm": 89.71574401855469,
"learning_rate": 0.00016242038216560508,
"loss": 3.1634,
"step": 85
},
{
"epoch": 0.05741626794258373,
"grad_norm": 10.840144157409668,
"learning_rate": 0.0001719745222929936,
"loss": 2.7482,
"step": 90
},
{
"epoch": 0.06060606060606061,
"grad_norm": 5.291273593902588,
"learning_rate": 0.00018152866242038214,
"loss": 2.3438,
"step": 95
},
{
"epoch": 0.06379585326953748,
"grad_norm": 2.17537260055542,
"learning_rate": 0.00019108280254777067,
"loss": 2.0583,
"step": 100
},
{
"epoch": 0.06698564593301436,
"grad_norm": 1.8088818788528442,
"learning_rate": 0.0002006369426751592,
"loss": 1.9395,
"step": 105
},
{
"epoch": 0.07017543859649122,
"grad_norm": 1.0773868560791016,
"learning_rate": 0.00021019108280254773,
"loss": 1.8029,
"step": 110
},
{
"epoch": 0.0733652312599681,
"grad_norm": 2.8027162551879883,
"learning_rate": 0.00021974522292993626,
"loss": 1.734,
"step": 115
},
{
"epoch": 0.07655502392344497,
"grad_norm": 1.8964555263519287,
"learning_rate": 0.00022929936305732485,
"loss": 1.6716,
"step": 120
},
{
"epoch": 0.07974481658692185,
"grad_norm": 1.0901538133621216,
"learning_rate": 0.00023885350318471338,
"loss": 1.6162,
"step": 125
},
{
"epoch": 0.08293460925039872,
"grad_norm": 1.5070509910583496,
"learning_rate": 0.0002484076433121019,
"loss": 1.6087,
"step": 130
},
{
"epoch": 0.0861244019138756,
"grad_norm": 1.8919157981872559,
"learning_rate": 0.00025796178343949044,
"loss": 1.5317,
"step": 135
},
{
"epoch": 0.08931419457735247,
"grad_norm": 1.317736268043518,
"learning_rate": 0.00026751592356687897,
"loss": 1.4964,
"step": 140
},
{
"epoch": 0.09250398724082935,
"grad_norm": 2.569183111190796,
"learning_rate": 0.0002770700636942675,
"loss": 1.5564,
"step": 145
},
{
"epoch": 0.09569377990430622,
"grad_norm": 2.390894651412964,
"learning_rate": 0.00028662420382165603,
"loss": 1.4957,
"step": 150
},
{
"epoch": 0.09888357256778309,
"grad_norm": 0.9399936199188232,
"learning_rate": 0.00029617834394904456,
"loss": 1.484,
"step": 155
},
{
"epoch": 0.10207336523125997,
"grad_norm": 2.9535129070281982,
"learning_rate": 0.0002999966490829603,
"loss": 1.4503,
"step": 160
},
{
"epoch": 0.10526315789473684,
"grad_norm": 1.0490965843200684,
"learning_rate": 0.00029997617179878324,
"loss": 1.4321,
"step": 165
},
{
"epoch": 0.10845295055821372,
"grad_norm": 4.929164409637451,
"learning_rate": 0.0002999370813893047,
"loss": 1.4327,
"step": 170
},
{
"epoch": 0.11164274322169059,
"grad_norm": 1.0862678289413452,
"learning_rate": 0.00029987938270592676,
"loss": 1.4237,
"step": 175
},
{
"epoch": 0.11483253588516747,
"grad_norm": 2.1204566955566406,
"learning_rate": 0.0002998030829094724,
"loss": 1.418,
"step": 180
},
{
"epoch": 0.11802232854864433,
"grad_norm": 2.93302583694458,
"learning_rate": 0.00029970819146929694,
"loss": 1.4072,
"step": 185
},
{
"epoch": 0.12121212121212122,
"grad_norm": 2.221076011657715,
"learning_rate": 0.0002995947201621131,
"loss": 1.4132,
"step": 190
},
{
"epoch": 0.12440191387559808,
"grad_norm": 1.8285828828811646,
"learning_rate": 0.00029946268307052886,
"loss": 1.4,
"step": 195
},
{
"epoch": 0.12759170653907495,
"grad_norm": 1.0585997104644775,
"learning_rate": 0.0002993120965813003,
"loss": 1.374,
"step": 200
},
{
"epoch": 0.13078149920255183,
"grad_norm": 2.2776687145233154,
"learning_rate": 0.0002991429793832975,
"loss": 1.3503,
"step": 205
},
{
"epoch": 0.1339712918660287,
"grad_norm": 2.238420009613037,
"learning_rate": 0.00029895535246518524,
"loss": 1.3755,
"step": 210
},
{
"epoch": 0.1371610845295056,
"grad_norm": 0.9944085478782654,
"learning_rate": 0.0002987492391128182,
"loss": 1.3629,
"step": 215
},
{
"epoch": 0.14035087719298245,
"grad_norm": 1.7009069919586182,
"learning_rate": 0.0002985246649063509,
"loss": 1.3613,
"step": 220
},
{
"epoch": 0.14354066985645933,
"grad_norm": 1.9367361068725586,
"learning_rate": 0.0002982816577170631,
"loss": 1.3585,
"step": 225
},
{
"epoch": 0.1467304625199362,
"grad_norm": 0.831079363822937,
"learning_rate": 0.00029802024770390087,
"loss": 1.3393,
"step": 230
},
{
"epoch": 0.14992025518341306,
"grad_norm": 1.10426664352417,
"learning_rate": 0.00029774046730973334,
"loss": 1.3418,
"step": 235
},
{
"epoch": 0.15311004784688995,
"grad_norm": 1.438004493713379,
"learning_rate": 0.00029744235125732664,
"loss": 1.3439,
"step": 240
},
{
"epoch": 0.15629984051036683,
"grad_norm": 4.208047866821289,
"learning_rate": 0.0002971259365450344,
"loss": 1.3377,
"step": 245
},
{
"epoch": 0.1594896331738437,
"grad_norm": 2.597606897354126,
"learning_rate": 0.00029679126244220596,
"loss": 1.2973,
"step": 250
},
{
"epoch": 0.16267942583732056,
"grad_norm": 3.7126145362854004,
"learning_rate": 0.00029643837048431293,
"loss": 1.336,
"step": 255
},
{
"epoch": 0.16586921850079744,
"grad_norm": 2.6157450675964355,
"learning_rate": 0.0002960673044677939,
"loss": 1.3273,
"step": 260
},
{
"epoch": 0.16905901116427433,
"grad_norm": 1.1743855476379395,
"learning_rate": 0.00029567811044461977,
"loss": 1.2961,
"step": 265
},
{
"epoch": 0.1722488038277512,
"grad_norm": 2.6032323837280273,
"learning_rate": 0.00029527083671657746,
"loss": 1.308,
"step": 270
},
{
"epoch": 0.17543859649122806,
"grad_norm": 1.2666016817092896,
"learning_rate": 0.00029484553382927594,
"loss": 1.2867,
"step": 275
},
{
"epoch": 0.17862838915470494,
"grad_norm": 2.308387279510498,
"learning_rate": 0.000294402254565873,
"loss": 1.3159,
"step": 280
},
{
"epoch": 0.18181818181818182,
"grad_norm": 2.5119080543518066,
"learning_rate": 0.00029394105394052434,
"loss": 1.3205,
"step": 285
},
{
"epoch": 0.1850079744816587,
"grad_norm": 2.0319368839263916,
"learning_rate": 0.00029346198919155616,
"loss": 1.3144,
"step": 290
},
{
"epoch": 0.18819776714513556,
"grad_norm": 1.0513851642608643,
"learning_rate": 0.00029296511977436107,
"loss": 1.2852,
"step": 295
},
{
"epoch": 0.19138755980861244,
"grad_norm": 1.9946495294570923,
"learning_rate": 0.0002924505073540198,
"loss": 1.2848,
"step": 300
},
{
"epoch": 0.19457735247208932,
"grad_norm": 0.9887159466743469,
"learning_rate": 0.0002919182157976476,
"loss": 1.2786,
"step": 305
},
{
"epoch": 0.19776714513556617,
"grad_norm": 2.8245911598205566,
"learning_rate": 0.00029136831116646815,
"loss": 1.2801,
"step": 310
},
{
"epoch": 0.20095693779904306,
"grad_norm": 1.0787121057510376,
"learning_rate": 0.000290800861707615,
"loss": 1.2676,
"step": 315
},
{
"epoch": 0.20414673046251994,
"grad_norm": 1.7965648174285889,
"learning_rate": 0.00029021593784566113,
"loss": 1.2793,
"step": 320
},
{
"epoch": 0.20733652312599682,
"grad_norm": 3.4487974643707275,
"learning_rate": 0.0002896136121738793,
"loss": 1.2753,
"step": 325
},
{
"epoch": 0.21052631578947367,
"grad_norm": 2.19303035736084,
"learning_rate": 0.0002889939594452323,
"loss": 1.2631,
"step": 330
},
{
"epoch": 0.21371610845295055,
"grad_norm": 1.1072807312011719,
"learning_rate": 0.00028835705656309583,
"loss": 1.2789,
"step": 335
},
{
"epoch": 0.21690590111642744,
"grad_norm": 3.124202251434326,
"learning_rate": 0.0002877029825717142,
"loss": 1.3006,
"step": 340
},
{
"epoch": 0.22009569377990432,
"grad_norm": 1.0346769094467163,
"learning_rate": 0.0002870318186463901,
"loss": 1.2368,
"step": 345
},
{
"epoch": 0.22328548644338117,
"grad_norm": 5.13249397277832,
"learning_rate": 0.0002863436480834105,
"loss": 1.2836,
"step": 350
},
{
"epoch": 0.22647527910685805,
"grad_norm": 0.9209335446357727,
"learning_rate": 0.00028563855628970886,
"loss": 1.259,
"step": 355
},
{
"epoch": 0.22966507177033493,
"grad_norm": 1.4709413051605225,
"learning_rate": 0.0002849166307722653,
"loss": 1.2966,
"step": 360
},
{
"epoch": 0.23285486443381181,
"grad_norm": 0.9667356610298157,
"learning_rate": 0.00028417796112724684,
"loss": 1.2771,
"step": 365
},
{
"epoch": 0.23604465709728867,
"grad_norm": 0.8139356374740601,
"learning_rate": 0.0002834226390288873,
"loss": 1.2409,
"step": 370
},
{
"epoch": 0.23923444976076555,
"grad_norm": 1.1209094524383545,
"learning_rate": 0.0002826507582181103,
"loss": 1.2499,
"step": 375
},
{
"epoch": 0.24242424242424243,
"grad_norm": 1.3784332275390625,
"learning_rate": 0.00028186241449089524,
"loss": 1.2648,
"step": 380
},
{
"epoch": 0.24561403508771928,
"grad_norm": 4.830300807952881,
"learning_rate": 0.000281057705686388,
"loss": 1.2524,
"step": 385
},
{
"epoch": 0.24880382775119617,
"grad_norm": 1.3136839866638184,
"learning_rate": 0.0002802367316747589,
"loss": 1.2545,
"step": 390
},
{
"epoch": 0.25199362041467305,
"grad_norm": 0.94329434633255,
"learning_rate": 0.0002793995943448078,
"loss": 1.2159,
"step": 395
},
{
"epoch": 0.2551834130781499,
"grad_norm": 1.6266140937805176,
"learning_rate": 0.00027854639759131893,
"loss": 1.2211,
"step": 400
},
{
"epoch": 0.2583732057416268,
"grad_norm": 1.1264214515686035,
"learning_rate": 0.00027767724730216696,
"loss": 1.252,
"step": 405
},
{
"epoch": 0.26156299840510366,
"grad_norm": 1.0141706466674805,
"learning_rate": 0.0002767922513451754,
"loss": 1.2613,
"step": 410
},
{
"epoch": 0.2647527910685805,
"grad_norm": 1.6436514854431152,
"learning_rate": 0.00027589151955472965,
"loss": 1.2489,
"step": 415
},
{
"epoch": 0.2679425837320574,
"grad_norm": 1.739797592163086,
"learning_rate": 0.00027497516371814543,
"loss": 1.2377,
"step": 420
},
{
"epoch": 0.2711323763955343,
"grad_norm": 1.399665117263794,
"learning_rate": 0.00027404329756179537,
"loss": 1.2445,
"step": 425
},
{
"epoch": 0.2743221690590112,
"grad_norm": 2.8554205894470215,
"learning_rate": 0.0002730960367369949,
"loss": 1.2909,
"step": 430
},
{
"epoch": 0.27751196172248804,
"grad_norm": 3.405055046081543,
"learning_rate": 0.00027213349880564873,
"loss": 1.2489,
"step": 435
},
{
"epoch": 0.2807017543859649,
"grad_norm": 0.9365301728248596,
"learning_rate": 0.0002711558032256607,
"loss": 1.236,
"step": 440
},
{
"epoch": 0.2838915470494418,
"grad_norm": 2.3004956245422363,
"learning_rate": 0.0002701630713361085,
"loss": 1.2398,
"step": 445
},
{
"epoch": 0.28708133971291866,
"grad_norm": 1.1962858438491821,
"learning_rate": 0.00026915542634218403,
"loss": 1.2487,
"step": 450
},
{
"epoch": 0.2902711323763955,
"grad_norm": 1.5624754428863525,
"learning_rate": 0.00026813299329990335,
"loss": 1.2467,
"step": 455
},
{
"epoch": 0.2934609250398724,
"grad_norm": 1.7164920568466187,
"learning_rate": 0.0002670958991005859,
"loss": 1.2415,
"step": 460
},
{
"epoch": 0.2966507177033493,
"grad_norm": 1.4587774276733398,
"learning_rate": 0.0002660442724551065,
"loss": 1.221,
"step": 465
},
{
"epoch": 0.29984051036682613,
"grad_norm": 3.389615774154663,
"learning_rate": 0.00026497824387792146,
"loss": 1.2282,
"step": 470
},
{
"epoch": 0.30303030303030304,
"grad_norm": 1.0039730072021484,
"learning_rate": 0.00026389794567087085,
"loss": 1.2331,
"step": 475
},
{
"epoch": 0.3062200956937799,
"grad_norm": 1.3434313535690308,
"learning_rate": 0.0002628035119067586,
"loss": 1.212,
"step": 480
},
{
"epoch": 0.3094098883572568,
"grad_norm": 1.2468559741973877,
"learning_rate": 0.0002616950784127135,
"loss": 1.1965,
"step": 485
},
{
"epoch": 0.31259968102073366,
"grad_norm": 1.0449252128601074,
"learning_rate": 0.00026057278275333165,
"loss": 1.2279,
"step": 490
},
{
"epoch": 0.3157894736842105,
"grad_norm": 6.562210559844971,
"learning_rate": 0.00025943676421360395,
"loss": 1.2084,
"step": 495
},
{
"epoch": 0.3189792663476874,
"grad_norm": 2.9650490283966064,
"learning_rate": 0.00025828716378163,
"loss": 1.2578,
"step": 500
},
{
"epoch": 0.32216905901116427,
"grad_norm": 2.523132801055908,
"learning_rate": 0.00025712412413112006,
"loss": 1.2443,
"step": 505
},
{
"epoch": 0.3253588516746411,
"grad_norm": 1.9372252225875854,
"learning_rate": 0.00025594778960368844,
"loss": 1.2412,
"step": 510
},
{
"epoch": 0.32854864433811803,
"grad_norm": 2.129570722579956,
"learning_rate": 0.0002547583061909396,
"loss": 1.2089,
"step": 515
},
{
"epoch": 0.3317384370015949,
"grad_norm": 1.6949142217636108,
"learning_rate": 0.00025355582151634956,
"loss": 1.2235,
"step": 520
},
{
"epoch": 0.3349282296650718,
"grad_norm": 3.6476926803588867,
"learning_rate": 0.00025234048481694477,
"loss": 1.1841,
"step": 525
},
{
"epoch": 0.33811802232854865,
"grad_norm": 2.0265157222747803,
"learning_rate": 0.0002511124469247809,
"loss": 1.2114,
"step": 530
},
{
"epoch": 0.3413078149920255,
"grad_norm": 0.7946969270706177,
"learning_rate": 0.00024987186024822295,
"loss": 1.2057,
"step": 535
},
{
"epoch": 0.3444976076555024,
"grad_norm": 2.393213987350464,
"learning_rate": 0.0002486188787530309,
"loss": 1.2209,
"step": 540
},
{
"epoch": 0.34768740031897927,
"grad_norm": 1.4503653049468994,
"learning_rate": 0.00024735365794325117,
"loss": 1.2303,
"step": 545
},
{
"epoch": 0.3508771929824561,
"grad_norm": 2.4336180686950684,
"learning_rate": 0.0002460763548419172,
"loss": 1.205,
"step": 550
},
{
"epoch": 0.35406698564593303,
"grad_norm": 1.3000552654266357,
"learning_rate": 0.0002447871279715624,
"loss": 1.2139,
"step": 555
},
{
"epoch": 0.3572567783094099,
"grad_norm": 1.1987704038619995,
"learning_rate": 0.00024348613733454565,
"loss": 1.2001,
"step": 560
},
{
"epoch": 0.36044657097288674,
"grad_norm": 1.4307914972305298,
"learning_rate": 0.00024217354439319427,
"loss": 1.1822,
"step": 565
},
{
"epoch": 0.36363636363636365,
"grad_norm": 2.28100848197937,
"learning_rate": 0.00024084951204976528,
"loss": 1.1826,
"step": 570
},
{
"epoch": 0.3668261562998405,
"grad_norm": 1.1329950094223022,
"learning_rate": 0.0002395142046262281,
"loss": 1.2024,
"step": 575
},
{
"epoch": 0.3700159489633174,
"grad_norm": 1.3367254734039307,
"learning_rate": 0.00023816778784387094,
"loss": 1.1933,
"step": 580
},
{
"epoch": 0.37320574162679426,
"grad_norm": 0.9757080078125,
"learning_rate": 0.0002368104288027336,
"loss": 1.1826,
"step": 585
},
{
"epoch": 0.3763955342902711,
"grad_norm": 2.52244234085083,
"learning_rate": 0.0002354422959608692,
"loss": 1.2129,
"step": 590
},
{
"epoch": 0.379585326953748,
"grad_norm": 2.156867265701294,
"learning_rate": 0.00023406355911343717,
"loss": 1.2185,
"step": 595
},
{
"epoch": 0.3827751196172249,
"grad_norm": 3.1043102741241455,
"learning_rate": 0.00023267438937163077,
"loss": 1.1834,
"step": 600
},
{
"epoch": 0.38596491228070173,
"grad_norm": 2.570702314376831,
"learning_rate": 0.00023127495914144051,
"loss": 1.2028,
"step": 605
},
{
"epoch": 0.38915470494417864,
"grad_norm": 0.836580753326416,
"learning_rate": 0.00022986544210225774,
"loss": 1.1895,
"step": 610
},
{
"epoch": 0.3923444976076555,
"grad_norm": 1.2737889289855957,
"learning_rate": 0.00022844601318531955,
"loss": 1.1641,
"step": 615
},
{
"epoch": 0.39553429027113235,
"grad_norm": 1.6395554542541504,
"learning_rate": 0.00022701684855199857,
"loss": 1.2172,
"step": 620
},
{
"epoch": 0.39872408293460926,
"grad_norm": 0.8626974821090698,
"learning_rate": 0.00022557812557194,
"loss": 1.1785,
"step": 625
},
{
"epoch": 0.4019138755980861,
"grad_norm": 2.091778039932251,
"learning_rate": 0.00022413002280104915,
"loss": 1.1817,
"step": 630
},
{
"epoch": 0.405103668261563,
"grad_norm": 1.2207390069961548,
"learning_rate": 0.00022267271995933074,
"loss": 1.2138,
"step": 635
},
{
"epoch": 0.4082934609250399,
"grad_norm": 1.2744272947311401,
"learning_rate": 0.00022120639790858482,
"loss": 1.1901,
"step": 640
},
{
"epoch": 0.41148325358851673,
"grad_norm": 1.1834518909454346,
"learning_rate": 0.00021973123862996044,
"loss": 1.2143,
"step": 645
},
{
"epoch": 0.41467304625199364,
"grad_norm": 1.2653913497924805,
"learning_rate": 0.00021824742520137026,
"loss": 1.2088,
"step": 650
},
{
"epoch": 0.4178628389154705,
"grad_norm": 1.1800236701965332,
"learning_rate": 0.00021675514177476945,
"loss": 1.1787,
"step": 655
},
{
"epoch": 0.42105263157894735,
"grad_norm": 1.9899177551269531,
"learning_rate": 0.0002152545735533012,
"loss": 1.1963,
"step": 660
},
{
"epoch": 0.42424242424242425,
"grad_norm": 1.0640288591384888,
"learning_rate": 0.00021374590676831136,
"loss": 1.1854,
"step": 665
},
{
"epoch": 0.4274322169059011,
"grad_norm": 1.9654450416564941,
"learning_rate": 0.00021222932865623605,
"loss": 1.1844,
"step": 670
},
{
"epoch": 0.430622009569378,
"grad_norm": 2.232189893722534,
"learning_rate": 0.00021070502743536414,
"loss": 1.1608,
"step": 675
},
{
"epoch": 0.43381180223285487,
"grad_norm": 2.0131752490997314,
"learning_rate": 0.00020917319228247805,
"loss": 1.1726,
"step": 680
},
{
"epoch": 0.4370015948963317,
"grad_norm": 3.602222204208374,
"learning_rate": 0.00020763401330937555,
"loss": 1.1757,
"step": 685
},
{
"epoch": 0.44019138755980863,
"grad_norm": 2.3335506916046143,
"learning_rate": 0.00020608768153927546,
"loss": 1.184,
"step": 690
},
{
"epoch": 0.4433811802232855,
"grad_norm": 1.028072714805603,
"learning_rate": 0.00020453438888311042,
"loss": 1.1648,
"step": 695
},
{
"epoch": 0.44657097288676234,
"grad_norm": 3.57364559173584,
"learning_rate": 0.00020297432811570916,
"loss": 1.1965,
"step": 700
},
{
"epoch": 0.44976076555023925,
"grad_norm": 1.4527466297149658,
"learning_rate": 0.00020140769285187187,
"loss": 1.1597,
"step": 705
},
{
"epoch": 0.4529505582137161,
"grad_norm": 1.855742335319519,
"learning_rate": 0.00019983467752234132,
"loss": 1.1677,
"step": 710
},
{
"epoch": 0.45614035087719296,
"grad_norm": 1.952112078666687,
"learning_rate": 0.0001982554773496723,
"loss": 1.2063,
"step": 715
},
{
"epoch": 0.45933014354066987,
"grad_norm": 1.2015854120254517,
"learning_rate": 0.00019667028832400345,
"loss": 1.1462,
"step": 720
},
{
"epoch": 0.4625199362041467,
"grad_norm": 3.997166872024536,
"learning_rate": 0.00019507930717873313,
"loss": 1.1694,
"step": 725
},
{
"epoch": 0.46570972886762363,
"grad_norm": 2.941664934158325,
"learning_rate": 0.00019348273136610364,
"loss": 1.1751,
"step": 730
},
{
"epoch": 0.4688995215311005,
"grad_norm": 1.275882601737976,
"learning_rate": 0.00019188075903269587,
"loss": 1.1763,
"step": 735
},
{
"epoch": 0.47208931419457734,
"grad_norm": 1.3392881155014038,
"learning_rate": 0.00019027358899483776,
"loss": 1.1659,
"step": 740
},
{
"epoch": 0.47527910685805425,
"grad_norm": 1.5464389324188232,
"learning_rate": 0.00018866142071393013,
"loss": 1.1615,
"step": 745
},
{
"epoch": 0.4784688995215311,
"grad_norm": 0.8039942979812622,
"learning_rate": 0.00018704445427169156,
"loss": 1.1703,
"step": 750
},
{
"epoch": 0.48165869218500795,
"grad_norm": 1.1516778469085693,
"learning_rate": 0.00018542289034532733,
"loss": 1.1602,
"step": 755
},
{
"epoch": 0.48484848484848486,
"grad_norm": 1.191139578819275,
"learning_rate": 0.00018379693018262349,
"loss": 1.1802,
"step": 760
},
{
"epoch": 0.4880382775119617,
"grad_norm": 1.7178115844726562,
"learning_rate": 0.00018216677557697083,
"loss": 1.1797,
"step": 765
},
{
"epoch": 0.49122807017543857,
"grad_norm": 2.011737585067749,
"learning_rate": 0.00018053262884232078,
"loss": 1.1788,
"step": 770
},
{
"epoch": 0.4944178628389155,
"grad_norm": 0.8188173174858093,
"learning_rate": 0.0001788946927880768,
"loss": 1.1602,
"step": 775
},
{
"epoch": 0.49760765550239233,
"grad_norm": 2.8875205516815186,
"learning_rate": 0.00017725317069392418,
"loss": 1.1633,
"step": 780
},
{
"epoch": 0.5007974481658692,
"grad_norm": 2.8602237701416016,
"learning_rate": 0.00017560826628460182,
"loss": 1.1598,
"step": 785
},
{
"epoch": 0.5039872408293461,
"grad_norm": 6.106576919555664,
"learning_rate": 0.00017396018370461808,
"loss": 1.1752,
"step": 790
},
{
"epoch": 0.507177033492823,
"grad_norm": 1.2913662195205688,
"learning_rate": 0.00017230912749291547,
"loss": 1.1865,
"step": 795
},
{
"epoch": 0.5103668261562998,
"grad_norm": 1.422013521194458,
"learning_rate": 0.00017065530255748557,
"loss": 1.1697,
"step": 800
},
{
"epoch": 0.5135566188197768,
"grad_norm": 1.5933501720428467,
"learning_rate": 0.00016899891414993854,
"loss": 1.1669,
"step": 805
},
{
"epoch": 0.5167464114832536,
"grad_norm": 1.5201044082641602,
"learning_rate": 0.00016734016784002994,
"loss": 1.1658,
"step": 810
},
{
"epoch": 0.5199362041467305,
"grad_norm": 1.0443668365478516,
"learning_rate": 0.000165679269490148,
"loss": 1.1562,
"step": 815
},
{
"epoch": 0.5231259968102073,
"grad_norm": 0.9849405884742737,
"learning_rate": 0.0001640164252297648,
"loss": 1.1485,
"step": 820
},
{
"epoch": 0.5263157894736842,
"grad_norm": 1.2747652530670166,
"learning_rate": 0.00016235184142985367,
"loss": 1.1511,
"step": 825
},
{
"epoch": 0.529505582137161,
"grad_norm": 1.8182193040847778,
"learning_rate": 0.00016068572467727762,
"loss": 1.1778,
"step": 830
},
{
"epoch": 0.532695374800638,
"grad_norm": 1.002661108970642,
"learning_rate": 0.00015901828174915005,
"loss": 1.1604,
"step": 835
},
{
"epoch": 0.5358851674641149,
"grad_norm": 1.4460569620132446,
"learning_rate": 0.00015734971958717228,
"loss": 1.1688,
"step": 840
},
{
"epoch": 0.5390749601275917,
"grad_norm": 1.7245659828186035,
"learning_rate": 0.00015568024527195067,
"loss": 1.1794,
"step": 845
},
{
"epoch": 0.5422647527910686,
"grad_norm": 1.0630652904510498,
"learning_rate": 0.0001540100659972963,
"loss": 1.133,
"step": 850
},
{
"epoch": 0.5454545454545454,
"grad_norm": 1.1989563703536987,
"learning_rate": 0.000152339389044511,
"loss": 1.163,
"step": 855
},
{
"epoch": 0.5486443381180224,
"grad_norm": 8.01758861541748,
"learning_rate": 0.00015066842175666186,
"loss": 1.1632,
"step": 860
},
{
"epoch": 0.5518341307814992,
"grad_norm": 0.8911394476890564,
"learning_rate": 0.0001489973715128487,
"loss": 1.136,
"step": 865
},
{
"epoch": 0.5550239234449761,
"grad_norm": 1.598703145980835,
"learning_rate": 0.00014732644570246675,
"loss": 1.1476,
"step": 870
},
{
"epoch": 0.5582137161084529,
"grad_norm": 1.122660756111145,
"learning_rate": 0.00014565585169946824,
"loss": 1.1598,
"step": 875
},
{
"epoch": 0.5614035087719298,
"grad_norm": 3.6311142444610596,
"learning_rate": 0.0001439857968366256,
"loss": 1.158,
"step": 880
},
{
"epoch": 0.5645933014354066,
"grad_norm": 2.771517515182495,
"learning_rate": 0.00014231648837980022,
"loss": 1.1269,
"step": 885
},
{
"epoch": 0.5677830940988836,
"grad_norm": 1.8766001462936401,
"learning_rate": 0.00014064813350221894,
"loss": 1.1855,
"step": 890
},
{
"epoch": 0.5709728867623605,
"grad_norm": 1.0254100561141968,
"learning_rate": 0.00013898093925876267,
"loss": 1.1206,
"step": 895
},
{
"epoch": 0.5741626794258373,
"grad_norm": 1.0249429941177368,
"learning_rate": 0.00013731511256026913,
"loss": 1.1452,
"step": 900
},
{
"epoch": 0.5773524720893142,
"grad_norm": 1.6923766136169434,
"learning_rate": 0.00013565086014785406,
"loss": 1.1558,
"step": 905
},
{
"epoch": 0.580542264752791,
"grad_norm": 1.1442967653274536,
"learning_rate": 0.00013398838856725257,
"loss": 1.1555,
"step": 910
},
{
"epoch": 0.583732057416268,
"grad_norm": 1.3362458944320679,
"learning_rate": 0.00013232790414318608,
"loss": 1.1294,
"step": 915
},
{
"epoch": 0.5869218500797448,
"grad_norm": 2.405693531036377,
"learning_rate": 0.0001306696129537553,
"loss": 1.1569,
"step": 920
},
{
"epoch": 0.5901116427432217,
"grad_norm": 1.8836421966552734,
"learning_rate": 0.00012901372080486472,
"loss": 1.1246,
"step": 925
},
{
"epoch": 0.5933014354066986,
"grad_norm": 1.0528597831726074,
"learning_rate": 0.00012736043320468073,
"loss": 1.1255,
"step": 930
},
{
"epoch": 0.5964912280701754,
"grad_norm": 1.1211520433425903,
"learning_rate": 0.0001257099553381262,
"loss": 1.1451,
"step": 935
},
{
"epoch": 0.5996810207336523,
"grad_norm": 1.0666625499725342,
"learning_rate": 0.00012406249204141603,
"loss": 1.1326,
"step": 940
},
{
"epoch": 0.6028708133971292,
"grad_norm": 1.0989271402359009,
"learning_rate": 0.000122418247776635,
"loss": 1.1428,
"step": 945
},
{
"epoch": 0.6060606060606061,
"grad_norm": 1.260853886604309,
"learning_rate": 0.00012077742660636299,
"loss": 1.1376,
"step": 950
},
{
"epoch": 0.6092503987240829,
"grad_norm": 0.7593328356742859,
"learning_rate": 0.00011914023216834904,
"loss": 1.114,
"step": 955
},
{
"epoch": 0.6124401913875598,
"grad_norm": 1.079769253730774,
"learning_rate": 0.0001175068676502386,
"loss": 1.1034,
"step": 960
},
{
"epoch": 0.6156299840510366,
"grad_norm": 3.5690054893493652,
"learning_rate": 0.00011587753576435634,
"loss": 1.1128,
"step": 965
},
{
"epoch": 0.6188197767145136,
"grad_norm": 1.176243543624878,
"learning_rate": 0.00011425243872254835,
"loss": 1.1106,
"step": 970
},
{
"epoch": 0.6220095693779905,
"grad_norm": 2.7429394721984863,
"learning_rate": 0.00011263177821108573,
"loss": 1.1347,
"step": 975
},
{
"epoch": 0.6251993620414673,
"grad_norm": 1.3033727407455444,
"learning_rate": 0.00011101575536563433,
"loss": 1.1124,
"step": 980
},
{
"epoch": 0.6283891547049442,
"grad_norm": 1.5057191848754883,
"learning_rate": 0.00010940457074629217,
"loss": 1.1176,
"step": 985
},
{
"epoch": 0.631578947368421,
"grad_norm": 1.3368103504180908,
"learning_rate": 0.00010779842431269843,
"loss": 1.1189,
"step": 990
},
{
"epoch": 0.6347687400318979,
"grad_norm": 1.240006685256958,
"learning_rate": 0.0001061975153992172,
"loss": 1.1093,
"step": 995
},
{
"epoch": 0.6379585326953748,
"grad_norm": 3.0179250240325928,
"learning_rate": 0.00010460204269019829,
"loss": 1.1025,
"step": 1000
},
{
"epoch": 0.6411483253588517,
"grad_norm": 1.1859713792800903,
"learning_rate": 0.0001030122041953196,
"loss": 1.1334,
"step": 1005
},
{
"epoch": 0.6443381180223285,
"grad_norm": 1.4847084283828735,
"learning_rate": 0.0001014281972250121,
"loss": 1.1351,
"step": 1010
},
{
"epoch": 0.6475279106858054,
"grad_norm": 1.057880163192749,
"learning_rate": 9.985021836597273e-05,
"loss": 1.1072,
"step": 1015
},
{
"epoch": 0.6507177033492823,
"grad_norm": 0.9342829585075378,
"learning_rate": 9.827846345676614e-05,
"loss": 1.1045,
"step": 1020
},
{
"epoch": 0.6539074960127592,
"grad_norm": 0.9297033548355103,
"learning_rate": 9.671312756351998e-05,
"loss": 1.1009,
"step": 1025
},
{
"epoch": 0.6570972886762361,
"grad_norm": 1.077148675918579,
"learning_rate": 9.515440495571569e-05,
"loss": 1.1088,
"step": 1030
},
{
"epoch": 0.6602870813397129,
"grad_norm": 1.4433211088180542,
"learning_rate": 9.360248908207813e-05,
"loss": 1.1026,
"step": 1035
},
{
"epoch": 0.6634768740031898,
"grad_norm": 1.0340611934661865,
"learning_rate": 9.205757254656755e-05,
"loss": 1.0965,
"step": 1040
},
{
"epoch": 0.6666666666666666,
"grad_norm": 1.4647072553634644,
"learning_rate": 9.05198470844756e-05,
"loss": 1.095,
"step": 1045
},
{
"epoch": 0.6698564593301436,
"grad_norm": 5.960877895355225,
"learning_rate": 8.898950353862998e-05,
"loss": 1.107,
"step": 1050
},
{
"epoch": 0.6730462519936204,
"grad_norm": 3.8718395233154297,
"learning_rate": 8.746673183570923e-05,
"loss": 1.108,
"step": 1055
},
{
"epoch": 0.6762360446570973,
"grad_norm": 1.6608846187591553,
"learning_rate": 8.595172096267157e-05,
"loss": 1.1405,
"step": 1060
},
{
"epoch": 0.6794258373205742,
"grad_norm": 1.0977705717086792,
"learning_rate": 8.444465894330024e-05,
"loss": 1.0896,
"step": 1065
},
{
"epoch": 0.682615629984051,
"grad_norm": 1.2941663265228271,
"learning_rate": 8.294573281486828e-05,
"loss": 1.099,
"step": 1070
},
{
"epoch": 0.6858054226475279,
"grad_norm": 1.8003350496292114,
"learning_rate": 8.145512860492596e-05,
"loss": 1.0998,
"step": 1075
},
{
"epoch": 0.6889952153110048,
"grad_norm": 8.684834480285645,
"learning_rate": 7.997303130821362e-05,
"loss": 1.1139,
"step": 1080
},
{
"epoch": 0.6921850079744817,
"grad_norm": 1.1457107067108154,
"learning_rate": 7.849962486370206e-05,
"loss": 1.1079,
"step": 1085
},
{
"epoch": 0.6953748006379585,
"grad_norm": 1.4086178541183472,
"learning_rate": 7.703509213176451e-05,
"loss": 1.1205,
"step": 1090
},
{
"epoch": 0.6985645933014354,
"grad_norm": 8.64991283416748,
"learning_rate": 7.557961487148272e-05,
"loss": 1.12,
"step": 1095
},
{
"epoch": 0.7017543859649122,
"grad_norm": 0.8322669267654419,
"learning_rate": 7.413337371808884e-05,
"loss": 1.0927,
"step": 1100
},
{
"epoch": 0.7049441786283892,
"grad_norm": 1.1140292882919312,
"learning_rate": 7.269654816054756e-05,
"loss": 1.0876,
"step": 1105
},
{
"epoch": 0.7081339712918661,
"grad_norm": 1.5485320091247559,
"learning_rate": 7.126931651928012e-05,
"loss": 1.0904,
"step": 1110
},
{
"epoch": 0.7113237639553429,
"grad_norm": 0.8744588494300842,
"learning_rate": 6.985185592403367e-05,
"loss": 1.1068,
"step": 1115
},
{
"epoch": 0.7145135566188198,
"grad_norm": 1.0260374546051025,
"learning_rate": 6.844434229189787e-05,
"loss": 1.1022,
"step": 1120
},
{
"epoch": 0.7177033492822966,
"grad_norm": 1.5165791511535645,
"learning_rate": 6.704695030547252e-05,
"loss": 1.0818,
"step": 1125
},
{
"epoch": 0.7208931419457735,
"grad_norm": 1.1698341369628906,
"learning_rate": 6.56598533911881e-05,
"loss": 1.0937,
"step": 1130
},
{
"epoch": 0.7240829346092504,
"grad_norm": 5.878746032714844,
"learning_rate": 6.428322369778254e-05,
"loss": 1.1108,
"step": 1135
},
{
"epoch": 0.7272727272727273,
"grad_norm": 0.82503342628479,
"learning_rate": 6.291723207493577e-05,
"loss": 1.0722,
"step": 1140
},
{
"epoch": 0.7304625199362041,
"grad_norm": 0.8583028316497803,
"learning_rate": 6.15620480520666e-05,
"loss": 1.0876,
"step": 1145
},
{
"epoch": 0.733652312599681,
"grad_norm": 0.9114026427268982,
"learning_rate": 6.0217839817292765e-05,
"loss": 1.0782,
"step": 1150
},
{
"epoch": 0.7368421052631579,
"grad_norm": 1.1162232160568237,
"learning_rate": 5.888477419655733e-05,
"loss": 1.0968,
"step": 1155
},
{
"epoch": 0.7400318979266348,
"grad_norm": 0.9924772381782532,
"learning_rate": 5.7563016632924555e-05,
"loss": 1.0821,
"step": 1160
},
{
"epoch": 0.7432216905901117,
"grad_norm": 0.9202504754066467,
"learning_rate": 5.625273116604728e-05,
"loss": 1.1216,
"step": 1165
},
{
"epoch": 0.7464114832535885,
"grad_norm": 1.0332766771316528,
"learning_rate": 5.495408041180829e-05,
"loss": 1.1094,
"step": 1170
},
{
"epoch": 0.7496012759170654,
"grad_norm": 1.1432628631591797,
"learning_rate": 5.3667225542138507e-05,
"loss": 1.0725,
"step": 1175
},
{
"epoch": 0.7527910685805422,
"grad_norm": 1.2031751871109009,
"learning_rate": 5.239232626501464e-05,
"loss": 1.1096,
"step": 1180
},
{
"epoch": 0.7559808612440191,
"grad_norm": 1.1352425813674927,
"learning_rate": 5.1129540804637906e-05,
"loss": 1.0949,
"step": 1185
},
{
"epoch": 0.759170653907496,
"grad_norm": 4.166080474853516,
"learning_rate": 4.9879025881797466e-05,
"loss": 1.0776,
"step": 1190
},
{
"epoch": 0.7623604465709729,
"grad_norm": 1.7659157514572144,
"learning_rate": 4.8640936694420245e-05,
"loss": 1.0777,
"step": 1195
},
{
"epoch": 0.7655502392344498,
"grad_norm": 0.734951376914978,
"learning_rate": 4.7415426898309704e-05,
"loss": 1.0787,
"step": 1200
},
{
"epoch": 0.7687400318979266,
"grad_norm": 1.0419098138809204,
"learning_rate": 4.62026485880761e-05,
"loss": 1.0811,
"step": 1205
},
{
"epoch": 0.7719298245614035,
"grad_norm": 0.9413526654243469,
"learning_rate": 4.50027522782603e-05,
"loss": 1.0771,
"step": 1210
},
{
"epoch": 0.7751196172248804,
"grad_norm": 1.194632649421692,
"learning_rate": 4.3815886884654136e-05,
"loss": 1.0781,
"step": 1215
},
{
"epoch": 0.7783094098883573,
"grad_norm": 1.6069307327270508,
"learning_rate": 4.264219970581854e-05,
"loss": 1.1017,
"step": 1220
},
{
"epoch": 0.7814992025518341,
"grad_norm": 1.064291000366211,
"learning_rate": 4.148183640480293e-05,
"loss": 1.0943,
"step": 1225
},
{
"epoch": 0.784688995215311,
"grad_norm": 1.8470526933670044,
"learning_rate": 4.0334940991067276e-05,
"loss": 1.1089,
"step": 1230
},
{
"epoch": 0.7878787878787878,
"grad_norm": 0.8893584609031677,
"learning_rate": 3.920165580260973e-05,
"loss": 1.0944,
"step": 1235
},
{
"epoch": 0.7910685805422647,
"grad_norm": 1.3273100852966309,
"learning_rate": 3.808212148830095e-05,
"loss": 1.0753,
"step": 1240
},
{
"epoch": 0.7942583732057417,
"grad_norm": 1.6681938171386719,
"learning_rate": 3.697647699042918e-05,
"loss": 1.0755,
"step": 1245
},
{
"epoch": 0.7974481658692185,
"grad_norm": 1.1112189292907715,
"learning_rate": 3.5884859527455995e-05,
"loss": 1.0852,
"step": 1250
},
{
"epoch": 0.8006379585326954,
"grad_norm": 0.9270617365837097,
"learning_rate": 3.48074045769868e-05,
"loss": 1.0873,
"step": 1255
},
{
"epoch": 0.8038277511961722,
"grad_norm": 1.1638352870941162,
"learning_rate": 3.3744245858956967e-05,
"loss": 1.1141,
"step": 1260
},
{
"epoch": 0.8070175438596491,
"grad_norm": 1.0835789442062378,
"learning_rate": 3.2695515319036186e-05,
"loss": 1.097,
"step": 1265
},
{
"epoch": 0.810207336523126,
"grad_norm": 0.7704162001609802,
"learning_rate": 3.1661343112253304e-05,
"loss": 1.081,
"step": 1270
},
{
"epoch": 0.8133971291866029,
"grad_norm": 0.9477359056472778,
"learning_rate": 3.064185758684265e-05,
"loss": 1.0632,
"step": 1275
},
{
"epoch": 0.8165869218500797,
"grad_norm": 1.0834468603134155,
"learning_rate": 2.96371852683157e-05,
"loss": 1.0939,
"step": 1280
},
{
"epoch": 0.8197767145135566,
"grad_norm": 1.0074337720870972,
"learning_rate": 2.8647450843757897e-05,
"loss": 1.1007,
"step": 1285
},
{
"epoch": 0.8229665071770335,
"grad_norm": 0.9465036392211914,
"learning_rate": 2.7672777146354246e-05,
"loss": 1.095,
"step": 1290
},
{
"epoch": 0.8261562998405104,
"grad_norm": 0.9678279161453247,
"learning_rate": 2.6713285140144802e-05,
"loss": 1.0927,
"step": 1295
},
{
"epoch": 0.8293460925039873,
"grad_norm": 1.2122068405151367,
"learning_rate": 2.5769093905012333e-05,
"loss": 1.0784,
"step": 1300
},
{
"epoch": 0.8325358851674641,
"grad_norm": 1.0039793252944946,
"learning_rate": 2.4840320621903253e-05,
"loss": 1.0766,
"step": 1305
},
{
"epoch": 0.835725677830941,
"grad_norm": 1.5479018688201904,
"learning_rate": 2.392708055828495e-05,
"loss": 1.0768,
"step": 1310
},
{
"epoch": 0.8389154704944178,
"grad_norm": 0.8418304324150085,
"learning_rate": 2.3029487053840295e-05,
"loss": 1.0777,
"step": 1315
},
{
"epoch": 0.8421052631578947,
"grad_norm": 2.277839183807373,
"learning_rate": 2.214765150640108e-05,
"loss": 1.0962,
"step": 1320
},
{
"epoch": 0.8452950558213717,
"grad_norm": 1.1263689994812012,
"learning_rate": 2.1281683358122996e-05,
"loss": 1.0756,
"step": 1325
},
{
"epoch": 0.8484848484848485,
"grad_norm": 1.8724466562271118,
"learning_rate": 2.043169008190289e-05,
"loss": 1.092,
"step": 1330
},
{
"epoch": 0.8516746411483254,
"grad_norm": 0.8570544123649597,
"learning_rate": 1.9597777168040872e-05,
"loss": 1.0956,
"step": 1335
},
{
"epoch": 0.8548644338118022,
"grad_norm": 0.7986017465591431,
"learning_rate": 1.8780048111147776e-05,
"loss": 1.0964,
"step": 1340
},
{
"epoch": 0.8580542264752791,
"grad_norm": 0.973429799079895,
"learning_rate": 1.797860439730126e-05,
"loss": 1.0466,
"step": 1345
},
{
"epoch": 0.861244019138756,
"grad_norm": 1.8588981628417969,
"learning_rate": 1.7193545491450183e-05,
"loss": 1.0906,
"step": 1350
},
{
"epoch": 0.8644338118022329,
"grad_norm": 0.8553722500801086,
"learning_rate": 1.6424968825070567e-05,
"loss": 1.0621,
"step": 1355
},
{
"epoch": 0.8676236044657097,
"grad_norm": 0.7932642698287964,
"learning_rate": 1.567296978407353e-05,
"loss": 1.0786,
"step": 1360
},
{
"epoch": 0.8708133971291866,
"grad_norm": 0.7676968574523926,
"learning_rate": 1.4937641696967245e-05,
"loss": 1.0959,
"step": 1365
},
{
"epoch": 0.8740031897926634,
"grad_norm": 0.8007521033287048,
"learning_rate": 1.4219075823274251e-05,
"loss": 1.075,
"step": 1370
},
{
"epoch": 0.8771929824561403,
"grad_norm": 0.7606749534606934,
"learning_rate": 1.3517361342205295e-05,
"loss": 1.0748,
"step": 1375
},
{
"epoch": 0.8803827751196173,
"grad_norm": 0.9343269467353821,
"learning_rate": 1.2832585341591844e-05,
"loss": 1.0499,
"step": 1380
},
{
"epoch": 0.8835725677830941,
"grad_norm": 1.2631272077560425,
"learning_rate": 1.2164832807077585e-05,
"loss": 1.0824,
"step": 1385
},
{
"epoch": 0.886762360446571,
"grad_norm": 0.8094949126243591,
"learning_rate": 1.151418661157122e-05,
"loss": 1.069,
"step": 1390
},
{
"epoch": 0.8899521531100478,
"grad_norm": 0.9011691808700562,
"learning_rate": 1.0880727504961339e-05,
"loss": 1.0696,
"step": 1395
},
{
"epoch": 0.8931419457735247,
"grad_norm": 0.710112988948822,
"learning_rate": 1.0264534104094812e-05,
"loss": 1.0808,
"step": 1400
},
{
"epoch": 0.8963317384370016,
"grad_norm": 0.9122905135154724,
"learning_rate": 9.665682883019732e-06,
"loss": 1.0729,
"step": 1405
},
{
"epoch": 0.8995215311004785,
"grad_norm": 0.9680069088935852,
"learning_rate": 9.084248163494511e-06,
"loss": 1.0741,
"step": 1410
},
{
"epoch": 0.9027113237639554,
"grad_norm": 1.0660099983215332,
"learning_rate": 8.520302105764148e-06,
"loss": 1.0786,
"step": 1415
},
{
"epoch": 0.9059011164274322,
"grad_norm": 0.8283365964889526,
"learning_rate": 7.973914699604367e-06,
"loss": 1.0749,
"step": 1420
},
{
"epoch": 0.9090909090909091,
"grad_norm": 0.7764257192611694,
"learning_rate": 7.445153755635569e-06,
"loss": 1.0869,
"step": 1425
},
{
"epoch": 0.9122807017543859,
"grad_norm": 0.7744048237800598,
"learning_rate": 6.934084896906983e-06,
"loss": 1.081,
"step": 1430
},
{
"epoch": 0.9154704944178629,
"grad_norm": 0.8904666900634766,
"learning_rate": 6.440771550752377e-06,
"loss": 1.0909,
"step": 1435
},
{
"epoch": 0.9186602870813397,
"grad_norm": 0.731381893157959,
"learning_rate": 5.965274940918274e-06,
"loss": 1.0837,
"step": 1440
},
{
"epoch": 0.9218500797448166,
"grad_norm": 2.323331117630005,
"learning_rate": 5.507654079965612e-06,
"loss": 1.0651,
"step": 1445
},
{
"epoch": 0.9250398724082934,
"grad_norm": 0.8549768328666687,
"learning_rate": 5.067965761945869e-06,
"loss": 1.0887,
"step": 1450
},
{
"epoch": 0.9282296650717703,
"grad_norm": 0.8538034558296204,
"learning_rate": 4.646264555352586e-06,
"loss": 1.0685,
"step": 1455
},
{
"epoch": 0.9314194577352473,
"grad_norm": 0.756767988204956,
"learning_rate": 4.242602796348915e-06,
"loss": 1.0661,
"step": 1460
},
{
"epoch": 0.9346092503987241,
"grad_norm": 1.35940682888031,
"learning_rate": 3.857030582272369e-06,
"loss": 1.062,
"step": 1465
},
{
"epoch": 0.937799043062201,
"grad_norm": 0.9812383651733398,
"learning_rate": 3.489595765417441e-06,
"loss": 1.0341,
"step": 1470
},
{
"epoch": 0.9409888357256778,
"grad_norm": 0.8831263780593872,
"learning_rate": 3.140343947096624e-06,
"loss": 1.0486,
"step": 1475
},
{
"epoch": 0.9441786283891547,
"grad_norm": 0.7819539904594421,
"learning_rate": 2.80931847198117e-06,
"loss": 1.1105,
"step": 1480
},
{
"epoch": 0.9473684210526315,
"grad_norm": 0.9179317355155945,
"learning_rate": 2.4965604227215774e-06,
"loss": 1.0849,
"step": 1485
},
{
"epoch": 0.9505582137161085,
"grad_norm": 0.8770614266395569,
"learning_rate": 2.202108614848885e-06,
"loss": 1.0684,
"step": 1490
},
{
"epoch": 0.9537480063795853,
"grad_norm": 0.7987916469573975,
"learning_rate": 1.925999591957561e-06,
"loss": 1.0725,
"step": 1495
},
{
"epoch": 0.9569377990430622,
"grad_norm": 0.754940927028656,
"learning_rate": 1.6682676211700107e-06,
"loss": 1.0815,
"step": 1500
},
{
"epoch": 0.960127591706539,
"grad_norm": 0.941967248916626,
"learning_rate": 1.4289446888838652e-06,
"loss": 1.0887,
"step": 1505
},
{
"epoch": 0.9633173843700159,
"grad_norm": 0.9065337181091309,
"learning_rate": 1.2080604968022378e-06,
"loss": 1.0604,
"step": 1510
},
{
"epoch": 0.9665071770334929,
"grad_norm": 0.7943056225776672,
"learning_rate": 1.0056424582474575e-06,
"loss": 1.0627,
"step": 1515
},
{
"epoch": 0.9696969696969697,
"grad_norm": 0.7137452960014343,
"learning_rate": 8.217156947590064e-07,
"loss": 1.0576,
"step": 1520
},
{
"epoch": 0.9728867623604466,
"grad_norm": 0.7708435654640198,
"learning_rate": 6.563030329755969e-07,
"loss": 1.0446,
"step": 1525
},
{
"epoch": 0.9760765550239234,
"grad_norm": 0.9459482431411743,
"learning_rate": 5.094250018023715e-07,
"loss": 1.0921,
"step": 1530
},
{
"epoch": 0.9792663476874003,
"grad_norm": 1.0283273458480835,
"learning_rate": 3.8109982986300747e-07,
"loss": 1.0788,
"step": 1535
},
{
"epoch": 0.9824561403508771,
"grad_norm": 0.7605658769607544,
"learning_rate": 2.7134344323747616e-07,
"loss": 1.0686,
"step": 1540
},
{
"epoch": 0.9856459330143541,
"grad_norm": 0.7354826331138611,
"learning_rate": 1.801694634854578e-07,
"loss": 1.0946,
"step": 1545
},
{
"epoch": 0.988835725677831,
"grad_norm": 1.082857608795166,
"learning_rate": 1.075892059558603e-07,
"loss": 1.0849,
"step": 1550
},
{
"epoch": 0.9920255183413078,
"grad_norm": 0.8959941864013672,
"learning_rate": 5.3611678382442516e-08,
"loss": 1.0725,
"step": 1555
},
{
"epoch": 0.9952153110047847,
"grad_norm": 0.8628972172737122,
"learning_rate": 1.824357976594193e-08,
"loss": 1.0438,
"step": 1560
},
{
"epoch": 0.9984051036682615,
"grad_norm": 0.8962126970291138,
"learning_rate": 1.4892995426396548e-09,
"loss": 1.0731,
"step": 1565
},
{
"epoch": 0.9996810207336523,
"eval_loss": 2.480717420578003,
"eval_runtime": 1.759,
"eval_samples_per_second": 5.685,
"eval_steps_per_second": 1.705,
"step": 1567
},
{
"epoch": 0.9996810207336523,
"step": 1567,
"total_flos": 5.97257971054936e+17,
"train_loss": 2.314191315838997,
"train_runtime": 7526.9596,
"train_samples_per_second": 1.666,
"train_steps_per_second": 0.208
}
],
"logging_steps": 5,
"max_steps": 1567,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.97257971054936e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}