Grogros's picture
Training in progress, step 2500, checkpoint
a2c3620 verified
raw
history blame
41.1 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 13.085022890778287,
"eval_steps": 500,
"global_step": 2500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.052321778940483975,
"grad_norm": 50.25,
"learning_rate": 8.000000000000001e-07,
"loss": 3.2827,
"step": 10
},
{
"epoch": 0.10464355788096795,
"grad_norm": 282.0,
"learning_rate": 1.6000000000000001e-06,
"loss": 3.2733,
"step": 20
},
{
"epoch": 0.15696533682145192,
"grad_norm": 390.0,
"learning_rate": 2.4000000000000003e-06,
"loss": 3.1571,
"step": 30
},
{
"epoch": 0.2092871157619359,
"grad_norm": 322.0,
"learning_rate": 3.2000000000000003e-06,
"loss": 3.393,
"step": 40
},
{
"epoch": 0.2616088947024199,
"grad_norm": 700.0,
"learning_rate": 4.000000000000001e-06,
"loss": 3.4911,
"step": 50
},
{
"epoch": 0.31393067364290383,
"grad_norm": 1704.0,
"learning_rate": 4.800000000000001e-06,
"loss": 3.9171,
"step": 60
},
{
"epoch": 0.36625245258338784,
"grad_norm": 214.0,
"learning_rate": 5.600000000000001e-06,
"loss": 4.6157,
"step": 70
},
{
"epoch": 0.4185742315238718,
"grad_norm": 1608.0,
"learning_rate": 6.4000000000000006e-06,
"loss": 4.779,
"step": 80
},
{
"epoch": 0.4708960104643558,
"grad_norm": 162.0,
"learning_rate": 7.2000000000000005e-06,
"loss": 4.2508,
"step": 90
},
{
"epoch": 0.5232177894048398,
"grad_norm": 149.0,
"learning_rate": 8.000000000000001e-06,
"loss": 4.6611,
"step": 100
},
{
"epoch": 0.5755395683453237,
"grad_norm": 214.0,
"learning_rate": 8.8e-06,
"loss": 3.9426,
"step": 110
},
{
"epoch": 0.6278613472858077,
"grad_norm": 408.0,
"learning_rate": 9.600000000000001e-06,
"loss": 3.7952,
"step": 120
},
{
"epoch": 0.6801831262262917,
"grad_norm": 71.0,
"learning_rate": 1.04e-05,
"loss": 3.647,
"step": 130
},
{
"epoch": 0.7325049051667757,
"grad_norm": 59.0,
"learning_rate": 1.1200000000000001e-05,
"loss": 3.6275,
"step": 140
},
{
"epoch": 0.7848266841072596,
"grad_norm": 45.25,
"learning_rate": 1.2e-05,
"loss": 3.4353,
"step": 150
},
{
"epoch": 0.8371484630477436,
"grad_norm": 47.0,
"learning_rate": 1.2800000000000001e-05,
"loss": 3.69,
"step": 160
},
{
"epoch": 0.8894702419882276,
"grad_norm": 33.25,
"learning_rate": 1.3600000000000002e-05,
"loss": 3.6108,
"step": 170
},
{
"epoch": 0.9417920209287116,
"grad_norm": 134.0,
"learning_rate": 1.4400000000000001e-05,
"loss": 3.7036,
"step": 180
},
{
"epoch": 0.9941137998691956,
"grad_norm": 45.25,
"learning_rate": 1.5200000000000002e-05,
"loss": 3.4621,
"step": 190
},
{
"epoch": 1.0464355788096795,
"grad_norm": 48.25,
"learning_rate": 1.6000000000000003e-05,
"loss": 3.4607,
"step": 200
},
{
"epoch": 1.0987573577501635,
"grad_norm": 42.0,
"learning_rate": 1.6800000000000002e-05,
"loss": 18.2652,
"step": 210
},
{
"epoch": 1.1510791366906474,
"grad_norm": 41.0,
"learning_rate": 1.76e-05,
"loss": 3.6676,
"step": 220
},
{
"epoch": 1.2034009156311314,
"grad_norm": 25.375,
"learning_rate": 1.8400000000000003e-05,
"loss": 3.3636,
"step": 230
},
{
"epoch": 1.2557226945716153,
"grad_norm": 35.25,
"learning_rate": 1.9200000000000003e-05,
"loss": 3.1784,
"step": 240
},
{
"epoch": 1.3080444735120995,
"grad_norm": 42.0,
"learning_rate": 2e-05,
"loss": 3.7673,
"step": 250
},
{
"epoch": 1.3603662524525835,
"grad_norm": 32.75,
"learning_rate": 1.9999025240093045e-05,
"loss": 3.7099,
"step": 260
},
{
"epoch": 1.4126880313930674,
"grad_norm": 27.625,
"learning_rate": 1.9996101150403543e-05,
"loss": 3.3748,
"step": 270
},
{
"epoch": 1.4650098103335514,
"grad_norm": 24.375,
"learning_rate": 1.9991228300988586e-05,
"loss": 3.1567,
"step": 280
},
{
"epoch": 1.5173315892740353,
"grad_norm": 26.625,
"learning_rate": 1.9984407641819812e-05,
"loss": 3.1535,
"step": 290
},
{
"epoch": 1.5696533682145193,
"grad_norm": 20.125,
"learning_rate": 1.9975640502598243e-05,
"loss": 3.0614,
"step": 300
},
{
"epoch": 1.6219751471550032,
"grad_norm": 23.125,
"learning_rate": 1.9964928592495046e-05,
"loss": 3.071,
"step": 310
},
{
"epoch": 1.6742969260954872,
"grad_norm": 32.25,
"learning_rate": 1.9952273999818312e-05,
"loss": 3.1193,
"step": 320
},
{
"epoch": 1.7266187050359711,
"grad_norm": 19.375,
"learning_rate": 1.9937679191605964e-05,
"loss": 3.0596,
"step": 330
},
{
"epoch": 1.7789404839764553,
"grad_norm": 36.75,
"learning_rate": 1.9921147013144782e-05,
"loss": 2.9772,
"step": 340
},
{
"epoch": 1.831262262916939,
"grad_norm": 27.25,
"learning_rate": 1.9902680687415704e-05,
"loss": 3.0119,
"step": 350
},
{
"epoch": 1.8835840418574232,
"grad_norm": 26.375,
"learning_rate": 1.988228381446553e-05,
"loss": 2.8278,
"step": 360
},
{
"epoch": 1.9359058207979072,
"grad_norm": 27.75,
"learning_rate": 1.985996037070505e-05,
"loss": 2.6952,
"step": 370
},
{
"epoch": 1.9882275997383911,
"grad_norm": 27.5,
"learning_rate": 1.983571470813386e-05,
"loss": 2.5663,
"step": 380
},
{
"epoch": 2.040549378678875,
"grad_norm": 27.375,
"learning_rate": 1.9809551553491918e-05,
"loss": 2.2019,
"step": 390
},
{
"epoch": 2.092871157619359,
"grad_norm": 15.75,
"learning_rate": 1.9781476007338058e-05,
"loss": 2.2746,
"step": 400
},
{
"epoch": 2.145192936559843,
"grad_norm": 38.0,
"learning_rate": 1.9751493543055634e-05,
"loss": 2.4245,
"step": 410
},
{
"epoch": 2.197514715500327,
"grad_norm": 30.125,
"learning_rate": 1.9719610005785466e-05,
"loss": 2.1032,
"step": 420
},
{
"epoch": 2.249836494440811,
"grad_norm": 18.5,
"learning_rate": 1.9685831611286312e-05,
"loss": 2.3059,
"step": 430
},
{
"epoch": 2.302158273381295,
"grad_norm": 26.5,
"learning_rate": 1.9650164944723116e-05,
"loss": 2.025,
"step": 440
},
{
"epoch": 2.354480052321779,
"grad_norm": 18.625,
"learning_rate": 1.961261695938319e-05,
"loss": 2.0708,
"step": 450
},
{
"epoch": 2.4068018312622628,
"grad_norm": 28.25,
"learning_rate": 1.9573194975320672e-05,
"loss": 1.926,
"step": 460
},
{
"epoch": 2.459123610202747,
"grad_norm": 24.75,
"learning_rate": 1.9531906677929472e-05,
"loss": 1.9348,
"step": 470
},
{
"epoch": 2.5114453891432307,
"grad_norm": 48.5,
"learning_rate": 1.9488760116444966e-05,
"loss": 1.8206,
"step": 480
},
{
"epoch": 2.563767168083715,
"grad_norm": 19.875,
"learning_rate": 1.944376370237481e-05,
"loss": 1.8137,
"step": 490
},
{
"epoch": 2.616088947024199,
"grad_norm": 25.125,
"learning_rate": 1.9396926207859085e-05,
"loss": 1.8683,
"step": 500
},
{
"epoch": 2.6684107259646828,
"grad_norm": 21.5,
"learning_rate": 1.9348256763960146e-05,
"loss": 1.6886,
"step": 510
},
{
"epoch": 2.720732504905167,
"grad_norm": 27.625,
"learning_rate": 1.9297764858882516e-05,
"loss": 1.6966,
"step": 520
},
{
"epoch": 2.7730542838456507,
"grad_norm": 16.375,
"learning_rate": 1.9245460336123136e-05,
"loss": 1.5617,
"step": 530
},
{
"epoch": 2.825376062786135,
"grad_norm": 27.5,
"learning_rate": 1.9191353392552346e-05,
"loss": 1.4437,
"step": 540
},
{
"epoch": 2.8776978417266186,
"grad_norm": 7.59375,
"learning_rate": 1.913545457642601e-05,
"loss": 1.3535,
"step": 550
},
{
"epoch": 2.9300196206671028,
"grad_norm": 23.625,
"learning_rate": 1.907777478532909e-05,
"loss": 1.3569,
"step": 560
},
{
"epoch": 2.982341399607587,
"grad_norm": 21.75,
"learning_rate": 1.901832526405114e-05,
"loss": 1.5882,
"step": 570
},
{
"epoch": 3.0346631785480707,
"grad_norm": 24.125,
"learning_rate": 1.895711760239413e-05,
"loss": 1.4584,
"step": 580
},
{
"epoch": 3.0869849574885544,
"grad_norm": 24.375,
"learning_rate": 1.889416373291298e-05,
"loss": 1.266,
"step": 590
},
{
"epoch": 3.1393067364290386,
"grad_norm": 9.3125,
"learning_rate": 1.8829475928589272e-05,
"loss": 1.1857,
"step": 600
},
{
"epoch": 3.1916285153695227,
"grad_norm": 12.875,
"learning_rate": 1.8763066800438638e-05,
"loss": 1.1123,
"step": 610
},
{
"epoch": 3.2439502943100065,
"grad_norm": 19.5,
"learning_rate": 1.869494929505219e-05,
"loss": 1.1477,
"step": 620
},
{
"epoch": 3.2962720732504907,
"grad_norm": 14.625,
"learning_rate": 1.8625136692072577e-05,
"loss": 1.1091,
"step": 630
},
{
"epoch": 3.3485938521909744,
"grad_norm": 5.90625,
"learning_rate": 1.855364260160507e-05,
"loss": 1.1665,
"step": 640
},
{
"epoch": 3.4009156311314586,
"grad_norm": 12.6875,
"learning_rate": 1.848048096156426e-05,
"loss": 1.0396,
"step": 650
},
{
"epoch": 3.4532374100719423,
"grad_norm": 6.65625,
"learning_rate": 1.8405666034956842e-05,
"loss": 1.0918,
"step": 660
},
{
"epoch": 3.5055591890124265,
"grad_norm": 18.625,
"learning_rate": 1.8329212407100996e-05,
"loss": 1.1203,
"step": 670
},
{
"epoch": 3.5578809679529106,
"grad_norm": 11.875,
"learning_rate": 1.8251134982782952e-05,
"loss": 1.1369,
"step": 680
},
{
"epoch": 3.6102027468933944,
"grad_norm": 17.125,
"learning_rate": 1.8171448983351284e-05,
"loss": 1.1366,
"step": 690
},
{
"epoch": 3.662524525833878,
"grad_norm": 47.25,
"learning_rate": 1.8090169943749477e-05,
"loss": 1.3546,
"step": 700
},
{
"epoch": 3.7148463047743623,
"grad_norm": 10.75,
"learning_rate": 1.8007313709487334e-05,
"loss": 1.2935,
"step": 710
},
{
"epoch": 3.7671680837148465,
"grad_norm": 11.125,
"learning_rate": 1.792289643355191e-05,
"loss": 1.024,
"step": 720
},
{
"epoch": 3.81948986265533,
"grad_norm": 11.75,
"learning_rate": 1.78369345732584e-05,
"loss": 1.0973,
"step": 730
},
{
"epoch": 3.8718116415958144,
"grad_norm": 27.0,
"learning_rate": 1.7749444887041797e-05,
"loss": 1.0991,
"step": 740
},
{
"epoch": 3.924133420536298,
"grad_norm": 14.5,
"learning_rate": 1.766044443118978e-05,
"loss": 1.0702,
"step": 750
},
{
"epoch": 3.9764551994767823,
"grad_norm": 9.0,
"learning_rate": 1.7569950556517566e-05,
"loss": 1.0792,
"step": 760
},
{
"epoch": 4.028776978417266,
"grad_norm": 10.6875,
"learning_rate": 1.747798090498532e-05,
"loss": 0.9713,
"step": 770
},
{
"epoch": 4.08109875735775,
"grad_norm": 11.125,
"learning_rate": 1.7384553406258842e-05,
"loss": 0.9195,
"step": 780
},
{
"epoch": 4.133420536298234,
"grad_norm": 9.4375,
"learning_rate": 1.7289686274214116e-05,
"loss": 0.8511,
"step": 790
},
{
"epoch": 4.185742315238718,
"grad_norm": 11.5,
"learning_rate": 1.7193398003386514e-05,
"loss": 0.8347,
"step": 800
},
{
"epoch": 4.238064094179202,
"grad_norm": 7.71875,
"learning_rate": 1.709570736536521e-05,
"loss": 0.861,
"step": 810
},
{
"epoch": 4.290385873119686,
"grad_norm": 8.5,
"learning_rate": 1.6996633405133656e-05,
"loss": 0.8834,
"step": 820
},
{
"epoch": 4.34270765206017,
"grad_norm": 9.9375,
"learning_rate": 1.68961954373567e-05,
"loss": 0.8895,
"step": 830
},
{
"epoch": 4.395029431000654,
"grad_norm": 8.875,
"learning_rate": 1.6794413042615168e-05,
"loss": 0.8292,
"step": 840
},
{
"epoch": 4.447351209941138,
"grad_norm": 9.125,
"learning_rate": 1.6691306063588583e-05,
"loss": 0.9389,
"step": 850
},
{
"epoch": 4.499672988881622,
"grad_norm": 5.875,
"learning_rate": 1.6586894601186804e-05,
"loss": 0.8355,
"step": 860
},
{
"epoch": 4.551994767822106,
"grad_norm": 8.4375,
"learning_rate": 1.6481199010631312e-05,
"loss": 0.8835,
"step": 870
},
{
"epoch": 4.60431654676259,
"grad_norm": 14.0625,
"learning_rate": 1.63742398974869e-05,
"loss": 0.8394,
"step": 880
},
{
"epoch": 4.656638325703074,
"grad_norm": 6.3125,
"learning_rate": 1.6266038113644605e-05,
"loss": 0.8661,
"step": 890
},
{
"epoch": 4.708960104643558,
"grad_norm": 5.4375,
"learning_rate": 1.6156614753256583e-05,
"loss": 0.828,
"step": 900
},
{
"epoch": 4.761281883584042,
"grad_norm": 6.5,
"learning_rate": 1.6045991148623752e-05,
"loss": 0.8028,
"step": 910
},
{
"epoch": 4.8136036625245255,
"grad_norm": 6.4375,
"learning_rate": 1.5934188866037017e-05,
"loss": 0.816,
"step": 920
},
{
"epoch": 4.86592544146501,
"grad_norm": 11.9375,
"learning_rate": 1.5821229701572897e-05,
"loss": 0.8221,
"step": 930
},
{
"epoch": 4.918247220405494,
"grad_norm": 8.8125,
"learning_rate": 1.570713567684432e-05,
"loss": 0.8955,
"step": 940
},
{
"epoch": 4.970568999345978,
"grad_norm": 5.4375,
"learning_rate": 1.5591929034707468e-05,
"loss": 0.8606,
"step": 950
},
{
"epoch": 5.022890778286461,
"grad_norm": 13.5,
"learning_rate": 1.5475632234925505e-05,
"loss": 0.7756,
"step": 960
},
{
"epoch": 5.075212557226946,
"grad_norm": 9.5625,
"learning_rate": 1.5358267949789968e-05,
"loss": 0.7097,
"step": 970
},
{
"epoch": 5.12753433616743,
"grad_norm": 7.5,
"learning_rate": 1.5239859059700794e-05,
"loss": 0.6738,
"step": 980
},
{
"epoch": 5.179856115107913,
"grad_norm": 10.9375,
"learning_rate": 1.5120428648705716e-05,
"loss": 0.6686,
"step": 990
},
{
"epoch": 5.232177894048398,
"grad_norm": 9.25,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.6961,
"step": 1000
},
{
"epoch": 5.284499672988882,
"grad_norm": 8.75,
"learning_rate": 1.4878596591387329e-05,
"loss": 0.707,
"step": 1010
},
{
"epoch": 5.3368214519293655,
"grad_norm": 12.25,
"learning_rate": 1.4756242090702756e-05,
"loss": 0.7172,
"step": 1020
},
{
"epoch": 5.389143230869849,
"grad_norm": 6.59375,
"learning_rate": 1.463296035119862e-05,
"loss": 0.6868,
"step": 1030
},
{
"epoch": 5.441465009810334,
"grad_norm": 5.3125,
"learning_rate": 1.4508775406894308e-05,
"loss": 0.6678,
"step": 1040
},
{
"epoch": 5.493786788750818,
"grad_norm": 5.84375,
"learning_rate": 1.4383711467890776e-05,
"loss": 0.6353,
"step": 1050
},
{
"epoch": 5.546108567691301,
"grad_norm": 6.6875,
"learning_rate": 1.4257792915650728e-05,
"loss": 0.702,
"step": 1060
},
{
"epoch": 5.598430346631785,
"grad_norm": 5.09375,
"learning_rate": 1.413104429824542e-05,
"loss": 0.7138,
"step": 1070
},
{
"epoch": 5.65075212557227,
"grad_norm": 10.0625,
"learning_rate": 1.4003490325568953e-05,
"loss": 0.6754,
"step": 1080
},
{
"epoch": 5.703073904512753,
"grad_norm": 10.625,
"learning_rate": 1.3875155864521031e-05,
"loss": 0.693,
"step": 1090
},
{
"epoch": 5.755395683453237,
"grad_norm": 5.9375,
"learning_rate": 1.3746065934159123e-05,
"loss": 0.6458,
"step": 1100
},
{
"epoch": 5.807717462393722,
"grad_norm": 8.3125,
"learning_rate": 1.3616245700820922e-05,
"loss": 0.673,
"step": 1110
},
{
"epoch": 5.8600392413342055,
"grad_norm": 7.71875,
"learning_rate": 1.3485720473218153e-05,
"loss": 0.7141,
"step": 1120
},
{
"epoch": 5.912361020274689,
"grad_norm": 11.4375,
"learning_rate": 1.3354515697502552e-05,
"loss": 0.664,
"step": 1130
},
{
"epoch": 5.964682799215173,
"grad_norm": 7.28125,
"learning_rate": 1.3222656952305113e-05,
"loss": 0.6634,
"step": 1140
},
{
"epoch": 6.017004578155658,
"grad_norm": 7.75,
"learning_rate": 1.3090169943749475e-05,
"loss": 0.5929,
"step": 1150
},
{
"epoch": 6.069326357096141,
"grad_norm": 10.625,
"learning_rate": 1.2957080500440469e-05,
"loss": 0.557,
"step": 1160
},
{
"epoch": 6.121648136036625,
"grad_norm": 4.90625,
"learning_rate": 1.2823414568428767e-05,
"loss": 0.5868,
"step": 1170
},
{
"epoch": 6.173969914977109,
"grad_norm": 7.40625,
"learning_rate": 1.2689198206152657e-05,
"loss": 0.5627,
"step": 1180
},
{
"epoch": 6.226291693917593,
"grad_norm": 7.53125,
"learning_rate": 1.2554457579357906e-05,
"loss": 0.5412,
"step": 1190
},
{
"epoch": 6.278613472858077,
"grad_norm": 6.03125,
"learning_rate": 1.2419218955996677e-05,
"loss": 0.5498,
"step": 1200
},
{
"epoch": 6.330935251798561,
"grad_norm": 7.5625,
"learning_rate": 1.2283508701106559e-05,
"loss": 0.589,
"step": 1210
},
{
"epoch": 6.3832570307390455,
"grad_norm": 6.90625,
"learning_rate": 1.2147353271670634e-05,
"loss": 0.5565,
"step": 1220
},
{
"epoch": 6.435578809679529,
"grad_norm": 8.0625,
"learning_rate": 1.2010779211459649e-05,
"loss": 0.564,
"step": 1230
},
{
"epoch": 6.487900588620013,
"grad_norm": 4.90625,
"learning_rate": 1.187381314585725e-05,
"loss": 0.5612,
"step": 1240
},
{
"epoch": 6.540222367560497,
"grad_norm": 5.34375,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.5532,
"step": 1250
},
{
"epoch": 6.592544146500981,
"grad_norm": 6.0625,
"learning_rate": 1.159881187691835e-05,
"loss": 0.5796,
"step": 1260
},
{
"epoch": 6.644865925441465,
"grad_norm": 7.125,
"learning_rate": 1.1460830285624119e-05,
"loss": 0.5547,
"step": 1270
},
{
"epoch": 6.697187704381949,
"grad_norm": 6.75,
"learning_rate": 1.1322563902571227e-05,
"loss": 0.5652,
"step": 1280
},
{
"epoch": 6.7495094833224325,
"grad_norm": 7.59375,
"learning_rate": 1.1184039683065014e-05,
"loss": 0.5366,
"step": 1290
},
{
"epoch": 6.801831262262917,
"grad_norm": 4.6875,
"learning_rate": 1.1045284632676535e-05,
"loss": 0.5645,
"step": 1300
},
{
"epoch": 6.854153041203401,
"grad_norm": 4.84375,
"learning_rate": 1.0906325801977804e-05,
"loss": 0.5297,
"step": 1310
},
{
"epoch": 6.906474820143885,
"grad_norm": 5.9375,
"learning_rate": 1.0767190281268187e-05,
"loss": 0.5563,
"step": 1320
},
{
"epoch": 6.958796599084369,
"grad_norm": 7.78125,
"learning_rate": 1.0627905195293135e-05,
"loss": 0.5587,
"step": 1330
},
{
"epoch": 7.011118378024853,
"grad_norm": 5.34375,
"learning_rate": 1.0488497697956134e-05,
"loss": 0.5201,
"step": 1340
},
{
"epoch": 7.063440156965337,
"grad_norm": 8.0625,
"learning_rate": 1.0348994967025012e-05,
"loss": 0.4576,
"step": 1350
},
{
"epoch": 7.11576193590582,
"grad_norm": 5.09375,
"learning_rate": 1.0209424198833571e-05,
"loss": 0.5009,
"step": 1360
},
{
"epoch": 7.168083714846305,
"grad_norm": 4.0625,
"learning_rate": 1.0069812602979617e-05,
"loss": 0.4734,
"step": 1370
},
{
"epoch": 7.220405493786789,
"grad_norm": 3.609375,
"learning_rate": 9.930187397020385e-06,
"loss": 0.4506,
"step": 1380
},
{
"epoch": 7.2727272727272725,
"grad_norm": 8.0625,
"learning_rate": 9.790575801166432e-06,
"loss": 0.5113,
"step": 1390
},
{
"epoch": 7.325049051667757,
"grad_norm": 5.8125,
"learning_rate": 9.651005032974994e-06,
"loss": 0.4691,
"step": 1400
},
{
"epoch": 7.377370830608241,
"grad_norm": 5.03125,
"learning_rate": 9.511502302043867e-06,
"loss": 0.4878,
"step": 1410
},
{
"epoch": 7.429692609548725,
"grad_norm": 6.1875,
"learning_rate": 9.372094804706867e-06,
"loss": 0.4673,
"step": 1420
},
{
"epoch": 7.482014388489208,
"grad_norm": 4.34375,
"learning_rate": 9.232809718731815e-06,
"loss": 0.4654,
"step": 1430
},
{
"epoch": 7.534336167429693,
"grad_norm": 6.0625,
"learning_rate": 9.093674198022201e-06,
"loss": 0.4706,
"step": 1440
},
{
"epoch": 7.586657946370177,
"grad_norm": 4.125,
"learning_rate": 8.954715367323468e-06,
"loss": 0.4622,
"step": 1450
},
{
"epoch": 7.63897972531066,
"grad_norm": 4.78125,
"learning_rate": 8.815960316934991e-06,
"loss": 0.4614,
"step": 1460
},
{
"epoch": 7.691301504251145,
"grad_norm": 3.8125,
"learning_rate": 8.677436097428775e-06,
"loss": 0.435,
"step": 1470
},
{
"epoch": 7.743623283191629,
"grad_norm": 5.625,
"learning_rate": 8.539169714375885e-06,
"loss": 0.4581,
"step": 1480
},
{
"epoch": 7.7959450621321125,
"grad_norm": 4.59375,
"learning_rate": 8.401188123081653e-06,
"loss": 0.4656,
"step": 1490
},
{
"epoch": 7.848266841072596,
"grad_norm": 5.375,
"learning_rate": 8.263518223330698e-06,
"loss": 0.4525,
"step": 1500
},
{
"epoch": 7.905166775670373,
"grad_norm": 7.3125,
"learning_rate": 8.126186854142752e-06,
"loss": 0.4519,
"step": 1510
},
{
"epoch": 7.9574885546108565,
"grad_norm": 5.5,
"learning_rate": 7.989220788540356e-06,
"loss": 0.4917,
"step": 1520
},
{
"epoch": 8.009810333551341,
"grad_norm": 3.640625,
"learning_rate": 7.852646728329368e-06,
"loss": 0.4613,
"step": 1530
},
{
"epoch": 8.062132112491824,
"grad_norm": 3.90625,
"learning_rate": 7.716491298893443e-06,
"loss": 0.3999,
"step": 1540
},
{
"epoch": 8.114453891432309,
"grad_norm": 3.53125,
"learning_rate": 7.580781044003324e-06,
"loss": 0.3909,
"step": 1550
},
{
"epoch": 8.166775670372793,
"grad_norm": 5.84375,
"learning_rate": 7.445542420642097e-06,
"loss": 0.4046,
"step": 1560
},
{
"epoch": 8.219097449313276,
"grad_norm": 3.5,
"learning_rate": 7.310801793847344e-06,
"loss": 0.3953,
"step": 1570
},
{
"epoch": 8.27141922825376,
"grad_norm": 3.953125,
"learning_rate": 7.176585431571235e-06,
"loss": 0.4144,
"step": 1580
},
{
"epoch": 8.323741007194245,
"grad_norm": 3.59375,
"learning_rate": 7.042919499559538e-06,
"loss": 0.4091,
"step": 1590
},
{
"epoch": 8.376062786134728,
"grad_norm": 3.71875,
"learning_rate": 6.909830056250527e-06,
"loss": 0.4056,
"step": 1600
},
{
"epoch": 8.428384565075213,
"grad_norm": 4.4375,
"learning_rate": 6.777343047694891e-06,
"loss": 0.4064,
"step": 1610
},
{
"epoch": 8.480706344015697,
"grad_norm": 3.578125,
"learning_rate": 6.645484302497452e-06,
"loss": 0.4054,
"step": 1620
},
{
"epoch": 8.53302812295618,
"grad_norm": 4.15625,
"learning_rate": 6.5142795267818505e-06,
"loss": 0.4314,
"step": 1630
},
{
"epoch": 8.585349901896665,
"grad_norm": 3.96875,
"learning_rate": 6.383754299179079e-06,
"loss": 0.4023,
"step": 1640
},
{
"epoch": 8.637671680837148,
"grad_norm": 3.5,
"learning_rate": 6.25393406584088e-06,
"loss": 0.4027,
"step": 1650
},
{
"epoch": 8.689993459777632,
"grad_norm": 4.3125,
"learning_rate": 6.124844135478971e-06,
"loss": 0.4086,
"step": 1660
},
{
"epoch": 8.742315238718117,
"grad_norm": 3.34375,
"learning_rate": 5.996509674431053e-06,
"loss": 0.3924,
"step": 1670
},
{
"epoch": 8.7946370176586,
"grad_norm": 5.78125,
"learning_rate": 5.868955701754584e-06,
"loss": 0.3933,
"step": 1680
},
{
"epoch": 8.846958796599084,
"grad_norm": 3.640625,
"learning_rate": 5.742207084349274e-06,
"loss": 0.4018,
"step": 1690
},
{
"epoch": 8.899280575539569,
"grad_norm": 4.65625,
"learning_rate": 5.616288532109225e-06,
"loss": 0.4096,
"step": 1700
},
{
"epoch": 8.951602354480052,
"grad_norm": 4.3125,
"learning_rate": 5.491224593105695e-06,
"loss": 0.4171,
"step": 1710
},
{
"epoch": 9.003924133420536,
"grad_norm": 2.703125,
"learning_rate": 5.367039648801386e-06,
"loss": 0.4009,
"step": 1720
},
{
"epoch": 9.056245912361021,
"grad_norm": 3.34375,
"learning_rate": 5.243757909297247e-06,
"loss": 0.3646,
"step": 1730
},
{
"epoch": 9.108567691301504,
"grad_norm": 3.640625,
"learning_rate": 5.121403408612672e-06,
"loss": 0.3731,
"step": 1740
},
{
"epoch": 9.160889470241989,
"grad_norm": 3.28125,
"learning_rate": 5.000000000000003e-06,
"loss": 0.3763,
"step": 1750
},
{
"epoch": 9.213211249182471,
"grad_norm": 3.59375,
"learning_rate": 4.879571351294287e-06,
"loss": 0.3662,
"step": 1760
},
{
"epoch": 9.265533028122956,
"grad_norm": 3.671875,
"learning_rate": 4.76014094029921e-06,
"loss": 0.37,
"step": 1770
},
{
"epoch": 9.31785480706344,
"grad_norm": 3.09375,
"learning_rate": 4.641732050210032e-06,
"loss": 0.3498,
"step": 1780
},
{
"epoch": 9.370176586003923,
"grad_norm": 3.59375,
"learning_rate": 4.524367765074499e-06,
"loss": 0.3578,
"step": 1790
},
{
"epoch": 9.422498364944408,
"grad_norm": 3.390625,
"learning_rate": 4.408070965292534e-06,
"loss": 0.3482,
"step": 1800
},
{
"epoch": 9.474820143884893,
"grad_norm": 2.984375,
"learning_rate": 4.292864323155684e-06,
"loss": 0.3684,
"step": 1810
},
{
"epoch": 9.527141922825376,
"grad_norm": 2.890625,
"learning_rate": 4.178770298427107e-06,
"loss": 0.3806,
"step": 1820
},
{
"epoch": 9.57946370176586,
"grad_norm": 3.765625,
"learning_rate": 4.065811133962987e-06,
"loss": 0.3718,
"step": 1830
},
{
"epoch": 9.631785480706345,
"grad_norm": 2.921875,
"learning_rate": 3.954008851376252e-06,
"loss": 0.3469,
"step": 1840
},
{
"epoch": 9.684107259646828,
"grad_norm": 3.53125,
"learning_rate": 3.8433852467434175e-06,
"loss": 0.3776,
"step": 1850
},
{
"epoch": 9.736429038587312,
"grad_norm": 3.78125,
"learning_rate": 3.7339618863553983e-06,
"loss": 0.3682,
"step": 1860
},
{
"epoch": 9.788750817527795,
"grad_norm": 3.375,
"learning_rate": 3.625760102513103e-06,
"loss": 0.3637,
"step": 1870
},
{
"epoch": 9.84107259646828,
"grad_norm": 3.6875,
"learning_rate": 3.5188009893686916e-06,
"loss": 0.367,
"step": 1880
},
{
"epoch": 9.893394375408764,
"grad_norm": 3.625,
"learning_rate": 3.4131053988131947e-06,
"loss": 0.3591,
"step": 1890
},
{
"epoch": 9.945716154349247,
"grad_norm": 3.375,
"learning_rate": 3.308693936411421e-06,
"loss": 0.3601,
"step": 1900
},
{
"epoch": 9.998037933289732,
"grad_norm": 3.59375,
"learning_rate": 3.2055869573848374e-06,
"loss": 0.344,
"step": 1910
},
{
"epoch": 10.050359712230216,
"grad_norm": 3.1875,
"learning_rate": 3.103804562643302e-06,
"loss": 0.3447,
"step": 1920
},
{
"epoch": 10.1026814911707,
"grad_norm": 2.921875,
"learning_rate": 3.003366594866345e-06,
"loss": 0.3423,
"step": 1930
},
{
"epoch": 10.155003270111184,
"grad_norm": 3.484375,
"learning_rate": 2.9042926346347932e-06,
"loss": 0.3488,
"step": 1940
},
{
"epoch": 10.207325049051668,
"grad_norm": 3.390625,
"learning_rate": 2.8066019966134907e-06,
"loss": 0.3577,
"step": 1950
},
{
"epoch": 10.259646827992151,
"grad_norm": 3.109375,
"learning_rate": 2.7103137257858867e-06,
"loss": 0.3234,
"step": 1960
},
{
"epoch": 10.311968606932636,
"grad_norm": 2.9375,
"learning_rate": 2.615446593741161e-06,
"loss": 0.3506,
"step": 1970
},
{
"epoch": 10.364290385873119,
"grad_norm": 3.078125,
"learning_rate": 2.522019095014683e-06,
"loss": 0.3399,
"step": 1980
},
{
"epoch": 10.416612164813603,
"grad_norm": 2.984375,
"learning_rate": 2.4300494434824373e-06,
"loss": 0.3303,
"step": 1990
},
{
"epoch": 10.468933943754088,
"grad_norm": 2.71875,
"learning_rate": 2.339555568810221e-06,
"loss": 0.3284,
"step": 2000
},
{
"epoch": 10.52125572269457,
"grad_norm": 3.640625,
"learning_rate": 2.2505551129582047e-06,
"loss": 0.3512,
"step": 2010
},
{
"epoch": 10.573577501635055,
"grad_norm": 3.390625,
"learning_rate": 2.163065426741603e-06,
"loss": 0.3434,
"step": 2020
},
{
"epoch": 10.62589928057554,
"grad_norm": 3.015625,
"learning_rate": 2.0771035664480944e-06,
"loss": 0.3314,
"step": 2030
},
{
"epoch": 10.678221059516023,
"grad_norm": 3.265625,
"learning_rate": 1.9926862905126663e-06,
"loss": 0.3507,
"step": 2040
},
{
"epoch": 10.730542838456508,
"grad_norm": 3.734375,
"learning_rate": 1.9098300562505266e-06,
"loss": 0.3588,
"step": 2050
},
{
"epoch": 10.782864617396992,
"grad_norm": 3.21875,
"learning_rate": 1.8285510166487154e-06,
"loss": 0.351,
"step": 2060
},
{
"epoch": 10.835186396337475,
"grad_norm": 3.25,
"learning_rate": 1.7488650172170496e-06,
"loss": 0.3386,
"step": 2070
},
{
"epoch": 10.88750817527796,
"grad_norm": 3.390625,
"learning_rate": 1.6707875928990059e-06,
"loss": 0.3219,
"step": 2080
},
{
"epoch": 10.939829954218443,
"grad_norm": 3.3125,
"learning_rate": 1.5943339650431578e-06,
"loss": 0.3498,
"step": 2090
},
{
"epoch": 10.992151733158927,
"grad_norm": 3.125,
"learning_rate": 1.5195190384357405e-06,
"loss": 0.3478,
"step": 2100
},
{
"epoch": 11.044473512099412,
"grad_norm": 3.234375,
"learning_rate": 1.446357398394934e-06,
"loss": 0.3425,
"step": 2110
},
{
"epoch": 11.096795291039895,
"grad_norm": 3.109375,
"learning_rate": 1.3748633079274254e-06,
"loss": 0.3389,
"step": 2120
},
{
"epoch": 11.14911706998038,
"grad_norm": 3.671875,
"learning_rate": 1.30505070494781e-06,
"loss": 0.3424,
"step": 2130
},
{
"epoch": 11.201438848920864,
"grad_norm": 3.28125,
"learning_rate": 1.2369331995613664e-06,
"loss": 0.326,
"step": 2140
},
{
"epoch": 11.253760627861347,
"grad_norm": 3.34375,
"learning_rate": 1.1705240714107301e-06,
"loss": 0.3508,
"step": 2150
},
{
"epoch": 11.306082406801831,
"grad_norm": 3.171875,
"learning_rate": 1.1058362670870248e-06,
"loss": 0.3335,
"step": 2160
},
{
"epoch": 11.358404185742316,
"grad_norm": 3.25,
"learning_rate": 1.042882397605871e-06,
"loss": 0.3207,
"step": 2170
},
{
"epoch": 11.410725964682799,
"grad_norm": 3.15625,
"learning_rate": 9.816747359488632e-07,
"loss": 0.3272,
"step": 2180
},
{
"epoch": 11.463047743623283,
"grad_norm": 3.09375,
"learning_rate": 9.222252146709143e-07,
"loss": 0.3271,
"step": 2190
},
{
"epoch": 11.515369522563766,
"grad_norm": 3.453125,
"learning_rate": 8.645454235739903e-07,
"loss": 0.3441,
"step": 2200
},
{
"epoch": 11.56769130150425,
"grad_norm": 3.46875,
"learning_rate": 8.086466074476562e-07,
"loss": 0.331,
"step": 2210
},
{
"epoch": 11.620013080444735,
"grad_norm": 3.265625,
"learning_rate": 7.545396638768698e-07,
"loss": 0.325,
"step": 2220
},
{
"epoch": 11.672334859385218,
"grad_norm": 3.328125,
"learning_rate": 7.022351411174866e-07,
"loss": 0.351,
"step": 2230
},
{
"epoch": 11.724656638325703,
"grad_norm": 3.171875,
"learning_rate": 6.517432360398556e-07,
"loss": 0.3408,
"step": 2240
},
{
"epoch": 11.776978417266188,
"grad_norm": 3.1875,
"learning_rate": 6.030737921409169e-07,
"loss": 0.337,
"step": 2250
},
{
"epoch": 11.82930019620667,
"grad_norm": 3.390625,
"learning_rate": 5.562362976251901e-07,
"loss": 0.3341,
"step": 2260
},
{
"epoch": 11.881621975147155,
"grad_norm": 2.703125,
"learning_rate": 5.112398835550348e-07,
"loss": 0.3341,
"step": 2270
},
{
"epoch": 11.93394375408764,
"grad_norm": 3.375,
"learning_rate": 4.6809332207053083e-07,
"loss": 0.3361,
"step": 2280
},
{
"epoch": 11.986265533028122,
"grad_norm": 3.09375,
"learning_rate": 4.268050246793276e-07,
"loss": 0.3334,
"step": 2290
},
{
"epoch": 12.038587311968607,
"grad_norm": 3.203125,
"learning_rate": 3.8738304061681107e-07,
"loss": 0.3409,
"step": 2300
},
{
"epoch": 12.090909090909092,
"grad_norm": 2.625,
"learning_rate": 3.498350552768859e-07,
"loss": 0.3357,
"step": 2310
},
{
"epoch": 12.143230869849575,
"grad_norm": 3.34375,
"learning_rate": 3.1416838871368925e-07,
"loss": 0.3436,
"step": 2320
},
{
"epoch": 12.19555264879006,
"grad_norm": 3.046875,
"learning_rate": 2.8038999421453827e-07,
"loss": 0.3243,
"step": 2330
},
{
"epoch": 12.247874427730542,
"grad_norm": 3.390625,
"learning_rate": 2.4850645694436736e-07,
"loss": 0.3425,
"step": 2340
},
{
"epoch": 12.300196206671027,
"grad_norm": 3.1875,
"learning_rate": 2.1852399266194312e-07,
"loss": 0.3372,
"step": 2350
},
{
"epoch": 12.352517985611511,
"grad_norm": 3.390625,
"learning_rate": 1.9044844650808468e-07,
"loss": 0.3366,
"step": 2360
},
{
"epoch": 12.404839764551994,
"grad_norm": 3.15625,
"learning_rate": 1.6428529186614195e-07,
"loss": 0.3298,
"step": 2370
},
{
"epoch": 12.457161543492479,
"grad_norm": 3.0,
"learning_rate": 1.400396292949513e-07,
"loss": 0.321,
"step": 2380
},
{
"epoch": 12.509483322432963,
"grad_norm": 3.015625,
"learning_rate": 1.1771618553447217e-07,
"loss": 0.3187,
"step": 2390
},
{
"epoch": 12.561805101373446,
"grad_norm": 2.796875,
"learning_rate": 9.731931258429638e-08,
"loss": 0.3369,
"step": 2400
},
{
"epoch": 12.61412688031393,
"grad_norm": 3.046875,
"learning_rate": 7.885298685522235e-08,
"loss": 0.3266,
"step": 2410
},
{
"epoch": 12.666448659254415,
"grad_norm": 3.328125,
"learning_rate": 6.232080839403631e-08,
"loss": 0.3405,
"step": 2420
},
{
"epoch": 12.718770438194898,
"grad_norm": 3.28125,
"learning_rate": 4.772600018168816e-08,
"loss": 0.3229,
"step": 2430
},
{
"epoch": 12.771092217135383,
"grad_norm": 3.046875,
"learning_rate": 3.50714075049563e-08,
"loss": 0.3404,
"step": 2440
},
{
"epoch": 12.823413996075868,
"grad_norm": 3.0625,
"learning_rate": 2.4359497401758026e-08,
"loss": 0.3396,
"step": 2450
},
{
"epoch": 12.87573577501635,
"grad_norm": 3.046875,
"learning_rate": 1.5592358180189782e-08,
"loss": 0.3351,
"step": 2460
},
{
"epoch": 12.928057553956835,
"grad_norm": 3.359375,
"learning_rate": 8.771699011416169e-09,
"loss": 0.3356,
"step": 2470
},
{
"epoch": 12.980379332897318,
"grad_norm": 3.421875,
"learning_rate": 3.898849596456477e-09,
"loss": 0.3388,
"step": 2480
},
{
"epoch": 13.032701111837802,
"grad_norm": 3.59375,
"learning_rate": 9.74759906957612e-10,
"loss": 0.3404,
"step": 2490
},
{
"epoch": 13.085022890778287,
"grad_norm": 3.0625,
"learning_rate": 0.0,
"loss": 0.3233,
"step": 2500
}
],
"logging_steps": 10,
"max_steps": 2500,
"num_input_tokens_seen": 0,
"num_train_epochs": 14,
"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": 9.563306454354493e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}