delarosajav95's picture
Upload folder using huggingface_hub
7ea357f verified
{
"best_metric": 0.5626052618026733,
"best_model_checkpoint": "/content/drive/MyDrive/tw-roberta-base-sentiment-FT-v2/checkpoint-2603",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 2603,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00384172109104879,
"grad_norm": 19.648235321044922,
"learning_rate": 1.2195121951219514e-07,
"loss": 0.7091,
"step": 10
},
{
"epoch": 0.00768344218209758,
"grad_norm": 15.138011932373047,
"learning_rate": 2.439024390243903e-07,
"loss": 0.5428,
"step": 20
},
{
"epoch": 0.01152516327314637,
"grad_norm": 15.91871452331543,
"learning_rate": 3.6585365853658536e-07,
"loss": 0.709,
"step": 30
},
{
"epoch": 0.01536688436419516,
"grad_norm": 11.673059463500977,
"learning_rate": 4.878048780487805e-07,
"loss": 0.6269,
"step": 40
},
{
"epoch": 0.01920860545524395,
"grad_norm": 10.827598571777344,
"learning_rate": 6.097560975609757e-07,
"loss": 0.6899,
"step": 50
},
{
"epoch": 0.02305032654629274,
"grad_norm": 29.76123809814453,
"learning_rate": 7.317073170731707e-07,
"loss": 0.7235,
"step": 60
},
{
"epoch": 0.02689204763734153,
"grad_norm": 16.770448684692383,
"learning_rate": 8.53658536585366e-07,
"loss": 0.731,
"step": 70
},
{
"epoch": 0.03073376872839032,
"grad_norm": 17.501832962036133,
"learning_rate": 9.75609756097561e-07,
"loss": 0.7907,
"step": 80
},
{
"epoch": 0.03457548981943911,
"grad_norm": 5.903749465942383,
"learning_rate": 1.0975609756097562e-06,
"loss": 0.6549,
"step": 90
},
{
"epoch": 0.0384172109104879,
"grad_norm": 12.823253631591797,
"learning_rate": 1.2195121951219514e-06,
"loss": 0.6833,
"step": 100
},
{
"epoch": 0.042258932001536686,
"grad_norm": 14.516304969787598,
"learning_rate": 1.3414634146341465e-06,
"loss": 0.7764,
"step": 110
},
{
"epoch": 0.04610065309258548,
"grad_norm": 17.775850296020508,
"learning_rate": 1.4634146341463414e-06,
"loss": 0.6677,
"step": 120
},
{
"epoch": 0.049942374183634265,
"grad_norm": 16.348901748657227,
"learning_rate": 1.5853658536585368e-06,
"loss": 0.6708,
"step": 130
},
{
"epoch": 0.05378409527468306,
"grad_norm": 20.729867935180664,
"learning_rate": 1.707317073170732e-06,
"loss": 0.685,
"step": 140
},
{
"epoch": 0.05762581636573185,
"grad_norm": 23.60687255859375,
"learning_rate": 1.8292682926829268e-06,
"loss": 0.7048,
"step": 150
},
{
"epoch": 0.06146753745678064,
"grad_norm": 24.990461349487305,
"learning_rate": 1.951219512195122e-06,
"loss": 0.6849,
"step": 160
},
{
"epoch": 0.06530925854782943,
"grad_norm": 21.754741668701172,
"learning_rate": 2.073170731707317e-06,
"loss": 0.6801,
"step": 170
},
{
"epoch": 0.06915097963887822,
"grad_norm": 19.427799224853516,
"learning_rate": 2.1951219512195125e-06,
"loss": 0.6006,
"step": 180
},
{
"epoch": 0.072992700729927,
"grad_norm": 11.91465950012207,
"learning_rate": 2.317073170731708e-06,
"loss": 0.6498,
"step": 190
},
{
"epoch": 0.0768344218209758,
"grad_norm": 24.343521118164062,
"learning_rate": 2.4390243902439027e-06,
"loss": 0.8272,
"step": 200
},
{
"epoch": 0.08067614291202459,
"grad_norm": 11.623435020446777,
"learning_rate": 2.5609756097560977e-06,
"loss": 0.6703,
"step": 210
},
{
"epoch": 0.08451786400307337,
"grad_norm": 8.984451293945312,
"learning_rate": 2.682926829268293e-06,
"loss": 0.6965,
"step": 220
},
{
"epoch": 0.08835958509412217,
"grad_norm": 26.78940773010254,
"learning_rate": 2.8048780487804884e-06,
"loss": 0.7135,
"step": 230
},
{
"epoch": 0.09220130618517096,
"grad_norm": 17.50589370727539,
"learning_rate": 2.926829268292683e-06,
"loss": 0.6637,
"step": 240
},
{
"epoch": 0.09604302727621974,
"grad_norm": 13.149524688720703,
"learning_rate": 3.0487804878048782e-06,
"loss": 0.5756,
"step": 250
},
{
"epoch": 0.09988474836726853,
"grad_norm": 10.727895736694336,
"learning_rate": 3.1707317073170736e-06,
"loss": 0.594,
"step": 260
},
{
"epoch": 0.10372646945831733,
"grad_norm": 15.031158447265625,
"learning_rate": 3.292682926829269e-06,
"loss": 0.7186,
"step": 270
},
{
"epoch": 0.10756819054936612,
"grad_norm": 10.520498275756836,
"learning_rate": 3.414634146341464e-06,
"loss": 0.5746,
"step": 280
},
{
"epoch": 0.1114099116404149,
"grad_norm": 19.504133224487305,
"learning_rate": 3.5365853658536588e-06,
"loss": 0.7709,
"step": 290
},
{
"epoch": 0.1152516327314637,
"grad_norm": 12.495412826538086,
"learning_rate": 3.6585365853658537e-06,
"loss": 0.6508,
"step": 300
},
{
"epoch": 0.11909335382251249,
"grad_norm": 9.115503311157227,
"learning_rate": 3.780487804878049e-06,
"loss": 0.5847,
"step": 310
},
{
"epoch": 0.12293507491356127,
"grad_norm": 12.583561897277832,
"learning_rate": 3.902439024390244e-06,
"loss": 0.6114,
"step": 320
},
{
"epoch": 0.12677679600461006,
"grad_norm": 16.474716186523438,
"learning_rate": 4.024390243902439e-06,
"loss": 0.5819,
"step": 330
},
{
"epoch": 0.13061851709565886,
"grad_norm": 12.282912254333496,
"learning_rate": 4.146341463414634e-06,
"loss": 0.5974,
"step": 340
},
{
"epoch": 0.13446023818670763,
"grad_norm": 14.967294692993164,
"learning_rate": 4.268292682926829e-06,
"loss": 0.515,
"step": 350
},
{
"epoch": 0.13830195927775643,
"grad_norm": 22.999889373779297,
"learning_rate": 4.390243902439025e-06,
"loss": 0.8314,
"step": 360
},
{
"epoch": 0.14214368036880523,
"grad_norm": 13.173623085021973,
"learning_rate": 4.51219512195122e-06,
"loss": 0.7274,
"step": 370
},
{
"epoch": 0.145985401459854,
"grad_norm": 10.259631156921387,
"learning_rate": 4.634146341463416e-06,
"loss": 0.5758,
"step": 380
},
{
"epoch": 0.1498271225509028,
"grad_norm": 20.109394073486328,
"learning_rate": 4.75609756097561e-06,
"loss": 0.6767,
"step": 390
},
{
"epoch": 0.1536688436419516,
"grad_norm": 12.53744125366211,
"learning_rate": 4.8780487804878055e-06,
"loss": 0.6554,
"step": 400
},
{
"epoch": 0.15751056473300037,
"grad_norm": 32.90926742553711,
"learning_rate": 5e-06,
"loss": 0.751,
"step": 410
},
{
"epoch": 0.16135228582404917,
"grad_norm": 13.864742279052734,
"learning_rate": 5.121951219512195e-06,
"loss": 0.5644,
"step": 420
},
{
"epoch": 0.16519400691509797,
"grad_norm": 16.864086151123047,
"learning_rate": 5.243902439024391e-06,
"loss": 0.7212,
"step": 430
},
{
"epoch": 0.16903572800614675,
"grad_norm": 8.035212516784668,
"learning_rate": 5.365853658536586e-06,
"loss": 0.6411,
"step": 440
},
{
"epoch": 0.17287744909719555,
"grad_norm": 15.027800559997559,
"learning_rate": 5.487804878048781e-06,
"loss": 0.7331,
"step": 450
},
{
"epoch": 0.17671917018824435,
"grad_norm": 9.771449089050293,
"learning_rate": 5.609756097560977e-06,
"loss": 0.6245,
"step": 460
},
{
"epoch": 0.18056089127929312,
"grad_norm": 7.735960960388184,
"learning_rate": 5.731707317073171e-06,
"loss": 0.5251,
"step": 470
},
{
"epoch": 0.18440261237034192,
"grad_norm": 7.348488807678223,
"learning_rate": 5.853658536585366e-06,
"loss": 0.5108,
"step": 480
},
{
"epoch": 0.1882443334613907,
"grad_norm": 30.567018508911133,
"learning_rate": 5.9756097560975615e-06,
"loss": 0.5508,
"step": 490
},
{
"epoch": 0.1920860545524395,
"grad_norm": 19.212230682373047,
"learning_rate": 6.0975609756097564e-06,
"loss": 0.5997,
"step": 500
},
{
"epoch": 0.1959277756434883,
"grad_norm": 17.70198631286621,
"learning_rate": 6.219512195121951e-06,
"loss": 0.8108,
"step": 510
},
{
"epoch": 0.19976949673453706,
"grad_norm": 13.471924781799316,
"learning_rate": 6.341463414634147e-06,
"loss": 0.6738,
"step": 520
},
{
"epoch": 0.20361121782558586,
"grad_norm": 15.494725227355957,
"learning_rate": 6.463414634146342e-06,
"loss": 0.8114,
"step": 530
},
{
"epoch": 0.20745293891663466,
"grad_norm": 9.314640045166016,
"learning_rate": 6.585365853658538e-06,
"loss": 0.5791,
"step": 540
},
{
"epoch": 0.21129466000768343,
"grad_norm": 11.314807891845703,
"learning_rate": 6.707317073170733e-06,
"loss": 0.6536,
"step": 550
},
{
"epoch": 0.21513638109873223,
"grad_norm": 16.462522506713867,
"learning_rate": 6.829268292682928e-06,
"loss": 0.5598,
"step": 560
},
{
"epoch": 0.21897810218978103,
"grad_norm": 36.564476013183594,
"learning_rate": 6.951219512195122e-06,
"loss": 0.5573,
"step": 570
},
{
"epoch": 0.2228198232808298,
"grad_norm": 16.07019805908203,
"learning_rate": 7.0731707317073175e-06,
"loss": 0.5328,
"step": 580
},
{
"epoch": 0.2266615443718786,
"grad_norm": 6.132660388946533,
"learning_rate": 7.1951219512195125e-06,
"loss": 0.4499,
"step": 590
},
{
"epoch": 0.2305032654629274,
"grad_norm": 21.4416561126709,
"learning_rate": 7.317073170731707e-06,
"loss": 0.6584,
"step": 600
},
{
"epoch": 0.23434498655397618,
"grad_norm": 18.0037841796875,
"learning_rate": 7.439024390243903e-06,
"loss": 0.4844,
"step": 610
},
{
"epoch": 0.23818670764502498,
"grad_norm": 17.625553131103516,
"learning_rate": 7.560975609756098e-06,
"loss": 0.5122,
"step": 620
},
{
"epoch": 0.24202842873607375,
"grad_norm": 10.607305526733398,
"learning_rate": 7.682926829268293e-06,
"loss": 0.5188,
"step": 630
},
{
"epoch": 0.24587014982712255,
"grad_norm": 26.88294792175293,
"learning_rate": 7.804878048780489e-06,
"loss": 0.7002,
"step": 640
},
{
"epoch": 0.24971187091817135,
"grad_norm": 38.178287506103516,
"learning_rate": 7.926829268292685e-06,
"loss": 0.9407,
"step": 650
},
{
"epoch": 0.2535535920092201,
"grad_norm": 8.800226211547852,
"learning_rate": 8.048780487804879e-06,
"loss": 0.4968,
"step": 660
},
{
"epoch": 0.2573953131002689,
"grad_norm": 30.46478843688965,
"learning_rate": 8.170731707317073e-06,
"loss": 0.5293,
"step": 670
},
{
"epoch": 0.2612370341913177,
"grad_norm": 20.630985260009766,
"learning_rate": 8.292682926829268e-06,
"loss": 0.5382,
"step": 680
},
{
"epoch": 0.2650787552823665,
"grad_norm": 19.19484519958496,
"learning_rate": 8.414634146341464e-06,
"loss": 0.6311,
"step": 690
},
{
"epoch": 0.26892047637341526,
"grad_norm": 26.084064483642578,
"learning_rate": 8.536585365853658e-06,
"loss": 0.6893,
"step": 700
},
{
"epoch": 0.27276219746446406,
"grad_norm": 11.942285537719727,
"learning_rate": 8.658536585365854e-06,
"loss": 0.5938,
"step": 710
},
{
"epoch": 0.27660391855551286,
"grad_norm": 25.995960235595703,
"learning_rate": 8.78048780487805e-06,
"loss": 0.5693,
"step": 720
},
{
"epoch": 0.28044563964656166,
"grad_norm": 10.440145492553711,
"learning_rate": 8.902439024390244e-06,
"loss": 0.5937,
"step": 730
},
{
"epoch": 0.28428736073761046,
"grad_norm": 21.39019012451172,
"learning_rate": 9.02439024390244e-06,
"loss": 0.664,
"step": 740
},
{
"epoch": 0.28812908182865926,
"grad_norm": 11.281585693359375,
"learning_rate": 9.146341463414635e-06,
"loss": 0.5178,
"step": 750
},
{
"epoch": 0.291970802919708,
"grad_norm": 13.577981948852539,
"learning_rate": 9.268292682926831e-06,
"loss": 0.5405,
"step": 760
},
{
"epoch": 0.2958125240107568,
"grad_norm": 55.213340759277344,
"learning_rate": 9.390243902439025e-06,
"loss": 0.5633,
"step": 770
},
{
"epoch": 0.2996542451018056,
"grad_norm": 19.74529266357422,
"learning_rate": 9.51219512195122e-06,
"loss": 0.7541,
"step": 780
},
{
"epoch": 0.3034959661928544,
"grad_norm": 45.70171356201172,
"learning_rate": 9.634146341463415e-06,
"loss": 0.6196,
"step": 790
},
{
"epoch": 0.3073376872839032,
"grad_norm": 23.01153564453125,
"learning_rate": 9.756097560975611e-06,
"loss": 0.7121,
"step": 800
},
{
"epoch": 0.311179408374952,
"grad_norm": 17.099529266357422,
"learning_rate": 9.878048780487805e-06,
"loss": 0.6021,
"step": 810
},
{
"epoch": 0.31502112946600075,
"grad_norm": 11.891583442687988,
"learning_rate": 1e-05,
"loss": 0.6071,
"step": 820
},
{
"epoch": 0.31886285055704955,
"grad_norm": 16.423572540283203,
"learning_rate": 9.98957464553795e-06,
"loss": 0.539,
"step": 830
},
{
"epoch": 0.32270457164809835,
"grad_norm": 11.026520729064941,
"learning_rate": 9.979149291075898e-06,
"loss": 0.615,
"step": 840
},
{
"epoch": 0.32654629273914715,
"grad_norm": 25.40671730041504,
"learning_rate": 9.968723936613845e-06,
"loss": 0.4819,
"step": 850
},
{
"epoch": 0.33038801383019595,
"grad_norm": 30.425880432128906,
"learning_rate": 9.958298582151794e-06,
"loss": 0.7362,
"step": 860
},
{
"epoch": 0.3342297349212447,
"grad_norm": 21.710176467895508,
"learning_rate": 9.947873227689742e-06,
"loss": 0.5052,
"step": 870
},
{
"epoch": 0.3380714560122935,
"grad_norm": 13.537766456604004,
"learning_rate": 9.93744787322769e-06,
"loss": 0.6032,
"step": 880
},
{
"epoch": 0.3419131771033423,
"grad_norm": 19.592073440551758,
"learning_rate": 9.927022518765639e-06,
"loss": 0.5222,
"step": 890
},
{
"epoch": 0.3457548981943911,
"grad_norm": 10.528463363647461,
"learning_rate": 9.916597164303588e-06,
"loss": 0.596,
"step": 900
},
{
"epoch": 0.3495966192854399,
"grad_norm": 15.643308639526367,
"learning_rate": 9.906171809841536e-06,
"loss": 0.7414,
"step": 910
},
{
"epoch": 0.3534383403764887,
"grad_norm": 22.77689552307129,
"learning_rate": 9.895746455379483e-06,
"loss": 0.5151,
"step": 920
},
{
"epoch": 0.35728006146753744,
"grad_norm": 23.217538833618164,
"learning_rate": 9.885321100917432e-06,
"loss": 0.7501,
"step": 930
},
{
"epoch": 0.36112178255858624,
"grad_norm": 21.08719825744629,
"learning_rate": 9.874895746455382e-06,
"loss": 0.4944,
"step": 940
},
{
"epoch": 0.36496350364963503,
"grad_norm": 19.93057632446289,
"learning_rate": 9.864470391993327e-06,
"loss": 0.7289,
"step": 950
},
{
"epoch": 0.36880522474068383,
"grad_norm": 14.810643196105957,
"learning_rate": 9.854045037531277e-06,
"loss": 0.4956,
"step": 960
},
{
"epoch": 0.37264694583173263,
"grad_norm": 19.596710205078125,
"learning_rate": 9.843619683069226e-06,
"loss": 0.5528,
"step": 970
},
{
"epoch": 0.3764886669227814,
"grad_norm": 23.963172912597656,
"learning_rate": 9.833194328607173e-06,
"loss": 0.5904,
"step": 980
},
{
"epoch": 0.3803303880138302,
"grad_norm": 14.250468254089355,
"learning_rate": 9.822768974145121e-06,
"loss": 0.6762,
"step": 990
},
{
"epoch": 0.384172109104879,
"grad_norm": 30.411888122558594,
"learning_rate": 9.81234361968307e-06,
"loss": 0.6031,
"step": 1000
},
{
"epoch": 0.3880138301959278,
"grad_norm": 4.892022132873535,
"learning_rate": 9.80191826522102e-06,
"loss": 0.5832,
"step": 1010
},
{
"epoch": 0.3918555512869766,
"grad_norm": 14.026780128479004,
"learning_rate": 9.791492910758967e-06,
"loss": 0.4432,
"step": 1020
},
{
"epoch": 0.3956972723780254,
"grad_norm": 15.22079086303711,
"learning_rate": 9.781067556296915e-06,
"loss": 0.5003,
"step": 1030
},
{
"epoch": 0.3995389934690741,
"grad_norm": 38.46358871459961,
"learning_rate": 9.770642201834864e-06,
"loss": 0.6863,
"step": 1040
},
{
"epoch": 0.4033807145601229,
"grad_norm": 28.509458541870117,
"learning_rate": 9.760216847372811e-06,
"loss": 0.6557,
"step": 1050
},
{
"epoch": 0.4072224356511717,
"grad_norm": 10.18283748626709,
"learning_rate": 9.749791492910759e-06,
"loss": 0.475,
"step": 1060
},
{
"epoch": 0.4110641567422205,
"grad_norm": 16.280475616455078,
"learning_rate": 9.739366138448708e-06,
"loss": 0.5423,
"step": 1070
},
{
"epoch": 0.4149058778332693,
"grad_norm": 27.256633758544922,
"learning_rate": 9.728940783986657e-06,
"loss": 0.4638,
"step": 1080
},
{
"epoch": 0.4187475989243181,
"grad_norm": 26.906049728393555,
"learning_rate": 9.718515429524605e-06,
"loss": 0.6528,
"step": 1090
},
{
"epoch": 0.42258932001536686,
"grad_norm": 10.475133895874023,
"learning_rate": 9.708090075062552e-06,
"loss": 0.8387,
"step": 1100
},
{
"epoch": 0.42643104110641566,
"grad_norm": 14.576977729797363,
"learning_rate": 9.697664720600502e-06,
"loss": 0.6325,
"step": 1110
},
{
"epoch": 0.43027276219746446,
"grad_norm": 17.823413848876953,
"learning_rate": 9.68723936613845e-06,
"loss": 0.613,
"step": 1120
},
{
"epoch": 0.43411448328851326,
"grad_norm": 12.499800682067871,
"learning_rate": 9.676814011676397e-06,
"loss": 0.5685,
"step": 1130
},
{
"epoch": 0.43795620437956206,
"grad_norm": 19.12653923034668,
"learning_rate": 9.666388657214346e-06,
"loss": 0.8678,
"step": 1140
},
{
"epoch": 0.4417979254706108,
"grad_norm": 5.942495822906494,
"learning_rate": 9.655963302752295e-06,
"loss": 0.4594,
"step": 1150
},
{
"epoch": 0.4456396465616596,
"grad_norm": 19.233552932739258,
"learning_rate": 9.645537948290243e-06,
"loss": 0.5747,
"step": 1160
},
{
"epoch": 0.4494813676527084,
"grad_norm": 17.434133529663086,
"learning_rate": 9.63511259382819e-06,
"loss": 0.5121,
"step": 1170
},
{
"epoch": 0.4533230887437572,
"grad_norm": 14.78231143951416,
"learning_rate": 9.62468723936614e-06,
"loss": 0.7225,
"step": 1180
},
{
"epoch": 0.457164809834806,
"grad_norm": 23.81663703918457,
"learning_rate": 9.614261884904089e-06,
"loss": 0.8527,
"step": 1190
},
{
"epoch": 0.4610065309258548,
"grad_norm": 18.266740798950195,
"learning_rate": 9.603836530442035e-06,
"loss": 0.4101,
"step": 1200
},
{
"epoch": 0.46484825201690355,
"grad_norm": 23.31222152709961,
"learning_rate": 9.593411175979984e-06,
"loss": 0.5847,
"step": 1210
},
{
"epoch": 0.46868997310795235,
"grad_norm": 11.039971351623535,
"learning_rate": 9.582985821517933e-06,
"loss": 0.6515,
"step": 1220
},
{
"epoch": 0.47253169419900115,
"grad_norm": 27.05122184753418,
"learning_rate": 9.57256046705588e-06,
"loss": 0.5968,
"step": 1230
},
{
"epoch": 0.47637341529004995,
"grad_norm": 18.416839599609375,
"learning_rate": 9.562135112593828e-06,
"loss": 0.6339,
"step": 1240
},
{
"epoch": 0.48021513638109875,
"grad_norm": 18.275182723999023,
"learning_rate": 9.551709758131778e-06,
"loss": 0.3595,
"step": 1250
},
{
"epoch": 0.4840568574721475,
"grad_norm": 32.038143157958984,
"learning_rate": 9.541284403669727e-06,
"loss": 0.8281,
"step": 1260
},
{
"epoch": 0.4878985785631963,
"grad_norm": 19.010108947753906,
"learning_rate": 9.530859049207674e-06,
"loss": 0.7158,
"step": 1270
},
{
"epoch": 0.4917402996542451,
"grad_norm": 9.5922269821167,
"learning_rate": 9.520433694745622e-06,
"loss": 0.5315,
"step": 1280
},
{
"epoch": 0.4955820207452939,
"grad_norm": 11.005895614624023,
"learning_rate": 9.510008340283571e-06,
"loss": 0.3599,
"step": 1290
},
{
"epoch": 0.4994237418363427,
"grad_norm": 51.6233024597168,
"learning_rate": 9.499582985821519e-06,
"loss": 0.537,
"step": 1300
},
{
"epoch": 0.5032654629273915,
"grad_norm": 19.033329010009766,
"learning_rate": 9.489157631359466e-06,
"loss": 0.6083,
"step": 1310
},
{
"epoch": 0.5071071840184402,
"grad_norm": 16.91973114013672,
"learning_rate": 9.478732276897415e-06,
"loss": 0.7693,
"step": 1320
},
{
"epoch": 0.5109489051094891,
"grad_norm": 23.38747215270996,
"learning_rate": 9.468306922435365e-06,
"loss": 0.6646,
"step": 1330
},
{
"epoch": 0.5147906262005378,
"grad_norm": 13.772806167602539,
"learning_rate": 9.457881567973312e-06,
"loss": 0.4763,
"step": 1340
},
{
"epoch": 0.5186323472915866,
"grad_norm": 8.950833320617676,
"learning_rate": 9.44745621351126e-06,
"loss": 0.5793,
"step": 1350
},
{
"epoch": 0.5224740683826354,
"grad_norm": 5.6142964363098145,
"learning_rate": 9.437030859049209e-06,
"loss": 0.5797,
"step": 1360
},
{
"epoch": 0.5263157894736842,
"grad_norm": 18.615188598632812,
"learning_rate": 9.426605504587157e-06,
"loss": 0.6041,
"step": 1370
},
{
"epoch": 0.530157510564733,
"grad_norm": 10.953849792480469,
"learning_rate": 9.416180150125104e-06,
"loss": 0.5933,
"step": 1380
},
{
"epoch": 0.5339992316557818,
"grad_norm": 11.613428115844727,
"learning_rate": 9.405754795663053e-06,
"loss": 0.5275,
"step": 1390
},
{
"epoch": 0.5378409527468305,
"grad_norm": 12.725924491882324,
"learning_rate": 9.395329441201003e-06,
"loss": 0.5673,
"step": 1400
},
{
"epoch": 0.5416826738378794,
"grad_norm": 34.54634094238281,
"learning_rate": 9.38490408673895e-06,
"loss": 0.6717,
"step": 1410
},
{
"epoch": 0.5455243949289281,
"grad_norm": 21.028316497802734,
"learning_rate": 9.374478732276898e-06,
"loss": 0.5483,
"step": 1420
},
{
"epoch": 0.549366116019977,
"grad_norm": 30.281667709350586,
"learning_rate": 9.364053377814847e-06,
"loss": 0.7806,
"step": 1430
},
{
"epoch": 0.5532078371110257,
"grad_norm": 11.983960151672363,
"learning_rate": 9.353628023352795e-06,
"loss": 0.5061,
"step": 1440
},
{
"epoch": 0.5570495582020746,
"grad_norm": 6.99747896194458,
"learning_rate": 9.343202668890742e-06,
"loss": 0.5623,
"step": 1450
},
{
"epoch": 0.5608912792931233,
"grad_norm": 11.219843864440918,
"learning_rate": 9.332777314428691e-06,
"loss": 0.6227,
"step": 1460
},
{
"epoch": 0.5647330003841721,
"grad_norm": 8.85550308227539,
"learning_rate": 9.32235195996664e-06,
"loss": 0.5908,
"step": 1470
},
{
"epoch": 0.5685747214752209,
"grad_norm": 15.55632209777832,
"learning_rate": 9.311926605504588e-06,
"loss": 0.5888,
"step": 1480
},
{
"epoch": 0.5724164425662697,
"grad_norm": 5.281271457672119,
"learning_rate": 9.301501251042536e-06,
"loss": 0.4795,
"step": 1490
},
{
"epoch": 0.5762581636573185,
"grad_norm": 10.58825397491455,
"learning_rate": 9.291075896580485e-06,
"loss": 0.4825,
"step": 1500
},
{
"epoch": 0.5800998847483673,
"grad_norm": 13.970091819763184,
"learning_rate": 9.280650542118432e-06,
"loss": 0.6107,
"step": 1510
},
{
"epoch": 0.583941605839416,
"grad_norm": 15.610709190368652,
"learning_rate": 9.270225187656382e-06,
"loss": 0.454,
"step": 1520
},
{
"epoch": 0.5877833269304649,
"grad_norm": 9.203128814697266,
"learning_rate": 9.25979983319433e-06,
"loss": 0.596,
"step": 1530
},
{
"epoch": 0.5916250480215136,
"grad_norm": 12.340123176574707,
"learning_rate": 9.249374478732278e-06,
"loss": 0.6622,
"step": 1540
},
{
"epoch": 0.5954667691125625,
"grad_norm": 6.894665718078613,
"learning_rate": 9.238949124270226e-06,
"loss": 0.4944,
"step": 1550
},
{
"epoch": 0.5993084902036112,
"grad_norm": 22.704559326171875,
"learning_rate": 9.228523769808174e-06,
"loss": 0.6151,
"step": 1560
},
{
"epoch": 0.60315021129466,
"grad_norm": 6.272796630859375,
"learning_rate": 9.218098415346123e-06,
"loss": 0.4866,
"step": 1570
},
{
"epoch": 0.6069919323857088,
"grad_norm": 40.39881134033203,
"learning_rate": 9.20767306088407e-06,
"loss": 0.5471,
"step": 1580
},
{
"epoch": 0.6108336534767576,
"grad_norm": 9.417654037475586,
"learning_rate": 9.19724770642202e-06,
"loss": 0.5702,
"step": 1590
},
{
"epoch": 0.6146753745678064,
"grad_norm": 8.880293846130371,
"learning_rate": 9.186822351959967e-06,
"loss": 0.7593,
"step": 1600
},
{
"epoch": 0.6185170956588552,
"grad_norm": 16.337783813476562,
"learning_rate": 9.176396997497916e-06,
"loss": 0.3708,
"step": 1610
},
{
"epoch": 0.622358816749904,
"grad_norm": 15.34815502166748,
"learning_rate": 9.165971643035864e-06,
"loss": 0.6829,
"step": 1620
},
{
"epoch": 0.6262005378409528,
"grad_norm": 12.125506401062012,
"learning_rate": 9.155546288573811e-06,
"loss": 0.5839,
"step": 1630
},
{
"epoch": 0.6300422589320015,
"grad_norm": 12.340716361999512,
"learning_rate": 9.14512093411176e-06,
"loss": 0.5855,
"step": 1640
},
{
"epoch": 0.6338839800230504,
"grad_norm": 17.276071548461914,
"learning_rate": 9.134695579649708e-06,
"loss": 0.4579,
"step": 1650
},
{
"epoch": 0.6377257011140991,
"grad_norm": 4.054512977600098,
"learning_rate": 9.124270225187658e-06,
"loss": 0.3717,
"step": 1660
},
{
"epoch": 0.641567422205148,
"grad_norm": 26.277875900268555,
"learning_rate": 9.113844870725605e-06,
"loss": 0.6934,
"step": 1670
},
{
"epoch": 0.6454091432961967,
"grad_norm": 23.17993927001953,
"learning_rate": 9.103419516263554e-06,
"loss": 0.8507,
"step": 1680
},
{
"epoch": 0.6492508643872454,
"grad_norm": 30.25948715209961,
"learning_rate": 9.092994161801502e-06,
"loss": 0.5851,
"step": 1690
},
{
"epoch": 0.6530925854782943,
"grad_norm": 12.083464622497559,
"learning_rate": 9.08256880733945e-06,
"loss": 0.5214,
"step": 1700
},
{
"epoch": 0.656934306569343,
"grad_norm": 26.132946014404297,
"learning_rate": 9.072143452877399e-06,
"loss": 0.5715,
"step": 1710
},
{
"epoch": 0.6607760276603919,
"grad_norm": 13.83061408996582,
"learning_rate": 9.061718098415346e-06,
"loss": 0.6076,
"step": 1720
},
{
"epoch": 0.6646177487514406,
"grad_norm": 36.992679595947266,
"learning_rate": 9.051292743953295e-06,
"loss": 0.5795,
"step": 1730
},
{
"epoch": 0.6684594698424894,
"grad_norm": 24.426977157592773,
"learning_rate": 9.040867389491243e-06,
"loss": 0.6913,
"step": 1740
},
{
"epoch": 0.6723011909335382,
"grad_norm": 15.399202346801758,
"learning_rate": 9.030442035029192e-06,
"loss": 0.647,
"step": 1750
},
{
"epoch": 0.676142912024587,
"grad_norm": 36.72813034057617,
"learning_rate": 9.02001668056714e-06,
"loss": 0.7641,
"step": 1760
},
{
"epoch": 0.6799846331156358,
"grad_norm": 19.219661712646484,
"learning_rate": 9.009591326105089e-06,
"loss": 0.7111,
"step": 1770
},
{
"epoch": 0.6838263542066846,
"grad_norm": 10.353839874267578,
"learning_rate": 8.999165971643037e-06,
"loss": 0.437,
"step": 1780
},
{
"epoch": 0.6876680752977334,
"grad_norm": 12.179790496826172,
"learning_rate": 8.988740617180984e-06,
"loss": 0.6514,
"step": 1790
},
{
"epoch": 0.6915097963887822,
"grad_norm": 15.036273956298828,
"learning_rate": 8.978315262718933e-06,
"loss": 0.4611,
"step": 1800
},
{
"epoch": 0.6953515174798309,
"grad_norm": 12.146955490112305,
"learning_rate": 8.967889908256881e-06,
"loss": 0.5176,
"step": 1810
},
{
"epoch": 0.6991932385708798,
"grad_norm": 16.004959106445312,
"learning_rate": 8.95746455379483e-06,
"loss": 0.3749,
"step": 1820
},
{
"epoch": 0.7030349596619285,
"grad_norm": 23.500526428222656,
"learning_rate": 8.947039199332778e-06,
"loss": 0.6124,
"step": 1830
},
{
"epoch": 0.7068766807529774,
"grad_norm": 11.367331504821777,
"learning_rate": 8.936613844870727e-06,
"loss": 0.3982,
"step": 1840
},
{
"epoch": 0.7107184018440261,
"grad_norm": 13.60319709777832,
"learning_rate": 8.926188490408674e-06,
"loss": 0.4618,
"step": 1850
},
{
"epoch": 0.7145601229350749,
"grad_norm": 9.807296752929688,
"learning_rate": 8.915763135946624e-06,
"loss": 0.552,
"step": 1860
},
{
"epoch": 0.7184018440261237,
"grad_norm": 41.238895416259766,
"learning_rate": 8.905337781484571e-06,
"loss": 0.738,
"step": 1870
},
{
"epoch": 0.7222435651171725,
"grad_norm": 8.117176055908203,
"learning_rate": 8.894912427022519e-06,
"loss": 0.546,
"step": 1880
},
{
"epoch": 0.7260852862082213,
"grad_norm": 8.292084693908691,
"learning_rate": 8.884487072560468e-06,
"loss": 0.5098,
"step": 1890
},
{
"epoch": 0.7299270072992701,
"grad_norm": 16.20579719543457,
"learning_rate": 8.874061718098416e-06,
"loss": 0.5693,
"step": 1900
},
{
"epoch": 0.7337687283903188,
"grad_norm": 10.686980247497559,
"learning_rate": 8.863636363636365e-06,
"loss": 0.6848,
"step": 1910
},
{
"epoch": 0.7376104494813677,
"grad_norm": 12.386652946472168,
"learning_rate": 8.853211009174312e-06,
"loss": 0.5282,
"step": 1920
},
{
"epoch": 0.7414521705724164,
"grad_norm": 11.129962921142578,
"learning_rate": 8.842785654712262e-06,
"loss": 0.5789,
"step": 1930
},
{
"epoch": 0.7452938916634653,
"grad_norm": 8.727615356445312,
"learning_rate": 8.83236030025021e-06,
"loss": 0.5936,
"step": 1940
},
{
"epoch": 0.749135612754514,
"grad_norm": 11.261787414550781,
"learning_rate": 8.821934945788157e-06,
"loss": 0.5308,
"step": 1950
},
{
"epoch": 0.7529773338455628,
"grad_norm": 23.387935638427734,
"learning_rate": 8.811509591326106e-06,
"loss": 0.5074,
"step": 1960
},
{
"epoch": 0.7568190549366116,
"grad_norm": 20.772794723510742,
"learning_rate": 8.801084236864054e-06,
"loss": 0.6157,
"step": 1970
},
{
"epoch": 0.7606607760276604,
"grad_norm": 23.0604305267334,
"learning_rate": 8.790658882402003e-06,
"loss": 0.5272,
"step": 1980
},
{
"epoch": 0.7645024971187092,
"grad_norm": 44.302425384521484,
"learning_rate": 8.78023352793995e-06,
"loss": 0.6709,
"step": 1990
},
{
"epoch": 0.768344218209758,
"grad_norm": 16.66979217529297,
"learning_rate": 8.7698081734779e-06,
"loss": 0.4651,
"step": 2000
},
{
"epoch": 0.7721859393008068,
"grad_norm": 18.14614486694336,
"learning_rate": 8.759382819015847e-06,
"loss": 0.5747,
"step": 2010
},
{
"epoch": 0.7760276603918556,
"grad_norm": 10.635650634765625,
"learning_rate": 8.748957464553796e-06,
"loss": 0.5169,
"step": 2020
},
{
"epoch": 0.7798693814829043,
"grad_norm": 13.54704475402832,
"learning_rate": 8.738532110091744e-06,
"loss": 0.4784,
"step": 2030
},
{
"epoch": 0.7837111025739532,
"grad_norm": 12.35689926147461,
"learning_rate": 8.728106755629691e-06,
"loss": 0.5529,
"step": 2040
},
{
"epoch": 0.7875528236650019,
"grad_norm": 7.250340461730957,
"learning_rate": 8.71768140116764e-06,
"loss": 0.6229,
"step": 2050
},
{
"epoch": 0.7913945447560508,
"grad_norm": 16.60529327392578,
"learning_rate": 8.707256046705588e-06,
"loss": 0.5726,
"step": 2060
},
{
"epoch": 0.7952362658470995,
"grad_norm": 18.4666805267334,
"learning_rate": 8.696830692243537e-06,
"loss": 0.5643,
"step": 2070
},
{
"epoch": 0.7990779869381482,
"grad_norm": 31.986207962036133,
"learning_rate": 8.686405337781485e-06,
"loss": 0.4759,
"step": 2080
},
{
"epoch": 0.8029197080291971,
"grad_norm": 30.724218368530273,
"learning_rate": 8.675979983319434e-06,
"loss": 0.6527,
"step": 2090
},
{
"epoch": 0.8067614291202458,
"grad_norm": 22.7759952545166,
"learning_rate": 8.665554628857382e-06,
"loss": 0.6438,
"step": 2100
},
{
"epoch": 0.8106031502112947,
"grad_norm": 14.61020565032959,
"learning_rate": 8.65512927439533e-06,
"loss": 0.3962,
"step": 2110
},
{
"epoch": 0.8144448713023434,
"grad_norm": 20.27998161315918,
"learning_rate": 8.644703919933279e-06,
"loss": 0.6989,
"step": 2120
},
{
"epoch": 0.8182865923933922,
"grad_norm": 10.2035493850708,
"learning_rate": 8.634278565471226e-06,
"loss": 0.5543,
"step": 2130
},
{
"epoch": 0.822128313484441,
"grad_norm": 16.954448699951172,
"learning_rate": 8.623853211009175e-06,
"loss": 0.4598,
"step": 2140
},
{
"epoch": 0.8259700345754898,
"grad_norm": 24.188817977905273,
"learning_rate": 8.613427856547123e-06,
"loss": 0.674,
"step": 2150
},
{
"epoch": 0.8298117556665386,
"grad_norm": 8.472796440124512,
"learning_rate": 8.603002502085072e-06,
"loss": 0.4246,
"step": 2160
},
{
"epoch": 0.8336534767575874,
"grad_norm": 21.893178939819336,
"learning_rate": 8.59257714762302e-06,
"loss": 0.5788,
"step": 2170
},
{
"epoch": 0.8374951978486362,
"grad_norm": 8.200776100158691,
"learning_rate": 8.582151793160967e-06,
"loss": 0.4215,
"step": 2180
},
{
"epoch": 0.841336918939685,
"grad_norm": 21.523435592651367,
"learning_rate": 8.571726438698917e-06,
"loss": 0.4367,
"step": 2190
},
{
"epoch": 0.8451786400307337,
"grad_norm": 18.608898162841797,
"learning_rate": 8.561301084236864e-06,
"loss": 0.6324,
"step": 2200
},
{
"epoch": 0.8490203611217826,
"grad_norm": 19.39713478088379,
"learning_rate": 8.550875729774813e-06,
"loss": 0.382,
"step": 2210
},
{
"epoch": 0.8528620822128313,
"grad_norm": 15.368677139282227,
"learning_rate": 8.540450375312761e-06,
"loss": 0.492,
"step": 2220
},
{
"epoch": 0.8567038033038802,
"grad_norm": 6.85573673248291,
"learning_rate": 8.53002502085071e-06,
"loss": 0.6801,
"step": 2230
},
{
"epoch": 0.8605455243949289,
"grad_norm": 11.223825454711914,
"learning_rate": 8.519599666388658e-06,
"loss": 0.7763,
"step": 2240
},
{
"epoch": 0.8643872454859777,
"grad_norm": 11.18885326385498,
"learning_rate": 8.509174311926605e-06,
"loss": 0.585,
"step": 2250
},
{
"epoch": 0.8682289665770265,
"grad_norm": 21.877548217773438,
"learning_rate": 8.498748957464554e-06,
"loss": 0.5873,
"step": 2260
},
{
"epoch": 0.8720706876680753,
"grad_norm": 25.72136116027832,
"learning_rate": 8.488323603002504e-06,
"loss": 0.5796,
"step": 2270
},
{
"epoch": 0.8759124087591241,
"grad_norm": 16.472366333007812,
"learning_rate": 8.477898248540451e-06,
"loss": 0.4431,
"step": 2280
},
{
"epoch": 0.8797541298501729,
"grad_norm": 5.752821445465088,
"learning_rate": 8.467472894078399e-06,
"loss": 0.7004,
"step": 2290
},
{
"epoch": 0.8835958509412216,
"grad_norm": 13.56191349029541,
"learning_rate": 8.457047539616348e-06,
"loss": 0.4899,
"step": 2300
},
{
"epoch": 0.8874375720322705,
"grad_norm": 5.017563343048096,
"learning_rate": 8.446622185154296e-06,
"loss": 0.7014,
"step": 2310
},
{
"epoch": 0.8912792931233192,
"grad_norm": 15.450356483459473,
"learning_rate": 8.436196830692243e-06,
"loss": 0.5414,
"step": 2320
},
{
"epoch": 0.8951210142143681,
"grad_norm": 16.416250228881836,
"learning_rate": 8.425771476230192e-06,
"loss": 0.698,
"step": 2330
},
{
"epoch": 0.8989627353054168,
"grad_norm": 11.185935020446777,
"learning_rate": 8.415346121768142e-06,
"loss": 0.6264,
"step": 2340
},
{
"epoch": 0.9028044563964657,
"grad_norm": 22.787181854248047,
"learning_rate": 8.40492076730609e-06,
"loss": 0.6908,
"step": 2350
},
{
"epoch": 0.9066461774875144,
"grad_norm": 11.522934913635254,
"learning_rate": 8.394495412844037e-06,
"loss": 0.5546,
"step": 2360
},
{
"epoch": 0.9104878985785632,
"grad_norm": 18.260616302490234,
"learning_rate": 8.384070058381986e-06,
"loss": 0.5925,
"step": 2370
},
{
"epoch": 0.914329619669612,
"grad_norm": 7.180076599121094,
"learning_rate": 8.373644703919933e-06,
"loss": 0.6639,
"step": 2380
},
{
"epoch": 0.9181713407606608,
"grad_norm": 11.107264518737793,
"learning_rate": 8.363219349457881e-06,
"loss": 0.6762,
"step": 2390
},
{
"epoch": 0.9220130618517096,
"grad_norm": 12.528190612792969,
"learning_rate": 8.35279399499583e-06,
"loss": 0.5435,
"step": 2400
},
{
"epoch": 0.9258547829427584,
"grad_norm": 29.454421997070312,
"learning_rate": 8.34236864053378e-06,
"loss": 0.5074,
"step": 2410
},
{
"epoch": 0.9296965040338071,
"grad_norm": 14.677248001098633,
"learning_rate": 8.331943286071727e-06,
"loss": 0.6161,
"step": 2420
},
{
"epoch": 0.933538225124856,
"grad_norm": 8.907113075256348,
"learning_rate": 8.321517931609675e-06,
"loss": 0.353,
"step": 2430
},
{
"epoch": 0.9373799462159047,
"grad_norm": 11.691315650939941,
"learning_rate": 8.311092577147624e-06,
"loss": 0.4516,
"step": 2440
},
{
"epoch": 0.9412216673069536,
"grad_norm": 2.8710756301879883,
"learning_rate": 8.300667222685571e-06,
"loss": 0.6726,
"step": 2450
},
{
"epoch": 0.9450633883980023,
"grad_norm": 11.67735481262207,
"learning_rate": 8.290241868223519e-06,
"loss": 0.6797,
"step": 2460
},
{
"epoch": 0.948905109489051,
"grad_norm": 17.547286987304688,
"learning_rate": 8.279816513761468e-06,
"loss": 0.7029,
"step": 2470
},
{
"epoch": 0.9527468305800999,
"grad_norm": 11.663725852966309,
"learning_rate": 8.269391159299417e-06,
"loss": 0.5016,
"step": 2480
},
{
"epoch": 0.9565885516711486,
"grad_norm": 9.743104934692383,
"learning_rate": 8.258965804837365e-06,
"loss": 0.5489,
"step": 2490
},
{
"epoch": 0.9604302727621975,
"grad_norm": 9.579474449157715,
"learning_rate": 8.248540450375313e-06,
"loss": 0.5867,
"step": 2500
},
{
"epoch": 0.9642719938532462,
"grad_norm": 13.63699722290039,
"learning_rate": 8.238115095913262e-06,
"loss": 0.5191,
"step": 2510
},
{
"epoch": 0.968113714944295,
"grad_norm": 10.331293106079102,
"learning_rate": 8.227689741451211e-06,
"loss": 0.6654,
"step": 2520
},
{
"epoch": 0.9719554360353438,
"grad_norm": 10.614498138427734,
"learning_rate": 8.217264386989159e-06,
"loss": 0.5947,
"step": 2530
},
{
"epoch": 0.9757971571263926,
"grad_norm": 10.182368278503418,
"learning_rate": 8.206839032527106e-06,
"loss": 0.5482,
"step": 2540
},
{
"epoch": 0.9796388782174414,
"grad_norm": 15.42397403717041,
"learning_rate": 8.196413678065055e-06,
"loss": 0.5144,
"step": 2550
},
{
"epoch": 0.9834805993084902,
"grad_norm": 8.317682266235352,
"learning_rate": 8.185988323603003e-06,
"loss": 0.4518,
"step": 2560
},
{
"epoch": 0.987322320399539,
"grad_norm": 43.10714340209961,
"learning_rate": 8.17556296914095e-06,
"loss": 0.5974,
"step": 2570
},
{
"epoch": 0.9911640414905878,
"grad_norm": 7.906277656555176,
"learning_rate": 8.1651376146789e-06,
"loss": 0.5745,
"step": 2580
},
{
"epoch": 0.9950057625816365,
"grad_norm": 10.229177474975586,
"learning_rate": 8.154712260216849e-06,
"loss": 0.4322,
"step": 2590
},
{
"epoch": 0.9988474836726854,
"grad_norm": 12.773459434509277,
"learning_rate": 8.144286905754796e-06,
"loss": 0.5947,
"step": 2600
},
{
"epoch": 1.0,
"eval_accuracy": 0.7737969455383729,
"eval_f1_per_label": [
0.778160354156419,
0.7230364524614806,
0.8299703264094955
],
"eval_f1_weighted": 0.774424228670159,
"eval_loss": 0.5626052618026733,
"eval_precision_per_label": [
0.7752368507023848,
0.7131208302446257,
0.8468059339993945
],
"eval_precision_weighted": 0.7753803799282116,
"eval_recall_per_label": [
0.7811059907834101,
0.7332317073170732,
0.8137910968868199
],
"eval_recall_weighted": 0.7737969455383729,
"eval_runtime": 38.6689,
"eval_samples_per_second": 269.235,
"eval_steps_per_second": 33.67,
"step": 2603
}
],
"logging_steps": 10,
"max_steps": 10412,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 3,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 656244433604970.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}