gpt2-cpt-wiki / trainer_state.json
ahmedalhammadi's picture
Model save
17fd767 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 865,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0011560693641618498,
"grad_norm": 2.560949806695945,
"learning_rate": 2.2988505747126437e-06,
"loss": 3.4668,
"step": 1
},
{
"epoch": 0.005780346820809248,
"grad_norm": 2.6052409820203866,
"learning_rate": 1.1494252873563218e-05,
"loss": 3.5049,
"step": 5
},
{
"epoch": 0.011560693641618497,
"grad_norm": 1.6807278319503598,
"learning_rate": 2.2988505747126437e-05,
"loss": 3.4523,
"step": 10
},
{
"epoch": 0.017341040462427744,
"grad_norm": 1.3872646318135757,
"learning_rate": 3.4482758620689657e-05,
"loss": 3.4305,
"step": 15
},
{
"epoch": 0.023121387283236993,
"grad_norm": 0.8854199637857243,
"learning_rate": 4.597701149425287e-05,
"loss": 3.3984,
"step": 20
},
{
"epoch": 0.028901734104046242,
"grad_norm": 1.1428954815654415,
"learning_rate": 5.747126436781609e-05,
"loss": 3.3641,
"step": 25
},
{
"epoch": 0.03468208092485549,
"grad_norm": 0.7871424143353113,
"learning_rate": 6.896551724137931e-05,
"loss": 3.3285,
"step": 30
},
{
"epoch": 0.04046242774566474,
"grad_norm": 0.6942416545211347,
"learning_rate": 8.045977011494253e-05,
"loss": 3.3348,
"step": 35
},
{
"epoch": 0.046242774566473986,
"grad_norm": 0.7481862396744489,
"learning_rate": 9.195402298850575e-05,
"loss": 3.3031,
"step": 40
},
{
"epoch": 0.05202312138728324,
"grad_norm": 0.7349744692819005,
"learning_rate": 0.00010344827586206898,
"loss": 3.3055,
"step": 45
},
{
"epoch": 0.057803468208092484,
"grad_norm": 0.787528126925392,
"learning_rate": 0.00011494252873563218,
"loss": 3.266,
"step": 50
},
{
"epoch": 0.06358381502890173,
"grad_norm": 0.6011067877083208,
"learning_rate": 0.0001264367816091954,
"loss": 3.2738,
"step": 55
},
{
"epoch": 0.06936416184971098,
"grad_norm": 0.549726888731836,
"learning_rate": 0.00013793103448275863,
"loss": 3.252,
"step": 60
},
{
"epoch": 0.07514450867052024,
"grad_norm": 0.4802594608855168,
"learning_rate": 0.00014942528735632183,
"loss": 3.2551,
"step": 65
},
{
"epoch": 0.08092485549132948,
"grad_norm": 0.43506119404453325,
"learning_rate": 0.00016091954022988506,
"loss": 3.2531,
"step": 70
},
{
"epoch": 0.08670520231213873,
"grad_norm": 0.43739695740996304,
"learning_rate": 0.00017241379310344826,
"loss": 3.2492,
"step": 75
},
{
"epoch": 0.09248554913294797,
"grad_norm": 0.4001379123552416,
"learning_rate": 0.0001839080459770115,
"loss": 3.2371,
"step": 80
},
{
"epoch": 0.09826589595375723,
"grad_norm": 0.3953084727624265,
"learning_rate": 0.00019540229885057472,
"loss": 3.2332,
"step": 85
},
{
"epoch": 0.10404624277456648,
"grad_norm": 0.39141010946909405,
"learning_rate": 0.00019999266250608563,
"loss": 3.2234,
"step": 90
},
{
"epoch": 0.10982658959537572,
"grad_norm": 0.3844664555693112,
"learning_rate": 0.00019994782616487538,
"loss": 3.2328,
"step": 95
},
{
"epoch": 0.11560693641618497,
"grad_norm": 0.38501166250330954,
"learning_rate": 0.00019986224812243038,
"loss": 3.2289,
"step": 100
},
{
"epoch": 0.12138728323699421,
"grad_norm": 0.367871059973961,
"learning_rate": 0.00019973596326290137,
"loss": 3.2289,
"step": 105
},
{
"epoch": 0.12716763005780346,
"grad_norm": 0.3652422215592574,
"learning_rate": 0.00019956902306374636,
"loss": 3.2293,
"step": 110
},
{
"epoch": 0.1329479768786127,
"grad_norm": 0.37757220530617325,
"learning_rate": 0.00019936149557474666,
"loss": 3.2363,
"step": 115
},
{
"epoch": 0.13872832369942195,
"grad_norm": 0.3718158923309793,
"learning_rate": 0.00019911346539026794,
"loss": 3.2098,
"step": 120
},
{
"epoch": 0.14450867052023122,
"grad_norm": 0.36307234840760944,
"learning_rate": 0.00019882503361477705,
"loss": 3.2133,
"step": 125
},
{
"epoch": 0.15028901734104047,
"grad_norm": 0.36600016095606147,
"learning_rate": 0.0001984963178216287,
"loss": 3.2086,
"step": 130
},
{
"epoch": 0.15606936416184972,
"grad_norm": 0.3476602101989908,
"learning_rate": 0.00019812745200513927,
"loss": 3.218,
"step": 135
},
{
"epoch": 0.16184971098265896,
"grad_norm": 0.34906685233203877,
"learning_rate": 0.00019771858652596657,
"loss": 3.2246,
"step": 140
},
{
"epoch": 0.1676300578034682,
"grad_norm": 0.3532865591665223,
"learning_rate": 0.00019726988804981844,
"loss": 3.1898,
"step": 145
},
{
"epoch": 0.17341040462427745,
"grad_norm": 0.40460405755243584,
"learning_rate": 0.00019678153947951497,
"loss": 3.218,
"step": 150
},
{
"epoch": 0.1791907514450867,
"grad_norm": 0.3304140989868754,
"learning_rate": 0.00019625373988043165,
"loss": 3.1992,
"step": 155
},
{
"epoch": 0.18497109826589594,
"grad_norm": 0.308497812696352,
"learning_rate": 0.00019568670439935458,
"loss": 3.209,
"step": 160
},
{
"epoch": 0.1907514450867052,
"grad_norm": 0.34528327664611236,
"learning_rate": 0.00019508066417678018,
"loss": 3.1914,
"step": 165
},
{
"epoch": 0.19653179190751446,
"grad_norm": 0.4165583915689433,
"learning_rate": 0.00019443586625269562,
"loss": 3.1977,
"step": 170
},
{
"epoch": 0.2023121387283237,
"grad_norm": 0.3650545500594017,
"learning_rate": 0.00019375257346587773,
"loss": 3.1801,
"step": 175
},
{
"epoch": 0.20809248554913296,
"grad_norm": 0.33959159442022663,
"learning_rate": 0.00019303106434675224,
"loss": 3.1965,
"step": 180
},
{
"epoch": 0.2138728323699422,
"grad_norm": 0.3590182979681496,
"learning_rate": 0.00019227163300385662,
"loss": 3.1719,
"step": 185
},
{
"epoch": 0.21965317919075145,
"grad_norm": 0.41052957903807297,
"learning_rate": 0.00019147458900395245,
"loss": 3.1926,
"step": 190
},
{
"epoch": 0.2254335260115607,
"grad_norm": 0.3794250436125987,
"learning_rate": 0.0001906402572458371,
"loss": 3.2074,
"step": 195
},
{
"epoch": 0.23121387283236994,
"grad_norm": 0.3198984083774458,
"learning_rate": 0.00018976897782790512,
"loss": 3.1859,
"step": 200
},
{
"epoch": 0.23699421965317918,
"grad_norm": 0.3163734942392586,
"learning_rate": 0.00018886110590951417,
"loss": 3.2047,
"step": 205
},
{
"epoch": 0.24277456647398843,
"grad_norm": 0.31805084628607355,
"learning_rate": 0.0001879170115662114,
"loss": 3.1871,
"step": 210
},
{
"epoch": 0.24855491329479767,
"grad_norm": 0.3432486403670197,
"learning_rate": 0.00018693707963887978,
"loss": 3.175,
"step": 215
},
{
"epoch": 0.2543352601156069,
"grad_norm": 0.3138776566225917,
"learning_rate": 0.00018592170957686552,
"loss": 3.1988,
"step": 220
},
{
"epoch": 0.26011560693641617,
"grad_norm": 0.30587921809108115,
"learning_rate": 0.0001848713152751506,
"loss": 3.1762,
"step": 225
},
{
"epoch": 0.2658959537572254,
"grad_norm": 0.2997567171818308,
"learning_rate": 0.0001837863249056369,
"loss": 3.2027,
"step": 230
},
{
"epoch": 0.27167630057803466,
"grad_norm": 0.335691454347307,
"learning_rate": 0.00018266718074261062,
"loss": 3.1688,
"step": 235
},
{
"epoch": 0.2774566473988439,
"grad_norm": 0.3307527141328154,
"learning_rate": 0.00018151433898245826,
"loss": 3.1766,
"step": 240
},
{
"epoch": 0.2832369942196532,
"grad_norm": 0.3141072784060351,
"learning_rate": 0.00018032826955770724,
"loss": 3.173,
"step": 245
},
{
"epoch": 0.28901734104046245,
"grad_norm": 0.4424843940179431,
"learning_rate": 0.00017910945594546757,
"loss": 3.1637,
"step": 250
},
{
"epoch": 0.2947976878612717,
"grad_norm": 0.30077059480155643,
"learning_rate": 0.00017785839497035222,
"loss": 3.1809,
"step": 255
},
{
"epoch": 0.30057803468208094,
"grad_norm": 0.31634582525373184,
"learning_rate": 0.0001765755966019566,
"loss": 3.1828,
"step": 260
},
{
"epoch": 0.3063583815028902,
"grad_norm": 0.29644760955094585,
"learning_rate": 0.00017526158374698,
"loss": 3.1691,
"step": 265
},
{
"epoch": 0.31213872832369943,
"grad_norm": 0.29157149074265853,
"learning_rate": 0.0001739168920360729,
"loss": 3.1512,
"step": 270
},
{
"epoch": 0.3179190751445087,
"grad_norm": 0.30009452294520444,
"learning_rate": 0.00017254206960549842,
"loss": 3.1816,
"step": 275
},
{
"epoch": 0.3236994219653179,
"grad_norm": 0.349631013624792,
"learning_rate": 0.0001711376768736956,
"loss": 3.1547,
"step": 280
},
{
"epoch": 0.32947976878612717,
"grad_norm": 0.33261830331078257,
"learning_rate": 0.000169704286312836,
"loss": 3.1684,
"step": 285
},
{
"epoch": 0.3352601156069364,
"grad_norm": 0.29085302891804077,
"learning_rate": 0.00016824248221546735,
"loss": 3.1492,
"step": 290
},
{
"epoch": 0.34104046242774566,
"grad_norm": 0.30061007694463854,
"learning_rate": 0.00016675286045633828,
"loss": 3.143,
"step": 295
},
{
"epoch": 0.3468208092485549,
"grad_norm": 0.4170871249784612,
"learning_rate": 0.00016523602824950235,
"loss": 3.1484,
"step": 300
},
{
"epoch": 0.35260115606936415,
"grad_norm": 0.2819705568636163,
"learning_rate": 0.00016369260390079933,
"loss": 3.1379,
"step": 305
},
{
"epoch": 0.3583815028901734,
"grad_norm": 0.28557604100223866,
"learning_rate": 0.00016212321655581554,
"loss": 3.1453,
"step": 310
},
{
"epoch": 0.36416184971098264,
"grad_norm": 0.29258283786258643,
"learning_rate": 0.00016052850594342534,
"loss": 3.1465,
"step": 315
},
{
"epoch": 0.3699421965317919,
"grad_norm": 0.41981326824430054,
"learning_rate": 0.00015890912211501877,
"loss": 3.1355,
"step": 320
},
{
"epoch": 0.37572254335260113,
"grad_norm": 0.27912148893790856,
"learning_rate": 0.00015726572517952122,
"loss": 3.1457,
"step": 325
},
{
"epoch": 0.3815028901734104,
"grad_norm": 0.33056252135761416,
"learning_rate": 0.00015559898503431335,
"loss": 3.1422,
"step": 330
},
{
"epoch": 0.3872832369942196,
"grad_norm": 0.3051613612126159,
"learning_rate": 0.0001539095810921612,
"loss": 3.159,
"step": 335
},
{
"epoch": 0.3930635838150289,
"grad_norm": 0.2838497459947755,
"learning_rate": 0.00015219820200426727,
"loss": 3.1469,
"step": 340
},
{
"epoch": 0.3988439306358382,
"grad_norm": 0.31465121621009734,
"learning_rate": 0.00015046554537955585,
"loss": 3.1395,
"step": 345
},
{
"epoch": 0.4046242774566474,
"grad_norm": 0.33199154940321435,
"learning_rate": 0.00014871231750030698,
"loss": 3.1535,
"step": 350
},
{
"epoch": 0.41040462427745666,
"grad_norm": 0.2789325679223692,
"learning_rate": 0.0001469392330342548,
"loss": 3.1359,
"step": 355
},
{
"epoch": 0.4161849710982659,
"grad_norm": 0.26987258223987126,
"learning_rate": 0.0001451470147432676,
"loss": 3.1238,
"step": 360
},
{
"epoch": 0.42196531791907516,
"grad_norm": 0.3824587738393317,
"learning_rate": 0.0001433363931887289,
"loss": 3.1187,
"step": 365
},
{
"epoch": 0.4277456647398844,
"grad_norm": 0.31988281654092277,
"learning_rate": 0.0001415081064337388,
"loss": 3.1285,
"step": 370
},
{
"epoch": 0.43352601156069365,
"grad_norm": 0.30612731851250463,
"learning_rate": 0.0001396628997422575,
"loss": 3.1437,
"step": 375
},
{
"epoch": 0.4393063583815029,
"grad_norm": 0.28986666743465456,
"learning_rate": 0.00013780152527531362,
"loss": 3.1352,
"step": 380
},
{
"epoch": 0.44508670520231214,
"grad_norm": 0.31394710597647135,
"learning_rate": 0.00013592474178440115,
"loss": 3.1621,
"step": 385
},
{
"epoch": 0.4508670520231214,
"grad_norm": 0.4294903312732592,
"learning_rate": 0.00013403331430218964,
"loss": 3.1426,
"step": 390
},
{
"epoch": 0.45664739884393063,
"grad_norm": 0.4265226280273843,
"learning_rate": 0.0001321280138306743,
"loss": 3.134,
"step": 395
},
{
"epoch": 0.4624277456647399,
"grad_norm": 0.38492594733609664,
"learning_rate": 0.0001302096170268926,
"loss": 3.1453,
"step": 400
},
{
"epoch": 0.4682080924855491,
"grad_norm": 0.29848798247224545,
"learning_rate": 0.0001282789058863359,
"loss": 3.1445,
"step": 405
},
{
"epoch": 0.47398843930635837,
"grad_norm": 0.3447604928374673,
"learning_rate": 0.0001263366674241847,
"loss": 3.1395,
"step": 410
},
{
"epoch": 0.4797687861271676,
"grad_norm": 0.3080929535135385,
"learning_rate": 0.0001243836933544982,
"loss": 3.1324,
"step": 415
},
{
"epoch": 0.48554913294797686,
"grad_norm": 0.314220865898827,
"learning_rate": 0.00012242077976748784,
"loss": 3.1301,
"step": 420
},
{
"epoch": 0.4913294797687861,
"grad_norm": 0.28685031067517336,
"learning_rate": 0.00012044872680500742,
"loss": 3.1313,
"step": 425
},
{
"epoch": 0.49710982658959535,
"grad_norm": 0.2956236061720464,
"learning_rate": 0.00011846833833439153,
"loss": 3.1348,
"step": 430
},
{
"epoch": 0.5028901734104047,
"grad_norm": 0.30651808915001155,
"learning_rate": 0.00011648042162077534,
"loss": 3.152,
"step": 435
},
{
"epoch": 0.5086705202312138,
"grad_norm": 0.4239949281706778,
"learning_rate": 0.00011448578699802933,
"loss": 3.1437,
"step": 440
},
{
"epoch": 0.5144508670520231,
"grad_norm": 0.27791759340010475,
"learning_rate": 0.00011248524753844325,
"loss": 3.1504,
"step": 445
},
{
"epoch": 0.5202312138728323,
"grad_norm": 0.3326391549276525,
"learning_rate": 0.00011047961872129362,
"loss": 3.1398,
"step": 450
},
{
"epoch": 0.5260115606936416,
"grad_norm": 0.3999790516242622,
"learning_rate": 0.00010846971810043016,
"loss": 3.1383,
"step": 455
},
{
"epoch": 0.5317919075144508,
"grad_norm": 0.36328178971277675,
"learning_rate": 0.00010645636497101672,
"loss": 3.1367,
"step": 460
},
{
"epoch": 0.5375722543352601,
"grad_norm": 0.30511312613079056,
"learning_rate": 0.000104440380035562,
"loss": 3.1348,
"step": 465
},
{
"epoch": 0.5433526011560693,
"grad_norm": 0.34508796373702927,
"learning_rate": 0.00010242258506937705,
"loss": 3.1273,
"step": 470
},
{
"epoch": 0.5491329479768786,
"grad_norm": 0.31298227959915587,
"learning_rate": 0.00010040380258559519,
"loss": 3.1055,
"step": 475
},
{
"epoch": 0.5549132947976878,
"grad_norm": 0.41126045157836544,
"learning_rate": 9.838485549989117e-05,
"loss": 3.1391,
"step": 480
},
{
"epoch": 0.5606936416184971,
"grad_norm": 0.31695235717793374,
"learning_rate": 9.636656679503647e-05,
"loss": 3.1027,
"step": 485
},
{
"epoch": 0.5664739884393064,
"grad_norm": 0.31731839716923793,
"learning_rate": 9.434975918542687e-05,
"loss": 3.1238,
"step": 490
},
{
"epoch": 0.5722543352601156,
"grad_norm": 0.30368775602371734,
"learning_rate": 9.233525478171985e-05,
"loss": 3.1328,
"step": 495
},
{
"epoch": 0.5780346820809249,
"grad_norm": 0.27566250598377473,
"learning_rate": 9.032387475571771e-05,
"loss": 3.1234,
"step": 500
},
{
"epoch": 0.5838150289017341,
"grad_norm": 0.42121488462702394,
"learning_rate": 8.831643900563372e-05,
"loss": 3.1527,
"step": 505
},
{
"epoch": 0.5895953757225434,
"grad_norm": 0.2983160621346518,
"learning_rate": 8.631376582187716e-05,
"loss": 3.1313,
"step": 510
},
{
"epoch": 0.5953757225433526,
"grad_norm": 0.383836042501806,
"learning_rate": 8.431667155349381e-05,
"loss": 3.125,
"step": 515
},
{
"epoch": 0.6011560693641619,
"grad_norm": 0.2946728067863111,
"learning_rate": 8.232597027539804e-05,
"loss": 3.1203,
"step": 520
},
{
"epoch": 0.6069364161849711,
"grad_norm": 0.40035002509511697,
"learning_rate": 8.034247345653148e-05,
"loss": 3.127,
"step": 525
},
{
"epoch": 0.6127167630057804,
"grad_norm": 0.30571803221597543,
"learning_rate": 7.836698962908432e-05,
"loss": 3.1051,
"step": 530
},
{
"epoch": 0.6184971098265896,
"grad_norm": 0.39524647237789706,
"learning_rate": 7.64003240589136e-05,
"loss": 3.1172,
"step": 535
},
{
"epoch": 0.6242774566473989,
"grad_norm": 0.28648345450162954,
"learning_rate": 7.444327841729282e-05,
"loss": 3.1266,
"step": 540
},
{
"epoch": 0.630057803468208,
"grad_norm": 0.28535372587420343,
"learning_rate": 7.249665045412703e-05,
"loss": 3.1211,
"step": 545
},
{
"epoch": 0.6358381502890174,
"grad_norm": 0.30735493866888736,
"learning_rate": 7.056123367276628e-05,
"loss": 3.1113,
"step": 550
},
{
"epoch": 0.6416184971098265,
"grad_norm": 0.35113611863875976,
"learning_rate": 6.863781700655011e-05,
"loss": 3.1145,
"step": 555
},
{
"epoch": 0.6473988439306358,
"grad_norm": 0.301896935911015,
"learning_rate": 6.67271844972147e-05,
"loss": 3.1109,
"step": 560
},
{
"epoch": 0.653179190751445,
"grad_norm": 0.2835016675616311,
"learning_rate": 6.483011497529456e-05,
"loss": 3.123,
"step": 565
},
{
"epoch": 0.6589595375722543,
"grad_norm": 0.3511471847470862,
"learning_rate": 6.29473817426477e-05,
"loss": 3.1207,
"step": 570
},
{
"epoch": 0.6647398843930635,
"grad_norm": 0.34719951816291245,
"learning_rate": 6.107975225723506e-05,
"loss": 3.1078,
"step": 575
},
{
"epoch": 0.6705202312138728,
"grad_norm": 0.32389493095679567,
"learning_rate": 5.922798782028186e-05,
"loss": 3.1172,
"step": 580
},
{
"epoch": 0.6763005780346821,
"grad_norm": 0.27935241278493833,
"learning_rate": 5.7392843265948445e-05,
"loss": 3.1367,
"step": 585
},
{
"epoch": 0.6820809248554913,
"grad_norm": 0.335471823945162,
"learning_rate": 5.5575066653637696e-05,
"loss": 3.1301,
"step": 590
},
{
"epoch": 0.6878612716763006,
"grad_norm": 0.28742846706476527,
"learning_rate": 5.377539896306363e-05,
"loss": 3.1074,
"step": 595
},
{
"epoch": 0.6936416184971098,
"grad_norm": 0.28846880995197993,
"learning_rate": 5.1994573792206156e-05,
"loss": 3.1301,
"step": 600
},
{
"epoch": 0.6994219653179191,
"grad_norm": 0.29195100089253184,
"learning_rate": 5.023331705827477e-05,
"loss": 3.1313,
"step": 605
},
{
"epoch": 0.7052023121387283,
"grad_norm": 0.31669385047045495,
"learning_rate": 4.8492346701803045e-05,
"loss": 3.1184,
"step": 610
},
{
"epoch": 0.7109826589595376,
"grad_norm": 0.28758180372925923,
"learning_rate": 4.677237239399489e-05,
"loss": 3.1281,
"step": 615
},
{
"epoch": 0.7167630057803468,
"grad_norm": 0.306876835225927,
"learning_rate": 4.507409524744151e-05,
"loss": 3.1086,
"step": 620
},
{
"epoch": 0.7225433526011561,
"grad_norm": 0.27410867188213767,
"learning_rate": 4.3398207530326915e-05,
"loss": 3.1129,
"step": 625
},
{
"epoch": 0.7283236994219653,
"grad_norm": 0.3366702488484758,
"learning_rate": 4.174539238423898e-05,
"loss": 3.1289,
"step": 630
},
{
"epoch": 0.7341040462427746,
"grad_norm": 0.2863969178824916,
"learning_rate": 4.0116323545700675e-05,
"loss": 3.1238,
"step": 635
},
{
"epoch": 0.7398843930635838,
"grad_norm": 0.3097945079410788,
"learning_rate": 3.8511665071535e-05,
"loss": 3.1031,
"step": 640
},
{
"epoch": 0.7456647398843931,
"grad_norm": 0.4123766504987303,
"learning_rate": 3.69320710681758e-05,
"loss": 3.1023,
"step": 645
},
{
"epoch": 0.7514450867052023,
"grad_norm": 0.3361752903628251,
"learning_rate": 3.537818542503443e-05,
"loss": 3.1113,
"step": 650
},
{
"epoch": 0.7572254335260116,
"grad_norm": 0.3077676593416445,
"learning_rate": 3.385064155203138e-05,
"loss": 3.1105,
"step": 655
},
{
"epoch": 0.7630057803468208,
"grad_norm": 0.2712348329777666,
"learning_rate": 3.2350062121399625e-05,
"loss": 3.1105,
"step": 660
},
{
"epoch": 0.7687861271676301,
"grad_norm": 0.29913041418922676,
"learning_rate": 3.087705881386486e-05,
"loss": 3.1219,
"step": 665
},
{
"epoch": 0.7745664739884393,
"grad_norm": 0.31812764724536047,
"learning_rate": 2.943223206930632e-05,
"loss": 3.1168,
"step": 670
},
{
"epoch": 0.7803468208092486,
"grad_norm": 0.35329118193515613,
"learning_rate": 2.8016170841999667e-05,
"loss": 3.109,
"step": 675
},
{
"epoch": 0.7861271676300579,
"grad_norm": 0.2990508230174604,
"learning_rate": 2.662945236054176e-05,
"loss": 3.1066,
"step": 680
},
{
"epoch": 0.791907514450867,
"grad_norm": 0.2863986880007164,
"learning_rate": 2.527264189255507e-05,
"loss": 3.1164,
"step": 685
},
{
"epoch": 0.7976878612716763,
"grad_norm": 0.30694277766185385,
"learning_rate": 2.3946292514267854e-05,
"loss": 3.1113,
"step": 690
},
{
"epoch": 0.8034682080924855,
"grad_norm": 0.3777893533757732,
"learning_rate": 2.2650944885063897e-05,
"loss": 3.1035,
"step": 695
},
{
"epoch": 0.8092485549132948,
"grad_norm": 0.30405287841305245,
"learning_rate": 2.138712702709359e-05,
"loss": 3.0957,
"step": 700
},
{
"epoch": 0.815028901734104,
"grad_norm": 0.3025648475201123,
"learning_rate": 2.0155354110036604e-05,
"loss": 3.1332,
"step": 705
},
{
"epoch": 0.8208092485549133,
"grad_norm": 0.2921917075952636,
"learning_rate": 1.89561282411033e-05,
"loss": 3.0969,
"step": 710
},
{
"epoch": 0.8265895953757225,
"grad_norm": 0.2951570047218817,
"learning_rate": 1.7789938260360904e-05,
"loss": 3.1125,
"step": 715
},
{
"epoch": 0.8323699421965318,
"grad_norm": 0.2941996616491899,
"learning_rate": 1.6657259541467883e-05,
"loss": 3.1,
"step": 720
},
{
"epoch": 0.838150289017341,
"grad_norm": 0.3422952891961912,
"learning_rate": 1.555855379789747e-05,
"loss": 3.0969,
"step": 725
},
{
"epoch": 0.8439306358381503,
"grad_norm": 0.29026242169978395,
"learning_rate": 1.4494268894729546e-05,
"loss": 3.1117,
"step": 730
},
{
"epoch": 0.8497109826589595,
"grad_norm": 0.41808268263107873,
"learning_rate": 1.346483866608751e-05,
"loss": 3.1078,
"step": 735
},
{
"epoch": 0.8554913294797688,
"grad_norm": 0.5577954106464427,
"learning_rate": 1.2470682738294737e-05,
"loss": 3.1344,
"step": 740
},
{
"epoch": 0.861271676300578,
"grad_norm": 0.34387551123301874,
"learning_rate": 1.1512206358822263e-05,
"loss": 3.1223,
"step": 745
},
{
"epoch": 0.8670520231213873,
"grad_norm": 0.3706950879303699,
"learning_rate": 1.058980023109798e-05,
"loss": 3.1148,
"step": 750
},
{
"epoch": 0.8728323699421965,
"grad_norm": 0.558405963959258,
"learning_rate": 9.703840355244286e-06,
"loss": 3.1094,
"step": 755
},
{
"epoch": 0.8786127167630058,
"grad_norm": 0.38255385526130775,
"learning_rate": 8.85468787480932e-06,
"loss": 3.1078,
"step": 760
},
{
"epoch": 0.884393063583815,
"grad_norm": 0.36369947881012377,
"learning_rate": 8.042688929554076e-06,
"loss": 3.1289,
"step": 765
},
{
"epoch": 0.8901734104046243,
"grad_norm": 0.35939189858543064,
"learning_rate": 7.268174514355564e-06,
"loss": 3.0895,
"step": 770
},
{
"epoch": 0.8959537572254336,
"grad_norm": 0.28406418416514867,
"learning_rate": 6.531460344283513e-06,
"loss": 3.1125,
"step": 775
},
{
"epoch": 0.9017341040462428,
"grad_norm": 0.7961530349923809,
"learning_rate": 5.832846725905506e-06,
"loss": 3.1148,
"step": 780
},
{
"epoch": 0.9075144508670521,
"grad_norm": 0.31387781257967007,
"learning_rate": 5.172618434873111e-06,
"loss": 3.1273,
"step": 785
},
{
"epoch": 0.9132947976878613,
"grad_norm": 0.35418591354001977,
"learning_rate": 4.5510445998388386e-06,
"loss": 3.1059,
"step": 790
},
{
"epoch": 0.9190751445086706,
"grad_norm": 0.31552685028654576,
"learning_rate": 3.968378592751398e-06,
"loss": 3.1219,
"step": 795
},
{
"epoch": 0.9248554913294798,
"grad_norm": 0.381623143871843,
"learning_rate": 3.424857925573699e-06,
"loss": 3.1105,
"step": 800
},
{
"epoch": 0.930635838150289,
"grad_norm": 0.3259845681670356,
"learning_rate": 2.9207041534659363e-06,
"loss": 3.0871,
"step": 805
},
{
"epoch": 0.9364161849710982,
"grad_norm": 0.30145173604175796,
"learning_rate": 2.4561227844731138e-06,
"loss": 3.118,
"step": 810
},
{
"epoch": 0.9421965317919075,
"grad_norm": 0.3337714000115938,
"learning_rate": 2.0313031957539197e-06,
"loss": 3.102,
"step": 815
},
{
"epoch": 0.9479768786127167,
"grad_norm": 0.30245031915454157,
"learning_rate": 1.646418556384921e-06,
"loss": 3.0863,
"step": 820
},
{
"epoch": 0.953757225433526,
"grad_norm": 0.29912565847350114,
"learning_rate": 1.3016257567717294e-06,
"loss": 3.1043,
"step": 825
},
{
"epoch": 0.9595375722543352,
"grad_norm": 0.31262691952047295,
"learning_rate": 9.970653446958134e-07,
"loss": 3.1074,
"step": 830
},
{
"epoch": 0.9653179190751445,
"grad_norm": 0.3748247921614159,
"learning_rate": 7.328614680230495e-07,
"loss": 3.0965,
"step": 835
},
{
"epoch": 0.9710982658959537,
"grad_norm": 0.30960477476352033,
"learning_rate": 5.091218240973472e-07,
"loss": 3.0949,
"step": 840
},
{
"epoch": 0.976878612716763,
"grad_norm": 0.3368057888691073,
"learning_rate": 3.259376158400329e-07,
"loss": 3.1063,
"step": 845
},
{
"epoch": 0.9826589595375722,
"grad_norm": 0.29119253652160076,
"learning_rate": 1.8338351457284352e-07,
"loss": 3.1402,
"step": 850
},
{
"epoch": 0.9884393063583815,
"grad_norm": 0.310724087204439,
"learning_rate": 8.15176295796638e-08,
"loss": 3.1078,
"step": 855
},
{
"epoch": 0.9942196531791907,
"grad_norm": 0.3151737727878063,
"learning_rate": 2.0381484419451646e-08,
"loss": 3.0969,
"step": 860
},
{
"epoch": 1.0,
"grad_norm": 0.33281701073497355,
"learning_rate": 0.0,
"loss": 3.1109,
"step": 865
},
{
"epoch": 1.0,
"step": 865,
"total_flos": 82545915985920.0,
"train_loss": 3.1589166365606935,
"train_runtime": 248.1689,
"train_samples_per_second": 445.922,
"train_steps_per_second": 3.486
}
],
"logging_steps": 5,
"max_steps": 865,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 82545915985920.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}