models / All key words /checkpoint-1749 /trainer_state.json
RishuD7's picture
Training in progress, epoch 2
46b6ac0 verified
raw
history blame
31.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9974293059125965,
"eval_steps": 500,
"global_step": 1749,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01713796058269066,
"grad_norm": 0.4733077883720398,
"learning_rate": 4.971412235563179e-05,
"loss": 2.5254,
"step": 10
},
{
"epoch": 0.03427592116538132,
"grad_norm": 0.44018083810806274,
"learning_rate": 4.9428244711263584e-05,
"loss": 1.8284,
"step": 20
},
{
"epoch": 0.05141388174807198,
"grad_norm": 0.7213996648788452,
"learning_rate": 4.914236706689537e-05,
"loss": 1.2128,
"step": 30
},
{
"epoch": 0.06855184233076264,
"grad_norm": 0.6227633953094482,
"learning_rate": 4.8856489422527165e-05,
"loss": 0.6727,
"step": 40
},
{
"epoch": 0.0856898029134533,
"grad_norm": 0.2804420590400696,
"learning_rate": 4.8570611778158946e-05,
"loss": 0.3089,
"step": 50
},
{
"epoch": 0.10282776349614396,
"grad_norm": 0.10756277292966843,
"learning_rate": 4.828473413379074e-05,
"loss": 0.2448,
"step": 60
},
{
"epoch": 0.11996572407883462,
"grad_norm": 0.11257284879684448,
"learning_rate": 4.799885648942253e-05,
"loss": 0.2268,
"step": 70
},
{
"epoch": 0.13710368466152528,
"grad_norm": 0.09793874621391296,
"learning_rate": 4.771297884505432e-05,
"loss": 0.2328,
"step": 80
},
{
"epoch": 0.15424164524421594,
"grad_norm": 0.10177452117204666,
"learning_rate": 4.742710120068611e-05,
"loss": 0.2183,
"step": 90
},
{
"epoch": 0.1713796058269066,
"grad_norm": 0.09770502895116806,
"learning_rate": 4.7141223556317895e-05,
"loss": 0.1971,
"step": 100
},
{
"epoch": 0.18851756640959727,
"grad_norm": 0.11037880927324295,
"learning_rate": 4.685534591194969e-05,
"loss": 0.1996,
"step": 110
},
{
"epoch": 0.20565552699228792,
"grad_norm": 0.11869871616363525,
"learning_rate": 4.656946826758148e-05,
"loss": 0.2044,
"step": 120
},
{
"epoch": 0.22279348757497858,
"grad_norm": 0.10279687494039536,
"learning_rate": 4.628359062321327e-05,
"loss": 0.1782,
"step": 130
},
{
"epoch": 0.23993144815766923,
"grad_norm": 0.10952438414096832,
"learning_rate": 4.599771297884506e-05,
"loss": 0.1837,
"step": 140
},
{
"epoch": 0.2570694087403599,
"grad_norm": 0.13122445344924927,
"learning_rate": 4.5711835334476845e-05,
"loss": 0.1907,
"step": 150
},
{
"epoch": 0.27420736932305056,
"grad_norm": 0.11156395077705383,
"learning_rate": 4.542595769010863e-05,
"loss": 0.1748,
"step": 160
},
{
"epoch": 0.2913453299057412,
"grad_norm": 0.1657029241323471,
"learning_rate": 4.5140080045740427e-05,
"loss": 0.1704,
"step": 170
},
{
"epoch": 0.30848329048843187,
"grad_norm": 0.11676887422800064,
"learning_rate": 4.4854202401372214e-05,
"loss": 0.16,
"step": 180
},
{
"epoch": 0.32562125107112255,
"grad_norm": 0.17466452717781067,
"learning_rate": 4.4568324757004e-05,
"loss": 0.1705,
"step": 190
},
{
"epoch": 0.3427592116538132,
"grad_norm": 0.1373518407344818,
"learning_rate": 4.4282447112635795e-05,
"loss": 0.1663,
"step": 200
},
{
"epoch": 0.35989717223650386,
"grad_norm": 0.11815926432609558,
"learning_rate": 4.399656946826758e-05,
"loss": 0.1562,
"step": 210
},
{
"epoch": 0.37703513281919454,
"grad_norm": 0.12364204227924347,
"learning_rate": 4.3710691823899376e-05,
"loss": 0.1655,
"step": 220
},
{
"epoch": 0.39417309340188517,
"grad_norm": 0.11595863103866577,
"learning_rate": 4.3424814179531164e-05,
"loss": 0.1621,
"step": 230
},
{
"epoch": 0.41131105398457585,
"grad_norm": 0.11320952326059341,
"learning_rate": 4.313893653516296e-05,
"loss": 0.1523,
"step": 240
},
{
"epoch": 0.4284490145672665,
"grad_norm": 0.12280760705471039,
"learning_rate": 4.285305889079474e-05,
"loss": 0.1711,
"step": 250
},
{
"epoch": 0.44558697514995715,
"grad_norm": 0.12085650116205215,
"learning_rate": 4.256718124642653e-05,
"loss": 0.1548,
"step": 260
},
{
"epoch": 0.46272493573264784,
"grad_norm": 0.1491166651248932,
"learning_rate": 4.228130360205832e-05,
"loss": 0.1631,
"step": 270
},
{
"epoch": 0.47986289631533846,
"grad_norm": 0.16156260669231415,
"learning_rate": 4.199542595769011e-05,
"loss": 0.1624,
"step": 280
},
{
"epoch": 0.49700085689802914,
"grad_norm": 0.12156664580106735,
"learning_rate": 4.17095483133219e-05,
"loss": 0.1383,
"step": 290
},
{
"epoch": 0.5141388174807198,
"grad_norm": 0.11533980071544647,
"learning_rate": 4.142367066895369e-05,
"loss": 0.1539,
"step": 300
},
{
"epoch": 0.5312767780634104,
"grad_norm": 0.1386200189590454,
"learning_rate": 4.113779302458548e-05,
"loss": 0.1525,
"step": 310
},
{
"epoch": 0.5484147386461011,
"grad_norm": 0.16111765801906586,
"learning_rate": 4.085191538021727e-05,
"loss": 0.14,
"step": 320
},
{
"epoch": 0.5655526992287918,
"grad_norm": 0.151380717754364,
"learning_rate": 4.0566037735849064e-05,
"loss": 0.1492,
"step": 330
},
{
"epoch": 0.5826906598114824,
"grad_norm": 0.15228472650051117,
"learning_rate": 4.028016009148085e-05,
"loss": 0.157,
"step": 340
},
{
"epoch": 0.5998286203941731,
"grad_norm": 0.11199972033500671,
"learning_rate": 3.999428244711264e-05,
"loss": 0.1492,
"step": 350
},
{
"epoch": 0.6169665809768637,
"grad_norm": 0.17204181849956512,
"learning_rate": 3.9708404802744425e-05,
"loss": 0.1504,
"step": 360
},
{
"epoch": 0.6341045415595544,
"grad_norm": 0.13271720707416534,
"learning_rate": 3.942252715837621e-05,
"loss": 0.1604,
"step": 370
},
{
"epoch": 0.6512425021422451,
"grad_norm": 0.15998151898384094,
"learning_rate": 3.913664951400801e-05,
"loss": 0.148,
"step": 380
},
{
"epoch": 0.6683804627249358,
"grad_norm": 0.12898313999176025,
"learning_rate": 3.8850771869639794e-05,
"loss": 0.1492,
"step": 390
},
{
"epoch": 0.6855184233076264,
"grad_norm": 0.13998836278915405,
"learning_rate": 3.856489422527159e-05,
"loss": 0.1548,
"step": 400
},
{
"epoch": 0.702656383890317,
"grad_norm": 0.14940115809440613,
"learning_rate": 3.8279016580903375e-05,
"loss": 0.1432,
"step": 410
},
{
"epoch": 0.7197943444730077,
"grad_norm": 0.13358236849308014,
"learning_rate": 3.799313893653517e-05,
"loss": 0.1459,
"step": 420
},
{
"epoch": 0.7369323050556984,
"grad_norm": 0.1597578376531601,
"learning_rate": 3.7707261292166957e-05,
"loss": 0.1351,
"step": 430
},
{
"epoch": 0.7540702656383891,
"grad_norm": 0.12782897055149078,
"learning_rate": 3.7421383647798744e-05,
"loss": 0.1392,
"step": 440
},
{
"epoch": 0.7712082262210797,
"grad_norm": 0.13537828624248505,
"learning_rate": 3.713550600343053e-05,
"loss": 0.1402,
"step": 450
},
{
"epoch": 0.7883461868037703,
"grad_norm": 0.17046277225017548,
"learning_rate": 3.684962835906232e-05,
"loss": 0.1227,
"step": 460
},
{
"epoch": 0.805484147386461,
"grad_norm": 0.16829894483089447,
"learning_rate": 3.656375071469411e-05,
"loss": 0.133,
"step": 470
},
{
"epoch": 0.8226221079691517,
"grad_norm": 0.17760640382766724,
"learning_rate": 3.62778730703259e-05,
"loss": 0.1361,
"step": 480
},
{
"epoch": 0.8397600685518424,
"grad_norm": 0.1783646047115326,
"learning_rate": 3.5991995425957694e-05,
"loss": 0.1272,
"step": 490
},
{
"epoch": 0.856898029134533,
"grad_norm": 0.1848060041666031,
"learning_rate": 3.570611778158948e-05,
"loss": 0.1281,
"step": 500
},
{
"epoch": 0.8740359897172236,
"grad_norm": 0.1244303435087204,
"learning_rate": 3.5420240137221275e-05,
"loss": 0.1276,
"step": 510
},
{
"epoch": 0.8911739502999143,
"grad_norm": 0.1454310566186905,
"learning_rate": 3.513436249285306e-05,
"loss": 0.1334,
"step": 520
},
{
"epoch": 0.908311910882605,
"grad_norm": 0.17194361984729767,
"learning_rate": 3.484848484848485e-05,
"loss": 0.1271,
"step": 530
},
{
"epoch": 0.9254498714652957,
"grad_norm": 0.15851227939128876,
"learning_rate": 3.456260720411664e-05,
"loss": 0.1304,
"step": 540
},
{
"epoch": 0.9425878320479862,
"grad_norm": 0.1614447981119156,
"learning_rate": 3.4276729559748424e-05,
"loss": 0.1256,
"step": 550
},
{
"epoch": 0.9597257926306769,
"grad_norm": 0.19016973674297333,
"learning_rate": 3.399085191538022e-05,
"loss": 0.1329,
"step": 560
},
{
"epoch": 0.9768637532133676,
"grad_norm": 0.15122413635253906,
"learning_rate": 3.3704974271012005e-05,
"loss": 0.1228,
"step": 570
},
{
"epoch": 0.9940017137960583,
"grad_norm": 0.15631020069122314,
"learning_rate": 3.34190966266438e-05,
"loss": 0.1235,
"step": 580
},
{
"epoch": 0.9991431019708654,
"eval_loss": 0.15606513619422913,
"eval_runtime": 439.0741,
"eval_samples_per_second": 10.932,
"eval_steps_per_second": 1.367,
"step": 583
},
{
"epoch": 1.0111396743787489,
"grad_norm": 0.20745624601840973,
"learning_rate": 3.313321898227559e-05,
"loss": 0.1245,
"step": 590
},
{
"epoch": 1.0282776349614395,
"grad_norm": 0.182315856218338,
"learning_rate": 3.284734133790738e-05,
"loss": 0.1112,
"step": 600
},
{
"epoch": 1.0454155955441302,
"grad_norm": 0.1425042450428009,
"learning_rate": 3.256146369353917e-05,
"loss": 0.1186,
"step": 610
},
{
"epoch": 1.062553556126821,
"grad_norm": 0.1898319274187088,
"learning_rate": 3.2275586049170955e-05,
"loss": 0.1203,
"step": 620
},
{
"epoch": 1.0796915167095116,
"grad_norm": 0.17110544443130493,
"learning_rate": 3.198970840480275e-05,
"loss": 0.1223,
"step": 630
},
{
"epoch": 1.0968294772922023,
"grad_norm": 0.17418451607227325,
"learning_rate": 3.170383076043453e-05,
"loss": 0.111,
"step": 640
},
{
"epoch": 1.113967437874893,
"grad_norm": 0.19765284657478333,
"learning_rate": 3.1417953116066324e-05,
"loss": 0.1173,
"step": 650
},
{
"epoch": 1.1311053984575836,
"grad_norm": 0.17013542354106903,
"learning_rate": 3.113207547169811e-05,
"loss": 0.1128,
"step": 660
},
{
"epoch": 1.1482433590402743,
"grad_norm": 0.21173644065856934,
"learning_rate": 3.0846197827329905e-05,
"loss": 0.109,
"step": 670
},
{
"epoch": 1.165381319622965,
"grad_norm": 0.13383643329143524,
"learning_rate": 3.056032018296169e-05,
"loss": 0.1092,
"step": 680
},
{
"epoch": 1.1825192802056554,
"grad_norm": 0.22101104259490967,
"learning_rate": 3.0274442538593483e-05,
"loss": 0.1175,
"step": 690
},
{
"epoch": 1.1996572407883461,
"grad_norm": 0.1745050698518753,
"learning_rate": 2.9988564894225274e-05,
"loss": 0.1096,
"step": 700
},
{
"epoch": 1.2167952013710368,
"grad_norm": 0.2413550466299057,
"learning_rate": 2.9702687249857064e-05,
"loss": 0.1044,
"step": 710
},
{
"epoch": 1.2339331619537275,
"grad_norm": 0.15909789502620697,
"learning_rate": 2.9416809605488855e-05,
"loss": 0.1076,
"step": 720
},
{
"epoch": 1.2510711225364182,
"grad_norm": 0.21382008492946625,
"learning_rate": 2.9130931961120646e-05,
"loss": 0.1077,
"step": 730
},
{
"epoch": 1.2682090831191088,
"grad_norm": 0.1845552772283554,
"learning_rate": 2.884505431675243e-05,
"loss": 0.102,
"step": 740
},
{
"epoch": 1.2853470437017995,
"grad_norm": 0.19705334305763245,
"learning_rate": 2.855917667238422e-05,
"loss": 0.1048,
"step": 750
},
{
"epoch": 1.3024850042844902,
"grad_norm": 0.16979779303073883,
"learning_rate": 2.827329902801601e-05,
"loss": 0.1012,
"step": 760
},
{
"epoch": 1.3196229648671807,
"grad_norm": 0.18766264617443085,
"learning_rate": 2.7987421383647798e-05,
"loss": 0.1043,
"step": 770
},
{
"epoch": 1.3367609254498714,
"grad_norm": 0.1593862771987915,
"learning_rate": 2.770154373927959e-05,
"loss": 0.0953,
"step": 780
},
{
"epoch": 1.353898886032562,
"grad_norm": 0.19427362084388733,
"learning_rate": 2.741566609491138e-05,
"loss": 0.1008,
"step": 790
},
{
"epoch": 1.3710368466152527,
"grad_norm": 0.21518777310848236,
"learning_rate": 2.712978845054317e-05,
"loss": 0.0973,
"step": 800
},
{
"epoch": 1.3881748071979434,
"grad_norm": 0.2065572291612625,
"learning_rate": 2.684391080617496e-05,
"loss": 0.1035,
"step": 810
},
{
"epoch": 1.405312767780634,
"grad_norm": 0.26617249846458435,
"learning_rate": 2.655803316180675e-05,
"loss": 0.0969,
"step": 820
},
{
"epoch": 1.4224507283633248,
"grad_norm": 0.17817485332489014,
"learning_rate": 2.627215551743854e-05,
"loss": 0.0944,
"step": 830
},
{
"epoch": 1.4395886889460154,
"grad_norm": 0.17743416130542755,
"learning_rate": 2.5986277873070326e-05,
"loss": 0.0984,
"step": 840
},
{
"epoch": 1.4567266495287061,
"grad_norm": 0.23810917139053345,
"learning_rate": 2.5700400228702117e-05,
"loss": 0.099,
"step": 850
},
{
"epoch": 1.4738646101113968,
"grad_norm": 0.18336652219295502,
"learning_rate": 2.5414522584333904e-05,
"loss": 0.0954,
"step": 860
},
{
"epoch": 1.4910025706940875,
"grad_norm": 0.22074759006500244,
"learning_rate": 2.5128644939965695e-05,
"loss": 0.0915,
"step": 870
},
{
"epoch": 1.5081405312767782,
"grad_norm": 0.2292771190404892,
"learning_rate": 2.4842767295597485e-05,
"loss": 0.0931,
"step": 880
},
{
"epoch": 1.5252784918594688,
"grad_norm": 0.27021974325180054,
"learning_rate": 2.4556889651229276e-05,
"loss": 0.0933,
"step": 890
},
{
"epoch": 1.5424164524421595,
"grad_norm": 0.28702589869499207,
"learning_rate": 2.4271012006861067e-05,
"loss": 0.0978,
"step": 900
},
{
"epoch": 1.5595544130248502,
"grad_norm": 0.18202678859233856,
"learning_rate": 2.3985134362492854e-05,
"loss": 0.0908,
"step": 910
},
{
"epoch": 1.5766923736075407,
"grad_norm": 0.15822364389896393,
"learning_rate": 2.3699256718124644e-05,
"loss": 0.0878,
"step": 920
},
{
"epoch": 1.5938303341902313,
"grad_norm": 0.21551179885864258,
"learning_rate": 2.3413379073756435e-05,
"loss": 0.0883,
"step": 930
},
{
"epoch": 1.610968294772922,
"grad_norm": 0.20409446954727173,
"learning_rate": 2.3127501429388222e-05,
"loss": 0.094,
"step": 940
},
{
"epoch": 1.6281062553556127,
"grad_norm": 0.16509220004081726,
"learning_rate": 2.2841623785020013e-05,
"loss": 0.0909,
"step": 950
},
{
"epoch": 1.6452442159383034,
"grad_norm": 0.1946859210729599,
"learning_rate": 2.25557461406518e-05,
"loss": 0.0898,
"step": 960
},
{
"epoch": 1.6623821765209938,
"grad_norm": 0.16525417566299438,
"learning_rate": 2.226986849628359e-05,
"loss": 0.0842,
"step": 970
},
{
"epoch": 1.6795201371036845,
"grad_norm": 0.26819315552711487,
"learning_rate": 2.198399085191538e-05,
"loss": 0.0897,
"step": 980
},
{
"epoch": 1.6966580976863752,
"grad_norm": 0.273593008518219,
"learning_rate": 2.1698113207547172e-05,
"loss": 0.0895,
"step": 990
},
{
"epoch": 1.713796058269066,
"grad_norm": 0.20378242433071136,
"learning_rate": 2.1412235563178963e-05,
"loss": 0.0912,
"step": 1000
},
{
"epoch": 1.7309340188517566,
"grad_norm": 0.24366410076618195,
"learning_rate": 2.112635791881075e-05,
"loss": 0.0843,
"step": 1010
},
{
"epoch": 1.7480719794344473,
"grad_norm": 0.2034538835287094,
"learning_rate": 2.084048027444254e-05,
"loss": 0.0874,
"step": 1020
},
{
"epoch": 1.765209940017138,
"grad_norm": 0.2260463535785675,
"learning_rate": 2.0554602630074328e-05,
"loss": 0.0898,
"step": 1030
},
{
"epoch": 1.7823479005998286,
"grad_norm": 0.165971040725708,
"learning_rate": 2.026872498570612e-05,
"loss": 0.0867,
"step": 1040
},
{
"epoch": 1.7994858611825193,
"grad_norm": 0.20090453326702118,
"learning_rate": 1.998284734133791e-05,
"loss": 0.0891,
"step": 1050
},
{
"epoch": 1.81662382176521,
"grad_norm": 0.24718008935451508,
"learning_rate": 1.9696969696969697e-05,
"loss": 0.0872,
"step": 1060
},
{
"epoch": 1.8337617823479007,
"grad_norm": 0.2808043360710144,
"learning_rate": 1.9411092052601487e-05,
"loss": 0.0889,
"step": 1070
},
{
"epoch": 1.8508997429305913,
"grad_norm": 0.19833321869373322,
"learning_rate": 1.9125214408233278e-05,
"loss": 0.0859,
"step": 1080
},
{
"epoch": 1.868037703513282,
"grad_norm": 0.21585367619991302,
"learning_rate": 1.883933676386507e-05,
"loss": 0.0872,
"step": 1090
},
{
"epoch": 1.8851756640959727,
"grad_norm": 0.16208423674106598,
"learning_rate": 1.8553459119496856e-05,
"loss": 0.0835,
"step": 1100
},
{
"epoch": 1.9023136246786634,
"grad_norm": 0.195535346865654,
"learning_rate": 1.8267581475128647e-05,
"loss": 0.0785,
"step": 1110
},
{
"epoch": 1.919451585261354,
"grad_norm": 0.22447216510772705,
"learning_rate": 1.7981703830760434e-05,
"loss": 0.08,
"step": 1120
},
{
"epoch": 1.9365895458440445,
"grad_norm": 0.22212448716163635,
"learning_rate": 1.7695826186392224e-05,
"loss": 0.0826,
"step": 1130
},
{
"epoch": 1.9537275064267352,
"grad_norm": 0.2077985554933548,
"learning_rate": 1.7409948542024015e-05,
"loss": 0.0822,
"step": 1140
},
{
"epoch": 1.9708654670094259,
"grad_norm": 0.20502477884292603,
"learning_rate": 1.7124070897655802e-05,
"loss": 0.0817,
"step": 1150
},
{
"epoch": 1.9880034275921166,
"grad_norm": 0.22330917418003082,
"learning_rate": 1.6838193253287593e-05,
"loss": 0.0837,
"step": 1160
},
{
"epoch": 2.0,
"eval_loss": 0.19116699695587158,
"eval_runtime": 439.6787,
"eval_samples_per_second": 10.917,
"eval_steps_per_second": 1.365,
"step": 1167
},
{
"epoch": 2.005141388174807,
"grad_norm": 0.1825590431690216,
"learning_rate": 1.6552315608919384e-05,
"loss": 0.0764,
"step": 1170
},
{
"epoch": 2.0222793487574977,
"grad_norm": 0.245217964053154,
"learning_rate": 1.6266437964551174e-05,
"loss": 0.0776,
"step": 1180
},
{
"epoch": 2.0394173093401884,
"grad_norm": 0.185066357254982,
"learning_rate": 1.5980560320182965e-05,
"loss": 0.0736,
"step": 1190
},
{
"epoch": 2.056555269922879,
"grad_norm": 0.1703159511089325,
"learning_rate": 1.5694682675814752e-05,
"loss": 0.075,
"step": 1200
},
{
"epoch": 2.0736932305055698,
"grad_norm": 0.19329093396663666,
"learning_rate": 1.540880503144654e-05,
"loss": 0.0789,
"step": 1210
},
{
"epoch": 2.0908311910882604,
"grad_norm": 0.22116591036319733,
"learning_rate": 1.5122927387078332e-05,
"loss": 0.0761,
"step": 1220
},
{
"epoch": 2.107969151670951,
"grad_norm": 0.17945989966392517,
"learning_rate": 1.4837049742710121e-05,
"loss": 0.0766,
"step": 1230
},
{
"epoch": 2.125107112253642,
"grad_norm": 0.21690496802330017,
"learning_rate": 1.4551172098341912e-05,
"loss": 0.0748,
"step": 1240
},
{
"epoch": 2.1422450728363325,
"grad_norm": 0.17853769659996033,
"learning_rate": 1.4265294453973699e-05,
"loss": 0.0755,
"step": 1250
},
{
"epoch": 2.159383033419023,
"grad_norm": 0.18670514225959778,
"learning_rate": 1.397941680960549e-05,
"loss": 0.0789,
"step": 1260
},
{
"epoch": 2.176520994001714,
"grad_norm": 0.2004610300064087,
"learning_rate": 1.3693539165237278e-05,
"loss": 0.0771,
"step": 1270
},
{
"epoch": 2.1936589545844045,
"grad_norm": 0.17286266386508942,
"learning_rate": 1.3407661520869069e-05,
"loss": 0.0757,
"step": 1280
},
{
"epoch": 2.210796915167095,
"grad_norm": 0.21835772693157196,
"learning_rate": 1.312178387650086e-05,
"loss": 0.0764,
"step": 1290
},
{
"epoch": 2.227934875749786,
"grad_norm": 0.2717360854148865,
"learning_rate": 1.2835906232132647e-05,
"loss": 0.0761,
"step": 1300
},
{
"epoch": 2.2450728363324766,
"grad_norm": 0.17896392941474915,
"learning_rate": 1.2550028587764438e-05,
"loss": 0.0748,
"step": 1310
},
{
"epoch": 2.2622107969151672,
"grad_norm": 0.20612064003944397,
"learning_rate": 1.2264150943396227e-05,
"loss": 0.0745,
"step": 1320
},
{
"epoch": 2.279348757497858,
"grad_norm": 0.25621137022972107,
"learning_rate": 1.1978273299028017e-05,
"loss": 0.0754,
"step": 1330
},
{
"epoch": 2.2964867180805486,
"grad_norm": 0.1826545149087906,
"learning_rate": 1.1692395654659806e-05,
"loss": 0.0738,
"step": 1340
},
{
"epoch": 2.3136246786632393,
"grad_norm": 0.22315889596939087,
"learning_rate": 1.1406518010291597e-05,
"loss": 0.0738,
"step": 1350
},
{
"epoch": 2.33076263924593,
"grad_norm": 0.2433796525001526,
"learning_rate": 1.1120640365923384e-05,
"loss": 0.0746,
"step": 1360
},
{
"epoch": 2.34790059982862,
"grad_norm": 0.19135648012161255,
"learning_rate": 1.0834762721555175e-05,
"loss": 0.0745,
"step": 1370
},
{
"epoch": 2.365038560411311,
"grad_norm": 0.21853765845298767,
"learning_rate": 1.0548885077186965e-05,
"loss": 0.0751,
"step": 1380
},
{
"epoch": 2.3821765209940016,
"grad_norm": 0.23422804474830627,
"learning_rate": 1.0263007432818754e-05,
"loss": 0.0736,
"step": 1390
},
{
"epoch": 2.3993144815766922,
"grad_norm": 0.22039854526519775,
"learning_rate": 9.977129788450543e-06,
"loss": 0.0722,
"step": 1400
},
{
"epoch": 2.416452442159383,
"grad_norm": 0.20668627321720123,
"learning_rate": 9.691252144082332e-06,
"loss": 0.074,
"step": 1410
},
{
"epoch": 2.4335904027420736,
"grad_norm": 0.3503040671348572,
"learning_rate": 9.405374499714123e-06,
"loss": 0.0786,
"step": 1420
},
{
"epoch": 2.4507283633247643,
"grad_norm": 0.2581626772880554,
"learning_rate": 9.119496855345912e-06,
"loss": 0.0721,
"step": 1430
},
{
"epoch": 2.467866323907455,
"grad_norm": 0.2439981997013092,
"learning_rate": 8.833619210977703e-06,
"loss": 0.0733,
"step": 1440
},
{
"epoch": 2.4850042844901457,
"grad_norm": 0.16303370893001556,
"learning_rate": 8.547741566609492e-06,
"loss": 0.0727,
"step": 1450
},
{
"epoch": 2.5021422450728363,
"grad_norm": 0.17133218050003052,
"learning_rate": 8.26186392224128e-06,
"loss": 0.0722,
"step": 1460
},
{
"epoch": 2.519280205655527,
"grad_norm": 0.2298302799463272,
"learning_rate": 7.975986277873071e-06,
"loss": 0.0717,
"step": 1470
},
{
"epoch": 2.5364181662382177,
"grad_norm": 0.22220905125141144,
"learning_rate": 7.69010863350486e-06,
"loss": 0.0763,
"step": 1480
},
{
"epoch": 2.5535561268209084,
"grad_norm": 0.2196768969297409,
"learning_rate": 7.40423098913665e-06,
"loss": 0.0694,
"step": 1490
},
{
"epoch": 2.570694087403599,
"grad_norm": 0.23876038193702698,
"learning_rate": 7.11835334476844e-06,
"loss": 0.0702,
"step": 1500
},
{
"epoch": 2.5878320479862897,
"grad_norm": 0.2197275310754776,
"learning_rate": 6.832475700400229e-06,
"loss": 0.0731,
"step": 1510
},
{
"epoch": 2.6049700085689804,
"grad_norm": 0.1521027684211731,
"learning_rate": 6.5465980560320186e-06,
"loss": 0.0706,
"step": 1520
},
{
"epoch": 2.622107969151671,
"grad_norm": 0.2315615713596344,
"learning_rate": 6.2607204116638075e-06,
"loss": 0.0699,
"step": 1530
},
{
"epoch": 2.6392459297343613,
"grad_norm": 0.22933197021484375,
"learning_rate": 5.974842767295598e-06,
"loss": 0.0726,
"step": 1540
},
{
"epoch": 2.656383890317052,
"grad_norm": 0.23843450844287872,
"learning_rate": 5.688965122927387e-06,
"loss": 0.0696,
"step": 1550
},
{
"epoch": 2.6735218508997427,
"grad_norm": 0.2547082304954529,
"learning_rate": 5.403087478559177e-06,
"loss": 0.0697,
"step": 1560
},
{
"epoch": 2.6906598114824334,
"grad_norm": 0.19213077425956726,
"learning_rate": 5.117209834190966e-06,
"loss": 0.0725,
"step": 1570
},
{
"epoch": 2.707797772065124,
"grad_norm": 0.19462022185325623,
"learning_rate": 4.8313321898227566e-06,
"loss": 0.0707,
"step": 1580
},
{
"epoch": 2.7249357326478147,
"grad_norm": 0.22448916733264923,
"learning_rate": 4.5454545454545455e-06,
"loss": 0.0708,
"step": 1590
},
{
"epoch": 2.7420736932305054,
"grad_norm": 0.22550085186958313,
"learning_rate": 4.259576901086335e-06,
"loss": 0.0705,
"step": 1600
},
{
"epoch": 2.759211653813196,
"grad_norm": 0.24738526344299316,
"learning_rate": 3.973699256718124e-06,
"loss": 0.0716,
"step": 1610
},
{
"epoch": 2.776349614395887,
"grad_norm": 0.20870988070964813,
"learning_rate": 3.687821612349914e-06,
"loss": 0.0674,
"step": 1620
},
{
"epoch": 2.7934875749785775,
"grad_norm": 0.2011324018239975,
"learning_rate": 3.4019439679817043e-06,
"loss": 0.0692,
"step": 1630
},
{
"epoch": 2.810625535561268,
"grad_norm": 0.25708264112472534,
"learning_rate": 3.1160663236134933e-06,
"loss": 0.0699,
"step": 1640
},
{
"epoch": 2.827763496143959,
"grad_norm": 0.20108073949813843,
"learning_rate": 2.830188679245283e-06,
"loss": 0.0702,
"step": 1650
},
{
"epoch": 2.8449014567266495,
"grad_norm": 0.21398206055164337,
"learning_rate": 2.5443110348770725e-06,
"loss": 0.0727,
"step": 1660
},
{
"epoch": 2.86203941730934,
"grad_norm": 0.1945817768573761,
"learning_rate": 2.2584333905088623e-06,
"loss": 0.0739,
"step": 1670
},
{
"epoch": 2.879177377892031,
"grad_norm": 0.20674385130405426,
"learning_rate": 1.972555746140652e-06,
"loss": 0.0738,
"step": 1680
},
{
"epoch": 2.8963153384747216,
"grad_norm": 0.2226879894733429,
"learning_rate": 1.6866781017724415e-06,
"loss": 0.0698,
"step": 1690
},
{
"epoch": 2.9134532990574122,
"grad_norm": 0.1832134872674942,
"learning_rate": 1.400800457404231e-06,
"loss": 0.0701,
"step": 1700
},
{
"epoch": 2.930591259640103,
"grad_norm": 0.2704426348209381,
"learning_rate": 1.1149228130360207e-06,
"loss": 0.0681,
"step": 1710
},
{
"epoch": 2.9477292202227936,
"grad_norm": 0.2618798315525055,
"learning_rate": 8.290451686678103e-07,
"loss": 0.0696,
"step": 1720
},
{
"epoch": 2.9648671808054843,
"grad_norm": 0.16076813638210297,
"learning_rate": 5.431675242995998e-07,
"loss": 0.0729,
"step": 1730
},
{
"epoch": 2.982005141388175,
"grad_norm": 0.20760373771190643,
"learning_rate": 2.572898799313894e-07,
"loss": 0.0693,
"step": 1740
},
{
"epoch": 2.9974293059125965,
"eval_loss": 0.2091314196586609,
"eval_runtime": 438.8842,
"eval_samples_per_second": 10.937,
"eval_steps_per_second": 1.367,
"step": 1749
}
],
"logging_steps": 10,
"max_steps": 1749,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 1.3059345020564275e+18,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}