Qwen2-7B-sft-ultrachat / trainer_state.json
AmberYifan's picture
Model save
83eca81 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1624,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006157635467980296,
"grad_norm": 5.843350091773468,
"learning_rate": 1.226993865030675e-07,
"loss": 1.3464,
"step": 1
},
{
"epoch": 0.003078817733990148,
"grad_norm": 5.3914915821981415,
"learning_rate": 6.134969325153375e-07,
"loss": 1.3329,
"step": 5
},
{
"epoch": 0.006157635467980296,
"grad_norm": 4.175790138169032,
"learning_rate": 1.226993865030675e-06,
"loss": 1.3034,
"step": 10
},
{
"epoch": 0.009236453201970444,
"grad_norm": 3.9614222860298014,
"learning_rate": 1.8404907975460124e-06,
"loss": 1.1286,
"step": 15
},
{
"epoch": 0.012315270935960592,
"grad_norm": 1.6761131953065662,
"learning_rate": 2.45398773006135e-06,
"loss": 1.1093,
"step": 20
},
{
"epoch": 0.01539408866995074,
"grad_norm": 1.514096342814139,
"learning_rate": 3.0674846625766875e-06,
"loss": 1.1518,
"step": 25
},
{
"epoch": 0.01847290640394089,
"grad_norm": 1.5136022864934484,
"learning_rate": 3.680981595092025e-06,
"loss": 1.0902,
"step": 30
},
{
"epoch": 0.021551724137931036,
"grad_norm": 1.3142636172978153,
"learning_rate": 4.294478527607362e-06,
"loss": 1.0347,
"step": 35
},
{
"epoch": 0.024630541871921183,
"grad_norm": 1.52893939969623,
"learning_rate": 4.9079754601227e-06,
"loss": 1.1391,
"step": 40
},
{
"epoch": 0.02770935960591133,
"grad_norm": 1.5303178517618214,
"learning_rate": 5.521472392638038e-06,
"loss": 1.0339,
"step": 45
},
{
"epoch": 0.03078817733990148,
"grad_norm": 1.5034987251473977,
"learning_rate": 6.134969325153375e-06,
"loss": 1.0692,
"step": 50
},
{
"epoch": 0.033866995073891626,
"grad_norm": 1.4647649766885826,
"learning_rate": 6.748466257668712e-06,
"loss": 1.0295,
"step": 55
},
{
"epoch": 0.03694581280788178,
"grad_norm": 1.6919934353518973,
"learning_rate": 7.36196319018405e-06,
"loss": 1.1643,
"step": 60
},
{
"epoch": 0.04002463054187192,
"grad_norm": 1.6081025398256859,
"learning_rate": 7.975460122699386e-06,
"loss": 1.0625,
"step": 65
},
{
"epoch": 0.04310344827586207,
"grad_norm": 1.5381998640784367,
"learning_rate": 8.588957055214725e-06,
"loss": 1.1089,
"step": 70
},
{
"epoch": 0.046182266009852216,
"grad_norm": 1.4922112152098923,
"learning_rate": 9.202453987730062e-06,
"loss": 1.1351,
"step": 75
},
{
"epoch": 0.04926108374384237,
"grad_norm": 1.467594723101496,
"learning_rate": 9.8159509202454e-06,
"loss": 1.1211,
"step": 80
},
{
"epoch": 0.05233990147783251,
"grad_norm": 1.5925222515863833,
"learning_rate": 1.0429447852760737e-05,
"loss": 1.0664,
"step": 85
},
{
"epoch": 0.05541871921182266,
"grad_norm": 1.5235805873007848,
"learning_rate": 1.1042944785276076e-05,
"loss": 1.1069,
"step": 90
},
{
"epoch": 0.058497536945812806,
"grad_norm": 1.5364395232528099,
"learning_rate": 1.1656441717791411e-05,
"loss": 1.1028,
"step": 95
},
{
"epoch": 0.06157635467980296,
"grad_norm": 1.4460488308276138,
"learning_rate": 1.226993865030675e-05,
"loss": 1.0731,
"step": 100
},
{
"epoch": 0.06465517241379311,
"grad_norm": 1.4350753386865465,
"learning_rate": 1.2883435582822085e-05,
"loss": 1.1041,
"step": 105
},
{
"epoch": 0.06773399014778325,
"grad_norm": 1.5175319041919364,
"learning_rate": 1.3496932515337424e-05,
"loss": 1.0848,
"step": 110
},
{
"epoch": 0.0708128078817734,
"grad_norm": 1.601567726747361,
"learning_rate": 1.4110429447852763e-05,
"loss": 1.1009,
"step": 115
},
{
"epoch": 0.07389162561576355,
"grad_norm": 1.4956706222097174,
"learning_rate": 1.47239263803681e-05,
"loss": 1.031,
"step": 120
},
{
"epoch": 0.0769704433497537,
"grad_norm": 1.3438559417065374,
"learning_rate": 1.5337423312883436e-05,
"loss": 1.0763,
"step": 125
},
{
"epoch": 0.08004926108374384,
"grad_norm": 1.465628260314698,
"learning_rate": 1.5950920245398772e-05,
"loss": 1.0581,
"step": 130
},
{
"epoch": 0.08312807881773399,
"grad_norm": 1.5030980367798943,
"learning_rate": 1.656441717791411e-05,
"loss": 1.1329,
"step": 135
},
{
"epoch": 0.08620689655172414,
"grad_norm": 1.4901594962947946,
"learning_rate": 1.717791411042945e-05,
"loss": 1.1137,
"step": 140
},
{
"epoch": 0.08928571428571429,
"grad_norm": 1.4927188541704075,
"learning_rate": 1.7791411042944788e-05,
"loss": 1.1489,
"step": 145
},
{
"epoch": 0.09236453201970443,
"grad_norm": 1.5206841909974278,
"learning_rate": 1.8404907975460123e-05,
"loss": 1.1431,
"step": 150
},
{
"epoch": 0.09544334975369458,
"grad_norm": 1.3755169597371524,
"learning_rate": 1.9018404907975462e-05,
"loss": 1.0751,
"step": 155
},
{
"epoch": 0.09852216748768473,
"grad_norm": 1.4255828099986778,
"learning_rate": 1.96319018404908e-05,
"loss": 1.1134,
"step": 160
},
{
"epoch": 0.10160098522167488,
"grad_norm": 1.456131920164264,
"learning_rate": 1.999990752408443e-05,
"loss": 1.1599,
"step": 165
},
{
"epoch": 0.10467980295566502,
"grad_norm": 1.443792052684783,
"learning_rate": 1.9998867189676517e-05,
"loss": 1.1417,
"step": 170
},
{
"epoch": 0.10775862068965517,
"grad_norm": 1.385887037326319,
"learning_rate": 1.999667104662347e-05,
"loss": 1.1416,
"step": 175
},
{
"epoch": 0.11083743842364532,
"grad_norm": 1.4612138225127072,
"learning_rate": 1.9993319348786157e-05,
"loss": 1.1645,
"step": 180
},
{
"epoch": 0.11391625615763547,
"grad_norm": 1.4105581859366445,
"learning_rate": 1.9988812483600597e-05,
"loss": 1.084,
"step": 185
},
{
"epoch": 0.11699507389162561,
"grad_norm": 1.4404260565534297,
"learning_rate": 1.9983150972033186e-05,
"loss": 1.1365,
"step": 190
},
{
"epoch": 0.12007389162561577,
"grad_norm": 1.6426918945470852,
"learning_rate": 1.9976335468520452e-05,
"loss": 1.1689,
"step": 195
},
{
"epoch": 0.12315270935960591,
"grad_norm": 1.4864165138126124,
"learning_rate": 1.9968366760893437e-05,
"loss": 1.1645,
"step": 200
},
{
"epoch": 0.12623152709359606,
"grad_norm": 1.7939843794460433,
"learning_rate": 1.9959245770286602e-05,
"loss": 1.148,
"step": 205
},
{
"epoch": 0.12931034482758622,
"grad_norm": 1.5857793027079103,
"learning_rate": 1.994897355103136e-05,
"loss": 1.1312,
"step": 210
},
{
"epoch": 0.13238916256157635,
"grad_norm": 1.4415644893189572,
"learning_rate": 1.9937551290534208e-05,
"loss": 1.0865,
"step": 215
},
{
"epoch": 0.1354679802955665,
"grad_norm": 1.3980022983035614,
"learning_rate": 1.9924980309139455e-05,
"loss": 1.1252,
"step": 220
},
{
"epoch": 0.13854679802955666,
"grad_norm": 1.4195721954468452,
"learning_rate": 1.9911262059976614e-05,
"loss": 1.148,
"step": 225
},
{
"epoch": 0.1416256157635468,
"grad_norm": 1.4507490770986011,
"learning_rate": 1.9896398128792413e-05,
"loss": 1.1406,
"step": 230
},
{
"epoch": 0.14470443349753695,
"grad_norm": 1.4400302139538153,
"learning_rate": 1.988039023376751e-05,
"loss": 1.1717,
"step": 235
},
{
"epoch": 0.1477832512315271,
"grad_norm": 1.5033011733483128,
"learning_rate": 1.9863240225317868e-05,
"loss": 1.2157,
"step": 240
},
{
"epoch": 0.15086206896551724,
"grad_norm": 1.392957766816036,
"learning_rate": 1.984495008588086e-05,
"loss": 1.1176,
"step": 245
},
{
"epoch": 0.1539408866995074,
"grad_norm": 1.3640840105691432,
"learning_rate": 1.982552192968612e-05,
"loss": 1.2012,
"step": 250
},
{
"epoch": 0.15701970443349753,
"grad_norm": 1.3725868186873555,
"learning_rate": 1.9804958002511137e-05,
"loss": 1.1476,
"step": 255
},
{
"epoch": 0.16009852216748768,
"grad_norm": 1.5087796579041755,
"learning_rate": 1.9783260681421667e-05,
"loss": 1.1699,
"step": 260
},
{
"epoch": 0.16317733990147784,
"grad_norm": 1.3296267344540686,
"learning_rate": 1.9760432474496963e-05,
"loss": 1.1148,
"step": 265
},
{
"epoch": 0.16625615763546797,
"grad_norm": 1.328564048422319,
"learning_rate": 1.973647602053984e-05,
"loss": 1.1504,
"step": 270
},
{
"epoch": 0.16933497536945813,
"grad_norm": 1.403483656734853,
"learning_rate": 1.9711394088771658e-05,
"loss": 1.1732,
"step": 275
},
{
"epoch": 0.1724137931034483,
"grad_norm": 1.3962668466241044,
"learning_rate": 1.9685189578512206e-05,
"loss": 1.1615,
"step": 280
},
{
"epoch": 0.17549261083743842,
"grad_norm": 1.421818277223714,
"learning_rate": 1.9657865518844578e-05,
"loss": 1.1419,
"step": 285
},
{
"epoch": 0.17857142857142858,
"grad_norm": 1.334139071432472,
"learning_rate": 1.962942506826501e-05,
"loss": 1.127,
"step": 290
},
{
"epoch": 0.1816502463054187,
"grad_norm": 1.340886825434671,
"learning_rate": 1.9599871514317785e-05,
"loss": 1.1638,
"step": 295
},
{
"epoch": 0.18472906403940886,
"grad_norm": 1.4407634585837834,
"learning_rate": 1.9569208273215204e-05,
"loss": 1.0957,
"step": 300
},
{
"epoch": 0.18780788177339902,
"grad_norm": 1.4866331876894523,
"learning_rate": 1.953743888944271e-05,
"loss": 1.1004,
"step": 305
},
{
"epoch": 0.19088669950738915,
"grad_norm": 1.5795823467975436,
"learning_rate": 1.950456703534915e-05,
"loss": 1.1833,
"step": 310
},
{
"epoch": 0.1939655172413793,
"grad_norm": 1.353448651780307,
"learning_rate": 1.9470596510722285e-05,
"loss": 1.103,
"step": 315
},
{
"epoch": 0.19704433497536947,
"grad_norm": 1.329300107648014,
"learning_rate": 1.9435531242349545e-05,
"loss": 1.2326,
"step": 320
},
{
"epoch": 0.2001231527093596,
"grad_norm": 1.4032070649087502,
"learning_rate": 1.9399375283564134e-05,
"loss": 1.1569,
"step": 325
},
{
"epoch": 0.20320197044334976,
"grad_norm": 1.4252758473368121,
"learning_rate": 1.9362132813776472e-05,
"loss": 1.1396,
"step": 330
},
{
"epoch": 0.2062807881773399,
"grad_norm": 1.3806516525627808,
"learning_rate": 1.9323808137991084e-05,
"loss": 1.1495,
"step": 335
},
{
"epoch": 0.20935960591133004,
"grad_norm": 1.3647072576147385,
"learning_rate": 1.9284405686308982e-05,
"loss": 1.1102,
"step": 340
},
{
"epoch": 0.2124384236453202,
"grad_norm": 1.3128534920037203,
"learning_rate": 1.924393001341555e-05,
"loss": 1.1486,
"step": 345
},
{
"epoch": 0.21551724137931033,
"grad_norm": 1.4353367487385866,
"learning_rate": 1.9202385798054073e-05,
"loss": 1.1107,
"step": 350
},
{
"epoch": 0.2185960591133005,
"grad_norm": 1.433228926845981,
"learning_rate": 1.9159777842484878e-05,
"loss": 1.1421,
"step": 355
},
{
"epoch": 0.22167487684729065,
"grad_norm": 1.369952146586952,
"learning_rate": 1.911611107193024e-05,
"loss": 1.1466,
"step": 360
},
{
"epoch": 0.22475369458128078,
"grad_norm": 1.4278395775034365,
"learning_rate": 1.9071390534005045e-05,
"loss": 1.1883,
"step": 365
},
{
"epoch": 0.22783251231527094,
"grad_norm": 1.474363251097099,
"learning_rate": 1.9025621398133333e-05,
"loss": 1.1683,
"step": 370
},
{
"epoch": 0.2309113300492611,
"grad_norm": 1.5957181591807041,
"learning_rate": 1.8978808954950722e-05,
"loss": 1.1573,
"step": 375
},
{
"epoch": 0.23399014778325122,
"grad_norm": 1.4241209521127645,
"learning_rate": 1.8930958615692854e-05,
"loss": 1.1811,
"step": 380
},
{
"epoch": 0.23706896551724138,
"grad_norm": 1.2564805728212545,
"learning_rate": 1.8882075911569887e-05,
"loss": 1.0686,
"step": 385
},
{
"epoch": 0.24014778325123154,
"grad_norm": 1.3305197237408193,
"learning_rate": 1.8832166493127128e-05,
"loss": 1.1292,
"step": 390
},
{
"epoch": 0.24322660098522167,
"grad_norm": 1.319219422937715,
"learning_rate": 1.8781236129591847e-05,
"loss": 1.1093,
"step": 395
},
{
"epoch": 0.24630541871921183,
"grad_norm": 1.3449392178558885,
"learning_rate": 1.8729290708206412e-05,
"loss": 1.1768,
"step": 400
},
{
"epoch": 0.24938423645320196,
"grad_norm": 1.3192643823753003,
"learning_rate": 1.867633623354773e-05,
"loss": 1.1821,
"step": 405
},
{
"epoch": 0.2524630541871921,
"grad_norm": 1.43329928436646,
"learning_rate": 1.8622378826833186e-05,
"loss": 1.1717,
"step": 410
},
{
"epoch": 0.2555418719211823,
"grad_norm": 1.3986218108029622,
"learning_rate": 1.856742472521304e-05,
"loss": 1.1769,
"step": 415
},
{
"epoch": 0.25862068965517243,
"grad_norm": 1.4212946008912386,
"learning_rate": 1.8511480281049475e-05,
"loss": 1.1582,
"step": 420
},
{
"epoch": 0.2616995073891626,
"grad_norm": 1.3262505168734555,
"learning_rate": 1.8454551961182276e-05,
"loss": 1.1359,
"step": 425
},
{
"epoch": 0.2647783251231527,
"grad_norm": 1.2763436042757645,
"learning_rate": 1.8396646346181327e-05,
"loss": 1.1515,
"step": 430
},
{
"epoch": 0.26785714285714285,
"grad_norm": 1.377828716119807,
"learning_rate": 1.8337770129585918e-05,
"loss": 1.2028,
"step": 435
},
{
"epoch": 0.270935960591133,
"grad_norm": 1.2691621787293876,
"learning_rate": 1.8277930117131025e-05,
"loss": 1.1953,
"step": 440
},
{
"epoch": 0.27401477832512317,
"grad_norm": 1.2890733806956751,
"learning_rate": 1.8217133225960597e-05,
"loss": 1.1223,
"step": 445
},
{
"epoch": 0.2770935960591133,
"grad_norm": 1.2488568388775438,
"learning_rate": 1.8155386483827995e-05,
"loss": 1.1517,
"step": 450
},
{
"epoch": 0.2801724137931034,
"grad_norm": 1.456423416411621,
"learning_rate": 1.8092697028283598e-05,
"loss": 1.146,
"step": 455
},
{
"epoch": 0.2832512315270936,
"grad_norm": 1.3277340164360807,
"learning_rate": 1.8029072105849767e-05,
"loss": 1.1332,
"step": 460
},
{
"epoch": 0.28633004926108374,
"grad_norm": 1.3626896440895009,
"learning_rate": 1.7964519071183188e-05,
"loss": 1.1487,
"step": 465
},
{
"epoch": 0.2894088669950739,
"grad_norm": 1.353461920463668,
"learning_rate": 1.789904538622471e-05,
"loss": 1.1471,
"step": 470
},
{
"epoch": 0.29248768472906406,
"grad_norm": 1.3532133561527293,
"learning_rate": 1.7832658619336794e-05,
"loss": 1.1755,
"step": 475
},
{
"epoch": 0.2955665024630542,
"grad_norm": 1.1794679443199467,
"learning_rate": 1.7765366444428655e-05,
"loss": 1.1514,
"step": 480
},
{
"epoch": 0.2986453201970443,
"grad_norm": 1.3481265374718707,
"learning_rate": 1.7697176640069217e-05,
"loss": 1.1099,
"step": 485
},
{
"epoch": 0.3017241379310345,
"grad_norm": 1.3327266633591084,
"learning_rate": 1.762809708858793e-05,
"loss": 1.1578,
"step": 490
},
{
"epoch": 0.30480295566502463,
"grad_norm": 1.3091186199590885,
"learning_rate": 1.7558135775163645e-05,
"loss": 1.1596,
"step": 495
},
{
"epoch": 0.3078817733990148,
"grad_norm": 1.343369051366129,
"learning_rate": 1.7487300786901568e-05,
"loss": 1.0686,
"step": 500
},
{
"epoch": 0.31096059113300495,
"grad_norm": 1.3538320494316356,
"learning_rate": 1.7415600311898436e-05,
"loss": 1.207,
"step": 505
},
{
"epoch": 0.31403940886699505,
"grad_norm": 1.3298775689771942,
"learning_rate": 1.734304263829602e-05,
"loss": 1.1691,
"step": 510
},
{
"epoch": 0.3171182266009852,
"grad_norm": 1.3589541179756608,
"learning_rate": 1.726963615332308e-05,
"loss": 1.2016,
"step": 515
},
{
"epoch": 0.32019704433497537,
"grad_norm": 1.3030410481127883,
"learning_rate": 1.7195389342325843e-05,
"loss": 1.1563,
"step": 520
},
{
"epoch": 0.3232758620689655,
"grad_norm": 1.2950296847883305,
"learning_rate": 1.7120310787787136e-05,
"loss": 1.1166,
"step": 525
},
{
"epoch": 0.3263546798029557,
"grad_norm": 1.3375676805552543,
"learning_rate": 1.7044409168334327e-05,
"loss": 1.1322,
"step": 530
},
{
"epoch": 0.3294334975369458,
"grad_norm": 1.2998873206460573,
"learning_rate": 1.696769325773611e-05,
"loss": 1.1129,
"step": 535
},
{
"epoch": 0.33251231527093594,
"grad_norm": 1.432713104848216,
"learning_rate": 1.6890171923888323e-05,
"loss": 1.1575,
"step": 540
},
{
"epoch": 0.3355911330049261,
"grad_norm": 1.2701927651923426,
"learning_rate": 1.6811854127788857e-05,
"loss": 1.2188,
"step": 545
},
{
"epoch": 0.33866995073891626,
"grad_norm": 1.2530170607893276,
"learning_rate": 1.6732748922501832e-05,
"loss": 1.2198,
"step": 550
},
{
"epoch": 0.3417487684729064,
"grad_norm": 1.2694258669502214,
"learning_rate": 1.6652865452111115e-05,
"loss": 1.1017,
"step": 555
},
{
"epoch": 0.3448275862068966,
"grad_norm": 1.3140587238035317,
"learning_rate": 1.657221295066332e-05,
"loss": 1.1666,
"step": 560
},
{
"epoch": 0.3479064039408867,
"grad_norm": 1.2619627249826628,
"learning_rate": 1.6490800741100396e-05,
"loss": 1.161,
"step": 565
},
{
"epoch": 0.35098522167487683,
"grad_norm": 1.3052363327624088,
"learning_rate": 1.6408638234181975e-05,
"loss": 1.1652,
"step": 570
},
{
"epoch": 0.354064039408867,
"grad_norm": 1.2738806799741185,
"learning_rate": 1.6325734927397514e-05,
"loss": 1.1426,
"step": 575
},
{
"epoch": 0.35714285714285715,
"grad_norm": 1.2395283626467042,
"learning_rate": 1.6242100403868472e-05,
"loss": 1.1432,
"step": 580
},
{
"epoch": 0.3602216748768473,
"grad_norm": 1.261677505047024,
"learning_rate": 1.615774433124054e-05,
"loss": 1.1285,
"step": 585
},
{
"epoch": 0.3633004926108374,
"grad_norm": 1.3095599835308926,
"learning_rate": 1.6072676460566136e-05,
"loss": 1.1548,
"step": 590
},
{
"epoch": 0.36637931034482757,
"grad_norm": 1.3707313897818,
"learning_rate": 1.5986906625177215e-05,
"loss": 1.1591,
"step": 595
},
{
"epoch": 0.3694581280788177,
"grad_norm": 1.304158441425243,
"learning_rate": 1.590044473954863e-05,
"loss": 1.2408,
"step": 600
},
{
"epoch": 0.3725369458128079,
"grad_norm": 1.2783114563405087,
"learning_rate": 1.5813300798152048e-05,
"loss": 1.1431,
"step": 605
},
{
"epoch": 0.37561576354679804,
"grad_norm": 1.2046312747773318,
"learning_rate": 1.5725484874300673e-05,
"loss": 1.1911,
"step": 610
},
{
"epoch": 0.3786945812807882,
"grad_norm": 1.367014173840811,
"learning_rate": 1.5637007118984814e-05,
"loss": 1.1635,
"step": 615
},
{
"epoch": 0.3817733990147783,
"grad_norm": 1.2858333743911394,
"learning_rate": 1.5547877759698498e-05,
"loss": 1.1625,
"step": 620
},
{
"epoch": 0.38485221674876846,
"grad_norm": 1.32869847720412,
"learning_rate": 1.5458107099257245e-05,
"loss": 1.1637,
"step": 625
},
{
"epoch": 0.3879310344827586,
"grad_norm": 1.3314037816161812,
"learning_rate": 1.5367705514607107e-05,
"loss": 1.1257,
"step": 630
},
{
"epoch": 0.3910098522167488,
"grad_norm": 1.3958490034015343,
"learning_rate": 1.527668345562516e-05,
"loss": 1.1316,
"step": 635
},
{
"epoch": 0.39408866995073893,
"grad_norm": 1.3855454169954289,
"learning_rate": 1.518505144391157e-05,
"loss": 1.1457,
"step": 640
},
{
"epoch": 0.39716748768472904,
"grad_norm": 1.4409699509040352,
"learning_rate": 1.5092820071573358e-05,
"loss": 1.1766,
"step": 645
},
{
"epoch": 0.4002463054187192,
"grad_norm": 1.3805435581242091,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.1466,
"step": 650
},
{
"epoch": 0.40332512315270935,
"grad_norm": 1.258410154020486,
"learning_rate": 1.490660195863106e-05,
"loss": 1.1181,
"step": 655
},
{
"epoch": 0.4064039408866995,
"grad_norm": 1.3599583985040797,
"learning_rate": 1.4812636743715912e-05,
"loss": 1.1226,
"step": 660
},
{
"epoch": 0.40948275862068967,
"grad_norm": 1.3240223097430759,
"learning_rate": 1.4718115217065766e-05,
"loss": 1.1616,
"step": 665
},
{
"epoch": 0.4125615763546798,
"grad_norm": 1.320273903835114,
"learning_rate": 1.462304830479811e-05,
"loss": 1.1094,
"step": 670
},
{
"epoch": 0.41564039408866993,
"grad_norm": 1.418496119977967,
"learning_rate": 1.4527446996073714e-05,
"loss": 1.1232,
"step": 675
},
{
"epoch": 0.4187192118226601,
"grad_norm": 1.2866030168232347,
"learning_rate": 1.4431322341826348e-05,
"loss": 1.1243,
"step": 680
},
{
"epoch": 0.42179802955665024,
"grad_norm": 1.313619018978023,
"learning_rate": 1.433468545348537e-05,
"loss": 1.1389,
"step": 685
},
{
"epoch": 0.4248768472906404,
"grad_norm": 1.2623905134078022,
"learning_rate": 1.4237547501691298e-05,
"loss": 1.1593,
"step": 690
},
{
"epoch": 0.42795566502463056,
"grad_norm": 1.3011545400372815,
"learning_rate": 1.4139919715004558e-05,
"loss": 1.1421,
"step": 695
},
{
"epoch": 0.43103448275862066,
"grad_norm": 1.3545316007587846,
"learning_rate": 1.4041813378607534e-05,
"loss": 1.1754,
"step": 700
},
{
"epoch": 0.4341133004926108,
"grad_norm": 1.3242562674990255,
"learning_rate": 1.3943239833000068e-05,
"loss": 1.1271,
"step": 705
},
{
"epoch": 0.437192118226601,
"grad_norm": 1.2767814196083729,
"learning_rate": 1.3844210472688557e-05,
"loss": 1.1199,
"step": 710
},
{
"epoch": 0.44027093596059114,
"grad_norm": 1.2182482932495882,
"learning_rate": 1.3744736744868832e-05,
"loss": 1.1254,
"step": 715
},
{
"epoch": 0.4433497536945813,
"grad_norm": 1.3375635761172409,
"learning_rate": 1.3644830148102915e-05,
"loss": 1.1866,
"step": 720
},
{
"epoch": 0.44642857142857145,
"grad_norm": 1.3255110997199386,
"learning_rate": 1.3544502230989868e-05,
"loss": 1.1503,
"step": 725
},
{
"epoch": 0.44950738916256155,
"grad_norm": 1.3147779635175787,
"learning_rate": 1.344376459083085e-05,
"loss": 1.1439,
"step": 730
},
{
"epoch": 0.4525862068965517,
"grad_norm": 1.4126847330769359,
"learning_rate": 1.3342628872288505e-05,
"loss": 1.1511,
"step": 735
},
{
"epoch": 0.45566502463054187,
"grad_norm": 1.254147390978192,
"learning_rate": 1.3241106766040957e-05,
"loss": 1.1124,
"step": 740
},
{
"epoch": 0.45874384236453203,
"grad_norm": 1.4158462283508406,
"learning_rate": 1.3139210007430404e-05,
"loss": 1.1268,
"step": 745
},
{
"epoch": 0.4618226600985222,
"grad_norm": 1.274295549864427,
"learning_rate": 1.3036950375106588e-05,
"loss": 1.1433,
"step": 750
},
{
"epoch": 0.4649014778325123,
"grad_norm": 1.2617430933700238,
"learning_rate": 1.2934339689665274e-05,
"loss": 1.1146,
"step": 755
},
{
"epoch": 0.46798029556650245,
"grad_norm": 1.3487276664804204,
"learning_rate": 1.283138981228184e-05,
"loss": 1.1449,
"step": 760
},
{
"epoch": 0.4710591133004926,
"grad_norm": 1.3409891428205658,
"learning_rate": 1.2728112643340201e-05,
"loss": 1.1493,
"step": 765
},
{
"epoch": 0.47413793103448276,
"grad_norm": 1.396899876425411,
"learning_rate": 1.26245201210572e-05,
"loss": 1.1271,
"step": 770
},
{
"epoch": 0.4772167487684729,
"grad_norm": 1.429878812227924,
"learning_rate": 1.2520624220102623e-05,
"loss": 1.147,
"step": 775
},
{
"epoch": 0.4802955665024631,
"grad_norm": 1.3680994340445878,
"learning_rate": 1.2416436950215001e-05,
"loss": 1.1549,
"step": 780
},
{
"epoch": 0.4833743842364532,
"grad_norm": 1.2809126976073921,
"learning_rate": 1.2311970354813345e-05,
"loss": 1.2296,
"step": 785
},
{
"epoch": 0.48645320197044334,
"grad_norm": 1.209841084988838,
"learning_rate": 1.220723650960502e-05,
"loss": 1.1269,
"step": 790
},
{
"epoch": 0.4895320197044335,
"grad_norm": 1.2683644324398295,
"learning_rate": 1.2102247521189838e-05,
"loss": 1.0921,
"step": 795
},
{
"epoch": 0.49261083743842365,
"grad_norm": 1.306364653386113,
"learning_rate": 1.199701552566064e-05,
"loss": 1.0953,
"step": 800
},
{
"epoch": 0.4956896551724138,
"grad_norm": 1.3446345064790628,
"learning_rate": 1.1891552687200414e-05,
"loss": 1.1815,
"step": 805
},
{
"epoch": 0.4987684729064039,
"grad_norm": 1.3760124296089344,
"learning_rate": 1.1785871196676196e-05,
"loss": 1.1991,
"step": 810
},
{
"epoch": 0.5018472906403941,
"grad_norm": 1.2989820511942007,
"learning_rate": 1.167998327022988e-05,
"loss": 1.2196,
"step": 815
},
{
"epoch": 0.5049261083743842,
"grad_norm": 1.2890262471345426,
"learning_rate": 1.1573901147866108e-05,
"loss": 1.1493,
"step": 820
},
{
"epoch": 0.5080049261083743,
"grad_norm": 1.3054232367226282,
"learning_rate": 1.1467637092037399e-05,
"loss": 1.1379,
"step": 825
},
{
"epoch": 0.5110837438423645,
"grad_norm": 1.2806067738215097,
"learning_rate": 1.1361203386226672e-05,
"loss": 1.1524,
"step": 830
},
{
"epoch": 0.5141625615763546,
"grad_norm": 1.3015064241753111,
"learning_rate": 1.1254612333527368e-05,
"loss": 1.1174,
"step": 835
},
{
"epoch": 0.5172413793103449,
"grad_norm": 1.2635037770276025,
"learning_rate": 1.1147876255221274e-05,
"loss": 1.1233,
"step": 840
},
{
"epoch": 0.520320197044335,
"grad_norm": 1.270876589703383,
"learning_rate": 1.1041007489354263e-05,
"loss": 1.1291,
"step": 845
},
{
"epoch": 0.5233990147783252,
"grad_norm": 1.2326128326003456,
"learning_rate": 1.093401838931009e-05,
"loss": 1.1404,
"step": 850
},
{
"epoch": 0.5264778325123153,
"grad_norm": 1.3292619486036605,
"learning_rate": 1.0826921322382407e-05,
"loss": 1.1366,
"step": 855
},
{
"epoch": 0.5295566502463054,
"grad_norm": 1.2922766694260241,
"learning_rate": 1.071972866834519e-05,
"loss": 1.07,
"step": 860
},
{
"epoch": 0.5326354679802956,
"grad_norm": 1.4629130522623432,
"learning_rate": 1.061245281802171e-05,
"loss": 1.1534,
"step": 865
},
{
"epoch": 0.5357142857142857,
"grad_norm": 1.4400653335991853,
"learning_rate": 1.0505106171852226e-05,
"loss": 1.0382,
"step": 870
},
{
"epoch": 0.5387931034482759,
"grad_norm": 1.4164366840619265,
"learning_rate": 1.039770113846056e-05,
"loss": 1.0858,
"step": 875
},
{
"epoch": 0.541871921182266,
"grad_norm": 1.3420773596241813,
"learning_rate": 1.0290250133219755e-05,
"loss": 1.1358,
"step": 880
},
{
"epoch": 0.5449507389162561,
"grad_norm": 1.381323881479654,
"learning_rate": 1.0182765576816916e-05,
"loss": 1.1936,
"step": 885
},
{
"epoch": 0.5480295566502463,
"grad_norm": 1.3077141979409566,
"learning_rate": 1.0075259893817465e-05,
"loss": 1.13,
"step": 890
},
{
"epoch": 0.5511083743842364,
"grad_norm": 1.2785692163195586,
"learning_rate": 9.967745511228922e-06,
"loss": 1.1013,
"step": 895
},
{
"epoch": 0.5541871921182266,
"grad_norm": 1.3238887266787467,
"learning_rate": 9.860234857064439e-06,
"loss": 1.1446,
"step": 900
},
{
"epoch": 0.5572660098522167,
"grad_norm": 1.2552475687020934,
"learning_rate": 9.752740358906168e-06,
"loss": 1.1467,
"step": 905
},
{
"epoch": 0.5603448275862069,
"grad_norm": 1.2859353975505403,
"learning_rate": 9.645274442468746e-06,
"loss": 1.1304,
"step": 910
},
{
"epoch": 0.5634236453201971,
"grad_norm": 1.32103468322843,
"learning_rate": 9.537849530162915e-06,
"loss": 1.1401,
"step": 915
},
{
"epoch": 0.5665024630541872,
"grad_norm": 1.2858854472176375,
"learning_rate": 9.430478039659604e-06,
"loss": 1.1225,
"step": 920
},
{
"epoch": 0.5695812807881774,
"grad_norm": 1.2241957927318483,
"learning_rate": 9.323172382454494e-06,
"loss": 1.1406,
"step": 925
},
{
"epoch": 0.5726600985221675,
"grad_norm": 1.3106424840021706,
"learning_rate": 9.215944962433329e-06,
"loss": 1.0716,
"step": 930
},
{
"epoch": 0.5757389162561576,
"grad_norm": 1.328991291258751,
"learning_rate": 9.108808174438128e-06,
"loss": 1.1526,
"step": 935
},
{
"epoch": 0.5788177339901478,
"grad_norm": 1.3253858882816794,
"learning_rate": 9.001774402834375e-06,
"loss": 1.0938,
"step": 940
},
{
"epoch": 0.5818965517241379,
"grad_norm": 1.3790143198853229,
"learning_rate": 8.89485602007949e-06,
"loss": 1.1491,
"step": 945
},
{
"epoch": 0.5849753694581281,
"grad_norm": 1.3721437129378793,
"learning_rate": 8.788065385292637e-06,
"loss": 1.1179,
"step": 950
},
{
"epoch": 0.5880541871921182,
"grad_norm": 1.2943447448922103,
"learning_rate": 8.68141484282609e-06,
"loss": 1.1475,
"step": 955
},
{
"epoch": 0.5911330049261084,
"grad_norm": 1.3915814263361685,
"learning_rate": 8.574916720838293e-06,
"loss": 1.1644,
"step": 960
},
{
"epoch": 0.5942118226600985,
"grad_norm": 1.3017011476050018,
"learning_rate": 8.468583329868805e-06,
"loss": 1.1538,
"step": 965
},
{
"epoch": 0.5972906403940886,
"grad_norm": 1.287037501496803,
"learning_rate": 8.362426961415274e-06,
"loss": 1.1395,
"step": 970
},
{
"epoch": 0.6003694581280788,
"grad_norm": 1.3072112443673463,
"learning_rate": 8.256459886512618e-06,
"loss": 1.1094,
"step": 975
},
{
"epoch": 0.603448275862069,
"grad_norm": 1.408104215539221,
"learning_rate": 8.150694354314556e-06,
"loss": 1.1805,
"step": 980
},
{
"epoch": 0.6065270935960592,
"grad_norm": 1.3830598239190213,
"learning_rate": 8.0451425906777e-06,
"loss": 1.1419,
"step": 985
},
{
"epoch": 0.6096059113300493,
"grad_norm": 1.2057457849631292,
"learning_rate": 7.939816796748296e-06,
"loss": 1.0916,
"step": 990
},
{
"epoch": 0.6126847290640394,
"grad_norm": 1.3321325020127246,
"learning_rate": 7.834729147551858e-06,
"loss": 1.1271,
"step": 995
},
{
"epoch": 0.6157635467980296,
"grad_norm": 1.2877038575950586,
"learning_rate": 7.729891790585817e-06,
"loss": 1.0773,
"step": 1000
},
{
"epoch": 0.6188423645320197,
"grad_norm": 1.4054501190801973,
"learning_rate": 7.625316844415327e-06,
"loss": 1.0729,
"step": 1005
},
{
"epoch": 0.6219211822660099,
"grad_norm": 1.2921416659706961,
"learning_rate": 7.521016397272436e-06,
"loss": 1.1236,
"step": 1010
},
{
"epoch": 0.625,
"grad_norm": 1.3554922588061638,
"learning_rate": 7.417002505658773e-06,
"loss": 1.1804,
"step": 1015
},
{
"epoch": 0.6280788177339901,
"grad_norm": 1.296529696491134,
"learning_rate": 7.313287192951866e-06,
"loss": 1.1374,
"step": 1020
},
{
"epoch": 0.6311576354679803,
"grad_norm": 1.416220009991982,
"learning_rate": 7.209882448015338e-06,
"loss": 1.1017,
"step": 1025
},
{
"epoch": 0.6342364532019704,
"grad_norm": 1.3604817265594524,
"learning_rate": 7.1068002238130465e-06,
"loss": 1.1288,
"step": 1030
},
{
"epoch": 0.6373152709359606,
"grad_norm": 1.4123360866519081,
"learning_rate": 7.004052436027397e-06,
"loss": 1.1167,
"step": 1035
},
{
"epoch": 0.6403940886699507,
"grad_norm": 1.2979806063416062,
"learning_rate": 6.901650961681976e-06,
"loss": 1.109,
"step": 1040
},
{
"epoch": 0.6434729064039408,
"grad_norm": 1.321344828264406,
"learning_rate": 6.799607637768621e-06,
"loss": 1.1232,
"step": 1045
},
{
"epoch": 0.646551724137931,
"grad_norm": 1.2905339687653805,
"learning_rate": 6.6979342598791395e-06,
"loss": 1.136,
"step": 1050
},
{
"epoch": 0.6496305418719212,
"grad_norm": 1.3460491626773499,
"learning_rate": 6.596642580841827e-06,
"loss": 1.1256,
"step": 1055
},
{
"epoch": 0.6527093596059114,
"grad_norm": 1.3726870557489323,
"learning_rate": 6.495744309362879e-06,
"loss": 1.0699,
"step": 1060
},
{
"epoch": 0.6557881773399015,
"grad_norm": 1.3758389788756697,
"learning_rate": 6.395251108672975e-06,
"loss": 1.1103,
"step": 1065
},
{
"epoch": 0.6588669950738916,
"grad_norm": 1.3175150669018996,
"learning_rate": 6.295174595179041e-06,
"loss": 1.1358,
"step": 1070
},
{
"epoch": 0.6619458128078818,
"grad_norm": 1.4440557594832506,
"learning_rate": 6.195526337121483e-06,
"loss": 1.1512,
"step": 1075
},
{
"epoch": 0.6650246305418719,
"grad_norm": 1.281223834271699,
"learning_rate": 6.096317853236975e-06,
"loss": 1.0488,
"step": 1080
},
{
"epoch": 0.6681034482758621,
"grad_norm": 1.3333895815375059,
"learning_rate": 5.997560611426947e-06,
"loss": 1.1212,
"step": 1085
},
{
"epoch": 0.6711822660098522,
"grad_norm": 1.4835630149487085,
"learning_rate": 5.899266027431965e-06,
"loss": 1.1475,
"step": 1090
},
{
"epoch": 0.6742610837438424,
"grad_norm": 1.230014673818002,
"learning_rate": 5.80144546351216e-06,
"loss": 1.0823,
"step": 1095
},
{
"epoch": 0.6773399014778325,
"grad_norm": 1.3136599547563141,
"learning_rate": 5.704110227133792e-06,
"loss": 1.1297,
"step": 1100
},
{
"epoch": 0.6804187192118226,
"grad_norm": 1.2611655712992518,
"learning_rate": 5.607271569662203e-06,
"loss": 1.0927,
"step": 1105
},
{
"epoch": 0.6834975369458128,
"grad_norm": 1.4451863415503081,
"learning_rate": 5.510940685061202e-06,
"loss": 1.1057,
"step": 1110
},
{
"epoch": 0.6865763546798029,
"grad_norm": 1.4565340385055305,
"learning_rate": 5.41512870859912e-06,
"loss": 1.1273,
"step": 1115
},
{
"epoch": 0.6896551724137931,
"grad_norm": 1.4226838775615385,
"learning_rate": 5.319846715561656e-06,
"loss": 1.1299,
"step": 1120
},
{
"epoch": 0.6927339901477833,
"grad_norm": 1.2449361430783144,
"learning_rate": 5.225105719971615e-06,
"loss": 1.0771,
"step": 1125
},
{
"epoch": 0.6958128078817734,
"grad_norm": 1.299840433099715,
"learning_rate": 5.130916673315762e-06,
"loss": 1.1599,
"step": 1130
},
{
"epoch": 0.6988916256157636,
"grad_norm": 1.325763367304545,
"learning_rate": 5.037290463278914e-06,
"loss": 1.104,
"step": 1135
},
{
"epoch": 0.7019704433497537,
"grad_norm": 1.3159800243764521,
"learning_rate": 4.94423791248536e-06,
"loss": 1.1091,
"step": 1140
},
{
"epoch": 0.7050492610837439,
"grad_norm": 1.4388756613251896,
"learning_rate": 4.851769777247857e-06,
"loss": 1.2012,
"step": 1145
},
{
"epoch": 0.708128078817734,
"grad_norm": 1.4240341880057417,
"learning_rate": 4.759896746324247e-06,
"loss": 1.1099,
"step": 1150
},
{
"epoch": 0.7112068965517241,
"grad_norm": 1.3713971334200277,
"learning_rate": 4.668629439681907e-06,
"loss": 1.1195,
"step": 1155
},
{
"epoch": 0.7142857142857143,
"grad_norm": 1.2767083656729454,
"learning_rate": 4.577978407270156e-06,
"loss": 1.1317,
"step": 1160
},
{
"epoch": 0.7173645320197044,
"grad_norm": 1.2774492120994825,
"learning_rate": 4.487954127800726e-06,
"loss": 1.0908,
"step": 1165
},
{
"epoch": 0.7204433497536946,
"grad_norm": 1.2591069594941473,
"learning_rate": 4.398567007536493e-06,
"loss": 1.1902,
"step": 1170
},
{
"epoch": 0.7235221674876847,
"grad_norm": 1.2590486720856533,
"learning_rate": 4.309827379088589e-06,
"loss": 1.1163,
"step": 1175
},
{
"epoch": 0.7266009852216748,
"grad_norm": 1.3229608109306659,
"learning_rate": 4.221745500221992e-06,
"loss": 1.0584,
"step": 1180
},
{
"epoch": 0.729679802955665,
"grad_norm": 1.5928553391241416,
"learning_rate": 4.134331552669812e-06,
"loss": 1.1441,
"step": 1185
},
{
"epoch": 0.7327586206896551,
"grad_norm": 1.328577121937309,
"learning_rate": 4.047595640956326e-06,
"loss": 1.1444,
"step": 1190
},
{
"epoch": 0.7358374384236454,
"grad_norm": 1.3216973125656395,
"learning_rate": 3.961547791228963e-06,
"loss": 1.0847,
"step": 1195
},
{
"epoch": 0.7389162561576355,
"grad_norm": 1.2497367688774053,
"learning_rate": 3.876197950099351e-06,
"loss": 1.0938,
"step": 1200
},
{
"epoch": 0.7419950738916257,
"grad_norm": 1.2969534183302347,
"learning_rate": 3.7915559834935355e-06,
"loss": 1.1264,
"step": 1205
},
{
"epoch": 0.7450738916256158,
"grad_norm": 1.2888255017145755,
"learning_rate": 3.7076316755115407e-06,
"loss": 1.0919,
"step": 1210
},
{
"epoch": 0.7481527093596059,
"grad_norm": 1.3437937322158908,
"learning_rate": 3.6244347272963974e-06,
"loss": 1.119,
"step": 1215
},
{
"epoch": 0.7512315270935961,
"grad_norm": 1.3707001294679344,
"learning_rate": 3.5419747559127294e-06,
"loss": 1.1318,
"step": 1220
},
{
"epoch": 0.7543103448275862,
"grad_norm": 1.3169029187267667,
"learning_rate": 3.4602612932351065e-06,
"loss": 1.1566,
"step": 1225
},
{
"epoch": 0.7573891625615764,
"grad_norm": 1.3785753893627313,
"learning_rate": 3.3793037848461873e-06,
"loss": 1.1103,
"step": 1230
},
{
"epoch": 0.7604679802955665,
"grad_norm": 1.2854976969755878,
"learning_rate": 3.2991115889448877e-06,
"loss": 1.1125,
"step": 1235
},
{
"epoch": 0.7635467980295566,
"grad_norm": 1.386115922264563,
"learning_rate": 3.2196939752646183e-06,
"loss": 1.112,
"step": 1240
},
{
"epoch": 0.7666256157635468,
"grad_norm": 1.4217969530530246,
"learning_rate": 3.141060124001776e-06,
"loss": 1.106,
"step": 1245
},
{
"epoch": 0.7697044334975369,
"grad_norm": 1.3463870607034563,
"learning_rate": 3.063219124754543e-06,
"loss": 1.1164,
"step": 1250
},
{
"epoch": 0.7727832512315271,
"grad_norm": 1.2704802717810082,
"learning_rate": 2.9861799754722033e-06,
"loss": 1.0775,
"step": 1255
},
{
"epoch": 0.7758620689655172,
"grad_norm": 1.2428934201623616,
"learning_rate": 2.9099515814150335e-06,
"loss": 1.0712,
"step": 1260
},
{
"epoch": 0.7789408866995073,
"grad_norm": 1.3245232940496297,
"learning_rate": 2.8345427541248993e-06,
"loss": 1.066,
"step": 1265
},
{
"epoch": 0.7820197044334976,
"grad_norm": 1.2615403946597639,
"learning_rate": 2.7599622104066937e-06,
"loss": 1.1648,
"step": 1270
},
{
"epoch": 0.7850985221674877,
"grad_norm": 1.3450446471320252,
"learning_rate": 2.6862185713207467e-06,
"loss": 1.1253,
"step": 1275
},
{
"epoch": 0.7881773399014779,
"grad_norm": 1.4175912491637548,
"learning_rate": 2.6133203611862554e-06,
"loss": 1.1117,
"step": 1280
},
{
"epoch": 0.791256157635468,
"grad_norm": 1.2420986430781604,
"learning_rate": 2.5412760065959386e-06,
"loss": 1.0995,
"step": 1285
},
{
"epoch": 0.7943349753694581,
"grad_norm": 1.2331322964747684,
"learning_rate": 2.4700938354419823e-06,
"loss": 1.1189,
"step": 1290
},
{
"epoch": 0.7974137931034483,
"grad_norm": 1.3156048137819454,
"learning_rate": 2.3997820759533654e-06,
"loss": 1.1342,
"step": 1295
},
{
"epoch": 0.8004926108374384,
"grad_norm": 1.296980383500544,
"learning_rate": 2.3303488557447374e-06,
"loss": 1.0762,
"step": 1300
},
{
"epoch": 0.8035714285714286,
"grad_norm": 1.3056631965466725,
"learning_rate": 2.26180220087692e-06,
"loss": 1.0865,
"step": 1305
},
{
"epoch": 0.8066502463054187,
"grad_norm": 1.2759251600792525,
"learning_rate": 2.194150034929133e-06,
"loss": 1.1162,
"step": 1310
},
{
"epoch": 0.8097290640394089,
"grad_norm": 1.374917359433893,
"learning_rate": 2.1274001780830776e-06,
"loss": 1.1325,
"step": 1315
},
{
"epoch": 0.812807881773399,
"grad_norm": 1.3441860512142203,
"learning_rate": 2.0615603462189824e-06,
"loss": 1.1439,
"step": 1320
},
{
"epoch": 0.8158866995073891,
"grad_norm": 1.2999627128748281,
"learning_rate": 1.9966381500236786e-06,
"loss": 1.0659,
"step": 1325
},
{
"epoch": 0.8189655172413793,
"grad_norm": 1.2690343751495285,
"learning_rate": 1.932641094110855e-06,
"loss": 1.0931,
"step": 1330
},
{
"epoch": 0.8220443349753694,
"grad_norm": 1.2722769348686476,
"learning_rate": 1.869576576153581e-06,
"loss": 1.0564,
"step": 1335
},
{
"epoch": 0.8251231527093597,
"grad_norm": 1.3627851683060783,
"learning_rate": 1.8074518860291646e-06,
"loss": 1.0904,
"step": 1340
},
{
"epoch": 0.8282019704433498,
"grad_norm": 1.3627422340762019,
"learning_rate": 1.746274204976498e-06,
"loss": 1.0968,
"step": 1345
},
{
"epoch": 0.8312807881773399,
"grad_norm": 1.2824262409067282,
"learning_rate": 1.6860506047659442e-06,
"loss": 1.1176,
"step": 1350
},
{
"epoch": 0.8343596059113301,
"grad_norm": 1.3498021119986188,
"learning_rate": 1.6267880468818787e-06,
"loss": 1.0863,
"step": 1355
},
{
"epoch": 0.8374384236453202,
"grad_norm": 1.349956446072757,
"learning_rate": 1.5684933817180014e-06,
"loss": 1.1216,
"step": 1360
},
{
"epoch": 0.8405172413793104,
"grad_norm": 1.3740555135252106,
"learning_rate": 1.5111733477854507e-06,
"loss": 1.1322,
"step": 1365
},
{
"epoch": 0.8435960591133005,
"grad_norm": 1.3102500704390403,
"learning_rate": 1.454834570933884e-06,
"loss": 1.0826,
"step": 1370
},
{
"epoch": 0.8466748768472906,
"grad_norm": 1.272586749536124,
"learning_rate": 1.399483563585573e-06,
"loss": 1.1171,
"step": 1375
},
{
"epoch": 0.8497536945812808,
"grad_norm": 1.4836760966376439,
"learning_rate": 1.345126723982594e-06,
"loss": 1.1857,
"step": 1380
},
{
"epoch": 0.8528325123152709,
"grad_norm": 1.3482035708833353,
"learning_rate": 1.2917703354472467e-06,
"loss": 1.1074,
"step": 1385
},
{
"epoch": 0.8559113300492611,
"grad_norm": 1.355149283773509,
"learning_rate": 1.2394205656557224e-06,
"loss": 1.0836,
"step": 1390
},
{
"epoch": 0.8589901477832512,
"grad_norm": 1.323566791186568,
"learning_rate": 1.1880834659251706e-06,
"loss": 1.1157,
"step": 1395
},
{
"epoch": 0.8620689655172413,
"grad_norm": 1.4462161132960698,
"learning_rate": 1.1377649705142012e-06,
"loss": 1.1163,
"step": 1400
},
{
"epoch": 0.8651477832512315,
"grad_norm": 1.4448546922620082,
"learning_rate": 1.0884708959369116e-06,
"loss": 1.1441,
"step": 1405
},
{
"epoch": 0.8682266009852216,
"grad_norm": 1.2936989849146427,
"learning_rate": 1.040206940290547e-06,
"loss": 1.0836,
"step": 1410
},
{
"epoch": 0.8713054187192119,
"grad_norm": 1.283611703847481,
"learning_rate": 9.929786825968213e-07,
"loss": 1.0859,
"step": 1415
},
{
"epoch": 0.874384236453202,
"grad_norm": 1.4322555134363704,
"learning_rate": 9.467915821570228e-07,
"loss": 1.1374,
"step": 1420
},
{
"epoch": 0.8774630541871922,
"grad_norm": 1.4264653346915517,
"learning_rate": 9.016509779209536e-07,
"loss": 1.1195,
"step": 1425
},
{
"epoch": 0.8805418719211823,
"grad_norm": 1.4399702434613786,
"learning_rate": 8.575620878697744e-07,
"loss": 1.08,
"step": 1430
},
{
"epoch": 0.8836206896551724,
"grad_norm": 1.3702090260449458,
"learning_rate": 8.145300084128349e-07,
"loss": 1.113,
"step": 1435
},
{
"epoch": 0.8866995073891626,
"grad_norm": 1.2366588204382565,
"learning_rate": 7.725597137985741e-07,
"loss": 1.0509,
"step": 1440
},
{
"epoch": 0.8897783251231527,
"grad_norm": 1.3532028078851,
"learning_rate": 7.316560555395069e-07,
"loss": 1.0742,
"step": 1445
},
{
"epoch": 0.8928571428571429,
"grad_norm": 1.285598415438746,
"learning_rate": 6.918237618514378e-07,
"loss": 1.0441,
"step": 1450
},
{
"epoch": 0.895935960591133,
"grad_norm": 1.30480133206637,
"learning_rate": 6.530674371068946e-07,
"loss": 1.1074,
"step": 1455
},
{
"epoch": 0.8990147783251231,
"grad_norm": 1.3640691838430612,
"learning_rate": 6.153915613028915e-07,
"loss": 1.1027,
"step": 1460
},
{
"epoch": 0.9020935960591133,
"grad_norm": 1.3291237725111644,
"learning_rate": 5.788004895430799e-07,
"loss": 1.0488,
"step": 1465
},
{
"epoch": 0.9051724137931034,
"grad_norm": 1.329762383974551,
"learning_rate": 5.43298451534312e-07,
"loss": 1.1452,
"step": 1470
},
{
"epoch": 0.9082512315270936,
"grad_norm": 1.337920093671748,
"learning_rate": 5.088895510977154e-07,
"loss": 1.0958,
"step": 1475
},
{
"epoch": 0.9113300492610837,
"grad_norm": 1.2966510834150082,
"learning_rate": 4.755777656943239e-07,
"loss": 1.1257,
"step": 1480
},
{
"epoch": 0.9144088669950738,
"grad_norm": 1.4498065494325396,
"learning_rate": 4.433669459652945e-07,
"loss": 1.0895,
"step": 1485
},
{
"epoch": 0.9174876847290641,
"grad_norm": 1.249200941643704,
"learning_rate": 4.1226081528680907e-07,
"loss": 1.1332,
"step": 1490
},
{
"epoch": 0.9205665024630542,
"grad_norm": 1.2595324166325088,
"learning_rate": 3.822629693396651e-07,
"loss": 1.0756,
"step": 1495
},
{
"epoch": 0.9236453201970444,
"grad_norm": 1.3613529920399665,
"learning_rate": 3.5337687569363734e-07,
"loss": 1.1334,
"step": 1500
},
{
"epoch": 0.9267241379310345,
"grad_norm": 1.3694156656575291,
"learning_rate": 3.2560587340665694e-07,
"loss": 1.1134,
"step": 1505
},
{
"epoch": 0.9298029556650246,
"grad_norm": 1.3425947934510352,
"learning_rate": 2.989531726388262e-07,
"loss": 1.1239,
"step": 1510
},
{
"epoch": 0.9328817733990148,
"grad_norm": 1.4174292077173756,
"learning_rate": 2.7342185428134604e-07,
"loss": 1.1221,
"step": 1515
},
{
"epoch": 0.9359605911330049,
"grad_norm": 1.2708583874949022,
"learning_rate": 2.4901486960039025e-07,
"loss": 1.1252,
"step": 1520
},
{
"epoch": 0.9390394088669951,
"grad_norm": 1.4025330356521701,
"learning_rate": 2.257350398959457e-07,
"loss": 1.0903,
"step": 1525
},
{
"epoch": 0.9421182266009852,
"grad_norm": 1.3353735923841465,
"learning_rate": 2.035850561756969e-07,
"loss": 1.1067,
"step": 1530
},
{
"epoch": 0.9451970443349754,
"grad_norm": 1.3391632129899467,
"learning_rate": 1.8256747884395577e-07,
"loss": 1.0972,
"step": 1535
},
{
"epoch": 0.9482758620689655,
"grad_norm": 1.336567520533369,
"learning_rate": 1.6268473740569723e-07,
"loss": 1.1908,
"step": 1540
},
{
"epoch": 0.9513546798029556,
"grad_norm": 1.3566300674572158,
"learning_rate": 1.4393913018572182e-07,
"loss": 1.0788,
"step": 1545
},
{
"epoch": 0.9544334975369458,
"grad_norm": 1.223524275093064,
"learning_rate": 1.2633282406298576e-07,
"loss": 1.1057,
"step": 1550
},
{
"epoch": 0.9575123152709359,
"grad_norm": 1.2282578810027194,
"learning_rate": 1.0986785422011593e-07,
"loss": 1.089,
"step": 1555
},
{
"epoch": 0.9605911330049262,
"grad_norm": 1.2477091366362096,
"learning_rate": 9.454612390816686e-08,
"loss": 1.0838,
"step": 1560
},
{
"epoch": 0.9636699507389163,
"grad_norm": 1.3175417353825196,
"learning_rate": 8.036940422660345e-08,
"loss": 1.1123,
"step": 1565
},
{
"epoch": 0.9667487684729064,
"grad_norm": 1.3729214986835607,
"learning_rate": 6.733933391858238e-08,
"loss": 1.1551,
"step": 1570
},
{
"epoch": 0.9698275862068966,
"grad_norm": 1.3235847896472202,
"learning_rate": 5.5457419181517145e-08,
"loss": 1.0947,
"step": 1575
},
{
"epoch": 0.9729064039408867,
"grad_norm": 1.2984893843749021,
"learning_rate": 4.472503349297497e-08,
"loss": 1.0559,
"step": 1580
},
{
"epoch": 0.9759852216748769,
"grad_norm": 1.297332656769399,
"learning_rate": 3.5143417451907195e-08,
"loss": 1.0677,
"step": 1585
},
{
"epoch": 0.979064039408867,
"grad_norm": 1.3589263123092756,
"learning_rate": 2.671367863524732e-08,
"loss": 1.1204,
"step": 1590
},
{
"epoch": 0.9821428571428571,
"grad_norm": 1.422246690168639,
"learning_rate": 1.943679146988009e-08,
"loss": 1.1374,
"step": 1595
},
{
"epoch": 0.9852216748768473,
"grad_norm": 1.3762281122078426,
"learning_rate": 1.3313597120002686e-08,
"loss": 1.1351,
"step": 1600
},
{
"epoch": 0.9883004926108374,
"grad_norm": 1.389119763370901,
"learning_rate": 8.34480338989141e-09,
"loss": 1.1496,
"step": 1605
},
{
"epoch": 0.9913793103448276,
"grad_norm": 1.2544988696586423,
"learning_rate": 4.530984642087122e-09,
"loss": 1.0332,
"step": 1610
},
{
"epoch": 0.9944581280788177,
"grad_norm": 1.2791538354318839,
"learning_rate": 1.872581730997247e-09,
"loss": 1.139,
"step": 1615
},
{
"epoch": 0.9975369458128078,
"grad_norm": 1.3493508593866985,
"learning_rate": 3.699019519387559e-10,
"loss": 1.0511,
"step": 1620
},
{
"epoch": 1.0,
"eval_loss": 1.104846477508545,
"eval_runtime": 955.5882,
"eval_samples_per_second": 24.183,
"eval_steps_per_second": 0.757,
"step": 1624
},
{
"epoch": 1.0,
"step": 1624,
"total_flos": 106409733357568.0,
"train_loss": 1.1280937663146429,
"train_runtime": 11413.2571,
"train_samples_per_second": 4.553,
"train_steps_per_second": 0.142
}
],
"logging_steps": 5,
"max_steps": 1624,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 106409733357568.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}