Grogros's picture
Training in progress, step 2000, checkpoint
993dfbb verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.464355788096796,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.052321778940483975,
"grad_norm": 73.5,
"learning_rate": 8.000000000000001e-07,
"loss": 0.4785,
"step": 10
},
{
"epoch": 0.10464355788096795,
"grad_norm": 280.0,
"learning_rate": 1.6000000000000001e-06,
"loss": 0.4749,
"step": 20
},
{
"epoch": 0.15696533682145192,
"grad_norm": 664.0,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.5162,
"step": 30
},
{
"epoch": 0.2092871157619359,
"grad_norm": 684.0,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.7172,
"step": 40
},
{
"epoch": 0.2616088947024199,
"grad_norm": 209.0,
"learning_rate": 4.000000000000001e-06,
"loss": 0.8219,
"step": 50
},
{
"epoch": 0.31393067364290383,
"grad_norm": 122.0,
"learning_rate": 4.800000000000001e-06,
"loss": 1.1019,
"step": 60
},
{
"epoch": 0.36625245258338784,
"grad_norm": 149.0,
"learning_rate": 5.600000000000001e-06,
"loss": 1.145,
"step": 70
},
{
"epoch": 0.4185742315238718,
"grad_norm": 123.5,
"learning_rate": 6.4000000000000006e-06,
"loss": 1.1876,
"step": 80
},
{
"epoch": 0.4708960104643558,
"grad_norm": 89.0,
"learning_rate": 7.2000000000000005e-06,
"loss": 1.207,
"step": 90
},
{
"epoch": 0.5232177894048398,
"grad_norm": 372.0,
"learning_rate": 8.000000000000001e-06,
"loss": 1.0986,
"step": 100
},
{
"epoch": 0.5755395683453237,
"grad_norm": 69.0,
"learning_rate": 8.8e-06,
"loss": 0.8367,
"step": 110
},
{
"epoch": 0.6278613472858077,
"grad_norm": 60.25,
"learning_rate": 9.600000000000001e-06,
"loss": 0.8822,
"step": 120
},
{
"epoch": 0.6801831262262917,
"grad_norm": 44.75,
"learning_rate": 1.04e-05,
"loss": 1.2104,
"step": 130
},
{
"epoch": 0.7325049051667757,
"grad_norm": 49.0,
"learning_rate": 1.1200000000000001e-05,
"loss": 0.8587,
"step": 140
},
{
"epoch": 0.7848266841072596,
"grad_norm": 42.5,
"learning_rate": 1.2e-05,
"loss": 0.761,
"step": 150
},
{
"epoch": 0.8371484630477436,
"grad_norm": 42.5,
"learning_rate": 1.2800000000000001e-05,
"loss": 0.7207,
"step": 160
},
{
"epoch": 0.8894702419882276,
"grad_norm": 28.25,
"learning_rate": 1.3600000000000002e-05,
"loss": 0.7541,
"step": 170
},
{
"epoch": 0.9417920209287116,
"grad_norm": 40.75,
"learning_rate": 1.4400000000000001e-05,
"loss": 0.7367,
"step": 180
},
{
"epoch": 0.9941137998691956,
"grad_norm": 231.0,
"learning_rate": 1.5200000000000002e-05,
"loss": 0.8107,
"step": 190
},
{
"epoch": 1.0464355788096795,
"grad_norm": 70.0,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.7498,
"step": 200
},
{
"epoch": 1.0987573577501635,
"grad_norm": 33.5,
"learning_rate": 1.6800000000000002e-05,
"loss": 0.7138,
"step": 210
},
{
"epoch": 1.1510791366906474,
"grad_norm": 34.75,
"learning_rate": 1.76e-05,
"loss": 0.6399,
"step": 220
},
{
"epoch": 1.2034009156311314,
"grad_norm": 20.125,
"learning_rate": 1.8400000000000003e-05,
"loss": 0.5844,
"step": 230
},
{
"epoch": 1.2557226945716153,
"grad_norm": 34.25,
"learning_rate": 1.9200000000000003e-05,
"loss": 0.6765,
"step": 240
},
{
"epoch": 1.3080444735120995,
"grad_norm": 37.0,
"learning_rate": 2e-05,
"loss": 3.7542,
"step": 250
},
{
"epoch": 1.3603662524525835,
"grad_norm": 27.25,
"learning_rate": 1.9999025240093045e-05,
"loss": 0.7183,
"step": 260
},
{
"epoch": 1.4126880313930674,
"grad_norm": 20.25,
"learning_rate": 1.9996101150403543e-05,
"loss": 0.5714,
"step": 270
},
{
"epoch": 1.4650098103335514,
"grad_norm": 21.125,
"learning_rate": 1.9991228300988586e-05,
"loss": 0.5506,
"step": 280
},
{
"epoch": 1.5173315892740353,
"grad_norm": 23.625,
"learning_rate": 1.9984407641819812e-05,
"loss": 0.5253,
"step": 290
},
{
"epoch": 1.5696533682145193,
"grad_norm": 20.75,
"learning_rate": 1.9975640502598243e-05,
"loss": 0.5671,
"step": 300
},
{
"epoch": 1.6219751471550032,
"grad_norm": 15.6875,
"learning_rate": 1.9964928592495046e-05,
"loss": 0.4991,
"step": 310
},
{
"epoch": 1.6742969260954872,
"grad_norm": 18.125,
"learning_rate": 1.9952273999818312e-05,
"loss": 0.5376,
"step": 320
},
{
"epoch": 1.7266187050359711,
"grad_norm": 18.125,
"learning_rate": 1.9937679191605964e-05,
"loss": 0.5307,
"step": 330
},
{
"epoch": 1.7789404839764553,
"grad_norm": 17.125,
"learning_rate": 1.9921147013144782e-05,
"loss": 0.522,
"step": 340
},
{
"epoch": 1.831262262916939,
"grad_norm": 11.375,
"learning_rate": 1.9902680687415704e-05,
"loss": 0.4873,
"step": 350
},
{
"epoch": 1.8835840418574232,
"grad_norm": 19.625,
"learning_rate": 1.988228381446553e-05,
"loss": 0.4609,
"step": 360
},
{
"epoch": 1.9359058207979072,
"grad_norm": 15.0625,
"learning_rate": 1.985996037070505e-05,
"loss": 0.4225,
"step": 370
},
{
"epoch": 1.9882275997383911,
"grad_norm": 19.0,
"learning_rate": 1.983571470813386e-05,
"loss": 0.4309,
"step": 380
},
{
"epoch": 2.040549378678875,
"grad_norm": 18.5,
"learning_rate": 1.9809551553491918e-05,
"loss": 0.4062,
"step": 390
},
{
"epoch": 2.092871157619359,
"grad_norm": 10.25,
"learning_rate": 1.9781476007338058e-05,
"loss": 0.3827,
"step": 400
},
{
"epoch": 2.145192936559843,
"grad_norm": 23.75,
"learning_rate": 1.9751493543055634e-05,
"loss": 0.3883,
"step": 410
},
{
"epoch": 2.197514715500327,
"grad_norm": 14.8125,
"learning_rate": 1.9719610005785466e-05,
"loss": 0.4069,
"step": 420
},
{
"epoch": 2.249836494440811,
"grad_norm": 23.125,
"learning_rate": 1.9685831611286312e-05,
"loss": 0.3815,
"step": 430
},
{
"epoch": 2.302158273381295,
"grad_norm": 10.8125,
"learning_rate": 1.9650164944723116e-05,
"loss": 0.3719,
"step": 440
},
{
"epoch": 2.354480052321779,
"grad_norm": 15.6875,
"learning_rate": 1.961261695938319e-05,
"loss": 0.4038,
"step": 450
},
{
"epoch": 2.4068018312622628,
"grad_norm": 18.875,
"learning_rate": 1.9573194975320672e-05,
"loss": 0.3864,
"step": 460
},
{
"epoch": 2.459123610202747,
"grad_norm": 21.375,
"learning_rate": 1.9531906677929472e-05,
"loss": 0.3941,
"step": 470
},
{
"epoch": 2.5114453891432307,
"grad_norm": 24.75,
"learning_rate": 1.9488760116444966e-05,
"loss": 0.3661,
"step": 480
},
{
"epoch": 2.563767168083715,
"grad_norm": 30.0,
"learning_rate": 1.944376370237481e-05,
"loss": 0.3604,
"step": 490
},
{
"epoch": 2.616088947024199,
"grad_norm": 11.6875,
"learning_rate": 1.9396926207859085e-05,
"loss": 0.3618,
"step": 500
},
{
"epoch": 2.6684107259646828,
"grad_norm": 24.875,
"learning_rate": 1.9348256763960146e-05,
"loss": 0.3942,
"step": 510
},
{
"epoch": 2.720732504905167,
"grad_norm": 3.390625,
"learning_rate": 1.9297764858882516e-05,
"loss": 0.3458,
"step": 520
},
{
"epoch": 2.7730542838456507,
"grad_norm": 10.3125,
"learning_rate": 1.9245460336123136e-05,
"loss": 0.3533,
"step": 530
},
{
"epoch": 2.825376062786135,
"grad_norm": 20.875,
"learning_rate": 1.9191353392552346e-05,
"loss": 0.3546,
"step": 540
},
{
"epoch": 2.8776978417266186,
"grad_norm": 14.3125,
"learning_rate": 1.913545457642601e-05,
"loss": 0.366,
"step": 550
},
{
"epoch": 2.9300196206671028,
"grad_norm": 13.875,
"learning_rate": 1.907777478532909e-05,
"loss": 0.3353,
"step": 560
},
{
"epoch": 2.982341399607587,
"grad_norm": 4.25,
"learning_rate": 1.901832526405114e-05,
"loss": 0.3564,
"step": 570
},
{
"epoch": 3.0346631785480707,
"grad_norm": 10.3125,
"learning_rate": 1.895711760239413e-05,
"loss": 0.3324,
"step": 580
},
{
"epoch": 3.0869849574885544,
"grad_norm": 6.15625,
"learning_rate": 1.889416373291298e-05,
"loss": 0.3254,
"step": 590
},
{
"epoch": 3.1393067364290386,
"grad_norm": 9.6875,
"learning_rate": 1.8829475928589272e-05,
"loss": 0.3278,
"step": 600
},
{
"epoch": 3.1916285153695227,
"grad_norm": 10.4375,
"learning_rate": 1.8763066800438638e-05,
"loss": 0.2962,
"step": 610
},
{
"epoch": 3.2439502943100065,
"grad_norm": 15.125,
"learning_rate": 1.869494929505219e-05,
"loss": 0.311,
"step": 620
},
{
"epoch": 3.2962720732504907,
"grad_norm": 13.0625,
"learning_rate": 1.8625136692072577e-05,
"loss": 0.2956,
"step": 630
},
{
"epoch": 3.3485938521909744,
"grad_norm": 12.875,
"learning_rate": 1.855364260160507e-05,
"loss": 0.3173,
"step": 640
},
{
"epoch": 3.4009156311314586,
"grad_norm": 10.1875,
"learning_rate": 1.848048096156426e-05,
"loss": 0.298,
"step": 650
},
{
"epoch": 3.4532374100719423,
"grad_norm": 6.375,
"learning_rate": 1.8405666034956842e-05,
"loss": 0.3216,
"step": 660
},
{
"epoch": 3.5055591890124265,
"grad_norm": 23.25,
"learning_rate": 1.8329212407100996e-05,
"loss": 0.3417,
"step": 670
},
{
"epoch": 3.5578809679529106,
"grad_norm": 11.25,
"learning_rate": 1.8251134982782952e-05,
"loss": 0.3169,
"step": 680
},
{
"epoch": 3.6102027468933944,
"grad_norm": 14.9375,
"learning_rate": 1.8171448983351284e-05,
"loss": 0.3221,
"step": 690
},
{
"epoch": 3.662524525833878,
"grad_norm": 9.375,
"learning_rate": 1.8090169943749477e-05,
"loss": 0.2793,
"step": 700
},
{
"epoch": 3.7148463047743623,
"grad_norm": 3.3125,
"learning_rate": 1.8007313709487334e-05,
"loss": 0.3063,
"step": 710
},
{
"epoch": 3.7671680837148465,
"grad_norm": 13.0625,
"learning_rate": 1.792289643355191e-05,
"loss": 0.2723,
"step": 720
},
{
"epoch": 3.81948986265533,
"grad_norm": 13.0,
"learning_rate": 1.78369345732584e-05,
"loss": 0.2924,
"step": 730
},
{
"epoch": 3.8718116415958144,
"grad_norm": 20.25,
"learning_rate": 1.7749444887041797e-05,
"loss": 0.314,
"step": 740
},
{
"epoch": 3.924133420536298,
"grad_norm": 7.0625,
"learning_rate": 1.766044443118978e-05,
"loss": 0.2965,
"step": 750
},
{
"epoch": 3.9764551994767823,
"grad_norm": 12.25,
"learning_rate": 1.7569950556517566e-05,
"loss": 0.2784,
"step": 760
},
{
"epoch": 4.028776978417266,
"grad_norm": 7.5,
"learning_rate": 1.747798090498532e-05,
"loss": 0.2626,
"step": 770
},
{
"epoch": 4.08109875735775,
"grad_norm": 15.0625,
"learning_rate": 1.7384553406258842e-05,
"loss": 0.2629,
"step": 780
},
{
"epoch": 4.133420536298234,
"grad_norm": 11.625,
"learning_rate": 1.7289686274214116e-05,
"loss": 0.252,
"step": 790
},
{
"epoch": 4.185742315238718,
"grad_norm": 9.75,
"learning_rate": 1.7193398003386514e-05,
"loss": 0.2466,
"step": 800
},
{
"epoch": 4.238064094179202,
"grad_norm": 11.3125,
"learning_rate": 1.709570736536521e-05,
"loss": 0.2547,
"step": 810
},
{
"epoch": 4.290385873119686,
"grad_norm": 7.15625,
"learning_rate": 1.6996633405133656e-05,
"loss": 0.272,
"step": 820
},
{
"epoch": 4.34270765206017,
"grad_norm": 9.1875,
"learning_rate": 1.68961954373567e-05,
"loss": 0.2467,
"step": 830
},
{
"epoch": 4.395029431000654,
"grad_norm": 8.125,
"learning_rate": 1.6794413042615168e-05,
"loss": 0.2421,
"step": 840
},
{
"epoch": 4.447351209941138,
"grad_norm": 9.4375,
"learning_rate": 1.6691306063588583e-05,
"loss": 0.2699,
"step": 850
},
{
"epoch": 4.499672988881622,
"grad_norm": 4.96875,
"learning_rate": 1.6586894601186804e-05,
"loss": 0.2446,
"step": 860
},
{
"epoch": 4.551994767822106,
"grad_norm": 7.46875,
"learning_rate": 1.6481199010631312e-05,
"loss": 0.2501,
"step": 870
},
{
"epoch": 4.60431654676259,
"grad_norm": 12.875,
"learning_rate": 1.63742398974869e-05,
"loss": 0.2508,
"step": 880
},
{
"epoch": 4.656638325703074,
"grad_norm": 10.4375,
"learning_rate": 1.6266038113644605e-05,
"loss": 0.2487,
"step": 890
},
{
"epoch": 4.708960104643558,
"grad_norm": 3.046875,
"learning_rate": 1.6156614753256583e-05,
"loss": 0.2384,
"step": 900
},
{
"epoch": 4.761281883584042,
"grad_norm": 11.1875,
"learning_rate": 1.6045991148623752e-05,
"loss": 0.2552,
"step": 910
},
{
"epoch": 4.8136036625245255,
"grad_norm": 10.6875,
"learning_rate": 1.5934188866037017e-05,
"loss": 0.2299,
"step": 920
},
{
"epoch": 4.86592544146501,
"grad_norm": 10.375,
"learning_rate": 1.5821229701572897e-05,
"loss": 0.2443,
"step": 930
},
{
"epoch": 4.918247220405494,
"grad_norm": 2.109375,
"learning_rate": 1.570713567684432e-05,
"loss": 0.2364,
"step": 940
},
{
"epoch": 4.970568999345978,
"grad_norm": 3.828125,
"learning_rate": 1.5591929034707468e-05,
"loss": 0.252,
"step": 950
},
{
"epoch": 5.022890778286461,
"grad_norm": 3.53125,
"learning_rate": 1.5475632234925505e-05,
"loss": 0.2499,
"step": 960
},
{
"epoch": 5.075212557226946,
"grad_norm": 7.90625,
"learning_rate": 1.5358267949789968e-05,
"loss": 0.2217,
"step": 970
},
{
"epoch": 5.12753433616743,
"grad_norm": 8.125,
"learning_rate": 1.5239859059700794e-05,
"loss": 0.2111,
"step": 980
},
{
"epoch": 5.179856115107913,
"grad_norm": 8.75,
"learning_rate": 1.5120428648705716e-05,
"loss": 0.2166,
"step": 990
},
{
"epoch": 5.232177894048398,
"grad_norm": 10.375,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.2056,
"step": 1000
},
{
"epoch": 5.284499672988882,
"grad_norm": 8.3125,
"learning_rate": 1.4878596591387329e-05,
"loss": 0.2002,
"step": 1010
},
{
"epoch": 5.3368214519293655,
"grad_norm": 8.4375,
"learning_rate": 1.4756242090702756e-05,
"loss": 0.2121,
"step": 1020
},
{
"epoch": 5.389143230869849,
"grad_norm": 6.5,
"learning_rate": 1.463296035119862e-05,
"loss": 0.2044,
"step": 1030
},
{
"epoch": 5.441465009810334,
"grad_norm": 12.5625,
"learning_rate": 1.4508775406894308e-05,
"loss": 0.217,
"step": 1040
},
{
"epoch": 5.493786788750818,
"grad_norm": 8.0625,
"learning_rate": 1.4383711467890776e-05,
"loss": 0.1979,
"step": 1050
},
{
"epoch": 5.546108567691301,
"grad_norm": 9.5,
"learning_rate": 1.4257792915650728e-05,
"loss": 0.2055,
"step": 1060
},
{
"epoch": 5.598430346631785,
"grad_norm": 7.25,
"learning_rate": 1.413104429824542e-05,
"loss": 0.1995,
"step": 1070
},
{
"epoch": 5.65075212557227,
"grad_norm": 3.0625,
"learning_rate": 1.4003490325568953e-05,
"loss": 0.2062,
"step": 1080
},
{
"epoch": 5.703073904512753,
"grad_norm": 13.875,
"learning_rate": 1.3875155864521031e-05,
"loss": 0.1973,
"step": 1090
},
{
"epoch": 5.755395683453237,
"grad_norm": 4.8125,
"learning_rate": 1.3746065934159123e-05,
"loss": 0.204,
"step": 1100
},
{
"epoch": 5.807717462393722,
"grad_norm": 7.65625,
"learning_rate": 1.3616245700820922e-05,
"loss": 0.1893,
"step": 1110
},
{
"epoch": 5.8600392413342055,
"grad_norm": 10.75,
"learning_rate": 1.3485720473218153e-05,
"loss": 0.2028,
"step": 1120
},
{
"epoch": 5.912361020274689,
"grad_norm": 7.71875,
"learning_rate": 1.3354515697502552e-05,
"loss": 0.1879,
"step": 1130
},
{
"epoch": 5.964682799215173,
"grad_norm": 6.4375,
"learning_rate": 1.3222656952305113e-05,
"loss": 0.1892,
"step": 1140
},
{
"epoch": 6.017004578155658,
"grad_norm": 3.4375,
"learning_rate": 1.3090169943749475e-05,
"loss": 0.2034,
"step": 1150
},
{
"epoch": 6.069326357096141,
"grad_norm": 9.0625,
"learning_rate": 1.2957080500440469e-05,
"loss": 0.1802,
"step": 1160
},
{
"epoch": 6.121648136036625,
"grad_norm": 7.9375,
"learning_rate": 1.2823414568428767e-05,
"loss": 0.1794,
"step": 1170
},
{
"epoch": 6.173969914977109,
"grad_norm": 7.28125,
"learning_rate": 1.2689198206152657e-05,
"loss": 0.1664,
"step": 1180
},
{
"epoch": 6.226291693917593,
"grad_norm": 9.25,
"learning_rate": 1.2554457579357906e-05,
"loss": 0.1859,
"step": 1190
},
{
"epoch": 6.278613472858077,
"grad_norm": 5.5625,
"learning_rate": 1.2419218955996677e-05,
"loss": 0.1643,
"step": 1200
},
{
"epoch": 6.330935251798561,
"grad_norm": 2.3125,
"learning_rate": 1.2283508701106559e-05,
"loss": 0.1696,
"step": 1210
},
{
"epoch": 6.3832570307390455,
"grad_norm": 5.0625,
"learning_rate": 1.2147353271670634e-05,
"loss": 0.1719,
"step": 1220
},
{
"epoch": 6.435578809679529,
"grad_norm": 7.3125,
"learning_rate": 1.2010779211459649e-05,
"loss": 0.1716,
"step": 1230
},
{
"epoch": 6.487900588620013,
"grad_norm": 4.125,
"learning_rate": 1.187381314585725e-05,
"loss": 0.1638,
"step": 1240
},
{
"epoch": 6.540222367560497,
"grad_norm": 6.0625,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.1708,
"step": 1250
},
{
"epoch": 6.592544146500981,
"grad_norm": 8.25,
"learning_rate": 1.159881187691835e-05,
"loss": 0.17,
"step": 1260
},
{
"epoch": 6.644865925441465,
"grad_norm": 5.09375,
"learning_rate": 1.1460830285624119e-05,
"loss": 0.1723,
"step": 1270
},
{
"epoch": 6.697187704381949,
"grad_norm": 6.5625,
"learning_rate": 1.1322563902571227e-05,
"loss": 0.1754,
"step": 1280
},
{
"epoch": 6.7495094833224325,
"grad_norm": 5.4375,
"learning_rate": 1.1184039683065014e-05,
"loss": 0.1596,
"step": 1290
},
{
"epoch": 6.801831262262917,
"grad_norm": 5.03125,
"learning_rate": 1.1045284632676535e-05,
"loss": 0.1591,
"step": 1300
},
{
"epoch": 6.854153041203401,
"grad_norm": 1.6171875,
"learning_rate": 1.0906325801977804e-05,
"loss": 0.1617,
"step": 1310
},
{
"epoch": 6.906474820143885,
"grad_norm": 5.75,
"learning_rate": 1.0767190281268187e-05,
"loss": 0.1598,
"step": 1320
},
{
"epoch": 6.958796599084369,
"grad_norm": 8.6875,
"learning_rate": 1.0627905195293135e-05,
"loss": 0.1559,
"step": 1330
},
{
"epoch": 7.011118378024853,
"grad_norm": 3.75,
"learning_rate": 1.0488497697956134e-05,
"loss": 0.173,
"step": 1340
},
{
"epoch": 7.063440156965337,
"grad_norm": 4.53125,
"learning_rate": 1.0348994967025012e-05,
"loss": 0.1495,
"step": 1350
},
{
"epoch": 7.11576193590582,
"grad_norm": 5.1875,
"learning_rate": 1.0209424198833571e-05,
"loss": 0.1428,
"step": 1360
},
{
"epoch": 7.168083714846305,
"grad_norm": 4.3125,
"learning_rate": 1.0069812602979617e-05,
"loss": 0.1433,
"step": 1370
},
{
"epoch": 7.220405493786789,
"grad_norm": 5.125,
"learning_rate": 9.930187397020385e-06,
"loss": 0.1519,
"step": 1380
},
{
"epoch": 7.2727272727272725,
"grad_norm": 4.4375,
"learning_rate": 9.790575801166432e-06,
"loss": 0.1491,
"step": 1390
},
{
"epoch": 7.325049051667757,
"grad_norm": 5.875,
"learning_rate": 9.651005032974994e-06,
"loss": 0.1435,
"step": 1400
},
{
"epoch": 7.377370830608241,
"grad_norm": 3.09375,
"learning_rate": 9.511502302043867e-06,
"loss": 0.1413,
"step": 1410
},
{
"epoch": 7.429692609548725,
"grad_norm": 5.5625,
"learning_rate": 9.372094804706867e-06,
"loss": 0.1398,
"step": 1420
},
{
"epoch": 7.482014388489208,
"grad_norm": 2.21875,
"learning_rate": 9.232809718731815e-06,
"loss": 0.1556,
"step": 1430
},
{
"epoch": 7.534336167429693,
"grad_norm": 4.03125,
"learning_rate": 9.093674198022201e-06,
"loss": 0.1479,
"step": 1440
},
{
"epoch": 7.586657946370177,
"grad_norm": 3.515625,
"learning_rate": 8.954715367323468e-06,
"loss": 0.1413,
"step": 1450
},
{
"epoch": 7.63897972531066,
"grad_norm": 5.375,
"learning_rate": 8.815960316934991e-06,
"loss": 0.1429,
"step": 1460
},
{
"epoch": 7.691301504251145,
"grad_norm": 2.09375,
"learning_rate": 8.677436097428775e-06,
"loss": 0.1425,
"step": 1470
},
{
"epoch": 7.743623283191629,
"grad_norm": 3.03125,
"learning_rate": 8.539169714375885e-06,
"loss": 0.1423,
"step": 1480
},
{
"epoch": 7.7959450621321125,
"grad_norm": 1.8515625,
"learning_rate": 8.401188123081653e-06,
"loss": 0.1396,
"step": 1490
},
{
"epoch": 7.848266841072596,
"grad_norm": 2.296875,
"learning_rate": 8.263518223330698e-06,
"loss": 0.1378,
"step": 1500
},
{
"epoch": 7.900588620013081,
"grad_norm": 2.984375,
"learning_rate": 8.126186854142752e-06,
"loss": 0.1319,
"step": 1510
},
{
"epoch": 7.9529103989535646,
"grad_norm": 1.5546875,
"learning_rate": 7.989220788540356e-06,
"loss": 0.1347,
"step": 1520
},
{
"epoch": 8.00523217789405,
"grad_norm": 1.109375,
"learning_rate": 7.852646728329368e-06,
"loss": 0.1356,
"step": 1530
},
{
"epoch": 8.057553956834532,
"grad_norm": 2.734375,
"learning_rate": 7.716491298893443e-06,
"loss": 0.131,
"step": 1540
},
{
"epoch": 8.109875735775017,
"grad_norm": 2.84375,
"learning_rate": 7.580781044003324e-06,
"loss": 0.1324,
"step": 1550
},
{
"epoch": 8.1621975147155,
"grad_norm": 2.265625,
"learning_rate": 7.445542420642097e-06,
"loss": 0.1296,
"step": 1560
},
{
"epoch": 8.214519293655984,
"grad_norm": 3.421875,
"learning_rate": 7.310801793847344e-06,
"loss": 0.1221,
"step": 1570
},
{
"epoch": 8.266841072596469,
"grad_norm": 2.484375,
"learning_rate": 7.176585431571235e-06,
"loss": 0.1287,
"step": 1580
},
{
"epoch": 8.319162851536952,
"grad_norm": 2.28125,
"learning_rate": 7.042919499559538e-06,
"loss": 0.1267,
"step": 1590
},
{
"epoch": 8.371484630477436,
"grad_norm": 2.4375,
"learning_rate": 6.909830056250527e-06,
"loss": 0.13,
"step": 1600
},
{
"epoch": 8.42380640941792,
"grad_norm": 1.5859375,
"learning_rate": 6.777343047694891e-06,
"loss": 0.127,
"step": 1610
},
{
"epoch": 8.476128188358404,
"grad_norm": 2.75,
"learning_rate": 6.645484302497452e-06,
"loss": 0.1231,
"step": 1620
},
{
"epoch": 8.528449967298888,
"grad_norm": 3.4375,
"learning_rate": 6.5142795267818505e-06,
"loss": 0.1271,
"step": 1630
},
{
"epoch": 8.580771746239373,
"grad_norm": 2.5625,
"learning_rate": 6.383754299179079e-06,
"loss": 0.1279,
"step": 1640
},
{
"epoch": 8.633093525179856,
"grad_norm": 0.90234375,
"learning_rate": 6.25393406584088e-06,
"loss": 0.1186,
"step": 1650
},
{
"epoch": 8.68541530412034,
"grad_norm": 1.203125,
"learning_rate": 6.124844135478971e-06,
"loss": 0.1218,
"step": 1660
},
{
"epoch": 8.737737083060825,
"grad_norm": 1.3828125,
"learning_rate": 5.996509674431053e-06,
"loss": 0.1255,
"step": 1670
},
{
"epoch": 8.790058862001308,
"grad_norm": 1.453125,
"learning_rate": 5.868955701754584e-06,
"loss": 0.117,
"step": 1680
},
{
"epoch": 8.842380640941792,
"grad_norm": 1.8671875,
"learning_rate": 5.742207084349274e-06,
"loss": 0.1256,
"step": 1690
},
{
"epoch": 8.894702419882275,
"grad_norm": 1.15625,
"learning_rate": 5.616288532109225e-06,
"loss": 0.1208,
"step": 1700
},
{
"epoch": 8.94702419882276,
"grad_norm": 5.25,
"learning_rate": 5.491224593105695e-06,
"loss": 0.1311,
"step": 1710
},
{
"epoch": 8.999345977763245,
"grad_norm": 1.75,
"learning_rate": 5.367039648801386e-06,
"loss": 0.1214,
"step": 1720
},
{
"epoch": 9.051667756703727,
"grad_norm": 2.5,
"learning_rate": 5.243757909297247e-06,
"loss": 0.1207,
"step": 1730
},
{
"epoch": 9.103989535644212,
"grad_norm": 0.88671875,
"learning_rate": 5.121403408612672e-06,
"loss": 0.1259,
"step": 1740
},
{
"epoch": 9.156311314584697,
"grad_norm": 2.21875,
"learning_rate": 5.000000000000003e-06,
"loss": 0.1147,
"step": 1750
},
{
"epoch": 9.20863309352518,
"grad_norm": 0.82421875,
"learning_rate": 4.879571351294287e-06,
"loss": 0.1174,
"step": 1760
},
{
"epoch": 9.260954872465664,
"grad_norm": 1.2578125,
"learning_rate": 4.76014094029921e-06,
"loss": 0.1145,
"step": 1770
},
{
"epoch": 9.313276651406149,
"grad_norm": 1.671875,
"learning_rate": 4.641732050210032e-06,
"loss": 0.1169,
"step": 1780
},
{
"epoch": 9.365598430346632,
"grad_norm": 1.03125,
"learning_rate": 4.524367765074499e-06,
"loss": 0.1125,
"step": 1790
},
{
"epoch": 9.417920209287116,
"grad_norm": 1.234375,
"learning_rate": 4.408070965292534e-06,
"loss": 0.1173,
"step": 1800
},
{
"epoch": 9.470241988227599,
"grad_norm": 0.80859375,
"learning_rate": 4.292864323155684e-06,
"loss": 0.1074,
"step": 1810
},
{
"epoch": 9.522563767168084,
"grad_norm": 1.3359375,
"learning_rate": 4.178770298427107e-06,
"loss": 0.1097,
"step": 1820
},
{
"epoch": 9.574885546108568,
"grad_norm": 0.94140625,
"learning_rate": 4.065811133962987e-06,
"loss": 0.1152,
"step": 1830
},
{
"epoch": 9.627207325049051,
"grad_norm": 0.72265625,
"learning_rate": 3.954008851376252e-06,
"loss": 0.1079,
"step": 1840
},
{
"epoch": 9.679529103989536,
"grad_norm": 1.2890625,
"learning_rate": 3.8433852467434175e-06,
"loss": 0.1223,
"step": 1850
},
{
"epoch": 9.73185088293002,
"grad_norm": 1.640625,
"learning_rate": 3.7339618863553983e-06,
"loss": 0.1204,
"step": 1860
},
{
"epoch": 9.784172661870503,
"grad_norm": 1.015625,
"learning_rate": 3.625760102513103e-06,
"loss": 0.1113,
"step": 1870
},
{
"epoch": 9.836494440810988,
"grad_norm": 1.5703125,
"learning_rate": 3.5188009893686916e-06,
"loss": 0.1145,
"step": 1880
},
{
"epoch": 9.888816219751472,
"grad_norm": 0.9765625,
"learning_rate": 3.4131053988131947e-06,
"loss": 0.1163,
"step": 1890
},
{
"epoch": 9.941137998691955,
"grad_norm": 0.83984375,
"learning_rate": 3.308693936411421e-06,
"loss": 0.1145,
"step": 1900
},
{
"epoch": 9.99345977763244,
"grad_norm": 1.015625,
"learning_rate": 3.2055869573848374e-06,
"loss": 0.1082,
"step": 1910
},
{
"epoch": 10.045781556572923,
"grad_norm": 0.88671875,
"learning_rate": 3.103804562643302e-06,
"loss": 0.1138,
"step": 1920
},
{
"epoch": 10.098103335513407,
"grad_norm": 0.80078125,
"learning_rate": 3.003366594866345e-06,
"loss": 0.1099,
"step": 1930
},
{
"epoch": 10.150425114453892,
"grad_norm": 1.4921875,
"learning_rate": 2.9042926346347932e-06,
"loss": 0.1063,
"step": 1940
},
{
"epoch": 10.202746893394375,
"grad_norm": 0.578125,
"learning_rate": 2.8066019966134907e-06,
"loss": 0.1101,
"step": 1950
},
{
"epoch": 10.25506867233486,
"grad_norm": 0.7734375,
"learning_rate": 2.7103137257858867e-06,
"loss": 0.108,
"step": 1960
},
{
"epoch": 10.307390451275344,
"grad_norm": 1.296875,
"learning_rate": 2.615446593741161e-06,
"loss": 0.1144,
"step": 1970
},
{
"epoch": 10.359712230215827,
"grad_norm": 0.88671875,
"learning_rate": 2.522019095014683e-06,
"loss": 0.1129,
"step": 1980
},
{
"epoch": 10.412034009156311,
"grad_norm": 0.56640625,
"learning_rate": 2.4300494434824373e-06,
"loss": 0.1115,
"step": 1990
},
{
"epoch": 10.464355788096796,
"grad_norm": 0.68359375,
"learning_rate": 2.339555568810221e-06,
"loss": 0.1137,
"step": 2000
}
],
"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": false
},
"attributes": {}
}
},
"total_flos": 7.650740827638989e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}