0311_intent / trainer_state.json
Nevamind-AI's picture
Upload model 2026-03-12 21:47:05
2e10dbb verified
Raw
History Blame Contribute Delete
42.4 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 2415,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.020714655618850338,
"grad_norm": 136.09461975097656,
"learning_rate": 3.7190082644628103e-07,
"loss": 2.8653,
"step": 10
},
{
"epoch": 0.041429311237700675,
"grad_norm": 88.58033752441406,
"learning_rate": 7.851239669421488e-07,
"loss": 2.5785,
"step": 20
},
{
"epoch": 0.06214396685655101,
"grad_norm": 70.43850708007812,
"learning_rate": 1.1983471074380167e-06,
"loss": 1.9446,
"step": 30
},
{
"epoch": 0.08285862247540135,
"grad_norm": 43.14393615722656,
"learning_rate": 1.6115702479338842e-06,
"loss": 1.0318,
"step": 40
},
{
"epoch": 0.10357327809425168,
"grad_norm": 36.25138473510742,
"learning_rate": 2.024793388429752e-06,
"loss": 0.6537,
"step": 50
},
{
"epoch": 0.12428793371310203,
"grad_norm": 29.691160202026367,
"learning_rate": 2.43801652892562e-06,
"loss": 0.586,
"step": 60
},
{
"epoch": 0.14500258933195237,
"grad_norm": 38.37786865234375,
"learning_rate": 2.851239669421488e-06,
"loss": 0.4644,
"step": 70
},
{
"epoch": 0.1657172449508027,
"grad_norm": 27.817943572998047,
"learning_rate": 3.264462809917356e-06,
"loss": 0.4554,
"step": 80
},
{
"epoch": 0.18643190056965303,
"grad_norm": 24.26976776123047,
"learning_rate": 3.6776859504132234e-06,
"loss": 0.4214,
"step": 90
},
{
"epoch": 0.20714655618850336,
"grad_norm": 21.54690933227539,
"learning_rate": 4.0909090909090915e-06,
"loss": 0.4377,
"step": 100
},
{
"epoch": 0.2278612118073537,
"grad_norm": 25.445524215698242,
"learning_rate": 4.504132231404959e-06,
"loss": 0.4332,
"step": 110
},
{
"epoch": 0.24857586742620405,
"grad_norm": 9.714593887329102,
"learning_rate": 4.917355371900827e-06,
"loss": 0.4261,
"step": 120
},
{
"epoch": 0.26929052304505435,
"grad_norm": 19.427701950073242,
"learning_rate": 5.3305785123966946e-06,
"loss": 0.2713,
"step": 130
},
{
"epoch": 0.29000517866390474,
"grad_norm": 26.93349838256836,
"learning_rate": 5.743801652892562e-06,
"loss": 0.4633,
"step": 140
},
{
"epoch": 0.31071983428275507,
"grad_norm": 16.846187591552734,
"learning_rate": 6.15702479338843e-06,
"loss": 0.3568,
"step": 150
},
{
"epoch": 0.3314344899016054,
"grad_norm": 19.229270935058594,
"learning_rate": 6.5702479338842985e-06,
"loss": 0.4279,
"step": 160
},
{
"epoch": 0.35214914552045573,
"grad_norm": 11.285515785217285,
"learning_rate": 6.983471074380166e-06,
"loss": 0.4001,
"step": 170
},
{
"epoch": 0.37286380113930606,
"grad_norm": 16.734804153442383,
"learning_rate": 7.396694214876033e-06,
"loss": 0.3646,
"step": 180
},
{
"epoch": 0.3935784567581564,
"grad_norm": 15.663717269897461,
"learning_rate": 7.809917355371902e-06,
"loss": 0.3548,
"step": 190
},
{
"epoch": 0.4142931123770067,
"grad_norm": 13.149024963378906,
"learning_rate": 8.22314049586777e-06,
"loss": 0.3367,
"step": 200
},
{
"epoch": 0.43500776799585705,
"grad_norm": 16.229578018188477,
"learning_rate": 8.636363636363637e-06,
"loss": 0.4299,
"step": 210
},
{
"epoch": 0.4557224236147074,
"grad_norm": 15.995393753051758,
"learning_rate": 9.049586776859506e-06,
"loss": 0.3799,
"step": 220
},
{
"epoch": 0.47643707923355777,
"grad_norm": 17.846311569213867,
"learning_rate": 9.462809917355372e-06,
"loss": 0.4196,
"step": 230
},
{
"epoch": 0.4971517348524081,
"grad_norm": 12.976713180541992,
"learning_rate": 9.876033057851241e-06,
"loss": 0.3538,
"step": 240
},
{
"epoch": 0.5178663904712584,
"grad_norm": 12.457372665405273,
"learning_rate": 9.99974395713694e-06,
"loss": 0.3195,
"step": 250
},
{
"epoch": 0.5385810460901087,
"grad_norm": 22.10851287841797,
"learning_rate": 9.998489932771846e-06,
"loss": 0.4551,
"step": 260
},
{
"epoch": 0.559295701708959,
"grad_norm": 14.96574592590332,
"learning_rate": 9.996191160403137e-06,
"loss": 0.3903,
"step": 270
},
{
"epoch": 0.5800103573278095,
"grad_norm": 17.109445571899414,
"learning_rate": 9.992848120503493e-06,
"loss": 0.4101,
"step": 280
},
{
"epoch": 0.6007250129466598,
"grad_norm": 18.271316528320312,
"learning_rate": 9.988461511810796e-06,
"loss": 0.3537,
"step": 290
},
{
"epoch": 0.6214396685655101,
"grad_norm": 14.461223602294922,
"learning_rate": 9.983032251182081e-06,
"loss": 0.4106,
"step": 300
},
{
"epoch": 0.6421543241843605,
"grad_norm": 20.726234436035156,
"learning_rate": 9.976561473401912e-06,
"loss": 0.3882,
"step": 310
},
{
"epoch": 0.6628689798032108,
"grad_norm": 9.426527976989746,
"learning_rate": 9.969050530945185e-06,
"loss": 0.4911,
"step": 320
},
{
"epoch": 0.6835836354220611,
"grad_norm": 12.789864540100098,
"learning_rate": 9.960500993694455e-06,
"loss": 0.4561,
"step": 330
},
{
"epoch": 0.7042982910409115,
"grad_norm": 13.208131790161133,
"learning_rate": 9.950914648611803e-06,
"loss": 0.3553,
"step": 340
},
{
"epoch": 0.7250129466597618,
"grad_norm": 13.009285926818848,
"learning_rate": 9.94029349936534e-06,
"loss": 0.2996,
"step": 350
},
{
"epoch": 0.7457276022786121,
"grad_norm": 19.585464477539062,
"learning_rate": 9.928639765910417e-06,
"loss": 0.4183,
"step": 360
},
{
"epoch": 0.7664422578974625,
"grad_norm": 14.149604797363281,
"learning_rate": 9.915955884025627e-06,
"loss": 0.3981,
"step": 370
},
{
"epoch": 0.7871569135163128,
"grad_norm": 11.50778865814209,
"learning_rate": 9.902244504803688e-06,
"loss": 0.4531,
"step": 380
},
{
"epoch": 0.8078715691351631,
"grad_norm": 13.067028999328613,
"learning_rate": 9.88750849409734e-06,
"loss": 0.3985,
"step": 390
},
{
"epoch": 0.8285862247540134,
"grad_norm": 23.008283615112305,
"learning_rate": 9.871750931920344e-06,
"loss": 0.3942,
"step": 400
},
{
"epoch": 0.8493008803728638,
"grad_norm": 13.678590774536133,
"learning_rate": 9.854975111803714e-06,
"loss": 0.3119,
"step": 410
},
{
"epoch": 0.8700155359917141,
"grad_norm": 14.53078842163086,
"learning_rate": 9.837184540107334e-06,
"loss": 0.3849,
"step": 420
},
{
"epoch": 0.8907301916105644,
"grad_norm": 10.536521911621094,
"learning_rate": 9.818382935287078e-06,
"loss": 0.4097,
"step": 430
},
{
"epoch": 0.9114448472294148,
"grad_norm": 12.507116317749023,
"learning_rate": 9.798574227117616e-06,
"loss": 0.34,
"step": 440
},
{
"epoch": 0.9321595028482651,
"grad_norm": 13.819009780883789,
"learning_rate": 9.777762555871024e-06,
"loss": 0.4503,
"step": 450
},
{
"epoch": 0.9528741584671155,
"grad_norm": 15.760241508483887,
"learning_rate": 9.75595227145143e-06,
"loss": 0.3229,
"step": 460
},
{
"epoch": 0.9735888140859659,
"grad_norm": 4.996370315551758,
"learning_rate": 9.73314793248582e-06,
"loss": 0.3724,
"step": 470
},
{
"epoch": 0.9943034697048162,
"grad_norm": 22.667329788208008,
"learning_rate": 9.709354305371237e-06,
"loss": 0.3355,
"step": 480
},
{
"epoch": 1.0145002589331953,
"grad_norm": 7.149298667907715,
"learning_rate": 9.684576363278526e-06,
"loss": 0.2252,
"step": 490
},
{
"epoch": 1.0352149145520455,
"grad_norm": 20.373506546020508,
"learning_rate": 9.658819285112894e-06,
"loss": 0.1902,
"step": 500
},
{
"epoch": 1.055929570170896,
"grad_norm": 14.847016334533691,
"learning_rate": 9.632088454431448e-06,
"loss": 0.3072,
"step": 510
},
{
"epoch": 1.0766442257897462,
"grad_norm": 16.063648223876953,
"learning_rate": 9.604389458317958e-06,
"loss": 0.2583,
"step": 520
},
{
"epoch": 1.0973588814085966,
"grad_norm": 6.721749305725098,
"learning_rate": 9.575728086215093e-06,
"loss": 0.1645,
"step": 530
},
{
"epoch": 1.1180735370274468,
"grad_norm": 8.20914077758789,
"learning_rate": 9.546110328714348e-06,
"loss": 0.218,
"step": 540
},
{
"epoch": 1.1387881926462973,
"grad_norm": 10.602900505065918,
"learning_rate": 9.515542376303942e-06,
"loss": 0.2281,
"step": 550
},
{
"epoch": 1.1595028482651477,
"grad_norm": 14.347077369689941,
"learning_rate": 9.484030618074912e-06,
"loss": 0.2464,
"step": 560
},
{
"epoch": 1.180217503883998,
"grad_norm": 8.088728904724121,
"learning_rate": 9.451581640385727e-06,
"loss": 0.1652,
"step": 570
},
{
"epoch": 1.2009321595028482,
"grad_norm": 9.3583402633667,
"learning_rate": 9.418202225485654e-06,
"loss": 0.1865,
"step": 580
},
{
"epoch": 1.2216468151216986,
"grad_norm": 11.516282081604004,
"learning_rate": 9.38389935009717e-06,
"loss": 0.1979,
"step": 590
},
{
"epoch": 1.242361470740549,
"grad_norm": 11.206570625305176,
"learning_rate": 9.348680183957748e-06,
"loss": 0.167,
"step": 600
},
{
"epoch": 1.2630761263593993,
"grad_norm": 7.137627601623535,
"learning_rate": 9.312552088321287e-06,
"loss": 0.2252,
"step": 610
},
{
"epoch": 1.2837907819782495,
"grad_norm": 5.875232219696045,
"learning_rate": 9.275522614419522e-06,
"loss": 0.1617,
"step": 620
},
{
"epoch": 1.3045054375971,
"grad_norm": 10.008681297302246,
"learning_rate": 9.237599501883711e-06,
"loss": 0.1646,
"step": 630
},
{
"epoch": 1.3252200932159504,
"grad_norm": 30.00780487060547,
"learning_rate": 9.198790677126959e-06,
"loss": 0.2157,
"step": 640
},
{
"epoch": 1.3459347488348006,
"grad_norm": 7.50967264175415,
"learning_rate": 9.159104251687498e-06,
"loss": 0.1859,
"step": 650
},
{
"epoch": 1.366649404453651,
"grad_norm": 16.224645614624023,
"learning_rate": 9.11854852053327e-06,
"loss": 0.229,
"step": 660
},
{
"epoch": 1.3873640600725012,
"grad_norm": 9.085508346557617,
"learning_rate": 9.07713196032817e-06,
"loss": 0.1284,
"step": 670
},
{
"epoch": 1.4080787156913517,
"grad_norm": 7.53919792175293,
"learning_rate": 9.034863227660326e-06,
"loss": 0.1658,
"step": 680
},
{
"epoch": 1.428793371310202,
"grad_norm": 7.7167863845825195,
"learning_rate": 8.99175115723275e-06,
"loss": 0.1364,
"step": 690
},
{
"epoch": 1.4495080269290523,
"grad_norm": 6.203945159912109,
"learning_rate": 8.947804760016778e-06,
"loss": 0.1828,
"step": 700
},
{
"epoch": 1.4702226825479026,
"grad_norm": 10.58707332611084,
"learning_rate": 8.903033221368662e-06,
"loss": 0.1568,
"step": 710
},
{
"epoch": 1.490937338166753,
"grad_norm": 10.055088996887207,
"learning_rate": 8.857445899109716e-06,
"loss": 0.2081,
"step": 720
},
{
"epoch": 1.5116519937856032,
"grad_norm": 14.575348854064941,
"learning_rate": 8.811052321570405e-06,
"loss": 0.2289,
"step": 730
},
{
"epoch": 1.5323666494044537,
"grad_norm": 5.889805316925049,
"learning_rate": 8.763862185598814e-06,
"loss": 0.1475,
"step": 740
},
{
"epoch": 1.553081305023304,
"grad_norm": 10.278194427490234,
"learning_rate": 8.715885354533871e-06,
"loss": 0.2298,
"step": 750
},
{
"epoch": 1.5737959606421543,
"grad_norm": 9.15528678894043,
"learning_rate": 8.667131856143793e-06,
"loss": 0.1903,
"step": 760
},
{
"epoch": 1.5945106162610045,
"grad_norm": 12.943020820617676,
"learning_rate": 8.61761188053015e-06,
"loss": 0.1925,
"step": 770
},
{
"epoch": 1.615225271879855,
"grad_norm": 13.724532127380371,
"learning_rate": 8.567335777998003e-06,
"loss": 0.2135,
"step": 780
},
{
"epoch": 1.6359399274987054,
"grad_norm": 16.677555084228516,
"learning_rate": 8.516314056892565e-06,
"loss": 0.2626,
"step": 790
},
{
"epoch": 1.6566545831175556,
"grad_norm": 16.909591674804688,
"learning_rate": 8.46455738140282e-06,
"loss": 0.2042,
"step": 800
},
{
"epoch": 1.6773692387364059,
"grad_norm": 10.952155113220215,
"learning_rate": 8.412076569332568e-06,
"loss": 0.203,
"step": 810
},
{
"epoch": 1.6980838943552563,
"grad_norm": 8.591595649719238,
"learning_rate": 8.358882589839365e-06,
"loss": 0.2102,
"step": 820
},
{
"epoch": 1.7187985499741067,
"grad_norm": 13.783975601196289,
"learning_rate": 8.304986561141844e-06,
"loss": 0.1425,
"step": 830
},
{
"epoch": 1.739513205592957,
"grad_norm": 18.49563217163086,
"learning_rate": 8.25039974819585e-06,
"loss": 0.2815,
"step": 840
},
{
"epoch": 1.7602278612118072,
"grad_norm": 7.381472110748291,
"learning_rate": 8.19513356033992e-06,
"loss": 0.146,
"step": 850
},
{
"epoch": 1.7809425168306579,
"grad_norm": 10.87417984008789,
"learning_rate": 8.139199548910605e-06,
"loss": 0.1795,
"step": 860
},
{
"epoch": 1.801657172449508,
"grad_norm": 10.996023178100586,
"learning_rate": 8.082609404828075e-06,
"loss": 0.2332,
"step": 870
},
{
"epoch": 1.8223718280683583,
"grad_norm": 13.015434265136719,
"learning_rate": 8.02537495615257e-06,
"loss": 0.1648,
"step": 880
},
{
"epoch": 1.8430864836872087,
"grad_norm": 6.8451995849609375,
"learning_rate": 7.967508165612197e-06,
"loss": 0.2004,
"step": 890
},
{
"epoch": 1.8638011393060592,
"grad_norm": 8.442510604858398,
"learning_rate": 7.909021128102552e-06,
"loss": 0.1851,
"step": 900
},
{
"epoch": 1.8845157949249094,
"grad_norm": 11.029095649719238,
"learning_rate": 7.84992606815875e-06,
"loss": 0.1906,
"step": 910
},
{
"epoch": 1.9052304505437596,
"grad_norm": 11.20981216430664,
"learning_rate": 7.790235337400319e-06,
"loss": 0.1497,
"step": 920
},
{
"epoch": 1.92594510616261,
"grad_norm": 11.603791236877441,
"learning_rate": 7.729961411949579e-06,
"loss": 0.2066,
"step": 930
},
{
"epoch": 1.9466597617814605,
"grad_norm": 6.199766159057617,
"learning_rate": 7.669116889823955e-06,
"loss": 0.1505,
"step": 940
},
{
"epoch": 1.9673744174003107,
"grad_norm": 12.146078109741211,
"learning_rate": 7.607714488302842e-06,
"loss": 0.1692,
"step": 950
},
{
"epoch": 1.988089073019161,
"grad_norm": 4.0871052742004395,
"learning_rate": 7.545767041269528e-06,
"loss": 0.1835,
"step": 960
},
{
"epoch": 2.0082858622475404,
"grad_norm": 10.530585289001465,
"learning_rate": 7.483287496528745e-06,
"loss": 0.1991,
"step": 970
},
{
"epoch": 2.0290005178663906,
"grad_norm": 1.808644413948059,
"learning_rate": 7.42028891310042e-06,
"loss": 0.0674,
"step": 980
},
{
"epoch": 2.049715173485241,
"grad_norm": 9.25330638885498,
"learning_rate": 7.356784458490172e-06,
"loss": 0.0613,
"step": 990
},
{
"epoch": 2.070429829104091,
"grad_norm": 3.011075258255005,
"learning_rate": 7.292787405937129e-06,
"loss": 0.0674,
"step": 1000
},
{
"epoch": 2.0911444847229417,
"grad_norm": 6.211314678192139,
"learning_rate": 7.228311131639667e-06,
"loss": 0.0594,
"step": 1010
},
{
"epoch": 2.111859140341792,
"grad_norm": 5.608636379241943,
"learning_rate": 7.163369111959594e-06,
"loss": 0.0668,
"step": 1020
},
{
"epoch": 2.132573795960642,
"grad_norm": 4.631962299346924,
"learning_rate": 7.097974920605435e-06,
"loss": 0.0535,
"step": 1030
},
{
"epoch": 2.1532884515794923,
"grad_norm": 19.285358428955078,
"learning_rate": 7.0321422257953505e-06,
"loss": 0.0872,
"step": 1040
},
{
"epoch": 2.174003107198343,
"grad_norm": 19.635221481323242,
"learning_rate": 6.965884787400301e-06,
"loss": 0.0827,
"step": 1050
},
{
"epoch": 2.194717762817193,
"grad_norm": 4.142362594604492,
"learning_rate": 6.899216454068063e-06,
"loss": 0.063,
"step": 1060
},
{
"epoch": 2.2154324184360434,
"grad_norm": 3.2913637161254883,
"learning_rate": 6.832151160328681e-06,
"loss": 0.0689,
"step": 1070
},
{
"epoch": 2.2361470740548937,
"grad_norm": 9.357172966003418,
"learning_rate": 6.764702923681977e-06,
"loss": 0.0596,
"step": 1080
},
{
"epoch": 2.2568617296737443,
"grad_norm": 18.493061065673828,
"learning_rate": 6.696885841667718e-06,
"loss": 0.1226,
"step": 1090
},
{
"epoch": 2.2775763852925945,
"grad_norm": 1.1360570192337036,
"learning_rate": 6.628714088919037e-06,
"loss": 0.044,
"step": 1100
},
{
"epoch": 2.2982910409114448,
"grad_norm": 21.6003475189209,
"learning_rate": 6.560201914199774e-06,
"loss": 0.0831,
"step": 1110
},
{
"epoch": 2.3190056965302954,
"grad_norm": 10.830430030822754,
"learning_rate": 6.491363637426289e-06,
"loss": 0.0716,
"step": 1120
},
{
"epoch": 2.3397203521491456,
"grad_norm": 1.8051860332489014,
"learning_rate": 6.422213646674416e-06,
"loss": 0.073,
"step": 1130
},
{
"epoch": 2.360435007767996,
"grad_norm": 10.868322372436523,
"learning_rate": 6.352766395172186e-06,
"loss": 0.1141,
"step": 1140
},
{
"epoch": 2.381149663386846,
"grad_norm": 9.984950065612793,
"learning_rate": 6.283036398278903e-06,
"loss": 0.1183,
"step": 1150
},
{
"epoch": 2.4018643190056963,
"grad_norm": 9.204029083251953,
"learning_rate": 6.2130382304512615e-06,
"loss": 0.0874,
"step": 1160
},
{
"epoch": 2.422578974624547,
"grad_norm": 15.734174728393555,
"learning_rate": 6.142786522197088e-06,
"loss": 0.0784,
"step": 1170
},
{
"epoch": 2.443293630243397,
"grad_norm": 3.7714240550994873,
"learning_rate": 6.072295957017385e-06,
"loss": 0.0365,
"step": 1180
},
{
"epoch": 2.4640082858622474,
"grad_norm": 7.589274883270264,
"learning_rate": 6.0015812683372975e-06,
"loss": 0.0637,
"step": 1190
},
{
"epoch": 2.484722941481098,
"grad_norm": 1.8057529926300049,
"learning_rate": 5.9306572364266294e-06,
"loss": 0.0324,
"step": 1200
},
{
"epoch": 2.5054375970999483,
"grad_norm": 8.49700927734375,
"learning_rate": 5.859538685310585e-06,
"loss": 0.0535,
"step": 1210
},
{
"epoch": 2.5261522527187985,
"grad_norm": 6.09406852722168,
"learning_rate": 5.788240479671359e-06,
"loss": 0.077,
"step": 1220
},
{
"epoch": 2.5468669083376487,
"grad_norm": 5.549806594848633,
"learning_rate": 5.716777521741223e-06,
"loss": 0.0611,
"step": 1230
},
{
"epoch": 2.567581563956499,
"grad_norm": 9.635648727416992,
"learning_rate": 5.645164748187781e-06,
"loss": 0.0459,
"step": 1240
},
{
"epoch": 2.5882962195753496,
"grad_norm": 8.788506507873535,
"learning_rate": 5.573417126992004e-06,
"loss": 0.0892,
"step": 1250
},
{
"epoch": 2.6090108751942,
"grad_norm": 12.776182174682617,
"learning_rate": 5.501549654319734e-06,
"loss": 0.0889,
"step": 1260
},
{
"epoch": 2.62972553081305,
"grad_norm": 8.335481643676758,
"learning_rate": 5.4295773513873085e-06,
"loss": 0.0509,
"step": 1270
},
{
"epoch": 2.6504401864319007,
"grad_norm": 9.699995040893555,
"learning_rate": 5.3575152613219065e-06,
"loss": 0.0742,
"step": 1280
},
{
"epoch": 2.671154842050751,
"grad_norm": 12.192926406860352,
"learning_rate": 5.285378446017373e-06,
"loss": 0.094,
"step": 1290
},
{
"epoch": 2.691869497669601,
"grad_norm": 13.16299819946289,
"learning_rate": 5.213181982986072e-06,
"loss": 0.1143,
"step": 1300
},
{
"epoch": 2.712584153288452,
"grad_norm": 0.24648113548755646,
"learning_rate": 5.140940962207508e-06,
"loss": 0.0551,
"step": 1310
},
{
"epoch": 2.733298808907302,
"grad_norm": 14.468437194824219,
"learning_rate": 5.068670482974316e-06,
"loss": 0.0546,
"step": 1320
},
{
"epoch": 2.7540134645261523,
"grad_norm": 3.7936367988586426,
"learning_rate": 4.996385650736324e-06,
"loss": 0.0567,
"step": 1330
},
{
"epoch": 2.7747281201450025,
"grad_norm": 4.176472187042236,
"learning_rate": 4.924101573943322e-06,
"loss": 0.0731,
"step": 1340
},
{
"epoch": 2.7954427757638527,
"grad_norm": 8.804961204528809,
"learning_rate": 4.8518333608872015e-06,
"loss": 0.0521,
"step": 1350
},
{
"epoch": 2.8161574313827034,
"grad_norm": 2.8285467624664307,
"learning_rate": 4.779596116544134e-06,
"loss": 0.0529,
"step": 1360
},
{
"epoch": 2.8368720870015536,
"grad_norm": 18.34342384338379,
"learning_rate": 4.707404939417429e-06,
"loss": 0.0746,
"step": 1370
},
{
"epoch": 2.857586742620404,
"grad_norm": 18.501070022583008,
"learning_rate": 4.635274918381768e-06,
"loss": 0.0812,
"step": 1380
},
{
"epoch": 2.8783013982392545,
"grad_norm": 8.442827224731445,
"learning_rate": 4.563221129529429e-06,
"loss": 0.0866,
"step": 1390
},
{
"epoch": 2.8990160538581047,
"grad_norm": 10.092520713806152,
"learning_rate": 4.491258633019194e-06,
"loss": 0.0834,
"step": 1400
},
{
"epoch": 2.919730709476955,
"grad_norm": 9.828836441040039,
"learning_rate": 4.419402469928582e-06,
"loss": 0.0702,
"step": 1410
},
{
"epoch": 2.940445365095805,
"grad_norm": 2.431955337524414,
"learning_rate": 4.34766765911008e-06,
"loss": 0.0675,
"step": 1420
},
{
"epoch": 2.961160020714656,
"grad_norm": 7.237964630126953,
"learning_rate": 4.276069194051994e-06,
"loss": 0.0722,
"step": 1430
},
{
"epoch": 2.981874676333506,
"grad_norm": 12.280393600463867,
"learning_rate": 4.2046220397446465e-06,
"loss": 0.0585,
"step": 1440
},
{
"epoch": 3.002071465561885,
"grad_norm": 5.047580718994141,
"learning_rate": 4.133341129552473e-06,
"loss": 0.0645,
"step": 1450
},
{
"epoch": 3.022786121180735,
"grad_norm": 0.9347874522209167,
"learning_rate": 4.0622413620927846e-06,
"loss": 0.0121,
"step": 1460
},
{
"epoch": 3.043500776799586,
"grad_norm": 2.7081985473632812,
"learning_rate": 3.99133759812175e-06,
"loss": 0.0149,
"step": 1470
},
{
"epoch": 3.064215432418436,
"grad_norm": 1.5603258609771729,
"learning_rate": 3.920644657428316e-06,
"loss": 0.0165,
"step": 1480
},
{
"epoch": 3.0849300880372863,
"grad_norm": 9.624794006347656,
"learning_rate": 3.850177315736681e-06,
"loss": 0.0273,
"step": 1490
},
{
"epoch": 3.1056447436561365,
"grad_norm": 0.5304170250892639,
"learning_rate": 3.779950301617984e-06,
"loss": 0.0305,
"step": 1500
},
{
"epoch": 3.126359399274987,
"grad_norm": 5.1905035972595215,
"learning_rate": 3.709978293411839e-06,
"loss": 0.0791,
"step": 1510
},
{
"epoch": 3.1470740548938374,
"grad_norm": 20.78911590576172,
"learning_rate": 3.6402759161583846e-06,
"loss": 0.0283,
"step": 1520
},
{
"epoch": 3.1677887105126876,
"grad_norm": 0.3733516037464142,
"learning_rate": 3.5708577385414495e-06,
"loss": 0.0163,
"step": 1530
},
{
"epoch": 3.1885033661315383,
"grad_norm": 0.5811702013015747,
"learning_rate": 3.5017382698435352e-06,
"loss": 0.0167,
"step": 1540
},
{
"epoch": 3.2092180217503885,
"grad_norm": 3.926090717315674,
"learning_rate": 3.432931956913166e-06,
"loss": 0.0172,
"step": 1550
},
{
"epoch": 3.2299326773692387,
"grad_norm": 0.14650128781795502,
"learning_rate": 3.3644531811453314e-06,
"loss": 0.0029,
"step": 1560
},
{
"epoch": 3.250647332988089,
"grad_norm": 1.0300089120864868,
"learning_rate": 3.296316255475586e-06,
"loss": 0.0099,
"step": 1570
},
{
"epoch": 3.271361988606939,
"grad_norm": 5.851058006286621,
"learning_rate": 3.2285354213884617e-06,
"loss": 0.0109,
"step": 1580
},
{
"epoch": 3.29207664422579,
"grad_norm": 4.821533679962158,
"learning_rate": 3.161124845940822e-06,
"loss": 0.02,
"step": 1590
},
{
"epoch": 3.31279129984464,
"grad_norm": 16.102802276611328,
"learning_rate": 3.094098618800756e-06,
"loss": 0.018,
"step": 1600
},
{
"epoch": 3.3335059554634903,
"grad_norm": 1.8471333980560303,
"learning_rate": 3.0274707493026736e-06,
"loss": 0.0256,
"step": 1610
},
{
"epoch": 3.354220611082341,
"grad_norm": 1.3267815113067627,
"learning_rate": 2.961255163519162e-06,
"loss": 0.0044,
"step": 1620
},
{
"epoch": 3.374935266701191,
"grad_norm": 1.5657950639724731,
"learning_rate": 2.89546570135027e-06,
"loss": 0.0136,
"step": 1630
},
{
"epoch": 3.3956499223200414,
"grad_norm": 6.528173923492432,
"learning_rate": 2.8301161136307864e-06,
"loss": 0.011,
"step": 1640
},
{
"epoch": 3.4163645779388916,
"grad_norm": 2.976943016052246,
"learning_rate": 2.7652200592561417e-06,
"loss": 0.0073,
"step": 1650
},
{
"epoch": 3.4370792335577423,
"grad_norm": 21.593252182006836,
"learning_rate": 2.7007911023275258e-06,
"loss": 0.0415,
"step": 1660
},
{
"epoch": 3.4577938891765925,
"grad_norm": 1.8981424570083618,
"learning_rate": 2.6368427093168235e-06,
"loss": 0.0257,
"step": 1670
},
{
"epoch": 3.4785085447954427,
"grad_norm": 4.041304588317871,
"learning_rate": 2.573388246251938e-06,
"loss": 0.0106,
"step": 1680
},
{
"epoch": 3.499223200414293,
"grad_norm": 2.491007089614868,
"learning_rate": 2.510440975923133e-06,
"loss": 0.0487,
"step": 1690
},
{
"epoch": 3.5199378560331436,
"grad_norm": 1.2121617794036865,
"learning_rate": 2.448014055110933e-06,
"loss": 0.0135,
"step": 1700
},
{
"epoch": 3.540652511651994,
"grad_norm": 9.507610321044922,
"learning_rate": 2.386120531836198e-06,
"loss": 0.0199,
"step": 1710
},
{
"epoch": 3.561367167270844,
"grad_norm": 0.10323593020439148,
"learning_rate": 2.324773342632905e-06,
"loss": 0.0124,
"step": 1720
},
{
"epoch": 3.5820818228896947,
"grad_norm": 11.508368492126465,
"learning_rate": 2.263985309844269e-06,
"loss": 0.0528,
"step": 1730
},
{
"epoch": 3.602796478508545,
"grad_norm": 9.40398120880127,
"learning_rate": 2.2037691389426905e-06,
"loss": 0.021,
"step": 1740
},
{
"epoch": 3.623511134127395,
"grad_norm": 0.310314416885376,
"learning_rate": 2.144137415874162e-06,
"loss": 0.0136,
"step": 1750
},
{
"epoch": 3.6442257897462453,
"grad_norm": 4.971359729766846,
"learning_rate": 2.0851026044276405e-06,
"loss": 0.0108,
"step": 1760
},
{
"epoch": 3.6649404453650956,
"grad_norm": 0.10849104076623917,
"learning_rate": 2.0266770436299577e-06,
"loss": 0.0252,
"step": 1770
},
{
"epoch": 3.685655100983946,
"grad_norm": 0.8350229263305664,
"learning_rate": 1.9688729451668116e-06,
"loss": 0.0247,
"step": 1780
},
{
"epoch": 3.7063697566027964,
"grad_norm": 14.722149848937988,
"learning_rate": 1.9117023908303534e-06,
"loss": 0.0262,
"step": 1790
},
{
"epoch": 3.7270844122216467,
"grad_norm": 2.200244426727295,
"learning_rate": 1.855177329993962e-06,
"loss": 0.0154,
"step": 1800
},
{
"epoch": 3.7477990678404973,
"grad_norm": 0.37544846534729004,
"learning_rate": 1.7993095771146518e-06,
"loss": 0.0141,
"step": 1810
},
{
"epoch": 3.7685137234593475,
"grad_norm": 2.636514663696289,
"learning_rate": 1.7441108092637143e-06,
"loss": 0.0234,
"step": 1820
},
{
"epoch": 3.7892283790781978,
"grad_norm": 0.1407538652420044,
"learning_rate": 1.6895925636860528e-06,
"loss": 0.0214,
"step": 1830
},
{
"epoch": 3.8099430346970484,
"grad_norm": 5.799379825592041,
"learning_rate": 1.635766235388761e-06,
"loss": 0.0128,
"step": 1840
},
{
"epoch": 3.8306576903158986,
"grad_norm": 5.826894283294678,
"learning_rate": 1.582643074759413e-06,
"loss": 0.0126,
"step": 1850
},
{
"epoch": 3.851372345934749,
"grad_norm": 2.7077250480651855,
"learning_rate": 1.530234185214592e-06,
"loss": 0.0384,
"step": 1860
},
{
"epoch": 3.872087001553599,
"grad_norm": 2.6759700775146484,
"learning_rate": 1.4785505208791334e-06,
"loss": 0.0221,
"step": 1870
},
{
"epoch": 3.8928016571724493,
"grad_norm": 2.3276588916778564,
"learning_rate": 1.4276028842965828e-06,
"loss": 0.009,
"step": 1880
},
{
"epoch": 3.9135163127913,
"grad_norm": 8.618206977844238,
"learning_rate": 1.3774019241713077e-06,
"loss": 0.0211,
"step": 1890
},
{
"epoch": 3.93423096841015,
"grad_norm": 3.8968656063079834,
"learning_rate": 1.3279581331428043e-06,
"loss": 0.0304,
"step": 1900
},
{
"epoch": 3.9549456240290004,
"grad_norm": 7.516331195831299,
"learning_rate": 1.2792818455925877e-06,
"loss": 0.029,
"step": 1910
},
{
"epoch": 3.975660279647851,
"grad_norm": 2.9737958908081055,
"learning_rate": 1.2313832354841793e-06,
"loss": 0.0141,
"step": 1920
},
{
"epoch": 3.9963749352667013,
"grad_norm": 8.040321350097656,
"learning_rate": 1.1842723142366197e-06,
"loss": 0.0195,
"step": 1930
},
{
"epoch": 4.016571724495081,
"grad_norm": 0.09274543821811676,
"learning_rate": 1.1379589286319525e-06,
"loss": 0.0033,
"step": 1940
},
{
"epoch": 4.0372863801139305,
"grad_norm": 1.255889892578125,
"learning_rate": 1.0924527587571287e-06,
"loss": 0.0038,
"step": 1950
},
{
"epoch": 4.058001035732781,
"grad_norm": 4.173186779022217,
"learning_rate": 1.0477633159807294e-06,
"loss": 0.0044,
"step": 1960
},
{
"epoch": 4.078715691351631,
"grad_norm": 4.816555023193359,
"learning_rate": 1.003899940964989e-06,
"loss": 0.0043,
"step": 1970
},
{
"epoch": 4.099430346970482,
"grad_norm": 3.484710454940796,
"learning_rate": 9.60871801713462e-07,
"loss": 0.0019,
"step": 1980
},
{
"epoch": 4.120145002589332,
"grad_norm": 0.058790285140275955,
"learning_rate": 9.186878916548025e-07,
"loss": 0.0035,
"step": 1990
},
{
"epoch": 4.140859658208182,
"grad_norm": 6.722171306610107,
"learning_rate": 8.773570277630166e-07,
"loss": 0.0108,
"step": 2000
},
{
"epoch": 4.161574313827033,
"grad_norm": 0.23930205404758453,
"learning_rate": 8.36887848714612e-07,
"loss": 0.0038,
"step": 2010
},
{
"epoch": 4.182288969445883,
"grad_norm": 0.1457829475402832,
"learning_rate": 7.972888130829909e-07,
"loss": 0.0007,
"step": 2020
},
{
"epoch": 4.203003625064733,
"grad_norm": 1.364937424659729,
"learning_rate": 7.585681975705167e-07,
"loss": 0.0082,
"step": 2030
},
{
"epoch": 4.223718280683584,
"grad_norm": 0.6660894751548767,
"learning_rate": 7.207340952785641e-07,
"loss": 0.0033,
"step": 2040
},
{
"epoch": 4.244432936302434,
"grad_norm": 0.8876777291297913,
"learning_rate": 6.837944140159658e-07,
"loss": 0.0033,
"step": 2050
},
{
"epoch": 4.265147591921284,
"grad_norm": 0.07557283341884613,
"learning_rate": 6.477568746461759e-07,
"loss": 0.0024,
"step": 2060
},
{
"epoch": 4.285862247540135,
"grad_norm": 6.100578784942627,
"learning_rate": 6.12629009473516e-07,
"loss": 0.0075,
"step": 2070
},
{
"epoch": 4.306576903158985,
"grad_norm": 0.3430367112159729,
"learning_rate": 5.784181606688211e-07,
"loss": 0.0027,
"step": 2080
},
{
"epoch": 4.327291558777835,
"grad_norm": 0.3723483383655548,
"learning_rate": 5.451314787348377e-07,
"loss": 0.0003,
"step": 2090
},
{
"epoch": 4.348006214396686,
"grad_norm": 0.11818315833806992,
"learning_rate": 5.127759210116751e-07,
"loss": 0.0022,
"step": 2100
},
{
"epoch": 4.368720870015536,
"grad_norm": 0.08157821744680405,
"learning_rate": 4.813582502226349e-07,
"loss": 0.0024,
"step": 2110
},
{
"epoch": 4.389435525634386,
"grad_norm": 0.5331207513809204,
"learning_rate": 4.5088503306071285e-07,
"loss": 0.0009,
"step": 2120
},
{
"epoch": 4.410150181253236,
"grad_norm": 0.28640031814575195,
"learning_rate": 4.2136263881607797e-07,
"loss": 0.0093,
"step": 2130
},
{
"epoch": 4.430864836872087,
"grad_norm": 0.05537045747041702,
"learning_rate": 3.927972380448136e-07,
"loss": 0.0004,
"step": 2140
},
{
"epoch": 4.4515794924909375,
"grad_norm": 0.36031514406204224,
"learning_rate": 3.651948012791845e-07,
"loss": 0.0009,
"step": 2150
},
{
"epoch": 4.472294148109787,
"grad_norm": 0.10676005482673645,
"learning_rate": 3.385610977797271e-07,
"loss": 0.0015,
"step": 2160
},
{
"epoch": 4.493008803728638,
"grad_norm": 0.14938266575336456,
"learning_rate": 3.1290169432939556e-07,
"loss": 0.0053,
"step": 2170
},
{
"epoch": 4.513723459347489,
"grad_norm": 10.720261573791504,
"learning_rate": 2.8822195407003815e-07,
"loss": 0.0035,
"step": 2180
},
{
"epoch": 4.534438114966338,
"grad_norm": 0.20982854068279266,
"learning_rate": 2.6452703538142555e-07,
"loss": 0.0062,
"step": 2190
},
{
"epoch": 4.555152770585189,
"grad_norm": 0.2586657404899597,
"learning_rate": 2.418218908030928e-07,
"loss": 0.0035,
"step": 2200
},
{
"epoch": 4.57586742620404,
"grad_norm": 0.3067372143268585,
"learning_rate": 2.2011126599918774e-07,
"loss": 0.0014,
"step": 2210
},
{
"epoch": 4.5965820818228895,
"grad_norm": 1.1566280126571655,
"learning_rate": 1.9939969876656973e-07,
"loss": 0.0021,
"step": 2220
},
{
"epoch": 4.61729673744174,
"grad_norm": 0.019078951328992844,
"learning_rate": 1.7969151808635233e-07,
"loss": 0.0007,
"step": 2230
},
{
"epoch": 4.638011393060591,
"grad_norm": 0.14642347395420074,
"learning_rate": 1.6099084321909264e-07,
"loss": 0.0048,
"step": 2240
},
{
"epoch": 4.658726048679441,
"grad_norm": 0.1196139007806778,
"learning_rate": 1.433015828438117e-07,
"loss": 0.0009,
"step": 2250
},
{
"epoch": 4.679440704298291,
"grad_norm": 0.5198209881782532,
"learning_rate": 1.2662743424102897e-07,
"loss": 0.0028,
"step": 2260
},
{
"epoch": 4.700155359917141,
"grad_norm": 7.20904016494751,
"learning_rate": 1.1097188251998792e-07,
"loss": 0.0113,
"step": 2270
},
{
"epoch": 4.720870015535992,
"grad_norm": 0.07779161632061005,
"learning_rate": 9.633819989022075e-08,
"loss": 0.0024,
"step": 2280
},
{
"epoch": 4.741584671154842,
"grad_norm": 0.4231589734554291,
"learning_rate": 8.27294449776167e-08,
"loss": 0.0051,
"step": 2290
},
{
"epoch": 4.762299326773692,
"grad_norm": 0.312343567609787,
"learning_rate": 7.014846218512783e-08,
"loss": 0.0015,
"step": 2300
},
{
"epoch": 4.783013982392543,
"grad_norm": 0.02143513597548008,
"learning_rate": 5.8597881098257924e-08,
"loss": 0.002,
"step": 2310
},
{
"epoch": 4.803728638011393,
"grad_norm": 2.8307344913482666,
"learning_rate": 4.80801159354366e-08,
"loss": 0.0013,
"step": 2320
},
{
"epoch": 4.824443293630243,
"grad_norm": 0.02532910369336605,
"learning_rate": 3.859736504342793e-08,
"loss": 0.0075,
"step": 2330
},
{
"epoch": 4.845157949249094,
"grad_norm": 1.2010622024536133,
"learning_rate": 3.015161043783854e-08,
"loss": 0.0014,
"step": 2340
},
{
"epoch": 4.865872604867944,
"grad_norm": 0.1263585388660431,
"learning_rate": 2.274461738885625e-08,
"loss": 0.02,
"step": 2350
},
{
"epoch": 4.886587260486794,
"grad_norm": 0.058176904916763306,
"learning_rate": 1.637793405228627e-08,
"loss": 0.0011,
"step": 2360
},
{
"epoch": 4.907301916105645,
"grad_norm": 1.3870699405670166,
"learning_rate": 1.1052891145963419e-08,
"loss": 0.0019,
"step": 2370
},
{
"epoch": 4.928016571724495,
"grad_norm": 0.031831249594688416,
"learning_rate": 6.770601671618471e-09,
"loss": 0.0039,
"step": 2380
},
{
"epoch": 4.9487312273433455,
"grad_norm": 0.8557251691818237,
"learning_rate": 3.5319606822453723e-09,
"loss": 0.0062,
"step": 2390
},
{
"epoch": 4.969445882962196,
"grad_norm": 0.17696042358875275,
"learning_rate": 1.337645095023654e-09,
"loss": 0.0034,
"step": 2400
},
{
"epoch": 4.990160538581046,
"grad_norm": 0.02319159172475338,
"learning_rate": 1.881135498349451e-10,
"loss": 0.005,
"step": 2410
}
],
"logging_steps": 10,
"max_steps": 2415,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 1.344014205321216e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}