original_checkpoint-1950 / trainer_state.json
YYT-t's picture
Upload folder using huggingface_hub
ad5e52a verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2609393817743878,
"eval_steps": 999999,
"global_step": 1950,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0013381506757660913,
"grad_norm": 43.25,
"learning_rate": 6.684491978609625e-09,
"loss": -1.2338,
"step": 10
},
{
"epoch": 0.0026763013515321826,
"grad_norm": 66.0,
"learning_rate": 1.336898395721925e-08,
"loss": -0.96,
"step": 20
},
{
"epoch": 0.004014452027298274,
"grad_norm": 77.5,
"learning_rate": 2.0053475935828877e-08,
"loss": -0.7695,
"step": 30
},
{
"epoch": 0.005352602703064365,
"grad_norm": 156.0,
"learning_rate": 2.67379679144385e-08,
"loss": -0.5852,
"step": 40
},
{
"epoch": 0.006690753378830456,
"grad_norm": 49.25,
"learning_rate": 3.342245989304813e-08,
"loss": -1.3508,
"step": 50
},
{
"epoch": 0.008028904054596548,
"grad_norm": 145.0,
"learning_rate": 4.0106951871657754e-08,
"loss": -0.7302,
"step": 60
},
{
"epoch": 0.009367054730362638,
"grad_norm": 4.96875,
"learning_rate": 4.679144385026738e-08,
"loss": -0.5402,
"step": 70
},
{
"epoch": 0.01070520540612873,
"grad_norm": 56.5,
"learning_rate": 5.3475935828877e-08,
"loss": -1.5851,
"step": 80
},
{
"epoch": 0.01204335608189482,
"grad_norm": 97.0,
"learning_rate": 6.016042780748662e-08,
"loss": -1.9164,
"step": 90
},
{
"epoch": 0.013381506757660913,
"grad_norm": 157.0,
"learning_rate": 6.684491978609626e-08,
"loss": -1.0399,
"step": 100
},
{
"epoch": 0.014719657433427003,
"grad_norm": 346.0,
"learning_rate": 7.352941176470588e-08,
"loss": -0.788,
"step": 110
},
{
"epoch": 0.016057808109193095,
"grad_norm": 416.0,
"learning_rate": 8.021390374331551e-08,
"loss": -1.6681,
"step": 120
},
{
"epoch": 0.017395958784959187,
"grad_norm": 58.0,
"learning_rate": 8.689839572192513e-08,
"loss": -0.9137,
"step": 130
},
{
"epoch": 0.018734109460725276,
"grad_norm": 7.03125,
"learning_rate": 9.358288770053476e-08,
"loss": -0.8646,
"step": 140
},
{
"epoch": 0.02007226013649137,
"grad_norm": 63.0,
"learning_rate": 1.0026737967914438e-07,
"loss": -0.5643,
"step": 150
},
{
"epoch": 0.02141041081225746,
"grad_norm": 46.0,
"learning_rate": 1.06951871657754e-07,
"loss": -0.8626,
"step": 160
},
{
"epoch": 0.022748561488023553,
"grad_norm": 91.0,
"learning_rate": 1.1363636363636363e-07,
"loss": -0.9937,
"step": 170
},
{
"epoch": 0.02408671216378964,
"grad_norm": 45.75,
"learning_rate": 1.2032085561497325e-07,
"loss": -1.1182,
"step": 180
},
{
"epoch": 0.025424862839555733,
"grad_norm": 69.5,
"learning_rate": 1.2700534759358288e-07,
"loss": -1.2665,
"step": 190
},
{
"epoch": 0.026763013515321826,
"grad_norm": 15.1875,
"learning_rate": 1.3368983957219251e-07,
"loss": -0.4304,
"step": 200
},
{
"epoch": 0.028101164191087918,
"grad_norm": 360.0,
"learning_rate": 1.4037433155080215e-07,
"loss": -2.4656,
"step": 210
},
{
"epoch": 0.029439314866854006,
"grad_norm": 11.5,
"learning_rate": 1.4705882352941175e-07,
"loss": -0.7774,
"step": 220
},
{
"epoch": 0.0307774655426201,
"grad_norm": 3.703125,
"learning_rate": 1.5374331550802138e-07,
"loss": -0.8901,
"step": 230
},
{
"epoch": 0.03211561621838619,
"grad_norm": 255.0,
"learning_rate": 1.6042780748663102e-07,
"loss": -1.2436,
"step": 240
},
{
"epoch": 0.03345376689415228,
"grad_norm": 72.0,
"learning_rate": 1.6711229946524065e-07,
"loss": -1.1494,
"step": 250
},
{
"epoch": 0.034791917569918375,
"grad_norm": 81.5,
"learning_rate": 1.7379679144385025e-07,
"loss": -1.0291,
"step": 260
},
{
"epoch": 0.03613006824568447,
"grad_norm": 9.0,
"learning_rate": 1.804812834224599e-07,
"loss": -0.7383,
"step": 270
},
{
"epoch": 0.03746821892145055,
"grad_norm": 10.9375,
"learning_rate": 1.8716577540106952e-07,
"loss": -0.7876,
"step": 280
},
{
"epoch": 0.038806369597216644,
"grad_norm": 26.125,
"learning_rate": 1.9385026737967912e-07,
"loss": -0.7877,
"step": 290
},
{
"epoch": 0.04014452027298274,
"grad_norm": 175.0,
"learning_rate": 2.0053475935828876e-07,
"loss": -1.557,
"step": 300
},
{
"epoch": 0.04148267094874883,
"grad_norm": 59.75,
"learning_rate": 2.072192513368984e-07,
"loss": -1.0401,
"step": 310
},
{
"epoch": 0.04282082162451492,
"grad_norm": 11.0625,
"learning_rate": 2.13903743315508e-07,
"loss": -0.8737,
"step": 320
},
{
"epoch": 0.04415897230028101,
"grad_norm": 13.5625,
"learning_rate": 2.2058823529411763e-07,
"loss": -0.8872,
"step": 330
},
{
"epoch": 0.045497122976047105,
"grad_norm": 7.71875,
"learning_rate": 2.2727272727272726e-07,
"loss": -0.6217,
"step": 340
},
{
"epoch": 0.0468352736518132,
"grad_norm": 21.75,
"learning_rate": 2.339572192513369e-07,
"loss": -1.1064,
"step": 350
},
{
"epoch": 0.04817342432757928,
"grad_norm": 44.0,
"learning_rate": 2.406417112299465e-07,
"loss": -1.0586,
"step": 360
},
{
"epoch": 0.049511575003345375,
"grad_norm": 32.5,
"learning_rate": 2.473262032085561e-07,
"loss": -0.7374,
"step": 370
},
{
"epoch": 0.05084972567911147,
"grad_norm": 83.0,
"learning_rate": 2.5401069518716576e-07,
"loss": -1.1667,
"step": 380
},
{
"epoch": 0.05218787635487756,
"grad_norm": 33.5,
"learning_rate": 2.6069518716577537e-07,
"loss": -1.0022,
"step": 390
},
{
"epoch": 0.05352602703064365,
"grad_norm": 181.0,
"learning_rate": 2.6737967914438503e-07,
"loss": -0.911,
"step": 400
},
{
"epoch": 0.05486417770640974,
"grad_norm": 169.0,
"learning_rate": 2.7406417112299463e-07,
"loss": -1.4837,
"step": 410
},
{
"epoch": 0.056202328382175835,
"grad_norm": 164.0,
"learning_rate": 2.807486631016043e-07,
"loss": -0.9708,
"step": 420
},
{
"epoch": 0.05754047905794193,
"grad_norm": 31.0,
"learning_rate": 2.874331550802139e-07,
"loss": -0.8173,
"step": 430
},
{
"epoch": 0.05887862973370801,
"grad_norm": 33.75,
"learning_rate": 2.941176470588235e-07,
"loss": -0.7977,
"step": 440
},
{
"epoch": 0.060216780409474105,
"grad_norm": 54.25,
"learning_rate": 3.008021390374331e-07,
"loss": -1.421,
"step": 450
},
{
"epoch": 0.0615549310852402,
"grad_norm": 34.75,
"learning_rate": 3.0748663101604277e-07,
"loss": -0.5687,
"step": 460
},
{
"epoch": 0.06289308176100629,
"grad_norm": 45.25,
"learning_rate": 3.141711229946524e-07,
"loss": -0.9605,
"step": 470
},
{
"epoch": 0.06423123243677238,
"grad_norm": 14.9375,
"learning_rate": 3.2085561497326203e-07,
"loss": -1.0447,
"step": 480
},
{
"epoch": 0.06556938311253847,
"grad_norm": 161.0,
"learning_rate": 3.2754010695187164e-07,
"loss": -1.2917,
"step": 490
},
{
"epoch": 0.06690753378830457,
"grad_norm": 38.25,
"learning_rate": 3.342245989304813e-07,
"loss": -0.7867,
"step": 500
},
{
"epoch": 0.06824568446407066,
"grad_norm": 268.0,
"learning_rate": 3.4090909090909085e-07,
"loss": -1.5734,
"step": 510
},
{
"epoch": 0.06958383513983675,
"grad_norm": 134.0,
"learning_rate": 3.475935828877005e-07,
"loss": -0.8703,
"step": 520
},
{
"epoch": 0.07092198581560284,
"grad_norm": 87.5,
"learning_rate": 3.542780748663101e-07,
"loss": -0.8778,
"step": 530
},
{
"epoch": 0.07226013649136893,
"grad_norm": 44.75,
"learning_rate": 3.609625668449198e-07,
"loss": -0.8009,
"step": 540
},
{
"epoch": 0.07359828716713501,
"grad_norm": 14.75,
"learning_rate": 3.6764705882352943e-07,
"loss": -0.642,
"step": 550
},
{
"epoch": 0.0749364378429011,
"grad_norm": 213.0,
"learning_rate": 3.7433155080213904e-07,
"loss": -1.1518,
"step": 560
},
{
"epoch": 0.0762745885186672,
"grad_norm": 77.0,
"learning_rate": 3.8101604278074864e-07,
"loss": -0.7262,
"step": 570
},
{
"epoch": 0.07761273919443329,
"grad_norm": 20.5,
"learning_rate": 3.8770053475935825e-07,
"loss": -0.6358,
"step": 580
},
{
"epoch": 0.07895088987019938,
"grad_norm": 6.625,
"learning_rate": 3.943850267379679e-07,
"loss": -0.4141,
"step": 590
},
{
"epoch": 0.08028904054596547,
"grad_norm": 42.75,
"learning_rate": 4.010695187165775e-07,
"loss": -0.8822,
"step": 600
},
{
"epoch": 0.08162719122173157,
"grad_norm": 42.75,
"learning_rate": 4.0775401069518717e-07,
"loss": -0.4594,
"step": 610
},
{
"epoch": 0.08296534189749766,
"grad_norm": 202.0,
"learning_rate": 4.144385026737968e-07,
"loss": -2.2936,
"step": 620
},
{
"epoch": 0.08430349257326375,
"grad_norm": 124.5,
"learning_rate": 4.2112299465240644e-07,
"loss": -0.8653,
"step": 630
},
{
"epoch": 0.08564164324902984,
"grad_norm": 149.0,
"learning_rate": 4.27807486631016e-07,
"loss": -1.6982,
"step": 640
},
{
"epoch": 0.08697979392479593,
"grad_norm": 262.0,
"learning_rate": 4.3449197860962565e-07,
"loss": -1.3561,
"step": 650
},
{
"epoch": 0.08831794460056203,
"grad_norm": 42.75,
"learning_rate": 4.4117647058823526e-07,
"loss": -1.4205,
"step": 660
},
{
"epoch": 0.08965609527632812,
"grad_norm": 430.0,
"learning_rate": 4.478609625668449e-07,
"loss": -1.6911,
"step": 670
},
{
"epoch": 0.09099424595209421,
"grad_norm": 54.75,
"learning_rate": 4.545454545454545e-07,
"loss": -1.7924,
"step": 680
},
{
"epoch": 0.0923323966278603,
"grad_norm": 41.0,
"learning_rate": 4.612299465240642e-07,
"loss": -1.2441,
"step": 690
},
{
"epoch": 0.0936705473036264,
"grad_norm": 121.0,
"learning_rate": 4.679144385026738e-07,
"loss": -1.1202,
"step": 700
},
{
"epoch": 0.09500869797939247,
"grad_norm": 26.125,
"learning_rate": 4.745989304812834e-07,
"loss": -0.8682,
"step": 710
},
{
"epoch": 0.09634684865515857,
"grad_norm": 65.0,
"learning_rate": 4.81283422459893e-07,
"loss": -1.1251,
"step": 720
},
{
"epoch": 0.09768499933092466,
"grad_norm": 164.0,
"learning_rate": 4.879679144385027e-07,
"loss": -1.714,
"step": 730
},
{
"epoch": 0.09902315000669075,
"grad_norm": 278.0,
"learning_rate": 4.946524064171122e-07,
"loss": -1.7572,
"step": 740
},
{
"epoch": 0.10036130068245684,
"grad_norm": 8.5,
"learning_rate": 4.999998908848282e-07,
"loss": -1.4453,
"step": 750
},
{
"epoch": 0.10169945135822293,
"grad_norm": 5.8125,
"learning_rate": 4.999960718638164e-07,
"loss": -1.0203,
"step": 760
},
{
"epoch": 0.10303760203398903,
"grad_norm": 462.0,
"learning_rate": 4.999867971794632e-07,
"loss": -1.7162,
"step": 770
},
{
"epoch": 0.10437575270975512,
"grad_norm": 42.25,
"learning_rate": 4.999720670341701e-07,
"loss": -2.1454,
"step": 780
},
{
"epoch": 0.10571390338552121,
"grad_norm": 956.0,
"learning_rate": 4.99951881749393e-07,
"loss": -1.8669,
"step": 790
},
{
"epoch": 0.1070520540612873,
"grad_norm": 11.5625,
"learning_rate": 4.999262417656353e-07,
"loss": -2.2964,
"step": 800
},
{
"epoch": 0.1083902047370534,
"grad_norm": 7.40625,
"learning_rate": 4.998951476424382e-07,
"loss": -1.1538,
"step": 810
},
{
"epoch": 0.10972835541281949,
"grad_norm": 1368.0,
"learning_rate": 4.998586000583687e-07,
"loss": -3.0573,
"step": 820
},
{
"epoch": 0.11106650608858558,
"grad_norm": 1768.0,
"learning_rate": 4.998165998110045e-07,
"loss": -2.3538,
"step": 830
},
{
"epoch": 0.11240465676435167,
"grad_norm": 125.0,
"learning_rate": 4.99769147816917e-07,
"loss": -1.1908,
"step": 840
},
{
"epoch": 0.11374280744011776,
"grad_norm": 716.0,
"learning_rate": 4.997162451116507e-07,
"loss": -1.2429,
"step": 850
},
{
"epoch": 0.11508095811588386,
"grad_norm": 72.0,
"learning_rate": 4.996578928497012e-07,
"loss": -2.3002,
"step": 860
},
{
"epoch": 0.11641910879164993,
"grad_norm": 16.0,
"learning_rate": 4.995940923044898e-07,
"loss": -1.9943,
"step": 870
},
{
"epoch": 0.11775725946741603,
"grad_norm": 150.0,
"learning_rate": 4.995248448683355e-07,
"loss": -2.9556,
"step": 880
},
{
"epoch": 0.11909541014318212,
"grad_norm": 54.75,
"learning_rate": 4.994501520524248e-07,
"loss": -2.435,
"step": 890
},
{
"epoch": 0.12043356081894821,
"grad_norm": 56.75,
"learning_rate": 4.993700154867787e-07,
"loss": -2.0542,
"step": 900
},
{
"epoch": 0.1217717114947143,
"grad_norm": 163.0,
"learning_rate": 4.992844369202173e-07,
"loss": -3.1973,
"step": 910
},
{
"epoch": 0.1231098621704804,
"grad_norm": 14.75,
"learning_rate": 4.991934182203214e-07,
"loss": -4.3573,
"step": 920
},
{
"epoch": 0.12444801284624649,
"grad_norm": 20.375,
"learning_rate": 4.990969613733915e-07,
"loss": -4.3314,
"step": 930
},
{
"epoch": 0.12578616352201258,
"grad_norm": 35.0,
"learning_rate": 4.989950684844051e-07,
"loss": -3.9402,
"step": 940
},
{
"epoch": 0.12712431419777867,
"grad_norm": 16.375,
"learning_rate": 4.988877417769705e-07,
"loss": -3.3578,
"step": 950
},
{
"epoch": 0.12846246487354476,
"grad_norm": 163.0,
"learning_rate": 4.987749835932777e-07,
"loss": -6.255,
"step": 960
},
{
"epoch": 0.12980061554931085,
"grad_norm": 61.75,
"learning_rate": 4.986567963940486e-07,
"loss": -5.0546,
"step": 970
},
{
"epoch": 0.13113876622507695,
"grad_norm": 49.0,
"learning_rate": 4.985331827584815e-07,
"loss": -3.643,
"step": 980
},
{
"epoch": 0.13247691690084304,
"grad_norm": 155.0,
"learning_rate": 4.984041453841966e-07,
"loss": -3.2031,
"step": 990
},
{
"epoch": 0.13381506757660913,
"grad_norm": 77.0,
"learning_rate": 4.982696870871761e-07,
"loss": -3.013,
"step": 1000
},
{
"epoch": 0.13515321825237522,
"grad_norm": 24.875,
"learning_rate": 4.981298108017027e-07,
"loss": -4.3903,
"step": 1010
},
{
"epoch": 0.13649136892814132,
"grad_norm": 44.5,
"learning_rate": 4.979845195802961e-07,
"loss": -3.194,
"step": 1020
},
{
"epoch": 0.1378295196039074,
"grad_norm": 32.25,
"learning_rate": 4.978338165936462e-07,
"loss": -3.9074,
"step": 1030
},
{
"epoch": 0.1391676702796735,
"grad_norm": 148.0,
"learning_rate": 4.976777051305436e-07,
"loss": -5.6556,
"step": 1040
},
{
"epoch": 0.1405058209554396,
"grad_norm": 366.0,
"learning_rate": 4.975161885978083e-07,
"loss": -4.4532,
"step": 1050
},
{
"epoch": 0.14184397163120568,
"grad_norm": 37.0,
"learning_rate": 4.973492705202148e-07,
"loss": -5.3149,
"step": 1060
},
{
"epoch": 0.14318212230697178,
"grad_norm": 2944.0,
"learning_rate": 4.971769545404158e-07,
"loss": -6.5053,
"step": 1070
},
{
"epoch": 0.14452027298273787,
"grad_norm": 388.0,
"learning_rate": 4.969992444188623e-07,
"loss": -5.4356,
"step": 1080
},
{
"epoch": 0.14585842365850396,
"grad_norm": 125.5,
"learning_rate": 4.968161440337216e-07,
"loss": -4.2288,
"step": 1090
},
{
"epoch": 0.14719657433427003,
"grad_norm": 56.0,
"learning_rate": 4.966276573807928e-07,
"loss": -5.4162,
"step": 1100
},
{
"epoch": 0.14853472501003612,
"grad_norm": 2112.0,
"learning_rate": 4.964337885734192e-07,
"loss": -10.277,
"step": 1110
},
{
"epoch": 0.1498728756858022,
"grad_norm": 67.5,
"learning_rate": 4.962345418423992e-07,
"loss": -7.698,
"step": 1120
},
{
"epoch": 0.1512110263615683,
"grad_norm": 44.25,
"learning_rate": 4.960299215358934e-07,
"loss": -3.43,
"step": 1130
},
{
"epoch": 0.1525491770373344,
"grad_norm": 2992.0,
"learning_rate": 4.958199321193302e-07,
"loss": -11.3613,
"step": 1140
},
{
"epoch": 0.15388732771310049,
"grad_norm": 3296.0,
"learning_rate": 4.956045781753075e-07,
"loss": -12.9118,
"step": 1150
},
{
"epoch": 0.15522547838886658,
"grad_norm": 3120.0,
"learning_rate": 4.95383864403494e-07,
"loss": -7.3724,
"step": 1160
},
{
"epoch": 0.15656362906463267,
"grad_norm": 146.0,
"learning_rate": 4.951577956205252e-07,
"loss": -8.3391,
"step": 1170
},
{
"epoch": 0.15790177974039876,
"grad_norm": 3408.0,
"learning_rate": 4.949263767598995e-07,
"loss": -10.8889,
"step": 1180
},
{
"epoch": 0.15923993041616485,
"grad_norm": 3632.0,
"learning_rate": 4.946896128718698e-07,
"loss": -9.2901,
"step": 1190
},
{
"epoch": 0.16057808109193095,
"grad_norm": 4448.0,
"learning_rate": 4.944475091233333e-07,
"loss": -12.0885,
"step": 1200
},
{
"epoch": 0.16191623176769704,
"grad_norm": 2816.0,
"learning_rate": 4.942000707977195e-07,
"loss": -12.379,
"step": 1210
},
{
"epoch": 0.16325438244346313,
"grad_norm": 286.0,
"learning_rate": 4.939473032948741e-07,
"loss": -2.5466,
"step": 1220
},
{
"epoch": 0.16459253311922922,
"grad_norm": 83.5,
"learning_rate": 4.936892121309411e-07,
"loss": -5.7836,
"step": 1230
},
{
"epoch": 0.16593068379499532,
"grad_norm": 5152.0,
"learning_rate": 4.934258029382431e-07,
"loss": -19.1814,
"step": 1240
},
{
"epoch": 0.1672688344707614,
"grad_norm": 65.0,
"learning_rate": 4.93157081465158e-07,
"loss": -5.7378,
"step": 1250
},
{
"epoch": 0.1686069851465275,
"grad_norm": 83.5,
"learning_rate": 4.928830535759934e-07,
"loss": -13.2967,
"step": 1260
},
{
"epoch": 0.1699451358222936,
"grad_norm": 8032.0,
"learning_rate": 4.926037252508591e-07,
"loss": -9.7339,
"step": 1270
},
{
"epoch": 0.17128328649805968,
"grad_norm": 55.5,
"learning_rate": 4.923191025855359e-07,
"loss": -4.0844,
"step": 1280
},
{
"epoch": 0.17262143717382578,
"grad_norm": 38.0,
"learning_rate": 4.920291917913432e-07,
"loss": -12.4584,
"step": 1290
},
{
"epoch": 0.17395958784959187,
"grad_norm": 115.0,
"learning_rate": 4.917339991950032e-07,
"loss": -8.7411,
"step": 1300
},
{
"epoch": 0.17529773852535796,
"grad_norm": 141.0,
"learning_rate": 4.914335312385027e-07,
"loss": -9.0839,
"step": 1310
},
{
"epoch": 0.17663588920112405,
"grad_norm": 7488.0,
"learning_rate": 4.911277944789531e-07,
"loss": -16.2416,
"step": 1320
},
{
"epoch": 0.17797403987689014,
"grad_norm": 27.625,
"learning_rate": 4.908167955884461e-07,
"loss": -1.2109,
"step": 1330
},
{
"epoch": 0.17931219055265624,
"grad_norm": 1944.0,
"learning_rate": 4.905005413539098e-07,
"loss": -12.3225,
"step": 1340
},
{
"epoch": 0.18065034122842233,
"grad_norm": 75.0,
"learning_rate": 4.90179038676959e-07,
"loss": -2.7202,
"step": 1350
},
{
"epoch": 0.18198849190418842,
"grad_norm": 63.5,
"learning_rate": 4.898522945737453e-07,
"loss": -4.8082,
"step": 1360
},
{
"epoch": 0.1833266425799545,
"grad_norm": 82.5,
"learning_rate": 4.895203161748042e-07,
"loss": -9.3348,
"step": 1370
},
{
"epoch": 0.1846647932557206,
"grad_norm": 133.0,
"learning_rate": 4.89183110724899e-07,
"loss": -2.2605,
"step": 1380
},
{
"epoch": 0.1860029439314867,
"grad_norm": 3808.0,
"learning_rate": 4.888406855828629e-07,
"loss": -4.6184,
"step": 1390
},
{
"epoch": 0.1873410946072528,
"grad_norm": 344.0,
"learning_rate": 4.884930482214386e-07,
"loss": -2.5858,
"step": 1400
},
{
"epoch": 0.18867924528301888,
"grad_norm": 384.0,
"learning_rate": 4.881402062271148e-07,
"loss": -6.3372,
"step": 1410
},
{
"epoch": 0.19001739595878495,
"grad_norm": 82.5,
"learning_rate": 4.877821672999613e-07,
"loss": -2.8738,
"step": 1420
},
{
"epoch": 0.19135554663455104,
"grad_norm": 186.0,
"learning_rate": 4.874189392534599e-07,
"loss": -1.0014,
"step": 1430
},
{
"epoch": 0.19269369731031713,
"grad_norm": 17.625,
"learning_rate": 4.870505300143352e-07,
"loss": -8.9454,
"step": 1440
},
{
"epoch": 0.19403184798608322,
"grad_norm": 1344.0,
"learning_rate": 4.866769476223804e-07,
"loss": -2.1685,
"step": 1450
},
{
"epoch": 0.19536999866184931,
"grad_norm": 153.0,
"learning_rate": 4.862982002302829e-07,
"loss": -0.1105,
"step": 1460
},
{
"epoch": 0.1967081493376154,
"grad_norm": 2704.0,
"learning_rate": 4.859142961034454e-07,
"loss": -4.0817,
"step": 1470
},
{
"epoch": 0.1980463000133815,
"grad_norm": 121.0,
"learning_rate": 4.855252436198064e-07,
"loss": 2.3027,
"step": 1480
},
{
"epoch": 0.1993844506891476,
"grad_norm": 464.0,
"learning_rate": 4.851310512696566e-07,
"loss": -3.0267,
"step": 1490
},
{
"epoch": 0.20072260136491368,
"grad_norm": 688.0,
"learning_rate": 4.847317276554545e-07,
"loss": -8.8319,
"step": 1500
},
{
"epoch": 0.20206075204067978,
"grad_norm": 1912.0,
"learning_rate": 4.843272814916375e-07,
"loss": -8.3295,
"step": 1510
},
{
"epoch": 0.20339890271644587,
"grad_norm": 81.0,
"learning_rate": 4.839177216044329e-07,
"loss": 1.4731,
"step": 1520
},
{
"epoch": 0.20473705339221196,
"grad_norm": 2352.0,
"learning_rate": 4.835030569316646e-07,
"loss": -2.4913,
"step": 1530
},
{
"epoch": 0.20607520406797805,
"grad_norm": 26.875,
"learning_rate": 4.830832965225581e-07,
"loss": -6.6273,
"step": 1540
},
{
"epoch": 0.20741335474374414,
"grad_norm": 156.0,
"learning_rate": 4.826584495375433e-07,
"loss": -4.7107,
"step": 1550
},
{
"epoch": 0.20875150541951024,
"grad_norm": 640.0,
"learning_rate": 4.822285252480543e-07,
"loss": -5.5531,
"step": 1560
},
{
"epoch": 0.21008965609527633,
"grad_norm": 93.0,
"learning_rate": 4.817935330363274e-07,
"loss": -0.0346,
"step": 1570
},
{
"epoch": 0.21142780677104242,
"grad_norm": 398.0,
"learning_rate": 4.813534823951958e-07,
"loss": -6.8717,
"step": 1580
},
{
"epoch": 0.2127659574468085,
"grad_norm": 121.5,
"learning_rate": 4.809083829278831e-07,
"loss": -0.3183,
"step": 1590
},
{
"epoch": 0.2141041081225746,
"grad_norm": 916.0,
"learning_rate": 4.804582443477936e-07,
"loss": -1.5798,
"step": 1600
},
{
"epoch": 0.2154422587983407,
"grad_norm": 10.3125,
"learning_rate": 4.800030764782993e-07,
"loss": -4.0797,
"step": 1610
},
{
"epoch": 0.2167804094741068,
"grad_norm": 3728.0,
"learning_rate": 4.795428892525273e-07,
"loss": -4.8349,
"step": 1620
},
{
"epoch": 0.21811856014987288,
"grad_norm": 162.0,
"learning_rate": 4.790776927131416e-07,
"loss": -2.2261,
"step": 1630
},
{
"epoch": 0.21945671082563897,
"grad_norm": 44.75,
"learning_rate": 4.786074970121246e-07,
"loss": -4.7069,
"step": 1640
},
{
"epoch": 0.22079486150140507,
"grad_norm": 52.25,
"learning_rate": 4.781323124105551e-07,
"loss": -7.4818,
"step": 1650
},
{
"epoch": 0.22213301217717116,
"grad_norm": 532.0,
"learning_rate": 4.776521492783852e-07,
"loss": -2.0291,
"step": 1660
},
{
"epoch": 0.22347116285293725,
"grad_norm": 3968.0,
"learning_rate": 4.771670180942129e-07,
"loss": -6.5649,
"step": 1670
},
{
"epoch": 0.22480931352870334,
"grad_norm": 34.75,
"learning_rate": 4.7667692944505433e-07,
"loss": -4.8102,
"step": 1680
},
{
"epoch": 0.22614746420446943,
"grad_norm": 1384.0,
"learning_rate": 4.761818940261122e-07,
"loss": -7.5108,
"step": 1690
},
{
"epoch": 0.22748561488023553,
"grad_norm": 217.0,
"learning_rate": 4.7568192264054264e-07,
"loss": -2.7564,
"step": 1700
},
{
"epoch": 0.22882376555600162,
"grad_norm": 356.0,
"learning_rate": 4.7517702619921935e-07,
"loss": -0.92,
"step": 1710
},
{
"epoch": 0.2301619162317677,
"grad_norm": 540.0,
"learning_rate": 4.746672157204954e-07,
"loss": 2.2638,
"step": 1720
},
{
"epoch": 0.23150006690753377,
"grad_norm": 44.25,
"learning_rate": 4.741525023299631e-07,
"loss": -6.1031,
"step": 1730
},
{
"epoch": 0.23283821758329987,
"grad_norm": 93.0,
"learning_rate": 4.736328972602106e-07,
"loss": -2.0605,
"step": 1740
},
{
"epoch": 0.23417636825906596,
"grad_norm": 1896.0,
"learning_rate": 4.731084118505776e-07,
"loss": -7.2052,
"step": 1750
},
{
"epoch": 0.23551451893483205,
"grad_norm": 35.75,
"learning_rate": 4.7257905754690724e-07,
"loss": 2.7438,
"step": 1760
},
{
"epoch": 0.23685266961059814,
"grad_norm": 195.0,
"learning_rate": 4.720448459012964e-07,
"loss": -2.656,
"step": 1770
},
{
"epoch": 0.23819082028636424,
"grad_norm": 1984.0,
"learning_rate": 4.7150578857184384e-07,
"loss": -7.6791,
"step": 1780
},
{
"epoch": 0.23952897096213033,
"grad_norm": 548.0,
"learning_rate": 4.7096189732239575e-07,
"loss": -2.1757,
"step": 1790
},
{
"epoch": 0.24086712163789642,
"grad_norm": 121.0,
"learning_rate": 4.7041318402228877e-07,
"loss": -4.9406,
"step": 1800
},
{
"epoch": 0.2422052723136625,
"grad_norm": 2480.0,
"learning_rate": 4.698596606460911e-07,
"loss": 6.3874,
"step": 1810
},
{
"epoch": 0.2435434229894286,
"grad_norm": 824.0,
"learning_rate": 4.693013392733415e-07,
"loss": -1.0411,
"step": 1820
},
{
"epoch": 0.2448815736651947,
"grad_norm": 330.0,
"learning_rate": 4.68738232088285e-07,
"loss": -1.7624,
"step": 1830
},
{
"epoch": 0.2462197243409608,
"grad_norm": 2160.0,
"learning_rate": 4.681703513796077e-07,
"loss": 0.637,
"step": 1840
},
{
"epoch": 0.24755787501672688,
"grad_norm": 660.0,
"learning_rate": 4.675977095401682e-07,
"loss": -5.6651,
"step": 1850
},
{
"epoch": 0.24889602569249297,
"grad_norm": 114.0,
"learning_rate": 4.6702031906672725e-07,
"loss": -8.9473,
"step": 1860
},
{
"epoch": 0.25023417636825906,
"grad_norm": 41.0,
"learning_rate": 4.664381925596748e-07,
"loss": -4.5124,
"step": 1870
},
{
"epoch": 0.25157232704402516,
"grad_norm": 70.0,
"learning_rate": 4.658513427227556e-07,
"loss": -4.7603,
"step": 1880
},
{
"epoch": 0.25291047771979125,
"grad_norm": 84.0,
"learning_rate": 4.652597823627915e-07,
"loss": -3.1663,
"step": 1890
},
{
"epoch": 0.25424862839555734,
"grad_norm": 12.0,
"learning_rate": 4.6466352438940186e-07,
"loss": -6.3194,
"step": 1900
},
{
"epoch": 0.25558677907132343,
"grad_norm": 404.0,
"learning_rate": 4.640625818147224e-07,
"loss": -3.6509,
"step": 1910
},
{
"epoch": 0.2569249297470895,
"grad_norm": 90.5,
"learning_rate": 4.634569677531204e-07,
"loss": -2.3439,
"step": 1920
},
{
"epoch": 0.2582630804228556,
"grad_norm": 16.75,
"learning_rate": 4.628466954209095e-07,
"loss": -0.8997,
"step": 1930
},
{
"epoch": 0.2596012310986217,
"grad_norm": 19.125,
"learning_rate": 4.622317781360604e-07,
"loss": -3.01,
"step": 1940
},
{
"epoch": 0.2609393817743878,
"grad_norm": 182.0,
"learning_rate": 4.6161222931791084e-07,
"loss": -4.8218,
"step": 1950
}
],
"logging_steps": 10,
"max_steps": 7473,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}