final_m2m100 / trainer_state.json
bishaltwr's picture
Upload 13 files
a8bf27e verified
{
"best_metric": 0.24187567830085754,
"best_model_checkpoint": "./results\\checkpoint-150000",
"epoch": 5.318552300921432,
"eval_steps": 10000,
"global_step": 200000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013296281030195855,
"grad_norm": 1.8945389986038208,
"learning_rate": 1.9986783320923308e-05,
"loss": 2.1575,
"step": 500
},
{
"epoch": 0.02659256206039171,
"grad_norm": 1.8132811784744263,
"learning_rate": 1.997348686309967e-05,
"loss": 0.6486,
"step": 1000
},
{
"epoch": 0.039888843090587565,
"grad_norm": 1.9245736598968506,
"learning_rate": 1.9960190405276038e-05,
"loss": 0.6164,
"step": 1500
},
{
"epoch": 0.05318512412078342,
"grad_norm": 1.4257850646972656,
"learning_rate": 1.99468939474524e-05,
"loss": 0.6067,
"step": 2000
},
{
"epoch": 0.06648140515097926,
"grad_norm": 1.434894323348999,
"learning_rate": 1.9933597489628764e-05,
"loss": 0.5671,
"step": 2500
},
{
"epoch": 0.07977768618117513,
"grad_norm": 1.8151600360870361,
"learning_rate": 1.992030103180513e-05,
"loss": 0.5535,
"step": 3000
},
{
"epoch": 0.09307396721137098,
"grad_norm": 1.9667155742645264,
"learning_rate": 1.990700457398149e-05,
"loss": 0.5628,
"step": 3500
},
{
"epoch": 0.10637024824156684,
"grad_norm": 2.0493931770324707,
"learning_rate": 1.9893708116157857e-05,
"loss": 0.5465,
"step": 4000
},
{
"epoch": 0.11966652927176269,
"grad_norm": 2.201901435852051,
"learning_rate": 1.988041165833422e-05,
"loss": 0.5472,
"step": 4500
},
{
"epoch": 0.13296281030195853,
"grad_norm": 1.8538507223129272,
"learning_rate": 1.9867115200510584e-05,
"loss": 0.5451,
"step": 5000
},
{
"epoch": 0.1462590913321544,
"grad_norm": 1.35111403465271,
"learning_rate": 1.985381874268695e-05,
"loss": 0.5333,
"step": 5500
},
{
"epoch": 0.15955537236235026,
"grad_norm": 1.2387117147445679,
"learning_rate": 1.9840522284863314e-05,
"loss": 0.5096,
"step": 6000
},
{
"epoch": 0.1728516533925461,
"grad_norm": 1.2727868556976318,
"learning_rate": 1.9827225827039677e-05,
"loss": 0.5256,
"step": 6500
},
{
"epoch": 0.18614793442274197,
"grad_norm": 1.7770028114318848,
"learning_rate": 1.9813929369216044e-05,
"loss": 0.5064,
"step": 7000
},
{
"epoch": 0.1994442154529378,
"grad_norm": 2.1460671424865723,
"learning_rate": 1.9800632911392407e-05,
"loss": 0.5066,
"step": 7500
},
{
"epoch": 0.21274049648313367,
"grad_norm": 1.315503716468811,
"learning_rate": 1.978733645356877e-05,
"loss": 0.4974,
"step": 8000
},
{
"epoch": 0.2260367775133295,
"grad_norm": 1.6402277946472168,
"learning_rate": 1.9774039995745137e-05,
"loss": 0.5019,
"step": 8500
},
{
"epoch": 0.23933305854352538,
"grad_norm": 1.4794352054595947,
"learning_rate": 1.97607435379215e-05,
"loss": 0.5072,
"step": 9000
},
{
"epoch": 0.25262933957372125,
"grad_norm": 1.432265043258667,
"learning_rate": 1.9747447080097863e-05,
"loss": 0.4844,
"step": 9500
},
{
"epoch": 0.26592562060391706,
"grad_norm": 1.7145007848739624,
"learning_rate": 1.973415062227423e-05,
"loss": 0.488,
"step": 10000
},
{
"epoch": 0.26592562060391706,
"eval_loss": 0.4845176041126251,
"eval_runtime": 45.8707,
"eval_samples_per_second": 66.251,
"eval_steps_per_second": 16.568,
"step": 10000
},
{
"epoch": 0.2792219016341129,
"grad_norm": 1.404540777206421,
"learning_rate": 1.972085416445059e-05,
"loss": 0.4931,
"step": 10500
},
{
"epoch": 0.2925181826643088,
"grad_norm": 1.3520866632461548,
"learning_rate": 1.9707557706626957e-05,
"loss": 0.4868,
"step": 11000
},
{
"epoch": 0.30581446369450466,
"grad_norm": 1.4363296031951904,
"learning_rate": 1.969426124880332e-05,
"loss": 0.4798,
"step": 11500
},
{
"epoch": 0.3191107447247005,
"grad_norm": 1.4917619228363037,
"learning_rate": 1.9680964790979683e-05,
"loss": 0.4736,
"step": 12000
},
{
"epoch": 0.33240702575489633,
"grad_norm": 1.7679712772369385,
"learning_rate": 1.966766833315605e-05,
"loss": 0.4778,
"step": 12500
},
{
"epoch": 0.3457033067850922,
"grad_norm": 1.4026507139205933,
"learning_rate": 1.9654371875332413e-05,
"loss": 0.4761,
"step": 13000
},
{
"epoch": 0.35899958781528807,
"grad_norm": 1.8736493587493896,
"learning_rate": 1.9641075417508776e-05,
"loss": 0.4871,
"step": 13500
},
{
"epoch": 0.37229586884548393,
"grad_norm": 1.2222760915756226,
"learning_rate": 1.9627778959685143e-05,
"loss": 0.4745,
"step": 14000
},
{
"epoch": 0.38559214987567975,
"grad_norm": 1.4624443054199219,
"learning_rate": 1.9614509094777154e-05,
"loss": 0.4573,
"step": 14500
},
{
"epoch": 0.3988884309058756,
"grad_norm": 1.8538755178451538,
"learning_rate": 1.9601212636953517e-05,
"loss": 0.4633,
"step": 15000
},
{
"epoch": 0.4121847119360715,
"grad_norm": 1.47249174118042,
"learning_rate": 1.9587916179129884e-05,
"loss": 0.4764,
"step": 15500
},
{
"epoch": 0.42548099296626735,
"grad_norm": 1.7755292654037476,
"learning_rate": 1.9574619721306244e-05,
"loss": 0.4699,
"step": 16000
},
{
"epoch": 0.4387772739964632,
"grad_norm": 1.4009391069412231,
"learning_rate": 1.956132326348261e-05,
"loss": 0.4666,
"step": 16500
},
{
"epoch": 0.452073555026659,
"grad_norm": 1.520727276802063,
"learning_rate": 1.9548026805658973e-05,
"loss": 0.4697,
"step": 17000
},
{
"epoch": 0.4653698360568549,
"grad_norm": 1.7645255327224731,
"learning_rate": 1.9534730347835337e-05,
"loss": 0.46,
"step": 17500
},
{
"epoch": 0.47866611708705076,
"grad_norm": 1.7914655208587646,
"learning_rate": 1.9521433890011703e-05,
"loss": 0.4601,
"step": 18000
},
{
"epoch": 0.4919623981172466,
"grad_norm": 1.4558111429214478,
"learning_rate": 1.9508164025103714e-05,
"loss": 0.4601,
"step": 18500
},
{
"epoch": 0.5052586791474425,
"grad_norm": 1.1980383396148682,
"learning_rate": 1.9494894160195725e-05,
"loss": 0.4563,
"step": 19000
},
{
"epoch": 0.5185549601776384,
"grad_norm": 1.8653793334960938,
"learning_rate": 1.9481597702372092e-05,
"loss": 0.4434,
"step": 19500
},
{
"epoch": 0.5318512412078341,
"grad_norm": 1.3913460969924927,
"learning_rate": 1.946830124454845e-05,
"loss": 0.45,
"step": 20000
},
{
"epoch": 0.5318512412078341,
"eval_loss": 0.4461110234260559,
"eval_runtime": 46.6164,
"eval_samples_per_second": 65.192,
"eval_steps_per_second": 16.303,
"step": 20000
},
{
"epoch": 0.54514752223803,
"grad_norm": 1.4441711902618408,
"learning_rate": 1.9455004786724818e-05,
"loss": 0.4536,
"step": 20500
},
{
"epoch": 0.5584438032682258,
"grad_norm": 1.2844038009643555,
"learning_rate": 1.9441708328901185e-05,
"loss": 0.447,
"step": 21000
},
{
"epoch": 0.5717400842984217,
"grad_norm": 2.10949444770813,
"learning_rate": 1.9428438463993192e-05,
"loss": 0.4484,
"step": 21500
},
{
"epoch": 0.5850363653286176,
"grad_norm": 0.925681471824646,
"learning_rate": 1.941514200616956e-05,
"loss": 0.4374,
"step": 22000
},
{
"epoch": 0.5983326463588134,
"grad_norm": 1.49970543384552,
"learning_rate": 1.9401845548345922e-05,
"loss": 0.4533,
"step": 22500
},
{
"epoch": 0.6116289273890093,
"grad_norm": 1.2436000108718872,
"learning_rate": 1.9388549090522286e-05,
"loss": 0.4455,
"step": 23000
},
{
"epoch": 0.6249252084192052,
"grad_norm": 1.1918786764144897,
"learning_rate": 1.9375252632698652e-05,
"loss": 0.4389,
"step": 23500
},
{
"epoch": 0.638221489449401,
"grad_norm": 1.2042317390441895,
"learning_rate": 1.9361956174875015e-05,
"loss": 0.4446,
"step": 24000
},
{
"epoch": 0.6515177704795968,
"grad_norm": 1.3460853099822998,
"learning_rate": 1.934865971705138e-05,
"loss": 0.4464,
"step": 24500
},
{
"epoch": 0.6648140515097927,
"grad_norm": 1.1541383266448975,
"learning_rate": 1.9335363259227745e-05,
"loss": 0.4404,
"step": 25000
},
{
"epoch": 0.6781103325399885,
"grad_norm": 1.2001688480377197,
"learning_rate": 1.9322093394319753e-05,
"loss": 0.4409,
"step": 25500
},
{
"epoch": 0.6914066135701844,
"grad_norm": 1.38569974899292,
"learning_rate": 1.930879693649612e-05,
"loss": 0.4412,
"step": 26000
},
{
"epoch": 0.7047028946003803,
"grad_norm": 1.6519745588302612,
"learning_rate": 1.9295500478672483e-05,
"loss": 0.4293,
"step": 26500
},
{
"epoch": 0.7179991756305761,
"grad_norm": 1.1891002655029297,
"learning_rate": 1.9282230613764494e-05,
"loss": 0.4478,
"step": 27000
},
{
"epoch": 0.731295456660772,
"grad_norm": 1.2890375852584839,
"learning_rate": 1.926893415594086e-05,
"loss": 0.4422,
"step": 27500
},
{
"epoch": 0.7445917376909679,
"grad_norm": 1.2893614768981934,
"learning_rate": 1.9255637698117224e-05,
"loss": 0.4379,
"step": 28000
},
{
"epoch": 0.7578880187211637,
"grad_norm": 1.2751696109771729,
"learning_rate": 1.9242341240293587e-05,
"loss": 0.4259,
"step": 28500
},
{
"epoch": 0.7711842997513595,
"grad_norm": 1.263238549232483,
"learning_rate": 1.9229044782469953e-05,
"loss": 0.4285,
"step": 29000
},
{
"epoch": 0.7844805807815554,
"grad_norm": 1.6520916223526,
"learning_rate": 1.921577491756196e-05,
"loss": 0.4278,
"step": 29500
},
{
"epoch": 0.7977768618117512,
"grad_norm": 1.4022353887557983,
"learning_rate": 1.9202478459738328e-05,
"loss": 0.4277,
"step": 30000
},
{
"epoch": 0.7977768618117512,
"eval_loss": 0.4259246587753296,
"eval_runtime": 45.6826,
"eval_samples_per_second": 66.524,
"eval_steps_per_second": 16.637,
"step": 30000
},
{
"epoch": 0.8110731428419471,
"grad_norm": 1.3312253952026367,
"learning_rate": 1.918920859483034e-05,
"loss": 0.4262,
"step": 30500
},
{
"epoch": 0.824369423872143,
"grad_norm": 1.5275497436523438,
"learning_rate": 1.91759121370067e-05,
"loss": 0.4281,
"step": 31000
},
{
"epoch": 0.8376657049023388,
"grad_norm": 1.7679028511047363,
"learning_rate": 1.916261567918307e-05,
"loss": 0.44,
"step": 31500
},
{
"epoch": 0.8509619859325347,
"grad_norm": 1.1467547416687012,
"learning_rate": 1.914931922135943e-05,
"loss": 0.4153,
"step": 32000
},
{
"epoch": 0.8642582669627306,
"grad_norm": 1.2685679197311401,
"learning_rate": 1.9136022763535795e-05,
"loss": 0.4232,
"step": 32500
},
{
"epoch": 0.8775545479929264,
"grad_norm": 0.9204725623130798,
"learning_rate": 1.912272630571216e-05,
"loss": 0.425,
"step": 33000
},
{
"epoch": 0.8908508290231222,
"grad_norm": 0.7971585988998413,
"learning_rate": 1.9109429847888525e-05,
"loss": 0.431,
"step": 33500
},
{
"epoch": 0.904147110053318,
"grad_norm": 1.6358304023742676,
"learning_rate": 1.9096133390064888e-05,
"loss": 0.4361,
"step": 34000
},
{
"epoch": 0.9174433910835139,
"grad_norm": 1.7240855693817139,
"learning_rate": 1.9082836932241255e-05,
"loss": 0.432,
"step": 34500
},
{
"epoch": 0.9307396721137098,
"grad_norm": 1.1937910318374634,
"learning_rate": 1.9069567067333262e-05,
"loss": 0.4324,
"step": 35000
},
{
"epoch": 0.9440359531439056,
"grad_norm": 1.1422160863876343,
"learning_rate": 1.905627060950963e-05,
"loss": 0.4286,
"step": 35500
},
{
"epoch": 0.9573322341741015,
"grad_norm": 1.0084590911865234,
"learning_rate": 1.9042974151685992e-05,
"loss": 0.4401,
"step": 36000
},
{
"epoch": 0.9706285152042974,
"grad_norm": 1.7879573106765747,
"learning_rate": 1.9029677693862355e-05,
"loss": 0.4259,
"step": 36500
},
{
"epoch": 0.9839247962344932,
"grad_norm": 1.1148507595062256,
"learning_rate": 1.9016381236038722e-05,
"loss": 0.3995,
"step": 37000
},
{
"epoch": 0.9972210772646891,
"grad_norm": 1.2119601964950562,
"learning_rate": 1.9003084778215085e-05,
"loss": 0.4228,
"step": 37500
},
{
"epoch": 1.010517358294885,
"grad_norm": 1.2811840772628784,
"learning_rate": 1.898978832039145e-05,
"loss": 0.3945,
"step": 38000
},
{
"epoch": 1.0238136393250807,
"grad_norm": 1.199591040611267,
"learning_rate": 1.8976491862567815e-05,
"loss": 0.3724,
"step": 38500
},
{
"epoch": 1.0371099203552767,
"grad_norm": 1.4783821105957031,
"learning_rate": 1.8963221997659823e-05,
"loss": 0.3869,
"step": 39000
},
{
"epoch": 1.0504062013854725,
"grad_norm": 1.1598395109176636,
"learning_rate": 1.894992553983619e-05,
"loss": 0.3888,
"step": 39500
},
{
"epoch": 1.0637024824156684,
"grad_norm": 1.0254014730453491,
"learning_rate": 1.8936629082012556e-05,
"loss": 0.3741,
"step": 40000
},
{
"epoch": 1.0637024824156684,
"eval_loss": 0.4110487699508667,
"eval_runtime": 45.9661,
"eval_samples_per_second": 66.114,
"eval_steps_per_second": 16.534,
"step": 40000
},
{
"epoch": 1.0769987634458642,
"grad_norm": 1.4140042066574097,
"learning_rate": 1.8923332624188916e-05,
"loss": 0.3838,
"step": 40500
},
{
"epoch": 1.09029504447606,
"grad_norm": 1.4062950611114502,
"learning_rate": 1.8910089352196578e-05,
"loss": 0.368,
"step": 41000
},
{
"epoch": 1.103591325506256,
"grad_norm": 1.2314609289169312,
"learning_rate": 1.889681948728859e-05,
"loss": 0.4033,
"step": 41500
},
{
"epoch": 1.1168876065364517,
"grad_norm": 1.4966250658035278,
"learning_rate": 1.8883523029464952e-05,
"loss": 0.3878,
"step": 42000
},
{
"epoch": 1.1301838875666477,
"grad_norm": 1.1920274496078491,
"learning_rate": 1.887022657164132e-05,
"loss": 0.375,
"step": 42500
},
{
"epoch": 1.1434801685968434,
"grad_norm": 1.0075514316558838,
"learning_rate": 1.8856930113817678e-05,
"loss": 0.3821,
"step": 43000
},
{
"epoch": 1.1567764496270394,
"grad_norm": 1.2424709796905518,
"learning_rate": 1.8843633655994045e-05,
"loss": 0.3793,
"step": 43500
},
{
"epoch": 1.1700727306572352,
"grad_norm": 0.7054141163825989,
"learning_rate": 1.8830337198170408e-05,
"loss": 0.3821,
"step": 44000
},
{
"epoch": 1.183369011687431,
"grad_norm": 0.7828935384750366,
"learning_rate": 1.881704074034677e-05,
"loss": 0.3737,
"step": 44500
},
{
"epoch": 1.196665292717627,
"grad_norm": 1.3097379207611084,
"learning_rate": 1.8803744282523138e-05,
"loss": 0.3747,
"step": 45000
},
{
"epoch": 1.2099615737478226,
"grad_norm": 1.2207602262496948,
"learning_rate": 1.87904478246995e-05,
"loss": 0.3799,
"step": 45500
},
{
"epoch": 1.2232578547780186,
"grad_norm": 1.5833189487457275,
"learning_rate": 1.8777151366875865e-05,
"loss": 0.387,
"step": 46000
},
{
"epoch": 1.2365541358082144,
"grad_norm": 1.3836820125579834,
"learning_rate": 1.876385490905223e-05,
"loss": 0.3853,
"step": 46500
},
{
"epoch": 1.2498504168384104,
"grad_norm": 0.9267215728759766,
"learning_rate": 1.8750558451228595e-05,
"loss": 0.3763,
"step": 47000
},
{
"epoch": 1.2631466978686061,
"grad_norm": 1.4826302528381348,
"learning_rate": 1.8737288586320605e-05,
"loss": 0.3753,
"step": 47500
},
{
"epoch": 1.2764429788988019,
"grad_norm": 1.7470266819000244,
"learning_rate": 1.8723992128496972e-05,
"loss": 0.389,
"step": 48000
},
{
"epoch": 1.2897392599289978,
"grad_norm": 0.9160776734352112,
"learning_rate": 1.8710695670673332e-05,
"loss": 0.3732,
"step": 48500
},
{
"epoch": 1.3030355409591938,
"grad_norm": 1.5541558265686035,
"learning_rate": 1.86973992128497e-05,
"loss": 0.3815,
"step": 49000
},
{
"epoch": 1.3163318219893896,
"grad_norm": 1.3254436254501343,
"learning_rate": 1.8684102755026062e-05,
"loss": 0.3786,
"step": 49500
},
{
"epoch": 1.3296281030195853,
"grad_norm": 1.5244851112365723,
"learning_rate": 1.8670806297202425e-05,
"loss": 0.3886,
"step": 50000
},
{
"epoch": 1.3296281030195853,
"eval_loss": 0.4009094834327698,
"eval_runtime": 45.5454,
"eval_samples_per_second": 66.725,
"eval_steps_per_second": 16.687,
"step": 50000
},
{
"epoch": 1.3429376803308115,
"grad_norm": 0.867463231086731,
"learning_rate": 1.8657509839378792e-05,
"loss": 0.3681,
"step": 50500
},
{
"epoch": 1.3562339613610073,
"grad_norm": 1.2311478853225708,
"learning_rate": 1.8644213381555155e-05,
"loss": 0.347,
"step": 51000
},
{
"epoch": 1.3695302423912032,
"grad_norm": 1.4698890447616577,
"learning_rate": 1.8630916923731518e-05,
"loss": 0.3666,
"step": 51500
},
{
"epoch": 1.382826523421399,
"grad_norm": 1.3057785034179688,
"learning_rate": 1.8617620465907885e-05,
"loss": 0.3716,
"step": 52000
},
{
"epoch": 1.3961228044515948,
"grad_norm": 0.9626977443695068,
"learning_rate": 1.8604324008084248e-05,
"loss": 0.3633,
"step": 52500
},
{
"epoch": 1.4094190854817907,
"grad_norm": 1.055158257484436,
"learning_rate": 1.859102755026061e-05,
"loss": 0.364,
"step": 53000
},
{
"epoch": 1.4227153665119867,
"grad_norm": 1.7065026760101318,
"learning_rate": 1.8577731092436978e-05,
"loss": 0.365,
"step": 53500
},
{
"epoch": 1.4360116475421825,
"grad_norm": 1.1983647346496582,
"learning_rate": 1.856443463461334e-05,
"loss": 0.3584,
"step": 54000
},
{
"epoch": 1.4493079285723782,
"grad_norm": 1.465380072593689,
"learning_rate": 1.8551138176789705e-05,
"loss": 0.3698,
"step": 54500
},
{
"epoch": 1.4626042096025742,
"grad_norm": 0.9600203037261963,
"learning_rate": 1.853784171896607e-05,
"loss": 0.3686,
"step": 55000
},
{
"epoch": 1.47590049063277,
"grad_norm": 0.7194857597351074,
"learning_rate": 1.852454526114243e-05,
"loss": 0.3691,
"step": 55500
},
{
"epoch": 1.489196771662966,
"grad_norm": 1.2525266408920288,
"learning_rate": 1.8511248803318798e-05,
"loss": 0.3716,
"step": 56000
},
{
"epoch": 1.5024930526931617,
"grad_norm": 1.4390616416931152,
"learning_rate": 1.849795234549516e-05,
"loss": 0.3642,
"step": 56500
},
{
"epoch": 1.5157893337233577,
"grad_norm": 0.9960741996765137,
"learning_rate": 1.8484655887671524e-05,
"loss": 0.3543,
"step": 57000
},
{
"epoch": 1.5290856147535534,
"grad_norm": 1.5157722234725952,
"learning_rate": 1.847135942984789e-05,
"loss": 0.3684,
"step": 57500
},
{
"epoch": 1.5423818957837492,
"grad_norm": 1.2276800870895386,
"learning_rate": 1.8458062972024254e-05,
"loss": 0.3682,
"step": 58000
},
{
"epoch": 1.5556781768139452,
"grad_norm": 0.7182838916778564,
"learning_rate": 1.8444793107116265e-05,
"loss": 0.3571,
"step": 58500
},
{
"epoch": 1.5689744578441411,
"grad_norm": 1.4738359451293945,
"learning_rate": 1.8431496649292632e-05,
"loss": 0.3495,
"step": 59000
},
{
"epoch": 1.582270738874337,
"grad_norm": 1.1519092321395874,
"learning_rate": 1.8418200191468995e-05,
"loss": 0.3656,
"step": 59500
},
{
"epoch": 1.5955670199045326,
"grad_norm": 0.9778446555137634,
"learning_rate": 1.8404903733645358e-05,
"loss": 0.3528,
"step": 60000
},
{
"epoch": 1.5955670199045326,
"eval_loss": 0.33645519614219666,
"eval_runtime": 45.1628,
"eval_samples_per_second": 67.29,
"eval_steps_per_second": 16.828,
"step": 60000
},
{
"epoch": 1.6088633009347286,
"grad_norm": 1.5486047267913818,
"learning_rate": 1.8391607275821725e-05,
"loss": 0.3587,
"step": 60500
},
{
"epoch": 1.6221595819649244,
"grad_norm": 0.8840271234512329,
"learning_rate": 1.8378337410913732e-05,
"loss": 0.3584,
"step": 61000
},
{
"epoch": 1.6354558629951201,
"grad_norm": 0.9995741248130798,
"learning_rate": 1.83650409530901e-05,
"loss": 0.3737,
"step": 61500
},
{
"epoch": 1.6487521440253161,
"grad_norm": 1.7882977724075317,
"learning_rate": 1.835177108818211e-05,
"loss": 0.3655,
"step": 62000
},
{
"epoch": 1.662048425055512,
"grad_norm": 0.7783369421958923,
"learning_rate": 1.8338474630358473e-05,
"loss": 0.3673,
"step": 62500
},
{
"epoch": 1.6753447060857078,
"grad_norm": 1.585405945777893,
"learning_rate": 1.832517817253484e-05,
"loss": 0.3595,
"step": 63000
},
{
"epoch": 1.6886409871159036,
"grad_norm": 1.3467520475387573,
"learning_rate": 1.8311881714711203e-05,
"loss": 0.3627,
"step": 63500
},
{
"epoch": 1.7019372681460996,
"grad_norm": 1.1446176767349243,
"learning_rate": 1.8298585256887566e-05,
"loss": 0.3574,
"step": 64000
},
{
"epoch": 1.7152335491762953,
"grad_norm": 0.9003855586051941,
"learning_rate": 1.828531539197958e-05,
"loss": 0.3665,
"step": 64500
},
{
"epoch": 1.728529830206491,
"grad_norm": 0.8468024730682373,
"learning_rate": 1.827201893415594e-05,
"loss": 0.3574,
"step": 65000
},
{
"epoch": 1.741826111236687,
"grad_norm": 1.0654727220535278,
"learning_rate": 1.8258722476332307e-05,
"loss": 0.3651,
"step": 65500
},
{
"epoch": 1.755122392266883,
"grad_norm": 0.6998704671859741,
"learning_rate": 1.824542601850867e-05,
"loss": 0.36,
"step": 66000
},
{
"epoch": 1.7684186732970788,
"grad_norm": 0.8846042156219482,
"learning_rate": 1.8232129560685034e-05,
"loss": 0.362,
"step": 66500
},
{
"epoch": 1.7817149543272746,
"grad_norm": 1.2595306634902954,
"learning_rate": 1.82188331028614e-05,
"loss": 0.3607,
"step": 67000
},
{
"epoch": 1.7950112353574705,
"grad_norm": 1.0262569189071655,
"learning_rate": 1.8205536645037764e-05,
"loss": 0.3528,
"step": 67500
},
{
"epoch": 1.8083075163876665,
"grad_norm": 1.034749150276184,
"learning_rate": 1.8192240187214127e-05,
"loss": 0.3659,
"step": 68000
},
{
"epoch": 1.8216037974178623,
"grad_norm": 1.6457266807556152,
"learning_rate": 1.817897032230614e-05,
"loss": 0.3618,
"step": 68500
},
{
"epoch": 1.834900078448058,
"grad_norm": 1.0784075260162354,
"learning_rate": 1.81656738644825e-05,
"loss": 0.3678,
"step": 69000
},
{
"epoch": 1.848196359478254,
"grad_norm": 1.7093465328216553,
"learning_rate": 1.8152377406658868e-05,
"loss": 0.3586,
"step": 69500
},
{
"epoch": 1.8614926405084498,
"grad_norm": 1.0873297452926636,
"learning_rate": 1.8139080948835234e-05,
"loss": 0.3486,
"step": 70000
},
{
"epoch": 1.8614926405084498,
"eval_loss": 0.33657437562942505,
"eval_runtime": 44.8327,
"eval_samples_per_second": 67.785,
"eval_steps_per_second": 16.952,
"step": 70000
},
{
"epoch": 1.8747889215386455,
"grad_norm": 1.2218577861785889,
"learning_rate": 1.8125784491011594e-05,
"loss": 0.3538,
"step": 70500
},
{
"epoch": 1.8880852025688415,
"grad_norm": 1.7675495147705078,
"learning_rate": 1.8112541219019256e-05,
"loss": 0.36,
"step": 71000
},
{
"epoch": 1.9013814835990375,
"grad_norm": 1.546845555305481,
"learning_rate": 1.809924476119562e-05,
"loss": 0.3681,
"step": 71500
},
{
"epoch": 1.9146777646292332,
"grad_norm": 1.0978270769119263,
"learning_rate": 1.8085948303371982e-05,
"loss": 0.349,
"step": 72000
},
{
"epoch": 1.927974045659429,
"grad_norm": 1.0180225372314453,
"learning_rate": 1.807265184554835e-05,
"loss": 0.3607,
"step": 72500
},
{
"epoch": 1.941270326689625,
"grad_norm": 1.5221401453018188,
"learning_rate": 1.8059355387724712e-05,
"loss": 0.3603,
"step": 73000
},
{
"epoch": 1.9545666077198207,
"grad_norm": 1.8798828125,
"learning_rate": 1.8046058929901076e-05,
"loss": 0.3609,
"step": 73500
},
{
"epoch": 1.9678628887500165,
"grad_norm": 1.5229233503341675,
"learning_rate": 1.8032762472077442e-05,
"loss": 0.3721,
"step": 74000
},
{
"epoch": 1.9811591697802124,
"grad_norm": 0.7534819841384888,
"learning_rate": 1.8019466014253802e-05,
"loss": 0.3606,
"step": 74500
},
{
"epoch": 1.9944554508104084,
"grad_norm": 1.0966280698776245,
"learning_rate": 1.800616955643017e-05,
"loss": 0.3581,
"step": 75000
},
{
"epoch": 2.0077517318406044,
"grad_norm": 1.165394902229309,
"learning_rate": 1.7992873098606532e-05,
"loss": 0.3426,
"step": 75500
},
{
"epoch": 2.0210480128708,
"grad_norm": 1.4377708435058594,
"learning_rate": 1.7979576640782895e-05,
"loss": 0.3315,
"step": 76000
},
{
"epoch": 2.034344293900996,
"grad_norm": 1.065831184387207,
"learning_rate": 1.7966280182959262e-05,
"loss": 0.3348,
"step": 76500
},
{
"epoch": 2.047640574931192,
"grad_norm": 1.0377391576766968,
"learning_rate": 1.7953010318051273e-05,
"loss": 0.3297,
"step": 77000
},
{
"epoch": 2.0609368559613874,
"grad_norm": 1.28931725025177,
"learning_rate": 1.7939713860227636e-05,
"loss": 0.3353,
"step": 77500
},
{
"epoch": 2.0742331369915834,
"grad_norm": 0.9061357378959656,
"learning_rate": 1.7926417402404003e-05,
"loss": 0.3373,
"step": 78000
},
{
"epoch": 2.0875294180217794,
"grad_norm": 1.162048101425171,
"learning_rate": 1.7913120944580366e-05,
"loss": 0.3287,
"step": 78500
},
{
"epoch": 2.1008256990519754,
"grad_norm": 1.1295771598815918,
"learning_rate": 1.7899851079672377e-05,
"loss": 0.3306,
"step": 79000
},
{
"epoch": 2.114121980082171,
"grad_norm": 1.3394831418991089,
"learning_rate": 1.788655462184874e-05,
"loss": 0.3425,
"step": 79500
},
{
"epoch": 2.127418261112367,
"grad_norm": 0.7900285124778748,
"learning_rate": 1.7873258164025103e-05,
"loss": 0.3339,
"step": 80000
},
{
"epoch": 2.127418261112367,
"eval_loss": 0.33293381333351135,
"eval_runtime": 45.161,
"eval_samples_per_second": 67.293,
"eval_steps_per_second": 16.829,
"step": 80000
},
{
"epoch": 2.140714542142563,
"grad_norm": 1.2849562168121338,
"learning_rate": 1.785996170620147e-05,
"loss": 0.3299,
"step": 80500
},
{
"epoch": 2.1540108231727584,
"grad_norm": 1.2442893981933594,
"learning_rate": 1.7846665248377833e-05,
"loss": 0.3234,
"step": 81000
},
{
"epoch": 2.1673071042029544,
"grad_norm": 0.9078606963157654,
"learning_rate": 1.7833368790554197e-05,
"loss": 0.3405,
"step": 81500
},
{
"epoch": 2.1806033852331503,
"grad_norm": 1.1512479782104492,
"learning_rate": 1.782009892564621e-05,
"loss": 0.332,
"step": 82000
},
{
"epoch": 2.1938996662633463,
"grad_norm": 1.0047634840011597,
"learning_rate": 1.7806802467822574e-05,
"loss": 0.3294,
"step": 82500
},
{
"epoch": 2.207195947293542,
"grad_norm": 0.8341502547264099,
"learning_rate": 1.7793506009998937e-05,
"loss": 0.3428,
"step": 83000
},
{
"epoch": 2.220492228323738,
"grad_norm": 1.1106518507003784,
"learning_rate": 1.7780209552175304e-05,
"loss": 0.3312,
"step": 83500
},
{
"epoch": 2.233788509353934,
"grad_norm": 1.0450632572174072,
"learning_rate": 1.7766913094351664e-05,
"loss": 0.3228,
"step": 84000
},
{
"epoch": 2.24708479038413,
"grad_norm": 1.2051053047180176,
"learning_rate": 1.775361663652803e-05,
"loss": 0.3231,
"step": 84500
},
{
"epoch": 2.2603810714143253,
"grad_norm": 1.2320146560668945,
"learning_rate": 1.7740320178704394e-05,
"loss": 0.3275,
"step": 85000
},
{
"epoch": 2.2736773524445213,
"grad_norm": 1.878662347793579,
"learning_rate": 1.7727023720880757e-05,
"loss": 0.3394,
"step": 85500
},
{
"epoch": 2.2869736334747173,
"grad_norm": 0.7427929043769836,
"learning_rate": 1.771375385597277e-05,
"loss": 0.3334,
"step": 86000
},
{
"epoch": 2.300269914504913,
"grad_norm": 0.6553477644920349,
"learning_rate": 1.7700483991064782e-05,
"loss": 0.3426,
"step": 86500
},
{
"epoch": 2.313566195535109,
"grad_norm": 1.1945719718933105,
"learning_rate": 1.7687187533241145e-05,
"loss": 0.3329,
"step": 87000
},
{
"epoch": 2.3268624765653048,
"grad_norm": 1.410997986793518,
"learning_rate": 1.7673891075417512e-05,
"loss": 0.3309,
"step": 87500
},
{
"epoch": 2.3401587575955007,
"grad_norm": 1.0178992748260498,
"learning_rate": 1.7660594617593872e-05,
"loss": 0.3247,
"step": 88000
},
{
"epoch": 2.3534550386256963,
"grad_norm": 1.4672740697860718,
"learning_rate": 1.764729815977024e-05,
"loss": 0.3373,
"step": 88500
},
{
"epoch": 2.3667513196558922,
"grad_norm": 1.1154576539993286,
"learning_rate": 1.763402829486225e-05,
"loss": 0.3331,
"step": 89000
},
{
"epoch": 2.3800476006860882,
"grad_norm": 1.5529305934906006,
"learning_rate": 1.7620731837038613e-05,
"loss": 0.3325,
"step": 89500
},
{
"epoch": 2.3933438817162838,
"grad_norm": 1.4075485467910767,
"learning_rate": 1.760743537921498e-05,
"loss": 0.3252,
"step": 90000
},
{
"epoch": 2.3933438817162838,
"eval_loss": 0.3309895098209381,
"eval_runtime": 45.3672,
"eval_samples_per_second": 66.987,
"eval_steps_per_second": 16.752,
"step": 90000
},
{
"epoch": 2.4066401627464797,
"grad_norm": 1.5770002603530884,
"learning_rate": 1.7594138921391343e-05,
"loss": 0.3341,
"step": 90500
},
{
"epoch": 2.4199364437766757,
"grad_norm": 1.350996494293213,
"learning_rate": 1.7580842463567706e-05,
"loss": 0.3316,
"step": 91000
},
{
"epoch": 2.4332327248068717,
"grad_norm": 1.3606607913970947,
"learning_rate": 1.7567599191575368e-05,
"loss": 0.3437,
"step": 91500
},
{
"epoch": 2.4465290058370672,
"grad_norm": 1.3645395040512085,
"learning_rate": 1.7554302733751728e-05,
"loss": 0.3287,
"step": 92000
},
{
"epoch": 2.459825286867263,
"grad_norm": 1.6436042785644531,
"learning_rate": 1.7541006275928094e-05,
"loss": 0.3443,
"step": 92500
},
{
"epoch": 2.473121567897459,
"grad_norm": 0.837202250957489,
"learning_rate": 1.7527709818104458e-05,
"loss": 0.3221,
"step": 93000
},
{
"epoch": 2.4864178489276547,
"grad_norm": 1.0937107801437378,
"learning_rate": 1.751441336028082e-05,
"loss": 0.3406,
"step": 93500
},
{
"epoch": 2.4997141299578507,
"grad_norm": 1.4137901067733765,
"learning_rate": 1.7501116902457187e-05,
"loss": 0.3243,
"step": 94000
},
{
"epoch": 2.5130104109880467,
"grad_norm": 0.8641353249549866,
"learning_rate": 1.748782044463355e-05,
"loss": 0.328,
"step": 94500
},
{
"epoch": 2.5263066920182427,
"grad_norm": 1.4282252788543701,
"learning_rate": 1.7474523986809914e-05,
"loss": 0.3362,
"step": 95000
},
{
"epoch": 2.5396029730484386,
"grad_norm": 1.3759071826934814,
"learning_rate": 1.746122752898628e-05,
"loss": 0.3339,
"step": 95500
},
{
"epoch": 2.552899254078634,
"grad_norm": 1.239725947380066,
"learning_rate": 1.7447931071162644e-05,
"loss": 0.3419,
"step": 96000
},
{
"epoch": 2.56619553510883,
"grad_norm": 0.919045627117157,
"learning_rate": 1.7434634613339007e-05,
"loss": 0.3369,
"step": 96500
},
{
"epoch": 2.5794918161390257,
"grad_norm": 1.8451613187789917,
"learning_rate": 1.7421338155515374e-05,
"loss": 0.3417,
"step": 97000
},
{
"epoch": 2.5927880971692217,
"grad_norm": 1.0559651851654053,
"learning_rate": 1.740806829060738e-05,
"loss": 0.3291,
"step": 97500
},
{
"epoch": 2.6060843781994176,
"grad_norm": 1.215611219406128,
"learning_rate": 1.7394771832783748e-05,
"loss": 0.3252,
"step": 98000
},
{
"epoch": 2.6193806592296136,
"grad_norm": 0.8735470175743103,
"learning_rate": 1.738147537496011e-05,
"loss": 0.3338,
"step": 98500
},
{
"epoch": 2.6326769402598096,
"grad_norm": 1.5552194118499756,
"learning_rate": 1.7368178917136474e-05,
"loss": 0.3336,
"step": 99000
},
{
"epoch": 2.645973221290005,
"grad_norm": 1.0891499519348145,
"learning_rate": 1.735490905222849e-05,
"loss": 0.3302,
"step": 99500
},
{
"epoch": 2.659269502320201,
"grad_norm": 1.1763145923614502,
"learning_rate": 1.73416391873205e-05,
"loss": 0.33,
"step": 100000
},
{
"epoch": 2.659269502320201,
"eval_loss": 0.3290364444255829,
"eval_runtime": 45.2861,
"eval_samples_per_second": 67.107,
"eval_steps_per_second": 16.782,
"step": 100000
},
{
"epoch": 2.6725657833503966,
"grad_norm": 1.2883906364440918,
"learning_rate": 1.7328342729496863e-05,
"loss": 0.3306,
"step": 100500
},
{
"epoch": 2.6858620643805926,
"grad_norm": 1.4006438255310059,
"learning_rate": 1.7315072864588877e-05,
"loss": 0.3342,
"step": 101000
},
{
"epoch": 2.6991583454107886,
"grad_norm": 1.019209861755371,
"learning_rate": 1.7301776406765237e-05,
"loss": 0.3321,
"step": 101500
},
{
"epoch": 2.7124546264409846,
"grad_norm": 1.1669857501983643,
"learning_rate": 1.7288479948941604e-05,
"loss": 0.334,
"step": 102000
},
{
"epoch": 2.7257509074711805,
"grad_norm": 0.8057425022125244,
"learning_rate": 1.7275183491117967e-05,
"loss": 0.3347,
"step": 102500
},
{
"epoch": 2.739047188501376,
"grad_norm": 0.6847462058067322,
"learning_rate": 1.726188703329433e-05,
"loss": 0.3299,
"step": 103000
},
{
"epoch": 2.752343469531572,
"grad_norm": 1.1315343379974365,
"learning_rate": 1.7248590575470697e-05,
"loss": 0.3424,
"step": 103500
},
{
"epoch": 2.765639750561768,
"grad_norm": 1.2325061559677124,
"learning_rate": 1.723529411764706e-05,
"loss": 0.3346,
"step": 104000
},
{
"epoch": 2.7789360315919636,
"grad_norm": 1.2530683279037476,
"learning_rate": 1.7221997659823423e-05,
"loss": 0.3299,
"step": 104500
},
{
"epoch": 2.7922323126221595,
"grad_norm": 1.4341391324996948,
"learning_rate": 1.720870120199979e-05,
"loss": 0.3331,
"step": 105000
},
{
"epoch": 2.8055285936523555,
"grad_norm": 0.983672559261322,
"learning_rate": 1.7195404744176153e-05,
"loss": 0.3229,
"step": 105500
},
{
"epoch": 2.8188248746825515,
"grad_norm": 1.336562156677246,
"learning_rate": 1.7182108286352516e-05,
"loss": 0.3336,
"step": 106000
},
{
"epoch": 2.832121155712747,
"grad_norm": 1.2226226329803467,
"learning_rate": 1.7168811828528883e-05,
"loss": 0.3296,
"step": 106500
},
{
"epoch": 2.845417436742943,
"grad_norm": 0.9698474407196045,
"learning_rate": 1.7155515370705243e-05,
"loss": 0.3362,
"step": 107000
},
{
"epoch": 2.858713717773139,
"grad_norm": 1.006219744682312,
"learning_rate": 1.7142245505797257e-05,
"loss": 0.3435,
"step": 107500
},
{
"epoch": 2.8720099988033345,
"grad_norm": 1.3786289691925049,
"learning_rate": 1.712894904797362e-05,
"loss": 0.335,
"step": 108000
},
{
"epoch": 2.8853062798335305,
"grad_norm": 1.3363252878189087,
"learning_rate": 1.7115652590149984e-05,
"loss": 0.3295,
"step": 108500
},
{
"epoch": 2.8986025608637265,
"grad_norm": 0.9451866149902344,
"learning_rate": 1.710235613232635e-05,
"loss": 0.3226,
"step": 109000
},
{
"epoch": 2.9118988418939225,
"grad_norm": 0.9065133929252625,
"learning_rate": 1.708908626741836e-05,
"loss": 0.3356,
"step": 109500
},
{
"epoch": 2.925195122924118,
"grad_norm": 2.04927396774292,
"learning_rate": 1.7075789809594725e-05,
"loss": 0.3325,
"step": 110000
},
{
"epoch": 2.925195122924118,
"eval_loss": 0.32618749141693115,
"eval_runtime": 44.7607,
"eval_samples_per_second": 67.894,
"eval_steps_per_second": 16.979,
"step": 110000
},
{
"epoch": 2.938491403954314,
"grad_norm": 1.1163157224655151,
"learning_rate": 1.706249335177109e-05,
"loss": 0.3257,
"step": 110500
},
{
"epoch": 2.95178768498451,
"grad_norm": 0.929104208946228,
"learning_rate": 1.7049196893947454e-05,
"loss": 0.3384,
"step": 111000
},
{
"epoch": 2.9650839660147055,
"grad_norm": 1.0319048166275024,
"learning_rate": 1.7035927029039465e-05,
"loss": 0.3337,
"step": 111500
},
{
"epoch": 2.9783802470449015,
"grad_norm": 1.5630576610565186,
"learning_rate": 1.702263057121583e-05,
"loss": 0.3372,
"step": 112000
},
{
"epoch": 2.9916765280750974,
"grad_norm": 1.2456904649734497,
"learning_rate": 1.7009334113392192e-05,
"loss": 0.339,
"step": 112500
},
{
"epoch": 3.0049728091052934,
"grad_norm": 1.1409209966659546,
"learning_rate": 1.699603765556856e-05,
"loss": 0.3236,
"step": 113000
},
{
"epoch": 3.018269090135489,
"grad_norm": 1.1287899017333984,
"learning_rate": 1.698276779066057e-05,
"loss": 0.2909,
"step": 113500
},
{
"epoch": 3.031565371165685,
"grad_norm": 1.0493087768554688,
"learning_rate": 1.6969471332836933e-05,
"loss": 0.2988,
"step": 114000
},
{
"epoch": 3.044861652195881,
"grad_norm": 0.8281829357147217,
"learning_rate": 1.69561748750133e-05,
"loss": 0.3001,
"step": 114500
},
{
"epoch": 3.058157933226077,
"grad_norm": 1.5901657342910767,
"learning_rate": 1.6942878417189663e-05,
"loss": 0.2954,
"step": 115000
},
{
"epoch": 3.0714542142562724,
"grad_norm": 1.0881614685058594,
"learning_rate": 1.6929581959366026e-05,
"loss": 0.2985,
"step": 115500
},
{
"epoch": 3.0847504952864684,
"grad_norm": 1.8229660987854004,
"learning_rate": 1.6916285501542392e-05,
"loss": 0.2959,
"step": 116000
},
{
"epoch": 3.0980467763166644,
"grad_norm": 0.8429426550865173,
"learning_rate": 1.6902989043718752e-05,
"loss": 0.2977,
"step": 116500
},
{
"epoch": 3.11134305734686,
"grad_norm": 0.7262697219848633,
"learning_rate": 1.688969258589512e-05,
"loss": 0.2984,
"step": 117000
},
{
"epoch": 3.124639338377056,
"grad_norm": 1.0413541793823242,
"learning_rate": 1.6876396128071482e-05,
"loss": 0.2959,
"step": 117500
},
{
"epoch": 3.137935619407252,
"grad_norm": 1.0889323949813843,
"learning_rate": 1.686315285607914e-05,
"loss": 0.3,
"step": 118000
},
{
"epoch": 3.151231900437448,
"grad_norm": 1.1839392185211182,
"learning_rate": 1.6849856398255507e-05,
"loss": 0.2975,
"step": 118500
},
{
"epoch": 3.1645281814676434,
"grad_norm": 0.779194712638855,
"learning_rate": 1.683655994043187e-05,
"loss": 0.3028,
"step": 119000
},
{
"epoch": 3.1778244624978393,
"grad_norm": 1.3120828866958618,
"learning_rate": 1.6823263482608234e-05,
"loss": 0.2929,
"step": 119500
},
{
"epoch": 3.1911207435280353,
"grad_norm": 1.7091648578643799,
"learning_rate": 1.68099670247846e-05,
"loss": 0.2948,
"step": 120000
},
{
"epoch": 3.1911207435280353,
"eval_loss": 0.3274182677268982,
"eval_runtime": 59.8113,
"eval_samples_per_second": 50.81,
"eval_steps_per_second": 12.707,
"step": 120000
},
{
"epoch": 3.2044436171202912,
"grad_norm": 1.2384920120239258,
"learning_rate": 1.679667056696096e-05,
"loss": 0.2823,
"step": 120500
},
{
"epoch": 3.217739898150487,
"grad_norm": 1.2225531339645386,
"learning_rate": 1.6783400702052975e-05,
"loss": 0.2925,
"step": 121000
},
{
"epoch": 3.231036179180683,
"grad_norm": 1.3342504501342773,
"learning_rate": 1.6770104244229338e-05,
"loss": 0.2906,
"step": 121500
},
{
"epoch": 3.244332460210879,
"grad_norm": 1.2133206129074097,
"learning_rate": 1.67568077864057e-05,
"loss": 0.2877,
"step": 122000
},
{
"epoch": 3.2576287412410747,
"grad_norm": 1.1577247381210327,
"learning_rate": 1.6743511328582068e-05,
"loss": 0.2876,
"step": 122500
},
{
"epoch": 3.2709250222712707,
"grad_norm": 1.1587375402450562,
"learning_rate": 1.673021487075843e-05,
"loss": 0.2937,
"step": 123000
},
{
"epoch": 3.2842213033014667,
"grad_norm": 1.1512658596038818,
"learning_rate": 1.6716918412934794e-05,
"loss": 0.2971,
"step": 123500
},
{
"epoch": 3.297517584331662,
"grad_norm": 0.8885172605514526,
"learning_rate": 1.670362195511116e-05,
"loss": 0.2825,
"step": 124000
},
{
"epoch": 3.310813865361858,
"grad_norm": 1.435475468635559,
"learning_rate": 1.6690325497287524e-05,
"loss": 0.2984,
"step": 124500
},
{
"epoch": 3.324110146392054,
"grad_norm": 1.7068617343902588,
"learning_rate": 1.6677029039463887e-05,
"loss": 0.2844,
"step": 125000
},
{
"epoch": 3.33740642742225,
"grad_norm": 0.8843211531639099,
"learning_rate": 1.6663732581640254e-05,
"loss": 0.2961,
"step": 125500
},
{
"epoch": 3.3507027084524457,
"grad_norm": 1.1262086629867554,
"learning_rate": 1.6650436123816614e-05,
"loss": 0.2896,
"step": 126000
},
{
"epoch": 3.3639989894826416,
"grad_norm": 1.073869228363037,
"learning_rate": 1.663713966599298e-05,
"loss": 0.2923,
"step": 126500
},
{
"epoch": 3.3772952705128376,
"grad_norm": 1.1707890033721924,
"learning_rate": 1.6623843208169347e-05,
"loss": 0.3003,
"step": 127000
},
{
"epoch": 3.3905915515430336,
"grad_norm": 1.2858471870422363,
"learning_rate": 1.6610546750345707e-05,
"loss": 0.3041,
"step": 127500
},
{
"epoch": 3.403887832573229,
"grad_norm": 0.9487111568450928,
"learning_rate": 1.6597250292522074e-05,
"loss": 0.2916,
"step": 128000
},
{
"epoch": 3.417184113603425,
"grad_norm": 1.1401737928390503,
"learning_rate": 1.6583953834698437e-05,
"loss": 0.2905,
"step": 128500
},
{
"epoch": 3.430480394633621,
"grad_norm": 0.862232506275177,
"learning_rate": 1.65706573768748e-05,
"loss": 0.292,
"step": 129000
},
{
"epoch": 3.443776675663817,
"grad_norm": 2.11210560798645,
"learning_rate": 1.6557360919051167e-05,
"loss": 0.2873,
"step": 129500
},
{
"epoch": 3.4570729566940126,
"grad_norm": 1.325928807258606,
"learning_rate": 1.654406446122753e-05,
"loss": 0.2874,
"step": 130000
},
{
"epoch": 3.4570729566940126,
"eval_loss": 0.27055609226226807,
"eval_runtime": 44.0558,
"eval_samples_per_second": 68.981,
"eval_steps_per_second": 17.251,
"step": 130000
},
{
"epoch": 3.4703692377242086,
"grad_norm": 0.9289048314094543,
"learning_rate": 1.6530768003403894e-05,
"loss": 0.2955,
"step": 130500
},
{
"epoch": 3.4836655187544046,
"grad_norm": 1.1079119443893433,
"learning_rate": 1.651747154558026e-05,
"loss": 0.3043,
"step": 131000
},
{
"epoch": 3.4969617997846,
"grad_norm": 0.927392840385437,
"learning_rate": 1.650420168067227e-05,
"loss": 0.2993,
"step": 131500
},
{
"epoch": 3.510258080814796,
"grad_norm": 1.21388578414917,
"learning_rate": 1.6490931815764282e-05,
"loss": 0.2922,
"step": 132000
},
{
"epoch": 3.523554361844992,
"grad_norm": 0.8197039365768433,
"learning_rate": 1.6477635357940645e-05,
"loss": 0.2945,
"step": 132500
},
{
"epoch": 3.536850642875188,
"grad_norm": 1.3974609375,
"learning_rate": 1.646433890011701e-05,
"loss": 0.2892,
"step": 133000
},
{
"epoch": 3.5501469239053836,
"grad_norm": 1.4183751344680786,
"learning_rate": 1.6451042442293375e-05,
"loss": 0.2879,
"step": 133500
},
{
"epoch": 3.5634432049355795,
"grad_norm": 1.218549132347107,
"learning_rate": 1.6437772577385386e-05,
"loss": 0.3097,
"step": 134000
},
{
"epoch": 3.5767394859657755,
"grad_norm": 1.6601920127868652,
"learning_rate": 1.642447611956175e-05,
"loss": 0.2867,
"step": 134500
},
{
"epoch": 3.590035766995971,
"grad_norm": 1.3657351732254028,
"learning_rate": 1.6411179661738116e-05,
"loss": 0.3013,
"step": 135000
},
{
"epoch": 3.603332048026167,
"grad_norm": 1.6279337406158447,
"learning_rate": 1.639788320391448e-05,
"loss": 0.3024,
"step": 135500
},
{
"epoch": 3.616628329056363,
"grad_norm": 1.4741065502166748,
"learning_rate": 1.6384586746090842e-05,
"loss": 0.2994,
"step": 136000
},
{
"epoch": 3.629924610086559,
"grad_norm": 1.1416784524917603,
"learning_rate": 1.637129028826721e-05,
"loss": 0.2996,
"step": 136500
},
{
"epoch": 3.6432208911167545,
"grad_norm": 1.3834564685821533,
"learning_rate": 1.635799383044357e-05,
"loss": 0.2884,
"step": 137000
},
{
"epoch": 3.6565171721469505,
"grad_norm": 1.2296993732452393,
"learning_rate": 1.6344697372619936e-05,
"loss": 0.2908,
"step": 137500
},
{
"epoch": 3.6698134531771465,
"grad_norm": 1.3037883043289185,
"learning_rate": 1.63314009147963e-05,
"loss": 0.2896,
"step": 138000
},
{
"epoch": 3.683109734207342,
"grad_norm": 1.5054666996002197,
"learning_rate": 1.6318104456972662e-05,
"loss": 0.2949,
"step": 138500
},
{
"epoch": 3.696406015237538,
"grad_norm": 1.01513671875,
"learning_rate": 1.630480799914903e-05,
"loss": 0.2964,
"step": 139000
},
{
"epoch": 3.709702296267734,
"grad_norm": 1.0762807130813599,
"learning_rate": 1.6291511541325392e-05,
"loss": 0.2938,
"step": 139500
},
{
"epoch": 3.72299857729793,
"grad_norm": 1.9730701446533203,
"learning_rate": 1.6278241676417403e-05,
"loss": 0.3019,
"step": 140000
},
{
"epoch": 3.72299857729793,
"eval_loss": 0.2732769846916199,
"eval_runtime": 44.8357,
"eval_samples_per_second": 67.781,
"eval_steps_per_second": 16.951,
"step": 140000
},
{
"epoch": 3.7362948583281255,
"grad_norm": 1.622164011001587,
"learning_rate": 1.626494521859377e-05,
"loss": 0.272,
"step": 140500
},
{
"epoch": 3.7495911393583214,
"grad_norm": 1.4417494535446167,
"learning_rate": 1.6251648760770133e-05,
"loss": 0.2696,
"step": 141000
},
{
"epoch": 3.7628874203885174,
"grad_norm": 0.9713847637176514,
"learning_rate": 1.6238352302946496e-05,
"loss": 0.276,
"step": 141500
},
{
"epoch": 3.776183701418713,
"grad_norm": 0.9661402106285095,
"learning_rate": 1.6225055845122863e-05,
"loss": 0.2773,
"step": 142000
},
{
"epoch": 3.789479982448909,
"grad_norm": 1.307726502418518,
"learning_rate": 1.6211759387299223e-05,
"loss": 0.2763,
"step": 142500
},
{
"epoch": 3.802776263479105,
"grad_norm": 1.0191502571105957,
"learning_rate": 1.619846292947559e-05,
"loss": 0.2872,
"step": 143000
},
{
"epoch": 3.816072544509301,
"grad_norm": 1.083509922027588,
"learning_rate": 1.6185166471651952e-05,
"loss": 0.2737,
"step": 143500
},
{
"epoch": 3.829368825539497,
"grad_norm": 1.0461057424545288,
"learning_rate": 1.6171870013828316e-05,
"loss": 0.2745,
"step": 144000
},
{
"epoch": 3.8426651065696924,
"grad_norm": 1.0616631507873535,
"learning_rate": 1.6158573556004682e-05,
"loss": 0.2753,
"step": 144500
},
{
"epoch": 3.8559613875998884,
"grad_norm": 1.418392539024353,
"learning_rate": 1.6145277098181046e-05,
"loss": 0.2815,
"step": 145000
},
{
"epoch": 3.869257668630084,
"grad_norm": 1.022754430770874,
"learning_rate": 1.613198064035741e-05,
"loss": 0.2721,
"step": 145500
},
{
"epoch": 3.88255394966028,
"grad_norm": 1.5018330812454224,
"learning_rate": 1.6118684182533776e-05,
"loss": 0.2804,
"step": 146000
},
{
"epoch": 3.895850230690476,
"grad_norm": 1.0998148918151855,
"learning_rate": 1.610538772471014e-05,
"loss": 0.2801,
"step": 146500
},
{
"epoch": 3.909146511720672,
"grad_norm": 1.5807846784591675,
"learning_rate": 1.6092091266886502e-05,
"loss": 0.2821,
"step": 147000
},
{
"epoch": 3.922442792750868,
"grad_norm": 1.443129539489746,
"learning_rate": 1.607879480906287e-05,
"loss": 0.2734,
"step": 147500
},
{
"epoch": 3.9357390737810634,
"grad_norm": 1.2961505651474,
"learning_rate": 1.6065498351239232e-05,
"loss": 0.2694,
"step": 148000
},
{
"epoch": 3.9490353548112593,
"grad_norm": 1.235811471939087,
"learning_rate": 1.6052228486331243e-05,
"loss": 0.2811,
"step": 148500
},
{
"epoch": 3.962331635841455,
"grad_norm": 1.3737879991531372,
"learning_rate": 1.6038932028507606e-05,
"loss": 0.2796,
"step": 149000
},
{
"epoch": 3.975627916871651,
"grad_norm": 1.3180122375488281,
"learning_rate": 1.602563557068397e-05,
"loss": 0.2752,
"step": 149500
},
{
"epoch": 3.988924197901847,
"grad_norm": 1.293617606163025,
"learning_rate": 1.6012339112860336e-05,
"loss": 0.2853,
"step": 150000
},
{
"epoch": 3.988924197901847,
"eval_loss": 0.24187567830085754,
"eval_runtime": 44.4954,
"eval_samples_per_second": 68.299,
"eval_steps_per_second": 17.08,
"step": 150000
},
{
"epoch": 4.002220478932043,
"grad_norm": 1.8393179178237915,
"learning_rate": 1.59990426550367e-05,
"loss": 0.2718,
"step": 150500
},
{
"epoch": 4.015516759962239,
"grad_norm": 1.5193239450454712,
"learning_rate": 1.5985746197213063e-05,
"loss": 0.2665,
"step": 151000
},
{
"epoch": 4.028813040992435,
"grad_norm": 1.0958846807479858,
"learning_rate": 1.597244973938943e-05,
"loss": 0.2725,
"step": 151500
},
{
"epoch": 4.04210932202263,
"grad_norm": 1.564980387687683,
"learning_rate": 1.595917987448144e-05,
"loss": 0.2745,
"step": 152000
},
{
"epoch": 4.055405603052826,
"grad_norm": 1.3031373023986816,
"learning_rate": 1.5945883416657803e-05,
"loss": 0.2646,
"step": 152500
},
{
"epoch": 4.068701884083022,
"grad_norm": 1.3589409589767456,
"learning_rate": 1.593258695883417e-05,
"loss": 0.2777,
"step": 153000
},
{
"epoch": 4.081998165113218,
"grad_norm": 1.092926263809204,
"learning_rate": 1.591929050101053e-05,
"loss": 0.2787,
"step": 153500
},
{
"epoch": 4.095294446143414,
"grad_norm": 1.362304925918579,
"learning_rate": 1.5906020636102544e-05,
"loss": 0.273,
"step": 154000
},
{
"epoch": 4.10859072717361,
"grad_norm": 1.3661013841629028,
"learning_rate": 1.5892724178278907e-05,
"loss": 0.2624,
"step": 154500
},
{
"epoch": 4.121887008203806,
"grad_norm": 0.923414945602417,
"learning_rate": 1.587942772045527e-05,
"loss": 0.2708,
"step": 155000
},
{
"epoch": 4.135183289234002,
"grad_norm": 1.3246159553527832,
"learning_rate": 1.5866131262631637e-05,
"loss": 0.2661,
"step": 155500
},
{
"epoch": 4.148479570264197,
"grad_norm": 1.3546644449234009,
"learning_rate": 1.5852834804808e-05,
"loss": 0.268,
"step": 156000
},
{
"epoch": 4.161775851294393,
"grad_norm": 1.048305630683899,
"learning_rate": 1.5839538346984364e-05,
"loss": 0.2711,
"step": 156500
},
{
"epoch": 4.175072132324589,
"grad_norm": 1.0217567682266235,
"learning_rate": 1.5826268482076378e-05,
"loss": 0.2689,
"step": 157000
},
{
"epoch": 4.188368413354785,
"grad_norm": 1.253959059715271,
"learning_rate": 1.5812972024252738e-05,
"loss": 0.2709,
"step": 157500
},
{
"epoch": 4.201664694384981,
"grad_norm": 1.3631120920181274,
"learning_rate": 1.5799675566429105e-05,
"loss": 0.2753,
"step": 158000
},
{
"epoch": 4.214960975415177,
"grad_norm": 1.5026861429214478,
"learning_rate": 1.578637910860547e-05,
"loss": 0.2729,
"step": 158500
},
{
"epoch": 4.228257256445373,
"grad_norm": 1.2928775548934937,
"learning_rate": 1.577308265078183e-05,
"loss": 0.2645,
"step": 159000
},
{
"epoch": 4.241553537475568,
"grad_norm": 0.8542189598083496,
"learning_rate": 1.5759812785873845e-05,
"loss": 0.2779,
"step": 159500
},
{
"epoch": 4.254849818505764,
"grad_norm": 1.4010766744613647,
"learning_rate": 1.574651632805021e-05,
"loss": 0.2709,
"step": 160000
},
{
"epoch": 4.254849818505764,
"eval_loss": 0.24389813840389252,
"eval_runtime": 44.8113,
"eval_samples_per_second": 67.818,
"eval_steps_per_second": 16.96,
"step": 160000
},
{
"epoch": 4.26814609953596,
"grad_norm": 1.1164586544036865,
"learning_rate": 1.5733219870226572e-05,
"loss": 0.2675,
"step": 160500
},
{
"epoch": 4.281442380566156,
"grad_norm": 1.361721158027649,
"learning_rate": 1.571992341240294e-05,
"loss": 0.2767,
"step": 161000
},
{
"epoch": 4.294738661596352,
"grad_norm": 1.3751747608184814,
"learning_rate": 1.5706626954579302e-05,
"loss": 0.2672,
"step": 161500
},
{
"epoch": 4.308034942626548,
"grad_norm": 1.032375693321228,
"learning_rate": 1.5693357089671313e-05,
"loss": 0.2786,
"step": 162000
},
{
"epoch": 4.321331223656744,
"grad_norm": 1.288988471031189,
"learning_rate": 1.568006063184768e-05,
"loss": 0.2845,
"step": 162500
},
{
"epoch": 4.334627504686939,
"grad_norm": 1.0330158472061157,
"learning_rate": 1.566676417402404e-05,
"loss": 0.2811,
"step": 163000
},
{
"epoch": 4.347923785717135,
"grad_norm": 1.7785344123840332,
"learning_rate": 1.5653467716200406e-05,
"loss": 0.2791,
"step": 163500
},
{
"epoch": 4.361220066747331,
"grad_norm": 1.7403333187103271,
"learning_rate": 1.5640197851292417e-05,
"loss": 0.2773,
"step": 164000
},
{
"epoch": 4.374516347777527,
"grad_norm": 1.0584579706192017,
"learning_rate": 1.562690139346878e-05,
"loss": 0.2711,
"step": 164500
},
{
"epoch": 4.387812628807723,
"grad_norm": 1.419774055480957,
"learning_rate": 1.5613604935645147e-05,
"loss": 0.2762,
"step": 165000
},
{
"epoch": 4.401108909837919,
"grad_norm": 1.3535691499710083,
"learning_rate": 1.560030847782151e-05,
"loss": 0.271,
"step": 165500
},
{
"epoch": 4.414405190868115,
"grad_norm": 1.4730337858200073,
"learning_rate": 1.5587012019997873e-05,
"loss": 0.2753,
"step": 166000
},
{
"epoch": 4.42770147189831,
"grad_norm": 1.1973862648010254,
"learning_rate": 1.557371556217424e-05,
"loss": 0.2731,
"step": 166500
},
{
"epoch": 4.440997752928506,
"grad_norm": 1.2967299222946167,
"learning_rate": 1.5560472290181895e-05,
"loss": 0.2815,
"step": 167000
},
{
"epoch": 4.454294033958702,
"grad_norm": 1.1886343955993652,
"learning_rate": 1.554717583235826e-05,
"loss": 0.27,
"step": 167500
},
{
"epoch": 4.467590314988898,
"grad_norm": 1.6000491380691528,
"learning_rate": 1.5533879374534625e-05,
"loss": 0.28,
"step": 168000
},
{
"epoch": 4.480886596019094,
"grad_norm": 1.6364268064498901,
"learning_rate": 1.5520582916710988e-05,
"loss": 0.2741,
"step": 168500
},
{
"epoch": 4.4941828770492895,
"grad_norm": 1.4403234720230103,
"learning_rate": 1.5507286458887355e-05,
"loss": 0.2768,
"step": 169000
},
{
"epoch": 4.5074791580794855,
"grad_norm": 1.1721081733703613,
"learning_rate": 1.5493990001063718e-05,
"loss": 0.2812,
"step": 169500
},
{
"epoch": 4.520775439109681,
"grad_norm": 1.213318943977356,
"learning_rate": 1.548072013615573e-05,
"loss": 0.2772,
"step": 170000
},
{
"epoch": 4.520775439109681,
"eval_loss": 0.2475610226392746,
"eval_runtime": 44.8886,
"eval_samples_per_second": 67.701,
"eval_steps_per_second": 16.931,
"step": 170000
},
{
"epoch": 4.534071720139877,
"grad_norm": 1.3363765478134155,
"learning_rate": 1.5467423678332095e-05,
"loss": 0.2748,
"step": 170500
},
{
"epoch": 4.547368001170073,
"grad_norm": 1.1976338624954224,
"learning_rate": 1.5454127220508455e-05,
"loss": 0.2731,
"step": 171000
},
{
"epoch": 4.5606642822002685,
"grad_norm": 1.1618109941482544,
"learning_rate": 1.5440830762684822e-05,
"loss": 0.2772,
"step": 171500
},
{
"epoch": 4.5739605632304645,
"grad_norm": 1.5081138610839844,
"learning_rate": 1.542753430486119e-05,
"loss": 0.2711,
"step": 172000
},
{
"epoch": 4.5872568442606605,
"grad_norm": 1.2148953676223755,
"learning_rate": 1.541423784703755e-05,
"loss": 0.2708,
"step": 172500
},
{
"epoch": 4.6005531252908565,
"grad_norm": 0.9179415702819824,
"learning_rate": 1.5400941389213915e-05,
"loss": 0.2674,
"step": 173000
},
{
"epoch": 4.613849406321052,
"grad_norm": 1.1413265466690063,
"learning_rate": 1.538764493139028e-05,
"loss": 0.2747,
"step": 173500
},
{
"epoch": 4.6271456873512475,
"grad_norm": 1.0427721738815308,
"learning_rate": 1.537434847356664e-05,
"loss": 0.2802,
"step": 174000
},
{
"epoch": 4.6404419683814435,
"grad_norm": 1.8311312198638916,
"learning_rate": 1.5361052015743008e-05,
"loss": 0.2746,
"step": 174500
},
{
"epoch": 4.6537382494116395,
"grad_norm": 1.482964038848877,
"learning_rate": 1.534775555791937e-05,
"loss": 0.2661,
"step": 175000
},
{
"epoch": 4.6670345304418355,
"grad_norm": 1.2513574361801147,
"learning_rate": 1.5334485693011382e-05,
"loss": 0.2654,
"step": 175500
},
{
"epoch": 4.6803308114720314,
"grad_norm": 1.0544030666351318,
"learning_rate": 1.532118923518775e-05,
"loss": 0.2783,
"step": 176000
},
{
"epoch": 4.693627092502227,
"grad_norm": 1.350472331047058,
"learning_rate": 1.530789277736411e-05,
"loss": 0.2846,
"step": 176500
},
{
"epoch": 4.7069233735324225,
"grad_norm": 1.0775673389434814,
"learning_rate": 1.5294596319540476e-05,
"loss": 0.2759,
"step": 177000
},
{
"epoch": 4.7202196545626185,
"grad_norm": 0.8350367546081543,
"learning_rate": 1.5281299861716842e-05,
"loss": 0.2778,
"step": 177500
},
{
"epoch": 4.7335159355928145,
"grad_norm": 1.2634960412979126,
"learning_rate": 1.5268003403893202e-05,
"loss": 0.2754,
"step": 178000
},
{
"epoch": 4.7468122166230104,
"grad_norm": 1.2727707624435425,
"learning_rate": 1.5254706946069569e-05,
"loss": 0.2811,
"step": 178500
},
{
"epoch": 4.760108497653206,
"grad_norm": 1.2721821069717407,
"learning_rate": 1.5241410488245934e-05,
"loss": 0.2765,
"step": 179000
},
{
"epoch": 4.773404778683402,
"grad_norm": 1.0992257595062256,
"learning_rate": 1.522816721625359e-05,
"loss": 0.2767,
"step": 179500
},
{
"epoch": 4.786701059713598,
"grad_norm": 0.9015975594520569,
"learning_rate": 1.5214870758429955e-05,
"loss": 0.2713,
"step": 180000
},
{
"epoch": 4.786701059713598,
"eval_loss": 0.24829423427581787,
"eval_runtime": 44.7845,
"eval_samples_per_second": 67.858,
"eval_steps_per_second": 16.97,
"step": 180000
},
{
"epoch": 4.7999973407437935,
"grad_norm": 1.1640844345092773,
"learning_rate": 1.5201600893521966e-05,
"loss": 0.2836,
"step": 180500
},
{
"epoch": 4.8132936217739895,
"grad_norm": 1.0341435670852661,
"learning_rate": 1.5188304435698331e-05,
"loss": 0.2761,
"step": 181000
},
{
"epoch": 4.826589902804185,
"grad_norm": 1.327324628829956,
"learning_rate": 1.5175007977874696e-05,
"loss": 0.2791,
"step": 181500
},
{
"epoch": 4.839886183834381,
"grad_norm": 0.8103187084197998,
"learning_rate": 1.5161738112966707e-05,
"loss": 0.2879,
"step": 182000
},
{
"epoch": 4.853182464864577,
"grad_norm": 0.7801828384399414,
"learning_rate": 1.5148441655143072e-05,
"loss": 0.2756,
"step": 182500
},
{
"epoch": 4.866478745894773,
"grad_norm": 1.30203378200531,
"learning_rate": 1.5135145197319437e-05,
"loss": 0.277,
"step": 183000
},
{
"epoch": 4.879775026924969,
"grad_norm": 1.3664675951004028,
"learning_rate": 1.5121848739495799e-05,
"loss": 0.2731,
"step": 183500
},
{
"epoch": 4.893071307955165,
"grad_norm": 1.314031720161438,
"learning_rate": 1.5108552281672163e-05,
"loss": 0.2729,
"step": 184000
},
{
"epoch": 4.90636758898536,
"grad_norm": 0.8956036567687988,
"learning_rate": 1.5095255823848527e-05,
"loss": 0.2788,
"step": 184500
},
{
"epoch": 4.919663870015556,
"grad_norm": 1.520376205444336,
"learning_rate": 1.5081959366024892e-05,
"loss": 0.2845,
"step": 185000
},
{
"epoch": 4.932960151045752,
"grad_norm": 1.3505889177322388,
"learning_rate": 1.5068662908201257e-05,
"loss": 0.2818,
"step": 185500
},
{
"epoch": 4.946256432075948,
"grad_norm": 0.6950279474258423,
"learning_rate": 1.505536645037762e-05,
"loss": 0.2737,
"step": 186000
},
{
"epoch": 4.959552713106144,
"grad_norm": 1.2404699325561523,
"learning_rate": 1.5042069992553985e-05,
"loss": 0.2813,
"step": 186500
},
{
"epoch": 4.97284899413634,
"grad_norm": 1.1977089643478394,
"learning_rate": 1.5028800127645997e-05,
"loss": 0.2758,
"step": 187000
},
{
"epoch": 4.986145275166536,
"grad_norm": 1.2810465097427368,
"learning_rate": 1.501550366982236e-05,
"loss": 0.287,
"step": 187500
},
{
"epoch": 4.999441556196732,
"grad_norm": 2.558598756790161,
"learning_rate": 1.5002207211998726e-05,
"loss": 0.2701,
"step": 188000
},
{
"epoch": 5.012737837226927,
"grad_norm": 1.2791069746017456,
"learning_rate": 1.498891075417509e-05,
"loss": 0.2406,
"step": 188500
},
{
"epoch": 5.026034118257123,
"grad_norm": 1.0913165807724,
"learning_rate": 1.4975614296351452e-05,
"loss": 0.2307,
"step": 189000
},
{
"epoch": 5.039330399287319,
"grad_norm": 1.1861522197723389,
"learning_rate": 1.4962317838527817e-05,
"loss": 0.2429,
"step": 189500
},
{
"epoch": 5.052626680317515,
"grad_norm": 1.2686249017715454,
"learning_rate": 1.494902138070418e-05,
"loss": 0.2395,
"step": 190000
},
{
"epoch": 5.052626680317515,
"eval_loss": 0.2490723580121994,
"eval_runtime": 43.0318,
"eval_samples_per_second": 70.622,
"eval_steps_per_second": 17.661,
"step": 190000
},
{
"epoch": 5.065922961347711,
"grad_norm": 1.4228299856185913,
"learning_rate": 1.4935724922880545e-05,
"loss": 0.2493,
"step": 190500
},
{
"epoch": 5.079219242377907,
"grad_norm": 1.0055017471313477,
"learning_rate": 1.492242846505691e-05,
"loss": 0.2522,
"step": 191000
},
{
"epoch": 5.092515523408102,
"grad_norm": 0.8438519239425659,
"learning_rate": 1.4909132007233274e-05,
"loss": 0.2546,
"step": 191500
},
{
"epoch": 5.105811804438298,
"grad_norm": 1.2010571956634521,
"learning_rate": 1.4895862142325286e-05,
"loss": 0.2352,
"step": 192000
},
{
"epoch": 5.119108085468494,
"grad_norm": 1.275994062423706,
"learning_rate": 1.4882565684501651e-05,
"loss": 0.2372,
"step": 192500
},
{
"epoch": 5.13240436649869,
"grad_norm": 0.7371090054512024,
"learning_rate": 1.4869269226678014e-05,
"loss": 0.2487,
"step": 193000
},
{
"epoch": 5.145700647528886,
"grad_norm": 1.3083887100219727,
"learning_rate": 1.485597276885438e-05,
"loss": 0.2485,
"step": 193500
},
{
"epoch": 5.158996928559082,
"grad_norm": 0.972006618976593,
"learning_rate": 1.4842676311030744e-05,
"loss": 0.2517,
"step": 194000
},
{
"epoch": 5.172293209589278,
"grad_norm": 1.3523329496383667,
"learning_rate": 1.4829379853207106e-05,
"loss": 0.243,
"step": 194500
},
{
"epoch": 5.185589490619474,
"grad_norm": 1.2454783916473389,
"learning_rate": 1.4816109988299118e-05,
"loss": 0.2456,
"step": 195000
},
{
"epoch": 5.198885771649669,
"grad_norm": 1.2170870304107666,
"learning_rate": 1.480284012339113e-05,
"loss": 0.2524,
"step": 195500
},
{
"epoch": 5.212182052679865,
"grad_norm": 1.7185641527175903,
"learning_rate": 1.4789570258483142e-05,
"loss": 0.2403,
"step": 196000
},
{
"epoch": 5.225478333710061,
"grad_norm": 1.2505462169647217,
"learning_rate": 1.4776273800659507e-05,
"loss": 0.248,
"step": 196500
},
{
"epoch": 5.238774614740257,
"grad_norm": 1.061320424079895,
"learning_rate": 1.4762977342835868e-05,
"loss": 0.2522,
"step": 197000
},
{
"epoch": 5.252070895770453,
"grad_norm": 1.1784652471542358,
"learning_rate": 1.4749680885012235e-05,
"loss": 0.2471,
"step": 197500
},
{
"epoch": 5.265367176800649,
"grad_norm": 1.6446605920791626,
"learning_rate": 1.47363844271886e-05,
"loss": 0.2459,
"step": 198000
},
{
"epoch": 5.278663457830845,
"grad_norm": 1.7436884641647339,
"learning_rate": 1.4723087969364962e-05,
"loss": 0.2452,
"step": 198500
},
{
"epoch": 5.29195973886104,
"grad_norm": 1.2458696365356445,
"learning_rate": 1.4709791511541326e-05,
"loss": 0.2535,
"step": 199000
},
{
"epoch": 5.305256019891236,
"grad_norm": 1.1361490488052368,
"learning_rate": 1.469649505371769e-05,
"loss": 0.2444,
"step": 199500
},
{
"epoch": 5.318552300921432,
"grad_norm": 1.2189501523971558,
"learning_rate": 1.4683198595894055e-05,
"loss": 0.2509,
"step": 200000
},
{
"epoch": 5.318552300921432,
"eval_loss": 0.25082090497016907,
"eval_runtime": 56.1856,
"eval_samples_per_second": 54.089,
"eval_steps_per_second": 13.527,
"step": 200000
}
],
"logging_steps": 500,
"max_steps": 752080,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 10000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.334195659820237e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}