smollm-350M-instruct-test2-ep2 / trainer_state.json
loubnabnl's picture
loubnabnl HF staff
Model save
749c6e9 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1632,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0012254901960784314,
"grad_norm": 1.6059832937437346,
"learning_rate": 6.0975609756097564e-06,
"loss": 1.3541,
"step": 1
},
{
"epoch": 0.006127450980392157,
"grad_norm": 1.5281382037952618,
"learning_rate": 3.048780487804878e-05,
"loss": 1.3583,
"step": 5
},
{
"epoch": 0.012254901960784314,
"grad_norm": 0.5993529609680898,
"learning_rate": 6.097560975609756e-05,
"loss": 1.3375,
"step": 10
},
{
"epoch": 0.01838235294117647,
"grad_norm": 0.7098761948973563,
"learning_rate": 9.146341463414634e-05,
"loss": 1.2793,
"step": 15
},
{
"epoch": 0.024509803921568627,
"grad_norm": 0.4448928165735333,
"learning_rate": 0.00012195121951219512,
"loss": 1.2037,
"step": 20
},
{
"epoch": 0.030637254901960783,
"grad_norm": 0.40161131951951523,
"learning_rate": 0.0001524390243902439,
"loss": 1.1336,
"step": 25
},
{
"epoch": 0.03676470588235294,
"grad_norm": 0.2541806870693389,
"learning_rate": 0.00018292682926829268,
"loss": 1.1063,
"step": 30
},
{
"epoch": 0.0428921568627451,
"grad_norm": 0.1491059867354642,
"learning_rate": 0.00021341463414634146,
"loss": 1.0795,
"step": 35
},
{
"epoch": 0.049019607843137254,
"grad_norm": 0.14162648176415202,
"learning_rate": 0.00024390243902439024,
"loss": 1.0729,
"step": 40
},
{
"epoch": 0.05514705882352941,
"grad_norm": 0.14138145278805817,
"learning_rate": 0.00027439024390243905,
"loss": 1.0504,
"step": 45
},
{
"epoch": 0.061274509803921566,
"grad_norm": 0.11598136180137979,
"learning_rate": 0.0003048780487804878,
"loss": 1.0378,
"step": 50
},
{
"epoch": 0.06740196078431372,
"grad_norm": 0.14589294245833054,
"learning_rate": 0.0003353658536585366,
"loss": 1.0446,
"step": 55
},
{
"epoch": 0.07352941176470588,
"grad_norm": 0.14730649378552943,
"learning_rate": 0.00036585365853658537,
"loss": 1.0333,
"step": 60
},
{
"epoch": 0.07965686274509803,
"grad_norm": 0.11759388636190853,
"learning_rate": 0.0003963414634146342,
"loss": 1.0143,
"step": 65
},
{
"epoch": 0.0857843137254902,
"grad_norm": 0.12311842814802663,
"learning_rate": 0.0004268292682926829,
"loss": 1.0148,
"step": 70
},
{
"epoch": 0.09191176470588236,
"grad_norm": 0.11751325803408062,
"learning_rate": 0.00045731707317073173,
"loss": 1.0176,
"step": 75
},
{
"epoch": 0.09803921568627451,
"grad_norm": 0.13732149342206665,
"learning_rate": 0.0004878048780487805,
"loss": 1.0042,
"step": 80
},
{
"epoch": 0.10416666666666667,
"grad_norm": 0.11309991089195273,
"learning_rate": 0.0005182926829268293,
"loss": 1.0065,
"step": 85
},
{
"epoch": 0.11029411764705882,
"grad_norm": 0.12583526404678766,
"learning_rate": 0.0005487804878048781,
"loss": 1.0149,
"step": 90
},
{
"epoch": 0.11642156862745098,
"grad_norm": 0.12017272173906957,
"learning_rate": 0.0005792682926829268,
"loss": 0.9948,
"step": 95
},
{
"epoch": 0.12254901960784313,
"grad_norm": 0.11719746827044987,
"learning_rate": 0.0006097560975609756,
"loss": 0.9905,
"step": 100
},
{
"epoch": 0.12867647058823528,
"grad_norm": 0.13729668356371552,
"learning_rate": 0.0006402439024390244,
"loss": 0.9977,
"step": 105
},
{
"epoch": 0.13480392156862744,
"grad_norm": 0.12981775917103477,
"learning_rate": 0.0006707317073170732,
"loss": 1.0017,
"step": 110
},
{
"epoch": 0.1409313725490196,
"grad_norm": 0.13870526825011106,
"learning_rate": 0.0007012195121951219,
"loss": 0.9997,
"step": 115
},
{
"epoch": 0.14705882352941177,
"grad_norm": 0.12747253256734123,
"learning_rate": 0.0007317073170731707,
"loss": 0.9877,
"step": 120
},
{
"epoch": 0.15318627450980393,
"grad_norm": 0.12869096982052203,
"learning_rate": 0.0007621951219512195,
"loss": 0.9823,
"step": 125
},
{
"epoch": 0.15931372549019607,
"grad_norm": 0.12889388640011323,
"learning_rate": 0.0007926829268292683,
"loss": 0.9774,
"step": 130
},
{
"epoch": 0.16544117647058823,
"grad_norm": 0.13890909917337924,
"learning_rate": 0.000823170731707317,
"loss": 0.9874,
"step": 135
},
{
"epoch": 0.1715686274509804,
"grad_norm": 0.167350127299137,
"learning_rate": 0.0008536585365853659,
"loss": 0.9855,
"step": 140
},
{
"epoch": 0.17769607843137256,
"grad_norm": 0.12637500439423752,
"learning_rate": 0.0008841463414634147,
"loss": 0.9837,
"step": 145
},
{
"epoch": 0.18382352941176472,
"grad_norm": 0.13036804871454152,
"learning_rate": 0.0009146341463414635,
"loss": 0.9846,
"step": 150
},
{
"epoch": 0.18995098039215685,
"grad_norm": 0.13716320964191064,
"learning_rate": 0.0009451219512195122,
"loss": 0.9742,
"step": 155
},
{
"epoch": 0.19607843137254902,
"grad_norm": 0.1505410439189676,
"learning_rate": 0.000975609756097561,
"loss": 0.9657,
"step": 160
},
{
"epoch": 0.20220588235294118,
"grad_norm": 0.13939847463577426,
"learning_rate": 0.0009999988550474805,
"loss": 0.982,
"step": 165
},
{
"epoch": 0.20833333333333334,
"grad_norm": 0.1723912783342495,
"learning_rate": 0.000999958782259877,
"loss": 0.9771,
"step": 170
},
{
"epoch": 0.21446078431372548,
"grad_norm": 0.20339647033601935,
"learning_rate": 0.0009998614670898504,
"loss": 0.9742,
"step": 175
},
{
"epoch": 0.22058823529411764,
"grad_norm": 0.1805520187680447,
"learning_rate": 0.0009997069206794246,
"loss": 0.9724,
"step": 180
},
{
"epoch": 0.2267156862745098,
"grad_norm": 0.14101202234864954,
"learning_rate": 0.000999495160723267,
"loss": 0.9699,
"step": 185
},
{
"epoch": 0.23284313725490197,
"grad_norm": 0.14408773000983136,
"learning_rate": 0.0009992262114666653,
"loss": 0.9721,
"step": 190
},
{
"epoch": 0.23897058823529413,
"grad_norm": 0.12211770445331499,
"learning_rate": 0.0009989001037027502,
"loss": 0.9638,
"step": 195
},
{
"epoch": 0.24509803921568626,
"grad_norm": 0.11058292325672553,
"learning_rate": 0.0009985168747689707,
"loss": 0.9613,
"step": 200
},
{
"epoch": 0.2512254901960784,
"grad_norm": 0.151326097792135,
"learning_rate": 0.0009980765685428175,
"loss": 0.9784,
"step": 205
},
{
"epoch": 0.25735294117647056,
"grad_norm": 0.13748406413323222,
"learning_rate": 0.0009975792354368017,
"loss": 0.9578,
"step": 210
},
{
"epoch": 0.26348039215686275,
"grad_norm": 0.13529789016829663,
"learning_rate": 0.000997024932392681,
"loss": 0.9561,
"step": 215
},
{
"epoch": 0.2696078431372549,
"grad_norm": 0.11913360946345405,
"learning_rate": 0.0009964137228749407,
"loss": 0.9587,
"step": 220
},
{
"epoch": 0.2757352941176471,
"grad_norm": 0.11311287494378686,
"learning_rate": 0.0009957456768635274,
"loss": 0.9534,
"step": 225
},
{
"epoch": 0.2818627450980392,
"grad_norm": 0.1687787460034738,
"learning_rate": 0.000995020870845837,
"loss": 0.9483,
"step": 230
},
{
"epoch": 0.28799019607843135,
"grad_norm": 0.13894852921173279,
"learning_rate": 0.000994239387807957,
"loss": 0.9465,
"step": 235
},
{
"epoch": 0.29411764705882354,
"grad_norm": 0.15098532770679463,
"learning_rate": 0.0009934013172251653,
"loss": 0.9512,
"step": 240
},
{
"epoch": 0.3002450980392157,
"grad_norm": 0.1603820773467054,
"learning_rate": 0.0009925067550516852,
"loss": 0.9364,
"step": 245
},
{
"epoch": 0.30637254901960786,
"grad_norm": 0.20531045303348816,
"learning_rate": 0.0009915558037097002,
"loss": 0.9436,
"step": 250
},
{
"epoch": 0.3125,
"grad_norm": 0.1373133786573118,
"learning_rate": 0.0009905485720776265,
"loss": 0.934,
"step": 255
},
{
"epoch": 0.31862745098039214,
"grad_norm": 1.8470429009125096,
"learning_rate": 0.0009894851754776472,
"loss": 0.9526,
"step": 260
},
{
"epoch": 0.3247549019607843,
"grad_norm": 0.11771908587868915,
"learning_rate": 0.000988365735662509,
"loss": 0.9513,
"step": 265
},
{
"epoch": 0.33088235294117646,
"grad_norm": 0.14600554728304563,
"learning_rate": 0.0009871903808015812,
"loss": 0.9424,
"step": 270
},
{
"epoch": 0.33700980392156865,
"grad_norm": 0.12078857521986237,
"learning_rate": 0.0009859592454661823,
"loss": 0.9501,
"step": 275
},
{
"epoch": 0.3431372549019608,
"grad_norm": 0.12236086569601477,
"learning_rate": 0.0009846724706141716,
"loss": 0.9445,
"step": 280
},
{
"epoch": 0.3492647058823529,
"grad_norm": 0.13112435126866281,
"learning_rate": 0.0009833302035738107,
"loss": 0.9363,
"step": 285
},
{
"epoch": 0.3553921568627451,
"grad_norm": 0.14235863463223497,
"learning_rate": 0.0009819325980268945,
"loss": 0.9485,
"step": 290
},
{
"epoch": 0.36151960784313725,
"grad_norm": 0.12952693104841728,
"learning_rate": 0.0009804798139911568,
"loss": 0.9421,
"step": 295
},
{
"epoch": 0.36764705882352944,
"grad_norm": 0.11889525565491425,
"learning_rate": 0.0009789720178019483,
"loss": 0.9321,
"step": 300
},
{
"epoch": 0.3737745098039216,
"grad_norm": 0.10497064780361466,
"learning_rate": 0.0009774093820931922,
"loss": 0.9383,
"step": 305
},
{
"epoch": 0.3799019607843137,
"grad_norm": 0.1297312332951932,
"learning_rate": 0.0009757920857776188,
"loss": 0.9315,
"step": 310
},
{
"epoch": 0.3860294117647059,
"grad_norm": 0.12939401003239853,
"learning_rate": 0.0009741203140262813,
"loss": 0.931,
"step": 315
},
{
"epoch": 0.39215686274509803,
"grad_norm": 0.1724687096774714,
"learning_rate": 0.0009723942582473544,
"loss": 0.9244,
"step": 320
},
{
"epoch": 0.39828431372549017,
"grad_norm": 0.1440746949158844,
"learning_rate": 0.000970614116064219,
"loss": 0.9186,
"step": 325
},
{
"epoch": 0.40441176470588236,
"grad_norm": 0.11601098074712127,
"learning_rate": 0.0009687800912928362,
"loss": 0.9331,
"step": 330
},
{
"epoch": 0.4105392156862745,
"grad_norm": 0.16676922492027155,
"learning_rate": 0.0009668923939184109,
"loss": 0.9282,
"step": 335
},
{
"epoch": 0.4166666666666667,
"grad_norm": 0.16264723211095694,
"learning_rate": 0.0009649512400713498,
"loss": 0.931,
"step": 340
},
{
"epoch": 0.4227941176470588,
"grad_norm": 0.12835068212058262,
"learning_rate": 0.000962956852002516,
"loss": 0.9212,
"step": 345
},
{
"epoch": 0.42892156862745096,
"grad_norm": 0.11722967905017813,
"learning_rate": 0.0009609094580577824,
"loss": 0.9301,
"step": 350
},
{
"epoch": 0.43504901960784315,
"grad_norm": 0.11753159563989828,
"learning_rate": 0.0009588092926518875,
"loss": 0.9181,
"step": 355
},
{
"epoch": 0.4411764705882353,
"grad_norm": 0.3058794099499992,
"learning_rate": 0.0009566565962415959,
"loss": 0.9276,
"step": 360
},
{
"epoch": 0.44730392156862747,
"grad_norm": 0.11638001282284417,
"learning_rate": 0.0009544516152981679,
"loss": 0.9187,
"step": 365
},
{
"epoch": 0.4534313725490196,
"grad_norm": 0.0979888983879341,
"learning_rate": 0.0009521946022791401,
"loss": 0.9178,
"step": 370
},
{
"epoch": 0.45955882352941174,
"grad_norm": 0.12474491987381439,
"learning_rate": 0.0009498858155994194,
"loss": 0.9248,
"step": 375
},
{
"epoch": 0.46568627450980393,
"grad_norm": 0.11539100379640589,
"learning_rate": 0.0009475255196016972,
"loss": 0.9082,
"step": 380
},
{
"epoch": 0.47181372549019607,
"grad_norm": 0.11060768973607205,
"learning_rate": 0.0009451139845261834,
"loss": 0.913,
"step": 385
},
{
"epoch": 0.47794117647058826,
"grad_norm": 0.10933884625046772,
"learning_rate": 0.0009426514864796647,
"loss": 0.9164,
"step": 390
},
{
"epoch": 0.4840686274509804,
"grad_norm": 0.12110040734071437,
"learning_rate": 0.000940138307403893,
"loss": 0.918,
"step": 395
},
{
"epoch": 0.49019607843137253,
"grad_norm": 0.12516912467922992,
"learning_rate": 0.0009375747350433044,
"loss": 0.9099,
"step": 400
},
{
"epoch": 0.4963235294117647,
"grad_norm": 0.15405339011075656,
"learning_rate": 0.0009349610629120733,
"loss": 0.9153,
"step": 405
},
{
"epoch": 0.5024509803921569,
"grad_norm": 0.15983105881560317,
"learning_rate": 0.0009322975902605082,
"loss": 0.9139,
"step": 410
},
{
"epoch": 0.508578431372549,
"grad_norm": 0.12456698491529061,
"learning_rate": 0.000929584622040788,
"loss": 0.9196,
"step": 415
},
{
"epoch": 0.5147058823529411,
"grad_norm": 0.39391857600951824,
"learning_rate": 0.0009268224688720474,
"loss": 0.911,
"step": 420
},
{
"epoch": 0.5208333333333334,
"grad_norm": 0.135863544001222,
"learning_rate": 0.0009240114470048129,
"loss": 0.9082,
"step": 425
},
{
"epoch": 0.5269607843137255,
"grad_norm": 0.16266736226237394,
"learning_rate": 0.0009211518782847931,
"loss": 0.9208,
"step": 430
},
{
"epoch": 0.5330882352941176,
"grad_norm": 0.14823148129955332,
"learning_rate": 0.0009182440901160307,
"loss": 0.9243,
"step": 435
},
{
"epoch": 0.5392156862745098,
"grad_norm": 0.14300453285294948,
"learning_rate": 0.0009152884154234145,
"loss": 0.9082,
"step": 440
},
{
"epoch": 0.5453431372549019,
"grad_norm": 0.11464976577167021,
"learning_rate": 0.0009122851926145641,
"loss": 0.9066,
"step": 445
},
{
"epoch": 0.5514705882352942,
"grad_norm": 0.1380022527629278,
"learning_rate": 0.0009092347655410818,
"loss": 0.9059,
"step": 450
},
{
"epoch": 0.5575980392156863,
"grad_norm": 0.12505924658066125,
"learning_rate": 0.0009061374834591849,
"loss": 0.9106,
"step": 455
},
{
"epoch": 0.5637254901960784,
"grad_norm": 0.14573814560545809,
"learning_rate": 0.0009029937009897176,
"loss": 0.9085,
"step": 460
},
{
"epoch": 0.5698529411764706,
"grad_norm": 0.12549980653285886,
"learning_rate": 0.0008998037780775488,
"loss": 0.9134,
"step": 465
},
{
"epoch": 0.5759803921568627,
"grad_norm": 1.0091372919881914,
"learning_rate": 0.0008965680799503608,
"loss": 0.9012,
"step": 470
},
{
"epoch": 0.5821078431372549,
"grad_norm": 0.12482100803406715,
"learning_rate": 0.0008932869770768326,
"loss": 0.9083,
"step": 475
},
{
"epoch": 0.5882352941176471,
"grad_norm": 0.16842450336753725,
"learning_rate": 0.0008899608451242233,
"loss": 0.906,
"step": 480
},
{
"epoch": 0.5943627450980392,
"grad_norm": 0.37435753717247394,
"learning_rate": 0.0008865900649153606,
"loss": 0.9116,
"step": 485
},
{
"epoch": 0.6004901960784313,
"grad_norm": 0.1504221848097725,
"learning_rate": 0.0008831750223850389,
"loss": 0.9069,
"step": 490
},
{
"epoch": 0.6066176470588235,
"grad_norm": 0.6779799933680686,
"learning_rate": 0.0008797161085358317,
"loss": 0.8935,
"step": 495
},
{
"epoch": 0.6127450980392157,
"grad_norm": 0.4033225235584718,
"learning_rate": 0.0008762137193933241,
"loss": 0.898,
"step": 500
},
{
"epoch": 0.6188725490196079,
"grad_norm": 0.12597786237207237,
"learning_rate": 0.0008726682559607706,
"loss": 0.8965,
"step": 505
},
{
"epoch": 0.625,
"grad_norm": 0.12434445433374085,
"learning_rate": 0.0008690801241731818,
"loss": 0.9195,
"step": 510
},
{
"epoch": 0.6311274509803921,
"grad_norm": 0.11180950505927977,
"learning_rate": 0.0008654497348508476,
"loss": 0.8856,
"step": 515
},
{
"epoch": 0.6372549019607843,
"grad_norm": 0.11471149278729899,
"learning_rate": 0.0008617775036523015,
"loss": 0.888,
"step": 520
},
{
"epoch": 0.6433823529411765,
"grad_norm": 0.10661278460678202,
"learning_rate": 0.000858063851026728,
"loss": 0.8844,
"step": 525
},
{
"epoch": 0.6495098039215687,
"grad_norm": 0.13323867388840102,
"learning_rate": 0.0008543092021658259,
"loss": 0.8917,
"step": 530
},
{
"epoch": 0.6556372549019608,
"grad_norm": 0.11051797161585711,
"learning_rate": 0.0008505139869551248,
"loss": 0.8966,
"step": 535
},
{
"epoch": 0.6617647058823529,
"grad_norm": 0.10201940027044504,
"learning_rate": 0.0008466786399247663,
"loss": 0.9086,
"step": 540
},
{
"epoch": 0.6678921568627451,
"grad_norm": 0.11341681063010137,
"learning_rate": 0.000842803600199753,
"loss": 0.885,
"step": 545
},
{
"epoch": 0.6740196078431373,
"grad_norm": 0.11249706294845149,
"learning_rate": 0.0008388893114496705,
"loss": 0.8761,
"step": 550
},
{
"epoch": 0.6801470588235294,
"grad_norm": 0.10372930065250463,
"learning_rate": 0.0008349362218378904,
"loss": 0.8875,
"step": 555
},
{
"epoch": 0.6862745098039216,
"grad_norm": 0.1473106555936528,
"learning_rate": 0.0008309447839702582,
"loss": 0.8813,
"step": 560
},
{
"epoch": 0.6924019607843137,
"grad_norm": 0.11251651358057665,
"learning_rate": 0.0008269154548432722,
"loss": 0.8856,
"step": 565
},
{
"epoch": 0.6985294117647058,
"grad_norm": 0.18983642337639475,
"learning_rate": 0.0008228486957917607,
"loss": 0.8893,
"step": 570
},
{
"epoch": 0.7046568627450981,
"grad_norm": 0.1926017574087406,
"learning_rate": 0.0008187449724360605,
"loss": 0.8853,
"step": 575
},
{
"epoch": 0.7107843137254902,
"grad_norm": 0.10232469720003605,
"learning_rate": 0.0008146047546287076,
"loss": 0.8786,
"step": 580
},
{
"epoch": 0.7169117647058824,
"grad_norm": 0.1029258945252611,
"learning_rate": 0.0008104285164006415,
"loss": 0.8799,
"step": 585
},
{
"epoch": 0.7230392156862745,
"grad_norm": 0.14002711821151018,
"learning_rate": 0.0008062167359069301,
"loss": 0.8827,
"step": 590
},
{
"epoch": 0.7291666666666666,
"grad_norm": 0.11144023976662691,
"learning_rate": 0.0008019698953720256,
"loss": 0.8832,
"step": 595
},
{
"epoch": 0.7352941176470589,
"grad_norm": 0.12878152634910894,
"learning_rate": 0.000797688481034551,
"loss": 0.8852,
"step": 600
},
{
"epoch": 0.741421568627451,
"grad_norm": 0.12427328372120441,
"learning_rate": 0.0007933729830916297,
"loss": 0.8807,
"step": 605
},
{
"epoch": 0.7475490196078431,
"grad_norm": 0.10823708822180528,
"learning_rate": 0.00078902389564276,
"loss": 0.8839,
"step": 610
},
{
"epoch": 0.7536764705882353,
"grad_norm": 0.106769228793293,
"learning_rate": 0.0007846417166332445,
"loss": 0.8756,
"step": 615
},
{
"epoch": 0.7598039215686274,
"grad_norm": 0.10610630308145001,
"learning_rate": 0.0007802269477971771,
"loss": 0.8786,
"step": 620
},
{
"epoch": 0.7659313725490197,
"grad_norm": 0.11560264922747754,
"learning_rate": 0.000775780094599998,
"loss": 0.8769,
"step": 625
},
{
"epoch": 0.7720588235294118,
"grad_norm": 0.14907985785369013,
"learning_rate": 0.0007713016661806211,
"loss": 0.8795,
"step": 630
},
{
"epoch": 0.7781862745098039,
"grad_norm": 0.11129324500895409,
"learning_rate": 0.00076679217529314,
"loss": 0.875,
"step": 635
},
{
"epoch": 0.7843137254901961,
"grad_norm": 0.14839037572821354,
"learning_rate": 0.0007622521382481208,
"loss": 0.8703,
"step": 640
},
{
"epoch": 0.7904411764705882,
"grad_norm": 0.13899413539068264,
"learning_rate": 0.0007576820748534875,
"loss": 0.8763,
"step": 645
},
{
"epoch": 0.7965686274509803,
"grad_norm": 0.11601000036057739,
"learning_rate": 0.0007530825083550073,
"loss": 0.887,
"step": 650
},
{
"epoch": 0.8026960784313726,
"grad_norm": 0.10442455243797781,
"learning_rate": 0.0007484539653763815,
"loss": 0.8751,
"step": 655
},
{
"epoch": 0.8088235294117647,
"grad_norm": 0.12520557374066849,
"learning_rate": 0.0007437969758589507,
"loss": 0.8673,
"step": 660
},
{
"epoch": 0.8149509803921569,
"grad_norm": 0.11448612465079618,
"learning_rate": 0.0007391120730010193,
"loss": 0.8694,
"step": 665
},
{
"epoch": 0.821078431372549,
"grad_norm": 0.13153196077249837,
"learning_rate": 0.0007343997931968067,
"loss": 0.87,
"step": 670
},
{
"epoch": 0.8272058823529411,
"grad_norm": 0.11840806919932775,
"learning_rate": 0.0007296606759750351,
"loss": 0.8672,
"step": 675
},
{
"epoch": 0.8333333333333334,
"grad_norm": 0.09757556694809401,
"learning_rate": 0.0007248952639371542,
"loss": 0.8676,
"step": 680
},
{
"epoch": 0.8394607843137255,
"grad_norm": 0.09022546372550531,
"learning_rate": 0.0007201041026952188,
"loss": 0.8664,
"step": 685
},
{
"epoch": 0.8455882352941176,
"grad_norm": 0.10331609924034306,
"learning_rate": 0.0007152877408094178,
"loss": 0.8616,
"step": 690
},
{
"epoch": 0.8517156862745098,
"grad_norm": 0.12505516849755346,
"learning_rate": 0.0007104467297252677,
"loss": 0.8652,
"step": 695
},
{
"epoch": 0.8578431372549019,
"grad_norm": 0.09465790589490469,
"learning_rate": 0.0007055816237104753,
"loss": 0.8699,
"step": 700
},
{
"epoch": 0.8639705882352942,
"grad_norm": 0.12150502920638975,
"learning_rate": 0.0007006929797914775,
"loss": 0.8597,
"step": 705
},
{
"epoch": 0.8700980392156863,
"grad_norm": 0.10318640070426116,
"learning_rate": 0.0006957813576896647,
"loss": 0.8603,
"step": 710
},
{
"epoch": 0.8762254901960784,
"grad_norm": 0.11768219039546857,
"learning_rate": 0.000690847319757296,
"loss": 0.8653,
"step": 715
},
{
"epoch": 0.8823529411764706,
"grad_norm": 0.13084092032465588,
"learning_rate": 0.000685891430913113,
"loss": 0.8599,
"step": 720
},
{
"epoch": 0.8884803921568627,
"grad_norm": 0.1378907468788972,
"learning_rate": 0.0006809142585776604,
"loss": 0.8625,
"step": 725
},
{
"epoch": 0.8946078431372549,
"grad_norm": 0.1137277604032764,
"learning_rate": 0.0006759163726083191,
"loss": 0.8626,
"step": 730
},
{
"epoch": 0.9007352941176471,
"grad_norm": 0.10001539507212627,
"learning_rate": 0.0006708983452340609,
"loss": 0.849,
"step": 735
},
{
"epoch": 0.9068627450980392,
"grad_norm": 0.10484673231574948,
"learning_rate": 0.0006658607509899319,
"loss": 0.8682,
"step": 740
},
{
"epoch": 0.9129901960784313,
"grad_norm": 0.15431021500080286,
"learning_rate": 0.0006608041666512712,
"loss": 0.8645,
"step": 745
},
{
"epoch": 0.9191176470588235,
"grad_norm": 0.11219846062082936,
"learning_rate": 0.0006557291711676738,
"loss": 0.8541,
"step": 750
},
{
"epoch": 0.9252450980392157,
"grad_norm": 0.11968297539967529,
"learning_rate": 0.0006506363455967037,
"loss": 0.8645,
"step": 755
},
{
"epoch": 0.9313725490196079,
"grad_norm": 0.1421862868626235,
"learning_rate": 0.0006455262730373672,
"loss": 0.8628,
"step": 760
},
{
"epoch": 0.9375,
"grad_norm": 0.09419342625695648,
"learning_rate": 0.0006403995385633503,
"loss": 0.859,
"step": 765
},
{
"epoch": 0.9436274509803921,
"grad_norm": 0.10436946711990462,
"learning_rate": 0.0006352567291560318,
"loss": 0.8564,
"step": 770
},
{
"epoch": 0.9497549019607843,
"grad_norm": 0.11378998198564375,
"learning_rate": 0.0006300984336372771,
"loss": 0.8552,
"step": 775
},
{
"epoch": 0.9558823529411765,
"grad_norm": 0.11204753073504012,
"learning_rate": 0.0006249252426020216,
"loss": 0.8567,
"step": 780
},
{
"epoch": 0.9620098039215687,
"grad_norm": 0.13969543336270682,
"learning_rate": 0.000619737748350651,
"loss": 0.8521,
"step": 785
},
{
"epoch": 0.9681372549019608,
"grad_norm": 0.10178000324550646,
"learning_rate": 0.0006145365448211866,
"loss": 0.849,
"step": 790
},
{
"epoch": 0.9742647058823529,
"grad_norm": 0.28123512574152176,
"learning_rate": 0.0006093222275212822,
"loss": 0.8539,
"step": 795
},
{
"epoch": 0.9803921568627451,
"grad_norm": 0.11687237794199178,
"learning_rate": 0.0006040953934600423,
"loss": 0.8466,
"step": 800
},
{
"epoch": 0.9865196078431373,
"grad_norm": 0.08664193399778343,
"learning_rate": 0.0005988566410796687,
"loss": 0.8408,
"step": 805
},
{
"epoch": 0.9926470588235294,
"grad_norm": 0.1332025987779646,
"learning_rate": 0.0005936065701869403,
"loss": 0.8545,
"step": 810
},
{
"epoch": 0.9987745098039216,
"grad_norm": 2.6257846647757304,
"learning_rate": 0.0005883457818845414,
"loss": 0.8575,
"step": 815
},
{
"epoch": 1.0,
"eval_loss": 1.2250986099243164,
"eval_runtime": 111.2787,
"eval_samples_per_second": 188.185,
"eval_steps_per_second": 5.886,
"step": 816
},
{
"epoch": 1.0049019607843137,
"grad_norm": 1.2727033946666415,
"learning_rate": 0.0005830748785022368,
"loss": 0.7791,
"step": 820
},
{
"epoch": 1.0110294117647058,
"grad_norm": 0.1911261436318345,
"learning_rate": 0.0005777944635279099,
"loss": 0.7643,
"step": 825
},
{
"epoch": 1.017156862745098,
"grad_norm": 0.1586922694379843,
"learning_rate": 0.0005725051415384657,
"loss": 0.7516,
"step": 830
},
{
"epoch": 1.0232843137254901,
"grad_norm": 0.11186631342494315,
"learning_rate": 0.0005672075181306108,
"loss": 0.7526,
"step": 835
},
{
"epoch": 1.0294117647058822,
"grad_norm": 0.13268928121380016,
"learning_rate": 0.0005619021998515165,
"loss": 0.7699,
"step": 840
},
{
"epoch": 1.0355392156862746,
"grad_norm": 0.11229206406982119,
"learning_rate": 0.0005565897941293721,
"loss": 0.7813,
"step": 845
},
{
"epoch": 1.0416666666666667,
"grad_norm": 0.12012493868077331,
"learning_rate": 0.000551270909203838,
"loss": 0.7606,
"step": 850
},
{
"epoch": 1.0477941176470589,
"grad_norm": 0.11528601274141542,
"learning_rate": 0.0005459461540564057,
"loss": 0.7597,
"step": 855
},
{
"epoch": 1.053921568627451,
"grad_norm": 0.10690663798544056,
"learning_rate": 0.0005406161383406731,
"loss": 0.7595,
"step": 860
},
{
"epoch": 1.0600490196078431,
"grad_norm": 0.13779006322984594,
"learning_rate": 0.000535281472312543,
"loss": 0.7604,
"step": 865
},
{
"epoch": 1.0661764705882353,
"grad_norm": 0.1286321993738431,
"learning_rate": 0.0005299427667603515,
"loss": 0.7591,
"step": 870
},
{
"epoch": 1.0723039215686274,
"grad_norm": 0.11691581398274645,
"learning_rate": 0.0005246006329349376,
"loss": 0.7539,
"step": 875
},
{
"epoch": 1.0784313725490196,
"grad_norm": 0.1359966051449655,
"learning_rate": 0.0005192556824796568,
"loss": 0.7478,
"step": 880
},
{
"epoch": 1.0845588235294117,
"grad_norm": 0.11784308765572785,
"learning_rate": 0.0005139085273603527,
"loss": 0.7526,
"step": 885
},
{
"epoch": 1.0906862745098038,
"grad_norm": 0.08243234125547984,
"learning_rate": 0.0005085597797952905,
"loss": 0.7503,
"step": 890
},
{
"epoch": 1.0968137254901962,
"grad_norm": 0.10687199207970824,
"learning_rate": 0.0005032100521850608,
"loss": 0.7639,
"step": 895
},
{
"epoch": 1.1029411764705883,
"grad_norm": 0.09754168316674887,
"learning_rate": 0.0004978599570424639,
"loss": 0.7648,
"step": 900
},
{
"epoch": 1.1090686274509804,
"grad_norm": 0.09597242384268918,
"learning_rate": 0.0004925101069223802,
"loss": 0.7618,
"step": 905
},
{
"epoch": 1.1151960784313726,
"grad_norm": 0.16042928535903608,
"learning_rate": 0.0004871611143516367,
"loss": 0.7488,
"step": 910
},
{
"epoch": 1.1213235294117647,
"grad_norm": 0.11558221571064126,
"learning_rate": 0.00048181359175887594,
"loss": 0.758,
"step": 915
},
{
"epoch": 1.1274509803921569,
"grad_norm": 0.10187875911094818,
"learning_rate": 0.0004764681514044362,
"loss": 0.7548,
"step": 920
},
{
"epoch": 1.133578431372549,
"grad_norm": 0.10845733289411896,
"learning_rate": 0.0004711254053102521,
"loss": 0.7447,
"step": 925
},
{
"epoch": 1.1397058823529411,
"grad_norm": 0.12423589225823602,
"learning_rate": 0.0004657859651897806,
"loss": 0.7567,
"step": 930
},
{
"epoch": 1.1458333333333333,
"grad_norm": 0.101823111875683,
"learning_rate": 0.0004604504423779639,
"loss": 0.7496,
"step": 935
},
{
"epoch": 1.1519607843137254,
"grad_norm": 0.1490251916250933,
"learning_rate": 0.00045511944776123513,
"loss": 0.7476,
"step": 940
},
{
"epoch": 1.1580882352941178,
"grad_norm": 0.0909899046261831,
"learning_rate": 0.00044979359170757555,
"loss": 0.7557,
"step": 945
},
{
"epoch": 1.1642156862745099,
"grad_norm": 0.10504026034830631,
"learning_rate": 0.00044447348399663056,
"loss": 0.7551,
"step": 950
},
{
"epoch": 1.170343137254902,
"grad_norm": 0.10154008572100809,
"learning_rate": 0.00043915973374989326,
"loss": 0.7553,
"step": 955
},
{
"epoch": 1.1764705882352942,
"grad_norm": 0.0948668753989249,
"learning_rate": 0.0004338529493609647,
"loss": 0.7529,
"step": 960
},
{
"epoch": 1.1825980392156863,
"grad_norm": 0.12214475449625242,
"learning_rate": 0.0004285537384258951,
"loss": 0.7544,
"step": 965
},
{
"epoch": 1.1887254901960784,
"grad_norm": 0.10021333779503093,
"learning_rate": 0.00042326270767361815,
"loss": 0.7561,
"step": 970
},
{
"epoch": 1.1948529411764706,
"grad_norm": 0.10089690279960518,
"learning_rate": 0.0004179804628964839,
"loss": 0.7473,
"step": 975
},
{
"epoch": 1.2009803921568627,
"grad_norm": 0.09480462930649244,
"learning_rate": 0.00041270760888089997,
"loss": 0.7543,
"step": 980
},
{
"epoch": 1.2071078431372548,
"grad_norm": 0.13593486404780272,
"learning_rate": 0.000407444749338085,
"loss": 0.7447,
"step": 985
},
{
"epoch": 1.213235294117647,
"grad_norm": 0.09373417852720169,
"learning_rate": 0.00040219248683494925,
"loss": 0.7516,
"step": 990
},
{
"epoch": 1.219362745098039,
"grad_norm": 0.09327325503229338,
"learning_rate": 0.00039695142272510334,
"loss": 0.7443,
"step": 995
},
{
"epoch": 1.2254901960784315,
"grad_norm": 0.10034654814592268,
"learning_rate": 0.0003917221570800065,
"loss": 0.7475,
"step": 1000
},
{
"epoch": 1.2316176470588236,
"grad_norm": 0.09837253795265176,
"learning_rate": 0.0003865052886202621,
"loss": 0.7438,
"step": 1005
},
{
"epoch": 1.2377450980392157,
"grad_norm": 0.09051967236076873,
"learning_rate": 0.000381301414647068,
"loss": 0.7537,
"step": 1010
},
{
"epoch": 1.2438725490196079,
"grad_norm": 0.08928603737077674,
"learning_rate": 0.0003761111309738285,
"loss": 0.7372,
"step": 1015
},
{
"epoch": 1.25,
"grad_norm": 0.10153157943466443,
"learning_rate": 0.0003709350318579371,
"loss": 0.748,
"step": 1020
},
{
"epoch": 1.2561274509803921,
"grad_norm": 0.09687550081111064,
"learning_rate": 0.0003657737099327378,
"loss": 0.7445,
"step": 1025
},
{
"epoch": 1.2622549019607843,
"grad_norm": 0.08345067550046266,
"learning_rate": 0.0003606277561396726,
"loss": 0.7459,
"step": 1030
},
{
"epoch": 1.2683823529411764,
"grad_norm": 0.09822605701018818,
"learning_rate": 0.0003554977596606203,
"loss": 0.7473,
"step": 1035
},
{
"epoch": 1.2745098039215685,
"grad_norm": 0.08897185232535443,
"learning_rate": 0.00035038430785044053,
"loss": 0.7485,
"step": 1040
},
{
"epoch": 1.280637254901961,
"grad_norm": 0.09625591066370137,
"learning_rate": 0.00034528798616972434,
"loss": 0.739,
"step": 1045
},
{
"epoch": 1.2867647058823528,
"grad_norm": 0.09405754837547836,
"learning_rate": 0.00034020937811776156,
"loss": 0.7558,
"step": 1050
},
{
"epoch": 1.2928921568627452,
"grad_norm": 0.10283887592029052,
"learning_rate": 0.0003351490651657347,
"loss": 0.7576,
"step": 1055
},
{
"epoch": 1.2990196078431373,
"grad_norm": 0.09668902027134954,
"learning_rate": 0.00033010762669014347,
"loss": 0.7339,
"step": 1060
},
{
"epoch": 1.3051470588235294,
"grad_norm": 0.09491296282202684,
"learning_rate": 0.00032508563990646925,
"loss": 0.74,
"step": 1065
},
{
"epoch": 1.3112745098039216,
"grad_norm": 0.08614797698276408,
"learning_rate": 0.00032008367980308734,
"loss": 0.7491,
"step": 1070
},
{
"epoch": 1.3174019607843137,
"grad_norm": 0.11385248252735118,
"learning_rate": 0.0003151023190754343,
"loss": 0.7424,
"step": 1075
},
{
"epoch": 1.3235294117647058,
"grad_norm": 0.09914180185658039,
"learning_rate": 0.0003101421280604379,
"loss": 0.7386,
"step": 1080
},
{
"epoch": 1.329656862745098,
"grad_norm": 0.23046737698236164,
"learning_rate": 0.000305203674671216,
"loss": 0.7429,
"step": 1085
},
{
"epoch": 1.3357843137254901,
"grad_norm": 0.08999049028390338,
"learning_rate": 0.00030028752433205476,
"loss": 0.7504,
"step": 1090
},
{
"epoch": 1.3419117647058822,
"grad_norm": 0.08798822285342148,
"learning_rate": 0.0002953942399136702,
"loss": 0.7475,
"step": 1095
},
{
"epoch": 1.3480392156862746,
"grad_norm": 0.11440187719573272,
"learning_rate": 0.00029052438166876307,
"loss": 0.745,
"step": 1100
},
{
"epoch": 1.3541666666666667,
"grad_norm": 0.09680996894090088,
"learning_rate": 0.00028567850716787257,
"loss": 0.7493,
"step": 1105
},
{
"epoch": 1.3602941176470589,
"grad_norm": 0.08285996425508975,
"learning_rate": 0.0002808571712355389,
"loss": 0.7503,
"step": 1110
},
{
"epoch": 1.366421568627451,
"grad_norm": 0.09255457708748827,
"learning_rate": 0.0002760609258867784,
"loss": 0.7318,
"step": 1115
},
{
"epoch": 1.3725490196078431,
"grad_norm": 0.09572569889952495,
"learning_rate": 0.00027129032026388045,
"loss": 0.7348,
"step": 1120
},
{
"epoch": 1.3786764705882353,
"grad_norm": 0.0909286336173143,
"learning_rate": 0.00026654590057353467,
"loss": 0.7403,
"step": 1125
},
{
"epoch": 1.3848039215686274,
"grad_norm": 0.08684037452287134,
"learning_rate": 0.00026182821002429345,
"loss": 0.7492,
"step": 1130
},
{
"epoch": 1.3909313725490196,
"grad_norm": 0.09039702206887036,
"learning_rate": 0.00025713778876437744,
"loss": 0.7271,
"step": 1135
},
{
"epoch": 1.3970588235294117,
"grad_norm": 0.10259305111827258,
"learning_rate": 0.00025247517381983136,
"loss": 0.7334,
"step": 1140
},
{
"epoch": 1.403186274509804,
"grad_norm": 0.09305514839850722,
"learning_rate": 0.00024784089903303854,
"loss": 0.7342,
"step": 1145
},
{
"epoch": 1.409313725490196,
"grad_norm": 0.09362025462459474,
"learning_rate": 0.00024323549500159802,
"loss": 0.7287,
"step": 1150
},
{
"epoch": 1.4154411764705883,
"grad_norm": 0.09297020814808991,
"learning_rate": 0.0002386594890175749,
"loss": 0.7424,
"step": 1155
},
{
"epoch": 1.4215686274509804,
"grad_norm": 0.08353530769016755,
"learning_rate": 0.0002341134050071283,
"loss": 0.7485,
"step": 1160
},
{
"epoch": 1.4276960784313726,
"grad_norm": 0.08590929777722105,
"learning_rate": 0.00022959776347052509,
"loss": 0.7347,
"step": 1165
},
{
"epoch": 1.4338235294117647,
"grad_norm": 0.09926401747517187,
"learning_rate": 0.00022511308142254488,
"loss": 0.7529,
"step": 1170
},
{
"epoch": 1.4399509803921569,
"grad_norm": 0.08954546869195683,
"learning_rate": 0.00022065987233328528,
"loss": 0.741,
"step": 1175
},
{
"epoch": 1.446078431372549,
"grad_norm": 0.08807524417797259,
"learning_rate": 0.000216238646069373,
"loss": 0.7409,
"step": 1180
},
{
"epoch": 1.4522058823529411,
"grad_norm": 0.09243225975101937,
"learning_rate": 0.00021184990883558658,
"loss": 0.7358,
"step": 1185
},
{
"epoch": 1.4583333333333333,
"grad_norm": 0.09464124110688574,
"learning_rate": 0.00020749416311689845,
"loss": 0.7346,
"step": 1190
},
{
"epoch": 1.4644607843137254,
"grad_norm": 0.09316779183905147,
"learning_rate": 0.0002031719076209445,
"loss": 0.7313,
"step": 1195
},
{
"epoch": 1.4705882352941178,
"grad_norm": 0.09732126328149814,
"learning_rate": 0.00019888363722092372,
"loss": 0.7341,
"step": 1200
},
{
"epoch": 1.4767156862745099,
"grad_norm": 0.08886419656539418,
"learning_rate": 0.0001946298428989386,
"loss": 0.7375,
"step": 1205
},
{
"epoch": 1.482843137254902,
"grad_norm": 0.07850103787876181,
"learning_rate": 0.00019041101168978093,
"loss": 0.7287,
"step": 1210
},
{
"epoch": 1.4889705882352942,
"grad_norm": 0.08830903517712305,
"learning_rate": 0.00018622762662516868,
"loss": 0.735,
"step": 1215
},
{
"epoch": 1.4950980392156863,
"grad_norm": 0.08702420978835,
"learning_rate": 0.00018208016667844152,
"loss": 0.7393,
"step": 1220
},
{
"epoch": 1.5012254901960784,
"grad_norm": 0.08438557069126026,
"learning_rate": 0.00017796910670972132,
"loss": 0.7423,
"step": 1225
},
{
"epoch": 1.5073529411764706,
"grad_norm": 0.0874124625381899,
"learning_rate": 0.00017389491741154372,
"loss": 0.7417,
"step": 1230
},
{
"epoch": 1.5134803921568627,
"grad_norm": 0.08983974571361636,
"learning_rate": 0.0001698580652549665,
"loss": 0.7284,
"step": 1235
},
{
"epoch": 1.5196078431372548,
"grad_norm": 0.09655404504961941,
"learning_rate": 0.00016585901243616042,
"loss": 0.732,
"step": 1240
},
{
"epoch": 1.5257352941176472,
"grad_norm": 0.08637672179778699,
"learning_rate": 0.00016189821682349205,
"loss": 0.7293,
"step": 1245
},
{
"epoch": 1.531862745098039,
"grad_norm": 0.08546099516549688,
"learning_rate": 0.0001579761319050991,
"loss": 0.7356,
"step": 1250
},
{
"epoch": 1.5379901960784315,
"grad_norm": 0.07907834707353141,
"learning_rate": 0.00015409320673696902,
"loss": 0.731,
"step": 1255
},
{
"epoch": 1.5441176470588234,
"grad_norm": 0.08633766548134404,
"learning_rate": 0.00015024988589152537,
"loss": 0.7254,
"step": 1260
},
{
"epoch": 1.5502450980392157,
"grad_norm": 0.09255543384492604,
"learning_rate": 0.00014644660940672628,
"loss": 0.7352,
"step": 1265
},
{
"epoch": 1.5563725490196079,
"grad_norm": 0.07948954260097911,
"learning_rate": 0.0001426838127356823,
"loss": 0.7281,
"step": 1270
},
{
"epoch": 1.5625,
"grad_norm": 0.0858902101428744,
"learning_rate": 0.0001389619266968002,
"loss": 0.7404,
"step": 1275
},
{
"epoch": 1.5686274509803921,
"grad_norm": 0.08099715928187635,
"learning_rate": 0.0001352813774244565,
"loss": 0.729,
"step": 1280
},
{
"epoch": 1.5747549019607843,
"grad_norm": 0.08675937769241077,
"learning_rate": 0.0001316425863202078,
"loss": 0.7289,
"step": 1285
},
{
"epoch": 1.5808823529411766,
"grad_norm": 0.08712801365461889,
"learning_rate": 0.00012804597000454215,
"loss": 0.7368,
"step": 1290
},
{
"epoch": 1.5870098039215685,
"grad_norm": 0.09259317971708025,
"learning_rate": 0.00012449194026917883,
"loss": 0.7254,
"step": 1295
},
{
"epoch": 1.593137254901961,
"grad_norm": 0.0821781596676491,
"learning_rate": 0.00012098090402992085,
"loss": 0.7307,
"step": 1300
},
{
"epoch": 1.5992647058823528,
"grad_norm": 0.08514490094990651,
"learning_rate": 0.00011751326328006473,
"loss": 0.7226,
"step": 1305
},
{
"epoch": 1.6053921568627452,
"grad_norm": 0.08798702323560283,
"learning_rate": 0.00011408941504437532,
"loss": 0.7274,
"step": 1310
},
{
"epoch": 1.6115196078431373,
"grad_norm": 0.08477334907464082,
"learning_rate": 0.00011070975133362842,
"loss": 0.7351,
"step": 1315
},
{
"epoch": 1.6176470588235294,
"grad_norm": 0.08440769123912943,
"learning_rate": 0.00010737465909972776,
"loss": 0.7322,
"step": 1320
},
{
"epoch": 1.6237745098039216,
"grad_norm": 0.08816338400851521,
"learning_rate": 0.00010408452019140119,
"loss": 0.7257,
"step": 1325
},
{
"epoch": 1.6299019607843137,
"grad_norm": 0.0889764540813042,
"learning_rate": 0.00010083971131048159,
"loss": 0.7285,
"step": 1330
},
{
"epoch": 1.6360294117647058,
"grad_norm": 0.08514875374173311,
"learning_rate": 9.764060396877661e-05,
"loss": 0.7323,
"step": 1335
},
{
"epoch": 1.642156862745098,
"grad_norm": 0.08728092386538332,
"learning_rate": 9.448756444553224e-05,
"loss": 0.7256,
"step": 1340
},
{
"epoch": 1.6482843137254903,
"grad_norm": 0.08430901480786084,
"learning_rate": 9.138095374549633e-05,
"loss": 0.7278,
"step": 1345
},
{
"epoch": 1.6544117647058822,
"grad_norm": 0.08407206279064601,
"learning_rate": 8.832112755758598e-05,
"loss": 0.7232,
"step": 1350
},
{
"epoch": 1.6605392156862746,
"grad_norm": 0.09172008766801877,
"learning_rate": 8.530843621416234e-05,
"loss": 0.7262,
"step": 1355
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.088740049378598,
"learning_rate": 8.234322465092047e-05,
"loss": 0.7294,
"step": 1360
},
{
"epoch": 1.6727941176470589,
"grad_norm": 0.08733287037829676,
"learning_rate": 7.942583236739581e-05,
"loss": 0.7326,
"step": 1365
},
{
"epoch": 1.678921568627451,
"grad_norm": 0.08946029254025908,
"learning_rate": 7.655659338809329e-05,
"loss": 0.7302,
"step": 1370
},
{
"epoch": 1.6850490196078431,
"grad_norm": 0.08125225656437084,
"learning_rate": 7.373583622424358e-05,
"loss": 0.7243,
"step": 1375
},
{
"epoch": 1.6911764705882353,
"grad_norm": 0.08262402915263288,
"learning_rate": 7.096388383619079e-05,
"loss": 0.722,
"step": 1380
},
{
"epoch": 1.6973039215686274,
"grad_norm": 0.0983748828611407,
"learning_rate": 6.824105359641513e-05,
"loss": 0.7224,
"step": 1385
},
{
"epoch": 1.7034313725490198,
"grad_norm": 0.09511486159825465,
"learning_rate": 6.556765725319525e-05,
"loss": 0.7353,
"step": 1390
},
{
"epoch": 1.7095588235294117,
"grad_norm": 0.08406547135240365,
"learning_rate": 6.294400089491526e-05,
"loss": 0.7249,
"step": 1395
},
{
"epoch": 1.715686274509804,
"grad_norm": 0.09349436979698456,
"learning_rate": 6.037038491501978e-05,
"loss": 0.7199,
"step": 1400
},
{
"epoch": 1.721813725490196,
"grad_norm": 0.0859858185739073,
"learning_rate": 5.7847103977619555e-05,
"loss": 0.7231,
"step": 1405
},
{
"epoch": 1.7279411764705883,
"grad_norm": 0.08083261397597263,
"learning_rate": 5.53744469837551e-05,
"loss": 0.7331,
"step": 1410
},
{
"epoch": 1.7340686274509802,
"grad_norm": 0.08197105924202848,
"learning_rate": 5.295269703831901e-05,
"loss": 0.725,
"step": 1415
},
{
"epoch": 1.7401960784313726,
"grad_norm": 0.07809550724924257,
"learning_rate": 5.058213141764151e-05,
"loss": 0.718,
"step": 1420
},
{
"epoch": 1.7463235294117647,
"grad_norm": 0.08030689228502133,
"learning_rate": 4.826302153774448e-05,
"loss": 0.7171,
"step": 1425
},
{
"epoch": 1.7524509803921569,
"grad_norm": 0.08468169044962492,
"learning_rate": 4.599563292326592e-05,
"loss": 0.7267,
"step": 1430
},
{
"epoch": 1.758578431372549,
"grad_norm": 0.0820979728898519,
"learning_rate": 4.3780225177058766e-05,
"loss": 0.7166,
"step": 1435
},
{
"epoch": 1.7647058823529411,
"grad_norm": 0.07927753918146413,
"learning_rate": 4.161705195046761e-05,
"loss": 0.718,
"step": 1440
},
{
"epoch": 1.7708333333333335,
"grad_norm": 0.0840926492467221,
"learning_rate": 3.9506360914287386e-05,
"loss": 0.728,
"step": 1445
},
{
"epoch": 1.7769607843137254,
"grad_norm": 0.08436514170292973,
"learning_rate": 3.744839373040682e-05,
"loss": 0.7214,
"step": 1450
},
{
"epoch": 1.7830882352941178,
"grad_norm": 0.08999651739438058,
"learning_rate": 3.5443386024138605e-05,
"loss": 0.7296,
"step": 1455
},
{
"epoch": 1.7892156862745097,
"grad_norm": 0.08092101714415846,
"learning_rate": 3.349156735724274e-05,
"loss": 0.7196,
"step": 1460
},
{
"epoch": 1.795343137254902,
"grad_norm": 0.08061728201126263,
"learning_rate": 3.1593161201642354e-05,
"loss": 0.7284,
"step": 1465
},
{
"epoch": 1.8014705882352942,
"grad_norm": 0.07834911210493091,
"learning_rate": 2.9748384913837522e-05,
"loss": 0.7325,
"step": 1470
},
{
"epoch": 1.8075980392156863,
"grad_norm": 0.0790057426287298,
"learning_rate": 2.7957449710019512e-05,
"loss": 0.7286,
"step": 1475
},
{
"epoch": 1.8137254901960784,
"grad_norm": 0.07695722244990424,
"learning_rate": 2.622056064188738e-05,
"loss": 0.7276,
"step": 1480
},
{
"epoch": 1.8198529411764706,
"grad_norm": 0.09150941908302032,
"learning_rate": 2.4537916573171337e-05,
"loss": 0.7239,
"step": 1485
},
{
"epoch": 1.8259803921568627,
"grad_norm": 0.09154350521364844,
"learning_rate": 2.2909710156863274e-05,
"loss": 0.7312,
"step": 1490
},
{
"epoch": 1.8321078431372548,
"grad_norm": 0.08002699190491802,
"learning_rate": 2.1336127813159355e-05,
"loss": 0.7254,
"step": 1495
},
{
"epoch": 1.8382352941176472,
"grad_norm": 0.08021887418189992,
"learning_rate": 1.981734970811644e-05,
"loss": 0.7222,
"step": 1500
},
{
"epoch": 1.844362745098039,
"grad_norm": 0.08930992030073814,
"learning_rate": 1.8353549733023333e-05,
"loss": 0.7383,
"step": 1505
},
{
"epoch": 1.8504901960784315,
"grad_norm": 0.08303320455844895,
"learning_rate": 1.6944895484492072e-05,
"loss": 0.7133,
"step": 1510
},
{
"epoch": 1.8566176470588234,
"grad_norm": 0.08729988838797742,
"learning_rate": 1.5591548245268428e-05,
"loss": 0.7315,
"step": 1515
},
{
"epoch": 1.8627450980392157,
"grad_norm": 0.08890946616187734,
"learning_rate": 1.429366296576623e-05,
"loss": 0.7197,
"step": 1520
},
{
"epoch": 1.8688725490196079,
"grad_norm": 0.08151959163399713,
"learning_rate": 1.30513882463264e-05,
"loss": 0.7263,
"step": 1525
},
{
"epoch": 1.875,
"grad_norm": 0.09562764992899297,
"learning_rate": 1.1864866320203115e-05,
"loss": 0.7188,
"step": 1530
},
{
"epoch": 1.8811274509803921,
"grad_norm": 0.07846982174735893,
"learning_rate": 1.073423303727894e-05,
"loss": 0.7237,
"step": 1535
},
{
"epoch": 1.8872549019607843,
"grad_norm": 0.07663001458145507,
"learning_rate": 9.659617848510882e-06,
"loss": 0.7252,
"step": 1540
},
{
"epoch": 1.8933823529411766,
"grad_norm": 0.08080118998190498,
"learning_rate": 8.64114379110853e-06,
"loss": 0.7112,
"step": 1545
},
{
"epoch": 1.8995098039215685,
"grad_norm": 0.08484892902062172,
"learning_rate": 7.678927474447817e-06,
"loss": 0.7264,
"step": 1550
},
{
"epoch": 1.905637254901961,
"grad_norm": 0.08516868212628753,
"learning_rate": 6.77307906671909e-06,
"loss": 0.7271,
"step": 1555
},
{
"epoch": 1.9117647058823528,
"grad_norm": 0.08133640776409674,
"learning_rate": 5.923702282314092e-06,
"loss": 0.7324,
"step": 1560
},
{
"epoch": 1.9178921568627452,
"grad_norm": 0.08097758322239303,
"learning_rate": 5.130894369951011e-06,
"loss": 0.7273,
"step": 1565
},
{
"epoch": 1.9240196078431373,
"grad_norm": 0.08298253969927805,
"learning_rate": 4.394746101540115e-06,
"loss": 0.7298,
"step": 1570
},
{
"epoch": 1.9301470588235294,
"grad_norm": 0.0776674873026092,
"learning_rate": 3.7153417617907802e-06,
"loss": 0.7199,
"step": 1575
},
{
"epoch": 1.9362745098039216,
"grad_norm": 0.08136684261699478,
"learning_rate": 3.092759138561607e-06,
"loss": 0.727,
"step": 1580
},
{
"epoch": 1.9424019607843137,
"grad_norm": 0.21064147236672387,
"learning_rate": 2.5270695139539833e-06,
"loss": 0.7305,
"step": 1585
},
{
"epoch": 1.9485294117647058,
"grad_norm": 0.07856752844029326,
"learning_rate": 2.018337656150726e-06,
"loss": 0.7259,
"step": 1590
},
{
"epoch": 1.954656862745098,
"grad_norm": 0.07818237444191369,
"learning_rate": 1.5666218120005682e-06,
"loss": 0.724,
"step": 1595
},
{
"epoch": 1.9607843137254903,
"grad_norm": 0.07498630792024302,
"learning_rate": 1.1719737003492159e-06,
"loss": 0.7205,
"step": 1600
},
{
"epoch": 1.9669117647058822,
"grad_norm": 0.07974040781241311,
"learning_rate": 8.344385061176962e-07,
"loss": 0.7228,
"step": 1605
},
{
"epoch": 1.9730392156862746,
"grad_norm": 0.08674324039372262,
"learning_rate": 5.540548751292173e-07,
"loss": 0.7364,
"step": 1610
},
{
"epoch": 1.9791666666666665,
"grad_norm": 0.08126471002081247,
"learning_rate": 3.3085490968409737e-07,
"loss": 0.7232,
"step": 1615
},
{
"epoch": 1.9852941176470589,
"grad_norm": 0.08409713343077478,
"learning_rate": 1.6486416488459277e-07,
"loss": 0.7251,
"step": 1620
},
{
"epoch": 1.991421568627451,
"grad_norm": 0.08609959331430181,
"learning_rate": 5.6101645708850346e-08,
"loss": 0.7326,
"step": 1625
},
{
"epoch": 1.9975490196078431,
"grad_norm": 0.0748443586344328,
"learning_rate": 4.579804834703438e-09,
"loss": 0.7238,
"step": 1630
},
{
"epoch": 2.0,
"eval_loss": 1.1972506046295166,
"eval_runtime": 112.8302,
"eval_samples_per_second": 185.598,
"eval_steps_per_second": 5.805,
"step": 1632
},
{
"epoch": 2.0,
"step": 1632,
"total_flos": 160150899916800.0,
"train_loss": 0.8347952699690473,
"train_runtime": 3713.7533,
"train_samples_per_second": 56.241,
"train_steps_per_second": 0.439
}
],
"logging_steps": 5,
"max_steps": 1632,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 160150899916800.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}