LegrandFrederic's picture
Upload trainer_state.json with huggingface_hub
38dafbd verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 1210,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08264462809917356,
"grad_norm": 2.061657190322876,
"learning_rate": 3.2786885245901635e-05,
"loss": 0.8384,
"step": 10
},
{
"epoch": 0.1652892561983471,
"grad_norm": 1.1209560632705688,
"learning_rate": 6.557377049180327e-05,
"loss": 0.3975,
"step": 20
},
{
"epoch": 0.24793388429752067,
"grad_norm": 1.1699508428573608,
"learning_rate": 9.836065573770493e-05,
"loss": 0.216,
"step": 30
},
{
"epoch": 0.3305785123966942,
"grad_norm": 0.6142070889472961,
"learning_rate": 0.00013114754098360654,
"loss": 0.1394,
"step": 40
},
{
"epoch": 0.4132231404958678,
"grad_norm": 1.4109835624694824,
"learning_rate": 0.0001639344262295082,
"loss": 0.1186,
"step": 50
},
{
"epoch": 0.49586776859504134,
"grad_norm": 0.6400930881500244,
"learning_rate": 0.00019672131147540985,
"loss": 0.1159,
"step": 60
},
{
"epoch": 0.5785123966942148,
"grad_norm": 0.6176881790161133,
"learning_rate": 0.00019996972439741538,
"loss": 0.1029,
"step": 70
},
{
"epoch": 0.6611570247933884,
"grad_norm": 0.7654891610145569,
"learning_rate": 0.00019986509152903302,
"loss": 0.0998,
"step": 80
},
{
"epoch": 0.743801652892562,
"grad_norm": 0.8429086804389954,
"learning_rate": 0.0001996858058202821,
"loss": 0.0898,
"step": 90
},
{
"epoch": 0.8264462809917356,
"grad_norm": 1.0951145887374878,
"learning_rate": 0.00019943200129384444,
"loss": 0.0762,
"step": 100
},
{
"epoch": 0.9090909090909091,
"grad_norm": 0.7709806561470032,
"learning_rate": 0.00019910386767796751,
"loss": 0.0828,
"step": 110
},
{
"epoch": 0.9917355371900827,
"grad_norm": 0.7118253707885742,
"learning_rate": 0.0001987016502646355,
"loss": 0.0742,
"step": 120
},
{
"epoch": 1.0743801652892562,
"grad_norm": 0.37856435775756836,
"learning_rate": 0.00019822564972620427,
"loss": 0.0638,
"step": 130
},
{
"epoch": 1.1570247933884297,
"grad_norm": 0.49986979365348816,
"learning_rate": 0.00019767622189063812,
"loss": 0.0623,
"step": 140
},
{
"epoch": 1.2396694214876034,
"grad_norm": 0.6002529859542847,
"learning_rate": 0.0001970537774755148,
"loss": 0.0636,
"step": 150
},
{
"epoch": 1.322314049586777,
"grad_norm": 0.8187810778617859,
"learning_rate": 0.00019635878178099928,
"loss": 0.0646,
"step": 160
},
{
"epoch": 1.4049586776859504,
"grad_norm": 0.5900979042053223,
"learning_rate": 0.00019559175434201458,
"loss": 0.0539,
"step": 170
},
{
"epoch": 1.487603305785124,
"grad_norm": 0.39900392293930054,
"learning_rate": 0.00019475326853987026,
"loss": 0.051,
"step": 180
},
{
"epoch": 1.5702479338842976,
"grad_norm": 0.4218977689743042,
"learning_rate": 0.0001938439511736388,
"loss": 0.0523,
"step": 190
},
{
"epoch": 1.6528925619834711,
"grad_norm": 0.3695419132709503,
"learning_rate": 0.00019286448199159995,
"loss": 0.0484,
"step": 200
},
{
"epoch": 1.7355371900826446,
"grad_norm": 0.5481135845184326,
"learning_rate": 0.0001918155931831042,
"loss": 0.0491,
"step": 210
},
{
"epoch": 1.8181818181818183,
"grad_norm": 0.6999943256378174,
"learning_rate": 0.00019069806883123387,
"loss": 0.0502,
"step": 220
},
{
"epoch": 1.9008264462809916,
"grad_norm": 0.46525853872299194,
"learning_rate": 0.0001895127443266722,
"loss": 0.0496,
"step": 230
},
{
"epoch": 1.9834710743801653,
"grad_norm": 0.35091671347618103,
"learning_rate": 0.0001882605057432181,
"loss": 0.0486,
"step": 240
},
{
"epoch": 2.0661157024793386,
"grad_norm": 0.30202504992485046,
"learning_rate": 0.00018694228917541313,
"loss": 0.0439,
"step": 250
},
{
"epoch": 2.1487603305785123,
"grad_norm": 0.3925149738788605,
"learning_rate": 0.00018555908003877635,
"loss": 0.0407,
"step": 260
},
{
"epoch": 2.231404958677686,
"grad_norm": 0.5707463026046753,
"learning_rate": 0.0001841119123331699,
"loss": 0.0415,
"step": 270
},
{
"epoch": 2.3140495867768593,
"grad_norm": 0.31396156549453735,
"learning_rate": 0.000182601867869846,
"loss": 0.0382,
"step": 280
},
{
"epoch": 2.396694214876033,
"grad_norm": 0.4403229355812073,
"learning_rate": 0.00018103007546275293,
"loss": 0.0408,
"step": 290
},
{
"epoch": 2.479338842975207,
"grad_norm": 0.5294861197471619,
"learning_rate": 0.00017939771008470512,
"loss": 0.043,
"step": 300
},
{
"epoch": 2.56198347107438,
"grad_norm": 0.4009588956832886,
"learning_rate": 0.00017770599198904763,
"loss": 0.0472,
"step": 310
},
{
"epoch": 2.644628099173554,
"grad_norm": 0.5458269119262695,
"learning_rate": 0.00017595618579747173,
"loss": 0.0376,
"step": 320
},
{
"epoch": 2.7272727272727275,
"grad_norm": 0.270888090133667,
"learning_rate": 0.0001741495995546634,
"loss": 0.0354,
"step": 330
},
{
"epoch": 2.809917355371901,
"grad_norm": 0.3030223548412323,
"learning_rate": 0.00017228758375049185,
"loss": 0.0427,
"step": 340
},
{
"epoch": 2.8925619834710745,
"grad_norm": 0.31921663880348206,
"learning_rate": 0.00017037153031046847,
"loss": 0.0415,
"step": 350
},
{
"epoch": 2.975206611570248,
"grad_norm": 0.2452174574136734,
"learning_rate": 0.000168402871555231,
"loss": 0.0418,
"step": 360
},
{
"epoch": 3.0578512396694215,
"grad_norm": 0.25872424244880676,
"learning_rate": 0.00016638307912983136,
"loss": 0.0371,
"step": 370
},
{
"epoch": 3.1404958677685952,
"grad_norm": 0.2113211750984192,
"learning_rate": 0.00016431366290362625,
"loss": 0.0311,
"step": 380
},
{
"epoch": 3.2231404958677685,
"grad_norm": 0.34439799189567566,
"learning_rate": 0.00016219616984159435,
"loss": 0.0348,
"step": 390
},
{
"epoch": 3.3057851239669422,
"grad_norm": 0.22683021426200867,
"learning_rate": 0.00016003218284792298,
"loss": 0.0335,
"step": 400
},
{
"epoch": 3.3884297520661155,
"grad_norm": 0.3409021496772766,
"learning_rate": 0.00015782331958272858,
"loss": 0.037,
"step": 410
},
{
"epoch": 3.4710743801652892,
"grad_norm": 0.27717071771621704,
"learning_rate": 0.00015557123125279636,
"loss": 0.0328,
"step": 420
},
{
"epoch": 3.553719008264463,
"grad_norm": 0.37764936685562134,
"learning_rate": 0.00015327760137724212,
"loss": 0.0354,
"step": 430
},
{
"epoch": 3.6363636363636362,
"grad_norm": 0.4590853452682495,
"learning_rate": 0.00015094414452901958,
"loss": 0.0351,
"step": 440
},
{
"epoch": 3.71900826446281,
"grad_norm": 0.3909158408641815,
"learning_rate": 0.00014857260505321407,
"loss": 0.0377,
"step": 450
},
{
"epoch": 3.8016528925619832,
"grad_norm": 0.3208233714103699,
"learning_rate": 0.00014616475576308005,
"loss": 0.0302,
"step": 460
},
{
"epoch": 3.884297520661157,
"grad_norm": 0.4053466022014618,
"learning_rate": 0.00014372239661479766,
"loss": 0.0318,
"step": 470
},
{
"epoch": 3.9669421487603307,
"grad_norm": 0.26150038838386536,
"learning_rate": 0.00014124735336193934,
"loss": 0.0339,
"step": 480
},
{
"epoch": 4.049586776859504,
"grad_norm": 0.29400137066841125,
"learning_rate": 0.0001387414761906516,
"loss": 0.0286,
"step": 490
},
{
"epoch": 4.132231404958677,
"grad_norm": 0.24488015472888947,
"learning_rate": 0.00013620663833657245,
"loss": 0.0296,
"step": 500
},
{
"epoch": 4.214876033057851,
"grad_norm": 0.23769892752170563,
"learning_rate": 0.00013364473468451888,
"loss": 0.0288,
"step": 510
},
{
"epoch": 4.297520661157025,
"grad_norm": 0.4920603334903717,
"learning_rate": 0.00013105768035199034,
"loss": 0.0329,
"step": 520
},
{
"epoch": 4.380165289256198,
"grad_norm": 0.3728867173194885,
"learning_rate": 0.00012844740925754792,
"loss": 0.0285,
"step": 530
},
{
"epoch": 4.462809917355372,
"grad_norm": 0.21319624781608582,
"learning_rate": 0.0001258158726751388,
"loss": 0.0298,
"step": 540
},
{
"epoch": 4.545454545454545,
"grad_norm": 0.255109965801239,
"learning_rate": 0.000123165037775447,
"loss": 0.0266,
"step": 550
},
{
"epoch": 4.628099173553719,
"grad_norm": 0.3256368339061737,
"learning_rate": 0.00012049688615536063,
"loss": 0.0314,
"step": 560
},
{
"epoch": 4.710743801652892,
"grad_norm": 0.2564131021499634,
"learning_rate": 0.00011781341235665528,
"loss": 0.0358,
"step": 570
},
{
"epoch": 4.793388429752066,
"grad_norm": 0.29052674770355225,
"learning_rate": 0.00011511662237500032,
"loss": 0.0281,
"step": 580
},
{
"epoch": 4.87603305785124,
"grad_norm": 0.2417948693037033,
"learning_rate": 0.00011240853216040312,
"loss": 0.0302,
"step": 590
},
{
"epoch": 4.958677685950414,
"grad_norm": 0.3323270082473755,
"learning_rate": 0.00010969116611021218,
"loss": 0.0294,
"step": 600
},
{
"epoch": 5.041322314049586,
"grad_norm": 0.28201115131378174,
"learning_rate": 0.00010696655555580524,
"loss": 0.0272,
"step": 610
},
{
"epoch": 5.12396694214876,
"grad_norm": 0.4427995979785919,
"learning_rate": 0.0001042367372440943,
"loss": 0.0259,
"step": 620
},
{
"epoch": 5.206611570247934,
"grad_norm": 0.2434374839067459,
"learning_rate": 0.00010150375181498202,
"loss": 0.0292,
"step": 630
},
{
"epoch": 5.289256198347108,
"grad_norm": 0.2886279821395874,
"learning_rate": 9.87696422759082e-05,
"loss": 0.03,
"step": 640
},
{
"epoch": 5.371900826446281,
"grad_norm": 0.2933793067932129,
"learning_rate": 9.603645247462633e-05,
"loss": 0.0316,
"step": 650
},
{
"epoch": 5.454545454545454,
"grad_norm": 0.363825261592865,
"learning_rate": 9.330622557135186e-05,
"loss": 0.0241,
"step": 660
},
{
"epoch": 5.537190082644628,
"grad_norm": 0.29603031277656555,
"learning_rate": 9.058100251142483e-05,
"loss": 0.0265,
"step": 670
},
{
"epoch": 5.619834710743802,
"grad_norm": 0.29677891731262207,
"learning_rate": 8.786282049962761e-05,
"loss": 0.0228,
"step": 680
},
{
"epoch": 5.702479338842975,
"grad_norm": 0.296303391456604,
"learning_rate": 8.515371147729943e-05,
"loss": 0.0215,
"step": 690
},
{
"epoch": 5.785123966942149,
"grad_norm": 0.29517602920532227,
"learning_rate": 8.245570060338512e-05,
"loss": 0.0235,
"step": 700
},
{
"epoch": 5.867768595041323,
"grad_norm": 0.24108897149562836,
"learning_rate": 7.977080474055404e-05,
"loss": 0.0256,
"step": 710
},
{
"epoch": 5.950413223140496,
"grad_norm": 0.23352974653244019,
"learning_rate": 7.710103094752103e-05,
"loss": 0.0276,
"step": 720
},
{
"epoch": 6.033057851239669,
"grad_norm": 0.21120014786720276,
"learning_rate": 7.44483749786957e-05,
"loss": 0.0254,
"step": 730
},
{
"epoch": 6.115702479338843,
"grad_norm": 0.2598652243614197,
"learning_rate": 7.181481979228262e-05,
"loss": 0.0264,
"step": 740
},
{
"epoch": 6.198347107438017,
"grad_norm": 0.21868811547756195,
"learning_rate": 6.920233406794672e-05,
"loss": 0.0217,
"step": 750
},
{
"epoch": 6.2809917355371905,
"grad_norm": 0.2242676317691803,
"learning_rate": 6.661287073515275e-05,
"loss": 0.0246,
"step": 760
},
{
"epoch": 6.363636363636363,
"grad_norm": 0.19823093712329865,
"learning_rate": 6.404836551327837e-05,
"loss": 0.0223,
"step": 770
},
{
"epoch": 6.446280991735537,
"grad_norm": 0.16410717368125916,
"learning_rate": 6.151073546459248e-05,
"loss": 0.0257,
"step": 780
},
{
"epoch": 6.528925619834711,
"grad_norm": 0.17154166102409363,
"learning_rate": 5.900187756118055e-05,
"loss": 0.024,
"step": 790
},
{
"epoch": 6.6115702479338845,
"grad_norm": 0.19076073169708252,
"learning_rate": 5.652366726688782e-05,
"loss": 0.0241,
"step": 800
},
{
"epoch": 6.694214876033058,
"grad_norm": 0.1697314828634262,
"learning_rate": 5.4077957135341115e-05,
"loss": 0.0209,
"step": 810
},
{
"epoch": 6.776859504132231,
"grad_norm": 0.14440375566482544,
"learning_rate": 5.1666575425096396e-05,
"loss": 0.0182,
"step": 820
},
{
"epoch": 6.859504132231405,
"grad_norm": 0.2061329334974289,
"learning_rate": 4.9291324732948376e-05,
"loss": 0.0235,
"step": 830
},
{
"epoch": 6.9421487603305785,
"grad_norm": 0.243088960647583,
"learning_rate": 4.6953980646422535e-05,
"loss": 0.0209,
"step": 840
},
{
"epoch": 7.024793388429752,
"grad_norm": 0.22780433297157288,
"learning_rate": 4.465629041645819e-05,
"loss": 0.0199,
"step": 850
},
{
"epoch": 7.107438016528926,
"grad_norm": 0.23546425998210907,
"learning_rate": 4.239997165127384e-05,
"loss": 0.02,
"step": 860
},
{
"epoch": 7.190082644628099,
"grad_norm": 0.19151107966899872,
"learning_rate": 4.0186711032391776e-05,
"loss": 0.0228,
"step": 870
},
{
"epoch": 7.2727272727272725,
"grad_norm": 0.1883740872144699,
"learning_rate": 3.801816305378124e-05,
"loss": 0.0226,
"step": 880
},
{
"epoch": 7.355371900826446,
"grad_norm": 0.23011337220668793,
"learning_rate": 3.5895948785063225e-05,
"loss": 0.0228,
"step": 890
},
{
"epoch": 7.43801652892562,
"grad_norm": 0.2320934236049652,
"learning_rate": 3.382165465970123e-05,
"loss": 0.0221,
"step": 900
},
{
"epoch": 7.520661157024794,
"grad_norm": 0.12290257960557938,
"learning_rate": 3.179683128908352e-05,
"loss": 0.019,
"step": 910
},
{
"epoch": 7.6033057851239665,
"grad_norm": 0.13940581679344177,
"learning_rate": 2.9822992303384024e-05,
"loss": 0.0173,
"step": 920
},
{
"epoch": 7.68595041322314,
"grad_norm": 0.21917001903057098,
"learning_rate": 2.7901613220067914e-05,
"loss": 0.0196,
"step": 930
},
{
"epoch": 7.768595041322314,
"grad_norm": 0.31197458505630493,
"learning_rate": 2.6034130340887895e-05,
"loss": 0.0186,
"step": 940
},
{
"epoch": 7.851239669421488,
"grad_norm": 0.19257141649723053,
"learning_rate": 2.4221939678195594e-05,
"loss": 0.0194,
"step": 950
},
{
"epoch": 7.933884297520661,
"grad_norm": 0.13493625819683075,
"learning_rate": 2.2466395911370817e-05,
"loss": 0.0204,
"step": 960
},
{
"epoch": 8.016528925619834,
"grad_norm": 0.17625942826271057,
"learning_rate": 2.07688113741488e-05,
"loss": 0.0202,
"step": 970
},
{
"epoch": 8.099173553719009,
"grad_norm": 0.17436304688453674,
"learning_rate": 1.913045507360227e-05,
"loss": 0.0179,
"step": 980
},
{
"epoch": 8.181818181818182,
"grad_norm": 0.16752925515174866,
"learning_rate": 1.7552551741511847e-05,
"loss": 0.0184,
"step": 990
},
{
"epoch": 8.264462809917354,
"grad_norm": 0.20424728095531464,
"learning_rate": 1.6036280918833924e-05,
"loss": 0.0204,
"step": 1000
},
{
"epoch": 8.347107438016529,
"grad_norm": 0.18081198632717133,
"learning_rate": 1.4582776073950143e-05,
"loss": 0.0163,
"step": 1010
},
{
"epoch": 8.429752066115702,
"grad_norm": 0.16358765959739685,
"learning_rate": 1.3193123755358072e-05,
"loss": 0.0229,
"step": 1020
},
{
"epoch": 8.512396694214877,
"grad_norm": 0.27697688341140747,
"learning_rate": 1.186836277943606e-05,
"loss": 0.0189,
"step": 1030
},
{
"epoch": 8.59504132231405,
"grad_norm": 0.15346001088619232,
"learning_rate": 1.0609483453889746e-05,
"loss": 0.0166,
"step": 1040
},
{
"epoch": 8.677685950413224,
"grad_norm": 0.19226881861686707,
"learning_rate": 9.41742683746042e-06,
"loss": 0.0163,
"step": 1050
},
{
"epoch": 8.760330578512397,
"grad_norm": 0.25044411420822144,
"learning_rate": 8.293084036448895e-06,
"loss": 0.0177,
"step": 1060
},
{
"epoch": 8.84297520661157,
"grad_norm": 0.11807776987552643,
"learning_rate": 7.237295538580791e-06,
"loss": 0.0161,
"step": 1070
},
{
"epoch": 8.925619834710744,
"grad_norm": 0.1679440587759018,
"learning_rate": 6.250850584710799e-06,
"loss": 0.0191,
"step": 1080
},
{
"epoch": 9.008264462809917,
"grad_norm": 0.17056939005851746,
"learning_rate": 5.334486578836118e-06,
"loss": 0.0146,
"step": 1090
},
{
"epoch": 9.090909090909092,
"grad_norm": 0.1600365787744522,
"learning_rate": 4.488888536859714e-06,
"loss": 0.0205,
"step": 1100
},
{
"epoch": 9.173553719008265,
"grad_norm": 0.18527384102344513,
"learning_rate": 3.7146885745157233e-06,
"loss": 0.0127,
"step": 1110
},
{
"epoch": 9.256198347107437,
"grad_norm": 0.11880697309970856,
"learning_rate": 3.012465434839529e-06,
"loss": 0.0168,
"step": 1120
},
{
"epoch": 9.338842975206612,
"grad_norm": 0.1584666520357132,
"learning_rate": 2.382744055536068e-06,
"loss": 0.0161,
"step": 1130
},
{
"epoch": 9.421487603305785,
"grad_norm": 0.18531374633312225,
"learning_rate": 1.8259951765694728e-06,
"loss": 0.0177,
"step": 1140
},
{
"epoch": 9.50413223140496,
"grad_norm": 0.17779088020324707,
"learning_rate": 1.3426349882676325e-06,
"loss": 0.0157,
"step": 1150
},
{
"epoch": 9.586776859504132,
"grad_norm": 0.1391703486442566,
"learning_rate": 9.3302482020452e-07,
"loss": 0.0167,
"step": 1160
},
{
"epoch": 9.669421487603305,
"grad_norm": 0.1815948635339737,
"learning_rate": 5.974708710930421e-07,
"loss": 0.0191,
"step": 1170
},
{
"epoch": 9.75206611570248,
"grad_norm": 0.2050154209136963,
"learning_rate": 3.362239798901712e-07,
"loss": 0.0188,
"step": 1180
},
{
"epoch": 9.834710743801653,
"grad_norm": 0.1503370851278305,
"learning_rate": 1.4947943828561574e-07,
"loss": 0.0154,
"step": 1190
},
{
"epoch": 9.917355371900827,
"grad_norm": 0.163643941283226,
"learning_rate": 3.737684471400993e-08,
"loss": 0.0187,
"step": 1200
},
{
"epoch": 10.0,
"grad_norm": 0.12294866144657135,
"learning_rate": 0.0,
"loss": 0.014,
"step": 1210
},
{
"epoch": 10.0,
"step": 1210,
"total_flos": 1.7516975778360288e+17,
"train_loss": 0.045855508757031656,
"train_runtime": 1400.3465,
"train_samples_per_second": 55.179,
"train_steps_per_second": 0.864
}
],
"logging_steps": 10,
"max_steps": 1210,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 10000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.7516975778360288e+17,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}