Gencode-BPE / checkpoint-1125 /trainer_state.json
andyjzhao's picture
Upload folder using huggingface_hub
4fdab16 verified
{
"best_global_step": 1125,
"best_metric": 5.3796281814575195,
"best_model_checkpoint": "/gpfs/scratch/guoh/DNAFM/output/gencode_human_12.8k_12800/Gencode-BPE/checkpoint-1125",
"epoch": 0.3191489361702128,
"eval_steps": 125,
"global_step": 1125,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005673758865248227,
"grad_norm": 1275.0146484375,
"loss": 281.4781,
"lr": 2e-06,
"step": 2,
"tokens_trained": 0.000192256
},
{
"epoch": 0.0011347517730496454,
"grad_norm": 1437.579833984375,
"loss": 267.2211,
"lr": 6e-06,
"step": 4,
"tokens_trained": 0.000382024
},
{
"epoch": 0.001702127659574468,
"grad_norm": 1719.271484375,
"loss": 219.3822,
"lr": 1e-05,
"step": 6,
"tokens_trained": 0.00057072
},
{
"epoch": 0.0022695035460992908,
"grad_norm": 1444.94970703125,
"loss": 133.8172,
"lr": 1.4e-05,
"step": 8,
"tokens_trained": 0.000761336
},
{
"epoch": 0.0028368794326241137,
"grad_norm": 238.9689178466797,
"loss": 90.8177,
"lr": 1.8e-05,
"step": 10,
"tokens_trained": 0.000953248
},
{
"epoch": 0.003404255319148936,
"grad_norm": 158.53497314453125,
"loss": 84.6922,
"lr": 2.2e-05,
"step": 12,
"tokens_trained": 0.00114424
},
{
"epoch": 0.003971631205673759,
"grad_norm": 146.10595703125,
"loss": 76.7055,
"lr": 2.6e-05,
"step": 14,
"tokens_trained": 0.001334104
},
{
"epoch": 0.0045390070921985815,
"grad_norm": 140.69964599609375,
"loss": 67.9952,
"lr": 3e-05,
"step": 16,
"tokens_trained": 0.00152392
},
{
"epoch": 0.005106382978723404,
"grad_norm": 108.80303192138672,
"loss": 57.8088,
"lr": 3.4000000000000007e-05,
"step": 18,
"tokens_trained": 0.001713872
},
{
"epoch": 0.005673758865248227,
"grad_norm": 106.82334899902344,
"loss": 48.6585,
"lr": 3.8e-05,
"step": 20,
"tokens_trained": 0.001903976
},
{
"epoch": 0.00624113475177305,
"grad_norm": 93.58769989013672,
"loss": 41.7984,
"lr": 4.2000000000000004e-05,
"step": 22,
"tokens_trained": 0.002094288
},
{
"epoch": 0.006808510638297872,
"grad_norm": 87.5854721069336,
"loss": 37.6201,
"lr": 4.6e-05,
"step": 24,
"tokens_trained": 0.002282496
},
{
"epoch": 0.007375886524822695,
"grad_norm": 84.12794494628906,
"loss": 35.0091,
"lr": 5e-05,
"step": 26,
"tokens_trained": 0.00247068
},
{
"epoch": 0.007943262411347518,
"grad_norm": 79.77535247802734,
"loss": 33.2253,
"lr": 5.4e-05,
"step": 28,
"tokens_trained": 0.002662888
},
{
"epoch": 0.00851063829787234,
"grad_norm": 66.42157745361328,
"loss": 32.0682,
"lr": 5.800000000000001e-05,
"step": 30,
"tokens_trained": 0.002851968
},
{
"epoch": 0.009078014184397163,
"grad_norm": 87.52485656738281,
"loss": 30.893,
"lr": 6.2e-05,
"step": 32,
"tokens_trained": 0.003041384
},
{
"epoch": 0.009645390070921986,
"grad_norm": 58.33614730834961,
"loss": 30.0513,
"lr": 6.6e-05,
"step": 34,
"tokens_trained": 0.003232872
},
{
"epoch": 0.010212765957446808,
"grad_norm": 54.629329681396484,
"loss": 29.0115,
"lr": 7.000000000000001e-05,
"step": 36,
"tokens_trained": 0.003423824
},
{
"epoch": 0.01078014184397163,
"grad_norm": 52.79097366333008,
"loss": 28.2084,
"lr": 7.4e-05,
"step": 38,
"tokens_trained": 0.003613232
},
{
"epoch": 0.011347517730496455,
"grad_norm": 54.481224060058594,
"loss": 27.4345,
"lr": 7.8e-05,
"step": 40,
"tokens_trained": 0.003800952
},
{
"epoch": 0.011914893617021277,
"grad_norm": 58.7069091796875,
"loss": 26.5936,
"lr": 8.2e-05,
"step": 42,
"tokens_trained": 0.003991512
},
{
"epoch": 0.0124822695035461,
"grad_norm": 49.30760955810547,
"loss": 26.0608,
"lr": 8.599999999999999e-05,
"step": 44,
"tokens_trained": 0.004180648
},
{
"epoch": 0.013049645390070922,
"grad_norm": 61.902587890625,
"loss": 25.5363,
"lr": 8.999999999999999e-05,
"step": 46,
"tokens_trained": 0.00437148
},
{
"epoch": 0.013617021276595745,
"grad_norm": 46.76111602783203,
"loss": 24.9599,
"lr": 9.400000000000001e-05,
"step": 48,
"tokens_trained": 0.004559344
},
{
"epoch": 0.014184397163120567,
"grad_norm": 57.06416702270508,
"loss": 24.4087,
"lr": 9.800000000000001e-05,
"step": 50,
"tokens_trained": 0.004749256
},
{
"epoch": 0.01475177304964539,
"grad_norm": 44.798736572265625,
"loss": 24.1444,
"lr": 0.000102,
"step": 52,
"tokens_trained": 0.004940192
},
{
"epoch": 0.015319148936170212,
"grad_norm": 40.29296875,
"loss": 23.6011,
"lr": 0.000106,
"step": 54,
"tokens_trained": 0.005130304
},
{
"epoch": 0.015886524822695036,
"grad_norm": 38.75099563598633,
"loss": 23.1781,
"lr": 0.00011,
"step": 56,
"tokens_trained": 0.005322864
},
{
"epoch": 0.016453900709219857,
"grad_norm": 37.470706939697266,
"loss": 22.9136,
"lr": 0.000114,
"step": 58,
"tokens_trained": 0.00551392
},
{
"epoch": 0.01702127659574468,
"grad_norm": 35.1894645690918,
"loss": 22.6336,
"lr": 0.000118,
"step": 60,
"tokens_trained": 0.005703096
},
{
"epoch": 0.017588652482269502,
"grad_norm": 35.136573791503906,
"loss": 22.2998,
"lr": 0.000122,
"step": 62,
"tokens_trained": 0.005892448
},
{
"epoch": 0.018156028368794326,
"grad_norm": 38.05111312866211,
"loss": 21.9401,
"lr": 0.000126,
"step": 64,
"tokens_trained": 0.006081656
},
{
"epoch": 0.01872340425531915,
"grad_norm": 35.63850021362305,
"loss": 21.7206,
"lr": 0.00013000000000000002,
"step": 66,
"tokens_trained": 0.006273032
},
{
"epoch": 0.01929078014184397,
"grad_norm": 34.327667236328125,
"loss": 21.4051,
"lr": 0.000134,
"step": 68,
"tokens_trained": 0.00646304
},
{
"epoch": 0.019858156028368795,
"grad_norm": 31.457059860229492,
"loss": 21.0774,
"lr": 0.00013800000000000002,
"step": 70,
"tokens_trained": 0.006652832
},
{
"epoch": 0.020425531914893616,
"grad_norm": 34.91672897338867,
"loss": 20.8718,
"lr": 0.00014199999999999998,
"step": 72,
"tokens_trained": 0.006843512
},
{
"epoch": 0.02099290780141844,
"grad_norm": 27.959579467773438,
"loss": 20.6932,
"lr": 0.000146,
"step": 74,
"tokens_trained": 0.007033584
},
{
"epoch": 0.02156028368794326,
"grad_norm": 26.569866180419922,
"loss": 20.4072,
"lr": 0.00015,
"step": 76,
"tokens_trained": 0.007224032
},
{
"epoch": 0.022127659574468085,
"grad_norm": 28.009904861450195,
"loss": 20.2229,
"lr": 0.000154,
"step": 78,
"tokens_trained": 0.00741368
},
{
"epoch": 0.02269503546099291,
"grad_norm": 28.892959594726562,
"loss": 20.0528,
"lr": 0.000158,
"step": 80,
"tokens_trained": 0.00760416
},
{
"epoch": 0.02326241134751773,
"grad_norm": 31.58131980895996,
"loss": 19.8016,
"lr": 0.000162,
"step": 82,
"tokens_trained": 0.007793952
},
{
"epoch": 0.023829787234042554,
"grad_norm": 31.01254653930664,
"loss": 19.634,
"lr": 0.00016600000000000002,
"step": 84,
"tokens_trained": 0.007980792
},
{
"epoch": 0.024397163120567375,
"grad_norm": 28.732515335083008,
"loss": 19.3777,
"lr": 0.00017,
"step": 86,
"tokens_trained": 0.008171968
},
{
"epoch": 0.0249645390070922,
"grad_norm": 24.31264877319336,
"loss": 19.1346,
"lr": 0.000174,
"step": 88,
"tokens_trained": 0.008361632
},
{
"epoch": 0.02553191489361702,
"grad_norm": 26.557010650634766,
"loss": 19.0014,
"lr": 0.000178,
"step": 90,
"tokens_trained": 0.008552328
},
{
"epoch": 0.026099290780141844,
"grad_norm": 21.156103134155273,
"loss": 18.7032,
"lr": 0.000182,
"step": 92,
"tokens_trained": 0.008743136
},
{
"epoch": 0.02666666666666667,
"grad_norm": 25.7484188079834,
"loss": 18.4836,
"lr": 0.000186,
"step": 94,
"tokens_trained": 0.008932056
},
{
"epoch": 0.02723404255319149,
"grad_norm": 22.27949333190918,
"loss": 18.2233,
"lr": 0.00019,
"step": 96,
"tokens_trained": 0.009121608
},
{
"epoch": 0.027801418439716313,
"grad_norm": 24.9247989654541,
"loss": 17.9867,
"lr": 0.000194,
"step": 98,
"tokens_trained": 0.009311008
},
{
"epoch": 0.028368794326241134,
"grad_norm": 24.302066802978516,
"loss": 17.8016,
"lr": 0.00019800000000000002,
"step": 100,
"tokens_trained": 0.009501456
},
{
"epoch": 0.02893617021276596,
"grad_norm": 23.458459854125977,
"loss": 17.6295,
"lr": 0.000202,
"step": 102,
"tokens_trained": 0.009693952
},
{
"epoch": 0.02950354609929078,
"grad_norm": 24.092350006103516,
"loss": 17.4593,
"lr": 0.000206,
"step": 104,
"tokens_trained": 0.009883328
},
{
"epoch": 0.030070921985815603,
"grad_norm": 22.54726219177246,
"loss": 17.2141,
"lr": 0.00021,
"step": 106,
"tokens_trained": 0.01007316
},
{
"epoch": 0.030638297872340424,
"grad_norm": 21.334760665893555,
"loss": 17.044,
"lr": 0.000214,
"step": 108,
"tokens_trained": 0.010266504
},
{
"epoch": 0.031205673758865248,
"grad_norm": 20.584287643432617,
"loss": 16.8919,
"lr": 0.000218,
"step": 110,
"tokens_trained": 0.010455736
},
{
"epoch": 0.03177304964539007,
"grad_norm": 23.51676368713379,
"loss": 16.751,
"lr": 0.000222,
"step": 112,
"tokens_trained": 0.010645208
},
{
"epoch": 0.03234042553191489,
"grad_norm": 23.278276443481445,
"loss": 16.5997,
"lr": 0.00022600000000000002,
"step": 114,
"tokens_trained": 0.010838928
},
{
"epoch": 0.032907801418439714,
"grad_norm": 25.4830265045166,
"loss": 16.3416,
"lr": 0.00023,
"step": 116,
"tokens_trained": 0.011027792
},
{
"epoch": 0.03347517730496454,
"grad_norm": 29.442413330078125,
"loss": 16.24,
"lr": 0.00023400000000000002,
"step": 118,
"tokens_trained": 0.011217456
},
{
"epoch": 0.03404255319148936,
"grad_norm": 21.77578353881836,
"loss": 16.1922,
"lr": 0.00023799999999999998,
"step": 120,
"tokens_trained": 0.01140804
},
{
"epoch": 0.03460992907801418,
"grad_norm": 27.040719985961914,
"loss": 15.9059,
"lr": 0.000242,
"step": 122,
"tokens_trained": 0.011597816
},
{
"epoch": 0.035177304964539004,
"grad_norm": 24.74480628967285,
"loss": 15.7818,
"lr": 0.000246,
"step": 124,
"tokens_trained": 0.011785624
},
{
"epoch": 0.03546099290780142,
"eval_loss": 15.553059577941895,
"eval_runtime": 23.5485,
"step": 125,
"tokens_trained": 0.011880832
},
{
"epoch": 0.03574468085106383,
"grad_norm": 23.13482666015625,
"loss": 15.5739,
"lr": 0.00025,
"step": 126,
"tokens_trained": 0.011975976
},
{
"epoch": 0.03631205673758865,
"grad_norm": 22.8618106842041,
"loss": 15.4302,
"lr": 0.000254,
"step": 128,
"tokens_trained": 0.012166744
},
{
"epoch": 0.03687943262411347,
"grad_norm": 26.804859161376953,
"loss": 15.3623,
"lr": 0.00025800000000000004,
"step": 130,
"tokens_trained": 0.01235436
},
{
"epoch": 0.0374468085106383,
"grad_norm": 21.826601028442383,
"loss": 15.1465,
"lr": 0.000262,
"step": 132,
"tokens_trained": 0.012544976
},
{
"epoch": 0.03801418439716312,
"grad_norm": 39.447086334228516,
"loss": 15.0137,
"lr": 0.000266,
"step": 134,
"tokens_trained": 0.012736352
},
{
"epoch": 0.03858156028368794,
"grad_norm": 23.44275665283203,
"loss": 14.9355,
"lr": 0.00027,
"step": 136,
"tokens_trained": 0.012925008
},
{
"epoch": 0.03914893617021276,
"grad_norm": 21.631427764892578,
"loss": 14.6825,
"lr": 0.00027400000000000005,
"step": 138,
"tokens_trained": 0.013114672
},
{
"epoch": 0.03971631205673759,
"grad_norm": 23.674650192260742,
"loss": 14.5194,
"lr": 0.00027800000000000004,
"step": 140,
"tokens_trained": 0.013304016
},
{
"epoch": 0.04028368794326241,
"grad_norm": 23.974796295166016,
"loss": 14.4829,
"lr": 0.00028199999999999997,
"step": 142,
"tokens_trained": 0.013496696
},
{
"epoch": 0.04085106382978723,
"grad_norm": 26.112201690673828,
"loss": 14.3027,
"lr": 0.00028599999999999996,
"step": 144,
"tokens_trained": 0.013684816
},
{
"epoch": 0.04141843971631206,
"grad_norm": 20.67386817932129,
"loss": 14.1499,
"lr": 0.00029,
"step": 146,
"tokens_trained": 0.013874832
},
{
"epoch": 0.04198581560283688,
"grad_norm": 24.253408432006836,
"loss": 13.9378,
"lr": 0.000294,
"step": 148,
"tokens_trained": 0.014065056
},
{
"epoch": 0.0425531914893617,
"grad_norm": 35.716087341308594,
"loss": 14.0562,
"lr": 0.000298,
"step": 150,
"tokens_trained": 0.014256784
},
{
"epoch": 0.04312056737588652,
"grad_norm": 29.414331436157227,
"loss": 14.0462,
"lr": 0.000302,
"step": 152,
"tokens_trained": 0.014446312
},
{
"epoch": 0.04368794326241135,
"grad_norm": 30.687482833862305,
"loss": 13.7603,
"lr": 0.000306,
"step": 154,
"tokens_trained": 0.014639872
},
{
"epoch": 0.04425531914893617,
"grad_norm": 29.806455612182617,
"loss": 13.708,
"lr": 0.00031,
"step": 156,
"tokens_trained": 0.014831112
},
{
"epoch": 0.04482269503546099,
"grad_norm": 24.900897979736328,
"loss": 13.548,
"lr": 0.000314,
"step": 158,
"tokens_trained": 0.015021288
},
{
"epoch": 0.04539007092198582,
"grad_norm": 24.29252815246582,
"loss": 13.3119,
"lr": 0.00031800000000000003,
"step": 160,
"tokens_trained": 0.01521228
},
{
"epoch": 0.04595744680851064,
"grad_norm": 20.68342399597168,
"loss": 13.1829,
"lr": 0.000322,
"step": 162,
"tokens_trained": 0.015403688
},
{
"epoch": 0.04652482269503546,
"grad_norm": 20.822795867919922,
"loss": 12.9044,
"lr": 0.000326,
"step": 164,
"tokens_trained": 0.015593416
},
{
"epoch": 0.04709219858156028,
"grad_norm": 21.689916610717773,
"loss": 12.6862,
"lr": 0.00033,
"step": 166,
"tokens_trained": 0.015784408
},
{
"epoch": 0.04765957446808511,
"grad_norm": 17.873889923095703,
"loss": 12.5502,
"lr": 0.00033400000000000004,
"step": 168,
"tokens_trained": 0.0159744
},
{
"epoch": 0.04822695035460993,
"grad_norm": 18.951616287231445,
"loss": 12.308,
"lr": 0.00033800000000000003,
"step": 170,
"tokens_trained": 0.016163736
},
{
"epoch": 0.04879432624113475,
"grad_norm": 15.146363258361816,
"loss": 12.1558,
"lr": 0.000342,
"step": 172,
"tokens_trained": 0.016353832
},
{
"epoch": 0.04936170212765958,
"grad_norm": 18.336984634399414,
"loss": 12.0386,
"lr": 0.000346,
"step": 174,
"tokens_trained": 0.016545088
},
{
"epoch": 0.0499290780141844,
"grad_norm": 17.221126556396484,
"loss": 11.8791,
"lr": 0.00035,
"step": 176,
"tokens_trained": 0.016735704
},
{
"epoch": 0.05049645390070922,
"grad_norm": 19.362564086914062,
"loss": 11.7224,
"lr": 0.000354,
"step": 178,
"tokens_trained": 0.016927944
},
{
"epoch": 0.05106382978723404,
"grad_norm": 15.564507484436035,
"loss": 11.6448,
"lr": 0.000358,
"step": 180,
"tokens_trained": 0.017116096
},
{
"epoch": 0.05163120567375887,
"grad_norm": 20.711383819580078,
"loss": 11.4398,
"lr": 0.000362,
"step": 182,
"tokens_trained": 0.01730564
},
{
"epoch": 0.05219858156028369,
"grad_norm": 18.627403259277344,
"loss": 11.3377,
"lr": 0.000366,
"step": 184,
"tokens_trained": 0.017495864
},
{
"epoch": 0.05276595744680851,
"grad_norm": 15.00942325592041,
"loss": 11.1416,
"lr": 0.00037,
"step": 186,
"tokens_trained": 0.017686464
},
{
"epoch": 0.05333333333333334,
"grad_norm": 17.070598602294922,
"loss": 11.0148,
"lr": 0.000374,
"step": 188,
"tokens_trained": 0.017879488
},
{
"epoch": 0.05390070921985816,
"grad_norm": 16.101457595825195,
"loss": 10.8874,
"lr": 0.000378,
"step": 190,
"tokens_trained": 0.018068312
},
{
"epoch": 0.05446808510638298,
"grad_norm": 15.613334655761719,
"loss": 10.7055,
"lr": 0.000382,
"step": 192,
"tokens_trained": 0.018255752
},
{
"epoch": 0.0550354609929078,
"grad_norm": 17.671857833862305,
"loss": 10.5706,
"lr": 0.000386,
"step": 194,
"tokens_trained": 0.018447096
},
{
"epoch": 0.05560283687943263,
"grad_norm": 16.080909729003906,
"loss": 10.4476,
"lr": 0.00039000000000000005,
"step": 196,
"tokens_trained": 0.018637264
},
{
"epoch": 0.05617021276595745,
"grad_norm": 15.02849292755127,
"loss": 10.2962,
"lr": 0.00039400000000000004,
"step": 198,
"tokens_trained": 0.018827552
},
{
"epoch": 0.05673758865248227,
"grad_norm": 14.990167617797852,
"loss": 10.1912,
"lr": 0.000398,
"step": 200,
"tokens_trained": 0.019018
},
{
"epoch": 0.05730496453900709,
"grad_norm": 15.390633583068848,
"loss": 10.0442,
"lr": 0.000402,
"step": 202,
"tokens_trained": 0.019209864
},
{
"epoch": 0.05787234042553192,
"grad_norm": 16.871570587158203,
"loss": 9.9685,
"lr": 0.00040600000000000006,
"step": 204,
"tokens_trained": 0.019400176
},
{
"epoch": 0.05843971631205674,
"grad_norm": 20.16544532775879,
"loss": 9.8531,
"lr": 0.00041,
"step": 206,
"tokens_trained": 0.019589424
},
{
"epoch": 0.05900709219858156,
"grad_norm": 16.825023651123047,
"loss": 9.7777,
"lr": 0.000414,
"step": 208,
"tokens_trained": 0.019779112
},
{
"epoch": 0.059574468085106386,
"grad_norm": 16.43510627746582,
"loss": 9.6122,
"lr": 0.00041799999999999997,
"step": 210,
"tokens_trained": 0.019970048
},
{
"epoch": 0.060141843971631206,
"grad_norm": 17.340473175048828,
"loss": 9.4859,
"lr": 0.000422,
"step": 212,
"tokens_trained": 0.020160968
},
{
"epoch": 0.06070921985815603,
"grad_norm": 15.019119262695312,
"loss": 9.3656,
"lr": 0.000426,
"step": 214,
"tokens_trained": 0.020349664
},
{
"epoch": 0.06127659574468085,
"grad_norm": 13.379194259643555,
"loss": 9.2348,
"lr": 0.00043,
"step": 216,
"tokens_trained": 0.020538192
},
{
"epoch": 0.061843971631205676,
"grad_norm": 16.71472930908203,
"loss": 9.2258,
"lr": 0.00043400000000000003,
"step": 218,
"tokens_trained": 0.020728936
},
{
"epoch": 0.062411347517730496,
"grad_norm": 12.743139266967773,
"loss": 9.0569,
"lr": 0.000438,
"step": 220,
"tokens_trained": 0.020917472
},
{
"epoch": 0.06297872340425532,
"grad_norm": 15.739934921264648,
"loss": 8.9623,
"lr": 0.000442,
"step": 222,
"tokens_trained": 0.02110928
},
{
"epoch": 0.06354609929078014,
"grad_norm": 14.23620891571045,
"loss": 8.8201,
"lr": 0.000446,
"step": 224,
"tokens_trained": 0.021300168
},
{
"epoch": 0.06411347517730497,
"grad_norm": 13.005538940429688,
"loss": 8.7235,
"lr": 0.00045000000000000004,
"step": 226,
"tokens_trained": 0.021490272
},
{
"epoch": 0.06468085106382979,
"grad_norm": 17.17629051208496,
"loss": 8.6907,
"lr": 0.00045400000000000003,
"step": 228,
"tokens_trained": 0.021681552
},
{
"epoch": 0.06524822695035461,
"grad_norm": 14.430739402770996,
"loss": 8.6196,
"lr": 0.000458,
"step": 230,
"tokens_trained": 0.02187236
},
{
"epoch": 0.06581560283687943,
"grad_norm": 14.575714111328125,
"loss": 8.4741,
"lr": 0.000462,
"step": 232,
"tokens_trained": 0.022061976
},
{
"epoch": 0.06638297872340425,
"grad_norm": 13.892754554748535,
"loss": 8.4118,
"lr": 0.00046600000000000005,
"step": 234,
"tokens_trained": 0.022252008
},
{
"epoch": 0.06695035460992908,
"grad_norm": 11.58240795135498,
"loss": 8.2781,
"lr": 0.00047,
"step": 236,
"tokens_trained": 0.02244284
},
{
"epoch": 0.0675177304964539,
"grad_norm": 13.022644996643066,
"loss": 8.2139,
"lr": 0.000474,
"step": 238,
"tokens_trained": 0.022631152
},
{
"epoch": 0.06808510638297872,
"grad_norm": 11.844677925109863,
"loss": 8.1134,
"lr": 0.00047799999999999996,
"step": 240,
"tokens_trained": 0.022821096
},
{
"epoch": 0.06865248226950355,
"grad_norm": 13.878067016601562,
"loss": 8.0221,
"lr": 0.000482,
"step": 242,
"tokens_trained": 0.023011656
},
{
"epoch": 0.06921985815602837,
"grad_norm": 12.34648323059082,
"loss": 7.9755,
"lr": 0.000486,
"step": 244,
"tokens_trained": 0.023201
},
{
"epoch": 0.06978723404255319,
"grad_norm": 14.238297462463379,
"loss": 7.8969,
"lr": 0.00049,
"step": 246,
"tokens_trained": 0.023391128
},
{
"epoch": 0.07035460992907801,
"grad_norm": 14.386019706726074,
"loss": 7.8627,
"lr": 0.000494,
"step": 248,
"tokens_trained": 0.023581768
},
{
"epoch": 0.07092198581560284,
"grad_norm": 13.623086929321289,
"loss": 7.7568,
"lr": 0.000498,
"step": 250,
"tokens_trained": 0.023771248
},
{
"epoch": 0.07092198581560284,
"eval_loss": 7.70297384262085,
"eval_runtime": 21.3853,
"step": 250,
"tokens_trained": 0.023771248
},
{
"epoch": 0.07148936170212766,
"grad_norm": 14.347646713256836,
"loss": 7.6842,
"lr": 0.0005020000000000001,
"step": 252,
"tokens_trained": 0.023961056
},
{
"epoch": 0.07205673758865248,
"grad_norm": 12.5592041015625,
"loss": 7.6516,
"lr": 0.000506,
"step": 254,
"tokens_trained": 0.024150968
},
{
"epoch": 0.0726241134751773,
"grad_norm": 13.219141960144043,
"loss": 7.5789,
"lr": 0.00051,
"step": 256,
"tokens_trained": 0.024340072
},
{
"epoch": 0.07319148936170213,
"grad_norm": 12.654081344604492,
"loss": 7.5369,
"lr": 0.000514,
"step": 258,
"tokens_trained": 0.024529296
},
{
"epoch": 0.07375886524822695,
"grad_norm": 13.136971473693848,
"loss": 7.4949,
"lr": 0.000518,
"step": 260,
"tokens_trained": 0.024719688
},
{
"epoch": 0.07432624113475177,
"grad_norm": 12.680288314819336,
"loss": 7.3904,
"lr": 0.000522,
"step": 262,
"tokens_trained": 0.024909632
},
{
"epoch": 0.0748936170212766,
"grad_norm": 12.754518508911133,
"loss": 7.3514,
"lr": 0.000526,
"step": 264,
"tokens_trained": 0.025098416
},
{
"epoch": 0.07546099290780142,
"grad_norm": 13.22311019897461,
"loss": 7.2951,
"lr": 0.0005300000000000001,
"step": 266,
"tokens_trained": 0.025287344
},
{
"epoch": 0.07602836879432624,
"grad_norm": 12.11903190612793,
"loss": 7.2229,
"lr": 0.0005340000000000001,
"step": 268,
"tokens_trained": 0.025477152
},
{
"epoch": 0.07659574468085106,
"grad_norm": 13.771833419799805,
"loss": 7.1815,
"lr": 0.0005380000000000001,
"step": 270,
"tokens_trained": 0.025668288
},
{
"epoch": 0.07716312056737588,
"grad_norm": 11.756864547729492,
"loss": 7.1669,
"lr": 0.0005420000000000001,
"step": 272,
"tokens_trained": 0.025858528
},
{
"epoch": 0.0777304964539007,
"grad_norm": 13.613094329833984,
"loss": 7.1079,
"lr": 0.000546,
"step": 274,
"tokens_trained": 0.026048616
},
{
"epoch": 0.07829787234042553,
"grad_norm": 10.001923561096191,
"loss": 7.0508,
"lr": 0.00055,
"step": 276,
"tokens_trained": 0.026236944
},
{
"epoch": 0.07886524822695036,
"grad_norm": 14.262083053588867,
"loss": 6.9955,
"lr": 0.000554,
"step": 278,
"tokens_trained": 0.026426848
},
{
"epoch": 0.07943262411347518,
"grad_norm": 12.381136894226074,
"loss": 6.9831,
"lr": 0.000558,
"step": 280,
"tokens_trained": 0.026616784
},
{
"epoch": 0.08,
"grad_norm": 9.815845489501953,
"loss": 6.917,
"lr": 0.0005620000000000001,
"step": 282,
"tokens_trained": 0.026805176
},
{
"epoch": 0.08056737588652482,
"grad_norm": 11.669997215270996,
"loss": 6.8999,
"lr": 0.000566,
"step": 284,
"tokens_trained": 0.02699488
},
{
"epoch": 0.08113475177304964,
"grad_norm": 12.770941734313965,
"loss": 6.8998,
"lr": 0.00057,
"step": 286,
"tokens_trained": 0.027185784
},
{
"epoch": 0.08170212765957446,
"grad_norm": 15.572457313537598,
"loss": 6.841,
"lr": 0.000574,
"step": 288,
"tokens_trained": 0.027375896
},
{
"epoch": 0.08226950354609928,
"grad_norm": 10.980833053588867,
"loss": 6.8545,
"lr": 0.000578,
"step": 290,
"tokens_trained": 0.02756588
},
{
"epoch": 0.08283687943262412,
"grad_norm": 11.678337097167969,
"loss": 6.7853,
"lr": 0.0005819999999999999,
"step": 292,
"tokens_trained": 0.02775456
},
{
"epoch": 0.08340425531914894,
"grad_norm": 9.77885913848877,
"loss": 6.7465,
"lr": 0.0005859999999999999,
"step": 294,
"tokens_trained": 0.027942856
},
{
"epoch": 0.08397163120567376,
"grad_norm": 13.62730884552002,
"loss": 6.7276,
"lr": 0.00059,
"step": 296,
"tokens_trained": 0.028133152
},
{
"epoch": 0.08453900709219858,
"grad_norm": 10.644404411315918,
"loss": 6.6802,
"lr": 0.000594,
"step": 298,
"tokens_trained": 0.028322192
},
{
"epoch": 0.0851063829787234,
"grad_norm": 11.130610466003418,
"loss": 6.6548,
"lr": 0.000598,
"step": 300,
"tokens_trained": 0.0285122
},
{
"epoch": 0.08567375886524822,
"grad_norm": 11.557455062866211,
"loss": 6.6155,
"lr": 0.000602,
"step": 302,
"tokens_trained": 0.028699792
},
{
"epoch": 0.08624113475177304,
"grad_norm": 9.276884078979492,
"loss": 6.5989,
"lr": 0.000606,
"step": 304,
"tokens_trained": 0.028889896
},
{
"epoch": 0.08680851063829788,
"grad_norm": 9.616179466247559,
"loss": 6.5773,
"lr": 0.00061,
"step": 306,
"tokens_trained": 0.029082272
},
{
"epoch": 0.0873758865248227,
"grad_norm": 10.575953483581543,
"loss": 6.5358,
"lr": 0.000614,
"step": 308,
"tokens_trained": 0.029273352
},
{
"epoch": 0.08794326241134752,
"grad_norm": 9.089850425720215,
"loss": 6.5088,
"lr": 0.0006180000000000001,
"step": 310,
"tokens_trained": 0.029463848
},
{
"epoch": 0.08851063829787234,
"grad_norm": 9.090002059936523,
"loss": 6.4849,
"lr": 0.000622,
"step": 312,
"tokens_trained": 0.029653272
},
{
"epoch": 0.08907801418439716,
"grad_norm": 12.038308143615723,
"loss": 6.4624,
"lr": 0.000626,
"step": 314,
"tokens_trained": 0.029841928
},
{
"epoch": 0.08964539007092198,
"grad_norm": 9.073866844177246,
"loss": 6.4515,
"lr": 0.00063,
"step": 316,
"tokens_trained": 0.030029808
},
{
"epoch": 0.0902127659574468,
"grad_norm": 8.727197647094727,
"loss": 6.43,
"lr": 0.000634,
"step": 318,
"tokens_trained": 0.030221288
},
{
"epoch": 0.09078014184397164,
"grad_norm": 14.558151245117188,
"loss": 6.4487,
"lr": 0.000638,
"step": 320,
"tokens_trained": 0.030410872
},
{
"epoch": 0.09134751773049646,
"grad_norm": 9.98914623260498,
"loss": 6.4279,
"lr": 0.000642,
"step": 322,
"tokens_trained": 0.030602376
},
{
"epoch": 0.09191489361702128,
"grad_norm": 10.395442962646484,
"loss": 6.4311,
"lr": 0.000646,
"step": 324,
"tokens_trained": 0.030792968
},
{
"epoch": 0.0924822695035461,
"grad_norm": 10.8250093460083,
"loss": 6.3726,
"lr": 0.0006500000000000001,
"step": 326,
"tokens_trained": 0.030982944
},
{
"epoch": 0.09304964539007092,
"grad_norm": 9.73416805267334,
"loss": 6.34,
"lr": 0.0006540000000000001,
"step": 328,
"tokens_trained": 0.031174928
},
{
"epoch": 0.09361702127659574,
"grad_norm": 8.596503257751465,
"loss": 6.3322,
"lr": 0.0006580000000000001,
"step": 330,
"tokens_trained": 0.031364288
},
{
"epoch": 0.09418439716312056,
"grad_norm": 8.49472427368164,
"loss": 6.3096,
"lr": 0.000662,
"step": 332,
"tokens_trained": 0.03155376
},
{
"epoch": 0.0947517730496454,
"grad_norm": 7.857503414154053,
"loss": 6.2368,
"lr": 0.000666,
"step": 334,
"tokens_trained": 0.031744368
},
{
"epoch": 0.09531914893617022,
"grad_norm": 9.007513999938965,
"loss": 6.198,
"lr": 0.00067,
"step": 336,
"tokens_trained": 0.031934136
},
{
"epoch": 0.09588652482269504,
"grad_norm": 8.185524940490723,
"loss": 6.2328,
"lr": 0.000674,
"step": 338,
"tokens_trained": 0.032124984
},
{
"epoch": 0.09645390070921986,
"grad_norm": 8.784396171569824,
"loss": 6.1945,
"lr": 0.0006780000000000001,
"step": 340,
"tokens_trained": 0.032316016
},
{
"epoch": 0.09702127659574468,
"grad_norm": 8.642311096191406,
"loss": 6.218,
"lr": 0.0006820000000000001,
"step": 342,
"tokens_trained": 0.032506224
},
{
"epoch": 0.0975886524822695,
"grad_norm": 8.493780136108398,
"loss": 6.194,
"lr": 0.0006860000000000001,
"step": 344,
"tokens_trained": 0.032696152
},
{
"epoch": 0.09815602836879432,
"grad_norm": 9.120508193969727,
"loss": 6.2241,
"lr": 0.00069,
"step": 346,
"tokens_trained": 0.032885688
},
{
"epoch": 0.09872340425531916,
"grad_norm": 9.34500503540039,
"loss": 6.1548,
"lr": 0.000694,
"step": 348,
"tokens_trained": 0.03307568
},
{
"epoch": 0.09929078014184398,
"grad_norm": 7.483356952667236,
"loss": 6.1282,
"lr": 0.0006979999999999999,
"step": 350,
"tokens_trained": 0.033267208
},
{
"epoch": 0.0998581560283688,
"grad_norm": 7.974069118499756,
"loss": 6.1032,
"lr": 0.0007019999999999999,
"step": 352,
"tokens_trained": 0.033458144
},
{
"epoch": 0.10042553191489362,
"grad_norm": 8.247384071350098,
"loss": 6.1698,
"lr": 0.0007059999999999999,
"step": 354,
"tokens_trained": 0.033650352
},
{
"epoch": 0.10099290780141844,
"grad_norm": 8.554885864257812,
"loss": 6.1429,
"lr": 0.00071,
"step": 356,
"tokens_trained": 0.033840232
},
{
"epoch": 0.10156028368794326,
"grad_norm": 7.209281921386719,
"loss": 6.0997,
"lr": 0.000714,
"step": 358,
"tokens_trained": 0.034030032
},
{
"epoch": 0.10212765957446808,
"grad_norm": 8.660383224487305,
"loss": 6.1497,
"lr": 0.000718,
"step": 360,
"tokens_trained": 0.034218592
},
{
"epoch": 0.10269503546099291,
"grad_norm": 9.382761001586914,
"loss": 6.0665,
"lr": 0.000722,
"step": 362,
"tokens_trained": 0.034408408
},
{
"epoch": 0.10326241134751774,
"grad_norm": 6.915714263916016,
"loss": 6.0636,
"lr": 0.000726,
"step": 364,
"tokens_trained": 0.034600016
},
{
"epoch": 0.10382978723404256,
"grad_norm": 7.8990631103515625,
"loss": 6.0975,
"lr": 0.00073,
"step": 366,
"tokens_trained": 0.034790792
},
{
"epoch": 0.10439716312056738,
"grad_norm": 8.859809875488281,
"loss": 6.0754,
"lr": 0.000734,
"step": 368,
"tokens_trained": 0.034981304
},
{
"epoch": 0.1049645390070922,
"grad_norm": 7.392801761627197,
"loss": 6.039,
"lr": 0.000738,
"step": 370,
"tokens_trained": 0.03516956
},
{
"epoch": 0.10553191489361702,
"grad_norm": 9.427324295043945,
"loss": 6.084,
"lr": 0.000742,
"step": 372,
"tokens_trained": 0.035358816
},
{
"epoch": 0.10609929078014184,
"grad_norm": 7.168910503387451,
"loss": 6.0498,
"lr": 0.000746,
"step": 374,
"tokens_trained": 0.035548016
},
{
"epoch": 0.10638297872340426,
"eval_loss": 6.038269996643066,
"eval_runtime": 21.3445,
"step": 375,
"tokens_trained": 0.035644104
},
{
"epoch": 0.10666666666666667,
"grad_norm": 7.899259567260742,
"loss": 6.0345,
"lr": 0.00075,
"step": 376,
"tokens_trained": 0.035739856
},
{
"epoch": 0.1072340425531915,
"grad_norm": 8.91533374786377,
"loss": 6.0386,
"lr": 0.000754,
"step": 378,
"tokens_trained": 0.035930264
},
{
"epoch": 0.10780141843971631,
"grad_norm": 6.998043060302734,
"loss": 6.0294,
"lr": 0.000758,
"step": 380,
"tokens_trained": 0.036119616
},
{
"epoch": 0.10836879432624114,
"grad_norm": 7.343894958496094,
"loss": 6.0116,
"lr": 0.000762,
"step": 382,
"tokens_trained": 0.036308416
},
{
"epoch": 0.10893617021276596,
"grad_norm": 8.182528495788574,
"loss": 5.9904,
"lr": 0.0007660000000000001,
"step": 384,
"tokens_trained": 0.036497264
},
{
"epoch": 0.10950354609929078,
"grad_norm": 7.927818775177002,
"loss": 6.0345,
"lr": 0.0007700000000000001,
"step": 386,
"tokens_trained": 0.036688192
},
{
"epoch": 0.1100709219858156,
"grad_norm": 8.07447338104248,
"loss": 5.9685,
"lr": 0.0007740000000000001,
"step": 388,
"tokens_trained": 0.036878256
},
{
"epoch": 0.11063829787234042,
"grad_norm": 7.281871318817139,
"loss": 6.0125,
"lr": 0.000778,
"step": 390,
"tokens_trained": 0.037068272
},
{
"epoch": 0.11120567375886525,
"grad_norm": 8.298929214477539,
"loss": 6.0071,
"lr": 0.000782,
"step": 392,
"tokens_trained": 0.037259464
},
{
"epoch": 0.11177304964539007,
"grad_norm": 7.546716690063477,
"loss": 5.9721,
"lr": 0.000786,
"step": 394,
"tokens_trained": 0.037449696
},
{
"epoch": 0.1123404255319149,
"grad_norm": 8.28548526763916,
"loss": 5.9819,
"lr": 0.00079,
"step": 396,
"tokens_trained": 0.037639672
},
{
"epoch": 0.11290780141843972,
"grad_norm": 7.064655303955078,
"loss": 5.9873,
"lr": 0.0007940000000000001,
"step": 398,
"tokens_trained": 0.03782712
},
{
"epoch": 0.11347517730496454,
"grad_norm": 7.743175506591797,
"loss": 5.9528,
"lr": 0.0007980000000000001,
"step": 400,
"tokens_trained": 0.03801792
},
{
"epoch": 0.11404255319148936,
"grad_norm": 7.00898551940918,
"loss": 5.9504,
"lr": 0.0008020000000000001,
"step": 402,
"tokens_trained": 0.038209176
},
{
"epoch": 0.11460992907801418,
"grad_norm": 7.9350409507751465,
"loss": 5.9555,
"lr": 0.0008060000000000001,
"step": 404,
"tokens_trained": 0.03839824
},
{
"epoch": 0.11517730496453901,
"grad_norm": 7.048569679260254,
"loss": 5.9787,
"lr": 0.0008100000000000001,
"step": 406,
"tokens_trained": 0.03858732
},
{
"epoch": 0.11574468085106383,
"grad_norm": 7.088194370269775,
"loss": 5.928,
"lr": 0.0008139999999999999,
"step": 408,
"tokens_trained": 0.038777712
},
{
"epoch": 0.11631205673758865,
"grad_norm": 8.230712890625,
"loss": 5.9716,
"lr": 0.0008179999999999999,
"step": 410,
"tokens_trained": 0.038969464
},
{
"epoch": 0.11687943262411347,
"grad_norm": 8.076972007751465,
"loss": 5.9624,
"lr": 0.0008219999999999999,
"step": 412,
"tokens_trained": 0.039162064
},
{
"epoch": 0.1174468085106383,
"grad_norm": 8.065289497375488,
"loss": 5.9937,
"lr": 0.000826,
"step": 414,
"tokens_trained": 0.039348688
},
{
"epoch": 0.11801418439716312,
"grad_norm": 6.393420696258545,
"loss": 5.9278,
"lr": 0.00083,
"step": 416,
"tokens_trained": 0.03953732
},
{
"epoch": 0.11858156028368794,
"grad_norm": 7.384702682495117,
"loss": 5.931,
"lr": 0.000834,
"step": 418,
"tokens_trained": 0.039729808
},
{
"epoch": 0.11914893617021277,
"grad_norm": 7.007425308227539,
"loss": 5.93,
"lr": 0.000838,
"step": 420,
"tokens_trained": 0.039921096
},
{
"epoch": 0.11971631205673759,
"grad_norm": 7.112692832946777,
"loss": 5.9625,
"lr": 0.000842,
"step": 422,
"tokens_trained": 0.040110856
},
{
"epoch": 0.12028368794326241,
"grad_norm": 8.484418869018555,
"loss": 5.9848,
"lr": 0.000846,
"step": 424,
"tokens_trained": 0.040300504
},
{
"epoch": 0.12085106382978723,
"grad_norm": 6.633459091186523,
"loss": 6.0226,
"lr": 0.00085,
"step": 426,
"tokens_trained": 0.04049056
},
{
"epoch": 0.12141843971631205,
"grad_norm": 7.796964168548584,
"loss": 5.9152,
"lr": 0.000854,
"step": 428,
"tokens_trained": 0.040680544
},
{
"epoch": 0.12198581560283688,
"grad_norm": 7.833578586578369,
"loss": 5.924,
"lr": 0.000858,
"step": 430,
"tokens_trained": 0.040873128
},
{
"epoch": 0.1225531914893617,
"grad_norm": 6.7470550537109375,
"loss": 5.9318,
"lr": 0.000862,
"step": 432,
"tokens_trained": 0.041063488
},
{
"epoch": 0.12312056737588653,
"grad_norm": 6.066318988800049,
"loss": 5.9569,
"lr": 0.000866,
"step": 434,
"tokens_trained": 0.041254368
},
{
"epoch": 0.12368794326241135,
"grad_norm": 6.753541469573975,
"loss": 5.8851,
"lr": 0.00087,
"step": 436,
"tokens_trained": 0.04144516
},
{
"epoch": 0.12425531914893617,
"grad_norm": 6.471331596374512,
"loss": 5.864,
"lr": 0.000874,
"step": 438,
"tokens_trained": 0.041636912
},
{
"epoch": 0.12482269503546099,
"grad_norm": 6.129056930541992,
"loss": 5.8965,
"lr": 0.000878,
"step": 440,
"tokens_trained": 0.041828104
},
{
"epoch": 0.1253900709219858,
"grad_norm": 6.478890895843506,
"loss": 5.8817,
"lr": 0.000882,
"step": 442,
"tokens_trained": 0.04201808
},
{
"epoch": 0.12595744680851065,
"grad_norm": 6.014713287353516,
"loss": 5.8268,
"lr": 0.0008860000000000001,
"step": 444,
"tokens_trained": 0.042207328
},
{
"epoch": 0.12652482269503545,
"grad_norm": 5.505755424499512,
"loss": 5.8684,
"lr": 0.0008900000000000001,
"step": 446,
"tokens_trained": 0.042398152
},
{
"epoch": 0.1270921985815603,
"grad_norm": 10.096606254577637,
"loss": 5.8608,
"lr": 0.000894,
"step": 448,
"tokens_trained": 0.042588984
},
{
"epoch": 0.1276595744680851,
"grad_norm": 6.388499736785889,
"loss": 5.8766,
"lr": 0.000898,
"step": 450,
"tokens_trained": 0.042778592
},
{
"epoch": 0.12822695035460993,
"grad_norm": 7.145125865936279,
"loss": 5.8571,
"lr": 0.000902,
"step": 452,
"tokens_trained": 0.042967176
},
{
"epoch": 0.12879432624113477,
"grad_norm": 6.826383113861084,
"loss": 5.8655,
"lr": 0.000906,
"step": 454,
"tokens_trained": 0.043158952
},
{
"epoch": 0.12936170212765957,
"grad_norm": 6.036892414093018,
"loss": 5.8775,
"lr": 0.00091,
"step": 456,
"tokens_trained": 0.043349288
},
{
"epoch": 0.1299290780141844,
"grad_norm": 6.36528205871582,
"loss": 5.8908,
"lr": 0.0009140000000000001,
"step": 458,
"tokens_trained": 0.043539888
},
{
"epoch": 0.13049645390070921,
"grad_norm": 6.317558288574219,
"loss": 5.8702,
"lr": 0.0009180000000000001,
"step": 460,
"tokens_trained": 0.04373232
},
{
"epoch": 0.13106382978723405,
"grad_norm": 6.427131175994873,
"loss": 5.8399,
"lr": 0.0009220000000000001,
"step": 462,
"tokens_trained": 0.043922744
},
{
"epoch": 0.13163120567375886,
"grad_norm": 5.666539669036865,
"loss": 5.7899,
"lr": 0.0009260000000000001,
"step": 464,
"tokens_trained": 0.044112888
},
{
"epoch": 0.1321985815602837,
"grad_norm": 5.241824150085449,
"loss": 5.8203,
"lr": 0.00093,
"step": 466,
"tokens_trained": 0.04430244
},
{
"epoch": 0.1327659574468085,
"grad_norm": 6.072646141052246,
"loss": 5.8367,
"lr": 0.000934,
"step": 468,
"tokens_trained": 0.044493528
},
{
"epoch": 0.13333333333333333,
"grad_norm": 6.414418697357178,
"loss": 5.8236,
"lr": 0.0009379999999999999,
"step": 470,
"tokens_trained": 0.044682328
},
{
"epoch": 0.13390070921985817,
"grad_norm": 6.958801746368408,
"loss": 5.8179,
"lr": 0.000942,
"step": 472,
"tokens_trained": 0.044874256
},
{
"epoch": 0.13446808510638297,
"grad_norm": 5.787843227386475,
"loss": 5.8478,
"lr": 0.000946,
"step": 474,
"tokens_trained": 0.045065616
},
{
"epoch": 0.1350354609929078,
"grad_norm": 5.5841240882873535,
"loss": 5.8307,
"lr": 0.00095,
"step": 476,
"tokens_trained": 0.045257024
},
{
"epoch": 0.13560283687943261,
"grad_norm": 6.607712745666504,
"loss": 5.8512,
"lr": 0.000954,
"step": 478,
"tokens_trained": 0.045446432
},
{
"epoch": 0.13617021276595745,
"grad_norm": 5.473597049713135,
"loss": 5.8174,
"lr": 0.000958,
"step": 480,
"tokens_trained": 0.045636392
},
{
"epoch": 0.13673758865248226,
"grad_norm": 5.435728549957275,
"loss": 5.8308,
"lr": 0.000962,
"step": 482,
"tokens_trained": 0.045823784
},
{
"epoch": 0.1373049645390071,
"grad_norm": 6.049300670623779,
"loss": 5.8293,
"lr": 0.000966,
"step": 484,
"tokens_trained": 0.046013408
},
{
"epoch": 0.13787234042553193,
"grad_norm": 6.311764717102051,
"loss": 5.8086,
"lr": 0.0009699999999999999,
"step": 486,
"tokens_trained": 0.046202528
},
{
"epoch": 0.13843971631205673,
"grad_norm": 5.886009216308594,
"loss": 5.7986,
"lr": 0.000974,
"step": 488,
"tokens_trained": 0.04639404
},
{
"epoch": 0.13900709219858157,
"grad_norm": 5.438202381134033,
"loss": 5.8473,
"lr": 0.000978,
"step": 490,
"tokens_trained": 0.046586512
},
{
"epoch": 0.13957446808510637,
"grad_norm": 5.08393669128418,
"loss": 5.7613,
"lr": 0.000982,
"step": 492,
"tokens_trained": 0.046777448
},
{
"epoch": 0.1401418439716312,
"grad_norm": 5.645389080047607,
"loss": 5.7723,
"lr": 0.0009860000000000001,
"step": 494,
"tokens_trained": 0.046966096
},
{
"epoch": 0.14070921985815601,
"grad_norm": 6.320916652679443,
"loss": 5.7772,
"lr": 0.00099,
"step": 496,
"tokens_trained": 0.047155152
},
{
"epoch": 0.14127659574468085,
"grad_norm": 5.573540210723877,
"loss": 5.7412,
"lr": 0.000994,
"step": 498,
"tokens_trained": 0.047345352
},
{
"epoch": 0.14184397163120568,
"grad_norm": 4.939594745635986,
"loss": 5.8208,
"lr": 0.000998,
"step": 500,
"tokens_trained": 0.047535016
},
{
"epoch": 0.14184397163120568,
"eval_loss": 5.799490928649902,
"eval_runtime": 20.8575,
"step": 500,
"tokens_trained": 0.047535016
},
{
"epoch": 0.1424113475177305,
"grad_norm": 5.805343151092529,
"loss": 5.7734,
"lr": 0.00099986013986014,
"step": 502,
"tokens_trained": 0.047724216
},
{
"epoch": 0.14297872340425533,
"grad_norm": 5.831176280975342,
"loss": 5.8044,
"lr": 0.0009995804195804196,
"step": 504,
"tokens_trained": 0.047914328
},
{
"epoch": 0.14354609929078013,
"grad_norm": 5.045091152191162,
"loss": 5.8133,
"lr": 0.0009993006993006994,
"step": 506,
"tokens_trained": 0.048105032
},
{
"epoch": 0.14411347517730497,
"grad_norm": 5.276819705963135,
"loss": 5.7555,
"lr": 0.000999020979020979,
"step": 508,
"tokens_trained": 0.048293104
},
{
"epoch": 0.14468085106382977,
"grad_norm": 5.710324287414551,
"loss": 5.7619,
"lr": 0.0009987412587412587,
"step": 510,
"tokens_trained": 0.048483888
},
{
"epoch": 0.1452482269503546,
"grad_norm": 4.9472527503967285,
"loss": 5.767,
"lr": 0.0009984615384615386,
"step": 512,
"tokens_trained": 0.04867336
},
{
"epoch": 0.14581560283687944,
"grad_norm": 5.410078525543213,
"loss": 5.7238,
"lr": 0.0009981818181818182,
"step": 514,
"tokens_trained": 0.048863104
},
{
"epoch": 0.14638297872340425,
"grad_norm": 6.025843143463135,
"loss": 5.7664,
"lr": 0.000997902097902098,
"step": 516,
"tokens_trained": 0.049053856
},
{
"epoch": 0.14695035460992908,
"grad_norm": 5.3211669921875,
"loss": 5.747,
"lr": 0.0009976223776223777,
"step": 518,
"tokens_trained": 0.049245104
},
{
"epoch": 0.1475177304964539,
"grad_norm": 6.059483051300049,
"loss": 5.7611,
"lr": 0.0009973426573426573,
"step": 520,
"tokens_trained": 0.049434368
},
{
"epoch": 0.14808510638297873,
"grad_norm": 5.362505912780762,
"loss": 5.7607,
"lr": 0.000997062937062937,
"step": 522,
"tokens_trained": 0.049622648
},
{
"epoch": 0.14865248226950353,
"grad_norm": 5.391371726989746,
"loss": 5.7857,
"lr": 0.0009967832167832168,
"step": 524,
"tokens_trained": 0.049812304
},
{
"epoch": 0.14921985815602837,
"grad_norm": 4.3839030265808105,
"loss": 5.7334,
"lr": 0.0009965034965034964,
"step": 526,
"tokens_trained": 0.05000356
},
{
"epoch": 0.1497872340425532,
"grad_norm": 5.008530616760254,
"loss": 5.7475,
"lr": 0.0009962237762237763,
"step": 528,
"tokens_trained": 0.050193304
},
{
"epoch": 0.150354609929078,
"grad_norm": 5.068671226501465,
"loss": 5.7866,
"lr": 0.000995944055944056,
"step": 530,
"tokens_trained": 0.050382856
},
{
"epoch": 0.15092198581560284,
"grad_norm": 5.399240493774414,
"loss": 5.6857,
"lr": 0.0009956643356643356,
"step": 532,
"tokens_trained": 0.050570864
},
{
"epoch": 0.15148936170212765,
"grad_norm": 5.689481735229492,
"loss": 5.7586,
"lr": 0.0009953846153846154,
"step": 534,
"tokens_trained": 0.050760384
},
{
"epoch": 0.15205673758865249,
"grad_norm": 4.652275562286377,
"loss": 5.7866,
"lr": 0.000995104895104895,
"step": 536,
"tokens_trained": 0.050952712
},
{
"epoch": 0.1526241134751773,
"grad_norm": 4.126920223236084,
"loss": 5.7261,
"lr": 0.000994825174825175,
"step": 538,
"tokens_trained": 0.051141656
},
{
"epoch": 0.15319148936170213,
"grad_norm": 4.233098030090332,
"loss": 5.6903,
"lr": 0.0009945454545454546,
"step": 540,
"tokens_trained": 0.051331256
},
{
"epoch": 0.15375886524822696,
"grad_norm": 4.271973133087158,
"loss": 5.7293,
"lr": 0.0009942657342657344,
"step": 542,
"tokens_trained": 0.051522072
},
{
"epoch": 0.15432624113475177,
"grad_norm": 4.653008937835693,
"loss": 5.7133,
"lr": 0.000993986013986014,
"step": 544,
"tokens_trained": 0.051711624
},
{
"epoch": 0.1548936170212766,
"grad_norm": 4.192624092102051,
"loss": 5.6876,
"lr": 0.0009937062937062937,
"step": 546,
"tokens_trained": 0.051901744
},
{
"epoch": 0.1554609929078014,
"grad_norm": 5.497848033905029,
"loss": 5.7378,
"lr": 0.0009934265734265735,
"step": 548,
"tokens_trained": 0.052092872
},
{
"epoch": 0.15602836879432624,
"grad_norm": 4.350259780883789,
"loss": 5.6533,
"lr": 0.0009931468531468532,
"step": 550,
"tokens_trained": 0.052281768
},
{
"epoch": 0.15659574468085105,
"grad_norm": 4.515641689300537,
"loss": 5.7492,
"lr": 0.000992867132867133,
"step": 552,
"tokens_trained": 0.052471848
},
{
"epoch": 0.15716312056737589,
"grad_norm": 4.628066539764404,
"loss": 5.7113,
"lr": 0.0009925874125874127,
"step": 554,
"tokens_trained": 0.052660168
},
{
"epoch": 0.15773049645390072,
"grad_norm": 4.8322930335998535,
"loss": 5.6696,
"lr": 0.0009923076923076923,
"step": 556,
"tokens_trained": 0.05284776
},
{
"epoch": 0.15829787234042553,
"grad_norm": 3.999706506729126,
"loss": 5.7296,
"lr": 0.000992027972027972,
"step": 558,
"tokens_trained": 0.053037344
},
{
"epoch": 0.15886524822695036,
"grad_norm": 4.332971572875977,
"loss": 5.7362,
"lr": 0.0009917482517482518,
"step": 560,
"tokens_trained": 0.053228168
},
{
"epoch": 0.15943262411347517,
"grad_norm": 4.500301361083984,
"loss": 5.6982,
"lr": 0.0009914685314685314,
"step": 562,
"tokens_trained": 0.05341856
},
{
"epoch": 0.16,
"grad_norm": 4.721808910369873,
"loss": 5.7166,
"lr": 0.0009911888111888113,
"step": 564,
"tokens_trained": 0.053608824
},
{
"epoch": 0.1605673758865248,
"grad_norm": 5.265316009521484,
"loss": 5.7069,
"lr": 0.000990909090909091,
"step": 566,
"tokens_trained": 0.053799728
},
{
"epoch": 0.16113475177304964,
"grad_norm": 5.024131774902344,
"loss": 5.7113,
"lr": 0.0009906293706293705,
"step": 568,
"tokens_trained": 0.05398944
},
{
"epoch": 0.16170212765957448,
"grad_norm": 4.063276767730713,
"loss": 5.6251,
"lr": 0.0009903496503496504,
"step": 570,
"tokens_trained": 0.054176512
},
{
"epoch": 0.1622695035460993,
"grad_norm": 4.15974760055542,
"loss": 5.6912,
"lr": 0.00099006993006993,
"step": 572,
"tokens_trained": 0.054367072
},
{
"epoch": 0.16283687943262412,
"grad_norm": 4.338894844055176,
"loss": 5.6807,
"lr": 0.0009897902097902099,
"step": 574,
"tokens_trained": 0.054559184
},
{
"epoch": 0.16340425531914893,
"grad_norm": 5.535487174987793,
"loss": 5.6765,
"lr": 0.0009895104895104895,
"step": 576,
"tokens_trained": 0.054748904
},
{
"epoch": 0.16397163120567376,
"grad_norm": 4.379040241241455,
"loss": 5.6884,
"lr": 0.0009892307692307694,
"step": 578,
"tokens_trained": 0.054936136
},
{
"epoch": 0.16453900709219857,
"grad_norm": 4.746179103851318,
"loss": 5.6885,
"lr": 0.000988951048951049,
"step": 580,
"tokens_trained": 0.055125584
},
{
"epoch": 0.1651063829787234,
"grad_norm": 4.949806213378906,
"loss": 5.7061,
"lr": 0.0009886713286713286,
"step": 582,
"tokens_trained": 0.055314608
},
{
"epoch": 0.16567375886524824,
"grad_norm": 4.507448196411133,
"loss": 5.6339,
"lr": 0.0009883916083916085,
"step": 584,
"tokens_trained": 0.055503992
},
{
"epoch": 0.16624113475177305,
"grad_norm": 4.131013870239258,
"loss": 5.7122,
"lr": 0.0009881118881118881,
"step": 586,
"tokens_trained": 0.055693376
},
{
"epoch": 0.16680851063829788,
"grad_norm": 5.32897424697876,
"loss": 5.7192,
"lr": 0.000987832167832168,
"step": 588,
"tokens_trained": 0.05588452
},
{
"epoch": 0.1673758865248227,
"grad_norm": 4.166877746582031,
"loss": 5.6666,
"lr": 0.0009875524475524476,
"step": 590,
"tokens_trained": 0.056073936
},
{
"epoch": 0.16794326241134752,
"grad_norm": 4.393389701843262,
"loss": 5.6113,
"lr": 0.0009872727272727273,
"step": 592,
"tokens_trained": 0.056262224
},
{
"epoch": 0.16851063829787233,
"grad_norm": 4.466696739196777,
"loss": 5.6466,
"lr": 0.000986993006993007,
"step": 594,
"tokens_trained": 0.056454008
},
{
"epoch": 0.16907801418439716,
"grad_norm": 3.9413373470306396,
"loss": 5.6838,
"lr": 0.0009867132867132867,
"step": 596,
"tokens_trained": 0.05664444
},
{
"epoch": 0.169645390070922,
"grad_norm": 3.594649314880371,
"loss": 5.6684,
"lr": 0.0009864335664335664,
"step": 598,
"tokens_trained": 0.056833864
},
{
"epoch": 0.1702127659574468,
"grad_norm": 3.5969483852386475,
"loss": 5.6619,
"lr": 0.0009861538461538462,
"step": 600,
"tokens_trained": 0.05702332
},
{
"epoch": 0.17078014184397164,
"grad_norm": 3.845414638519287,
"loss": 5.5855,
"lr": 0.0009858741258741259,
"step": 602,
"tokens_trained": 0.057212776
},
{
"epoch": 0.17134751773049645,
"grad_norm": 3.9198834896087646,
"loss": 5.6551,
"lr": 0.0009855944055944055,
"step": 604,
"tokens_trained": 0.05740152
},
{
"epoch": 0.17191489361702128,
"grad_norm": 3.6764986515045166,
"loss": 5.6228,
"lr": 0.0009853146853146854,
"step": 606,
"tokens_trained": 0.057595616
},
{
"epoch": 0.1724822695035461,
"grad_norm": 3.8210043907165527,
"loss": 5.6557,
"lr": 0.000985034965034965,
"step": 608,
"tokens_trained": 0.057783968
},
{
"epoch": 0.17304964539007092,
"grad_norm": 3.893644094467163,
"loss": 5.6675,
"lr": 0.0009847552447552449,
"step": 610,
"tokens_trained": 0.057974832
},
{
"epoch": 0.17361702127659576,
"grad_norm": 3.280839681625366,
"loss": 5.6442,
"lr": 0.0009844755244755245,
"step": 612,
"tokens_trained": 0.058166272
},
{
"epoch": 0.17418439716312056,
"grad_norm": 3.4350404739379883,
"loss": 5.6555,
"lr": 0.0009841958041958043,
"step": 614,
"tokens_trained": 0.058356008
},
{
"epoch": 0.1747517730496454,
"grad_norm": 3.7700448036193848,
"loss": 5.6138,
"lr": 0.000983916083916084,
"step": 616,
"tokens_trained": 0.058546792
},
{
"epoch": 0.1753191489361702,
"grad_norm": 3.8182730674743652,
"loss": 5.6931,
"lr": 0.0009836363636363636,
"step": 618,
"tokens_trained": 0.058736296
},
{
"epoch": 0.17588652482269504,
"grad_norm": 3.9105372428894043,
"loss": 5.6431,
"lr": 0.0009833566433566435,
"step": 620,
"tokens_trained": 0.058927576
},
{
"epoch": 0.17645390070921985,
"grad_norm": 3.8897712230682373,
"loss": 5.6203,
"lr": 0.000983076923076923,
"step": 622,
"tokens_trained": 0.059118416
},
{
"epoch": 0.17702127659574468,
"grad_norm": 3.512194871902466,
"loss": 5.6292,
"lr": 0.000982797202797203,
"step": 624,
"tokens_trained": 0.059308568
},
{
"epoch": 0.1773049645390071,
"eval_loss": 5.630118370056152,
"eval_runtime": 21.1591,
"step": 625,
"tokens_trained": 0.059404056
},
{
"epoch": 0.17758865248226952,
"grad_norm": 2.990100383758545,
"loss": 5.622,
"lr": 0.0009825174825174826,
"step": 626,
"tokens_trained": 0.059499776
},
{
"epoch": 0.17815602836879432,
"grad_norm": 3.0487334728240967,
"loss": 5.6629,
"lr": 0.0009822377622377622,
"step": 628,
"tokens_trained": 0.059690208
},
{
"epoch": 0.17872340425531916,
"grad_norm": 3.6905510425567627,
"loss": 5.6345,
"lr": 0.0009819580419580419,
"step": 630,
"tokens_trained": 0.059881352
},
{
"epoch": 0.17929078014184396,
"grad_norm": 3.302255630493164,
"loss": 5.6733,
"lr": 0.0009816783216783217,
"step": 632,
"tokens_trained": 0.060071896
},
{
"epoch": 0.1798581560283688,
"grad_norm": 3.6833834648132324,
"loss": 5.5868,
"lr": 0.0009813986013986014,
"step": 634,
"tokens_trained": 0.060260504
},
{
"epoch": 0.1804255319148936,
"grad_norm": 3.1528804302215576,
"loss": 5.6128,
"lr": 0.0009811188811188812,
"step": 636,
"tokens_trained": 0.060450584
},
{
"epoch": 0.18099290780141844,
"grad_norm": 3.788860559463501,
"loss": 5.6235,
"lr": 0.0009808391608391608,
"step": 638,
"tokens_trained": 0.060640872
},
{
"epoch": 0.18156028368794327,
"grad_norm": 3.192462682723999,
"loss": 5.545,
"lr": 0.0009805594405594405,
"step": 640,
"tokens_trained": 0.060832776
},
{
"epoch": 0.18212765957446808,
"grad_norm": 3.505732774734497,
"loss": 5.5801,
"lr": 0.0009802797202797203,
"step": 642,
"tokens_trained": 0.06102204
},
{
"epoch": 0.18269503546099292,
"grad_norm": 3.9589102268218994,
"loss": 5.6091,
"lr": 0.00098,
"step": 644,
"tokens_trained": 0.061209744
},
{
"epoch": 0.18326241134751772,
"grad_norm": 3.4410059452056885,
"loss": 5.6279,
"lr": 0.0009797202797202798,
"step": 646,
"tokens_trained": 0.061400392
},
{
"epoch": 0.18382978723404256,
"grad_norm": 3.7746005058288574,
"loss": 5.6124,
"lr": 0.0009794405594405595,
"step": 648,
"tokens_trained": 0.061592232
},
{
"epoch": 0.18439716312056736,
"grad_norm": 3.75022292137146,
"loss": 5.5826,
"lr": 0.000979160839160839,
"step": 650,
"tokens_trained": 0.061781824
},
{
"epoch": 0.1849645390070922,
"grad_norm": 3.7629313468933105,
"loss": 5.555,
"lr": 0.000978881118881119,
"step": 652,
"tokens_trained": 0.061972744
},
{
"epoch": 0.18553191489361703,
"grad_norm": 4.5046820640563965,
"loss": 5.5972,
"lr": 0.0009786013986013986,
"step": 654,
"tokens_trained": 0.062163456
},
{
"epoch": 0.18609929078014184,
"grad_norm": 3.443138599395752,
"loss": 5.6061,
"lr": 0.0009783216783216782,
"step": 656,
"tokens_trained": 0.06235208
},
{
"epoch": 0.18666666666666668,
"grad_norm": 3.2661828994750977,
"loss": 5.5479,
"lr": 0.000978041958041958,
"step": 658,
"tokens_trained": 0.062544416
},
{
"epoch": 0.18723404255319148,
"grad_norm": 3.9571003913879395,
"loss": 5.6069,
"lr": 0.000977762237762238,
"step": 660,
"tokens_trained": 0.062733992
},
{
"epoch": 0.18780141843971632,
"grad_norm": 3.705880641937256,
"loss": 5.5915,
"lr": 0.0009774825174825176,
"step": 662,
"tokens_trained": 0.062922536
},
{
"epoch": 0.18836879432624112,
"grad_norm": 4.066433429718018,
"loss": 5.6031,
"lr": 0.0009772027972027972,
"step": 664,
"tokens_trained": 0.063114224
},
{
"epoch": 0.18893617021276596,
"grad_norm": 3.356651782989502,
"loss": 5.6045,
"lr": 0.0009769230769230768,
"step": 666,
"tokens_trained": 0.063304616
},
{
"epoch": 0.1895035460992908,
"grad_norm": 3.8084938526153564,
"loss": 5.6138,
"lr": 0.0009766433566433567,
"step": 668,
"tokens_trained": 0.06349476
},
{
"epoch": 0.1900709219858156,
"grad_norm": 4.282619953155518,
"loss": 5.5704,
"lr": 0.0009763636363636363,
"step": 670,
"tokens_trained": 0.063684848
},
{
"epoch": 0.19063829787234043,
"grad_norm": 3.045057773590088,
"loss": 5.6427,
"lr": 0.0009760839160839161,
"step": 672,
"tokens_trained": 0.063875192
},
{
"epoch": 0.19120567375886524,
"grad_norm": 3.360164165496826,
"loss": 5.5778,
"lr": 0.0009758041958041958,
"step": 674,
"tokens_trained": 0.06406636
},
{
"epoch": 0.19177304964539008,
"grad_norm": 3.5778472423553467,
"loss": 5.5389,
"lr": 0.0009755244755244756,
"step": 676,
"tokens_trained": 0.064254376
},
{
"epoch": 0.19234042553191488,
"grad_norm": 3.34869384765625,
"loss": 5.5894,
"lr": 0.0009752447552447553,
"step": 678,
"tokens_trained": 0.0644448
},
{
"epoch": 0.19290780141843972,
"grad_norm": 3.083582878112793,
"loss": 5.5776,
"lr": 0.0009749650349650349,
"step": 680,
"tokens_trained": 0.064633712
},
{
"epoch": 0.19347517730496455,
"grad_norm": 3.345973491668701,
"loss": 5.5987,
"lr": 0.0009746853146853148,
"step": 682,
"tokens_trained": 0.064824808
},
{
"epoch": 0.19404255319148936,
"grad_norm": 3.9262702465057373,
"loss": 5.64,
"lr": 0.0009744055944055944,
"step": 684,
"tokens_trained": 0.065016224
},
{
"epoch": 0.1946099290780142,
"grad_norm": 3.298543930053711,
"loss": 5.587,
"lr": 0.0009741258741258742,
"step": 686,
"tokens_trained": 0.065204216
},
{
"epoch": 0.195177304964539,
"grad_norm": 3.118626832962036,
"loss": 5.5864,
"lr": 0.0009738461538461538,
"step": 688,
"tokens_trained": 0.065393256
},
{
"epoch": 0.19574468085106383,
"grad_norm": 2.983548402786255,
"loss": 5.5506,
"lr": 0.0009735664335664336,
"step": 690,
"tokens_trained": 0.06558324
},
{
"epoch": 0.19631205673758864,
"grad_norm": 3.5204527378082275,
"loss": 5.5336,
"lr": 0.0009732867132867133,
"step": 692,
"tokens_trained": 0.065775624
},
{
"epoch": 0.19687943262411348,
"grad_norm": 3.138550281524658,
"loss": 5.5677,
"lr": 0.000973006993006993,
"step": 694,
"tokens_trained": 0.0659666
},
{
"epoch": 0.1974468085106383,
"grad_norm": 3.0961053371429443,
"loss": 5.5714,
"lr": 0.0009727272727272728,
"step": 696,
"tokens_trained": 0.066155512
},
{
"epoch": 0.19801418439716312,
"grad_norm": 3.4929685592651367,
"loss": 5.5829,
"lr": 0.0009724475524475524,
"step": 698,
"tokens_trained": 0.06634576
},
{
"epoch": 0.19858156028368795,
"grad_norm": 3.1820616722106934,
"loss": 5.6108,
"lr": 0.0009721678321678323,
"step": 700,
"tokens_trained": 0.066537016
},
{
"epoch": 0.19914893617021276,
"grad_norm": 3.4244654178619385,
"loss": 5.6025,
"lr": 0.0009718881118881119,
"step": 702,
"tokens_trained": 0.066727856
},
{
"epoch": 0.1997163120567376,
"grad_norm": 3.258605480194092,
"loss": 5.5581,
"lr": 0.0009716083916083917,
"step": 704,
"tokens_trained": 0.066916672
},
{
"epoch": 0.2002836879432624,
"grad_norm": 2.7159688472747803,
"loss": 5.5478,
"lr": 0.0009713286713286713,
"step": 706,
"tokens_trained": 0.067107704
},
{
"epoch": 0.20085106382978724,
"grad_norm": 3.1941912174224854,
"loss": 5.6126,
"lr": 0.000971048951048951,
"step": 708,
"tokens_trained": 0.067297896
},
{
"epoch": 0.20141843971631207,
"grad_norm": 3.20470929145813,
"loss": 5.5628,
"lr": 0.0009707692307692308,
"step": 710,
"tokens_trained": 0.06748608
},
{
"epoch": 0.20198581560283688,
"grad_norm": 3.6400153636932373,
"loss": 5.5758,
"lr": 0.0009704895104895105,
"step": 712,
"tokens_trained": 0.0676766
},
{
"epoch": 0.2025531914893617,
"grad_norm": 2.881639003753662,
"loss": 5.5512,
"lr": 0.0009702097902097903,
"step": 714,
"tokens_trained": 0.067865848
},
{
"epoch": 0.20312056737588652,
"grad_norm": 3.1113905906677246,
"loss": 5.5396,
"lr": 0.0009699300699300699,
"step": 716,
"tokens_trained": 0.068055368
},
{
"epoch": 0.20368794326241135,
"grad_norm": 3.135014772415161,
"loss": 5.5763,
"lr": 0.0009696503496503498,
"step": 718,
"tokens_trained": 0.068248544
},
{
"epoch": 0.20425531914893616,
"grad_norm": 3.1870718002319336,
"loss": 5.5903,
"lr": 0.0009693706293706294,
"step": 720,
"tokens_trained": 0.068436944
},
{
"epoch": 0.204822695035461,
"grad_norm": 3.125596523284912,
"loss": 5.6033,
"lr": 0.0009690909090909091,
"step": 722,
"tokens_trained": 0.06862548
},
{
"epoch": 0.20539007092198583,
"grad_norm": 2.897671699523926,
"loss": 5.5946,
"lr": 0.0009688111888111888,
"step": 724,
"tokens_trained": 0.068815232
},
{
"epoch": 0.20595744680851064,
"grad_norm": 2.855313539505005,
"loss": 5.5731,
"lr": 0.0009685314685314685,
"step": 726,
"tokens_trained": 0.06900692
},
{
"epoch": 0.20652482269503547,
"grad_norm": 2.7760672569274902,
"loss": 5.4949,
"lr": 0.0009682517482517483,
"step": 728,
"tokens_trained": 0.069195376
},
{
"epoch": 0.20709219858156028,
"grad_norm": 2.9300007820129395,
"loss": 5.5491,
"lr": 0.000967972027972028,
"step": 730,
"tokens_trained": 0.069385512
},
{
"epoch": 0.2076595744680851,
"grad_norm": 3.299860954284668,
"loss": 5.5405,
"lr": 0.0009676923076923078,
"step": 732,
"tokens_trained": 0.069573304
},
{
"epoch": 0.20822695035460992,
"grad_norm": 3.300189256668091,
"loss": 5.5797,
"lr": 0.0009674125874125874,
"step": 734,
"tokens_trained": 0.069764248
},
{
"epoch": 0.20879432624113475,
"grad_norm": 2.932995557785034,
"loss": 5.5556,
"lr": 0.0009671328671328672,
"step": 736,
"tokens_trained": 0.06995496
},
{
"epoch": 0.2093617021276596,
"grad_norm": 2.6711719036102295,
"loss": 5.48,
"lr": 0.0009668531468531469,
"step": 738,
"tokens_trained": 0.070142776
},
{
"epoch": 0.2099290780141844,
"grad_norm": 2.833314895629883,
"loss": 5.542,
"lr": 0.0009665734265734266,
"step": 740,
"tokens_trained": 0.070332064
},
{
"epoch": 0.21049645390070923,
"grad_norm": 2.899843215942383,
"loss": 5.5649,
"lr": 0.0009662937062937063,
"step": 742,
"tokens_trained": 0.070523448
},
{
"epoch": 0.21106382978723404,
"grad_norm": 2.96528697013855,
"loss": 5.5277,
"lr": 0.000966013986013986,
"step": 744,
"tokens_trained": 0.070713768
},
{
"epoch": 0.21163120567375887,
"grad_norm": 2.921109437942505,
"loss": 5.5646,
"lr": 0.0009657342657342657,
"step": 746,
"tokens_trained": 0.070905704
},
{
"epoch": 0.21219858156028368,
"grad_norm": 3.2725329399108887,
"loss": 5.4786,
"lr": 0.0009654545454545455,
"step": 748,
"tokens_trained": 0.071096008
},
{
"epoch": 0.2127659574468085,
"grad_norm": 2.8296804428100586,
"loss": 5.573,
"lr": 0.0009651748251748252,
"step": 750,
"tokens_trained": 0.07128828
},
{
"epoch": 0.2127659574468085,
"eval_loss": 5.535472869873047,
"eval_runtime": 21.0109,
"step": 750,
"tokens_trained": 0.07128828
},
{
"epoch": 0.21333333333333335,
"grad_norm": 3.0509591102600098,
"loss": 5.6037,
"lr": 0.0009648951048951049,
"step": 752,
"tokens_trained": 0.071479496
},
{
"epoch": 0.21390070921985815,
"grad_norm": 2.6773571968078613,
"loss": 5.5266,
"lr": 0.0009646153846153846,
"step": 754,
"tokens_trained": 0.071668568
},
{
"epoch": 0.214468085106383,
"grad_norm": 2.9600210189819336,
"loss": 5.5362,
"lr": 0.0009643356643356644,
"step": 756,
"tokens_trained": 0.071860552
},
{
"epoch": 0.2150354609929078,
"grad_norm": 2.6674885749816895,
"loss": 5.5388,
"lr": 0.0009640559440559441,
"step": 758,
"tokens_trained": 0.07204912
},
{
"epoch": 0.21560283687943263,
"grad_norm": 2.50179386138916,
"loss": 5.5027,
"lr": 0.0009637762237762237,
"step": 760,
"tokens_trained": 0.072239952
},
{
"epoch": 0.21617021276595744,
"grad_norm": 2.843411684036255,
"loss": 5.5221,
"lr": 0.0009634965034965035,
"step": 762,
"tokens_trained": 0.07243076
},
{
"epoch": 0.21673758865248227,
"grad_norm": 2.8686277866363525,
"loss": 5.4896,
"lr": 0.0009632167832167832,
"step": 764,
"tokens_trained": 0.072623272
},
{
"epoch": 0.2173049645390071,
"grad_norm": 2.611424684524536,
"loss": 5.5557,
"lr": 0.000962937062937063,
"step": 766,
"tokens_trained": 0.07281408
},
{
"epoch": 0.2178723404255319,
"grad_norm": 3.013145685195923,
"loss": 5.4964,
"lr": 0.0009626573426573427,
"step": 768,
"tokens_trained": 0.073005016
},
{
"epoch": 0.21843971631205675,
"grad_norm": 2.8682022094726562,
"loss": 5.5232,
"lr": 0.0009623776223776224,
"step": 770,
"tokens_trained": 0.07319652
},
{
"epoch": 0.21900709219858155,
"grad_norm": 2.6478466987609863,
"loss": 5.5517,
"lr": 0.0009620979020979021,
"step": 772,
"tokens_trained": 0.073387048
},
{
"epoch": 0.2195744680851064,
"grad_norm": 2.7273097038269043,
"loss": 5.5572,
"lr": 0.0009618181818181818,
"step": 774,
"tokens_trained": 0.073577424
},
{
"epoch": 0.2201418439716312,
"grad_norm": 3.104907751083374,
"loss": 5.5081,
"lr": 0.0009615384615384616,
"step": 776,
"tokens_trained": 0.073766712
},
{
"epoch": 0.22070921985815603,
"grad_norm": 2.9616432189941406,
"loss": 5.5059,
"lr": 0.0009612587412587412,
"step": 778,
"tokens_trained": 0.073956272
},
{
"epoch": 0.22127659574468084,
"grad_norm": 3.330319881439209,
"loss": 5.4811,
"lr": 0.000960979020979021,
"step": 780,
"tokens_trained": 0.074144008
},
{
"epoch": 0.22184397163120567,
"grad_norm": 2.964371919631958,
"loss": 5.4763,
"lr": 0.0009606993006993007,
"step": 782,
"tokens_trained": 0.074333888
},
{
"epoch": 0.2224113475177305,
"grad_norm": 3.13899827003479,
"loss": 5.5262,
"lr": 0.0009604195804195805,
"step": 784,
"tokens_trained": 0.074523584
},
{
"epoch": 0.2229787234042553,
"grad_norm": 3.2576637268066406,
"loss": 5.4983,
"lr": 0.0009601398601398602,
"step": 786,
"tokens_trained": 0.074714128
},
{
"epoch": 0.22354609929078015,
"grad_norm": 2.916149616241455,
"loss": 5.504,
"lr": 0.0009598601398601398,
"step": 788,
"tokens_trained": 0.074905104
},
{
"epoch": 0.22411347517730495,
"grad_norm": 2.842733144760132,
"loss": 5.4997,
"lr": 0.0009595804195804196,
"step": 790,
"tokens_trained": 0.075096328
},
{
"epoch": 0.2246808510638298,
"grad_norm": 2.880695104598999,
"loss": 5.5131,
"lr": 0.0009593006993006993,
"step": 792,
"tokens_trained": 0.075286104
},
{
"epoch": 0.2252482269503546,
"grad_norm": 2.620516300201416,
"loss": 5.5291,
"lr": 0.0009590209790209791,
"step": 794,
"tokens_trained": 0.075477392
},
{
"epoch": 0.22581560283687943,
"grad_norm": 2.622455358505249,
"loss": 5.5433,
"lr": 0.0009587412587412587,
"step": 796,
"tokens_trained": 0.0756682
},
{
"epoch": 0.22638297872340427,
"grad_norm": 2.532047986984253,
"loss": 5.5169,
"lr": 0.0009584615384615385,
"step": 798,
"tokens_trained": 0.075856528
},
{
"epoch": 0.22695035460992907,
"grad_norm": 2.628110885620117,
"loss": 5.5369,
"lr": 0.0009581818181818182,
"step": 800,
"tokens_trained": 0.076046256
},
{
"epoch": 0.2275177304964539,
"grad_norm": 2.376600980758667,
"loss": 5.4888,
"lr": 0.000957902097902098,
"step": 802,
"tokens_trained": 0.076236016
},
{
"epoch": 0.22808510638297871,
"grad_norm": 2.433666706085205,
"loss": 5.5044,
"lr": 0.0009576223776223777,
"step": 804,
"tokens_trained": 0.07642324
},
{
"epoch": 0.22865248226950355,
"grad_norm": 2.3850929737091064,
"loss": 5.4941,
"lr": 0.0009573426573426573,
"step": 806,
"tokens_trained": 0.07661376
},
{
"epoch": 0.22921985815602836,
"grad_norm": 2.4664969444274902,
"loss": 5.5257,
"lr": 0.0009570629370629371,
"step": 808,
"tokens_trained": 0.076804952
},
{
"epoch": 0.2297872340425532,
"grad_norm": 2.8514602184295654,
"loss": 5.5335,
"lr": 0.0009567832167832168,
"step": 810,
"tokens_trained": 0.076995064
},
{
"epoch": 0.23035460992907802,
"grad_norm": 2.508887767791748,
"loss": 5.5093,
"lr": 0.0009565034965034966,
"step": 812,
"tokens_trained": 0.077185344
},
{
"epoch": 0.23092198581560283,
"grad_norm": 2.5842514038085938,
"loss": 5.5246,
"lr": 0.0009562237762237762,
"step": 814,
"tokens_trained": 0.077375232
},
{
"epoch": 0.23148936170212767,
"grad_norm": 2.621562957763672,
"loss": 5.4948,
"lr": 0.0009559440559440559,
"step": 816,
"tokens_trained": 0.07756528
},
{
"epoch": 0.23205673758865247,
"grad_norm": 2.3230698108673096,
"loss": 5.5367,
"lr": 0.0009556643356643357,
"step": 818,
"tokens_trained": 0.077754936
},
{
"epoch": 0.2326241134751773,
"grad_norm": 2.728039264678955,
"loss": 5.4548,
"lr": 0.0009553846153846154,
"step": 820,
"tokens_trained": 0.077944056
},
{
"epoch": 0.23319148936170211,
"grad_norm": 2.786271333694458,
"loss": 5.4701,
"lr": 0.0009551048951048952,
"step": 822,
"tokens_trained": 0.07813272
},
{
"epoch": 0.23375886524822695,
"grad_norm": 2.449995517730713,
"loss": 5.5505,
"lr": 0.0009548251748251748,
"step": 824,
"tokens_trained": 0.078321888
},
{
"epoch": 0.23432624113475178,
"grad_norm": 2.394447088241577,
"loss": 5.4709,
"lr": 0.0009545454545454546,
"step": 826,
"tokens_trained": 0.078510288
},
{
"epoch": 0.2348936170212766,
"grad_norm": 2.5857675075531006,
"loss": 5.4986,
"lr": 0.0009542657342657343,
"step": 828,
"tokens_trained": 0.078698032
},
{
"epoch": 0.23546099290780143,
"grad_norm": 2.728743314743042,
"loss": 5.4983,
"lr": 0.000953986013986014,
"step": 830,
"tokens_trained": 0.078890608
},
{
"epoch": 0.23602836879432623,
"grad_norm": 2.3619866371154785,
"loss": 5.4985,
"lr": 0.0009537062937062937,
"step": 832,
"tokens_trained": 0.079081968
},
{
"epoch": 0.23659574468085107,
"grad_norm": 2.6265158653259277,
"loss": 5.5088,
"lr": 0.0009534265734265734,
"step": 834,
"tokens_trained": 0.079270712
},
{
"epoch": 0.23716312056737587,
"grad_norm": 2.3731281757354736,
"loss": 5.4682,
"lr": 0.0009531468531468532,
"step": 836,
"tokens_trained": 0.079459912
},
{
"epoch": 0.2377304964539007,
"grad_norm": 2.375283718109131,
"loss": 5.4278,
"lr": 0.0009528671328671329,
"step": 838,
"tokens_trained": 0.079649408
},
{
"epoch": 0.23829787234042554,
"grad_norm": 2.6856729984283447,
"loss": 5.5277,
"lr": 0.0009525874125874127,
"step": 840,
"tokens_trained": 0.079839552
},
{
"epoch": 0.23886524822695035,
"grad_norm": 2.5037410259246826,
"loss": 5.5022,
"lr": 0.0009523076923076923,
"step": 842,
"tokens_trained": 0.08002732
},
{
"epoch": 0.23943262411347518,
"grad_norm": 2.25175404548645,
"loss": 5.4918,
"lr": 0.000952027972027972,
"step": 844,
"tokens_trained": 0.080216416
},
{
"epoch": 0.24,
"grad_norm": 2.3555264472961426,
"loss": 5.5134,
"lr": 0.0009517482517482518,
"step": 846,
"tokens_trained": 0.080406928
},
{
"epoch": 0.24056737588652483,
"grad_norm": 2.390998601913452,
"loss": 5.4721,
"lr": 0.0009514685314685315,
"step": 848,
"tokens_trained": 0.080596232
},
{
"epoch": 0.24113475177304963,
"grad_norm": 2.1585986614227295,
"loss": 5.4511,
"lr": 0.0009511888111888112,
"step": 850,
"tokens_trained": 0.080786848
},
{
"epoch": 0.24170212765957447,
"grad_norm": 2.7733986377716064,
"loss": 5.5269,
"lr": 0.0009509090909090909,
"step": 852,
"tokens_trained": 0.080978144
},
{
"epoch": 0.2422695035460993,
"grad_norm": 2.8021209239959717,
"loss": 5.4751,
"lr": 0.0009506293706293707,
"step": 854,
"tokens_trained": 0.081167712
},
{
"epoch": 0.2428368794326241,
"grad_norm": 2.5434224605560303,
"loss": 5.5154,
"lr": 0.0009503496503496504,
"step": 856,
"tokens_trained": 0.081357584
},
{
"epoch": 0.24340425531914894,
"grad_norm": 2.456421136856079,
"loss": 5.5459,
"lr": 0.0009500699300699301,
"step": 858,
"tokens_trained": 0.081545992
},
{
"epoch": 0.24397163120567375,
"grad_norm": 2.317312002182007,
"loss": 5.4644,
"lr": 0.0009497902097902098,
"step": 860,
"tokens_trained": 0.081735392
},
{
"epoch": 0.24453900709219858,
"grad_norm": 2.3580780029296875,
"loss": 5.4359,
"lr": 0.0009495104895104895,
"step": 862,
"tokens_trained": 0.081925608
},
{
"epoch": 0.2451063829787234,
"grad_norm": 2.6440224647521973,
"loss": 5.4757,
"lr": 0.0009492307692307693,
"step": 864,
"tokens_trained": 0.08211328
},
{
"epoch": 0.24567375886524823,
"grad_norm": 2.5468132495880127,
"loss": 5.4115,
"lr": 0.000948951048951049,
"step": 866,
"tokens_trained": 0.082303736
},
{
"epoch": 0.24624113475177306,
"grad_norm": 2.431992530822754,
"loss": 5.4655,
"lr": 0.0009486713286713286,
"step": 868,
"tokens_trained": 0.082492896
},
{
"epoch": 0.24680851063829787,
"grad_norm": 2.443335771560669,
"loss": 5.4684,
"lr": 0.0009483916083916084,
"step": 870,
"tokens_trained": 0.082684024
},
{
"epoch": 0.2473758865248227,
"grad_norm": 2.6467180252075195,
"loss": 5.5017,
"lr": 0.0009481118881118881,
"step": 872,
"tokens_trained": 0.08287444
},
{
"epoch": 0.2479432624113475,
"grad_norm": 2.6044974327087402,
"loss": 5.4637,
"lr": 0.0009478321678321679,
"step": 874,
"tokens_trained": 0.08306436
},
{
"epoch": 0.24822695035460993,
"eval_loss": 5.4816508293151855,
"eval_runtime": 20.9467,
"step": 875,
"tokens_trained": 0.083158888
},
{
"epoch": 0.24851063829787234,
"grad_norm": 2.6221189498901367,
"loss": 5.4785,
"lr": 0.0009475524475524476,
"step": 876,
"tokens_trained": 0.083253472
},
{
"epoch": 0.24907801418439715,
"grad_norm": 2.409327983856201,
"loss": 5.42,
"lr": 0.0009472727272727273,
"step": 878,
"tokens_trained": 0.08344528
},
{
"epoch": 0.24964539007092199,
"grad_norm": 2.2504723072052,
"loss": 5.399,
"lr": 0.000946993006993007,
"step": 880,
"tokens_trained": 0.083635752
},
{
"epoch": 0.2502127659574468,
"grad_norm": 2.3018665313720703,
"loss": 5.4512,
"lr": 0.0009467132867132868,
"step": 882,
"tokens_trained": 0.08382576
},
{
"epoch": 0.2507801418439716,
"grad_norm": 2.5774636268615723,
"loss": 5.4592,
"lr": 0.0009464335664335665,
"step": 884,
"tokens_trained": 0.084016232
},
{
"epoch": 0.25134751773049646,
"grad_norm": 2.614935874938965,
"loss": 5.4772,
"lr": 0.0009461538461538461,
"step": 886,
"tokens_trained": 0.084206992
},
{
"epoch": 0.2519148936170213,
"grad_norm": 2.4281506538391113,
"loss": 5.4972,
"lr": 0.0009458741258741259,
"step": 888,
"tokens_trained": 0.084395848
},
{
"epoch": 0.2524822695035461,
"grad_norm": 2.3668100833892822,
"loss": 5.4505,
"lr": 0.0009455944055944056,
"step": 890,
"tokens_trained": 0.084583704
},
{
"epoch": 0.2530496453900709,
"grad_norm": 2.1937146186828613,
"loss": 5.4981,
"lr": 0.0009453146853146854,
"step": 892,
"tokens_trained": 0.08477096
},
{
"epoch": 0.25361702127659574,
"grad_norm": 2.2917556762695312,
"loss": 5.4224,
"lr": 0.000945034965034965,
"step": 894,
"tokens_trained": 0.084961048
},
{
"epoch": 0.2541843971631206,
"grad_norm": 2.1254703998565674,
"loss": 5.4409,
"lr": 0.0009447552447552447,
"step": 896,
"tokens_trained": 0.085153256
},
{
"epoch": 0.2547517730496454,
"grad_norm": 2.267159938812256,
"loss": 5.4527,
"lr": 0.0009444755244755245,
"step": 898,
"tokens_trained": 0.085343128
},
{
"epoch": 0.2553191489361702,
"grad_norm": 2.1975555419921875,
"loss": 5.516,
"lr": 0.0009441958041958042,
"step": 900,
"tokens_trained": 0.085534024
},
{
"epoch": 0.255886524822695,
"grad_norm": 2.3459436893463135,
"loss": 5.4592,
"lr": 0.000943916083916084,
"step": 902,
"tokens_trained": 0.085725136
},
{
"epoch": 0.25645390070921986,
"grad_norm": 2.4788501262664795,
"loss": 5.3937,
"lr": 0.0009436363636363636,
"step": 904,
"tokens_trained": 0.08591548
},
{
"epoch": 0.2570212765957447,
"grad_norm": 2.415065288543701,
"loss": 5.3991,
"lr": 0.0009433566433566434,
"step": 906,
"tokens_trained": 0.086105008
},
{
"epoch": 0.25758865248226953,
"grad_norm": 2.1260058879852295,
"loss": 5.4122,
"lr": 0.0009430769230769231,
"step": 908,
"tokens_trained": 0.08629424
},
{
"epoch": 0.2581560283687943,
"grad_norm": 2.1759092807769775,
"loss": 5.4663,
"lr": 0.0009427972027972029,
"step": 910,
"tokens_trained": 0.086485784
},
{
"epoch": 0.25872340425531914,
"grad_norm": 2.3481245040893555,
"loss": 5.4398,
"lr": 0.0009425174825174825,
"step": 912,
"tokens_trained": 0.086676744
},
{
"epoch": 0.259290780141844,
"grad_norm": 2.312612533569336,
"loss": 5.4615,
"lr": 0.0009422377622377622,
"step": 914,
"tokens_trained": 0.086866424
},
{
"epoch": 0.2598581560283688,
"grad_norm": 2.4709548950195312,
"loss": 5.4062,
"lr": 0.000941958041958042,
"step": 916,
"tokens_trained": 0.087055824
},
{
"epoch": 0.2604255319148936,
"grad_norm": 2.3664543628692627,
"loss": 5.4696,
"lr": 0.0009416783216783217,
"step": 918,
"tokens_trained": 0.087244136
},
{
"epoch": 0.26099290780141843,
"grad_norm": 2.423687696456909,
"loss": 5.4762,
"lr": 0.0009413986013986015,
"step": 920,
"tokens_trained": 0.087432584
},
{
"epoch": 0.26156028368794326,
"grad_norm": 2.4002890586853027,
"loss": 5.4743,
"lr": 0.0009411188811188811,
"step": 922,
"tokens_trained": 0.087622248
},
{
"epoch": 0.2621276595744681,
"grad_norm": 2.107527494430542,
"loss": 5.4013,
"lr": 0.0009408391608391608,
"step": 924,
"tokens_trained": 0.087809888
},
{
"epoch": 0.26269503546099293,
"grad_norm": 2.05177640914917,
"loss": 5.4601,
"lr": 0.0009405594405594406,
"step": 926,
"tokens_trained": 0.088002704
},
{
"epoch": 0.2632624113475177,
"grad_norm": 2.303874969482422,
"loss": 5.456,
"lr": 0.0009402797202797203,
"step": 928,
"tokens_trained": 0.088191344
},
{
"epoch": 0.26382978723404255,
"grad_norm": 2.4369659423828125,
"loss": 5.4162,
"lr": 0.00094,
"step": 930,
"tokens_trained": 0.088380832
},
{
"epoch": 0.2643971631205674,
"grad_norm": 2.4750819206237793,
"loss": 5.455,
"lr": 0.0009397202797202797,
"step": 932,
"tokens_trained": 0.088569936
},
{
"epoch": 0.2649645390070922,
"grad_norm": 2.09557843208313,
"loss": 5.4273,
"lr": 0.0009394405594405595,
"step": 934,
"tokens_trained": 0.08876116
},
{
"epoch": 0.265531914893617,
"grad_norm": 2.0984373092651367,
"loss": 5.4342,
"lr": 0.0009391608391608392,
"step": 936,
"tokens_trained": 0.088951032
},
{
"epoch": 0.26609929078014183,
"grad_norm": 2.1150097846984863,
"loss": 5.4344,
"lr": 0.000938881118881119,
"step": 938,
"tokens_trained": 0.08914124
},
{
"epoch": 0.26666666666666666,
"grad_norm": 2.1577563285827637,
"loss": 5.455,
"lr": 0.0009386013986013986,
"step": 940,
"tokens_trained": 0.089330952
},
{
"epoch": 0.2672340425531915,
"grad_norm": 2.0483016967773438,
"loss": 5.413,
"lr": 0.0009383216783216783,
"step": 942,
"tokens_trained": 0.08952116
},
{
"epoch": 0.26780141843971633,
"grad_norm": 2.3116559982299805,
"loss": 5.455,
"lr": 0.0009380419580419581,
"step": 944,
"tokens_trained": 0.089712888
},
{
"epoch": 0.2683687943262411,
"grad_norm": 2.2459256649017334,
"loss": 5.3971,
"lr": 0.0009377622377622378,
"step": 946,
"tokens_trained": 0.089903936
},
{
"epoch": 0.26893617021276595,
"grad_norm": 2.3048787117004395,
"loss": 5.4454,
"lr": 0.0009374825174825175,
"step": 948,
"tokens_trained": 0.090095888
},
{
"epoch": 0.2695035460992908,
"grad_norm": 2.196735143661499,
"loss": 5.4101,
"lr": 0.0009372027972027972,
"step": 950,
"tokens_trained": 0.090287472
},
{
"epoch": 0.2700709219858156,
"grad_norm": 2.3908562660217285,
"loss": 5.4731,
"lr": 0.0009369230769230769,
"step": 952,
"tokens_trained": 0.090476568
},
{
"epoch": 0.27063829787234045,
"grad_norm": 2.154932975769043,
"loss": 5.4104,
"lr": 0.0009366433566433567,
"step": 954,
"tokens_trained": 0.090665592
},
{
"epoch": 0.27120567375886523,
"grad_norm": 2.340907096862793,
"loss": 5.3707,
"lr": 0.0009363636363636364,
"step": 956,
"tokens_trained": 0.090853232
},
{
"epoch": 0.27177304964539006,
"grad_norm": 2.1736438274383545,
"loss": 5.4484,
"lr": 0.0009360839160839161,
"step": 958,
"tokens_trained": 0.091043808
},
{
"epoch": 0.2723404255319149,
"grad_norm": 2.3518154621124268,
"loss": 5.4919,
"lr": 0.0009358041958041958,
"step": 960,
"tokens_trained": 0.09123384
},
{
"epoch": 0.27290780141843973,
"grad_norm": 2.6673426628112793,
"loss": 5.4008,
"lr": 0.0009355244755244755,
"step": 962,
"tokens_trained": 0.091422544
},
{
"epoch": 0.2734751773049645,
"grad_norm": 2.4755311012268066,
"loss": 5.4533,
"lr": 0.0009352447552447553,
"step": 964,
"tokens_trained": 0.09161544
},
{
"epoch": 0.27404255319148935,
"grad_norm": 2.338452100753784,
"loss": 5.4953,
"lr": 0.0009349650349650349,
"step": 966,
"tokens_trained": 0.091806344
},
{
"epoch": 0.2746099290780142,
"grad_norm": 2.170426845550537,
"loss": 5.4588,
"lr": 0.0009346853146853147,
"step": 968,
"tokens_trained": 0.091996648
},
{
"epoch": 0.275177304964539,
"grad_norm": 2.2587599754333496,
"loss": 5.4547,
"lr": 0.0009344055944055944,
"step": 970,
"tokens_trained": 0.09218848
},
{
"epoch": 0.27574468085106385,
"grad_norm": 2.0009043216705322,
"loss": 5.4116,
"lr": 0.0009341258741258742,
"step": 972,
"tokens_trained": 0.092377984
},
{
"epoch": 0.27631205673758863,
"grad_norm": 2.0617294311523438,
"loss": 5.4541,
"lr": 0.0009338461538461539,
"step": 974,
"tokens_trained": 0.092569472
},
{
"epoch": 0.27687943262411346,
"grad_norm": 2.059300661087036,
"loss": 5.4414,
"lr": 0.0009335664335664336,
"step": 976,
"tokens_trained": 0.092758496
},
{
"epoch": 0.2774468085106383,
"grad_norm": 2.2815263271331787,
"loss": 5.4435,
"lr": 0.0009332867132867133,
"step": 978,
"tokens_trained": 0.092950368
},
{
"epoch": 0.27801418439716313,
"grad_norm": 2.1770365238189697,
"loss": 5.4481,
"lr": 0.0009330069930069929,
"step": 980,
"tokens_trained": 0.093140552
},
{
"epoch": 0.27858156028368797,
"grad_norm": 2.0089797973632812,
"loss": 5.4117,
"lr": 0.0009327272727272728,
"step": 982,
"tokens_trained": 0.093332312
},
{
"epoch": 0.27914893617021275,
"grad_norm": 2.2188286781311035,
"loss": 5.4594,
"lr": 0.0009324475524475524,
"step": 984,
"tokens_trained": 0.093520792
},
{
"epoch": 0.2797163120567376,
"grad_norm": 2.310481548309326,
"loss": 5.393,
"lr": 0.0009321678321678322,
"step": 986,
"tokens_trained": 0.093710608
},
{
"epoch": 0.2802836879432624,
"grad_norm": 2.3832972049713135,
"loss": 5.4277,
"lr": 0.0009318881118881119,
"step": 988,
"tokens_trained": 0.093900952
},
{
"epoch": 0.28085106382978725,
"grad_norm": 2.011126756668091,
"loss": 5.4097,
"lr": 0.0009316083916083917,
"step": 990,
"tokens_trained": 0.094091
},
{
"epoch": 0.28141843971631203,
"grad_norm": 2.2632968425750732,
"loss": 5.4388,
"lr": 0.0009313286713286714,
"step": 992,
"tokens_trained": 0.094281216
},
{
"epoch": 0.28198581560283686,
"grad_norm": 2.3477587699890137,
"loss": 5.3728,
"lr": 0.000931048951048951,
"step": 994,
"tokens_trained": 0.094470264
},
{
"epoch": 0.2825531914893617,
"grad_norm": 2.486196756362915,
"loss": 5.414,
"lr": 0.0009307692307692308,
"step": 996,
"tokens_trained": 0.094662816
},
{
"epoch": 0.28312056737588653,
"grad_norm": 2.5286316871643066,
"loss": 5.4063,
"lr": 0.0009304895104895104,
"step": 998,
"tokens_trained": 0.094852896
},
{
"epoch": 0.28368794326241137,
"grad_norm": 2.712406635284424,
"loss": 5.4274,
"lr": 0.0009302097902097903,
"step": 1000,
"tokens_trained": 0.09504336
},
{
"epoch": 0.28368794326241137,
"eval_loss": 5.434450626373291,
"eval_runtime": 21.0388,
"step": 1000,
"tokens_trained": 0.09504336
},
{
"epoch": 0.28425531914893615,
"grad_norm": 2.245316505432129,
"loss": 5.3551,
"lr": 0.0009299300699300699,
"step": 1002,
"tokens_trained": 0.095233944
},
{
"epoch": 0.284822695035461,
"grad_norm": 2.335533618927002,
"loss": 5.4608,
"lr": 0.0009296503496503497,
"step": 1004,
"tokens_trained": 0.095423184
},
{
"epoch": 0.2853900709219858,
"grad_norm": 2.232128858566284,
"loss": 5.4374,
"lr": 0.0009293706293706294,
"step": 1006,
"tokens_trained": 0.095612672
},
{
"epoch": 0.28595744680851065,
"grad_norm": 2.148329257965088,
"loss": 5.463,
"lr": 0.0009290909090909091,
"step": 1008,
"tokens_trained": 0.095802784
},
{
"epoch": 0.2865248226950355,
"grad_norm": 1.9580810070037842,
"loss": 5.291,
"lr": 0.0009288111888111889,
"step": 1010,
"tokens_trained": 0.095990776
},
{
"epoch": 0.28709219858156027,
"grad_norm": 1.9873988628387451,
"loss": 5.4103,
"lr": 0.0009285314685314685,
"step": 1012,
"tokens_trained": 0.096180648
},
{
"epoch": 0.2876595744680851,
"grad_norm": 2.0297746658325195,
"loss": 5.4078,
"lr": 0.0009282517482517483,
"step": 1014,
"tokens_trained": 0.09637224
},
{
"epoch": 0.28822695035460993,
"grad_norm": 1.928497076034546,
"loss": 5.3162,
"lr": 0.0009279720279720279,
"step": 1016,
"tokens_trained": 0.096561744
},
{
"epoch": 0.28879432624113477,
"grad_norm": 2.1219675540924072,
"loss": 5.4358,
"lr": 0.0009276923076923078,
"step": 1018,
"tokens_trained": 0.096752296
},
{
"epoch": 0.28936170212765955,
"grad_norm": 2.0021066665649414,
"loss": 5.4232,
"lr": 0.0009274125874125874,
"step": 1020,
"tokens_trained": 0.096943856
},
{
"epoch": 0.2899290780141844,
"grad_norm": 1.9920068979263306,
"loss": 5.407,
"lr": 0.0009271328671328671,
"step": 1022,
"tokens_trained": 0.097133632
},
{
"epoch": 0.2904964539007092,
"grad_norm": 1.8810361623764038,
"loss": 5.4293,
"lr": 0.0009268531468531469,
"step": 1024,
"tokens_trained": 0.097325976
},
{
"epoch": 0.29106382978723405,
"grad_norm": 1.8560134172439575,
"loss": 5.4236,
"lr": 0.0009265734265734266,
"step": 1026,
"tokens_trained": 0.0975142
},
{
"epoch": 0.2916312056737589,
"grad_norm": 2.1735010147094727,
"loss": 5.4252,
"lr": 0.0009262937062937064,
"step": 1028,
"tokens_trained": 0.0977042
},
{
"epoch": 0.29219858156028367,
"grad_norm": 2.2467288970947266,
"loss": 5.3756,
"lr": 0.000926013986013986,
"step": 1030,
"tokens_trained": 0.097893376
},
{
"epoch": 0.2927659574468085,
"grad_norm": 1.9609313011169434,
"loss": 5.4091,
"lr": 0.0009257342657342658,
"step": 1032,
"tokens_trained": 0.0980824
},
{
"epoch": 0.29333333333333333,
"grad_norm": 2.116384267807007,
"loss": 5.4001,
"lr": 0.0009254545454545454,
"step": 1034,
"tokens_trained": 0.098271304
},
{
"epoch": 0.29390070921985817,
"grad_norm": 2.1869800090789795,
"loss": 5.4102,
"lr": 0.0009251748251748252,
"step": 1036,
"tokens_trained": 0.098461528
},
{
"epoch": 0.294468085106383,
"grad_norm": 2.2882192134857178,
"loss": 5.4723,
"lr": 0.0009248951048951049,
"step": 1038,
"tokens_trained": 0.09865268
},
{
"epoch": 0.2950354609929078,
"grad_norm": 2.1590888500213623,
"loss": 5.3523,
"lr": 0.0009246153846153846,
"step": 1040,
"tokens_trained": 0.098842688
},
{
"epoch": 0.2956028368794326,
"grad_norm": 2.284207582473755,
"loss": 5.4647,
"lr": 0.0009243356643356644,
"step": 1042,
"tokens_trained": 0.099031544
},
{
"epoch": 0.29617021276595745,
"grad_norm": 2.333207845687866,
"loss": 5.4655,
"lr": 0.0009240559440559441,
"step": 1044,
"tokens_trained": 0.09922264
},
{
"epoch": 0.2967375886524823,
"grad_norm": 2.357572555541992,
"loss": 5.3909,
"lr": 0.0009237762237762239,
"step": 1046,
"tokens_trained": 0.099411416
},
{
"epoch": 0.29730496453900707,
"grad_norm": 1.88053297996521,
"loss": 5.4119,
"lr": 0.0009234965034965035,
"step": 1048,
"tokens_trained": 0.099602112
},
{
"epoch": 0.2978723404255319,
"grad_norm": 1.8860585689544678,
"loss": 5.3867,
"lr": 0.0009232167832167832,
"step": 1050,
"tokens_trained": 0.099792552
},
{
"epoch": 0.29843971631205674,
"grad_norm": 2.000173568725586,
"loss": 5.3773,
"lr": 0.0009229370629370629,
"step": 1052,
"tokens_trained": 0.099981752
},
{
"epoch": 0.29900709219858157,
"grad_norm": 2.015394926071167,
"loss": 5.3936,
"lr": 0.0009226573426573427,
"step": 1054,
"tokens_trained": 0.10017428
},
{
"epoch": 0.2995744680851064,
"grad_norm": 2.0050301551818848,
"loss": 5.3653,
"lr": 0.0009223776223776224,
"step": 1056,
"tokens_trained": 0.100364544
},
{
"epoch": 0.3001418439716312,
"grad_norm": 1.7397475242614746,
"loss": 5.3224,
"lr": 0.0009220979020979021,
"step": 1058,
"tokens_trained": 0.100555648
},
{
"epoch": 0.300709219858156,
"grad_norm": 1.9808533191680908,
"loss": 5.3822,
"lr": 0.0009218181818181819,
"step": 1060,
"tokens_trained": 0.100744968
},
{
"epoch": 0.30127659574468085,
"grad_norm": 2.034329652786255,
"loss": 5.3961,
"lr": 0.0009215384615384616,
"step": 1062,
"tokens_trained": 0.100934176
},
{
"epoch": 0.3018439716312057,
"grad_norm": 2.1286778450012207,
"loss": 5.4061,
"lr": 0.0009212587412587413,
"step": 1064,
"tokens_trained": 0.101125216
},
{
"epoch": 0.3024113475177305,
"grad_norm": 2.131822347640991,
"loss": 5.3675,
"lr": 0.000920979020979021,
"step": 1066,
"tokens_trained": 0.101314504
},
{
"epoch": 0.3029787234042553,
"grad_norm": 2.162069320678711,
"loss": 5.4552,
"lr": 0.0009206993006993007,
"step": 1068,
"tokens_trained": 0.101503352
},
{
"epoch": 0.30354609929078014,
"grad_norm": 2.5730931758880615,
"loss": 5.3978,
"lr": 0.0009204195804195804,
"step": 1070,
"tokens_trained": 0.101691504
},
{
"epoch": 0.30411347517730497,
"grad_norm": 2.2053022384643555,
"loss": 5.3604,
"lr": 0.0009201398601398602,
"step": 1072,
"tokens_trained": 0.101883072
},
{
"epoch": 0.3046808510638298,
"grad_norm": 2.1578407287597656,
"loss": 5.4236,
"lr": 0.0009198601398601398,
"step": 1074,
"tokens_trained": 0.102075832
},
{
"epoch": 0.3052482269503546,
"grad_norm": 2.0061423778533936,
"loss": 5.3882,
"lr": 0.0009195804195804196,
"step": 1076,
"tokens_trained": 0.102266768
},
{
"epoch": 0.3058156028368794,
"grad_norm": 1.8915576934814453,
"loss": 5.3539,
"lr": 0.0009193006993006993,
"step": 1078,
"tokens_trained": 0.102457096
},
{
"epoch": 0.30638297872340425,
"grad_norm": 2.15053129196167,
"loss": 5.4222,
"lr": 0.0009190209790209791,
"step": 1080,
"tokens_trained": 0.102647544
},
{
"epoch": 0.3069503546099291,
"grad_norm": 2.241217851638794,
"loss": 5.4275,
"lr": 0.0009187412587412588,
"step": 1082,
"tokens_trained": 0.10283904
},
{
"epoch": 0.3075177304964539,
"grad_norm": 2.37854266166687,
"loss": 5.419,
"lr": 0.0009184615384615385,
"step": 1084,
"tokens_trained": 0.103028464
},
{
"epoch": 0.3080851063829787,
"grad_norm": 2.00118350982666,
"loss": 5.4225,
"lr": 0.0009181818181818182,
"step": 1086,
"tokens_trained": 0.10321896
},
{
"epoch": 0.30865248226950354,
"grad_norm": 2.2643723487854004,
"loss": 5.4487,
"lr": 0.0009179020979020978,
"step": 1088,
"tokens_trained": 0.103409256
},
{
"epoch": 0.30921985815602837,
"grad_norm": 2.4618585109710693,
"loss": 5.4211,
"lr": 0.0009176223776223777,
"step": 1090,
"tokens_trained": 0.103597272
},
{
"epoch": 0.3097872340425532,
"grad_norm": 2.141491174697876,
"loss": 5.3758,
"lr": 0.0009173426573426573,
"step": 1092,
"tokens_trained": 0.103786128
},
{
"epoch": 0.31035460992907804,
"grad_norm": 1.9777475595474243,
"loss": 5.4129,
"lr": 0.0009170629370629371,
"step": 1094,
"tokens_trained": 0.103974864
},
{
"epoch": 0.3109219858156028,
"grad_norm": 1.9153270721435547,
"loss": 5.3912,
"lr": 0.0009167832167832168,
"step": 1096,
"tokens_trained": 0.104163864
},
{
"epoch": 0.31148936170212765,
"grad_norm": 2.172558546066284,
"loss": 5.3425,
"lr": 0.0009165034965034966,
"step": 1098,
"tokens_trained": 0.104353136
},
{
"epoch": 0.3120567375886525,
"grad_norm": 2.049896717071533,
"loss": 5.3732,
"lr": 0.0009162237762237763,
"step": 1100,
"tokens_trained": 0.10454476
},
{
"epoch": 0.3126241134751773,
"grad_norm": 1.9415545463562012,
"loss": 5.3873,
"lr": 0.0009159440559440559,
"step": 1102,
"tokens_trained": 0.104734296
},
{
"epoch": 0.3131914893617021,
"grad_norm": 1.7280856370925903,
"loss": 5.3857,
"lr": 0.0009156643356643357,
"step": 1104,
"tokens_trained": 0.104925648
},
{
"epoch": 0.31375886524822694,
"grad_norm": 1.9120069742202759,
"loss": 5.3216,
"lr": 0.0009153846153846153,
"step": 1106,
"tokens_trained": 0.105115776
},
{
"epoch": 0.31432624113475177,
"grad_norm": 2.007101058959961,
"loss": 5.4074,
"lr": 0.0009151048951048952,
"step": 1108,
"tokens_trained": 0.105305656
},
{
"epoch": 0.3148936170212766,
"grad_norm": 1.9159268140792847,
"loss": 5.3625,
"lr": 0.0009148251748251748,
"step": 1110,
"tokens_trained": 0.105494632
},
{
"epoch": 0.31546099290780144,
"grad_norm": 1.9235239028930664,
"loss": 5.3362,
"lr": 0.0009145454545454546,
"step": 1112,
"tokens_trained": 0.105683536
},
{
"epoch": 0.3160283687943262,
"grad_norm": 1.8954299688339233,
"loss": 5.3531,
"lr": 0.0009142657342657343,
"step": 1114,
"tokens_trained": 0.105873176
},
{
"epoch": 0.31659574468085105,
"grad_norm": 2.026578426361084,
"loss": 5.408,
"lr": 0.000913986013986014,
"step": 1116,
"tokens_trained": 0.10606276
},
{
"epoch": 0.3171631205673759,
"grad_norm": 1.9014806747436523,
"loss": 5.363,
"lr": 0.0009137062937062938,
"step": 1118,
"tokens_trained": 0.106254616
},
{
"epoch": 0.3177304964539007,
"grad_norm": 1.849649429321289,
"loss": 5.3811,
"lr": 0.0009134265734265734,
"step": 1120,
"tokens_trained": 0.106445376
},
{
"epoch": 0.31829787234042556,
"grad_norm": 1.7405186891555786,
"loss": 5.3504,
"lr": 0.0009131468531468532,
"step": 1122,
"tokens_trained": 0.106636072
},
{
"epoch": 0.31886524822695034,
"grad_norm": 1.867285966873169,
"loss": 5.3675,
"lr": 0.0009128671328671328,
"step": 1124,
"tokens_trained": 0.106827896
},
{
"epoch": 0.3191489361702128,
"eval_loss": 5.3796281814575195,
"eval_runtime": 20.7444,
"step": 1125,
"tokens_trained": 0.106922416
}
],
"logging_steps": 2,
"max_steps": 7650,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 125,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}