ds-random-1 / trainer_state.json
vitaleantonio's picture
Upload ds-random-1
2f93db3 verified
Raw
History Blame Contribute Delete
137 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 845,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0011837821840781297,
"grad_norm": 27.25,
"learning_rate": 4.739336492890996e-08,
"loss": 4.5742,
"step": 1
},
{
"epoch": 0.0023675643681562593,
"grad_norm": 25.875,
"learning_rate": 9.478672985781992e-08,
"loss": 4.1168,
"step": 2
},
{
"epoch": 0.003551346552234389,
"grad_norm": 25.5,
"learning_rate": 1.4218009478672986e-07,
"loss": 4.2987,
"step": 3
},
{
"epoch": 0.004735128736312519,
"grad_norm": 30.25,
"learning_rate": 1.8957345971563984e-07,
"loss": 4.5405,
"step": 4
},
{
"epoch": 0.005918910920390648,
"grad_norm": 27.125,
"learning_rate": 2.3696682464454978e-07,
"loss": 4.3069,
"step": 5
},
{
"epoch": 0.007102693104468778,
"grad_norm": 26.0,
"learning_rate": 2.843601895734597e-07,
"loss": 4.552,
"step": 6
},
{
"epoch": 0.008286475288546907,
"grad_norm": 31.125,
"learning_rate": 3.317535545023697e-07,
"loss": 4.3416,
"step": 7
},
{
"epoch": 0.009470257472625037,
"grad_norm": 25.25,
"learning_rate": 3.791469194312797e-07,
"loss": 4.5185,
"step": 8
},
{
"epoch": 0.010654039656703166,
"grad_norm": 28.375,
"learning_rate": 4.265402843601896e-07,
"loss": 4.6644,
"step": 9
},
{
"epoch": 0.011837821840781295,
"grad_norm": 24.25,
"learning_rate": 4.7393364928909956e-07,
"loss": 4.0805,
"step": 10
},
{
"epoch": 0.013021604024859426,
"grad_norm": 31.0,
"learning_rate": 5.213270142180095e-07,
"loss": 4.8569,
"step": 11
},
{
"epoch": 0.014205386208937555,
"grad_norm": 27.75,
"learning_rate": 5.687203791469194e-07,
"loss": 4.2514,
"step": 12
},
{
"epoch": 0.015389168393015686,
"grad_norm": 25.0,
"learning_rate": 6.161137440758294e-07,
"loss": 4.0034,
"step": 13
},
{
"epoch": 0.016572950577093813,
"grad_norm": 25.0,
"learning_rate": 6.635071090047394e-07,
"loss": 4.568,
"step": 14
},
{
"epoch": 0.017756732761171946,
"grad_norm": 27.875,
"learning_rate": 7.109004739336493e-07,
"loss": 4.7432,
"step": 15
},
{
"epoch": 0.018940514945250075,
"grad_norm": 24.375,
"learning_rate": 7.582938388625594e-07,
"loss": 4.1086,
"step": 16
},
{
"epoch": 0.020124297129328204,
"grad_norm": 32.0,
"learning_rate": 8.056872037914692e-07,
"loss": 5.0878,
"step": 17
},
{
"epoch": 0.021308079313406333,
"grad_norm": 27.875,
"learning_rate": 8.530805687203792e-07,
"loss": 4.1515,
"step": 18
},
{
"epoch": 0.022491861497484462,
"grad_norm": 31.875,
"learning_rate": 9.004739336492892e-07,
"loss": 4.4924,
"step": 19
},
{
"epoch": 0.02367564368156259,
"grad_norm": 30.75,
"learning_rate": 9.478672985781991e-07,
"loss": 4.1903,
"step": 20
},
{
"epoch": 0.024859425865640723,
"grad_norm": 24.25,
"learning_rate": 9.95260663507109e-07,
"loss": 4.1328,
"step": 21
},
{
"epoch": 0.026043208049718852,
"grad_norm": 29.75,
"learning_rate": 1.042654028436019e-06,
"loss": 4.3652,
"step": 22
},
{
"epoch": 0.02722699023379698,
"grad_norm": 31.5,
"learning_rate": 1.090047393364929e-06,
"loss": 4.5804,
"step": 23
},
{
"epoch": 0.02841077241787511,
"grad_norm": 27.875,
"learning_rate": 1.1374407582938388e-06,
"loss": 4.2407,
"step": 24
},
{
"epoch": 0.02959455460195324,
"grad_norm": 26.0,
"learning_rate": 1.184834123222749e-06,
"loss": 3.823,
"step": 25
},
{
"epoch": 0.030778336786031372,
"grad_norm": 24.75,
"learning_rate": 1.2322274881516587e-06,
"loss": 4.5008,
"step": 26
},
{
"epoch": 0.0319621189701095,
"grad_norm": 34.5,
"learning_rate": 1.2796208530805687e-06,
"loss": 4.1535,
"step": 27
},
{
"epoch": 0.033145901154187626,
"grad_norm": 30.375,
"learning_rate": 1.3270142180094788e-06,
"loss": 4.6596,
"step": 28
},
{
"epoch": 0.03432968333826576,
"grad_norm": 28.375,
"learning_rate": 1.3744075829383887e-06,
"loss": 4.2302,
"step": 29
},
{
"epoch": 0.03551346552234389,
"grad_norm": 29.75,
"learning_rate": 1.4218009478672987e-06,
"loss": 3.9536,
"step": 30
},
{
"epoch": 0.03669724770642202,
"grad_norm": 25.625,
"learning_rate": 1.4691943127962086e-06,
"loss": 4.0247,
"step": 31
},
{
"epoch": 0.03788102989050015,
"grad_norm": 28.625,
"learning_rate": 1.5165876777251187e-06,
"loss": 4.2866,
"step": 32
},
{
"epoch": 0.03906481207457828,
"grad_norm": 27.0,
"learning_rate": 1.5639810426540287e-06,
"loss": 4.3479,
"step": 33
},
{
"epoch": 0.04024859425865641,
"grad_norm": 27.125,
"learning_rate": 1.6113744075829384e-06,
"loss": 4.1932,
"step": 34
},
{
"epoch": 0.041432376442734536,
"grad_norm": 31.375,
"learning_rate": 1.6587677725118483e-06,
"loss": 4.5418,
"step": 35
},
{
"epoch": 0.042616158626812665,
"grad_norm": 24.5,
"learning_rate": 1.7061611374407585e-06,
"loss": 3.9115,
"step": 36
},
{
"epoch": 0.043799940810890794,
"grad_norm": 29.0,
"learning_rate": 1.7535545023696684e-06,
"loss": 4.4143,
"step": 37
},
{
"epoch": 0.044983722994968924,
"grad_norm": 27.25,
"learning_rate": 1.8009478672985784e-06,
"loss": 4.256,
"step": 38
},
{
"epoch": 0.04616750517904705,
"grad_norm": 25.375,
"learning_rate": 1.8483412322274883e-06,
"loss": 3.8378,
"step": 39
},
{
"epoch": 0.04735128736312518,
"grad_norm": 27.125,
"learning_rate": 1.8957345971563982e-06,
"loss": 3.9533,
"step": 40
},
{
"epoch": 0.04853506954720332,
"grad_norm": 28.375,
"learning_rate": 1.943127962085308e-06,
"loss": 4.006,
"step": 41
},
{
"epoch": 0.049718851731281447,
"grad_norm": 25.875,
"learning_rate": 1.990521327014218e-06,
"loss": 4.3288,
"step": 42
},
{
"epoch": 0.050902633915359576,
"grad_norm": 25.875,
"learning_rate": 2.037914691943128e-06,
"loss": 4.1281,
"step": 43
},
{
"epoch": 0.052086416099437705,
"grad_norm": 26.0,
"learning_rate": 2.085308056872038e-06,
"loss": 4.2562,
"step": 44
},
{
"epoch": 0.053270198283515834,
"grad_norm": 29.375,
"learning_rate": 2.1327014218009483e-06,
"loss": 4.144,
"step": 45
},
{
"epoch": 0.05445398046759396,
"grad_norm": 28.75,
"learning_rate": 2.180094786729858e-06,
"loss": 4.2635,
"step": 46
},
{
"epoch": 0.05563776265167209,
"grad_norm": 30.5,
"learning_rate": 2.2274881516587678e-06,
"loss": 4.1032,
"step": 47
},
{
"epoch": 0.05682154483575022,
"grad_norm": 28.375,
"learning_rate": 2.2748815165876777e-06,
"loss": 4.0056,
"step": 48
},
{
"epoch": 0.05800532701982835,
"grad_norm": 21.25,
"learning_rate": 2.322274881516588e-06,
"loss": 3.6885,
"step": 49
},
{
"epoch": 0.05918910920390648,
"grad_norm": 38.75,
"learning_rate": 2.369668246445498e-06,
"loss": 4.8308,
"step": 50
},
{
"epoch": 0.06037289138798461,
"grad_norm": 27.5,
"learning_rate": 2.417061611374408e-06,
"loss": 3.9768,
"step": 51
},
{
"epoch": 0.061556673572062744,
"grad_norm": 24.0,
"learning_rate": 2.4644549763033174e-06,
"loss": 3.6757,
"step": 52
},
{
"epoch": 0.06274045575614087,
"grad_norm": 27.25,
"learning_rate": 2.5118483412322274e-06,
"loss": 4.0805,
"step": 53
},
{
"epoch": 0.063924237940219,
"grad_norm": 24.25,
"learning_rate": 2.5592417061611373e-06,
"loss": 3.896,
"step": 54
},
{
"epoch": 0.06510802012429713,
"grad_norm": 26.0,
"learning_rate": 2.606635071090048e-06,
"loss": 3.9153,
"step": 55
},
{
"epoch": 0.06629180230837525,
"grad_norm": 23.25,
"learning_rate": 2.6540284360189576e-06,
"loss": 3.9136,
"step": 56
},
{
"epoch": 0.06747558449245339,
"grad_norm": 27.0,
"learning_rate": 2.7014218009478675e-06,
"loss": 4.0031,
"step": 57
},
{
"epoch": 0.06865936667653152,
"grad_norm": 25.75,
"learning_rate": 2.7488151658767775e-06,
"loss": 3.8149,
"step": 58
},
{
"epoch": 0.06984314886060965,
"grad_norm": 23.5,
"learning_rate": 2.7962085308056874e-06,
"loss": 3.6599,
"step": 59
},
{
"epoch": 0.07102693104468778,
"grad_norm": 23.625,
"learning_rate": 2.8436018957345973e-06,
"loss": 3.9296,
"step": 60
},
{
"epoch": 0.0722107132287659,
"grad_norm": 22.5,
"learning_rate": 2.8909952606635073e-06,
"loss": 3.8185,
"step": 61
},
{
"epoch": 0.07339449541284404,
"grad_norm": 25.375,
"learning_rate": 2.938388625592417e-06,
"loss": 4.0957,
"step": 62
},
{
"epoch": 0.07457827759692216,
"grad_norm": 19.625,
"learning_rate": 2.985781990521327e-06,
"loss": 3.8312,
"step": 63
},
{
"epoch": 0.0757620597810003,
"grad_norm": 24.75,
"learning_rate": 3.0331753554502375e-06,
"loss": 3.9194,
"step": 64
},
{
"epoch": 0.07694584196507842,
"grad_norm": 24.625,
"learning_rate": 3.0805687203791474e-06,
"loss": 3.8047,
"step": 65
},
{
"epoch": 0.07812962414915656,
"grad_norm": 20.375,
"learning_rate": 3.1279620853080574e-06,
"loss": 4.0207,
"step": 66
},
{
"epoch": 0.07931340633323468,
"grad_norm": 21.875,
"learning_rate": 3.1753554502369673e-06,
"loss": 3.6675,
"step": 67
},
{
"epoch": 0.08049718851731281,
"grad_norm": 17.875,
"learning_rate": 3.222748815165877e-06,
"loss": 3.5946,
"step": 68
},
{
"epoch": 0.08168097070139095,
"grad_norm": 17.75,
"learning_rate": 3.2701421800947867e-06,
"loss": 3.5922,
"step": 69
},
{
"epoch": 0.08286475288546907,
"grad_norm": 18.375,
"learning_rate": 3.3175355450236967e-06,
"loss": 3.4621,
"step": 70
},
{
"epoch": 0.08404853506954721,
"grad_norm": 16.625,
"learning_rate": 3.3649289099526066e-06,
"loss": 3.4249,
"step": 71
},
{
"epoch": 0.08523231725362533,
"grad_norm": 17.0,
"learning_rate": 3.412322274881517e-06,
"loss": 3.1019,
"step": 72
},
{
"epoch": 0.08641609943770347,
"grad_norm": 16.875,
"learning_rate": 3.459715639810427e-06,
"loss": 3.8747,
"step": 73
},
{
"epoch": 0.08759988162178159,
"grad_norm": 17.25,
"learning_rate": 3.507109004739337e-06,
"loss": 3.2951,
"step": 74
},
{
"epoch": 0.08878366380585972,
"grad_norm": 14.875,
"learning_rate": 3.5545023696682468e-06,
"loss": 3.6178,
"step": 75
},
{
"epoch": 0.08996744598993785,
"grad_norm": 14.875,
"learning_rate": 3.6018957345971567e-06,
"loss": 3.6471,
"step": 76
},
{
"epoch": 0.09115122817401598,
"grad_norm": 15.375,
"learning_rate": 3.6492890995260666e-06,
"loss": 3.6079,
"step": 77
},
{
"epoch": 0.0923350103580941,
"grad_norm": 14.5625,
"learning_rate": 3.6966824644549766e-06,
"loss": 3.5527,
"step": 78
},
{
"epoch": 0.09351879254217224,
"grad_norm": 13.875,
"learning_rate": 3.7440758293838865e-06,
"loss": 3.6016,
"step": 79
},
{
"epoch": 0.09470257472625036,
"grad_norm": 13.125,
"learning_rate": 3.7914691943127964e-06,
"loss": 3.142,
"step": 80
},
{
"epoch": 0.0958863569103285,
"grad_norm": 13.3125,
"learning_rate": 3.838862559241707e-06,
"loss": 3.6945,
"step": 81
},
{
"epoch": 0.09707013909440664,
"grad_norm": 13.1875,
"learning_rate": 3.886255924170616e-06,
"loss": 3.3941,
"step": 82
},
{
"epoch": 0.09825392127848476,
"grad_norm": 12.375,
"learning_rate": 3.933649289099527e-06,
"loss": 3.4295,
"step": 83
},
{
"epoch": 0.09943770346256289,
"grad_norm": 11.9375,
"learning_rate": 3.981042654028436e-06,
"loss": 3.3487,
"step": 84
},
{
"epoch": 0.10062148564664102,
"grad_norm": 12.25,
"learning_rate": 4.0284360189573465e-06,
"loss": 2.9911,
"step": 85
},
{
"epoch": 0.10180526783071915,
"grad_norm": 13.1875,
"learning_rate": 4.075829383886256e-06,
"loss": 3.2688,
"step": 86
},
{
"epoch": 0.10298905001479727,
"grad_norm": 13.875,
"learning_rate": 4.123222748815166e-06,
"loss": 3.3584,
"step": 87
},
{
"epoch": 0.10417283219887541,
"grad_norm": 11.1875,
"learning_rate": 4.170616113744076e-06,
"loss": 3.3488,
"step": 88
},
{
"epoch": 0.10535661438295353,
"grad_norm": 9.625,
"learning_rate": 4.218009478672986e-06,
"loss": 3.0363,
"step": 89
},
{
"epoch": 0.10654039656703167,
"grad_norm": 11.25,
"learning_rate": 4.265402843601897e-06,
"loss": 3.0994,
"step": 90
},
{
"epoch": 0.10772417875110979,
"grad_norm": 10.625,
"learning_rate": 4.312796208530806e-06,
"loss": 3.1566,
"step": 91
},
{
"epoch": 0.10890796093518793,
"grad_norm": 10.25,
"learning_rate": 4.360189573459716e-06,
"loss": 3.1273,
"step": 92
},
{
"epoch": 0.11009174311926606,
"grad_norm": 10.25,
"learning_rate": 4.407582938388626e-06,
"loss": 3.3201,
"step": 93
},
{
"epoch": 0.11127552530334418,
"grad_norm": 10.8125,
"learning_rate": 4.4549763033175355e-06,
"loss": 3.4172,
"step": 94
},
{
"epoch": 0.11245930748742232,
"grad_norm": 9.4375,
"learning_rate": 4.502369668246446e-06,
"loss": 2.954,
"step": 95
},
{
"epoch": 0.11364308967150044,
"grad_norm": 10.25,
"learning_rate": 4.549763033175355e-06,
"loss": 3.1252,
"step": 96
},
{
"epoch": 0.11482687185557858,
"grad_norm": 11.625,
"learning_rate": 4.597156398104266e-06,
"loss": 3.2224,
"step": 97
},
{
"epoch": 0.1160106540396567,
"grad_norm": 9.0625,
"learning_rate": 4.644549763033176e-06,
"loss": 3.2088,
"step": 98
},
{
"epoch": 0.11719443622373484,
"grad_norm": 10.375,
"learning_rate": 4.691943127962086e-06,
"loss": 3.2489,
"step": 99
},
{
"epoch": 0.11837821840781296,
"grad_norm": 9.8125,
"learning_rate": 4.739336492890996e-06,
"loss": 3.2759,
"step": 100
},
{
"epoch": 0.1195620005918911,
"grad_norm": 9.125,
"learning_rate": 4.7867298578199055e-06,
"loss": 3.4241,
"step": 101
},
{
"epoch": 0.12074578277596922,
"grad_norm": 9.4375,
"learning_rate": 4.834123222748816e-06,
"loss": 3.4328,
"step": 102
},
{
"epoch": 0.12192956496004735,
"grad_norm": 8.4375,
"learning_rate": 4.881516587677725e-06,
"loss": 3.2802,
"step": 103
},
{
"epoch": 0.12311334714412549,
"grad_norm": 9.125,
"learning_rate": 4.928909952606635e-06,
"loss": 3.1197,
"step": 104
},
{
"epoch": 0.12429712932820361,
"grad_norm": 9.625,
"learning_rate": 4.976303317535545e-06,
"loss": 3.1239,
"step": 105
},
{
"epoch": 0.12548091151228175,
"grad_norm": 8.3125,
"learning_rate": 5.023696682464455e-06,
"loss": 3.4392,
"step": 106
},
{
"epoch": 0.12666469369635988,
"grad_norm": 8.625,
"learning_rate": 5.071090047393366e-06,
"loss": 2.8405,
"step": 107
},
{
"epoch": 0.127848475880438,
"grad_norm": 8.875,
"learning_rate": 5.118483412322275e-06,
"loss": 3.1389,
"step": 108
},
{
"epoch": 0.12903225806451613,
"grad_norm": 8.1875,
"learning_rate": 5.165876777251185e-06,
"loss": 3.102,
"step": 109
},
{
"epoch": 0.13021604024859426,
"grad_norm": 8.25,
"learning_rate": 5.213270142180096e-06,
"loss": 3.3589,
"step": 110
},
{
"epoch": 0.1313998224326724,
"grad_norm": 7.6875,
"learning_rate": 5.260663507109005e-06,
"loss": 2.9471,
"step": 111
},
{
"epoch": 0.1325836046167505,
"grad_norm": 8.4375,
"learning_rate": 5.308056872037915e-06,
"loss": 3.5415,
"step": 112
},
{
"epoch": 0.13376738680082864,
"grad_norm": 8.0625,
"learning_rate": 5.355450236966825e-06,
"loss": 3.157,
"step": 113
},
{
"epoch": 0.13495116898490678,
"grad_norm": 8.75,
"learning_rate": 5.402843601895735e-06,
"loss": 3.2572,
"step": 114
},
{
"epoch": 0.1361349511689849,
"grad_norm": 8.25,
"learning_rate": 5.4502369668246446e-06,
"loss": 2.5215,
"step": 115
},
{
"epoch": 0.13731873335306305,
"grad_norm": 8.0,
"learning_rate": 5.497630331753555e-06,
"loss": 3.0994,
"step": 116
},
{
"epoch": 0.13850251553714116,
"grad_norm": 6.71875,
"learning_rate": 5.5450236966824644e-06,
"loss": 2.7125,
"step": 117
},
{
"epoch": 0.1396862977212193,
"grad_norm": 7.96875,
"learning_rate": 5.592417061611375e-06,
"loss": 3.2456,
"step": 118
},
{
"epoch": 0.14087007990529743,
"grad_norm": 7.28125,
"learning_rate": 5.639810426540285e-06,
"loss": 3.0475,
"step": 119
},
{
"epoch": 0.14205386208937557,
"grad_norm": 7.1875,
"learning_rate": 5.687203791469195e-06,
"loss": 2.6618,
"step": 120
},
{
"epoch": 0.14323764427345367,
"grad_norm": 7.0625,
"learning_rate": 5.734597156398105e-06,
"loss": 2.9899,
"step": 121
},
{
"epoch": 0.1444214264575318,
"grad_norm": 7.6875,
"learning_rate": 5.7819905213270145e-06,
"loss": 2.954,
"step": 122
},
{
"epoch": 0.14560520864160995,
"grad_norm": 8.0625,
"learning_rate": 5.829383886255925e-06,
"loss": 3.1818,
"step": 123
},
{
"epoch": 0.14678899082568808,
"grad_norm": 6.59375,
"learning_rate": 5.876777251184834e-06,
"loss": 2.9092,
"step": 124
},
{
"epoch": 0.1479727730097662,
"grad_norm": 7.34375,
"learning_rate": 5.924170616113745e-06,
"loss": 2.7546,
"step": 125
},
{
"epoch": 0.14915655519384433,
"grad_norm": 6.6875,
"learning_rate": 5.971563981042654e-06,
"loss": 2.7714,
"step": 126
},
{
"epoch": 0.15034033737792246,
"grad_norm": 7.65625,
"learning_rate": 6.018957345971565e-06,
"loss": 3.1014,
"step": 127
},
{
"epoch": 0.1515241195620006,
"grad_norm": 6.40625,
"learning_rate": 6.066350710900475e-06,
"loss": 2.6143,
"step": 128
},
{
"epoch": 0.15270790174607873,
"grad_norm": 7.0,
"learning_rate": 6.1137440758293845e-06,
"loss": 2.7326,
"step": 129
},
{
"epoch": 0.15389168393015684,
"grad_norm": 6.625,
"learning_rate": 6.161137440758295e-06,
"loss": 3.0394,
"step": 130
},
{
"epoch": 0.15507546611423498,
"grad_norm": 6.4375,
"learning_rate": 6.208530805687204e-06,
"loss": 2.8432,
"step": 131
},
{
"epoch": 0.1562592482983131,
"grad_norm": 6.3125,
"learning_rate": 6.255924170616115e-06,
"loss": 3.0408,
"step": 132
},
{
"epoch": 0.15744303048239125,
"grad_norm": 6.53125,
"learning_rate": 6.303317535545023e-06,
"loss": 3.3141,
"step": 133
},
{
"epoch": 0.15862681266646936,
"grad_norm": 7.15625,
"learning_rate": 6.350710900473935e-06,
"loss": 2.8043,
"step": 134
},
{
"epoch": 0.1598105948505475,
"grad_norm": 6.5625,
"learning_rate": 6.398104265402843e-06,
"loss": 2.9025,
"step": 135
},
{
"epoch": 0.16099437703462563,
"grad_norm": 6.28125,
"learning_rate": 6.445497630331754e-06,
"loss": 2.7204,
"step": 136
},
{
"epoch": 0.16217815921870377,
"grad_norm": 6.625,
"learning_rate": 6.492890995260665e-06,
"loss": 3.2232,
"step": 137
},
{
"epoch": 0.1633619414027819,
"grad_norm": 6.125,
"learning_rate": 6.5402843601895735e-06,
"loss": 2.7932,
"step": 138
},
{
"epoch": 0.16454572358686,
"grad_norm": 5.4375,
"learning_rate": 6.587677725118484e-06,
"loss": 2.9037,
"step": 139
},
{
"epoch": 0.16572950577093815,
"grad_norm": 6.53125,
"learning_rate": 6.635071090047393e-06,
"loss": 2.7124,
"step": 140
},
{
"epoch": 0.16691328795501628,
"grad_norm": 5.8125,
"learning_rate": 6.682464454976304e-06,
"loss": 2.8579,
"step": 141
},
{
"epoch": 0.16809707013909442,
"grad_norm": 6.09375,
"learning_rate": 6.729857819905213e-06,
"loss": 2.7268,
"step": 142
},
{
"epoch": 0.16928085232317253,
"grad_norm": 5.4375,
"learning_rate": 6.777251184834124e-06,
"loss": 2.8448,
"step": 143
},
{
"epoch": 0.17046463450725066,
"grad_norm": 6.09375,
"learning_rate": 6.824644549763034e-06,
"loss": 2.9575,
"step": 144
},
{
"epoch": 0.1716484166913288,
"grad_norm": 5.46875,
"learning_rate": 6.8720379146919435e-06,
"loss": 3.0127,
"step": 145
},
{
"epoch": 0.17283219887540693,
"grad_norm": 5.96875,
"learning_rate": 6.919431279620854e-06,
"loss": 3.029,
"step": 146
},
{
"epoch": 0.17401598105948504,
"grad_norm": 5.875,
"learning_rate": 6.966824644549763e-06,
"loss": 2.981,
"step": 147
},
{
"epoch": 0.17519976324356318,
"grad_norm": 5.9375,
"learning_rate": 7.014218009478674e-06,
"loss": 2.7306,
"step": 148
},
{
"epoch": 0.17638354542764131,
"grad_norm": 6.375,
"learning_rate": 7.061611374407583e-06,
"loss": 3.0311,
"step": 149
},
{
"epoch": 0.17756732761171945,
"grad_norm": 6.1875,
"learning_rate": 7.1090047393364935e-06,
"loss": 3.01,
"step": 150
},
{
"epoch": 0.17875110979579759,
"grad_norm": 6.40625,
"learning_rate": 7.156398104265403e-06,
"loss": 2.8043,
"step": 151
},
{
"epoch": 0.1799348919798757,
"grad_norm": 6.09375,
"learning_rate": 7.203791469194313e-06,
"loss": 3.0152,
"step": 152
},
{
"epoch": 0.18111867416395383,
"grad_norm": 7.03125,
"learning_rate": 7.251184834123224e-06,
"loss": 3.0736,
"step": 153
},
{
"epoch": 0.18230245634803197,
"grad_norm": 6.3125,
"learning_rate": 7.298578199052133e-06,
"loss": 2.8339,
"step": 154
},
{
"epoch": 0.1834862385321101,
"grad_norm": 6.9375,
"learning_rate": 7.345971563981044e-06,
"loss": 3.1329,
"step": 155
},
{
"epoch": 0.1846700207161882,
"grad_norm": 6.03125,
"learning_rate": 7.393364928909953e-06,
"loss": 3.1381,
"step": 156
},
{
"epoch": 0.18585380290026635,
"grad_norm": 5.625,
"learning_rate": 7.4407582938388635e-06,
"loss": 2.918,
"step": 157
},
{
"epoch": 0.18703758508434448,
"grad_norm": 5.375,
"learning_rate": 7.488151658767773e-06,
"loss": 2.895,
"step": 158
},
{
"epoch": 0.18822136726842262,
"grad_norm": 5.90625,
"learning_rate": 7.535545023696683e-06,
"loss": 2.8723,
"step": 159
},
{
"epoch": 0.18940514945250073,
"grad_norm": 6.625,
"learning_rate": 7.582938388625593e-06,
"loss": 2.7011,
"step": 160
},
{
"epoch": 0.19058893163657886,
"grad_norm": 5.6875,
"learning_rate": 7.630331753554503e-06,
"loss": 2.9097,
"step": 161
},
{
"epoch": 0.191772713820657,
"grad_norm": 5.625,
"learning_rate": 7.677725118483414e-06,
"loss": 3.1994,
"step": 162
},
{
"epoch": 0.19295649600473513,
"grad_norm": 5.65625,
"learning_rate": 7.725118483412322e-06,
"loss": 2.9914,
"step": 163
},
{
"epoch": 0.19414027818881327,
"grad_norm": 5.4375,
"learning_rate": 7.772511848341233e-06,
"loss": 2.8243,
"step": 164
},
{
"epoch": 0.19532406037289138,
"grad_norm": 5.71875,
"learning_rate": 7.819905213270143e-06,
"loss": 2.7478,
"step": 165
},
{
"epoch": 0.19650784255696951,
"grad_norm": 5.34375,
"learning_rate": 7.867298578199053e-06,
"loss": 2.8231,
"step": 166
},
{
"epoch": 0.19769162474104765,
"grad_norm": 5.09375,
"learning_rate": 7.914691943127962e-06,
"loss": 2.9692,
"step": 167
},
{
"epoch": 0.19887540692512579,
"grad_norm": 6.78125,
"learning_rate": 7.962085308056872e-06,
"loss": 2.9149,
"step": 168
},
{
"epoch": 0.2000591891092039,
"grad_norm": 5.5,
"learning_rate": 8.009478672985783e-06,
"loss": 3.0864,
"step": 169
},
{
"epoch": 0.20124297129328203,
"grad_norm": 5.34375,
"learning_rate": 8.056872037914693e-06,
"loss": 2.8221,
"step": 170
},
{
"epoch": 0.20242675347736017,
"grad_norm": 5.53125,
"learning_rate": 8.104265402843603e-06,
"loss": 2.8299,
"step": 171
},
{
"epoch": 0.2036105356614383,
"grad_norm": 5.25,
"learning_rate": 8.151658767772512e-06,
"loss": 2.5595,
"step": 172
},
{
"epoch": 0.20479431784551644,
"grad_norm": 6.0625,
"learning_rate": 8.199052132701422e-06,
"loss": 3.0452,
"step": 173
},
{
"epoch": 0.20597810002959455,
"grad_norm": 5.40625,
"learning_rate": 8.246445497630333e-06,
"loss": 2.6605,
"step": 174
},
{
"epoch": 0.20716188221367268,
"grad_norm": 6.03125,
"learning_rate": 8.293838862559243e-06,
"loss": 2.6988,
"step": 175
},
{
"epoch": 0.20834566439775082,
"grad_norm": 5.46875,
"learning_rate": 8.341232227488152e-06,
"loss": 2.8868,
"step": 176
},
{
"epoch": 0.20952944658182895,
"grad_norm": 5.53125,
"learning_rate": 8.388625592417062e-06,
"loss": 2.7421,
"step": 177
},
{
"epoch": 0.21071322876590706,
"grad_norm": 5.9375,
"learning_rate": 8.436018957345973e-06,
"loss": 2.9454,
"step": 178
},
{
"epoch": 0.2118970109499852,
"grad_norm": 5.59375,
"learning_rate": 8.483412322274883e-06,
"loss": 2.913,
"step": 179
},
{
"epoch": 0.21308079313406333,
"grad_norm": 5.71875,
"learning_rate": 8.530805687203793e-06,
"loss": 2.9006,
"step": 180
},
{
"epoch": 0.21426457531814147,
"grad_norm": 5.6875,
"learning_rate": 8.578199052132702e-06,
"loss": 2.8203,
"step": 181
},
{
"epoch": 0.21544835750221958,
"grad_norm": 6.21875,
"learning_rate": 8.625592417061612e-06,
"loss": 3.0179,
"step": 182
},
{
"epoch": 0.21663213968629771,
"grad_norm": 5.3125,
"learning_rate": 8.672985781990521e-06,
"loss": 2.9326,
"step": 183
},
{
"epoch": 0.21781592187037585,
"grad_norm": 5.71875,
"learning_rate": 8.720379146919431e-06,
"loss": 2.8996,
"step": 184
},
{
"epoch": 0.218999704054454,
"grad_norm": 4.875,
"learning_rate": 8.767772511848342e-06,
"loss": 2.7646,
"step": 185
},
{
"epoch": 0.22018348623853212,
"grad_norm": 5.96875,
"learning_rate": 8.815165876777252e-06,
"loss": 3.1929,
"step": 186
},
{
"epoch": 0.22136726842261023,
"grad_norm": 5.6875,
"learning_rate": 8.862559241706162e-06,
"loss": 2.8751,
"step": 187
},
{
"epoch": 0.22255105060668837,
"grad_norm": 5.75,
"learning_rate": 8.909952606635071e-06,
"loss": 3.2585,
"step": 188
},
{
"epoch": 0.2237348327907665,
"grad_norm": 6.625,
"learning_rate": 8.957345971563981e-06,
"loss": 3.6785,
"step": 189
},
{
"epoch": 0.22491861497484464,
"grad_norm": 5.0625,
"learning_rate": 9.004739336492892e-06,
"loss": 2.5239,
"step": 190
},
{
"epoch": 0.22610239715892275,
"grad_norm": 5.78125,
"learning_rate": 9.052132701421802e-06,
"loss": 2.8453,
"step": 191
},
{
"epoch": 0.22728617934300088,
"grad_norm": 5.375,
"learning_rate": 9.09952606635071e-06,
"loss": 2.9407,
"step": 192
},
{
"epoch": 0.22846996152707902,
"grad_norm": 5.40625,
"learning_rate": 9.146919431279621e-06,
"loss": 2.7989,
"step": 193
},
{
"epoch": 0.22965374371115715,
"grad_norm": 5.875,
"learning_rate": 9.194312796208532e-06,
"loss": 3.2391,
"step": 194
},
{
"epoch": 0.2308375258952353,
"grad_norm": 6.15625,
"learning_rate": 9.241706161137442e-06,
"loss": 2.8217,
"step": 195
},
{
"epoch": 0.2320213080793134,
"grad_norm": 5.375,
"learning_rate": 9.289099526066352e-06,
"loss": 3.0008,
"step": 196
},
{
"epoch": 0.23320509026339153,
"grad_norm": 4.75,
"learning_rate": 9.336492890995261e-06,
"loss": 2.6389,
"step": 197
},
{
"epoch": 0.23438887244746967,
"grad_norm": 5.03125,
"learning_rate": 9.383886255924171e-06,
"loss": 2.7761,
"step": 198
},
{
"epoch": 0.2355726546315478,
"grad_norm": 5.4375,
"learning_rate": 9.431279620853082e-06,
"loss": 2.6324,
"step": 199
},
{
"epoch": 0.23675643681562591,
"grad_norm": 5.6875,
"learning_rate": 9.478672985781992e-06,
"loss": 2.7339,
"step": 200
},
{
"epoch": 0.23794021899970405,
"grad_norm": 5.09375,
"learning_rate": 9.5260663507109e-06,
"loss": 3.0592,
"step": 201
},
{
"epoch": 0.2391240011837822,
"grad_norm": 6.21875,
"learning_rate": 9.573459715639811e-06,
"loss": 2.7575,
"step": 202
},
{
"epoch": 0.24030778336786032,
"grad_norm": 6.0625,
"learning_rate": 9.620853080568721e-06,
"loss": 3.4123,
"step": 203
},
{
"epoch": 0.24149156555193843,
"grad_norm": 5.3125,
"learning_rate": 9.668246445497632e-06,
"loss": 2.4718,
"step": 204
},
{
"epoch": 0.24267534773601657,
"grad_norm": 4.9375,
"learning_rate": 9.715639810426542e-06,
"loss": 2.8354,
"step": 205
},
{
"epoch": 0.2438591299200947,
"grad_norm": 4.8125,
"learning_rate": 9.76303317535545e-06,
"loss": 2.9036,
"step": 206
},
{
"epoch": 0.24504291210417284,
"grad_norm": 5.59375,
"learning_rate": 9.810426540284361e-06,
"loss": 2.9836,
"step": 207
},
{
"epoch": 0.24622669428825097,
"grad_norm": 5.59375,
"learning_rate": 9.85781990521327e-06,
"loss": 2.9898,
"step": 208
},
{
"epoch": 0.24741047647232908,
"grad_norm": 6.5,
"learning_rate": 9.905213270142182e-06,
"loss": 2.5649,
"step": 209
},
{
"epoch": 0.24859425865640722,
"grad_norm": 4.9375,
"learning_rate": 9.95260663507109e-06,
"loss": 2.5127,
"step": 210
},
{
"epoch": 0.24977804084048535,
"grad_norm": 4.75,
"learning_rate": 1e-05,
"loss": 2.7704,
"step": 211
},
{
"epoch": 0.2509618230245635,
"grad_norm": 4.9375,
"learning_rate": 1.004739336492891e-05,
"loss": 2.6617,
"step": 212
},
{
"epoch": 0.2521456052086416,
"grad_norm": 5.46875,
"learning_rate": 1.0094786729857822e-05,
"loss": 3.0098,
"step": 213
},
{
"epoch": 0.25332938739271976,
"grad_norm": 4.8125,
"learning_rate": 1.0142180094786732e-05,
"loss": 2.8491,
"step": 214
},
{
"epoch": 0.25451316957679787,
"grad_norm": 4.8125,
"learning_rate": 1.018957345971564e-05,
"loss": 2.9454,
"step": 215
},
{
"epoch": 0.255696951760876,
"grad_norm": 5.1875,
"learning_rate": 1.023696682464455e-05,
"loss": 2.9804,
"step": 216
},
{
"epoch": 0.25688073394495414,
"grad_norm": 5.21875,
"learning_rate": 1.0284360189573461e-05,
"loss": 2.5158,
"step": 217
},
{
"epoch": 0.25806451612903225,
"grad_norm": 4.90625,
"learning_rate": 1.033175355450237e-05,
"loss": 2.4959,
"step": 218
},
{
"epoch": 0.2592482983131104,
"grad_norm": 5.15625,
"learning_rate": 1.037914691943128e-05,
"loss": 2.76,
"step": 219
},
{
"epoch": 0.2604320804971885,
"grad_norm": 5.375,
"learning_rate": 1.0426540284360192e-05,
"loss": 3.1584,
"step": 220
},
{
"epoch": 0.26161586268126663,
"grad_norm": 5.46875,
"learning_rate": 1.0473933649289101e-05,
"loss": 2.9186,
"step": 221
},
{
"epoch": 0.2627996448653448,
"grad_norm": 5.0,
"learning_rate": 1.052132701421801e-05,
"loss": 2.549,
"step": 222
},
{
"epoch": 0.2639834270494229,
"grad_norm": 5.625,
"learning_rate": 1.056872037914692e-05,
"loss": 2.8233,
"step": 223
},
{
"epoch": 0.265167209233501,
"grad_norm": 5.71875,
"learning_rate": 1.061611374407583e-05,
"loss": 2.8856,
"step": 224
},
{
"epoch": 0.2663509914175792,
"grad_norm": 4.53125,
"learning_rate": 1.066350710900474e-05,
"loss": 2.695,
"step": 225
},
{
"epoch": 0.2675347736016573,
"grad_norm": 5.3125,
"learning_rate": 1.071090047393365e-05,
"loss": 2.4322,
"step": 226
},
{
"epoch": 0.26871855578573545,
"grad_norm": 5.46875,
"learning_rate": 1.075829383886256e-05,
"loss": 2.9831,
"step": 227
},
{
"epoch": 0.26990233796981355,
"grad_norm": 5.3125,
"learning_rate": 1.080568720379147e-05,
"loss": 2.7865,
"step": 228
},
{
"epoch": 0.27108612015389166,
"grad_norm": 5.3125,
"learning_rate": 1.085308056872038e-05,
"loss": 2.853,
"step": 229
},
{
"epoch": 0.2722699023379698,
"grad_norm": 5.25,
"learning_rate": 1.0900473933649289e-05,
"loss": 2.5822,
"step": 230
},
{
"epoch": 0.27345368452204794,
"grad_norm": 5.25,
"learning_rate": 1.0947867298578201e-05,
"loss": 2.8897,
"step": 231
},
{
"epoch": 0.2746374667061261,
"grad_norm": 4.375,
"learning_rate": 1.099526066350711e-05,
"loss": 2.3975,
"step": 232
},
{
"epoch": 0.2758212488902042,
"grad_norm": 5.03125,
"learning_rate": 1.104265402843602e-05,
"loss": 2.6928,
"step": 233
},
{
"epoch": 0.2770050310742823,
"grad_norm": 5.9375,
"learning_rate": 1.1090047393364929e-05,
"loss": 3.2237,
"step": 234
},
{
"epoch": 0.2781888132583605,
"grad_norm": 5.75,
"learning_rate": 1.1137440758293841e-05,
"loss": 3.2215,
"step": 235
},
{
"epoch": 0.2793725954424386,
"grad_norm": 4.46875,
"learning_rate": 1.118483412322275e-05,
"loss": 2.8132,
"step": 236
},
{
"epoch": 0.2805563776265167,
"grad_norm": 5.15625,
"learning_rate": 1.1232227488151658e-05,
"loss": 3.0152,
"step": 237
},
{
"epoch": 0.28174015981059486,
"grad_norm": 5.25,
"learning_rate": 1.127962085308057e-05,
"loss": 3.1626,
"step": 238
},
{
"epoch": 0.28292394199467297,
"grad_norm": 5.4375,
"learning_rate": 1.132701421800948e-05,
"loss": 2.6208,
"step": 239
},
{
"epoch": 0.28410772417875113,
"grad_norm": 5.28125,
"learning_rate": 1.137440758293839e-05,
"loss": 2.4686,
"step": 240
},
{
"epoch": 0.28529150636282924,
"grad_norm": 4.96875,
"learning_rate": 1.1421800947867298e-05,
"loss": 3.0794,
"step": 241
},
{
"epoch": 0.28647528854690735,
"grad_norm": 4.78125,
"learning_rate": 1.146919431279621e-05,
"loss": 2.5172,
"step": 242
},
{
"epoch": 0.2876590707309855,
"grad_norm": 4.84375,
"learning_rate": 1.1516587677725119e-05,
"loss": 2.6685,
"step": 243
},
{
"epoch": 0.2888428529150636,
"grad_norm": 4.84375,
"learning_rate": 1.1563981042654029e-05,
"loss": 2.8994,
"step": 244
},
{
"epoch": 0.2900266350991418,
"grad_norm": 4.8125,
"learning_rate": 1.1611374407582941e-05,
"loss": 3.1005,
"step": 245
},
{
"epoch": 0.2912104172832199,
"grad_norm": 5.0625,
"learning_rate": 1.165876777251185e-05,
"loss": 2.8181,
"step": 246
},
{
"epoch": 0.292394199467298,
"grad_norm": 5.09375,
"learning_rate": 1.1706161137440758e-05,
"loss": 2.7756,
"step": 247
},
{
"epoch": 0.29357798165137616,
"grad_norm": 4.5,
"learning_rate": 1.1753554502369669e-05,
"loss": 2.5114,
"step": 248
},
{
"epoch": 0.29476176383545427,
"grad_norm": 5.53125,
"learning_rate": 1.180094786729858e-05,
"loss": 2.8279,
"step": 249
},
{
"epoch": 0.2959455460195324,
"grad_norm": 5.03125,
"learning_rate": 1.184834123222749e-05,
"loss": 2.6553,
"step": 250
},
{
"epoch": 0.29712932820361054,
"grad_norm": 4.8125,
"learning_rate": 1.1895734597156398e-05,
"loss": 2.6956,
"step": 251
},
{
"epoch": 0.29831311038768865,
"grad_norm": 5.125,
"learning_rate": 1.1943127962085309e-05,
"loss": 2.7031,
"step": 252
},
{
"epoch": 0.2994968925717668,
"grad_norm": 4.65625,
"learning_rate": 1.1990521327014219e-05,
"loss": 2.8315,
"step": 253
},
{
"epoch": 0.3006806747558449,
"grad_norm": 5.28125,
"learning_rate": 1.203791469194313e-05,
"loss": 2.8987,
"step": 254
},
{
"epoch": 0.30186445693992303,
"grad_norm": 4.46875,
"learning_rate": 1.2085308056872038e-05,
"loss": 2.7542,
"step": 255
},
{
"epoch": 0.3030482391240012,
"grad_norm": 4.625,
"learning_rate": 1.213270142180095e-05,
"loss": 2.8007,
"step": 256
},
{
"epoch": 0.3042320213080793,
"grad_norm": 5.5625,
"learning_rate": 1.2180094786729859e-05,
"loss": 3.22,
"step": 257
},
{
"epoch": 0.30541580349215747,
"grad_norm": 5.15625,
"learning_rate": 1.2227488151658769e-05,
"loss": 2.4949,
"step": 258
},
{
"epoch": 0.3065995856762356,
"grad_norm": 6.3125,
"learning_rate": 1.2274881516587678e-05,
"loss": 3.0903,
"step": 259
},
{
"epoch": 0.3077833678603137,
"grad_norm": 4.71875,
"learning_rate": 1.232227488151659e-05,
"loss": 3.0174,
"step": 260
},
{
"epoch": 0.30896715004439185,
"grad_norm": 5.3125,
"learning_rate": 1.2369668246445498e-05,
"loss": 2.7283,
"step": 261
},
{
"epoch": 0.31015093222846996,
"grad_norm": 5.71875,
"learning_rate": 1.2417061611374409e-05,
"loss": 3.1703,
"step": 262
},
{
"epoch": 0.31133471441254806,
"grad_norm": 5.53125,
"learning_rate": 1.2464454976303319e-05,
"loss": 2.4287,
"step": 263
},
{
"epoch": 0.3125184965966262,
"grad_norm": 4.9375,
"learning_rate": 1.251184834123223e-05,
"loss": 2.8703,
"step": 264
},
{
"epoch": 0.31370227878070434,
"grad_norm": 4.40625,
"learning_rate": 1.2559241706161138e-05,
"loss": 2.5718,
"step": 265
},
{
"epoch": 0.3148860609647825,
"grad_norm": 4.21875,
"learning_rate": 1.2606635071090047e-05,
"loss": 2.4072,
"step": 266
},
{
"epoch": 0.3160698431488606,
"grad_norm": 4.4375,
"learning_rate": 1.2654028436018959e-05,
"loss": 3.0766,
"step": 267
},
{
"epoch": 0.3172536253329387,
"grad_norm": 4.3125,
"learning_rate": 1.270142180094787e-05,
"loss": 2.9474,
"step": 268
},
{
"epoch": 0.3184374075170169,
"grad_norm": 6.09375,
"learning_rate": 1.2748815165876778e-05,
"loss": 2.851,
"step": 269
},
{
"epoch": 0.319621189701095,
"grad_norm": 5.53125,
"learning_rate": 1.2796208530805687e-05,
"loss": 3.2042,
"step": 270
},
{
"epoch": 0.32080497188517315,
"grad_norm": 5.0,
"learning_rate": 1.2843601895734599e-05,
"loss": 3.0455,
"step": 271
},
{
"epoch": 0.32198875406925126,
"grad_norm": 4.71875,
"learning_rate": 1.2890995260663507e-05,
"loss": 3.0739,
"step": 272
},
{
"epoch": 0.32317253625332937,
"grad_norm": 5.21875,
"learning_rate": 1.2938388625592418e-05,
"loss": 2.7899,
"step": 273
},
{
"epoch": 0.32435631843740753,
"grad_norm": 5.09375,
"learning_rate": 1.298578199052133e-05,
"loss": 2.5534,
"step": 274
},
{
"epoch": 0.32554010062148564,
"grad_norm": 4.96875,
"learning_rate": 1.3033175355450238e-05,
"loss": 3.0155,
"step": 275
},
{
"epoch": 0.3267238828055638,
"grad_norm": 4.8125,
"learning_rate": 1.3080568720379147e-05,
"loss": 2.2551,
"step": 276
},
{
"epoch": 0.3279076649896419,
"grad_norm": 4.84375,
"learning_rate": 1.3127962085308057e-05,
"loss": 2.9656,
"step": 277
},
{
"epoch": 0.32909144717372,
"grad_norm": 5.25,
"learning_rate": 1.3175355450236968e-05,
"loss": 2.714,
"step": 278
},
{
"epoch": 0.3302752293577982,
"grad_norm": 5.40625,
"learning_rate": 1.3222748815165878e-05,
"loss": 3.3093,
"step": 279
},
{
"epoch": 0.3314590115418763,
"grad_norm": 4.78125,
"learning_rate": 1.3270142180094787e-05,
"loss": 2.8451,
"step": 280
},
{
"epoch": 0.3326427937259544,
"grad_norm": 5.59375,
"learning_rate": 1.3317535545023699e-05,
"loss": 2.639,
"step": 281
},
{
"epoch": 0.33382657591003256,
"grad_norm": 5.1875,
"learning_rate": 1.3364928909952607e-05,
"loss": 2.4743,
"step": 282
},
{
"epoch": 0.33501035809411067,
"grad_norm": 4.71875,
"learning_rate": 1.3412322274881518e-05,
"loss": 2.6672,
"step": 283
},
{
"epoch": 0.33619414027818884,
"grad_norm": 6.84375,
"learning_rate": 1.3459715639810426e-05,
"loss": 2.0719,
"step": 284
},
{
"epoch": 0.33737792246226694,
"grad_norm": 4.8125,
"learning_rate": 1.3507109004739339e-05,
"loss": 2.91,
"step": 285
},
{
"epoch": 0.33856170464634505,
"grad_norm": 5.15625,
"learning_rate": 1.3554502369668247e-05,
"loss": 2.9267,
"step": 286
},
{
"epoch": 0.3397454868304232,
"grad_norm": 5.4375,
"learning_rate": 1.3601895734597158e-05,
"loss": 2.8538,
"step": 287
},
{
"epoch": 0.3409292690145013,
"grad_norm": 4.8125,
"learning_rate": 1.3649289099526068e-05,
"loss": 2.255,
"step": 288
},
{
"epoch": 0.3421130511985795,
"grad_norm": 4.9375,
"learning_rate": 1.3696682464454978e-05,
"loss": 2.8949,
"step": 289
},
{
"epoch": 0.3432968333826576,
"grad_norm": 4.75,
"learning_rate": 1.3744075829383887e-05,
"loss": 2.7718,
"step": 290
},
{
"epoch": 0.3444806155667357,
"grad_norm": 4.4375,
"learning_rate": 1.3791469194312797e-05,
"loss": 2.879,
"step": 291
},
{
"epoch": 0.34566439775081387,
"grad_norm": 5.28125,
"learning_rate": 1.3838862559241708e-05,
"loss": 2.9023,
"step": 292
},
{
"epoch": 0.346848179934892,
"grad_norm": 4.65625,
"learning_rate": 1.3886255924170618e-05,
"loss": 2.5042,
"step": 293
},
{
"epoch": 0.3480319621189701,
"grad_norm": 4.8125,
"learning_rate": 1.3933649289099527e-05,
"loss": 2.7081,
"step": 294
},
{
"epoch": 0.34921574430304825,
"grad_norm": 4.53125,
"learning_rate": 1.3981042654028435e-05,
"loss": 2.6192,
"step": 295
},
{
"epoch": 0.35039952648712636,
"grad_norm": 4.75,
"learning_rate": 1.4028436018957347e-05,
"loss": 2.6729,
"step": 296
},
{
"epoch": 0.3515833086712045,
"grad_norm": 4.75,
"learning_rate": 1.4075829383886258e-05,
"loss": 2.7472,
"step": 297
},
{
"epoch": 0.35276709085528263,
"grad_norm": 4.625,
"learning_rate": 1.4123222748815166e-05,
"loss": 2.6944,
"step": 298
},
{
"epoch": 0.35395087303936074,
"grad_norm": 4.875,
"learning_rate": 1.4170616113744078e-05,
"loss": 2.8301,
"step": 299
},
{
"epoch": 0.3551346552234389,
"grad_norm": 4.75,
"learning_rate": 1.4218009478672987e-05,
"loss": 2.5333,
"step": 300
},
{
"epoch": 0.356318437407517,
"grad_norm": 4.625,
"learning_rate": 1.4265402843601896e-05,
"loss": 2.6664,
"step": 301
},
{
"epoch": 0.35750221959159517,
"grad_norm": 4.875,
"learning_rate": 1.4312796208530806e-05,
"loss": 2.6661,
"step": 302
},
{
"epoch": 0.3586860017756733,
"grad_norm": 5.15625,
"learning_rate": 1.4360189573459718e-05,
"loss": 2.8139,
"step": 303
},
{
"epoch": 0.3598697839597514,
"grad_norm": 4.84375,
"learning_rate": 1.4407582938388627e-05,
"loss": 2.8003,
"step": 304
},
{
"epoch": 0.36105356614382955,
"grad_norm": 5.25,
"learning_rate": 1.4454976303317535e-05,
"loss": 2.7978,
"step": 305
},
{
"epoch": 0.36223734832790766,
"grad_norm": 5.75,
"learning_rate": 1.4502369668246448e-05,
"loss": 3.0917,
"step": 306
},
{
"epoch": 0.36342113051198577,
"grad_norm": 4.875,
"learning_rate": 1.4549763033175356e-05,
"loss": 2.7671,
"step": 307
},
{
"epoch": 0.36460491269606393,
"grad_norm": 4.8125,
"learning_rate": 1.4597156398104267e-05,
"loss": 2.5533,
"step": 308
},
{
"epoch": 0.36578869488014204,
"grad_norm": 5.09375,
"learning_rate": 1.4644549763033175e-05,
"loss": 2.6768,
"step": 309
},
{
"epoch": 0.3669724770642202,
"grad_norm": 5.4375,
"learning_rate": 1.4691943127962087e-05,
"loss": 2.8195,
"step": 310
},
{
"epoch": 0.3681562592482983,
"grad_norm": 4.46875,
"learning_rate": 1.4739336492890996e-05,
"loss": 2.5481,
"step": 311
},
{
"epoch": 0.3693400414323764,
"grad_norm": 5.125,
"learning_rate": 1.4786729857819906e-05,
"loss": 2.8285,
"step": 312
},
{
"epoch": 0.3705238236164546,
"grad_norm": 5.0625,
"learning_rate": 1.4834123222748817e-05,
"loss": 2.6925,
"step": 313
},
{
"epoch": 0.3717076058005327,
"grad_norm": 5.34375,
"learning_rate": 1.4881516587677727e-05,
"loss": 3.0766,
"step": 314
},
{
"epoch": 0.37289138798461086,
"grad_norm": 5.09375,
"learning_rate": 1.4928909952606636e-05,
"loss": 3.1,
"step": 315
},
{
"epoch": 0.37407517016868896,
"grad_norm": 4.90625,
"learning_rate": 1.4976303317535546e-05,
"loss": 2.9711,
"step": 316
},
{
"epoch": 0.3752589523527671,
"grad_norm": 5.4375,
"learning_rate": 1.5023696682464456e-05,
"loss": 2.8579,
"step": 317
},
{
"epoch": 0.37644273453684524,
"grad_norm": 4.5,
"learning_rate": 1.5071090047393367e-05,
"loss": 2.7418,
"step": 318
},
{
"epoch": 0.37762651672092334,
"grad_norm": 4.625,
"learning_rate": 1.5118483412322275e-05,
"loss": 2.4723,
"step": 319
},
{
"epoch": 0.37881029890500145,
"grad_norm": 4.96875,
"learning_rate": 1.5165876777251186e-05,
"loss": 2.635,
"step": 320
},
{
"epoch": 0.3799940810890796,
"grad_norm": 4.78125,
"learning_rate": 1.5213270142180096e-05,
"loss": 3.0549,
"step": 321
},
{
"epoch": 0.3811778632731577,
"grad_norm": 4.75,
"learning_rate": 1.5260663507109007e-05,
"loss": 2.9297,
"step": 322
},
{
"epoch": 0.3823616454572359,
"grad_norm": 4.71875,
"learning_rate": 1.5308056872037915e-05,
"loss": 2.708,
"step": 323
},
{
"epoch": 0.383545427641314,
"grad_norm": 4.65625,
"learning_rate": 1.5355450236966827e-05,
"loss": 2.77,
"step": 324
},
{
"epoch": 0.3847292098253921,
"grad_norm": 5.0625,
"learning_rate": 1.5402843601895736e-05,
"loss": 2.819,
"step": 325
},
{
"epoch": 0.38591299200947027,
"grad_norm": 4.875,
"learning_rate": 1.5450236966824645e-05,
"loss": 2.5151,
"step": 326
},
{
"epoch": 0.3870967741935484,
"grad_norm": 4.78125,
"learning_rate": 1.5497630331753553e-05,
"loss": 2.5492,
"step": 327
},
{
"epoch": 0.38828055637762654,
"grad_norm": 5.21875,
"learning_rate": 1.5545023696682465e-05,
"loss": 3.1629,
"step": 328
},
{
"epoch": 0.38946433856170465,
"grad_norm": 5.21875,
"learning_rate": 1.5592417061611377e-05,
"loss": 2.7724,
"step": 329
},
{
"epoch": 0.39064812074578276,
"grad_norm": 5.1875,
"learning_rate": 1.5639810426540286e-05,
"loss": 2.7371,
"step": 330
},
{
"epoch": 0.3918319029298609,
"grad_norm": 5.0,
"learning_rate": 1.5687203791469198e-05,
"loss": 2.5081,
"step": 331
},
{
"epoch": 0.39301568511393903,
"grad_norm": 4.9375,
"learning_rate": 1.5734597156398107e-05,
"loss": 2.8753,
"step": 332
},
{
"epoch": 0.3941994672980172,
"grad_norm": 5.21875,
"learning_rate": 1.5781990521327015e-05,
"loss": 2.9915,
"step": 333
},
{
"epoch": 0.3953832494820953,
"grad_norm": 4.53125,
"learning_rate": 1.5829383886255924e-05,
"loss": 2.6159,
"step": 334
},
{
"epoch": 0.3965670316661734,
"grad_norm": 4.84375,
"learning_rate": 1.5876777251184836e-05,
"loss": 2.6686,
"step": 335
},
{
"epoch": 0.39775081385025157,
"grad_norm": 4.375,
"learning_rate": 1.5924170616113745e-05,
"loss": 2.7223,
"step": 336
},
{
"epoch": 0.3989345960343297,
"grad_norm": 5.8125,
"learning_rate": 1.5971563981042653e-05,
"loss": 3.0036,
"step": 337
},
{
"epoch": 0.4001183782184078,
"grad_norm": 4.96875,
"learning_rate": 1.6018957345971565e-05,
"loss": 3.0889,
"step": 338
},
{
"epoch": 0.40130216040248595,
"grad_norm": 4.75,
"learning_rate": 1.6066350710900474e-05,
"loss": 2.4813,
"step": 339
},
{
"epoch": 0.40248594258656406,
"grad_norm": 5.0625,
"learning_rate": 1.6113744075829386e-05,
"loss": 2.5486,
"step": 340
},
{
"epoch": 0.4036697247706422,
"grad_norm": 4.75,
"learning_rate": 1.6161137440758295e-05,
"loss": 2.6352,
"step": 341
},
{
"epoch": 0.40485350695472033,
"grad_norm": 4.65625,
"learning_rate": 1.6208530805687207e-05,
"loss": 2.944,
"step": 342
},
{
"epoch": 0.40603728913879844,
"grad_norm": 4.53125,
"learning_rate": 1.6255924170616116e-05,
"loss": 2.7707,
"step": 343
},
{
"epoch": 0.4072210713228766,
"grad_norm": 4.75,
"learning_rate": 1.6303317535545024e-05,
"loss": 2.5338,
"step": 344
},
{
"epoch": 0.4084048535069547,
"grad_norm": 4.875,
"learning_rate": 1.6350710900473933e-05,
"loss": 2.764,
"step": 345
},
{
"epoch": 0.4095886356910329,
"grad_norm": 5.34375,
"learning_rate": 1.6398104265402845e-05,
"loss": 2.8279,
"step": 346
},
{
"epoch": 0.410772417875111,
"grad_norm": 5.125,
"learning_rate": 1.6445497630331754e-05,
"loss": 2.8334,
"step": 347
},
{
"epoch": 0.4119562000591891,
"grad_norm": 4.5625,
"learning_rate": 1.6492890995260666e-05,
"loss": 2.807,
"step": 348
},
{
"epoch": 0.41313998224326726,
"grad_norm": 4.6875,
"learning_rate": 1.6540284360189574e-05,
"loss": 2.7753,
"step": 349
},
{
"epoch": 0.41432376442734536,
"grad_norm": 4.5625,
"learning_rate": 1.6587677725118486e-05,
"loss": 2.7581,
"step": 350
},
{
"epoch": 0.4155075466114235,
"grad_norm": 5.3125,
"learning_rate": 1.6635071090047395e-05,
"loss": 2.4765,
"step": 351
},
{
"epoch": 0.41669132879550164,
"grad_norm": 4.78125,
"learning_rate": 1.6682464454976304e-05,
"loss": 2.5752,
"step": 352
},
{
"epoch": 0.41787511097957974,
"grad_norm": 4.6875,
"learning_rate": 1.6729857819905216e-05,
"loss": 2.8467,
"step": 353
},
{
"epoch": 0.4190588931636579,
"grad_norm": 5.03125,
"learning_rate": 1.6777251184834124e-05,
"loss": 2.4303,
"step": 354
},
{
"epoch": 0.420242675347736,
"grad_norm": 4.65625,
"learning_rate": 1.6824644549763033e-05,
"loss": 2.7506,
"step": 355
},
{
"epoch": 0.4214264575318141,
"grad_norm": 4.71875,
"learning_rate": 1.6872037914691945e-05,
"loss": 2.6954,
"step": 356
},
{
"epoch": 0.4226102397158923,
"grad_norm": 5.0625,
"learning_rate": 1.6919431279620854e-05,
"loss": 2.6394,
"step": 357
},
{
"epoch": 0.4237940218999704,
"grad_norm": 4.5,
"learning_rate": 1.6966824644549766e-05,
"loss": 2.6936,
"step": 358
},
{
"epoch": 0.42497780408404856,
"grad_norm": 5.25,
"learning_rate": 1.7014218009478674e-05,
"loss": 2.8144,
"step": 359
},
{
"epoch": 0.42616158626812667,
"grad_norm": 5.09375,
"learning_rate": 1.7061611374407587e-05,
"loss": 2.9599,
"step": 360
},
{
"epoch": 0.4273453684522048,
"grad_norm": 4.8125,
"learning_rate": 1.7109004739336495e-05,
"loss": 2.6884,
"step": 361
},
{
"epoch": 0.42852915063628294,
"grad_norm": 5.46875,
"learning_rate": 1.7156398104265404e-05,
"loss": 2.4406,
"step": 362
},
{
"epoch": 0.42971293282036105,
"grad_norm": 4.875,
"learning_rate": 1.7203791469194316e-05,
"loss": 2.8712,
"step": 363
},
{
"epoch": 0.43089671500443916,
"grad_norm": 4.59375,
"learning_rate": 1.7251184834123225e-05,
"loss": 2.6344,
"step": 364
},
{
"epoch": 0.4320804971885173,
"grad_norm": 5.0625,
"learning_rate": 1.7298578199052133e-05,
"loss": 2.9339,
"step": 365
},
{
"epoch": 0.43326427937259543,
"grad_norm": 5.6875,
"learning_rate": 1.7345971563981042e-05,
"loss": 3.0146,
"step": 366
},
{
"epoch": 0.4344480615566736,
"grad_norm": 5.0625,
"learning_rate": 1.7393364928909954e-05,
"loss": 2.8382,
"step": 367
},
{
"epoch": 0.4356318437407517,
"grad_norm": 5.15625,
"learning_rate": 1.7440758293838863e-05,
"loss": 3.0245,
"step": 368
},
{
"epoch": 0.4368156259248298,
"grad_norm": 4.875,
"learning_rate": 1.7488151658767775e-05,
"loss": 2.8044,
"step": 369
},
{
"epoch": 0.437999408108908,
"grad_norm": 4.84375,
"learning_rate": 1.7535545023696683e-05,
"loss": 2.9253,
"step": 370
},
{
"epoch": 0.4391831902929861,
"grad_norm": 4.84375,
"learning_rate": 1.7582938388625595e-05,
"loss": 3.1525,
"step": 371
},
{
"epoch": 0.44036697247706424,
"grad_norm": 4.875,
"learning_rate": 1.7630331753554504e-05,
"loss": 2.5946,
"step": 372
},
{
"epoch": 0.44155075466114235,
"grad_norm": 5.28125,
"learning_rate": 1.7677725118483413e-05,
"loss": 2.5128,
"step": 373
},
{
"epoch": 0.44273453684522046,
"grad_norm": 4.5625,
"learning_rate": 1.7725118483412325e-05,
"loss": 3.1451,
"step": 374
},
{
"epoch": 0.4439183190292986,
"grad_norm": 4.6875,
"learning_rate": 1.7772511848341233e-05,
"loss": 2.855,
"step": 375
},
{
"epoch": 0.44510210121337673,
"grad_norm": 4.9375,
"learning_rate": 1.7819905213270142e-05,
"loss": 2.9335,
"step": 376
},
{
"epoch": 0.44628588339745484,
"grad_norm": 4.65625,
"learning_rate": 1.7867298578199054e-05,
"loss": 2.7664,
"step": 377
},
{
"epoch": 0.447469665581533,
"grad_norm": 4.75,
"learning_rate": 1.7914691943127963e-05,
"loss": 2.309,
"step": 378
},
{
"epoch": 0.4486534477656111,
"grad_norm": 4.40625,
"learning_rate": 1.7962085308056875e-05,
"loss": 3.0141,
"step": 379
},
{
"epoch": 0.4498372299496893,
"grad_norm": 4.96875,
"learning_rate": 1.8009478672985784e-05,
"loss": 2.3059,
"step": 380
},
{
"epoch": 0.4510210121337674,
"grad_norm": 4.90625,
"learning_rate": 1.8056872037914696e-05,
"loss": 3.252,
"step": 381
},
{
"epoch": 0.4522047943178455,
"grad_norm": 5.34375,
"learning_rate": 1.8104265402843604e-05,
"loss": 3.0884,
"step": 382
},
{
"epoch": 0.45338857650192366,
"grad_norm": 4.5625,
"learning_rate": 1.8151658767772513e-05,
"loss": 2.4152,
"step": 383
},
{
"epoch": 0.45457235868600177,
"grad_norm": 4.6875,
"learning_rate": 1.819905213270142e-05,
"loss": 2.4958,
"step": 384
},
{
"epoch": 0.45575614087007993,
"grad_norm": 4.375,
"learning_rate": 1.8246445497630334e-05,
"loss": 2.7179,
"step": 385
},
{
"epoch": 0.45693992305415804,
"grad_norm": 4.40625,
"learning_rate": 1.8293838862559242e-05,
"loss": 2.9143,
"step": 386
},
{
"epoch": 0.45812370523823615,
"grad_norm": 4.5,
"learning_rate": 1.8341232227488154e-05,
"loss": 2.4235,
"step": 387
},
{
"epoch": 0.4593074874223143,
"grad_norm": 4.78125,
"learning_rate": 1.8388625592417063e-05,
"loss": 3.1037,
"step": 388
},
{
"epoch": 0.4604912696063924,
"grad_norm": 4.46875,
"learning_rate": 1.8436018957345975e-05,
"loss": 2.7058,
"step": 389
},
{
"epoch": 0.4616750517904706,
"grad_norm": 4.53125,
"learning_rate": 1.8483412322274884e-05,
"loss": 2.7252,
"step": 390
},
{
"epoch": 0.4628588339745487,
"grad_norm": 4.84375,
"learning_rate": 1.8530805687203792e-05,
"loss": 3.0053,
"step": 391
},
{
"epoch": 0.4640426161586268,
"grad_norm": 4.75,
"learning_rate": 1.8578199052132704e-05,
"loss": 2.5684,
"step": 392
},
{
"epoch": 0.46522639834270496,
"grad_norm": 4.625,
"learning_rate": 1.8625592417061613e-05,
"loss": 2.5282,
"step": 393
},
{
"epoch": 0.46641018052678307,
"grad_norm": 4.9375,
"learning_rate": 1.8672985781990522e-05,
"loss": 2.4713,
"step": 394
},
{
"epoch": 0.4675939627108612,
"grad_norm": 4.84375,
"learning_rate": 1.872037914691943e-05,
"loss": 2.4372,
"step": 395
},
{
"epoch": 0.46877774489493934,
"grad_norm": 4.4375,
"learning_rate": 1.8767772511848342e-05,
"loss": 2.9421,
"step": 396
},
{
"epoch": 0.46996152707901745,
"grad_norm": 5.4375,
"learning_rate": 1.881516587677725e-05,
"loss": 3.1285,
"step": 397
},
{
"epoch": 0.4711453092630956,
"grad_norm": 4.28125,
"learning_rate": 1.8862559241706163e-05,
"loss": 2.2699,
"step": 398
},
{
"epoch": 0.4723290914471737,
"grad_norm": 4.46875,
"learning_rate": 1.8909952606635075e-05,
"loss": 2.2156,
"step": 399
},
{
"epoch": 0.47351287363125183,
"grad_norm": 5.25,
"learning_rate": 1.8957345971563984e-05,
"loss": 3.0645,
"step": 400
},
{
"epoch": 0.47469665581533,
"grad_norm": 4.4375,
"learning_rate": 1.9004739336492893e-05,
"loss": 2.972,
"step": 401
},
{
"epoch": 0.4758804379994081,
"grad_norm": 4.6875,
"learning_rate": 1.90521327014218e-05,
"loss": 2.6146,
"step": 402
},
{
"epoch": 0.47706422018348627,
"grad_norm": 4.6875,
"learning_rate": 1.9099526066350713e-05,
"loss": 3.0106,
"step": 403
},
{
"epoch": 0.4782480023675644,
"grad_norm": 4.875,
"learning_rate": 1.9146919431279622e-05,
"loss": 2.7097,
"step": 404
},
{
"epoch": 0.4794317845516425,
"grad_norm": 4.4375,
"learning_rate": 1.919431279620853e-05,
"loss": 2.8993,
"step": 405
},
{
"epoch": 0.48061556673572065,
"grad_norm": 4.59375,
"learning_rate": 1.9241706161137443e-05,
"loss": 2.6624,
"step": 406
},
{
"epoch": 0.48179934891979875,
"grad_norm": 5.1875,
"learning_rate": 1.928909952606635e-05,
"loss": 2.8009,
"step": 407
},
{
"epoch": 0.48298313110387686,
"grad_norm": 4.78125,
"learning_rate": 1.9336492890995263e-05,
"loss": 3.189,
"step": 408
},
{
"epoch": 0.484166913287955,
"grad_norm": 4.40625,
"learning_rate": 1.9383886255924172e-05,
"loss": 2.7469,
"step": 409
},
{
"epoch": 0.48535069547203313,
"grad_norm": 4.875,
"learning_rate": 1.9431279620853084e-05,
"loss": 2.4736,
"step": 410
},
{
"epoch": 0.4865344776561113,
"grad_norm": 4.6875,
"learning_rate": 1.9478672985781993e-05,
"loss": 2.8223,
"step": 411
},
{
"epoch": 0.4877182598401894,
"grad_norm": 4.84375,
"learning_rate": 1.95260663507109e-05,
"loss": 2.9889,
"step": 412
},
{
"epoch": 0.4889020420242675,
"grad_norm": 4.28125,
"learning_rate": 1.957345971563981e-05,
"loss": 2.9711,
"step": 413
},
{
"epoch": 0.4900858242083457,
"grad_norm": 4.875,
"learning_rate": 1.9620853080568722e-05,
"loss": 2.7299,
"step": 414
},
{
"epoch": 0.4912696063924238,
"grad_norm": 4.75,
"learning_rate": 1.966824644549763e-05,
"loss": 2.7704,
"step": 415
},
{
"epoch": 0.49245338857650195,
"grad_norm": 4.84375,
"learning_rate": 1.971563981042654e-05,
"loss": 3.0171,
"step": 416
},
{
"epoch": 0.49363717076058006,
"grad_norm": 4.34375,
"learning_rate": 1.976303317535545e-05,
"loss": 2.7554,
"step": 417
},
{
"epoch": 0.49482095294465817,
"grad_norm": 4.46875,
"learning_rate": 1.9810426540284364e-05,
"loss": 2.7022,
"step": 418
},
{
"epoch": 0.49600473512873633,
"grad_norm": 4.21875,
"learning_rate": 1.9857819905213272e-05,
"loss": 2.7364,
"step": 419
},
{
"epoch": 0.49718851731281444,
"grad_norm": 4.46875,
"learning_rate": 1.990521327014218e-05,
"loss": 2.5352,
"step": 420
},
{
"epoch": 0.49837229949689255,
"grad_norm": 4.65625,
"learning_rate": 1.9952606635071093e-05,
"loss": 2.6267,
"step": 421
},
{
"epoch": 0.4995560816809707,
"grad_norm": 4.59375,
"learning_rate": 2e-05,
"loss": 2.9234,
"step": 422
},
{
"epoch": 0.5007398638650489,
"grad_norm": 5.34375,
"learning_rate": 1.9999996578946986e-05,
"loss": 2.8771,
"step": 423
},
{
"epoch": 0.501923646049127,
"grad_norm": 4.59375,
"learning_rate": 1.9999986315790288e-05,
"loss": 2.5393,
"step": 424
},
{
"epoch": 0.5031074282332051,
"grad_norm": 4.46875,
"learning_rate": 1.9999969210536924e-05,
"loss": 2.4292,
"step": 425
},
{
"epoch": 0.5042912104172832,
"grad_norm": 4.5625,
"learning_rate": 1.99999452631986e-05,
"loss": 2.9455,
"step": 426
},
{
"epoch": 0.5054749926013613,
"grad_norm": 5.4375,
"learning_rate": 1.9999914473791704e-05,
"loss": 2.8429,
"step": 427
},
{
"epoch": 0.5066587747854395,
"grad_norm": 4.90625,
"learning_rate": 1.9999876842337294e-05,
"loss": 2.9468,
"step": 428
},
{
"epoch": 0.5078425569695176,
"grad_norm": 5.25,
"learning_rate": 1.9999832368861126e-05,
"loss": 2.9273,
"step": 429
},
{
"epoch": 0.5090263391535957,
"grad_norm": 5.15625,
"learning_rate": 1.9999781053393626e-05,
"loss": 3.2937,
"step": 430
},
{
"epoch": 0.5102101213376738,
"grad_norm": 4.9375,
"learning_rate": 1.9999722895969904e-05,
"loss": 2.6501,
"step": 431
},
{
"epoch": 0.511393903521752,
"grad_norm": 4.34375,
"learning_rate": 1.9999657896629752e-05,
"loss": 2.7118,
"step": 432
},
{
"epoch": 0.5125776857058302,
"grad_norm": 4.84375,
"learning_rate": 1.9999586055417645e-05,
"loss": 2.617,
"step": 433
},
{
"epoch": 0.5137614678899083,
"grad_norm": 4.1875,
"learning_rate": 1.9999507372382738e-05,
"loss": 2.8919,
"step": 434
},
{
"epoch": 0.5149452500739864,
"grad_norm": 4.8125,
"learning_rate": 1.9999421847578864e-05,
"loss": 2.7508,
"step": 435
},
{
"epoch": 0.5161290322580645,
"grad_norm": 4.59375,
"learning_rate": 1.999932948106454e-05,
"loss": 2.5654,
"step": 436
},
{
"epoch": 0.5173128144421426,
"grad_norm": 4.78125,
"learning_rate": 1.999923027290297e-05,
"loss": 2.8408,
"step": 437
},
{
"epoch": 0.5184965966262208,
"grad_norm": 4.5,
"learning_rate": 1.9999124223162023e-05,
"loss": 2.8589,
"step": 438
},
{
"epoch": 0.5196803788102989,
"grad_norm": 4.375,
"learning_rate": 1.9999011331914264e-05,
"loss": 2.866,
"step": 439
},
{
"epoch": 0.520864160994377,
"grad_norm": 4.71875,
"learning_rate": 1.999889159923694e-05,
"loss": 2.6634,
"step": 440
},
{
"epoch": 0.5220479431784552,
"grad_norm": 4.40625,
"learning_rate": 1.999876502521197e-05,
"loss": 3.1033,
"step": 441
},
{
"epoch": 0.5232317253625333,
"grad_norm": 4.34375,
"learning_rate": 1.999863160992595e-05,
"loss": 2.5757,
"step": 442
},
{
"epoch": 0.5244155075466114,
"grad_norm": 4.875,
"learning_rate": 1.9998491353470176e-05,
"loss": 2.9225,
"step": 443
},
{
"epoch": 0.5255992897306896,
"grad_norm": 4.46875,
"learning_rate": 1.9998344255940602e-05,
"loss": 2.9235,
"step": 444
},
{
"epoch": 0.5267830719147677,
"grad_norm": 4.90625,
"learning_rate": 1.9998190317437883e-05,
"loss": 2.7662,
"step": 445
},
{
"epoch": 0.5279668540988458,
"grad_norm": 4.5,
"learning_rate": 1.999802953806734e-05,
"loss": 3.0117,
"step": 446
},
{
"epoch": 0.5291506362829239,
"grad_norm": 4.34375,
"learning_rate": 1.999786191793898e-05,
"loss": 2.8025,
"step": 447
},
{
"epoch": 0.530334418467002,
"grad_norm": 4.3125,
"learning_rate": 1.9997687457167495e-05,
"loss": 2.7641,
"step": 448
},
{
"epoch": 0.5315182006510802,
"grad_norm": 4.9375,
"learning_rate": 1.9997506155872246e-05,
"loss": 2.648,
"step": 449
},
{
"epoch": 0.5327019828351583,
"grad_norm": 4.125,
"learning_rate": 1.9997318014177283e-05,
"loss": 2.5183,
"step": 450
},
{
"epoch": 0.5338857650192365,
"grad_norm": 4.75,
"learning_rate": 1.9997123032211343e-05,
"loss": 3.0498,
"step": 451
},
{
"epoch": 0.5350695472033146,
"grad_norm": 4.625,
"learning_rate": 1.9996921210107823e-05,
"loss": 2.6986,
"step": 452
},
{
"epoch": 0.5362533293873927,
"grad_norm": 4.625,
"learning_rate": 1.999671254800482e-05,
"loss": 3.1015,
"step": 453
},
{
"epoch": 0.5374371115714709,
"grad_norm": 5.15625,
"learning_rate": 1.9996497046045096e-05,
"loss": 3.0756,
"step": 454
},
{
"epoch": 0.538620893755549,
"grad_norm": 4.09375,
"learning_rate": 1.9996274704376105e-05,
"loss": 2.7572,
"step": 455
},
{
"epoch": 0.5398046759396271,
"grad_norm": 4.625,
"learning_rate": 1.9996045523149977e-05,
"loss": 2.8732,
"step": 456
},
{
"epoch": 0.5409884581237052,
"grad_norm": 4.25,
"learning_rate": 1.9995809502523513e-05,
"loss": 2.4689,
"step": 457
},
{
"epoch": 0.5421722403077833,
"grad_norm": 4.5,
"learning_rate": 1.9995566642658208e-05,
"loss": 2.5635,
"step": 458
},
{
"epoch": 0.5433560224918615,
"grad_norm": 4.8125,
"learning_rate": 1.9995316943720225e-05,
"loss": 2.8135,
"step": 459
},
{
"epoch": 0.5445398046759397,
"grad_norm": 4.375,
"learning_rate": 1.9995060405880412e-05,
"loss": 2.5494,
"step": 460
},
{
"epoch": 0.5457235868600178,
"grad_norm": 4.59375,
"learning_rate": 1.999479702931429e-05,
"loss": 3.0223,
"step": 461
},
{
"epoch": 0.5469073690440959,
"grad_norm": 4.8125,
"learning_rate": 1.9994526814202076e-05,
"loss": 2.4756,
"step": 462
},
{
"epoch": 0.548091151228174,
"grad_norm": 4.53125,
"learning_rate": 1.9994249760728645e-05,
"loss": 2.7521,
"step": 463
},
{
"epoch": 0.5492749334122522,
"grad_norm": 3.859375,
"learning_rate": 1.9993965869083562e-05,
"loss": 2.4649,
"step": 464
},
{
"epoch": 0.5504587155963303,
"grad_norm": 4.75,
"learning_rate": 1.999367513946107e-05,
"loss": 2.6839,
"step": 465
},
{
"epoch": 0.5516424977804084,
"grad_norm": 5.3125,
"learning_rate": 1.9993377572060084e-05,
"loss": 2.7087,
"step": 466
},
{
"epoch": 0.5528262799644865,
"grad_norm": 4.59375,
"learning_rate": 1.999307316708421e-05,
"loss": 2.7079,
"step": 467
},
{
"epoch": 0.5540100621485646,
"grad_norm": 4.375,
"learning_rate": 1.9992761924741718e-05,
"loss": 2.7192,
"step": 468
},
{
"epoch": 0.5551938443326427,
"grad_norm": 4.9375,
"learning_rate": 1.9992443845245572e-05,
"loss": 2.8079,
"step": 469
},
{
"epoch": 0.556377626516721,
"grad_norm": 4.1875,
"learning_rate": 1.99921189288134e-05,
"loss": 2.934,
"step": 470
},
{
"epoch": 0.5575614087007991,
"grad_norm": 4.625,
"learning_rate": 1.999178717566751e-05,
"loss": 2.8011,
"step": 471
},
{
"epoch": 0.5587451908848772,
"grad_norm": 4.34375,
"learning_rate": 1.9991448586034897e-05,
"loss": 2.5154,
"step": 472
},
{
"epoch": 0.5599289730689553,
"grad_norm": 4.875,
"learning_rate": 1.9991103160147226e-05,
"loss": 3.0889,
"step": 473
},
{
"epoch": 0.5611127552530334,
"grad_norm": 4.46875,
"learning_rate": 1.9990750898240837e-05,
"loss": 2.468,
"step": 474
},
{
"epoch": 0.5622965374371116,
"grad_norm": 4.21875,
"learning_rate": 1.9990391800556757e-05,
"loss": 2.7099,
"step": 475
},
{
"epoch": 0.5634803196211897,
"grad_norm": 4.6875,
"learning_rate": 1.9990025867340683e-05,
"loss": 2.6567,
"step": 476
},
{
"epoch": 0.5646641018052678,
"grad_norm": 4.46875,
"learning_rate": 1.998965309884299e-05,
"loss": 2.4946,
"step": 477
},
{
"epoch": 0.5658478839893459,
"grad_norm": 4.9375,
"learning_rate": 1.9989273495318726e-05,
"loss": 2.9824,
"step": 478
},
{
"epoch": 0.567031666173424,
"grad_norm": 4.5,
"learning_rate": 1.9988887057027627e-05,
"loss": 2.6195,
"step": 479
},
{
"epoch": 0.5682154483575023,
"grad_norm": 4.625,
"learning_rate": 1.998849378423409e-05,
"loss": 2.561,
"step": 480
},
{
"epoch": 0.5693992305415804,
"grad_norm": 5.59375,
"learning_rate": 1.998809367720721e-05,
"loss": 2.6358,
"step": 481
},
{
"epoch": 0.5705830127256585,
"grad_norm": 4.8125,
"learning_rate": 1.9987686736220726e-05,
"loss": 2.9791,
"step": 482
},
{
"epoch": 0.5717667949097366,
"grad_norm": 4.78125,
"learning_rate": 1.9987272961553087e-05,
"loss": 2.774,
"step": 483
},
{
"epoch": 0.5729505770938147,
"grad_norm": 4.625,
"learning_rate": 1.998685235348739e-05,
"loss": 2.9152,
"step": 484
},
{
"epoch": 0.5741343592778929,
"grad_norm": 4.53125,
"learning_rate": 1.998642491231143e-05,
"loss": 2.9774,
"step": 485
},
{
"epoch": 0.575318141461971,
"grad_norm": 4.4375,
"learning_rate": 1.9985990638317663e-05,
"loss": 2.6951,
"step": 486
},
{
"epoch": 0.5765019236460491,
"grad_norm": 4.90625,
"learning_rate": 1.998554953180322e-05,
"loss": 3.0327,
"step": 487
},
{
"epoch": 0.5776857058301272,
"grad_norm": 4.375,
"learning_rate": 1.9985101593069914e-05,
"loss": 2.8345,
"step": 488
},
{
"epoch": 0.5788694880142053,
"grad_norm": 4.5625,
"learning_rate": 1.998464682242423e-05,
"loss": 2.2809,
"step": 489
},
{
"epoch": 0.5800532701982836,
"grad_norm": 4.71875,
"learning_rate": 1.9984185220177327e-05,
"loss": 2.5339,
"step": 490
},
{
"epoch": 0.5812370523823617,
"grad_norm": 3.890625,
"learning_rate": 1.9983716786645035e-05,
"loss": 2.8075,
"step": 491
},
{
"epoch": 0.5824208345664398,
"grad_norm": 4.65625,
"learning_rate": 1.9983241522147864e-05,
"loss": 2.6906,
"step": 492
},
{
"epoch": 0.5836046167505179,
"grad_norm": 4.4375,
"learning_rate": 1.9982759427011e-05,
"loss": 2.3835,
"step": 493
},
{
"epoch": 0.584788398934596,
"grad_norm": 4.40625,
"learning_rate": 1.9982270501564286e-05,
"loss": 3.085,
"step": 494
},
{
"epoch": 0.5859721811186742,
"grad_norm": 4.53125,
"learning_rate": 1.9981774746142254e-05,
"loss": 2.7208,
"step": 495
},
{
"epoch": 0.5871559633027523,
"grad_norm": 4.875,
"learning_rate": 1.9981272161084113e-05,
"loss": 2.6536,
"step": 496
},
{
"epoch": 0.5883397454868304,
"grad_norm": 4.9375,
"learning_rate": 1.998076274673373e-05,
"loss": 2.7804,
"step": 497
},
{
"epoch": 0.5895235276709085,
"grad_norm": 4.8125,
"learning_rate": 1.998024650343965e-05,
"loss": 2.9326,
"step": 498
},
{
"epoch": 0.5907073098549867,
"grad_norm": 5.125,
"learning_rate": 1.9979723431555098e-05,
"loss": 2.9943,
"step": 499
},
{
"epoch": 0.5918910920390648,
"grad_norm": 4.625,
"learning_rate": 1.9979193531437962e-05,
"loss": 2.9678,
"step": 500
},
{
"epoch": 0.593074874223143,
"grad_norm": 4.125,
"learning_rate": 1.9978656803450804e-05,
"loss": 2.6534,
"step": 501
},
{
"epoch": 0.5942586564072211,
"grad_norm": 4.65625,
"learning_rate": 1.9978113247960862e-05,
"loss": 2.627,
"step": 502
},
{
"epoch": 0.5954424385912992,
"grad_norm": 4.59375,
"learning_rate": 1.997756286534004e-05,
"loss": 2.6195,
"step": 503
},
{
"epoch": 0.5966262207753773,
"grad_norm": 4.34375,
"learning_rate": 1.9977005655964916e-05,
"loss": 2.635,
"step": 504
},
{
"epoch": 0.5978100029594554,
"grad_norm": 4.5,
"learning_rate": 1.997644162021674e-05,
"loss": 3.0525,
"step": 505
},
{
"epoch": 0.5989937851435336,
"grad_norm": 4.9375,
"learning_rate": 1.997587075848143e-05,
"loss": 2.5361,
"step": 506
},
{
"epoch": 0.6001775673276117,
"grad_norm": 4.5625,
"learning_rate": 1.9975293071149577e-05,
"loss": 2.6306,
"step": 507
},
{
"epoch": 0.6013613495116898,
"grad_norm": 5.21875,
"learning_rate": 1.997470855861644e-05,
"loss": 3.0632,
"step": 508
},
{
"epoch": 0.602545131695768,
"grad_norm": 5.3125,
"learning_rate": 1.997411722128195e-05,
"loss": 3.1031,
"step": 509
},
{
"epoch": 0.6037289138798461,
"grad_norm": 4.59375,
"learning_rate": 1.99735190595507e-05,
"loss": 2.7346,
"step": 510
},
{
"epoch": 0.6049126960639243,
"grad_norm": 4.28125,
"learning_rate": 1.9972914073831967e-05,
"loss": 2.9642,
"step": 511
},
{
"epoch": 0.6060964782480024,
"grad_norm": 4.46875,
"learning_rate": 1.9972302264539686e-05,
"loss": 2.8106,
"step": 512
},
{
"epoch": 0.6072802604320805,
"grad_norm": 4.46875,
"learning_rate": 1.997168363209246e-05,
"loss": 2.7211,
"step": 513
},
{
"epoch": 0.6084640426161586,
"grad_norm": 4.03125,
"learning_rate": 1.9971058176913566e-05,
"loss": 2.4382,
"step": 514
},
{
"epoch": 0.6096478248002367,
"grad_norm": 5.53125,
"learning_rate": 1.997042589943095e-05,
"loss": 2.7241,
"step": 515
},
{
"epoch": 0.6108316069843149,
"grad_norm": 4.34375,
"learning_rate": 1.9969786800077217e-05,
"loss": 2.7381,
"step": 516
},
{
"epoch": 0.612015389168393,
"grad_norm": 5.0,
"learning_rate": 1.9969140879289654e-05,
"loss": 2.8834,
"step": 517
},
{
"epoch": 0.6131991713524712,
"grad_norm": 4.59375,
"learning_rate": 1.99684881375102e-05,
"loss": 2.8296,
"step": 518
},
{
"epoch": 0.6143829535365493,
"grad_norm": 4.28125,
"learning_rate": 1.9967828575185467e-05,
"loss": 2.8824,
"step": 519
},
{
"epoch": 0.6155667357206274,
"grad_norm": 4.8125,
"learning_rate": 1.996716219276674e-05,
"loss": 2.7783,
"step": 520
},
{
"epoch": 0.6167505179047056,
"grad_norm": 4.03125,
"learning_rate": 1.996648899070996e-05,
"loss": 2.5804,
"step": 521
},
{
"epoch": 0.6179343000887837,
"grad_norm": 4.96875,
"learning_rate": 1.996580896947574e-05,
"loss": 2.6926,
"step": 522
},
{
"epoch": 0.6191180822728618,
"grad_norm": 5.1875,
"learning_rate": 1.9965122129529362e-05,
"loss": 2.6601,
"step": 523
},
{
"epoch": 0.6203018644569399,
"grad_norm": 4.15625,
"learning_rate": 1.9964428471340765e-05,
"loss": 2.7183,
"step": 524
},
{
"epoch": 0.621485646641018,
"grad_norm": 4.34375,
"learning_rate": 1.9963727995384558e-05,
"loss": 2.6511,
"step": 525
},
{
"epoch": 0.6226694288250961,
"grad_norm": 4.3125,
"learning_rate": 1.9963020702140016e-05,
"loss": 2.6517,
"step": 526
},
{
"epoch": 0.6238532110091743,
"grad_norm": 4.5625,
"learning_rate": 1.9962306592091073e-05,
"loss": 2.9489,
"step": 527
},
{
"epoch": 0.6250369931932525,
"grad_norm": 4.4375,
"learning_rate": 1.9961585665726332e-05,
"loss": 2.6911,
"step": 528
},
{
"epoch": 0.6262207753773306,
"grad_norm": 5.03125,
"learning_rate": 1.996085792353906e-05,
"loss": 2.9397,
"step": 529
},
{
"epoch": 0.6274045575614087,
"grad_norm": 4.5,
"learning_rate": 1.9960123366027187e-05,
"loss": 2.6896,
"step": 530
},
{
"epoch": 0.6285883397454868,
"grad_norm": 4.875,
"learning_rate": 1.99593819936933e-05,
"loss": 2.3817,
"step": 531
},
{
"epoch": 0.629772121929565,
"grad_norm": 4.21875,
"learning_rate": 1.9958633807044657e-05,
"loss": 3.116,
"step": 532
},
{
"epoch": 0.6309559041136431,
"grad_norm": 4.53125,
"learning_rate": 1.9957878806593176e-05,
"loss": 2.5594,
"step": 533
},
{
"epoch": 0.6321396862977212,
"grad_norm": 4.125,
"learning_rate": 1.9957116992855435e-05,
"loss": 2.7295,
"step": 534
},
{
"epoch": 0.6333234684817993,
"grad_norm": 4.375,
"learning_rate": 1.9956348366352675e-05,
"loss": 2.7084,
"step": 535
},
{
"epoch": 0.6345072506658774,
"grad_norm": 4.75,
"learning_rate": 1.9955572927610798e-05,
"loss": 2.7115,
"step": 536
},
{
"epoch": 0.6356910328499557,
"grad_norm": 4.4375,
"learning_rate": 1.9954790677160368e-05,
"loss": 2.9742,
"step": 537
},
{
"epoch": 0.6368748150340338,
"grad_norm": 4.09375,
"learning_rate": 1.9954001615536612e-05,
"loss": 3.1781,
"step": 538
},
{
"epoch": 0.6380585972181119,
"grad_norm": 4.65625,
"learning_rate": 1.995320574327941e-05,
"loss": 2.4473,
"step": 539
},
{
"epoch": 0.63924237940219,
"grad_norm": 4.65625,
"learning_rate": 1.995240306093331e-05,
"loss": 2.8824,
"step": 540
},
{
"epoch": 0.6404261615862681,
"grad_norm": 4.78125,
"learning_rate": 1.9951593569047513e-05,
"loss": 2.7433,
"step": 541
},
{
"epoch": 0.6416099437703463,
"grad_norm": 4.1875,
"learning_rate": 1.995077726817588e-05,
"loss": 2.563,
"step": 542
},
{
"epoch": 0.6427937259544244,
"grad_norm": 4.875,
"learning_rate": 1.9949954158876938e-05,
"loss": 2.9397,
"step": 543
},
{
"epoch": 0.6439775081385025,
"grad_norm": 4.71875,
"learning_rate": 1.994912424171386e-05,
"loss": 3.1348,
"step": 544
},
{
"epoch": 0.6451612903225806,
"grad_norm": 4.5,
"learning_rate": 1.994828751725449e-05,
"loss": 2.5916,
"step": 545
},
{
"epoch": 0.6463450725066587,
"grad_norm": 3.9375,
"learning_rate": 1.9947443986071328e-05,
"loss": 2.6637,
"step": 546
},
{
"epoch": 0.647528854690737,
"grad_norm": 4.40625,
"learning_rate": 1.9946593648741515e-05,
"loss": 2.5269,
"step": 547
},
{
"epoch": 0.6487126368748151,
"grad_norm": 5.34375,
"learning_rate": 1.9945736505846866e-05,
"loss": 2.7976,
"step": 548
},
{
"epoch": 0.6498964190588932,
"grad_norm": 4.25,
"learning_rate": 1.994487255797385e-05,
"loss": 2.747,
"step": 549
},
{
"epoch": 0.6510802012429713,
"grad_norm": 4.375,
"learning_rate": 1.994400180571359e-05,
"loss": 2.2085,
"step": 550
},
{
"epoch": 0.6522639834270494,
"grad_norm": 4.09375,
"learning_rate": 1.994312424966186e-05,
"loss": 2.7235,
"step": 551
},
{
"epoch": 0.6534477656111276,
"grad_norm": 4.375,
"learning_rate": 1.9942239890419097e-05,
"loss": 3.007,
"step": 552
},
{
"epoch": 0.6546315477952057,
"grad_norm": 4.40625,
"learning_rate": 1.9941348728590385e-05,
"loss": 2.6234,
"step": 553
},
{
"epoch": 0.6558153299792838,
"grad_norm": 4.59375,
"learning_rate": 1.9940450764785465e-05,
"loss": 2.7641,
"step": 554
},
{
"epoch": 0.6569991121633619,
"grad_norm": 4.78125,
"learning_rate": 1.9939545999618737e-05,
"loss": 2.4349,
"step": 555
},
{
"epoch": 0.65818289434744,
"grad_norm": 4.125,
"learning_rate": 1.9938634433709254e-05,
"loss": 2.6999,
"step": 556
},
{
"epoch": 0.6593666765315181,
"grad_norm": 4.53125,
"learning_rate": 1.9937716067680712e-05,
"loss": 2.5148,
"step": 557
},
{
"epoch": 0.6605504587155964,
"grad_norm": 3.953125,
"learning_rate": 1.993679090216147e-05,
"loss": 3.0745,
"step": 558
},
{
"epoch": 0.6617342408996745,
"grad_norm": 4.8125,
"learning_rate": 1.9935858937784537e-05,
"loss": 2.9972,
"step": 559
},
{
"epoch": 0.6629180230837526,
"grad_norm": 4.90625,
"learning_rate": 1.993492017518757e-05,
"loss": 2.7369,
"step": 560
},
{
"epoch": 0.6641018052678307,
"grad_norm": 4.59375,
"learning_rate": 1.9933974615012888e-05,
"loss": 2.73,
"step": 561
},
{
"epoch": 0.6652855874519088,
"grad_norm": 4.65625,
"learning_rate": 1.9933022257907445e-05,
"loss": 2.5335,
"step": 562
},
{
"epoch": 0.666469369635987,
"grad_norm": 4.6875,
"learning_rate": 1.9932063104522857e-05,
"loss": 2.3654,
"step": 563
},
{
"epoch": 0.6676531518200651,
"grad_norm": 3.90625,
"learning_rate": 1.9931097155515383e-05,
"loss": 2.4536,
"step": 564
},
{
"epoch": 0.6688369340041432,
"grad_norm": 4.625,
"learning_rate": 1.9930124411545943e-05,
"loss": 3.0691,
"step": 565
},
{
"epoch": 0.6700207161882213,
"grad_norm": 4.71875,
"learning_rate": 1.9929144873280092e-05,
"loss": 2.7916,
"step": 566
},
{
"epoch": 0.6712044983722995,
"grad_norm": 4.46875,
"learning_rate": 1.9928158541388046e-05,
"loss": 2.5077,
"step": 567
},
{
"epoch": 0.6723882805563777,
"grad_norm": 5.3125,
"learning_rate": 1.9927165416544656e-05,
"loss": 3.0197,
"step": 568
},
{
"epoch": 0.6735720627404558,
"grad_norm": 4.4375,
"learning_rate": 1.9926165499429437e-05,
"loss": 3.0066,
"step": 569
},
{
"epoch": 0.6747558449245339,
"grad_norm": 4.34375,
"learning_rate": 1.992515879072654e-05,
"loss": 2.5028,
"step": 570
},
{
"epoch": 0.675939627108612,
"grad_norm": 4.46875,
"learning_rate": 1.9924145291124764e-05,
"loss": 2.853,
"step": 571
},
{
"epoch": 0.6771234092926901,
"grad_norm": 4.5,
"learning_rate": 1.9923125001317557e-05,
"loss": 2.9009,
"step": 572
},
{
"epoch": 0.6783071914767683,
"grad_norm": 4.4375,
"learning_rate": 1.9922097922003016e-05,
"loss": 2.6961,
"step": 573
},
{
"epoch": 0.6794909736608464,
"grad_norm": 4.21875,
"learning_rate": 1.992106405388387e-05,
"loss": 2.7008,
"step": 574
},
{
"epoch": 0.6806747558449245,
"grad_norm": 4.15625,
"learning_rate": 1.992002339766751e-05,
"loss": 2.6626,
"step": 575
},
{
"epoch": 0.6818585380290026,
"grad_norm": 3.96875,
"learning_rate": 1.9918975954065964e-05,
"loss": 2.5642,
"step": 576
},
{
"epoch": 0.6830423202130808,
"grad_norm": 5.0,
"learning_rate": 1.9917921723795903e-05,
"loss": 2.464,
"step": 577
},
{
"epoch": 0.684226102397159,
"grad_norm": 4.40625,
"learning_rate": 1.9916860707578642e-05,
"loss": 2.5868,
"step": 578
},
{
"epoch": 0.6854098845812371,
"grad_norm": 4.5,
"learning_rate": 1.9915792906140138e-05,
"loss": 2.9558,
"step": 579
},
{
"epoch": 0.6865936667653152,
"grad_norm": 4.28125,
"learning_rate": 1.9914718320210994e-05,
"loss": 2.4406,
"step": 580
},
{
"epoch": 0.6877774489493933,
"grad_norm": 4.59375,
"learning_rate": 1.9913636950526455e-05,
"loss": 2.6716,
"step": 581
},
{
"epoch": 0.6889612311334714,
"grad_norm": 4.5,
"learning_rate": 1.9912548797826402e-05,
"loss": 2.5916,
"step": 582
},
{
"epoch": 0.6901450133175495,
"grad_norm": 4.59375,
"learning_rate": 1.9911453862855362e-05,
"loss": 2.8234,
"step": 583
},
{
"epoch": 0.6913287955016277,
"grad_norm": 4.4375,
"learning_rate": 1.99103521463625e-05,
"loss": 2.5454,
"step": 584
},
{
"epoch": 0.6925125776857058,
"grad_norm": 4.8125,
"learning_rate": 1.9909243649101625e-05,
"loss": 2.728,
"step": 585
},
{
"epoch": 0.693696359869784,
"grad_norm": 5.03125,
"learning_rate": 1.9908128371831177e-05,
"loss": 2.7296,
"step": 586
},
{
"epoch": 0.6948801420538621,
"grad_norm": 4.71875,
"learning_rate": 1.990700631531425e-05,
"loss": 2.8561,
"step": 587
},
{
"epoch": 0.6960639242379402,
"grad_norm": 4.71875,
"learning_rate": 1.9905877480318556e-05,
"loss": 2.8237,
"step": 588
},
{
"epoch": 0.6972477064220184,
"grad_norm": 4.40625,
"learning_rate": 1.9904741867616463e-05,
"loss": 2.4267,
"step": 589
},
{
"epoch": 0.6984314886060965,
"grad_norm": 4.46875,
"learning_rate": 1.990359947798497e-05,
"loss": 2.9332,
"step": 590
},
{
"epoch": 0.6996152707901746,
"grad_norm": 3.890625,
"learning_rate": 1.9902450312205707e-05,
"loss": 2.8438,
"step": 591
},
{
"epoch": 0.7007990529742527,
"grad_norm": 5.15625,
"learning_rate": 1.9901294371064947e-05,
"loss": 2.7563,
"step": 592
},
{
"epoch": 0.7019828351583308,
"grad_norm": 4.5625,
"learning_rate": 1.9900131655353597e-05,
"loss": 2.9209,
"step": 593
},
{
"epoch": 0.703166617342409,
"grad_norm": 5.0,
"learning_rate": 1.9898962165867204e-05,
"loss": 2.4509,
"step": 594
},
{
"epoch": 0.7043503995264871,
"grad_norm": 4.25,
"learning_rate": 1.989778590340594e-05,
"loss": 2.6434,
"step": 595
},
{
"epoch": 0.7055341817105653,
"grad_norm": 4.28125,
"learning_rate": 1.9896602868774617e-05,
"loss": 2.8239,
"step": 596
},
{
"epoch": 0.7067179638946434,
"grad_norm": 4.59375,
"learning_rate": 1.9895413062782683e-05,
"loss": 3.076,
"step": 597
},
{
"epoch": 0.7079017460787215,
"grad_norm": 4.9375,
"learning_rate": 1.9894216486244214e-05,
"loss": 2.6014,
"step": 598
},
{
"epoch": 0.7090855282627997,
"grad_norm": 5.25,
"learning_rate": 1.9893013139977917e-05,
"loss": 2.6695,
"step": 599
},
{
"epoch": 0.7102693104468778,
"grad_norm": 4.0625,
"learning_rate": 1.989180302480714e-05,
"loss": 2.803,
"step": 600
},
{
"epoch": 0.7114530926309559,
"grad_norm": 4.28125,
"learning_rate": 1.989058614155985e-05,
"loss": 2.6803,
"step": 601
},
{
"epoch": 0.712636874815034,
"grad_norm": 4.90625,
"learning_rate": 1.9889362491068658e-05,
"loss": 2.7176,
"step": 602
},
{
"epoch": 0.7138206569991121,
"grad_norm": 5.28125,
"learning_rate": 1.9888132074170797e-05,
"loss": 3.049,
"step": 603
},
{
"epoch": 0.7150044391831903,
"grad_norm": 4.90625,
"learning_rate": 1.988689489170813e-05,
"loss": 2.7108,
"step": 604
},
{
"epoch": 0.7161882213672685,
"grad_norm": 4.90625,
"learning_rate": 1.9885650944527146e-05,
"loss": 2.6473,
"step": 605
},
{
"epoch": 0.7173720035513466,
"grad_norm": 4.625,
"learning_rate": 1.9884400233478976e-05,
"loss": 2.9112,
"step": 606
},
{
"epoch": 0.7185557857354247,
"grad_norm": 4.34375,
"learning_rate": 1.9883142759419364e-05,
"loss": 2.9322,
"step": 607
},
{
"epoch": 0.7197395679195028,
"grad_norm": 4.28125,
"learning_rate": 1.9881878523208687e-05,
"loss": 2.9772,
"step": 608
},
{
"epoch": 0.720923350103581,
"grad_norm": 4.8125,
"learning_rate": 1.9880607525711954e-05,
"loss": 2.6923,
"step": 609
},
{
"epoch": 0.7221071322876591,
"grad_norm": 4.3125,
"learning_rate": 1.987932976779879e-05,
"loss": 2.5212,
"step": 610
},
{
"epoch": 0.7232909144717372,
"grad_norm": 4.5625,
"learning_rate": 1.9878045250343445e-05,
"loss": 2.3864,
"step": 611
},
{
"epoch": 0.7244746966558153,
"grad_norm": 4.96875,
"learning_rate": 1.987675397422481e-05,
"loss": 2.5733,
"step": 612
},
{
"epoch": 0.7256584788398934,
"grad_norm": 4.78125,
"learning_rate": 1.9875455940326386e-05,
"loss": 2.7831,
"step": 613
},
{
"epoch": 0.7268422610239715,
"grad_norm": 5.03125,
"learning_rate": 1.9874151149536304e-05,
"loss": 2.9132,
"step": 614
},
{
"epoch": 0.7280260432080498,
"grad_norm": 4.28125,
"learning_rate": 1.9872839602747308e-05,
"loss": 2.8321,
"step": 615
},
{
"epoch": 0.7292098253921279,
"grad_norm": 4.90625,
"learning_rate": 1.987152130085678e-05,
"loss": 3.0614,
"step": 616
},
{
"epoch": 0.730393607576206,
"grad_norm": 4.65625,
"learning_rate": 1.9870196244766715e-05,
"loss": 2.556,
"step": 617
},
{
"epoch": 0.7315773897602841,
"grad_norm": 4.40625,
"learning_rate": 1.9868864435383724e-05,
"loss": 2.837,
"step": 618
},
{
"epoch": 0.7327611719443622,
"grad_norm": 5.0,
"learning_rate": 1.9867525873619056e-05,
"loss": 2.9625,
"step": 619
},
{
"epoch": 0.7339449541284404,
"grad_norm": 4.28125,
"learning_rate": 1.986618056038856e-05,
"loss": 2.4284,
"step": 620
},
{
"epoch": 0.7351287363125185,
"grad_norm": 4.4375,
"learning_rate": 1.9864828496612717e-05,
"loss": 2.5562,
"step": 621
},
{
"epoch": 0.7363125184965966,
"grad_norm": 4.125,
"learning_rate": 1.9863469683216622e-05,
"loss": 2.821,
"step": 622
},
{
"epoch": 0.7374963006806747,
"grad_norm": 4.15625,
"learning_rate": 1.9862104121129992e-05,
"loss": 2.3722,
"step": 623
},
{
"epoch": 0.7386800828647528,
"grad_norm": 3.953125,
"learning_rate": 1.9860731811287157e-05,
"loss": 2.6551,
"step": 624
},
{
"epoch": 0.7398638650488311,
"grad_norm": 3.984375,
"learning_rate": 1.9859352754627067e-05,
"loss": 2.692,
"step": 625
},
{
"epoch": 0.7410476472329092,
"grad_norm": 4.21875,
"learning_rate": 1.9857966952093285e-05,
"loss": 2.6048,
"step": 626
},
{
"epoch": 0.7422314294169873,
"grad_norm": 4.625,
"learning_rate": 1.9856574404633996e-05,
"loss": 2.7087,
"step": 627
},
{
"epoch": 0.7434152116010654,
"grad_norm": 4.75,
"learning_rate": 1.9855175113201994e-05,
"loss": 2.7129,
"step": 628
},
{
"epoch": 0.7445989937851435,
"grad_norm": 4.375,
"learning_rate": 1.9853769078754685e-05,
"loss": 2.6135,
"step": 629
},
{
"epoch": 0.7457827759692217,
"grad_norm": 4.3125,
"learning_rate": 1.9852356302254098e-05,
"loss": 2.2924,
"step": 630
},
{
"epoch": 0.7469665581532998,
"grad_norm": 4.25,
"learning_rate": 1.9850936784666865e-05,
"loss": 2.5269,
"step": 631
},
{
"epoch": 0.7481503403373779,
"grad_norm": 4.09375,
"learning_rate": 1.9849510526964243e-05,
"loss": 2.5773,
"step": 632
},
{
"epoch": 0.749334122521456,
"grad_norm": 4.4375,
"learning_rate": 1.9848077530122083e-05,
"loss": 2.526,
"step": 633
},
{
"epoch": 0.7505179047055341,
"grad_norm": 5.15625,
"learning_rate": 1.984663779512086e-05,
"loss": 2.6791,
"step": 634
},
{
"epoch": 0.7517016868896124,
"grad_norm": 4.25,
"learning_rate": 1.984519132294566e-05,
"loss": 2.5493,
"step": 635
},
{
"epoch": 0.7528854690736905,
"grad_norm": 4.1875,
"learning_rate": 1.984373811458617e-05,
"loss": 2.8055,
"step": 636
},
{
"epoch": 0.7540692512577686,
"grad_norm": 4.40625,
"learning_rate": 1.9842278171036692e-05,
"loss": 2.9258,
"step": 637
},
{
"epoch": 0.7552530334418467,
"grad_norm": 4.53125,
"learning_rate": 1.9840811493296134e-05,
"loss": 2.5569,
"step": 638
},
{
"epoch": 0.7564368156259248,
"grad_norm": 4.25,
"learning_rate": 1.9839338082368017e-05,
"loss": 2.3998,
"step": 639
},
{
"epoch": 0.7576205978100029,
"grad_norm": 5.0625,
"learning_rate": 1.9837857939260457e-05,
"loss": 2.8316,
"step": 640
},
{
"epoch": 0.7588043799940811,
"grad_norm": 4.28125,
"learning_rate": 1.983637106498619e-05,
"loss": 2.726,
"step": 641
},
{
"epoch": 0.7599881621781592,
"grad_norm": 4.625,
"learning_rate": 1.9834877460562546e-05,
"loss": 2.9761,
"step": 642
},
{
"epoch": 0.7611719443622373,
"grad_norm": 4.375,
"learning_rate": 1.9833377127011468e-05,
"loss": 3.0479,
"step": 643
},
{
"epoch": 0.7623557265463154,
"grad_norm": 4.625,
"learning_rate": 1.98318700653595e-05,
"loss": 2.9874,
"step": 644
},
{
"epoch": 0.7635395087303936,
"grad_norm": 4.5,
"learning_rate": 1.9830356276637788e-05,
"loss": 2.5282,
"step": 645
},
{
"epoch": 0.7647232909144718,
"grad_norm": 4.125,
"learning_rate": 1.9828835761882085e-05,
"loss": 2.9227,
"step": 646
},
{
"epoch": 0.7659070730985499,
"grad_norm": 4.75,
"learning_rate": 1.982730852213274e-05,
"loss": 2.9667,
"step": 647
},
{
"epoch": 0.767090855282628,
"grad_norm": 4.46875,
"learning_rate": 1.9825774558434712e-05,
"loss": 2.5896,
"step": 648
},
{
"epoch": 0.7682746374667061,
"grad_norm": 3.859375,
"learning_rate": 1.9824233871837547e-05,
"loss": 2.521,
"step": 649
},
{
"epoch": 0.7694584196507842,
"grad_norm": 4.3125,
"learning_rate": 1.9822686463395406e-05,
"loss": 2.3522,
"step": 650
},
{
"epoch": 0.7706422018348624,
"grad_norm": 4.3125,
"learning_rate": 1.982113233416704e-05,
"loss": 2.6371,
"step": 651
},
{
"epoch": 0.7718259840189405,
"grad_norm": 4.4375,
"learning_rate": 1.98195714852158e-05,
"loss": 2.8795,
"step": 652
},
{
"epoch": 0.7730097662030186,
"grad_norm": 4.75,
"learning_rate": 1.9818003917609637e-05,
"loss": 2.2281,
"step": 653
},
{
"epoch": 0.7741935483870968,
"grad_norm": 4.15625,
"learning_rate": 1.9816429632421095e-05,
"loss": 2.5841,
"step": 654
},
{
"epoch": 0.7753773305711749,
"grad_norm": 4.21875,
"learning_rate": 1.9814848630727323e-05,
"loss": 3.0166,
"step": 655
},
{
"epoch": 0.7765611127552531,
"grad_norm": 4.90625,
"learning_rate": 1.9813260913610048e-05,
"loss": 2.5244,
"step": 656
},
{
"epoch": 0.7777448949393312,
"grad_norm": 3.84375,
"learning_rate": 1.9811666482155608e-05,
"loss": 2.5887,
"step": 657
},
{
"epoch": 0.7789286771234093,
"grad_norm": 5.0,
"learning_rate": 1.9810065337454934e-05,
"loss": 3.0088,
"step": 658
},
{
"epoch": 0.7801124593074874,
"grad_norm": 4.65625,
"learning_rate": 1.9808457480603547e-05,
"loss": 2.8829,
"step": 659
},
{
"epoch": 0.7812962414915655,
"grad_norm": 4.5625,
"learning_rate": 1.980684291270155e-05,
"loss": 3.0234,
"step": 660
},
{
"epoch": 0.7824800236756437,
"grad_norm": 4.84375,
"learning_rate": 1.9805221634853656e-05,
"loss": 2.9785,
"step": 661
},
{
"epoch": 0.7836638058597218,
"grad_norm": 4.125,
"learning_rate": 1.980359364816916e-05,
"loss": 2.8455,
"step": 662
},
{
"epoch": 0.7848475880438,
"grad_norm": 4.5625,
"learning_rate": 1.980195895376194e-05,
"loss": 2.9199,
"step": 663
},
{
"epoch": 0.7860313702278781,
"grad_norm": 4.28125,
"learning_rate": 1.980031755275048e-05,
"loss": 2.6206,
"step": 664
},
{
"epoch": 0.7872151524119562,
"grad_norm": 4.15625,
"learning_rate": 1.9798669446257844e-05,
"loss": 2.4331,
"step": 665
},
{
"epoch": 0.7883989345960344,
"grad_norm": 4.28125,
"learning_rate": 1.9797014635411674e-05,
"loss": 2.4075,
"step": 666
},
{
"epoch": 0.7895827167801125,
"grad_norm": 3.8125,
"learning_rate": 1.979535312134422e-05,
"loss": 2.5911,
"step": 667
},
{
"epoch": 0.7907664989641906,
"grad_norm": 4.34375,
"learning_rate": 1.9793684905192302e-05,
"loss": 2.7445,
"step": 668
},
{
"epoch": 0.7919502811482687,
"grad_norm": 4.0625,
"learning_rate": 1.9792009988097334e-05,
"loss": 2.4411,
"step": 669
},
{
"epoch": 0.7931340633323468,
"grad_norm": 4.75,
"learning_rate": 1.979032837120531e-05,
"loss": 2.7688,
"step": 670
},
{
"epoch": 0.7943178455164249,
"grad_norm": 4.21875,
"learning_rate": 1.978864005566681e-05,
"loss": 2.1891,
"step": 671
},
{
"epoch": 0.7955016277005031,
"grad_norm": 4.4375,
"learning_rate": 1.9786945042636998e-05,
"loss": 2.8605,
"step": 672
},
{
"epoch": 0.7966854098845813,
"grad_norm": 4.5,
"learning_rate": 1.9785243333275622e-05,
"loss": 2.7968,
"step": 673
},
{
"epoch": 0.7978691920686594,
"grad_norm": 4.46875,
"learning_rate": 1.9783534928747006e-05,
"loss": 2.4442,
"step": 674
},
{
"epoch": 0.7990529742527375,
"grad_norm": 4.6875,
"learning_rate": 1.9781819830220058e-05,
"loss": 2.6155,
"step": 675
},
{
"epoch": 0.8002367564368156,
"grad_norm": 4.75,
"learning_rate": 1.978009803886827e-05,
"loss": 2.4824,
"step": 676
},
{
"epoch": 0.8014205386208938,
"grad_norm": 4.53125,
"learning_rate": 1.9778369555869714e-05,
"loss": 2.6693,
"step": 677
},
{
"epoch": 0.8026043208049719,
"grad_norm": 4.5625,
"learning_rate": 1.9776634382407027e-05,
"loss": 2.9669,
"step": 678
},
{
"epoch": 0.80378810298905,
"grad_norm": 4.3125,
"learning_rate": 1.9774892519667433e-05,
"loss": 2.8019,
"step": 679
},
{
"epoch": 0.8049718851731281,
"grad_norm": 4.21875,
"learning_rate": 1.9773143968842743e-05,
"loss": 2.7486,
"step": 680
},
{
"epoch": 0.8061556673572062,
"grad_norm": 4.46875,
"learning_rate": 1.9771388731129325e-05,
"loss": 2.7975,
"step": 681
},
{
"epoch": 0.8073394495412844,
"grad_norm": 4.78125,
"learning_rate": 1.9769626807728134e-05,
"loss": 2.663,
"step": 682
},
{
"epoch": 0.8085232317253626,
"grad_norm": 4.375,
"learning_rate": 1.9767858199844697e-05,
"loss": 2.777,
"step": 683
},
{
"epoch": 0.8097070139094407,
"grad_norm": 4.84375,
"learning_rate": 1.9766082908689117e-05,
"loss": 2.8866,
"step": 684
},
{
"epoch": 0.8108907960935188,
"grad_norm": 4.5,
"learning_rate": 1.9764300935476065e-05,
"loss": 2.8192,
"step": 685
},
{
"epoch": 0.8120745782775969,
"grad_norm": 4.90625,
"learning_rate": 1.9762512281424778e-05,
"loss": 2.9202,
"step": 686
},
{
"epoch": 0.8132583604616751,
"grad_norm": 4.0,
"learning_rate": 1.9760716947759086e-05,
"loss": 2.3563,
"step": 687
},
{
"epoch": 0.8144421426457532,
"grad_norm": 5.09375,
"learning_rate": 1.9758914935707366e-05,
"loss": 2.4792,
"step": 688
},
{
"epoch": 0.8156259248298313,
"grad_norm": 4.59375,
"learning_rate": 1.9757106246502577e-05,
"loss": 2.4805,
"step": 689
},
{
"epoch": 0.8168097070139094,
"grad_norm": 4.71875,
"learning_rate": 1.9755290881382244e-05,
"loss": 2.6702,
"step": 690
},
{
"epoch": 0.8179934891979875,
"grad_norm": 4.0,
"learning_rate": 1.9753468841588456e-05,
"loss": 2.5932,
"step": 691
},
{
"epoch": 0.8191772713820658,
"grad_norm": 4.90625,
"learning_rate": 1.9751640128367872e-05,
"loss": 2.5145,
"step": 692
},
{
"epoch": 0.8203610535661439,
"grad_norm": 4.125,
"learning_rate": 1.974980474297172e-05,
"loss": 2.6263,
"step": 693
},
{
"epoch": 0.821544835750222,
"grad_norm": 4.84375,
"learning_rate": 1.974796268665579e-05,
"loss": 2.8267,
"step": 694
},
{
"epoch": 0.8227286179343001,
"grad_norm": 4.15625,
"learning_rate": 1.9746113960680435e-05,
"loss": 2.4361,
"step": 695
},
{
"epoch": 0.8239124001183782,
"grad_norm": 4.5,
"learning_rate": 1.9744258566310574e-05,
"loss": 2.4392,
"step": 696
},
{
"epoch": 0.8250961823024563,
"grad_norm": 4.15625,
"learning_rate": 1.9742396504815687e-05,
"loss": 2.6312,
"step": 697
},
{
"epoch": 0.8262799644865345,
"grad_norm": 4.375,
"learning_rate": 1.974052777746981e-05,
"loss": 2.8784,
"step": 698
},
{
"epoch": 0.8274637466706126,
"grad_norm": 4.53125,
"learning_rate": 1.973865238555156e-05,
"loss": 2.8234,
"step": 699
},
{
"epoch": 0.8286475288546907,
"grad_norm": 4.4375,
"learning_rate": 1.9736770330344084e-05,
"loss": 2.8006,
"step": 700
},
{
"epoch": 0.8298313110387688,
"grad_norm": 4.3125,
"learning_rate": 1.973488161313512e-05,
"loss": 2.448,
"step": 701
},
{
"epoch": 0.831015093222847,
"grad_norm": 4.5625,
"learning_rate": 1.9732986235216937e-05,
"loss": 2.846,
"step": 702
},
{
"epoch": 0.8321988754069252,
"grad_norm": 5.34375,
"learning_rate": 1.9731084197886376e-05,
"loss": 2.8718,
"step": 703
},
{
"epoch": 0.8333826575910033,
"grad_norm": 4.59375,
"learning_rate": 1.9729175502444832e-05,
"loss": 2.6046,
"step": 704
},
{
"epoch": 0.8345664397750814,
"grad_norm": 4.375,
"learning_rate": 1.9727260150198254e-05,
"loss": 2.5858,
"step": 705
},
{
"epoch": 0.8357502219591595,
"grad_norm": 4.1875,
"learning_rate": 1.9725338142457145e-05,
"loss": 2.6371,
"step": 706
},
{
"epoch": 0.8369340041432376,
"grad_norm": 4.53125,
"learning_rate": 1.9723409480536566e-05,
"loss": 2.6958,
"step": 707
},
{
"epoch": 0.8381177863273158,
"grad_norm": 4.9375,
"learning_rate": 1.9721474165756124e-05,
"loss": 2.6909,
"step": 708
},
{
"epoch": 0.8393015685113939,
"grad_norm": 4.21875,
"learning_rate": 1.9719532199439986e-05,
"loss": 2.5668,
"step": 709
},
{
"epoch": 0.840485350695472,
"grad_norm": 4.84375,
"learning_rate": 1.9717583582916862e-05,
"loss": 2.7497,
"step": 710
},
{
"epoch": 0.8416691328795501,
"grad_norm": 4.0625,
"learning_rate": 1.9715628317520022e-05,
"loss": 2.8988,
"step": 711
},
{
"epoch": 0.8428529150636282,
"grad_norm": 4.6875,
"learning_rate": 1.9713666404587274e-05,
"loss": 2.5417,
"step": 712
},
{
"epoch": 0.8440366972477065,
"grad_norm": 4.53125,
"learning_rate": 1.9711697845460978e-05,
"loss": 2.8351,
"step": 713
},
{
"epoch": 0.8452204794317846,
"grad_norm": 5.15625,
"learning_rate": 1.970972264148805e-05,
"loss": 2.6508,
"step": 714
},
{
"epoch": 0.8464042616158627,
"grad_norm": 4.90625,
"learning_rate": 1.9707740794019937e-05,
"loss": 2.8921,
"step": 715
},
{
"epoch": 0.8475880437999408,
"grad_norm": 4.75,
"learning_rate": 1.970575230441265e-05,
"loss": 2.6767,
"step": 716
},
{
"epoch": 0.8487718259840189,
"grad_norm": 4.4375,
"learning_rate": 1.9703757174026726e-05,
"loss": 2.4478,
"step": 717
},
{
"epoch": 0.8499556081680971,
"grad_norm": 4.59375,
"learning_rate": 1.970175540422726e-05,
"loss": 2.8067,
"step": 718
},
{
"epoch": 0.8511393903521752,
"grad_norm": 4.71875,
"learning_rate": 1.969974699638388e-05,
"loss": 2.9803,
"step": 719
},
{
"epoch": 0.8523231725362533,
"grad_norm": 4.5625,
"learning_rate": 1.969773195187076e-05,
"loss": 2.5863,
"step": 720
},
{
"epoch": 0.8535069547203314,
"grad_norm": 4.53125,
"learning_rate": 1.9695710272066623e-05,
"loss": 2.5013,
"step": 721
},
{
"epoch": 0.8546907369044096,
"grad_norm": 4.6875,
"learning_rate": 1.969368195835471e-05,
"loss": 2.5718,
"step": 722
},
{
"epoch": 0.8558745190884878,
"grad_norm": 3.9375,
"learning_rate": 1.9691647012122825e-05,
"loss": 2.5935,
"step": 723
},
{
"epoch": 0.8570583012725659,
"grad_norm": 3.9375,
"learning_rate": 1.9689605434763298e-05,
"loss": 2.7084,
"step": 724
},
{
"epoch": 0.858242083456644,
"grad_norm": 4.40625,
"learning_rate": 1.9687557227672997e-05,
"loss": 2.8408,
"step": 725
},
{
"epoch": 0.8594258656407221,
"grad_norm": 5.9375,
"learning_rate": 1.9685502392253326e-05,
"loss": 2.5317,
"step": 726
},
{
"epoch": 0.8606096478248002,
"grad_norm": 4.3125,
"learning_rate": 1.9683440929910223e-05,
"loss": 2.3043,
"step": 727
},
{
"epoch": 0.8617934300088783,
"grad_norm": 4.78125,
"learning_rate": 1.968137284205417e-05,
"loss": 2.5764,
"step": 728
},
{
"epoch": 0.8629772121929565,
"grad_norm": 4.1875,
"learning_rate": 1.9679298130100165e-05,
"loss": 2.8978,
"step": 729
},
{
"epoch": 0.8641609943770346,
"grad_norm": 5.0,
"learning_rate": 1.967721679546776e-05,
"loss": 2.3907,
"step": 730
},
{
"epoch": 0.8653447765611127,
"grad_norm": 4.90625,
"learning_rate": 1.9675128839581013e-05,
"loss": 2.9282,
"step": 731
},
{
"epoch": 0.8665285587451909,
"grad_norm": 4.28125,
"learning_rate": 1.9673034263868533e-05,
"loss": 2.5821,
"step": 732
},
{
"epoch": 0.867712340929269,
"grad_norm": 4.5625,
"learning_rate": 1.967093306976345e-05,
"loss": 2.622,
"step": 733
},
{
"epoch": 0.8688961231133472,
"grad_norm": 4.5625,
"learning_rate": 1.9668825258703424e-05,
"loss": 2.9779,
"step": 734
},
{
"epoch": 0.8700799052974253,
"grad_norm": 4.9375,
"learning_rate": 1.966671083213064e-05,
"loss": 2.8442,
"step": 735
},
{
"epoch": 0.8712636874815034,
"grad_norm": 4.96875,
"learning_rate": 1.9664589791491812e-05,
"loss": 2.9357,
"step": 736
},
{
"epoch": 0.8724474696655815,
"grad_norm": 4.5625,
"learning_rate": 1.966246213823818e-05,
"loss": 2.4707,
"step": 737
},
{
"epoch": 0.8736312518496596,
"grad_norm": 4.59375,
"learning_rate": 1.9660327873825503e-05,
"loss": 2.538,
"step": 738
},
{
"epoch": 0.8748150340337378,
"grad_norm": 4.65625,
"learning_rate": 1.9658186999714067e-05,
"loss": 2.8768,
"step": 739
},
{
"epoch": 0.875998816217816,
"grad_norm": 4.25,
"learning_rate": 1.9656039517368686e-05,
"loss": 2.6136,
"step": 740
},
{
"epoch": 0.877182598401894,
"grad_norm": 5.0625,
"learning_rate": 1.9653885428258686e-05,
"loss": 2.737,
"step": 741
},
{
"epoch": 0.8783663805859722,
"grad_norm": 3.90625,
"learning_rate": 1.965172473385792e-05,
"loss": 2.2199,
"step": 742
},
{
"epoch": 0.8795501627700503,
"grad_norm": 4.5,
"learning_rate": 1.9649557435644757e-05,
"loss": 2.7758,
"step": 743
},
{
"epoch": 0.8807339449541285,
"grad_norm": 4.15625,
"learning_rate": 1.9647383535102085e-05,
"loss": 2.8697,
"step": 744
},
{
"epoch": 0.8819177271382066,
"grad_norm": 4.4375,
"learning_rate": 1.964520303371731e-05,
"loss": 2.8299,
"step": 745
},
{
"epoch": 0.8831015093222847,
"grad_norm": 4.4375,
"learning_rate": 1.9643015932982355e-05,
"loss": 2.6092,
"step": 746
},
{
"epoch": 0.8842852915063628,
"grad_norm": 4.25,
"learning_rate": 1.9640822234393654e-05,
"loss": 2.5451,
"step": 747
},
{
"epoch": 0.8854690736904409,
"grad_norm": 4.40625,
"learning_rate": 1.9638621939452166e-05,
"loss": 2.6748,
"step": 748
},
{
"epoch": 0.8866528558745191,
"grad_norm": 4.65625,
"learning_rate": 1.963641504966335e-05,
"loss": 2.7055,
"step": 749
},
{
"epoch": 0.8878366380585972,
"grad_norm": 4.21875,
"learning_rate": 1.9634201566537182e-05,
"loss": 2.7432,
"step": 750
},
{
"epoch": 0.8890204202426754,
"grad_norm": 4.78125,
"learning_rate": 1.963198149158816e-05,
"loss": 3.2116,
"step": 751
},
{
"epoch": 0.8902042024267535,
"grad_norm": 4.625,
"learning_rate": 1.962975482633527e-05,
"loss": 2.6164,
"step": 752
},
{
"epoch": 0.8913879846108316,
"grad_norm": 4.53125,
"learning_rate": 1.9627521572302035e-05,
"loss": 2.7443,
"step": 753
},
{
"epoch": 0.8925717667949097,
"grad_norm": 4.59375,
"learning_rate": 1.9625281731016455e-05,
"loss": 2.6206,
"step": 754
},
{
"epoch": 0.8937555489789879,
"grad_norm": 4.09375,
"learning_rate": 1.9623035304011062e-05,
"loss": 2.5069,
"step": 755
},
{
"epoch": 0.894939331163066,
"grad_norm": 4.25,
"learning_rate": 1.962078229282289e-05,
"loss": 2.3173,
"step": 756
},
{
"epoch": 0.8961231133471441,
"grad_norm": 4.21875,
"learning_rate": 1.961852269899346e-05,
"loss": 2.4459,
"step": 757
},
{
"epoch": 0.8973068955312222,
"grad_norm": 4.65625,
"learning_rate": 1.9616256524068822e-05,
"loss": 2.3314,
"step": 758
},
{
"epoch": 0.8984906777153003,
"grad_norm": 4.59375,
"learning_rate": 1.961398376959951e-05,
"loss": 2.6148,
"step": 759
},
{
"epoch": 0.8996744598993786,
"grad_norm": 4.15625,
"learning_rate": 1.961170443714057e-05,
"loss": 2.5566,
"step": 760
},
{
"epoch": 0.9008582420834567,
"grad_norm": 4.40625,
"learning_rate": 1.9609418528251543e-05,
"loss": 2.7433,
"step": 761
},
{
"epoch": 0.9020420242675348,
"grad_norm": 4.34375,
"learning_rate": 1.9607126044496476e-05,
"loss": 2.8541,
"step": 762
},
{
"epoch": 0.9032258064516129,
"grad_norm": 4.34375,
"learning_rate": 1.9604826987443905e-05,
"loss": 2.5727,
"step": 763
},
{
"epoch": 0.904409588635691,
"grad_norm": 4.46875,
"learning_rate": 1.960252135866687e-05,
"loss": 2.5726,
"step": 764
},
{
"epoch": 0.9055933708197692,
"grad_norm": 4.625,
"learning_rate": 1.9600209159742913e-05,
"loss": 2.8777,
"step": 765
},
{
"epoch": 0.9067771530038473,
"grad_norm": 4.875,
"learning_rate": 1.959789039225406e-05,
"loss": 2.8927,
"step": 766
},
{
"epoch": 0.9079609351879254,
"grad_norm": 4.6875,
"learning_rate": 1.9595565057786838e-05,
"loss": 2.7569,
"step": 767
},
{
"epoch": 0.9091447173720035,
"grad_norm": 4.59375,
"learning_rate": 1.9593233157932265e-05,
"loss": 2.5841,
"step": 768
},
{
"epoch": 0.9103284995560816,
"grad_norm": 4.71875,
"learning_rate": 1.9590894694285852e-05,
"loss": 2.488,
"step": 769
},
{
"epoch": 0.9115122817401599,
"grad_norm": 4.25,
"learning_rate": 1.9588549668447595e-05,
"loss": 2.9169,
"step": 770
},
{
"epoch": 0.912696063924238,
"grad_norm": 4.625,
"learning_rate": 1.9586198082021995e-05,
"loss": 2.6622,
"step": 771
},
{
"epoch": 0.9138798461083161,
"grad_norm": 4.5,
"learning_rate": 1.958383993661803e-05,
"loss": 2.8777,
"step": 772
},
{
"epoch": 0.9150636282923942,
"grad_norm": 5.0625,
"learning_rate": 1.9581475233849165e-05,
"loss": 2.9759,
"step": 773
},
{
"epoch": 0.9162474104764723,
"grad_norm": 4.40625,
"learning_rate": 1.957910397533335e-05,
"loss": 2.4661,
"step": 774
},
{
"epoch": 0.9174311926605505,
"grad_norm": 4.53125,
"learning_rate": 1.9576726162693036e-05,
"loss": 2.7026,
"step": 775
},
{
"epoch": 0.9186149748446286,
"grad_norm": 3.8125,
"learning_rate": 1.9574341797555143e-05,
"loss": 2.42,
"step": 776
},
{
"epoch": 0.9197987570287067,
"grad_norm": 4.09375,
"learning_rate": 1.9571950881551073e-05,
"loss": 2.7335,
"step": 777
},
{
"epoch": 0.9209825392127848,
"grad_norm": 4.5625,
"learning_rate": 1.9569553416316725e-05,
"loss": 2.5518,
"step": 778
},
{
"epoch": 0.9221663213968629,
"grad_norm": 4.5,
"learning_rate": 1.9567149403492467e-05,
"loss": 2.5461,
"step": 779
},
{
"epoch": 0.9233501035809412,
"grad_norm": 4.09375,
"learning_rate": 1.9564738844723153e-05,
"loss": 2.5361,
"step": 780
},
{
"epoch": 0.9245338857650193,
"grad_norm": 4.625,
"learning_rate": 1.9562321741658106e-05,
"loss": 3.1115,
"step": 781
},
{
"epoch": 0.9257176679490974,
"grad_norm": 4.78125,
"learning_rate": 1.9559898095951137e-05,
"loss": 2.7055,
"step": 782
},
{
"epoch": 0.9269014501331755,
"grad_norm": 4.65625,
"learning_rate": 1.955746790926053e-05,
"loss": 2.9354,
"step": 783
},
{
"epoch": 0.9280852323172536,
"grad_norm": 4.40625,
"learning_rate": 1.9555031183249046e-05,
"loss": 2.3607,
"step": 784
},
{
"epoch": 0.9292690145013317,
"grad_norm": 4.21875,
"learning_rate": 1.9552587919583915e-05,
"loss": 2.5434,
"step": 785
},
{
"epoch": 0.9304527966854099,
"grad_norm": 5.0,
"learning_rate": 1.955013811993685e-05,
"loss": 3.1603,
"step": 786
},
{
"epoch": 0.931636578869488,
"grad_norm": 4.8125,
"learning_rate": 1.9547681785984024e-05,
"loss": 2.6145,
"step": 787
},
{
"epoch": 0.9328203610535661,
"grad_norm": 4.125,
"learning_rate": 1.954521891940609e-05,
"loss": 2.8456,
"step": 788
},
{
"epoch": 0.9340041432376442,
"grad_norm": 4.09375,
"learning_rate": 1.9542749521888165e-05,
"loss": 2.6692,
"step": 789
},
{
"epoch": 0.9351879254217224,
"grad_norm": 4.65625,
"learning_rate": 1.9540273595119842e-05,
"loss": 2.7225,
"step": 790
},
{
"epoch": 0.9363717076058006,
"grad_norm": 3.984375,
"learning_rate": 1.953779114079517e-05,
"loss": 2.0607,
"step": 791
},
{
"epoch": 0.9375554897898787,
"grad_norm": 4.6875,
"learning_rate": 1.9535302160612674e-05,
"loss": 2.6539,
"step": 792
},
{
"epoch": 0.9387392719739568,
"grad_norm": 4.5625,
"learning_rate": 1.953280665627534e-05,
"loss": 2.8294,
"step": 793
},
{
"epoch": 0.9399230541580349,
"grad_norm": 4.5625,
"learning_rate": 1.953030462949062e-05,
"loss": 2.7902,
"step": 794
},
{
"epoch": 0.941106836342113,
"grad_norm": 4.71875,
"learning_rate": 1.9527796081970423e-05,
"loss": 2.7581,
"step": 795
},
{
"epoch": 0.9422906185261912,
"grad_norm": 4.0625,
"learning_rate": 1.9525281015431127e-05,
"loss": 2.7359,
"step": 796
},
{
"epoch": 0.9434744007102693,
"grad_norm": 3.65625,
"learning_rate": 1.9522759431593566e-05,
"loss": 2.4659,
"step": 797
},
{
"epoch": 0.9446581828943474,
"grad_norm": 4.25,
"learning_rate": 1.9520231332183037e-05,
"loss": 2.6183,
"step": 798
},
{
"epoch": 0.9458419650784256,
"grad_norm": 4.0625,
"learning_rate": 1.951769671892929e-05,
"loss": 2.2723,
"step": 799
},
{
"epoch": 0.9470257472625037,
"grad_norm": 4.34375,
"learning_rate": 1.9515155593566536e-05,
"loss": 2.9629,
"step": 800
},
{
"epoch": 0.9482095294465819,
"grad_norm": 5.28125,
"learning_rate": 1.9512607957833438e-05,
"loss": 2.9293,
"step": 801
},
{
"epoch": 0.94939331163066,
"grad_norm": 4.46875,
"learning_rate": 1.9510053813473115e-05,
"loss": 3.1096,
"step": 802
},
{
"epoch": 0.9505770938147381,
"grad_norm": 4.3125,
"learning_rate": 1.950749316223314e-05,
"loss": 2.597,
"step": 803
},
{
"epoch": 0.9517608759988162,
"grad_norm": 4.375,
"learning_rate": 1.9504926005865542e-05,
"loss": 2.5539,
"step": 804
},
{
"epoch": 0.9529446581828943,
"grad_norm": 4.96875,
"learning_rate": 1.950235234612679e-05,
"loss": 2.5333,
"step": 805
},
{
"epoch": 0.9541284403669725,
"grad_norm": 4.75,
"learning_rate": 1.9499772184777814e-05,
"loss": 3.3359,
"step": 806
},
{
"epoch": 0.9553122225510506,
"grad_norm": 4.28125,
"learning_rate": 1.9497185523583986e-05,
"loss": 2.7828,
"step": 807
},
{
"epoch": 0.9564960047351287,
"grad_norm": 4.21875,
"learning_rate": 1.9494592364315125e-05,
"loss": 2.5705,
"step": 808
},
{
"epoch": 0.9576797869192069,
"grad_norm": 3.84375,
"learning_rate": 1.9491992708745502e-05,
"loss": 2.6607,
"step": 809
},
{
"epoch": 0.958863569103285,
"grad_norm": 4.15625,
"learning_rate": 1.948938655865383e-05,
"loss": 2.4996,
"step": 810
},
{
"epoch": 0.9600473512873631,
"grad_norm": 4.84375,
"learning_rate": 1.9486773915823258e-05,
"loss": 2.4498,
"step": 811
},
{
"epoch": 0.9612311334714413,
"grad_norm": 4.1875,
"learning_rate": 1.948415478204139e-05,
"loss": 2.4218,
"step": 812
},
{
"epoch": 0.9624149156555194,
"grad_norm": 4.84375,
"learning_rate": 1.9481529159100258e-05,
"loss": 2.5013,
"step": 813
},
{
"epoch": 0.9635986978395975,
"grad_norm": 4.90625,
"learning_rate": 1.947889704879635e-05,
"loss": 2.9975,
"step": 814
},
{
"epoch": 0.9647824800236756,
"grad_norm": 4.75,
"learning_rate": 1.9476258452930577e-05,
"loss": 2.5171,
"step": 815
},
{
"epoch": 0.9659662622077537,
"grad_norm": 4.40625,
"learning_rate": 1.94736133733083e-05,
"loss": 2.9159,
"step": 816
},
{
"epoch": 0.9671500443918319,
"grad_norm": 4.21875,
"learning_rate": 1.9470961811739304e-05,
"loss": 2.6609,
"step": 817
},
{
"epoch": 0.96833382657591,
"grad_norm": 4.78125,
"learning_rate": 1.946830377003782e-05,
"loss": 3.1055,
"step": 818
},
{
"epoch": 0.9695176087599882,
"grad_norm": 3.984375,
"learning_rate": 1.946563925002251e-05,
"loss": 2.3084,
"step": 819
},
{
"epoch": 0.9707013909440663,
"grad_norm": 4.09375,
"learning_rate": 1.9462968253516462e-05,
"loss": 2.5402,
"step": 820
},
{
"epoch": 0.9718851731281444,
"grad_norm": 4.25,
"learning_rate": 1.94602907823472e-05,
"loss": 2.6274,
"step": 821
},
{
"epoch": 0.9730689553122226,
"grad_norm": 4.8125,
"learning_rate": 1.945760683834668e-05,
"loss": 2.6139,
"step": 822
},
{
"epoch": 0.9742527374963007,
"grad_norm": 4.5,
"learning_rate": 1.9454916423351288e-05,
"loss": 2.5494,
"step": 823
},
{
"epoch": 0.9754365196803788,
"grad_norm": 4.75,
"learning_rate": 1.945221953920183e-05,
"loss": 2.7888,
"step": 824
},
{
"epoch": 0.9766203018644569,
"grad_norm": 4.40625,
"learning_rate": 1.9449516187743546e-05,
"loss": 2.8302,
"step": 825
},
{
"epoch": 0.977804084048535,
"grad_norm": 4.34375,
"learning_rate": 1.94468063708261e-05,
"loss": 2.8079,
"step": 826
},
{
"epoch": 0.9789878662326132,
"grad_norm": 4.28125,
"learning_rate": 1.9444090090303567e-05,
"loss": 2.8151,
"step": 827
},
{
"epoch": 0.9801716484166914,
"grad_norm": 4.125,
"learning_rate": 1.9441367348034464e-05,
"loss": 2.4723,
"step": 828
},
{
"epoch": 0.9813554306007695,
"grad_norm": 4.9375,
"learning_rate": 1.9438638145881718e-05,
"loss": 3.2675,
"step": 829
},
{
"epoch": 0.9825392127848476,
"grad_norm": 4.6875,
"learning_rate": 1.9435902485712677e-05,
"loss": 2.8028,
"step": 830
},
{
"epoch": 0.9837229949689257,
"grad_norm": 4.40625,
"learning_rate": 1.9433160369399108e-05,
"loss": 2.7554,
"step": 831
},
{
"epoch": 0.9849067771530039,
"grad_norm": 4.5625,
"learning_rate": 1.94304117988172e-05,
"loss": 2.524,
"step": 832
},
{
"epoch": 0.986090559337082,
"grad_norm": 4.34375,
"learning_rate": 1.9427656775847553e-05,
"loss": 2.3596,
"step": 833
},
{
"epoch": 0.9872743415211601,
"grad_norm": 4.5,
"learning_rate": 1.9424895302375177e-05,
"loss": 2.6464,
"step": 834
},
{
"epoch": 0.9884581237052382,
"grad_norm": 4.75,
"learning_rate": 1.9422127380289508e-05,
"loss": 2.4242,
"step": 835
},
{
"epoch": 0.9896419058893163,
"grad_norm": 4.4375,
"learning_rate": 1.941935301148439e-05,
"loss": 2.4942,
"step": 836
},
{
"epoch": 0.9908256880733946,
"grad_norm": 4.46875,
"learning_rate": 1.9416572197858063e-05,
"loss": 2.8784,
"step": 837
},
{
"epoch": 0.9920094702574727,
"grad_norm": 4.96875,
"learning_rate": 1.9413784941313203e-05,
"loss": 2.9636,
"step": 838
},
{
"epoch": 0.9931932524415508,
"grad_norm": 4.09375,
"learning_rate": 1.941099124375687e-05,
"loss": 2.4056,
"step": 839
},
{
"epoch": 0.9943770346256289,
"grad_norm": 5.0625,
"learning_rate": 1.9408191107100554e-05,
"loss": 2.5094,
"step": 840
},
{
"epoch": 0.995560816809707,
"grad_norm": 5.0,
"learning_rate": 1.9405384533260124e-05,
"loss": 2.7804,
"step": 841
},
{
"epoch": 0.9967445989937851,
"grad_norm": 4.34375,
"learning_rate": 1.9402571524155877e-05,
"loss": 2.6124,
"step": 842
},
{
"epoch": 0.9979283811778633,
"grad_norm": 4.6875,
"learning_rate": 1.9399752081712498e-05,
"loss": 2.7607,
"step": 843
},
{
"epoch": 0.9991121633619414,
"grad_norm": 4.0,
"learning_rate": 1.9396926207859085e-05,
"loss": 2.5465,
"step": 844
},
{
"epoch": 1.0,
"grad_norm": 3.609375,
"learning_rate": 1.939409390452913e-05,
"loss": 1.9983,
"step": 845
}
],
"logging_steps": 1.0,
"max_steps": 4220,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.3126189689443942e+17,
"train_batch_size": 12,
"trial_name": null,
"trial_params": null
}