PEFT
Safetensors
deu05232's picture
Upload folder using huggingface_hub
b51176e verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9996979764421625,
"eval_steps": 500,
"global_step": 1655,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006040471156750227,
"grad_norm": 6.352119345594041,
"learning_rate": 4.9999999999999996e-05,
"loss": 5.7625,
"step": 10
},
{
"epoch": 0.012080942313500454,
"grad_norm": 3.5107589040708578,
"learning_rate": 6.505149978319905e-05,
"loss": 3.1477,
"step": 20
},
{
"epoch": 0.018121413470250678,
"grad_norm": 1.7597502982401718,
"learning_rate": 7.385606273598311e-05,
"loss": 1.8234,
"step": 30
},
{
"epoch": 0.024161884627000908,
"grad_norm": 2.0430582664699704,
"learning_rate": 8.01029995663981e-05,
"loss": 1.482,
"step": 40
},
{
"epoch": 0.030202355783751134,
"grad_norm": 2.30138022647804,
"learning_rate": 8.494850021680092e-05,
"loss": 1.427,
"step": 50
},
{
"epoch": 0.036242826940501356,
"grad_norm": 1.961300808555845,
"learning_rate": 8.890756251918216e-05,
"loss": 1.3652,
"step": 60
},
{
"epoch": 0.042283298097251586,
"grad_norm": 1.5670057056368645,
"learning_rate": 9.225490200071284e-05,
"loss": 1.2859,
"step": 70
},
{
"epoch": 0.048323769254001815,
"grad_norm": 1.5648604780816326,
"learning_rate": 9.515449934959716e-05,
"loss": 1.2166,
"step": 80
},
{
"epoch": 0.05436424041075204,
"grad_norm": 1.5594489363452173,
"learning_rate": 9.771212547196623e-05,
"loss": 1.2299,
"step": 90
},
{
"epoch": 0.06040471156750227,
"grad_norm": 1.478498798125124,
"learning_rate": 9.999999999999999e-05,
"loss": 1.1406,
"step": 100
},
{
"epoch": 0.0664451827242525,
"grad_norm": 1.3456415286113537,
"learning_rate": 9.942122186495178e-05,
"loss": 1.1512,
"step": 110
},
{
"epoch": 0.07248565388100271,
"grad_norm": 1.4169868695799486,
"learning_rate": 9.877813504823152e-05,
"loss": 1.2473,
"step": 120
},
{
"epoch": 0.07852612503775294,
"grad_norm": 1.5442406663559958,
"learning_rate": 9.813504823151127e-05,
"loss": 1.1609,
"step": 130
},
{
"epoch": 0.08456659619450317,
"grad_norm": 1.3840740480619829,
"learning_rate": 9.7491961414791e-05,
"loss": 1.1617,
"step": 140
},
{
"epoch": 0.0906070673512534,
"grad_norm": 1.1099163069476086,
"learning_rate": 9.684887459807074e-05,
"loss": 1.1746,
"step": 150
},
{
"epoch": 0.09664753850800363,
"grad_norm": 1.2420434112131873,
"learning_rate": 9.620578778135049e-05,
"loss": 1.1504,
"step": 160
},
{
"epoch": 0.10268800966475385,
"grad_norm": 1.081321720135299,
"learning_rate": 9.556270096463023e-05,
"loss": 1.1605,
"step": 170
},
{
"epoch": 0.10872848082150408,
"grad_norm": 1.0982034537770153,
"learning_rate": 9.491961414790998e-05,
"loss": 1.0799,
"step": 180
},
{
"epoch": 0.1147689519782543,
"grad_norm": 1.1736811633063773,
"learning_rate": 9.427652733118972e-05,
"loss": 1.1242,
"step": 190
},
{
"epoch": 0.12080942313500453,
"grad_norm": 1.3595797342301437,
"learning_rate": 9.363344051446946e-05,
"loss": 1.1016,
"step": 200
},
{
"epoch": 0.12684989429175475,
"grad_norm": 1.2621841618934533,
"learning_rate": 9.29903536977492e-05,
"loss": 1.0695,
"step": 210
},
{
"epoch": 0.132890365448505,
"grad_norm": 1.2070699106064489,
"learning_rate": 9.234726688102894e-05,
"loss": 1.1049,
"step": 220
},
{
"epoch": 0.1389308366052552,
"grad_norm": 1.0416383062176056,
"learning_rate": 9.17041800643087e-05,
"loss": 1.1467,
"step": 230
},
{
"epoch": 0.14497130776200542,
"grad_norm": 1.1856097509180394,
"learning_rate": 9.106109324758843e-05,
"loss": 1.0746,
"step": 240
},
{
"epoch": 0.15101177891875567,
"grad_norm": 1.144246874115688,
"learning_rate": 9.041800643086817e-05,
"loss": 1.2018,
"step": 250
},
{
"epoch": 0.15705225007550588,
"grad_norm": 0.9353587652819314,
"learning_rate": 8.977491961414792e-05,
"loss": 1.0789,
"step": 260
},
{
"epoch": 0.16309272123225613,
"grad_norm": 1.0285527563460544,
"learning_rate": 8.913183279742766e-05,
"loss": 1.0555,
"step": 270
},
{
"epoch": 0.16913319238900634,
"grad_norm": 0.9852353032151006,
"learning_rate": 8.848874598070739e-05,
"loss": 1.1451,
"step": 280
},
{
"epoch": 0.17517366354575656,
"grad_norm": 1.175932073617665,
"learning_rate": 8.784565916398714e-05,
"loss": 1.0789,
"step": 290
},
{
"epoch": 0.1812141347025068,
"grad_norm": 1.213820312892746,
"learning_rate": 8.720257234726688e-05,
"loss": 1.0475,
"step": 300
},
{
"epoch": 0.18725460585925702,
"grad_norm": 1.1846528600649535,
"learning_rate": 8.655948553054663e-05,
"loss": 1.0521,
"step": 310
},
{
"epoch": 0.19329507701600726,
"grad_norm": 1.1497197430459096,
"learning_rate": 8.591639871382637e-05,
"loss": 1.082,
"step": 320
},
{
"epoch": 0.19933554817275748,
"grad_norm": 1.1612797319381625,
"learning_rate": 8.52733118971061e-05,
"loss": 1.0793,
"step": 330
},
{
"epoch": 0.2053760193295077,
"grad_norm": 1.082739707844854,
"learning_rate": 8.463022508038586e-05,
"loss": 1.1061,
"step": 340
},
{
"epoch": 0.21141649048625794,
"grad_norm": 1.2757899011878036,
"learning_rate": 8.398713826366559e-05,
"loss": 1.073,
"step": 350
},
{
"epoch": 0.21745696164300815,
"grad_norm": 0.9540956853203417,
"learning_rate": 8.334405144694534e-05,
"loss": 1.0135,
"step": 360
},
{
"epoch": 0.2234974327997584,
"grad_norm": 1.0200709241255603,
"learning_rate": 8.270096463022508e-05,
"loss": 1.1389,
"step": 370
},
{
"epoch": 0.2295379039565086,
"grad_norm": 0.8455317026975807,
"learning_rate": 8.205787781350482e-05,
"loss": 1.0598,
"step": 380
},
{
"epoch": 0.23557837511325883,
"grad_norm": 1.1381349305391164,
"learning_rate": 8.141479099678457e-05,
"loss": 1.0777,
"step": 390
},
{
"epoch": 0.24161884627000907,
"grad_norm": 1.103747383663609,
"learning_rate": 8.07717041800643e-05,
"loss": 1.0617,
"step": 400
},
{
"epoch": 0.24765931742675928,
"grad_norm": 1.138904626814912,
"learning_rate": 8.012861736334406e-05,
"loss": 1.0324,
"step": 410
},
{
"epoch": 0.2536997885835095,
"grad_norm": 1.0781428262426909,
"learning_rate": 7.94855305466238e-05,
"loss": 1.0859,
"step": 420
},
{
"epoch": 0.2597402597402597,
"grad_norm": 1.0846995831727089,
"learning_rate": 7.884244372990353e-05,
"loss": 1.0553,
"step": 430
},
{
"epoch": 0.26578073089701,
"grad_norm": 0.8641072003497396,
"learning_rate": 7.819935691318328e-05,
"loss": 1.0068,
"step": 440
},
{
"epoch": 0.2718212020537602,
"grad_norm": 1.110226877216393,
"learning_rate": 7.755627009646302e-05,
"loss": 1.0115,
"step": 450
},
{
"epoch": 0.2778616732105104,
"grad_norm": 1.1418636977442045,
"learning_rate": 7.691318327974277e-05,
"loss": 1.0373,
"step": 460
},
{
"epoch": 0.28390214436726063,
"grad_norm": 0.9476740742119087,
"learning_rate": 7.62700964630225e-05,
"loss": 1.0023,
"step": 470
},
{
"epoch": 0.28994261552401085,
"grad_norm": 1.1736350313366837,
"learning_rate": 7.562700964630224e-05,
"loss": 1.0338,
"step": 480
},
{
"epoch": 0.2959830866807611,
"grad_norm": 1.113923619981689,
"learning_rate": 7.4983922829582e-05,
"loss": 0.9855,
"step": 490
},
{
"epoch": 0.30202355783751134,
"grad_norm": 1.0389339180007815,
"learning_rate": 7.434083601286173e-05,
"loss": 1.0525,
"step": 500
},
{
"epoch": 0.30806402899426155,
"grad_norm": 1.161270624803982,
"learning_rate": 7.369774919614148e-05,
"loss": 1.0697,
"step": 510
},
{
"epoch": 0.31410450015101177,
"grad_norm": 0.8892068789215148,
"learning_rate": 7.305466237942122e-05,
"loss": 0.9889,
"step": 520
},
{
"epoch": 0.320144971307762,
"grad_norm": 1.0455859065719944,
"learning_rate": 7.241157556270097e-05,
"loss": 0.9898,
"step": 530
},
{
"epoch": 0.32618544246451225,
"grad_norm": 1.0186894188406512,
"learning_rate": 7.17684887459807e-05,
"loss": 0.9904,
"step": 540
},
{
"epoch": 0.33222591362126247,
"grad_norm": 1.0072092839183986,
"learning_rate": 7.112540192926044e-05,
"loss": 0.9873,
"step": 550
},
{
"epoch": 0.3382663847780127,
"grad_norm": 0.9663462582485958,
"learning_rate": 7.04823151125402e-05,
"loss": 1.0375,
"step": 560
},
{
"epoch": 0.3443068559347629,
"grad_norm": 0.9103712505082897,
"learning_rate": 6.983922829581993e-05,
"loss": 1.0383,
"step": 570
},
{
"epoch": 0.3503473270915131,
"grad_norm": 1.0485963233672557,
"learning_rate": 6.919614147909968e-05,
"loss": 0.9758,
"step": 580
},
{
"epoch": 0.3563877982482634,
"grad_norm": 0.9912979171159205,
"learning_rate": 6.855305466237942e-05,
"loss": 0.993,
"step": 590
},
{
"epoch": 0.3624282694050136,
"grad_norm": 1.1550179596081722,
"learning_rate": 6.790996784565917e-05,
"loss": 1.032,
"step": 600
},
{
"epoch": 0.3684687405617638,
"grad_norm": 1.0176105219446732,
"learning_rate": 6.726688102893891e-05,
"loss": 1.0094,
"step": 610
},
{
"epoch": 0.37450921171851403,
"grad_norm": 1.1210756115920897,
"learning_rate": 6.662379421221864e-05,
"loss": 0.968,
"step": 620
},
{
"epoch": 0.38054968287526425,
"grad_norm": 0.9310657150450071,
"learning_rate": 6.59807073954984e-05,
"loss": 1.0102,
"step": 630
},
{
"epoch": 0.3865901540320145,
"grad_norm": 1.1633016127800648,
"learning_rate": 6.533762057877813e-05,
"loss": 1.0256,
"step": 640
},
{
"epoch": 0.39263062518876474,
"grad_norm": 0.8195008101746646,
"learning_rate": 6.469453376205788e-05,
"loss": 0.9906,
"step": 650
},
{
"epoch": 0.39867109634551495,
"grad_norm": 0.9310761172857367,
"learning_rate": 6.405144694533762e-05,
"loss": 0.9754,
"step": 660
},
{
"epoch": 0.40471156750226517,
"grad_norm": 1.0516630367824455,
"learning_rate": 6.340836012861736e-05,
"loss": 1.0275,
"step": 670
},
{
"epoch": 0.4107520386590154,
"grad_norm": 1.0629036969985795,
"learning_rate": 6.276527331189711e-05,
"loss": 1.0088,
"step": 680
},
{
"epoch": 0.41679250981576565,
"grad_norm": 1.0110994904370134,
"learning_rate": 6.212218649517684e-05,
"loss": 1.0416,
"step": 690
},
{
"epoch": 0.42283298097251587,
"grad_norm": 0.8895584335650736,
"learning_rate": 6.14790996784566e-05,
"loss": 1.0762,
"step": 700
},
{
"epoch": 0.4288734521292661,
"grad_norm": 1.0448634604827216,
"learning_rate": 6.083601286173633e-05,
"loss": 0.9771,
"step": 710
},
{
"epoch": 0.4349139232860163,
"grad_norm": 0.7905625978703504,
"learning_rate": 6.019292604501608e-05,
"loss": 1.0104,
"step": 720
},
{
"epoch": 0.4409543944427665,
"grad_norm": 1.0522004404580236,
"learning_rate": 5.954983922829582e-05,
"loss": 0.9977,
"step": 730
},
{
"epoch": 0.4469948655995168,
"grad_norm": 0.989475716298655,
"learning_rate": 5.8906752411575564e-05,
"loss": 0.9752,
"step": 740
},
{
"epoch": 0.453035336756267,
"grad_norm": 1.1463565668787514,
"learning_rate": 5.826366559485531e-05,
"loss": 0.9922,
"step": 750
},
{
"epoch": 0.4590758079130172,
"grad_norm": 1.189865689753586,
"learning_rate": 5.7620578778135045e-05,
"loss": 1.0211,
"step": 760
},
{
"epoch": 0.46511627906976744,
"grad_norm": 1.0920686333427474,
"learning_rate": 5.6977491961414796e-05,
"loss": 0.9664,
"step": 770
},
{
"epoch": 0.47115675022651765,
"grad_norm": 1.0174913677757231,
"learning_rate": 5.633440514469453e-05,
"loss": 0.9992,
"step": 780
},
{
"epoch": 0.4771972213832679,
"grad_norm": 1.1913080680366728,
"learning_rate": 5.5691318327974284e-05,
"loss": 1.033,
"step": 790
},
{
"epoch": 0.48323769254001814,
"grad_norm": 1.0204323369307062,
"learning_rate": 5.504823151125402e-05,
"loss": 0.9807,
"step": 800
},
{
"epoch": 0.48927816369676835,
"grad_norm": 1.118864062431584,
"learning_rate": 5.440514469453376e-05,
"loss": 0.974,
"step": 810
},
{
"epoch": 0.49531863485351857,
"grad_norm": 1.0350012597705058,
"learning_rate": 5.376205787781351e-05,
"loss": 0.9705,
"step": 820
},
{
"epoch": 0.5013591060102688,
"grad_norm": 1.0845595520731828,
"learning_rate": 5.3118971061093246e-05,
"loss": 0.9582,
"step": 830
},
{
"epoch": 0.507399577167019,
"grad_norm": 0.9453749574005488,
"learning_rate": 5.2475884244372996e-05,
"loss": 1.0293,
"step": 840
},
{
"epoch": 0.5134400483237692,
"grad_norm": 1.042699724920899,
"learning_rate": 5.183279742765273e-05,
"loss": 0.952,
"step": 850
},
{
"epoch": 0.5194805194805194,
"grad_norm": 1.024020216858902,
"learning_rate": 5.118971061093247e-05,
"loss": 1.018,
"step": 860
},
{
"epoch": 0.5255209906372698,
"grad_norm": 1.0360224854752502,
"learning_rate": 5.054662379421222e-05,
"loss": 0.9295,
"step": 870
},
{
"epoch": 0.53156146179402,
"grad_norm": 1.1683508369643563,
"learning_rate": 4.9903536977491965e-05,
"loss": 1.0133,
"step": 880
},
{
"epoch": 0.5376019329507702,
"grad_norm": 0.8614966755997071,
"learning_rate": 4.92604501607717e-05,
"loss": 0.993,
"step": 890
},
{
"epoch": 0.5436424041075204,
"grad_norm": 0.9857361206695465,
"learning_rate": 4.8617363344051446e-05,
"loss": 0.951,
"step": 900
},
{
"epoch": 0.5496828752642706,
"grad_norm": 0.8956078547131043,
"learning_rate": 4.797427652733119e-05,
"loss": 0.9268,
"step": 910
},
{
"epoch": 0.5557233464210208,
"grad_norm": 0.8885268581836658,
"learning_rate": 4.7331189710610934e-05,
"loss": 0.9688,
"step": 920
},
{
"epoch": 0.561763817577771,
"grad_norm": 1.136712299735102,
"learning_rate": 4.668810289389068e-05,
"loss": 0.9545,
"step": 930
},
{
"epoch": 0.5678042887345213,
"grad_norm": 1.114040839440962,
"learning_rate": 4.604501607717042e-05,
"loss": 1.0,
"step": 940
},
{
"epoch": 0.5738447598912715,
"grad_norm": 1.2120423884348053,
"learning_rate": 4.5401929260450165e-05,
"loss": 0.9525,
"step": 950
},
{
"epoch": 0.5798852310480217,
"grad_norm": 0.9841344976466476,
"learning_rate": 4.47588424437299e-05,
"loss": 1.0389,
"step": 960
},
{
"epoch": 0.585925702204772,
"grad_norm": 1.0459005071658793,
"learning_rate": 4.4115755627009646e-05,
"loss": 1.0041,
"step": 970
},
{
"epoch": 0.5919661733615222,
"grad_norm": 1.2096290639870764,
"learning_rate": 4.347266881028939e-05,
"loss": 0.9939,
"step": 980
},
{
"epoch": 0.5980066445182725,
"grad_norm": 1.0171142436328486,
"learning_rate": 4.2829581993569134e-05,
"loss": 0.9432,
"step": 990
},
{
"epoch": 0.6040471156750227,
"grad_norm": 1.0557726010616861,
"learning_rate": 4.218649517684888e-05,
"loss": 1.0041,
"step": 1000
},
{
"epoch": 0.6100875868317729,
"grad_norm": 0.9854936325370102,
"learning_rate": 4.154340836012862e-05,
"loss": 0.9598,
"step": 1010
},
{
"epoch": 0.6161280579885231,
"grad_norm": 1.0002881708013533,
"learning_rate": 4.090032154340836e-05,
"loss": 0.9537,
"step": 1020
},
{
"epoch": 0.6221685291452733,
"grad_norm": 1.0163254545569222,
"learning_rate": 4.02572347266881e-05,
"loss": 0.9781,
"step": 1030
},
{
"epoch": 0.6282090003020235,
"grad_norm": 1.0700856083800017,
"learning_rate": 3.961414790996785e-05,
"loss": 0.9418,
"step": 1040
},
{
"epoch": 0.6342494714587738,
"grad_norm": 0.925802326406659,
"learning_rate": 3.897106109324759e-05,
"loss": 0.9355,
"step": 1050
},
{
"epoch": 0.640289942615524,
"grad_norm": 1.0173964783122673,
"learning_rate": 3.8327974276527335e-05,
"loss": 0.9311,
"step": 1060
},
{
"epoch": 0.6463304137722743,
"grad_norm": 1.0886760638416628,
"learning_rate": 3.768488745980708e-05,
"loss": 1.0104,
"step": 1070
},
{
"epoch": 0.6523708849290245,
"grad_norm": 0.8784480294988184,
"learning_rate": 3.7041800643086816e-05,
"loss": 0.9631,
"step": 1080
},
{
"epoch": 0.6584113560857747,
"grad_norm": 1.0061477546516637,
"learning_rate": 3.639871382636656e-05,
"loss": 0.9209,
"step": 1090
},
{
"epoch": 0.6644518272425249,
"grad_norm": 1.0443361002098694,
"learning_rate": 3.5755627009646303e-05,
"loss": 0.9494,
"step": 1100
},
{
"epoch": 0.6704922983992752,
"grad_norm": 1.064188874483296,
"learning_rate": 3.511254019292605e-05,
"loss": 0.9871,
"step": 1110
},
{
"epoch": 0.6765327695560254,
"grad_norm": 0.9804777210337282,
"learning_rate": 3.446945337620579e-05,
"loss": 0.9357,
"step": 1120
},
{
"epoch": 0.6825732407127756,
"grad_norm": 1.0053083581127769,
"learning_rate": 3.3826366559485535e-05,
"loss": 0.9637,
"step": 1130
},
{
"epoch": 0.6886137118695258,
"grad_norm": 1.0062328413826747,
"learning_rate": 3.318327974276528e-05,
"loss": 0.9914,
"step": 1140
},
{
"epoch": 0.694654183026276,
"grad_norm": 1.0659942748249296,
"learning_rate": 3.2540192926045016e-05,
"loss": 0.9332,
"step": 1150
},
{
"epoch": 0.7006946541830262,
"grad_norm": 1.2425227959394274,
"learning_rate": 3.189710610932476e-05,
"loss": 0.9951,
"step": 1160
},
{
"epoch": 0.7067351253397764,
"grad_norm": 1.0269910163244402,
"learning_rate": 3.1254019292604504e-05,
"loss": 0.9805,
"step": 1170
},
{
"epoch": 0.7127755964965268,
"grad_norm": 1.067485855484705,
"learning_rate": 3.061093247588425e-05,
"loss": 0.975,
"step": 1180
},
{
"epoch": 0.718816067653277,
"grad_norm": 0.9819234749980894,
"learning_rate": 2.996784565916399e-05,
"loss": 0.9805,
"step": 1190
},
{
"epoch": 0.7248565388100272,
"grad_norm": 0.9915476687600292,
"learning_rate": 2.9324758842443732e-05,
"loss": 0.9365,
"step": 1200
},
{
"epoch": 0.7308970099667774,
"grad_norm": 1.048821106029052,
"learning_rate": 2.8681672025723473e-05,
"loss": 0.9861,
"step": 1210
},
{
"epoch": 0.7369374811235276,
"grad_norm": 0.9121022219179783,
"learning_rate": 2.8038585209003217e-05,
"loss": 0.9854,
"step": 1220
},
{
"epoch": 0.7429779522802779,
"grad_norm": 0.9525288844616361,
"learning_rate": 2.739549839228296e-05,
"loss": 0.948,
"step": 1230
},
{
"epoch": 0.7490184234370281,
"grad_norm": 1.1391100357014714,
"learning_rate": 2.67524115755627e-05,
"loss": 0.8887,
"step": 1240
},
{
"epoch": 0.7550588945937783,
"grad_norm": 1.1078585866746686,
"learning_rate": 2.6109324758842445e-05,
"loss": 0.9715,
"step": 1250
},
{
"epoch": 0.7610993657505285,
"grad_norm": 0.9323091046055703,
"learning_rate": 2.546623794212219e-05,
"loss": 0.9359,
"step": 1260
},
{
"epoch": 0.7671398369072787,
"grad_norm": 1.146046378807531,
"learning_rate": 2.482315112540193e-05,
"loss": 0.8967,
"step": 1270
},
{
"epoch": 0.773180308064029,
"grad_norm": 1.14163561365635,
"learning_rate": 2.4180064308681673e-05,
"loss": 0.9707,
"step": 1280
},
{
"epoch": 0.7792207792207793,
"grad_norm": 1.0034307361335086,
"learning_rate": 2.3536977491961414e-05,
"loss": 0.9668,
"step": 1290
},
{
"epoch": 0.7852612503775295,
"grad_norm": 1.1199578096409222,
"learning_rate": 2.2893890675241158e-05,
"loss": 0.968,
"step": 1300
},
{
"epoch": 0.7913017215342797,
"grad_norm": 1.0809213063777794,
"learning_rate": 2.22508038585209e-05,
"loss": 0.9264,
"step": 1310
},
{
"epoch": 0.7973421926910299,
"grad_norm": 1.1266044230874084,
"learning_rate": 2.1607717041800642e-05,
"loss": 1.0203,
"step": 1320
},
{
"epoch": 0.8033826638477801,
"grad_norm": 0.8540728431635001,
"learning_rate": 2.0964630225080386e-05,
"loss": 0.924,
"step": 1330
},
{
"epoch": 0.8094231350045303,
"grad_norm": 1.0063045365537524,
"learning_rate": 2.032154340836013e-05,
"loss": 0.9656,
"step": 1340
},
{
"epoch": 0.8154636061612806,
"grad_norm": 0.9432512605760064,
"learning_rate": 1.967845659163987e-05,
"loss": 1.0254,
"step": 1350
},
{
"epoch": 0.8215040773180308,
"grad_norm": 1.162199676010242,
"learning_rate": 1.9035369774919614e-05,
"loss": 0.9549,
"step": 1360
},
{
"epoch": 0.827544548474781,
"grad_norm": 1.0184734737311432,
"learning_rate": 1.8392282958199358e-05,
"loss": 0.8937,
"step": 1370
},
{
"epoch": 0.8335850196315313,
"grad_norm": 1.0321283898574098,
"learning_rate": 1.77491961414791e-05,
"loss": 0.9641,
"step": 1380
},
{
"epoch": 0.8396254907882815,
"grad_norm": 0.948342731761788,
"learning_rate": 1.7106109324758842e-05,
"loss": 0.907,
"step": 1390
},
{
"epoch": 0.8456659619450317,
"grad_norm": 1.016072519476065,
"learning_rate": 1.6463022508038586e-05,
"loss": 0.999,
"step": 1400
},
{
"epoch": 0.851706433101782,
"grad_norm": 0.8891894724654406,
"learning_rate": 1.581993569131833e-05,
"loss": 0.9238,
"step": 1410
},
{
"epoch": 0.8577469042585322,
"grad_norm": 1.0116016221718374,
"learning_rate": 1.517684887459807e-05,
"loss": 0.9488,
"step": 1420
},
{
"epoch": 0.8637873754152824,
"grad_norm": 1.092739541532347,
"learning_rate": 1.4533762057877815e-05,
"loss": 0.9971,
"step": 1430
},
{
"epoch": 0.8698278465720326,
"grad_norm": 0.8563957174375877,
"learning_rate": 1.3890675241157558e-05,
"loss": 1.0133,
"step": 1440
},
{
"epoch": 0.8758683177287828,
"grad_norm": 1.089288756096709,
"learning_rate": 1.3247588424437299e-05,
"loss": 0.9127,
"step": 1450
},
{
"epoch": 0.881908788885533,
"grad_norm": 0.9458299067214011,
"learning_rate": 1.2604501607717043e-05,
"loss": 0.9668,
"step": 1460
},
{
"epoch": 0.8879492600422833,
"grad_norm": 1.2229020868039389,
"learning_rate": 1.1961414790996785e-05,
"loss": 0.9506,
"step": 1470
},
{
"epoch": 0.8939897311990336,
"grad_norm": 1.0615217830735095,
"learning_rate": 1.1318327974276529e-05,
"loss": 0.9219,
"step": 1480
},
{
"epoch": 0.9000302023557838,
"grad_norm": 1.1622944573297567,
"learning_rate": 1.0675241157556271e-05,
"loss": 0.9391,
"step": 1490
},
{
"epoch": 0.906070673512534,
"grad_norm": 0.9443566657008828,
"learning_rate": 1.0032154340836013e-05,
"loss": 0.8955,
"step": 1500
},
{
"epoch": 0.9121111446692842,
"grad_norm": 1.1367332066610845,
"learning_rate": 9.389067524115757e-06,
"loss": 0.9385,
"step": 1510
},
{
"epoch": 0.9181516158260344,
"grad_norm": 0.9414922696266849,
"learning_rate": 8.7459807073955e-06,
"loss": 0.9318,
"step": 1520
},
{
"epoch": 0.9241920869827847,
"grad_norm": 1.0844935096035118,
"learning_rate": 8.102893890675242e-06,
"loss": 0.9311,
"step": 1530
},
{
"epoch": 0.9302325581395349,
"grad_norm": 1.120509038145209,
"learning_rate": 7.459807073954985e-06,
"loss": 0.9422,
"step": 1540
},
{
"epoch": 0.9362730292962851,
"grad_norm": 0.9486397409946379,
"learning_rate": 6.816720257234727e-06,
"loss": 0.9162,
"step": 1550
},
{
"epoch": 0.9423135004530353,
"grad_norm": 1.1412479158621043,
"learning_rate": 6.17363344051447e-06,
"loss": 0.9676,
"step": 1560
},
{
"epoch": 0.9483539716097855,
"grad_norm": 1.050318112867144,
"learning_rate": 5.530546623794212e-06,
"loss": 0.9754,
"step": 1570
},
{
"epoch": 0.9543944427665358,
"grad_norm": 1.0466438135565226,
"learning_rate": 4.887459807073955e-06,
"loss": 0.926,
"step": 1580
},
{
"epoch": 0.9604349139232861,
"grad_norm": 0.9720115456232871,
"learning_rate": 4.244372990353698e-06,
"loss": 0.9447,
"step": 1590
},
{
"epoch": 0.9664753850800363,
"grad_norm": 0.8786923129454015,
"learning_rate": 3.6012861736334403e-06,
"loss": 0.9443,
"step": 1600
},
{
"epoch": 0.9725158562367865,
"grad_norm": 1.0733513985052048,
"learning_rate": 2.9581993569131834e-06,
"loss": 0.9053,
"step": 1610
},
{
"epoch": 0.9785563273935367,
"grad_norm": 0.8731368575153022,
"learning_rate": 2.315112540192926e-06,
"loss": 0.9803,
"step": 1620
},
{
"epoch": 0.9845967985502869,
"grad_norm": 1.0060959243542735,
"learning_rate": 1.6720257234726688e-06,
"loss": 0.9563,
"step": 1630
},
{
"epoch": 0.9906372697070371,
"grad_norm": 0.9113226806468382,
"learning_rate": 1.0289389067524116e-06,
"loss": 0.9191,
"step": 1640
},
{
"epoch": 0.9966777408637874,
"grad_norm": 0.9160377841463557,
"learning_rate": 3.8585209003215437e-07,
"loss": 0.9117,
"step": 1650
}
],
"logging_steps": 10,
"max_steps": 1655,
"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": 0.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}