Francois-CKPTs / checkpoint-1090 /trainer_state.json
kalomaze's picture
Upload folder using huggingface_hub
59fdd89 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.5057471264367814,
"eval_steps": 109,
"global_step": 1090,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0022988505747126436,
"grad_norm": 0.5069637298583984,
"learning_rate": 0.0,
"loss": 1.731,
"step": 1
},
{
"epoch": 0.0022988505747126436,
"eval_loss": 2.414314031600952,
"eval_runtime": 25.166,
"eval_samples_per_second": 8.543,
"eval_steps_per_second": 0.556,
"step": 1
},
{
"epoch": 0.004597701149425287,
"grad_norm": 0.4284007251262665,
"learning_rate": 7.5e-07,
"loss": 1.5988,
"step": 2
},
{
"epoch": 0.006896551724137931,
"grad_norm": 0.3730175197124481,
"learning_rate": 1.5e-06,
"loss": 1.6805,
"step": 3
},
{
"epoch": 0.009195402298850575,
"grad_norm": 0.5110131502151489,
"learning_rate": 2.25e-06,
"loss": 1.5713,
"step": 4
},
{
"epoch": 0.011494252873563218,
"grad_norm": 0.4888417720794678,
"learning_rate": 3e-06,
"loss": 1.7453,
"step": 5
},
{
"epoch": 0.013793103448275862,
"grad_norm": 0.4452195167541504,
"learning_rate": 3.75e-06,
"loss": 1.5119,
"step": 6
},
{
"epoch": 0.016091954022988506,
"grad_norm": 0.34987178444862366,
"learning_rate": 4.5e-06,
"loss": 1.5568,
"step": 7
},
{
"epoch": 0.01839080459770115,
"grad_norm": 0.4203605353832245,
"learning_rate": 5.25e-06,
"loss": 1.5328,
"step": 8
},
{
"epoch": 0.020689655172413793,
"grad_norm": 0.4149104356765747,
"learning_rate": 6e-06,
"loss": 1.5431,
"step": 9
},
{
"epoch": 0.022988505747126436,
"grad_norm": 0.3467399775981903,
"learning_rate": 6.750000000000001e-06,
"loss": 1.5327,
"step": 10
},
{
"epoch": 0.02528735632183908,
"grad_norm": 0.41448578238487244,
"learning_rate": 7.5e-06,
"loss": 1.5403,
"step": 11
},
{
"epoch": 0.027586206896551724,
"grad_norm": 0.3749900162220001,
"learning_rate": 8.25e-06,
"loss": 1.5399,
"step": 12
},
{
"epoch": 0.029885057471264367,
"grad_norm": 0.31972795724868774,
"learning_rate": 9e-06,
"loss": 1.6906,
"step": 13
},
{
"epoch": 0.03218390804597701,
"grad_norm": 0.35329630970954895,
"learning_rate": 9.75e-06,
"loss": 1.555,
"step": 14
},
{
"epoch": 0.034482758620689655,
"grad_norm": 0.2345588505268097,
"learning_rate": 1.05e-05,
"loss": 1.6135,
"step": 15
},
{
"epoch": 0.0367816091954023,
"grad_norm": 0.4078080952167511,
"learning_rate": 1.125e-05,
"loss": 1.6193,
"step": 16
},
{
"epoch": 0.03908045977011494,
"grad_norm": 0.26700371503829956,
"learning_rate": 1.2e-05,
"loss": 1.5204,
"step": 17
},
{
"epoch": 0.041379310344827586,
"grad_norm": 0.24357175827026367,
"learning_rate": 1.275e-05,
"loss": 1.5078,
"step": 18
},
{
"epoch": 0.04367816091954023,
"grad_norm": 0.2841810882091522,
"learning_rate": 1.3500000000000001e-05,
"loss": 1.6501,
"step": 19
},
{
"epoch": 0.04597701149425287,
"grad_norm": 0.23267385363578796,
"learning_rate": 1.4249999999999999e-05,
"loss": 1.5619,
"step": 20
},
{
"epoch": 0.04827586206896552,
"grad_norm": 0.28393587470054626,
"learning_rate": 1.5e-05,
"loss": 1.4791,
"step": 21
},
{
"epoch": 0.05057471264367816,
"grad_norm": 0.29562872648239136,
"learning_rate": 1.575e-05,
"loss": 1.6896,
"step": 22
},
{
"epoch": 0.052873563218390804,
"grad_norm": 0.3160124719142914,
"learning_rate": 1.65e-05,
"loss": 1.6216,
"step": 23
},
{
"epoch": 0.05517241379310345,
"grad_norm": 0.23838184773921967,
"learning_rate": 1.725e-05,
"loss": 1.5922,
"step": 24
},
{
"epoch": 0.05747126436781609,
"grad_norm": 0.2532449960708618,
"learning_rate": 1.8e-05,
"loss": 1.4571,
"step": 25
},
{
"epoch": 0.059770114942528735,
"grad_norm": 0.23338833451271057,
"learning_rate": 1.8750000000000002e-05,
"loss": 1.5694,
"step": 26
},
{
"epoch": 0.06206896551724138,
"grad_norm": 0.22958090901374817,
"learning_rate": 1.95e-05,
"loss": 1.6798,
"step": 27
},
{
"epoch": 0.06436781609195402,
"grad_norm": 0.21505244076251984,
"learning_rate": 2.025e-05,
"loss": 1.6731,
"step": 28
},
{
"epoch": 0.06666666666666667,
"grad_norm": 0.2669045627117157,
"learning_rate": 2.1e-05,
"loss": 1.8578,
"step": 29
},
{
"epoch": 0.06896551724137931,
"grad_norm": 0.29674679040908813,
"learning_rate": 2.175e-05,
"loss": 1.6049,
"step": 30
},
{
"epoch": 0.07126436781609195,
"grad_norm": 0.28321748971939087,
"learning_rate": 2.25e-05,
"loss": 1.4984,
"step": 31
},
{
"epoch": 0.0735632183908046,
"grad_norm": 0.21930895745754242,
"learning_rate": 2.3250000000000003e-05,
"loss": 1.625,
"step": 32
},
{
"epoch": 0.07586206896551724,
"grad_norm": 0.29348301887512207,
"learning_rate": 2.4e-05,
"loss": 1.6346,
"step": 33
},
{
"epoch": 0.07816091954022988,
"grad_norm": 0.2185889631509781,
"learning_rate": 2.475e-05,
"loss": 1.4568,
"step": 34
},
{
"epoch": 0.08045977011494253,
"grad_norm": 0.20907077193260193,
"learning_rate": 2.55e-05,
"loss": 1.5471,
"step": 35
},
{
"epoch": 0.08275862068965517,
"grad_norm": 0.22380973398685455,
"learning_rate": 2.625e-05,
"loss": 1.6173,
"step": 36
},
{
"epoch": 0.08505747126436781,
"grad_norm": 0.21461962163448334,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.576,
"step": 37
},
{
"epoch": 0.08735632183908046,
"grad_norm": 0.3937881290912628,
"learning_rate": 2.7750000000000004e-05,
"loss": 1.5894,
"step": 38
},
{
"epoch": 0.0896551724137931,
"grad_norm": 0.35467925667762756,
"learning_rate": 2.8499999999999998e-05,
"loss": 1.5258,
"step": 39
},
{
"epoch": 0.09195402298850575,
"grad_norm": 0.25823158025741577,
"learning_rate": 2.925e-05,
"loss": 1.5129,
"step": 40
},
{
"epoch": 0.09425287356321839,
"grad_norm": 0.40610358119010925,
"learning_rate": 3e-05,
"loss": 1.7819,
"step": 41
},
{
"epoch": 0.09655172413793103,
"grad_norm": 0.2139093577861786,
"learning_rate": 2.999997438684708e-05,
"loss": 1.5814,
"step": 42
},
{
"epoch": 0.09885057471264368,
"grad_norm": 0.2259477972984314,
"learning_rate": 2.9999897547475787e-05,
"loss": 1.5568,
"step": 43
},
{
"epoch": 0.10114942528735632,
"grad_norm": 0.21875832974910736,
"learning_rate": 2.9999769482148537e-05,
"loss": 1.5982,
"step": 44
},
{
"epoch": 0.10344827586206896,
"grad_norm": 0.19804655015468597,
"learning_rate": 2.9999590191302685e-05,
"loss": 1.604,
"step": 45
},
{
"epoch": 0.10574712643678161,
"grad_norm": 0.21753054857254028,
"learning_rate": 2.9999359675550518e-05,
"loss": 1.514,
"step": 46
},
{
"epoch": 0.10804597701149425,
"grad_norm": 0.2550787627696991,
"learning_rate": 2.9999077935679278e-05,
"loss": 1.619,
"step": 47
},
{
"epoch": 0.1103448275862069,
"grad_norm": 0.21381859481334686,
"learning_rate": 2.9998744972651123e-05,
"loss": 1.7447,
"step": 48
},
{
"epoch": 0.11264367816091954,
"grad_norm": 0.18944889307022095,
"learning_rate": 2.9998360787603152e-05,
"loss": 1.559,
"step": 49
},
{
"epoch": 0.11494252873563218,
"grad_norm": 0.3304287791252136,
"learning_rate": 2.999792538184739e-05,
"loss": 1.4765,
"step": 50
},
{
"epoch": 0.11724137931034483,
"grad_norm": 0.20207946002483368,
"learning_rate": 2.999743875687079e-05,
"loss": 1.5633,
"step": 51
},
{
"epoch": 0.11954022988505747,
"grad_norm": 0.22447501122951508,
"learning_rate": 2.9996900914335215e-05,
"loss": 1.4947,
"step": 52
},
{
"epoch": 0.12183908045977011,
"grad_norm": 0.19888006150722504,
"learning_rate": 2.999631185607745e-05,
"loss": 1.4622,
"step": 53
},
{
"epoch": 0.12413793103448276,
"grad_norm": 0.20114877820014954,
"learning_rate": 2.999567158410917e-05,
"loss": 1.6337,
"step": 54
},
{
"epoch": 0.12643678160919541,
"grad_norm": 0.18649515509605408,
"learning_rate": 2.9994980100616965e-05,
"loss": 1.3233,
"step": 55
},
{
"epoch": 0.12873563218390804,
"grad_norm": 0.2480180561542511,
"learning_rate": 2.9994237407962312e-05,
"loss": 1.572,
"step": 56
},
{
"epoch": 0.1310344827586207,
"grad_norm": 0.20667031407356262,
"learning_rate": 2.9993443508681568e-05,
"loss": 1.6211,
"step": 57
},
{
"epoch": 0.13333333333333333,
"grad_norm": 0.20844992995262146,
"learning_rate": 2.9992598405485974e-05,
"loss": 1.5465,
"step": 58
},
{
"epoch": 0.135632183908046,
"grad_norm": 0.1889929622411728,
"learning_rate": 2.9991702101261625e-05,
"loss": 1.3084,
"step": 59
},
{
"epoch": 0.13793103448275862,
"grad_norm": 0.20737043023109436,
"learning_rate": 2.999075459906948e-05,
"loss": 1.5021,
"step": 60
},
{
"epoch": 0.14022988505747128,
"grad_norm": 0.20062296092510223,
"learning_rate": 2.9989755902145345e-05,
"loss": 1.5962,
"step": 61
},
{
"epoch": 0.1425287356321839,
"grad_norm": 0.22415389120578766,
"learning_rate": 2.998870601389985e-05,
"loss": 1.5384,
"step": 62
},
{
"epoch": 0.14482758620689656,
"grad_norm": 0.22267140448093414,
"learning_rate": 2.998760493791846e-05,
"loss": 1.4724,
"step": 63
},
{
"epoch": 0.1471264367816092,
"grad_norm": 0.7529204487800598,
"learning_rate": 2.9986452677961444e-05,
"loss": 1.6365,
"step": 64
},
{
"epoch": 0.14942528735632185,
"grad_norm": 0.1924290955066681,
"learning_rate": 2.998524923796387e-05,
"loss": 1.6797,
"step": 65
},
{
"epoch": 0.15172413793103448,
"grad_norm": 0.19907116889953613,
"learning_rate": 2.998399462203559e-05,
"loss": 1.5057,
"step": 66
},
{
"epoch": 0.15402298850574714,
"grad_norm": 0.22147919237613678,
"learning_rate": 2.9982688834461224e-05,
"loss": 1.6233,
"step": 67
},
{
"epoch": 0.15632183908045977,
"grad_norm": 0.20038853585720062,
"learning_rate": 2.9981331879700154e-05,
"loss": 1.4315,
"step": 68
},
{
"epoch": 0.15862068965517243,
"grad_norm": 0.18834556639194489,
"learning_rate": 2.9979923762386502e-05,
"loss": 1.5417,
"step": 69
},
{
"epoch": 0.16091954022988506,
"grad_norm": 0.21252746880054474,
"learning_rate": 2.9978464487329103e-05,
"loss": 1.551,
"step": 70
},
{
"epoch": 0.1632183908045977,
"grad_norm": 0.1933295726776123,
"learning_rate": 2.997695405951151e-05,
"loss": 1.6536,
"step": 71
},
{
"epoch": 0.16551724137931034,
"grad_norm": 0.20261478424072266,
"learning_rate": 2.997539248409197e-05,
"loss": 1.447,
"step": 72
},
{
"epoch": 0.167816091954023,
"grad_norm": 0.19905412197113037,
"learning_rate": 2.9973779766403397e-05,
"loss": 1.5292,
"step": 73
},
{
"epoch": 0.17011494252873563,
"grad_norm": 0.18111269176006317,
"learning_rate": 2.9972115911953362e-05,
"loss": 1.5375,
"step": 74
},
{
"epoch": 0.1724137931034483,
"grad_norm": 0.1907217800617218,
"learning_rate": 2.9970400926424075e-05,
"loss": 1.5131,
"step": 75
},
{
"epoch": 0.17471264367816092,
"grad_norm": 0.23455685377120972,
"learning_rate": 2.9968634815672358e-05,
"loss": 1.4095,
"step": 76
},
{
"epoch": 0.17701149425287357,
"grad_norm": 0.17424362897872925,
"learning_rate": 2.9966817585729628e-05,
"loss": 1.668,
"step": 77
},
{
"epoch": 0.1793103448275862,
"grad_norm": 0.23638956248760223,
"learning_rate": 2.9964949242801892e-05,
"loss": 1.6052,
"step": 78
},
{
"epoch": 0.18160919540229886,
"grad_norm": 0.2161344438791275,
"learning_rate": 2.9963029793269706e-05,
"loss": 1.5685,
"step": 79
},
{
"epoch": 0.1839080459770115,
"grad_norm": 0.2340526580810547,
"learning_rate": 2.9961059243688148e-05,
"loss": 1.5669,
"step": 80
},
{
"epoch": 0.18620689655172415,
"grad_norm": 0.1841650903224945,
"learning_rate": 2.9959037600786822e-05,
"loss": 1.5704,
"step": 81
},
{
"epoch": 0.18850574712643678,
"grad_norm": 0.20588481426239014,
"learning_rate": 2.995696487146981e-05,
"loss": 1.7211,
"step": 82
},
{
"epoch": 0.19080459770114944,
"grad_norm": 0.20442944765090942,
"learning_rate": 2.9954841062815667e-05,
"loss": 1.6141,
"step": 83
},
{
"epoch": 0.19310344827586207,
"grad_norm": 0.19162479043006897,
"learning_rate": 2.9952666182077388e-05,
"loss": 1.6093,
"step": 84
},
{
"epoch": 0.19540229885057472,
"grad_norm": 0.20947952568531036,
"learning_rate": 2.995044023668237e-05,
"loss": 1.5725,
"step": 85
},
{
"epoch": 0.19770114942528735,
"grad_norm": 0.1801944524049759,
"learning_rate": 2.9948163234232417e-05,
"loss": 1.6016,
"step": 86
},
{
"epoch": 0.2,
"grad_norm": 0.2099916785955429,
"learning_rate": 2.9945835182503694e-05,
"loss": 1.5365,
"step": 87
},
{
"epoch": 0.20229885057471264,
"grad_norm": 0.2339092642068863,
"learning_rate": 2.994345608944669e-05,
"loss": 1.5603,
"step": 88
},
{
"epoch": 0.2045977011494253,
"grad_norm": 0.22072693705558777,
"learning_rate": 2.994102596318622e-05,
"loss": 1.5614,
"step": 89
},
{
"epoch": 0.20689655172413793,
"grad_norm": 0.21728575229644775,
"learning_rate": 2.9938544812021384e-05,
"loss": 1.6696,
"step": 90
},
{
"epoch": 0.20919540229885059,
"grad_norm": 0.20296227931976318,
"learning_rate": 2.9936012644425518e-05,
"loss": 1.5268,
"step": 91
},
{
"epoch": 0.21149425287356322,
"grad_norm": 0.26510635018348694,
"learning_rate": 2.9933429469046202e-05,
"loss": 1.6672,
"step": 92
},
{
"epoch": 0.21379310344827587,
"grad_norm": 0.19461052119731903,
"learning_rate": 2.99307952947052e-05,
"loss": 1.4914,
"step": 93
},
{
"epoch": 0.2160919540229885,
"grad_norm": 0.2512831389904022,
"learning_rate": 2.992811013039845e-05,
"loss": 1.671,
"step": 94
},
{
"epoch": 0.21839080459770116,
"grad_norm": 0.2247190624475479,
"learning_rate": 2.9925373985296022e-05,
"loss": 1.5807,
"step": 95
},
{
"epoch": 0.2206896551724138,
"grad_norm": 0.20809918642044067,
"learning_rate": 2.9922586868742085e-05,
"loss": 1.5098,
"step": 96
},
{
"epoch": 0.22298850574712645,
"grad_norm": 0.1891755610704422,
"learning_rate": 2.991974879025489e-05,
"loss": 1.461,
"step": 97
},
{
"epoch": 0.22528735632183908,
"grad_norm": 0.24038074910640717,
"learning_rate": 2.9916859759526718e-05,
"loss": 1.6229,
"step": 98
},
{
"epoch": 0.22758620689655173,
"grad_norm": 0.2145155966281891,
"learning_rate": 2.9913919786423868e-05,
"loss": 1.4588,
"step": 99
},
{
"epoch": 0.22988505747126436,
"grad_norm": 0.26329857110977173,
"learning_rate": 2.9910928880986593e-05,
"loss": 1.481,
"step": 100
},
{
"epoch": 0.23218390804597702,
"grad_norm": 0.20909543335437775,
"learning_rate": 2.9907887053429107e-05,
"loss": 1.4284,
"step": 101
},
{
"epoch": 0.23448275862068965,
"grad_norm": 0.17718562483787537,
"learning_rate": 2.9904794314139508e-05,
"loss": 1.5976,
"step": 102
},
{
"epoch": 0.2367816091954023,
"grad_norm": 0.2007722556591034,
"learning_rate": 2.990165067367977e-05,
"loss": 1.5414,
"step": 103
},
{
"epoch": 0.23908045977011494,
"grad_norm": 0.24877959489822388,
"learning_rate": 2.98984561427857e-05,
"loss": 1.6262,
"step": 104
},
{
"epoch": 0.2413793103448276,
"grad_norm": 0.7631202936172485,
"learning_rate": 2.98952107323669e-05,
"loss": 1.6812,
"step": 105
},
{
"epoch": 0.24367816091954023,
"grad_norm": 0.1995263695716858,
"learning_rate": 2.9891914453506738e-05,
"loss": 1.7776,
"step": 106
},
{
"epoch": 0.24597701149425288,
"grad_norm": 0.24228224158287048,
"learning_rate": 2.9888567317462274e-05,
"loss": 1.6015,
"step": 107
},
{
"epoch": 0.2482758620689655,
"grad_norm": 0.2489222288131714,
"learning_rate": 2.9885169335664285e-05,
"loss": 1.3039,
"step": 108
},
{
"epoch": 0.25057471264367814,
"grad_norm": 0.5918052792549133,
"learning_rate": 2.988172051971717e-05,
"loss": 1.451,
"step": 109
},
{
"epoch": 0.25057471264367814,
"eval_loss": 2.301447629928589,
"eval_runtime": 25.4002,
"eval_samples_per_second": 8.465,
"eval_steps_per_second": 0.551,
"step": 109
},
{
"epoch": 0.25287356321839083,
"grad_norm": 0.24599245190620422,
"learning_rate": 2.9878220881398933e-05,
"loss": 1.6464,
"step": 110
},
{
"epoch": 0.25517241379310346,
"grad_norm": 0.20595747232437134,
"learning_rate": 2.987467043266114e-05,
"loss": 1.5419,
"step": 111
},
{
"epoch": 0.2574712643678161,
"grad_norm": 0.20620642602443695,
"learning_rate": 2.9871069185628895e-05,
"loss": 1.5379,
"step": 112
},
{
"epoch": 0.2597701149425287,
"grad_norm": 0.18572480976581573,
"learning_rate": 2.986741715260076e-05,
"loss": 1.6103,
"step": 113
},
{
"epoch": 0.2620689655172414,
"grad_norm": 0.20042060315608978,
"learning_rate": 2.986371434604875e-05,
"loss": 1.5626,
"step": 114
},
{
"epoch": 0.26436781609195403,
"grad_norm": 0.19916732609272003,
"learning_rate": 2.9859960778618268e-05,
"loss": 1.3422,
"step": 115
},
{
"epoch": 0.26666666666666666,
"grad_norm": 0.20298229157924652,
"learning_rate": 2.9856156463128078e-05,
"loss": 1.6126,
"step": 116
},
{
"epoch": 0.2689655172413793,
"grad_norm": 0.24507172405719757,
"learning_rate": 2.9852301412570248e-05,
"loss": 1.5705,
"step": 117
},
{
"epoch": 0.271264367816092,
"grad_norm": 0.17676107585430145,
"learning_rate": 2.9848395640110103e-05,
"loss": 1.5538,
"step": 118
},
{
"epoch": 0.2735632183908046,
"grad_norm": 0.18487243354320526,
"learning_rate": 2.984443915908621e-05,
"loss": 1.5449,
"step": 119
},
{
"epoch": 0.27586206896551724,
"grad_norm": 0.18909598886966705,
"learning_rate": 2.984043198301029e-05,
"loss": 1.4912,
"step": 120
},
{
"epoch": 0.27816091954022987,
"grad_norm": 0.20144197344779968,
"learning_rate": 2.9836374125567193e-05,
"loss": 1.5309,
"step": 121
},
{
"epoch": 0.28045977011494255,
"grad_norm": 0.17654699087142944,
"learning_rate": 2.9832265600614857e-05,
"loss": 1.5224,
"step": 122
},
{
"epoch": 0.2827586206896552,
"grad_norm": 0.24907322227954865,
"learning_rate": 2.9828106422184256e-05,
"loss": 1.5011,
"step": 123
},
{
"epoch": 0.2850574712643678,
"grad_norm": 0.2545442581176758,
"learning_rate": 2.9823896604479347e-05,
"loss": 1.5756,
"step": 124
},
{
"epoch": 0.28735632183908044,
"grad_norm": 0.21520832180976868,
"learning_rate": 2.9819636161877026e-05,
"loss": 1.4542,
"step": 125
},
{
"epoch": 0.2896551724137931,
"grad_norm": 0.2093474119901657,
"learning_rate": 2.981532510892707e-05,
"loss": 1.6188,
"step": 126
},
{
"epoch": 0.29195402298850576,
"grad_norm": 0.1842268705368042,
"learning_rate": 2.9810963460352095e-05,
"loss": 1.645,
"step": 127
},
{
"epoch": 0.2942528735632184,
"grad_norm": 0.19314023852348328,
"learning_rate": 2.9806551231047524e-05,
"loss": 1.5098,
"step": 128
},
{
"epoch": 0.296551724137931,
"grad_norm": 0.19428691267967224,
"learning_rate": 2.9802088436081494e-05,
"loss": 1.5213,
"step": 129
},
{
"epoch": 0.2988505747126437,
"grad_norm": 0.21802888810634613,
"learning_rate": 2.9797575090694846e-05,
"loss": 1.5769,
"step": 130
},
{
"epoch": 0.30114942528735633,
"grad_norm": 0.2127716988325119,
"learning_rate": 2.9793011210301036e-05,
"loss": 1.558,
"step": 131
},
{
"epoch": 0.30344827586206896,
"grad_norm": 0.1973733901977539,
"learning_rate": 2.978839681048613e-05,
"loss": 1.5049,
"step": 132
},
{
"epoch": 0.3057471264367816,
"grad_norm": 0.21672004461288452,
"learning_rate": 2.9783731907008686e-05,
"loss": 1.6039,
"step": 133
},
{
"epoch": 0.3080459770114943,
"grad_norm": 0.2606683075428009,
"learning_rate": 2.9779016515799772e-05,
"loss": 1.5188,
"step": 134
},
{
"epoch": 0.3103448275862069,
"grad_norm": 0.22503024339675903,
"learning_rate": 2.977425065296285e-05,
"loss": 1.4091,
"step": 135
},
{
"epoch": 0.31264367816091954,
"grad_norm": 0.23185481131076813,
"learning_rate": 2.9769434334773753e-05,
"loss": 1.4243,
"step": 136
},
{
"epoch": 0.31494252873563217,
"grad_norm": 0.19816772639751434,
"learning_rate": 2.976456757768064e-05,
"loss": 1.6168,
"step": 137
},
{
"epoch": 0.31724137931034485,
"grad_norm": 0.2723851501941681,
"learning_rate": 2.97596503983039e-05,
"loss": 1.6332,
"step": 138
},
{
"epoch": 0.3195402298850575,
"grad_norm": 0.2749796211719513,
"learning_rate": 2.975468281343613e-05,
"loss": 1.3299,
"step": 139
},
{
"epoch": 0.3218390804597701,
"grad_norm": 0.30528461933135986,
"learning_rate": 2.9749664840042068e-05,
"loss": 1.3724,
"step": 140
},
{
"epoch": 0.32413793103448274,
"grad_norm": 0.19242194294929504,
"learning_rate": 2.974459649525853e-05,
"loss": 1.5917,
"step": 141
},
{
"epoch": 0.3264367816091954,
"grad_norm": 0.1887774020433426,
"learning_rate": 2.9739477796394345e-05,
"loss": 1.4494,
"step": 142
},
{
"epoch": 0.32873563218390806,
"grad_norm": 0.18469025194644928,
"learning_rate": 2.9734308760930333e-05,
"loss": 1.5302,
"step": 143
},
{
"epoch": 0.3310344827586207,
"grad_norm": 0.19204415380954742,
"learning_rate": 2.9729089406519185e-05,
"loss": 1.4373,
"step": 144
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.22177982330322266,
"learning_rate": 2.9723819750985456e-05,
"loss": 1.5731,
"step": 145
},
{
"epoch": 0.335632183908046,
"grad_norm": 0.3154543340206146,
"learning_rate": 2.9718499812325478e-05,
"loss": 1.4676,
"step": 146
},
{
"epoch": 0.33793103448275863,
"grad_norm": 0.2371883988380432,
"learning_rate": 2.9713129608707306e-05,
"loss": 1.4022,
"step": 147
},
{
"epoch": 0.34022988505747126,
"grad_norm": 0.18416638672351837,
"learning_rate": 2.970770915847065e-05,
"loss": 1.4383,
"step": 148
},
{
"epoch": 0.3425287356321839,
"grad_norm": 0.1935587376356125,
"learning_rate": 2.970223848012682e-05,
"loss": 1.7535,
"step": 149
},
{
"epoch": 0.3448275862068966,
"grad_norm": 0.18453308939933777,
"learning_rate": 2.969671759235866e-05,
"loss": 1.5818,
"step": 150
},
{
"epoch": 0.3471264367816092,
"grad_norm": 0.4305981695652008,
"learning_rate": 2.969114651402049e-05,
"loss": 1.5134,
"step": 151
},
{
"epoch": 0.34942528735632183,
"grad_norm": 0.246451273560524,
"learning_rate": 2.9685525264138013e-05,
"loss": 1.6639,
"step": 152
},
{
"epoch": 0.35172413793103446,
"grad_norm": 0.19947314262390137,
"learning_rate": 2.9679853861908294e-05,
"loss": 1.6807,
"step": 153
},
{
"epoch": 0.35402298850574715,
"grad_norm": 0.17848755419254303,
"learning_rate": 2.9674132326699668e-05,
"loss": 1.4965,
"step": 154
},
{
"epoch": 0.3563218390804598,
"grad_norm": 0.2055070549249649,
"learning_rate": 2.966836067805167e-05,
"loss": 1.4978,
"step": 155
},
{
"epoch": 0.3586206896551724,
"grad_norm": 0.18802429735660553,
"learning_rate": 2.9662538935674986e-05,
"loss": 1.7455,
"step": 156
},
{
"epoch": 0.36091954022988504,
"grad_norm": 0.2917739450931549,
"learning_rate": 2.965666711945137e-05,
"loss": 1.5253,
"step": 157
},
{
"epoch": 0.3632183908045977,
"grad_norm": 0.20041197538375854,
"learning_rate": 2.9650745249433595e-05,
"loss": 1.5816,
"step": 158
},
{
"epoch": 0.36551724137931035,
"grad_norm": 0.222783163189888,
"learning_rate": 2.964477334584535e-05,
"loss": 1.6189,
"step": 159
},
{
"epoch": 0.367816091954023,
"grad_norm": 0.17899613082408905,
"learning_rate": 2.9638751429081213e-05,
"loss": 1.3234,
"step": 160
},
{
"epoch": 0.3701149425287356,
"grad_norm": 0.2762451469898224,
"learning_rate": 2.9632679519706553e-05,
"loss": 1.6324,
"step": 161
},
{
"epoch": 0.3724137931034483,
"grad_norm": 0.2608356773853302,
"learning_rate": 2.9626557638457465e-05,
"loss": 1.5323,
"step": 162
},
{
"epoch": 0.37471264367816093,
"grad_norm": 0.21601971983909607,
"learning_rate": 2.9620385806240712e-05,
"loss": 1.47,
"step": 163
},
{
"epoch": 0.37701149425287356,
"grad_norm": 0.2666752338409424,
"learning_rate": 2.9614164044133635e-05,
"loss": 1.525,
"step": 164
},
{
"epoch": 0.3793103448275862,
"grad_norm": 0.19111081957817078,
"learning_rate": 2.9607892373384093e-05,
"loss": 1.6568,
"step": 165
},
{
"epoch": 0.3816091954022989,
"grad_norm": 0.2580263018608093,
"learning_rate": 2.9601570815410394e-05,
"loss": 1.5956,
"step": 166
},
{
"epoch": 0.3839080459770115,
"grad_norm": 0.17312514781951904,
"learning_rate": 2.9595199391801203e-05,
"loss": 1.6219,
"step": 167
},
{
"epoch": 0.38620689655172413,
"grad_norm": 0.2434745728969574,
"learning_rate": 2.9588778124315482e-05,
"loss": 1.6046,
"step": 168
},
{
"epoch": 0.38850574712643676,
"grad_norm": 0.19827675819396973,
"learning_rate": 2.9582307034882425e-05,
"loss": 1.6823,
"step": 169
},
{
"epoch": 0.39080459770114945,
"grad_norm": 0.18195027112960815,
"learning_rate": 2.9575786145601366e-05,
"loss": 1.5218,
"step": 170
},
{
"epoch": 0.3931034482758621,
"grad_norm": 0.19265489280223846,
"learning_rate": 2.9569215478741706e-05,
"loss": 1.4899,
"step": 171
},
{
"epoch": 0.3954022988505747,
"grad_norm": 0.19982010126113892,
"learning_rate": 2.956259505674285e-05,
"loss": 1.5444,
"step": 172
},
{
"epoch": 0.39770114942528734,
"grad_norm": 0.205831840634346,
"learning_rate": 2.955592490221411e-05,
"loss": 1.6583,
"step": 173
},
{
"epoch": 0.4,
"grad_norm": 0.18726621568202972,
"learning_rate": 2.9549205037934644e-05,
"loss": 1.528,
"step": 174
},
{
"epoch": 0.40229885057471265,
"grad_norm": 0.19567659497261047,
"learning_rate": 2.9542435486853375e-05,
"loss": 1.4926,
"step": 175
},
{
"epoch": 0.4045977011494253,
"grad_norm": 0.19164112210273743,
"learning_rate": 2.9535616272088917e-05,
"loss": 1.6581,
"step": 176
},
{
"epoch": 0.4068965517241379,
"grad_norm": 0.20306922495365143,
"learning_rate": 2.9528747416929467e-05,
"loss": 1.5799,
"step": 177
},
{
"epoch": 0.4091954022988506,
"grad_norm": 0.3285149335861206,
"learning_rate": 2.9521828944832776e-05,
"loss": 1.523,
"step": 178
},
{
"epoch": 0.4114942528735632,
"grad_norm": 0.20765793323516846,
"learning_rate": 2.951486087942602e-05,
"loss": 1.5063,
"step": 179
},
{
"epoch": 0.41379310344827586,
"grad_norm": 0.1997794359922409,
"learning_rate": 2.9507843244505757e-05,
"loss": 1.5787,
"step": 180
},
{
"epoch": 0.4160919540229885,
"grad_norm": 0.17902271449565887,
"learning_rate": 2.9500776064037813e-05,
"loss": 1.6037,
"step": 181
},
{
"epoch": 0.41839080459770117,
"grad_norm": 0.22518625855445862,
"learning_rate": 2.949365936215723e-05,
"loss": 1.5013,
"step": 182
},
{
"epoch": 0.4206896551724138,
"grad_norm": 0.19029757380485535,
"learning_rate": 2.9486493163168162e-05,
"loss": 1.4483,
"step": 183
},
{
"epoch": 0.42298850574712643,
"grad_norm": 0.18223826587200165,
"learning_rate": 2.9479277491543805e-05,
"loss": 1.401,
"step": 184
},
{
"epoch": 0.42528735632183906,
"grad_norm": 0.17190386354923248,
"learning_rate": 2.9472012371926304e-05,
"loss": 1.5885,
"step": 185
},
{
"epoch": 0.42758620689655175,
"grad_norm": 0.18991060554981232,
"learning_rate": 2.9464697829126672e-05,
"loss": 1.5913,
"step": 186
},
{
"epoch": 0.4298850574712644,
"grad_norm": 0.2093537151813507,
"learning_rate": 2.9457333888124715e-05,
"loss": 1.5961,
"step": 187
},
{
"epoch": 0.432183908045977,
"grad_norm": 0.21198369562625885,
"learning_rate": 2.9449920574068932e-05,
"loss": 1.4423,
"step": 188
},
{
"epoch": 0.43448275862068964,
"grad_norm": 0.19372902810573578,
"learning_rate": 2.9442457912276433e-05,
"loss": 1.4868,
"step": 189
},
{
"epoch": 0.4367816091954023,
"grad_norm": 0.1903308779001236,
"learning_rate": 2.9434945928232858e-05,
"loss": 1.4748,
"step": 190
},
{
"epoch": 0.43908045977011495,
"grad_norm": 0.18743303418159485,
"learning_rate": 2.942738464759229e-05,
"loss": 1.6275,
"step": 191
},
{
"epoch": 0.4413793103448276,
"grad_norm": 0.18451575934886932,
"learning_rate": 2.941977409617715e-05,
"loss": 1.5791,
"step": 192
},
{
"epoch": 0.4436781609195402,
"grad_norm": 0.19575345516204834,
"learning_rate": 2.941211429997815e-05,
"loss": 1.6363,
"step": 193
},
{
"epoch": 0.4459770114942529,
"grad_norm": 0.18840475380420685,
"learning_rate": 2.9404405285154146e-05,
"loss": 1.4679,
"step": 194
},
{
"epoch": 0.4482758620689655,
"grad_norm": 0.21825407445430756,
"learning_rate": 2.9396647078032105e-05,
"loss": 1.6299,
"step": 195
},
{
"epoch": 0.45057471264367815,
"grad_norm": 0.2002447247505188,
"learning_rate": 2.9388839705106975e-05,
"loss": 1.5971,
"step": 196
},
{
"epoch": 0.4528735632183908,
"grad_norm": 0.1966497004032135,
"learning_rate": 2.9380983193041613e-05,
"loss": 1.4369,
"step": 197
},
{
"epoch": 0.45517241379310347,
"grad_norm": 0.21710893511772156,
"learning_rate": 2.9373077568666698e-05,
"loss": 1.6347,
"step": 198
},
{
"epoch": 0.4574712643678161,
"grad_norm": 0.2616933286190033,
"learning_rate": 2.9365122858980616e-05,
"loss": 1.413,
"step": 199
},
{
"epoch": 0.45977011494252873,
"grad_norm": 0.202956423163414,
"learning_rate": 2.93571190911494e-05,
"loss": 1.5948,
"step": 200
},
{
"epoch": 0.46206896551724136,
"grad_norm": 0.20405063033103943,
"learning_rate": 2.9349066292506613e-05,
"loss": 1.5108,
"step": 201
},
{
"epoch": 0.46436781609195404,
"grad_norm": 0.21279285848140717,
"learning_rate": 2.9340964490553264e-05,
"loss": 1.522,
"step": 202
},
{
"epoch": 0.4666666666666667,
"grad_norm": 0.17347782850265503,
"learning_rate": 2.9332813712957705e-05,
"loss": 1.4932,
"step": 203
},
{
"epoch": 0.4689655172413793,
"grad_norm": 0.1769653856754303,
"learning_rate": 2.932461398755556e-05,
"loss": 1.6899,
"step": 204
},
{
"epoch": 0.47126436781609193,
"grad_norm": 0.18849113583564758,
"learning_rate": 2.9316365342349603e-05,
"loss": 1.5253,
"step": 205
},
{
"epoch": 0.4735632183908046,
"grad_norm": 0.19086049497127533,
"learning_rate": 2.9308067805509672e-05,
"loss": 1.6,
"step": 206
},
{
"epoch": 0.47586206896551725,
"grad_norm": 0.22243310511112213,
"learning_rate": 2.9299721405372585e-05,
"loss": 1.527,
"step": 207
},
{
"epoch": 0.4781609195402299,
"grad_norm": 0.20413143932819366,
"learning_rate": 2.9291326170442016e-05,
"loss": 1.496,
"step": 208
},
{
"epoch": 0.4804597701149425,
"grad_norm": 0.27051493525505066,
"learning_rate": 2.928288212938842e-05,
"loss": 1.4875,
"step": 209
},
{
"epoch": 0.4827586206896552,
"grad_norm": 0.19858244061470032,
"learning_rate": 2.927438931104895e-05,
"loss": 1.6859,
"step": 210
},
{
"epoch": 0.4850574712643678,
"grad_norm": 0.22106030583381653,
"learning_rate": 2.9265847744427305e-05,
"loss": 1.5115,
"step": 211
},
{
"epoch": 0.48735632183908045,
"grad_norm": 0.2160608172416687,
"learning_rate": 2.9257257458693682e-05,
"loss": 1.4681,
"step": 212
},
{
"epoch": 0.4896551724137931,
"grad_norm": 0.658218264579773,
"learning_rate": 2.9248618483184658e-05,
"loss": 1.538,
"step": 213
},
{
"epoch": 0.49195402298850577,
"grad_norm": 0.18368496000766754,
"learning_rate": 2.9239930847403083e-05,
"loss": 1.5704,
"step": 214
},
{
"epoch": 0.4942528735632184,
"grad_norm": 0.17574946582317352,
"learning_rate": 2.923119458101799e-05,
"loss": 1.5235,
"step": 215
},
{
"epoch": 0.496551724137931,
"grad_norm": 0.19917380809783936,
"learning_rate": 2.922240971386449e-05,
"loss": 1.6152,
"step": 216
},
{
"epoch": 0.49885057471264366,
"grad_norm": 0.16305314004421234,
"learning_rate": 2.9213576275943665e-05,
"loss": 1.5827,
"step": 217
},
{
"epoch": 0.5011494252873563,
"grad_norm": 0.19054944813251495,
"learning_rate": 2.9204694297422482e-05,
"loss": 1.4026,
"step": 218
},
{
"epoch": 0.5011494252873563,
"eval_loss": 2.2824206352233887,
"eval_runtime": 25.2204,
"eval_samples_per_second": 8.525,
"eval_steps_per_second": 0.555,
"step": 218
},
{
"epoch": 0.503448275862069,
"grad_norm": 0.20445501804351807,
"learning_rate": 2.9195763808633672e-05,
"loss": 1.5159,
"step": 219
},
{
"epoch": 0.5057471264367817,
"grad_norm": 0.17130975425243378,
"learning_rate": 2.918678484007562e-05,
"loss": 1.4964,
"step": 220
},
{
"epoch": 0.5080459770114942,
"grad_norm": 0.20928241312503815,
"learning_rate": 2.9177757422412294e-05,
"loss": 1.5437,
"step": 221
},
{
"epoch": 0.5103448275862069,
"grad_norm": 0.19081518054008484,
"learning_rate": 2.9168681586473106e-05,
"loss": 1.4357,
"step": 222
},
{
"epoch": 0.5126436781609195,
"grad_norm": 0.19667470455169678,
"learning_rate": 2.9159557363252838e-05,
"loss": 1.6565,
"step": 223
},
{
"epoch": 0.5149425287356322,
"grad_norm": 0.18910986185073853,
"learning_rate": 2.915038478391149e-05,
"loss": 1.522,
"step": 224
},
{
"epoch": 0.5172413793103449,
"grad_norm": 0.2085963785648346,
"learning_rate": 2.9141163879774234e-05,
"loss": 1.6788,
"step": 225
},
{
"epoch": 0.5195402298850574,
"grad_norm": 0.18078270554542542,
"learning_rate": 2.9131894682331245e-05,
"loss": 1.6741,
"step": 226
},
{
"epoch": 0.5218390804597701,
"grad_norm": 0.22367380559444427,
"learning_rate": 2.9122577223237653e-05,
"loss": 1.5036,
"step": 227
},
{
"epoch": 0.5241379310344828,
"grad_norm": 0.21635231375694275,
"learning_rate": 2.9113211534313385e-05,
"loss": 1.4944,
"step": 228
},
{
"epoch": 0.5264367816091954,
"grad_norm": 0.2017892450094223,
"learning_rate": 2.910379764754308e-05,
"loss": 1.8761,
"step": 229
},
{
"epoch": 0.5287356321839081,
"grad_norm": 0.2097645252943039,
"learning_rate": 2.9094335595075997e-05,
"loss": 1.4648,
"step": 230
},
{
"epoch": 0.5310344827586206,
"grad_norm": 0.19613298773765564,
"learning_rate": 2.908482540922585e-05,
"loss": 1.5537,
"step": 231
},
{
"epoch": 0.5333333333333333,
"grad_norm": 0.17055240273475647,
"learning_rate": 2.9075267122470758e-05,
"loss": 1.5733,
"step": 232
},
{
"epoch": 0.535632183908046,
"grad_norm": 0.3605201542377472,
"learning_rate": 2.906566076745311e-05,
"loss": 1.4766,
"step": 233
},
{
"epoch": 0.5379310344827586,
"grad_norm": 0.19592449069023132,
"learning_rate": 2.9056006376979437e-05,
"loss": 1.513,
"step": 234
},
{
"epoch": 0.5402298850574713,
"grad_norm": 0.1732814908027649,
"learning_rate": 2.9046303984020325e-05,
"loss": 1.4264,
"step": 235
},
{
"epoch": 0.542528735632184,
"grad_norm": 0.20567089319229126,
"learning_rate": 2.9036553621710288e-05,
"loss": 1.4883,
"step": 236
},
{
"epoch": 0.5448275862068965,
"grad_norm": 0.21223081648349762,
"learning_rate": 2.902675532334767e-05,
"loss": 1.6405,
"step": 237
},
{
"epoch": 0.5471264367816092,
"grad_norm": 0.21892322599887848,
"learning_rate": 2.90169091223945e-05,
"loss": 1.7308,
"step": 238
},
{
"epoch": 0.5494252873563218,
"grad_norm": 0.18415787816047668,
"learning_rate": 2.9007015052476425e-05,
"loss": 1.5607,
"step": 239
},
{
"epoch": 0.5517241379310345,
"grad_norm": 0.20931364595890045,
"learning_rate": 2.8997073147382547e-05,
"loss": 1.7103,
"step": 240
},
{
"epoch": 0.5540229885057472,
"grad_norm": 0.196925088763237,
"learning_rate": 2.8987083441065335e-05,
"loss": 1.4841,
"step": 241
},
{
"epoch": 0.5563218390804597,
"grad_norm": 0.19692716002464294,
"learning_rate": 2.8977045967640515e-05,
"loss": 1.6854,
"step": 242
},
{
"epoch": 0.5586206896551724,
"grad_norm": 0.2814970016479492,
"learning_rate": 2.8966960761386928e-05,
"loss": 1.4908,
"step": 243
},
{
"epoch": 0.5609195402298851,
"grad_norm": 0.17633461952209473,
"learning_rate": 2.895682785674643e-05,
"loss": 1.7045,
"step": 244
},
{
"epoch": 0.5632183908045977,
"grad_norm": 0.2070118486881256,
"learning_rate": 2.894664728832377e-05,
"loss": 1.5913,
"step": 245
},
{
"epoch": 0.5655172413793104,
"grad_norm": 0.17303098738193512,
"learning_rate": 2.8936419090886484e-05,
"loss": 1.671,
"step": 246
},
{
"epoch": 0.5678160919540229,
"grad_norm": 0.19265800714492798,
"learning_rate": 2.8926143299364745e-05,
"loss": 1.6094,
"step": 247
},
{
"epoch": 0.5701149425287356,
"grad_norm": 0.24474768340587616,
"learning_rate": 2.891581994885129e-05,
"loss": 1.5176,
"step": 248
},
{
"epoch": 0.5724137931034483,
"grad_norm": 0.2834344804286957,
"learning_rate": 2.8905449074601248e-05,
"loss": 1.5418,
"step": 249
},
{
"epoch": 0.5747126436781609,
"grad_norm": 0.19386981427669525,
"learning_rate": 2.889503071203206e-05,
"loss": 1.5267,
"step": 250
},
{
"epoch": 0.5770114942528736,
"grad_norm": 0.19057254493236542,
"learning_rate": 2.8884564896723345e-05,
"loss": 1.4453,
"step": 251
},
{
"epoch": 0.5793103448275863,
"grad_norm": 0.2260250449180603,
"learning_rate": 2.887405166441677e-05,
"loss": 1.5412,
"step": 252
},
{
"epoch": 0.5816091954022988,
"grad_norm": 0.19622193276882172,
"learning_rate": 2.886349105101594e-05,
"loss": 1.6258,
"step": 253
},
{
"epoch": 0.5839080459770115,
"grad_norm": 0.2061966061592102,
"learning_rate": 2.8852883092586264e-05,
"loss": 1.5939,
"step": 254
},
{
"epoch": 0.5862068965517241,
"grad_norm": 0.19955196976661682,
"learning_rate": 2.8842227825354857e-05,
"loss": 1.7664,
"step": 255
},
{
"epoch": 0.5885057471264368,
"grad_norm": 0.24448463320732117,
"learning_rate": 2.8831525285710364e-05,
"loss": 1.3442,
"step": 256
},
{
"epoch": 0.5908045977011495,
"grad_norm": 0.1870369166135788,
"learning_rate": 2.882077551020291e-05,
"loss": 1.3912,
"step": 257
},
{
"epoch": 0.593103448275862,
"grad_norm": 0.17911529541015625,
"learning_rate": 2.88099785355439e-05,
"loss": 1.58,
"step": 258
},
{
"epoch": 0.5954022988505747,
"grad_norm": 0.206022247672081,
"learning_rate": 2.879913439860595e-05,
"loss": 1.4448,
"step": 259
},
{
"epoch": 0.5977011494252874,
"grad_norm": 0.19694238901138306,
"learning_rate": 2.878824313642273e-05,
"loss": 1.478,
"step": 260
},
{
"epoch": 0.6,
"grad_norm": 0.17010873556137085,
"learning_rate": 2.8777304786188847e-05,
"loss": 1.4349,
"step": 261
},
{
"epoch": 0.6022988505747127,
"grad_norm": 0.19739097356796265,
"learning_rate": 2.8766319385259717e-05,
"loss": 1.5758,
"step": 262
},
{
"epoch": 0.6045977011494252,
"grad_norm": 0.196018785238266,
"learning_rate": 2.8755286971151447e-05,
"loss": 1.4977,
"step": 263
},
{
"epoch": 0.6068965517241379,
"grad_norm": 0.16239720582962036,
"learning_rate": 2.8744207581540686e-05,
"loss": 1.5372,
"step": 264
},
{
"epoch": 0.6091954022988506,
"grad_norm": 0.18915416300296783,
"learning_rate": 2.8733081254264518e-05,
"loss": 1.5605,
"step": 265
},
{
"epoch": 0.6114942528735632,
"grad_norm": 0.20293830335140228,
"learning_rate": 2.8721908027320315e-05,
"loss": 1.6384,
"step": 266
},
{
"epoch": 0.6137931034482759,
"grad_norm": 0.7928096652030945,
"learning_rate": 2.8710687938865624e-05,
"loss": 1.6019,
"step": 267
},
{
"epoch": 0.6160919540229886,
"grad_norm": 0.21928972005844116,
"learning_rate": 2.869942102721802e-05,
"loss": 1.6336,
"step": 268
},
{
"epoch": 0.6183908045977011,
"grad_norm": 0.20363996922969818,
"learning_rate": 2.8688107330854992e-05,
"loss": 1.4864,
"step": 269
},
{
"epoch": 0.6206896551724138,
"grad_norm": 0.21159179508686066,
"learning_rate": 2.8676746888413792e-05,
"loss": 1.626,
"step": 270
},
{
"epoch": 0.6229885057471264,
"grad_norm": 0.18884380161762238,
"learning_rate": 2.8665339738691326e-05,
"loss": 1.6014,
"step": 271
},
{
"epoch": 0.6252873563218391,
"grad_norm": 0.18361367285251617,
"learning_rate": 2.8653885920644e-05,
"loss": 1.4524,
"step": 272
},
{
"epoch": 0.6275862068965518,
"grad_norm": 0.16966724395751953,
"learning_rate": 2.86423854733876e-05,
"loss": 1.6177,
"step": 273
},
{
"epoch": 0.6298850574712643,
"grad_norm": 0.18425606191158295,
"learning_rate": 2.863083843619715e-05,
"loss": 1.6304,
"step": 274
},
{
"epoch": 0.632183908045977,
"grad_norm": 0.205034077167511,
"learning_rate": 2.8619244848506797e-05,
"loss": 1.3749,
"step": 275
},
{
"epoch": 0.6344827586206897,
"grad_norm": 0.1978350430727005,
"learning_rate": 2.8607604749909647e-05,
"loss": 1.5757,
"step": 276
},
{
"epoch": 0.6367816091954023,
"grad_norm": 0.17334821820259094,
"learning_rate": 2.8595918180157648e-05,
"loss": 1.5297,
"step": 277
},
{
"epoch": 0.639080459770115,
"grad_norm": 0.21464063227176666,
"learning_rate": 2.8584185179161457e-05,
"loss": 1.6198,
"step": 278
},
{
"epoch": 0.6413793103448275,
"grad_norm": 0.21049116551876068,
"learning_rate": 2.8572405786990293e-05,
"loss": 1.5821,
"step": 279
},
{
"epoch": 0.6436781609195402,
"grad_norm": 0.21829204261302948,
"learning_rate": 2.8560580043871808e-05,
"loss": 1.3784,
"step": 280
},
{
"epoch": 0.6459770114942529,
"grad_norm": 0.1938474029302597,
"learning_rate": 2.8548707990191933e-05,
"loss": 1.5445,
"step": 281
},
{
"epoch": 0.6482758620689655,
"grad_norm": 0.2118452936410904,
"learning_rate": 2.853678966649478e-05,
"loss": 1.5428,
"step": 282
},
{
"epoch": 0.6505747126436782,
"grad_norm": 0.24130851030349731,
"learning_rate": 2.852482511348245e-05,
"loss": 1.6268,
"step": 283
},
{
"epoch": 0.6528735632183909,
"grad_norm": 0.20688006281852722,
"learning_rate": 2.851281437201494e-05,
"loss": 1.6642,
"step": 284
},
{
"epoch": 0.6551724137931034,
"grad_norm": 0.20292113721370697,
"learning_rate": 2.8500757483109977e-05,
"loss": 1.4183,
"step": 285
},
{
"epoch": 0.6574712643678161,
"grad_norm": 0.18396663665771484,
"learning_rate": 2.8488654487942885e-05,
"loss": 1.5558,
"step": 286
},
{
"epoch": 0.6597701149425287,
"grad_norm": 0.23628288507461548,
"learning_rate": 2.8476505427846443e-05,
"loss": 1.4014,
"step": 287
},
{
"epoch": 0.6620689655172414,
"grad_norm": 0.18764841556549072,
"learning_rate": 2.846431034431076e-05,
"loss": 1.439,
"step": 288
},
{
"epoch": 0.664367816091954,
"grad_norm": 0.2228286862373352,
"learning_rate": 2.8452069278983095e-05,
"loss": 1.5919,
"step": 289
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.21330665051937103,
"learning_rate": 2.8439782273667755e-05,
"loss": 1.4919,
"step": 290
},
{
"epoch": 0.6689655172413793,
"grad_norm": 0.18442875146865845,
"learning_rate": 2.8427449370325938e-05,
"loss": 1.37,
"step": 291
},
{
"epoch": 0.671264367816092,
"grad_norm": 0.19341664016246796,
"learning_rate": 2.8415070611075575e-05,
"loss": 1.3518,
"step": 292
},
{
"epoch": 0.6735632183908046,
"grad_norm": 0.225533127784729,
"learning_rate": 2.8402646038191212e-05,
"loss": 1.6061,
"step": 293
},
{
"epoch": 0.6758620689655173,
"grad_norm": 0.2696436941623688,
"learning_rate": 2.8390175694103852e-05,
"loss": 1.5768,
"step": 294
},
{
"epoch": 0.6781609195402298,
"grad_norm": 0.25022217631340027,
"learning_rate": 2.8377659621400794e-05,
"loss": 1.337,
"step": 295
},
{
"epoch": 0.6804597701149425,
"grad_norm": 0.26814812421798706,
"learning_rate": 2.8365097862825516e-05,
"loss": 1.7392,
"step": 296
},
{
"epoch": 0.6827586206896552,
"grad_norm": 0.2581053674221039,
"learning_rate": 2.835249046127753e-05,
"loss": 1.5165,
"step": 297
},
{
"epoch": 0.6850574712643678,
"grad_norm": 0.18305552005767822,
"learning_rate": 2.8339837459812202e-05,
"loss": 1.4269,
"step": 298
},
{
"epoch": 0.6873563218390805,
"grad_norm": 0.1749197542667389,
"learning_rate": 2.8327138901640632e-05,
"loss": 1.368,
"step": 299
},
{
"epoch": 0.6896551724137931,
"grad_norm": 0.16818371415138245,
"learning_rate": 2.8314394830129505e-05,
"loss": 1.4152,
"step": 300
},
{
"epoch": 0.6919540229885057,
"grad_norm": 0.16995173692703247,
"learning_rate": 2.830160528880093e-05,
"loss": 1.4784,
"step": 301
},
{
"epoch": 0.6942528735632184,
"grad_norm": 0.19039668142795563,
"learning_rate": 2.8288770321332307e-05,
"loss": 1.3605,
"step": 302
},
{
"epoch": 0.696551724137931,
"grad_norm": 0.19171744585037231,
"learning_rate": 2.8275889971556167e-05,
"loss": 1.5314,
"step": 303
},
{
"epoch": 0.6988505747126437,
"grad_norm": 0.20389091968536377,
"learning_rate": 2.826296428346003e-05,
"loss": 1.4642,
"step": 304
},
{
"epoch": 0.7011494252873564,
"grad_norm": 0.17727336287498474,
"learning_rate": 2.8249993301186244e-05,
"loss": 1.6588,
"step": 305
},
{
"epoch": 0.7034482758620689,
"grad_norm": 0.17864014208316803,
"learning_rate": 2.8236977069031838e-05,
"loss": 1.4938,
"step": 306
},
{
"epoch": 0.7057471264367816,
"grad_norm": 0.19913828372955322,
"learning_rate": 2.822391563144838e-05,
"loss": 1.6352,
"step": 307
},
{
"epoch": 0.7080459770114943,
"grad_norm": 0.203240767121315,
"learning_rate": 2.821080903304182e-05,
"loss": 1.5064,
"step": 308
},
{
"epoch": 0.7103448275862069,
"grad_norm": 0.16706302762031555,
"learning_rate": 2.8197657318572326e-05,
"loss": 1.5739,
"step": 309
},
{
"epoch": 0.7126436781609196,
"grad_norm": 0.1778131127357483,
"learning_rate": 2.8184460532954152e-05,
"loss": 1.4593,
"step": 310
},
{
"epoch": 0.7149425287356321,
"grad_norm": 0.19013363122940063,
"learning_rate": 2.8171218721255468e-05,
"loss": 1.3718,
"step": 311
},
{
"epoch": 0.7172413793103448,
"grad_norm": 0.17926853895187378,
"learning_rate": 2.815793192869822e-05,
"loss": 1.628,
"step": 312
},
{
"epoch": 0.7195402298850575,
"grad_norm": 0.22089271247386932,
"learning_rate": 2.8144600200657953e-05,
"loss": 1.4963,
"step": 313
},
{
"epoch": 0.7218390804597701,
"grad_norm": 0.21324951946735382,
"learning_rate": 2.8131223582663687e-05,
"loss": 1.5972,
"step": 314
},
{
"epoch": 0.7241379310344828,
"grad_norm": 0.18063107132911682,
"learning_rate": 2.811780212039773e-05,
"loss": 1.615,
"step": 315
},
{
"epoch": 0.7264367816091954,
"grad_norm": 0.2106839269399643,
"learning_rate": 2.8104335859695545e-05,
"loss": 1.7129,
"step": 316
},
{
"epoch": 0.728735632183908,
"grad_norm": 0.19900445640087128,
"learning_rate": 2.8090824846545583e-05,
"loss": 1.6241,
"step": 317
},
{
"epoch": 0.7310344827586207,
"grad_norm": 0.19344286620616913,
"learning_rate": 2.807726912708914e-05,
"loss": 1.5673,
"step": 318
},
{
"epoch": 0.7333333333333333,
"grad_norm": 0.2059333771467209,
"learning_rate": 2.806366874762017e-05,
"loss": 1.5415,
"step": 319
},
{
"epoch": 0.735632183908046,
"grad_norm": 0.23455306887626648,
"learning_rate": 2.805002375458515e-05,
"loss": 1.4997,
"step": 320
},
{
"epoch": 0.7379310344827587,
"grad_norm": 0.2209428995847702,
"learning_rate": 2.8036334194582924e-05,
"loss": 1.4683,
"step": 321
},
{
"epoch": 0.7402298850574712,
"grad_norm": 0.2665802240371704,
"learning_rate": 2.8022600114364534e-05,
"loss": 1.3659,
"step": 322
},
{
"epoch": 0.7425287356321839,
"grad_norm": 0.2058359831571579,
"learning_rate": 2.800882156083305e-05,
"loss": 1.41,
"step": 323
},
{
"epoch": 0.7448275862068966,
"grad_norm": 0.1997438669204712,
"learning_rate": 2.7994998581043443e-05,
"loss": 1.5762,
"step": 324
},
{
"epoch": 0.7471264367816092,
"grad_norm": 0.20264290273189545,
"learning_rate": 2.7981131222202387e-05,
"loss": 1.5485,
"step": 325
},
{
"epoch": 0.7494252873563219,
"grad_norm": 0.21155625581741333,
"learning_rate": 2.7967219531668118e-05,
"loss": 1.6362,
"step": 326
},
{
"epoch": 0.7517241379310344,
"grad_norm": 0.17439904808998108,
"learning_rate": 2.7953263556950273e-05,
"loss": 1.6573,
"step": 327
},
{
"epoch": 0.7517241379310344,
"eval_loss": 2.2581052780151367,
"eval_runtime": 24.7946,
"eval_samples_per_second": 8.671,
"eval_steps_per_second": 0.565,
"step": 327
},
{
"epoch": 0.7540229885057471,
"grad_norm": 0.18361178040504456,
"learning_rate": 2.793926334570972e-05,
"loss": 1.2546,
"step": 328
},
{
"epoch": 0.7563218390804598,
"grad_norm": 0.2303590178489685,
"learning_rate": 2.7925218945758396e-05,
"loss": 1.5352,
"step": 329
},
{
"epoch": 0.7586206896551724,
"grad_norm": 0.23574653267860413,
"learning_rate": 2.7911130405059155e-05,
"loss": 1.6258,
"step": 330
},
{
"epoch": 0.7609195402298851,
"grad_norm": 0.18484550714492798,
"learning_rate": 2.7896997771725588e-05,
"loss": 1.4507,
"step": 331
},
{
"epoch": 0.7632183908045977,
"grad_norm": 0.18624041974544525,
"learning_rate": 2.7882821094021864e-05,
"loss": 1.5138,
"step": 332
},
{
"epoch": 0.7655172413793103,
"grad_norm": 0.18977145850658417,
"learning_rate": 2.7868600420362576e-05,
"loss": 1.5012,
"step": 333
},
{
"epoch": 0.767816091954023,
"grad_norm": 0.18062737584114075,
"learning_rate": 2.7854335799312566e-05,
"loss": 1.5509,
"step": 334
},
{
"epoch": 0.7701149425287356,
"grad_norm": 0.2696746289730072,
"learning_rate": 2.784002727958675e-05,
"loss": 1.5426,
"step": 335
},
{
"epoch": 0.7724137931034483,
"grad_norm": 0.18752269446849823,
"learning_rate": 2.7825674910049968e-05,
"loss": 1.5908,
"step": 336
},
{
"epoch": 0.774712643678161,
"grad_norm": 0.19890910387039185,
"learning_rate": 2.7811278739716816e-05,
"loss": 1.5495,
"step": 337
},
{
"epoch": 0.7770114942528735,
"grad_norm": 0.18307459354400635,
"learning_rate": 2.7796838817751467e-05,
"loss": 1.5245,
"step": 338
},
{
"epoch": 0.7793103448275862,
"grad_norm": 0.17525285482406616,
"learning_rate": 2.778235519346751e-05,
"loss": 1.6004,
"step": 339
},
{
"epoch": 0.7816091954022989,
"grad_norm": 0.1960344910621643,
"learning_rate": 2.7767827916327787e-05,
"loss": 1.4949,
"step": 340
},
{
"epoch": 0.7839080459770115,
"grad_norm": 0.17853619158267975,
"learning_rate": 2.7753257035944216e-05,
"loss": 1.5535,
"step": 341
},
{
"epoch": 0.7862068965517242,
"grad_norm": 0.17083661258220673,
"learning_rate": 2.773864260207761e-05,
"loss": 1.461,
"step": 342
},
{
"epoch": 0.7885057471264367,
"grad_norm": 0.17479828000068665,
"learning_rate": 2.7723984664637545e-05,
"loss": 1.4954,
"step": 343
},
{
"epoch": 0.7908045977011494,
"grad_norm": 0.2625036835670471,
"learning_rate": 2.770928327368215e-05,
"loss": 1.3964,
"step": 344
},
{
"epoch": 0.7931034482758621,
"grad_norm": 0.22769753634929657,
"learning_rate": 2.769453847941795e-05,
"loss": 1.3916,
"step": 345
},
{
"epoch": 0.7954022988505747,
"grad_norm": 0.19266977906227112,
"learning_rate": 2.7679750332199707e-05,
"loss": 1.4965,
"step": 346
},
{
"epoch": 0.7977011494252874,
"grad_norm": 0.19969883561134338,
"learning_rate": 2.7664918882530227e-05,
"loss": 1.5231,
"step": 347
},
{
"epoch": 0.8,
"grad_norm": 0.19699935615062714,
"learning_rate": 2.7650044181060202e-05,
"loss": 1.6496,
"step": 348
},
{
"epoch": 0.8022988505747126,
"grad_norm": 0.2416319102048874,
"learning_rate": 2.7635126278588042e-05,
"loss": 1.4772,
"step": 349
},
{
"epoch": 0.8045977011494253,
"grad_norm": 0.18814043700695038,
"learning_rate": 2.762016522605967e-05,
"loss": 1.5088,
"step": 350
},
{
"epoch": 0.8068965517241379,
"grad_norm": 0.21547584235668182,
"learning_rate": 2.760516107456839e-05,
"loss": 1.4792,
"step": 351
},
{
"epoch": 0.8091954022988506,
"grad_norm": 0.1696031093597412,
"learning_rate": 2.7590113875354684e-05,
"loss": 1.5588,
"step": 352
},
{
"epoch": 0.8114942528735632,
"grad_norm": 0.19598573446273804,
"learning_rate": 2.7575023679806044e-05,
"loss": 1.3997,
"step": 353
},
{
"epoch": 0.8137931034482758,
"grad_norm": 0.1826913207769394,
"learning_rate": 2.7559890539456808e-05,
"loss": 1.432,
"step": 354
},
{
"epoch": 0.8160919540229885,
"grad_norm": 0.20719464123249054,
"learning_rate": 2.754471450598796e-05,
"loss": 1.4608,
"step": 355
},
{
"epoch": 0.8183908045977012,
"grad_norm": 0.2266138643026352,
"learning_rate": 2.752949563122698e-05,
"loss": 1.6123,
"step": 356
},
{
"epoch": 0.8206896551724138,
"grad_norm": 0.20128245651721954,
"learning_rate": 2.7514233967147652e-05,
"loss": 1.7266,
"step": 357
},
{
"epoch": 0.8229885057471265,
"grad_norm": 0.18546128273010254,
"learning_rate": 2.749892956586989e-05,
"loss": 1.4787,
"step": 358
},
{
"epoch": 0.825287356321839,
"grad_norm": 0.2048066109418869,
"learning_rate": 2.7483582479659545e-05,
"loss": 1.6225,
"step": 359
},
{
"epoch": 0.8275862068965517,
"grad_norm": 0.19592110812664032,
"learning_rate": 2.746819276092826e-05,
"loss": 1.6216,
"step": 360
},
{
"epoch": 0.8298850574712644,
"grad_norm": 0.17077720165252686,
"learning_rate": 2.745276046223326e-05,
"loss": 1.5412,
"step": 361
},
{
"epoch": 0.832183908045977,
"grad_norm": 0.20424050092697144,
"learning_rate": 2.74372856362772e-05,
"loss": 1.6018,
"step": 362
},
{
"epoch": 0.8344827586206897,
"grad_norm": 0.19228434562683105,
"learning_rate": 2.7421768335907942e-05,
"loss": 1.6863,
"step": 363
},
{
"epoch": 0.8367816091954023,
"grad_norm": 0.18955634534358978,
"learning_rate": 2.7406208614118427e-05,
"loss": 1.5339,
"step": 364
},
{
"epoch": 0.8390804597701149,
"grad_norm": 0.2024989128112793,
"learning_rate": 2.7390606524046462e-05,
"loss": 1.5823,
"step": 365
},
{
"epoch": 0.8413793103448276,
"grad_norm": 0.1808302104473114,
"learning_rate": 2.7374962118974533e-05,
"loss": 1.6178,
"step": 366
},
{
"epoch": 0.8436781609195402,
"grad_norm": 0.25428861379623413,
"learning_rate": 2.7359275452329657e-05,
"loss": 1.5141,
"step": 367
},
{
"epoch": 0.8459770114942529,
"grad_norm": 0.19765780866146088,
"learning_rate": 2.734354657768316e-05,
"loss": 1.55,
"step": 368
},
{
"epoch": 0.8482758620689655,
"grad_norm": 0.1827484667301178,
"learning_rate": 2.7327775548750516e-05,
"loss": 1.6114,
"step": 369
},
{
"epoch": 0.8505747126436781,
"grad_norm": 0.17866359651088715,
"learning_rate": 2.7311962419391164e-05,
"loss": 1.4726,
"step": 370
},
{
"epoch": 0.8528735632183908,
"grad_norm": 0.18344362080097198,
"learning_rate": 2.729610724360832e-05,
"loss": 1.4964,
"step": 371
},
{
"epoch": 0.8551724137931035,
"grad_norm": 0.19222599267959595,
"learning_rate": 2.7280210075548784e-05,
"loss": 1.5168,
"step": 372
},
{
"epoch": 0.8574712643678161,
"grad_norm": 0.18410854041576385,
"learning_rate": 2.726427096950277e-05,
"loss": 1.5264,
"step": 373
},
{
"epoch": 0.8597701149425288,
"grad_norm": 0.20303085446357727,
"learning_rate": 2.724828997990372e-05,
"loss": 1.4673,
"step": 374
},
{
"epoch": 0.8620689655172413,
"grad_norm": 0.19090887904167175,
"learning_rate": 2.72322671613281e-05,
"loss": 1.6077,
"step": 375
},
{
"epoch": 0.864367816091954,
"grad_norm": 0.26263174414634705,
"learning_rate": 2.7216202568495227e-05,
"loss": 1.3828,
"step": 376
},
{
"epoch": 0.8666666666666667,
"grad_norm": 0.19087761640548706,
"learning_rate": 2.7200096256267087e-05,
"loss": 1.4027,
"step": 377
},
{
"epoch": 0.8689655172413793,
"grad_norm": 0.18839100003242493,
"learning_rate": 2.718394827964814e-05,
"loss": 1.3651,
"step": 378
},
{
"epoch": 0.871264367816092,
"grad_norm": 0.20130708813667297,
"learning_rate": 2.716775869378513e-05,
"loss": 1.5589,
"step": 379
},
{
"epoch": 0.8735632183908046,
"grad_norm": 0.19122594594955444,
"learning_rate": 2.7151527553966903e-05,
"loss": 1.3604,
"step": 380
},
{
"epoch": 0.8758620689655172,
"grad_norm": 0.21470162272453308,
"learning_rate": 2.7135254915624213e-05,
"loss": 1.3683,
"step": 381
},
{
"epoch": 0.8781609195402299,
"grad_norm": 0.1866234391927719,
"learning_rate": 2.7118940834329535e-05,
"loss": 1.5383,
"step": 382
},
{
"epoch": 0.8804597701149425,
"grad_norm": 0.21003670990467072,
"learning_rate": 2.710258536579688e-05,
"loss": 1.3652,
"step": 383
},
{
"epoch": 0.8827586206896552,
"grad_norm": 0.3734110891819,
"learning_rate": 2.70861885658816e-05,
"loss": 1.4374,
"step": 384
},
{
"epoch": 0.8850574712643678,
"grad_norm": 0.3391740620136261,
"learning_rate": 2.706975049058019e-05,
"loss": 1.4359,
"step": 385
},
{
"epoch": 0.8873563218390804,
"grad_norm": 0.18111281096935272,
"learning_rate": 2.7053271196030103e-05,
"loss": 1.505,
"step": 386
},
{
"epoch": 0.8896551724137931,
"grad_norm": 0.32430529594421387,
"learning_rate": 2.703675073850958e-05,
"loss": 1.6701,
"step": 387
},
{
"epoch": 0.8919540229885058,
"grad_norm": 0.23176854848861694,
"learning_rate": 2.7020189174437405e-05,
"loss": 1.6119,
"step": 388
},
{
"epoch": 0.8942528735632184,
"grad_norm": 0.19289056956768036,
"learning_rate": 2.7003586560372768e-05,
"loss": 1.4551,
"step": 389
},
{
"epoch": 0.896551724137931,
"grad_norm": 0.2000240683555603,
"learning_rate": 2.6986942953015043e-05,
"loss": 1.4728,
"step": 390
},
{
"epoch": 0.8988505747126436,
"grad_norm": 0.19711917638778687,
"learning_rate": 2.6970258409203596e-05,
"loss": 1.4702,
"step": 391
},
{
"epoch": 0.9011494252873563,
"grad_norm": 0.19048166275024414,
"learning_rate": 2.6953532985917595e-05,
"loss": 1.5124,
"step": 392
},
{
"epoch": 0.903448275862069,
"grad_norm": 0.1823759227991104,
"learning_rate": 2.6936766740275818e-05,
"loss": 1.5782,
"step": 393
},
{
"epoch": 0.9057471264367816,
"grad_norm": 0.32403135299682617,
"learning_rate": 2.6919959729536458e-05,
"loss": 1.5246,
"step": 394
},
{
"epoch": 0.9080459770114943,
"grad_norm": 0.18626323342323303,
"learning_rate": 2.6903112011096914e-05,
"loss": 1.495,
"step": 395
},
{
"epoch": 0.9103448275862069,
"grad_norm": 0.19439269602298737,
"learning_rate": 2.688622364249361e-05,
"loss": 1.345,
"step": 396
},
{
"epoch": 0.9126436781609195,
"grad_norm": 0.21047940850257874,
"learning_rate": 2.6869294681401798e-05,
"loss": 1.5771,
"step": 397
},
{
"epoch": 0.9149425287356322,
"grad_norm": 0.34387603402137756,
"learning_rate": 2.6852325185635357e-05,
"loss": 1.5482,
"step": 398
},
{
"epoch": 0.9172413793103448,
"grad_norm": 0.19977940618991852,
"learning_rate": 2.6835315213146586e-05,
"loss": 1.4504,
"step": 399
},
{
"epoch": 0.9195402298850575,
"grad_norm": 0.19440104067325592,
"learning_rate": 2.6818264822026026e-05,
"loss": 1.7115,
"step": 400
},
{
"epoch": 0.9218390804597701,
"grad_norm": 0.18868982791900635,
"learning_rate": 2.6801174070502248e-05,
"loss": 1.3848,
"step": 401
},
{
"epoch": 0.9241379310344827,
"grad_norm": 0.17231613397598267,
"learning_rate": 2.6784043016941656e-05,
"loss": 1.5376,
"step": 402
},
{
"epoch": 0.9264367816091954,
"grad_norm": 0.19504061341285706,
"learning_rate": 2.6766871719848284e-05,
"loss": 1.6811,
"step": 403
},
{
"epoch": 0.9287356321839081,
"grad_norm": 0.17492131888866425,
"learning_rate": 2.6749660237863612e-05,
"loss": 1.6218,
"step": 404
},
{
"epoch": 0.9310344827586207,
"grad_norm": 0.1997053325176239,
"learning_rate": 2.6732408629766344e-05,
"loss": 1.6273,
"step": 405
},
{
"epoch": 0.9333333333333333,
"grad_norm": 0.18289603292942047,
"learning_rate": 2.6715116954472234e-05,
"loss": 1.5621,
"step": 406
},
{
"epoch": 0.9356321839080459,
"grad_norm": 0.19396287202835083,
"learning_rate": 2.6697785271033842e-05,
"loss": 1.2912,
"step": 407
},
{
"epoch": 0.9379310344827586,
"grad_norm": 0.1871613711118698,
"learning_rate": 2.6680413638640394e-05,
"loss": 1.5291,
"step": 408
},
{
"epoch": 0.9402298850574713,
"grad_norm": 0.17659619450569153,
"learning_rate": 2.6663002116617515e-05,
"loss": 1.596,
"step": 409
},
{
"epoch": 0.9425287356321839,
"grad_norm": 0.2125513255596161,
"learning_rate": 2.664555076442707e-05,
"loss": 1.5239,
"step": 410
},
{
"epoch": 0.9448275862068966,
"grad_norm": 0.17410100996494293,
"learning_rate": 2.6628059641666947e-05,
"loss": 1.5228,
"step": 411
},
{
"epoch": 0.9471264367816092,
"grad_norm": 0.16883061826229095,
"learning_rate": 2.6610528808070857e-05,
"loss": 1.5093,
"step": 412
},
{
"epoch": 0.9494252873563218,
"grad_norm": 0.2219240665435791,
"learning_rate": 2.659295832350812e-05,
"loss": 1.3804,
"step": 413
},
{
"epoch": 0.9517241379310345,
"grad_norm": 0.2025938779115677,
"learning_rate": 2.657534824798346e-05,
"loss": 1.4901,
"step": 414
},
{
"epoch": 0.9540229885057471,
"grad_norm": 0.21257524192333221,
"learning_rate": 2.655769864163684e-05,
"loss": 1.5115,
"step": 415
},
{
"epoch": 0.9563218390804598,
"grad_norm": 0.18569877743721008,
"learning_rate": 2.6540009564743186e-05,
"loss": 1.5241,
"step": 416
},
{
"epoch": 0.9586206896551724,
"grad_norm": 0.18792696297168732,
"learning_rate": 2.6522281077712237e-05,
"loss": 1.6364,
"step": 417
},
{
"epoch": 0.960919540229885,
"grad_norm": 0.16503970324993134,
"learning_rate": 2.650451324108832e-05,
"loss": 1.5259,
"step": 418
},
{
"epoch": 0.9632183908045977,
"grad_norm": 0.17835144698619843,
"learning_rate": 2.6486706115550152e-05,
"loss": 1.5109,
"step": 419
},
{
"epoch": 0.9655172413793104,
"grad_norm": 0.20384320616722107,
"learning_rate": 2.646885976191061e-05,
"loss": 1.5824,
"step": 420
},
{
"epoch": 0.967816091954023,
"grad_norm": 0.17631903290748596,
"learning_rate": 2.6450974241116545e-05,
"loss": 1.5405,
"step": 421
},
{
"epoch": 0.9701149425287356,
"grad_norm": 0.1788354218006134,
"learning_rate": 2.643304961424857e-05,
"loss": 1.5368,
"step": 422
},
{
"epoch": 0.9724137931034482,
"grad_norm": 0.1732684075832367,
"learning_rate": 2.641508594252084e-05,
"loss": 1.3928,
"step": 423
},
{
"epoch": 0.9747126436781609,
"grad_norm": 0.19117887318134308,
"learning_rate": 2.639708328728087e-05,
"loss": 1.3744,
"step": 424
},
{
"epoch": 0.9770114942528736,
"grad_norm": 0.22916676104068756,
"learning_rate": 2.6379041710009283e-05,
"loss": 1.434,
"step": 425
},
{
"epoch": 0.9793103448275862,
"grad_norm": 0.18841995298862457,
"learning_rate": 2.6360961272319643e-05,
"loss": 1.5632,
"step": 426
},
{
"epoch": 0.9816091954022989,
"grad_norm": 0.18780235946178436,
"learning_rate": 2.6342842035958215e-05,
"loss": 1.5137,
"step": 427
},
{
"epoch": 0.9839080459770115,
"grad_norm": 0.21761077642440796,
"learning_rate": 2.6324684062803768e-05,
"loss": 1.6862,
"step": 428
},
{
"epoch": 0.9862068965517241,
"grad_norm": 0.20078086853027344,
"learning_rate": 2.6306487414867367e-05,
"loss": 1.5312,
"step": 429
},
{
"epoch": 0.9885057471264368,
"grad_norm": 0.1899338960647583,
"learning_rate": 2.6288252154292143e-05,
"loss": 1.7545,
"step": 430
},
{
"epoch": 0.9908045977011494,
"grad_norm": 0.18865884840488434,
"learning_rate": 2.6269978343353103e-05,
"loss": 1.5403,
"step": 431
},
{
"epoch": 0.993103448275862,
"grad_norm": 0.18721292912960052,
"learning_rate": 2.6251666044456895e-05,
"loss": 1.5109,
"step": 432
},
{
"epoch": 0.9954022988505747,
"grad_norm": 0.19300366938114166,
"learning_rate": 2.623331532014162e-05,
"loss": 1.5299,
"step": 433
},
{
"epoch": 0.9977011494252873,
"grad_norm": 0.17586664855480194,
"learning_rate": 2.6214926233076596e-05,
"loss": 1.4818,
"step": 434
},
{
"epoch": 1.0,
"grad_norm": 0.1846192181110382,
"learning_rate": 2.619649884606216e-05,
"loss": 1.467,
"step": 435
},
{
"epoch": 1.0022988505747126,
"grad_norm": 0.19920676946640015,
"learning_rate": 2.617803322202944e-05,
"loss": 1.587,
"step": 436
},
{
"epoch": 1.0022988505747126,
"eval_loss": 2.2424099445343018,
"eval_runtime": 24.6813,
"eval_samples_per_second": 8.711,
"eval_steps_per_second": 0.567,
"step": 436
},
{
"epoch": 1.0045977011494254,
"grad_norm": 0.17951138317584991,
"learning_rate": 2.6159529424040152e-05,
"loss": 1.5239,
"step": 437
},
{
"epoch": 1.006896551724138,
"grad_norm": 0.17600172758102417,
"learning_rate": 2.6140987515286368e-05,
"loss": 1.4123,
"step": 438
},
{
"epoch": 1.0091954022988505,
"grad_norm": 0.1901494413614273,
"learning_rate": 2.612240755909034e-05,
"loss": 1.375,
"step": 439
},
{
"epoch": 1.0114942528735633,
"grad_norm": 0.18664933741092682,
"learning_rate": 2.6103789618904212e-05,
"loss": 1.4077,
"step": 440
},
{
"epoch": 1.013793103448276,
"grad_norm": 0.18296094238758087,
"learning_rate": 2.6085133758309887e-05,
"loss": 1.2304,
"step": 441
},
{
"epoch": 1.0160919540229885,
"grad_norm": 0.18246351182460785,
"learning_rate": 2.606644004101875e-05,
"loss": 1.5893,
"step": 442
},
{
"epoch": 1.018390804597701,
"grad_norm": 0.1839461624622345,
"learning_rate": 2.6047708530871466e-05,
"loss": 1.7963,
"step": 443
},
{
"epoch": 1.0206896551724138,
"grad_norm": 0.3928722143173218,
"learning_rate": 2.6028939291837783e-05,
"loss": 1.642,
"step": 444
},
{
"epoch": 1.0229885057471264,
"grad_norm": 0.17699632048606873,
"learning_rate": 2.601013238801628e-05,
"loss": 1.4775,
"step": 445
},
{
"epoch": 1.025287356321839,
"grad_norm": 0.17887839674949646,
"learning_rate": 2.5991287883634173e-05,
"loss": 1.5849,
"step": 446
},
{
"epoch": 1.0275862068965518,
"grad_norm": 0.2123589962720871,
"learning_rate": 2.597240584304708e-05,
"loss": 1.3949,
"step": 447
},
{
"epoch": 1.0298850574712644,
"grad_norm": 0.1909758448600769,
"learning_rate": 2.595348633073882e-05,
"loss": 1.4768,
"step": 448
},
{
"epoch": 1.032183908045977,
"grad_norm": 0.20288285613059998,
"learning_rate": 2.5934529411321174e-05,
"loss": 1.449,
"step": 449
},
{
"epoch": 1.0344827586206897,
"grad_norm": 0.17669205367565155,
"learning_rate": 2.5915535149533667e-05,
"loss": 1.5509,
"step": 450
},
{
"epoch": 1.0367816091954023,
"grad_norm": 0.1899123340845108,
"learning_rate": 2.5896503610243362e-05,
"loss": 1.4966,
"step": 451
},
{
"epoch": 1.0390804597701149,
"grad_norm": 0.18714012205600739,
"learning_rate": 2.5877434858444623e-05,
"loss": 1.5139,
"step": 452
},
{
"epoch": 1.0413793103448277,
"grad_norm": 0.1939937174320221,
"learning_rate": 2.585832895925889e-05,
"loss": 1.5004,
"step": 453
},
{
"epoch": 1.0436781609195402,
"grad_norm": 0.19414936006069183,
"learning_rate": 2.583918597793448e-05,
"loss": 1.6026,
"step": 454
},
{
"epoch": 1.0459770114942528,
"grad_norm": 0.19046179950237274,
"learning_rate": 2.582000597984633e-05,
"loss": 1.4502,
"step": 455
},
{
"epoch": 1.0482758620689656,
"grad_norm": 0.20748762786388397,
"learning_rate": 2.580078903049582e-05,
"loss": 1.6354,
"step": 456
},
{
"epoch": 1.0505747126436782,
"grad_norm": 0.1758117377758026,
"learning_rate": 2.578153519551049e-05,
"loss": 1.6335,
"step": 457
},
{
"epoch": 1.0528735632183908,
"grad_norm": 0.17251557111740112,
"learning_rate": 2.576224454064387e-05,
"loss": 1.5272,
"step": 458
},
{
"epoch": 1.0551724137931036,
"grad_norm": 0.18571054935455322,
"learning_rate": 2.5742917131775227e-05,
"loss": 1.3825,
"step": 459
},
{
"epoch": 1.0574712643678161,
"grad_norm": 0.2120322287082672,
"learning_rate": 2.572355303490934e-05,
"loss": 1.5367,
"step": 460
},
{
"epoch": 1.0597701149425287,
"grad_norm": 0.21388618648052216,
"learning_rate": 2.5704152316176287e-05,
"loss": 1.6139,
"step": 461
},
{
"epoch": 1.0620689655172413,
"grad_norm": 0.208335742354393,
"learning_rate": 2.568471504183121e-05,
"loss": 1.4389,
"step": 462
},
{
"epoch": 1.064367816091954,
"grad_norm": 0.19265100359916687,
"learning_rate": 2.5665241278254096e-05,
"loss": 1.5455,
"step": 463
},
{
"epoch": 1.0666666666666667,
"grad_norm": 0.21192842721939087,
"learning_rate": 2.5645731091949542e-05,
"loss": 1.4247,
"step": 464
},
{
"epoch": 1.0689655172413792,
"grad_norm": 0.19817666709423065,
"learning_rate": 2.5626184549546535e-05,
"loss": 1.4795,
"step": 465
},
{
"epoch": 1.071264367816092,
"grad_norm": 0.19475719332695007,
"learning_rate": 2.5606601717798212e-05,
"loss": 1.6022,
"step": 466
},
{
"epoch": 1.0735632183908046,
"grad_norm": 0.18997976183891296,
"learning_rate": 2.5586982663581655e-05,
"loss": 1.4705,
"step": 467
},
{
"epoch": 1.0758620689655172,
"grad_norm": 0.17738305032253265,
"learning_rate": 2.5567327453897644e-05,
"loss": 1.4985,
"step": 468
},
{
"epoch": 1.07816091954023,
"grad_norm": 0.1642778068780899,
"learning_rate": 2.554763615587042e-05,
"loss": 1.4678,
"step": 469
},
{
"epoch": 1.0804597701149425,
"grad_norm": 0.19081969559192657,
"learning_rate": 2.5527908836747492e-05,
"loss": 1.6873,
"step": 470
},
{
"epoch": 1.0827586206896551,
"grad_norm": 0.19890892505645752,
"learning_rate": 2.5508145563899364e-05,
"loss": 1.4902,
"step": 471
},
{
"epoch": 1.085057471264368,
"grad_norm": 0.18225252628326416,
"learning_rate": 2.548834640481934e-05,
"loss": 1.2756,
"step": 472
},
{
"epoch": 1.0873563218390805,
"grad_norm": 0.1741209626197815,
"learning_rate": 2.5468511427123264e-05,
"loss": 1.5775,
"step": 473
},
{
"epoch": 1.089655172413793,
"grad_norm": 0.16915111243724823,
"learning_rate": 2.544864069854932e-05,
"loss": 1.6355,
"step": 474
},
{
"epoch": 1.0919540229885056,
"grad_norm": 0.18193410336971283,
"learning_rate": 2.542873428695777e-05,
"loss": 1.5925,
"step": 475
},
{
"epoch": 1.0942528735632184,
"grad_norm": 0.17539438605308533,
"learning_rate": 2.5408792260330746e-05,
"loss": 1.6416,
"step": 476
},
{
"epoch": 1.096551724137931,
"grad_norm": 0.21445949375629425,
"learning_rate": 2.5388814686772e-05,
"loss": 1.4386,
"step": 477
},
{
"epoch": 1.0988505747126436,
"grad_norm": 0.18149080872535706,
"learning_rate": 2.536880163450669e-05,
"loss": 1.5481,
"step": 478
},
{
"epoch": 1.1011494252873564,
"grad_norm": 0.21017950773239136,
"learning_rate": 2.5348753171881137e-05,
"loss": 1.4857,
"step": 479
},
{
"epoch": 1.103448275862069,
"grad_norm": 0.19322200119495392,
"learning_rate": 2.532866936736257e-05,
"loss": 1.5321,
"step": 480
},
{
"epoch": 1.1057471264367815,
"grad_norm": 0.199620321393013,
"learning_rate": 2.530855028953894e-05,
"loss": 1.5783,
"step": 481
},
{
"epoch": 1.1080459770114943,
"grad_norm": 0.1887032836675644,
"learning_rate": 2.528839600711865e-05,
"loss": 1.504,
"step": 482
},
{
"epoch": 1.110344827586207,
"grad_norm": 0.1904177963733673,
"learning_rate": 2.5268206588930332e-05,
"loss": 1.4799,
"step": 483
},
{
"epoch": 1.1126436781609195,
"grad_norm": 0.18373800814151764,
"learning_rate": 2.5247982103922598e-05,
"loss": 1.5968,
"step": 484
},
{
"epoch": 1.1149425287356323,
"grad_norm": 0.18844591081142426,
"learning_rate": 2.522772262116383e-05,
"loss": 1.611,
"step": 485
},
{
"epoch": 1.1172413793103448,
"grad_norm": 0.21098919212818146,
"learning_rate": 2.5207428209841925e-05,
"loss": 1.4789,
"step": 486
},
{
"epoch": 1.1195402298850574,
"grad_norm": 0.1811923384666443,
"learning_rate": 2.5187098939264064e-05,
"loss": 1.4954,
"step": 487
},
{
"epoch": 1.1218390804597702,
"grad_norm": 0.20556038618087769,
"learning_rate": 2.5166734878856474e-05,
"loss": 1.5531,
"step": 488
},
{
"epoch": 1.1241379310344828,
"grad_norm": 0.18028612434864044,
"learning_rate": 2.5146336098164195e-05,
"loss": 1.3443,
"step": 489
},
{
"epoch": 1.1264367816091954,
"grad_norm": 0.19548887014389038,
"learning_rate": 2.5125902666850843e-05,
"loss": 1.6089,
"step": 490
},
{
"epoch": 1.1287356321839082,
"grad_norm": 0.18403364717960358,
"learning_rate": 2.510543465469836e-05,
"loss": 1.4687,
"step": 491
},
{
"epoch": 1.1310344827586207,
"grad_norm": 0.19192993640899658,
"learning_rate": 2.508493213160679e-05,
"loss": 1.496,
"step": 492
},
{
"epoch": 1.1333333333333333,
"grad_norm": 0.20319294929504395,
"learning_rate": 2.5064395167594037e-05,
"loss": 1.6872,
"step": 493
},
{
"epoch": 1.1356321839080459,
"grad_norm": 0.1924794316291809,
"learning_rate": 2.5043823832795616e-05,
"loss": 1.4849,
"step": 494
},
{
"epoch": 1.1379310344827587,
"grad_norm": 0.178504079580307,
"learning_rate": 2.502321819746443e-05,
"loss": 1.4512,
"step": 495
},
{
"epoch": 1.1402298850574712,
"grad_norm": 0.17655041813850403,
"learning_rate": 2.500257833197052e-05,
"loss": 1.7281,
"step": 496
},
{
"epoch": 1.1425287356321838,
"grad_norm": 0.18397659063339233,
"learning_rate": 2.498190430680082e-05,
"loss": 1.4352,
"step": 497
},
{
"epoch": 1.1448275862068966,
"grad_norm": 0.19358468055725098,
"learning_rate": 2.4961196192558924e-05,
"loss": 1.5055,
"step": 498
},
{
"epoch": 1.1471264367816092,
"grad_norm": 0.19119885563850403,
"learning_rate": 2.4940454059964844e-05,
"loss": 1.6555,
"step": 499
},
{
"epoch": 1.1494252873563218,
"grad_norm": 0.17836236953735352,
"learning_rate": 2.491967797985478e-05,
"loss": 1.5815,
"step": 500
},
{
"epoch": 1.1517241379310346,
"grad_norm": 0.18401266634464264,
"learning_rate": 2.4898868023180844e-05,
"loss": 1.4338,
"step": 501
},
{
"epoch": 1.1540229885057471,
"grad_norm": 0.19115357100963593,
"learning_rate": 2.4878024261010845e-05,
"loss": 1.5077,
"step": 502
},
{
"epoch": 1.1563218390804597,
"grad_norm": 0.17622840404510498,
"learning_rate": 2.485714676452805e-05,
"loss": 1.4336,
"step": 503
},
{
"epoch": 1.1586206896551725,
"grad_norm": 0.17741276323795319,
"learning_rate": 2.483623560503094e-05,
"loss": 1.4782,
"step": 504
},
{
"epoch": 1.160919540229885,
"grad_norm": 0.2652662992477417,
"learning_rate": 2.4815290853932924e-05,
"loss": 1.6103,
"step": 505
},
{
"epoch": 1.1632183908045977,
"grad_norm": 0.18884335458278656,
"learning_rate": 2.4794312582762165e-05,
"loss": 1.6267,
"step": 506
},
{
"epoch": 1.1655172413793102,
"grad_norm": 0.18492935597896576,
"learning_rate": 2.477330086316128e-05,
"loss": 1.5227,
"step": 507
},
{
"epoch": 1.167816091954023,
"grad_norm": 0.19032172858715057,
"learning_rate": 2.475225576688712e-05,
"loss": 1.4278,
"step": 508
},
{
"epoch": 1.1701149425287356,
"grad_norm": 0.1816961020231247,
"learning_rate": 2.4731177365810526e-05,
"loss": 1.3952,
"step": 509
},
{
"epoch": 1.1724137931034484,
"grad_norm": 0.18908639252185822,
"learning_rate": 2.4710065731916067e-05,
"loss": 1.5689,
"step": 510
},
{
"epoch": 1.174712643678161,
"grad_norm": 0.19389130175113678,
"learning_rate": 2.4688920937301812e-05,
"loss": 1.5451,
"step": 511
},
{
"epoch": 1.1770114942528735,
"grad_norm": 0.19861985743045807,
"learning_rate": 2.4667743054179075e-05,
"loss": 1.5875,
"step": 512
},
{
"epoch": 1.1793103448275861,
"grad_norm": 0.2147730439901352,
"learning_rate": 2.464653215487217e-05,
"loss": 1.4581,
"step": 513
},
{
"epoch": 1.181609195402299,
"grad_norm": 0.18973737955093384,
"learning_rate": 2.4625288311818168e-05,
"loss": 1.4877,
"step": 514
},
{
"epoch": 1.1839080459770115,
"grad_norm": 0.1921122670173645,
"learning_rate": 2.4604011597566644e-05,
"loss": 1.3518,
"step": 515
},
{
"epoch": 1.186206896551724,
"grad_norm": 0.1912504881620407,
"learning_rate": 2.458270208477942e-05,
"loss": 1.4809,
"step": 516
},
{
"epoch": 1.1885057471264369,
"grad_norm": 0.18589767813682556,
"learning_rate": 2.4561359846230346e-05,
"loss": 1.4578,
"step": 517
},
{
"epoch": 1.1908045977011494,
"grad_norm": 0.17742007970809937,
"learning_rate": 2.4539984954805023e-05,
"loss": 1.286,
"step": 518
},
{
"epoch": 1.193103448275862,
"grad_norm": 0.17479638755321503,
"learning_rate": 2.4518577483500565e-05,
"loss": 1.5269,
"step": 519
},
{
"epoch": 1.1954022988505748,
"grad_norm": 0.19213594496250153,
"learning_rate": 2.4497137505425347e-05,
"loss": 1.7029,
"step": 520
},
{
"epoch": 1.1977011494252874,
"grad_norm": 0.19730371236801147,
"learning_rate": 2.4475665093798766e-05,
"loss": 1.4455,
"step": 521
},
{
"epoch": 1.2,
"grad_norm": 0.20502667129039764,
"learning_rate": 2.4454160321950973e-05,
"loss": 1.532,
"step": 522
},
{
"epoch": 1.2022988505747128,
"grad_norm": 0.3687721788883209,
"learning_rate": 2.443262326332264e-05,
"loss": 1.5503,
"step": 523
},
{
"epoch": 1.2045977011494253,
"grad_norm": 0.20593665540218353,
"learning_rate": 2.441105399146469e-05,
"loss": 1.674,
"step": 524
},
{
"epoch": 1.206896551724138,
"grad_norm": 0.1837199330329895,
"learning_rate": 2.4389452580038075e-05,
"loss": 1.5844,
"step": 525
},
{
"epoch": 1.2091954022988505,
"grad_norm": 0.18324591219425201,
"learning_rate": 2.4367819102813492e-05,
"loss": 1.548,
"step": 526
},
{
"epoch": 1.2114942528735633,
"grad_norm": 0.1887226104736328,
"learning_rate": 2.4346153633671137e-05,
"loss": 1.4427,
"step": 527
},
{
"epoch": 1.2137931034482758,
"grad_norm": 0.18387746810913086,
"learning_rate": 2.4324456246600487e-05,
"loss": 1.4186,
"step": 528
},
{
"epoch": 1.2160919540229884,
"grad_norm": 0.19124281406402588,
"learning_rate": 2.4302727015700004e-05,
"loss": 1.4066,
"step": 529
},
{
"epoch": 1.2183908045977012,
"grad_norm": 0.18245410919189453,
"learning_rate": 2.4280966015176903e-05,
"loss": 1.4503,
"step": 530
},
{
"epoch": 1.2206896551724138,
"grad_norm": 0.18176697194576263,
"learning_rate": 2.4259173319346894e-05,
"loss": 1.4911,
"step": 531
},
{
"epoch": 1.2229885057471264,
"grad_norm": 0.2285512387752533,
"learning_rate": 2.4237349002633934e-05,
"loss": 1.3263,
"step": 532
},
{
"epoch": 1.2252873563218392,
"grad_norm": 0.18840406835079193,
"learning_rate": 2.421549313956996e-05,
"loss": 1.6583,
"step": 533
},
{
"epoch": 1.2275862068965517,
"grad_norm": 0.1896274983882904,
"learning_rate": 2.419360580479465e-05,
"loss": 1.6112,
"step": 534
},
{
"epoch": 1.2298850574712643,
"grad_norm": 0.18891143798828125,
"learning_rate": 2.4171687073055154e-05,
"loss": 1.328,
"step": 535
},
{
"epoch": 1.232183908045977,
"grad_norm": 0.2316858023405075,
"learning_rate": 2.414973701920585e-05,
"loss": 1.6478,
"step": 536
},
{
"epoch": 1.2344827586206897,
"grad_norm": 0.17436787486076355,
"learning_rate": 2.4127755718208092e-05,
"loss": 1.4956,
"step": 537
},
{
"epoch": 1.2367816091954023,
"grad_norm": 0.7482878565788269,
"learning_rate": 2.4105743245129925e-05,
"loss": 1.3817,
"step": 538
},
{
"epoch": 1.2390804597701148,
"grad_norm": 0.18221990764141083,
"learning_rate": 2.408369967514586e-05,
"loss": 1.4785,
"step": 539
},
{
"epoch": 1.2413793103448276,
"grad_norm": 0.21372325718402863,
"learning_rate": 2.406162508353662e-05,
"loss": 1.5874,
"step": 540
},
{
"epoch": 1.2436781609195402,
"grad_norm": 0.18980319797992706,
"learning_rate": 2.4039519545688848e-05,
"loss": 1.3447,
"step": 541
},
{
"epoch": 1.245977011494253,
"grad_norm": 0.2008126825094223,
"learning_rate": 2.401738313709488e-05,
"loss": 1.3493,
"step": 542
},
{
"epoch": 1.2482758620689656,
"grad_norm": 0.18841980397701263,
"learning_rate": 2.399521593335248e-05,
"loss": 1.5396,
"step": 543
},
{
"epoch": 1.2505747126436781,
"grad_norm": 0.18760916590690613,
"learning_rate": 2.3973018010164577e-05,
"loss": 1.6343,
"step": 544
},
{
"epoch": 1.2528735632183907,
"grad_norm": 0.20947614312171936,
"learning_rate": 2.3950789443339014e-05,
"loss": 1.2928,
"step": 545
},
{
"epoch": 1.2528735632183907,
"eval_loss": 2.2228856086730957,
"eval_runtime": 24.7314,
"eval_samples_per_second": 8.693,
"eval_steps_per_second": 0.566,
"step": 545
},
{
"epoch": 1.2551724137931035,
"grad_norm": 0.19504812359809875,
"learning_rate": 2.3928530308788282e-05,
"loss": 1.5574,
"step": 546
},
{
"epoch": 1.257471264367816,
"grad_norm": 0.17835503816604614,
"learning_rate": 2.3906240682529263e-05,
"loss": 1.433,
"step": 547
},
{
"epoch": 1.2597701149425287,
"grad_norm": 0.1863379180431366,
"learning_rate": 2.388392064068297e-05,
"loss": 1.2436,
"step": 548
},
{
"epoch": 1.2620689655172415,
"grad_norm": 0.18111759424209595,
"learning_rate": 2.3861570259474286e-05,
"loss": 1.4295,
"step": 549
},
{
"epoch": 1.264367816091954,
"grad_norm": 0.2355654388666153,
"learning_rate": 2.3839189615231712e-05,
"loss": 1.2904,
"step": 550
},
{
"epoch": 1.2666666666666666,
"grad_norm": 0.17872202396392822,
"learning_rate": 2.3816778784387097e-05,
"loss": 1.5191,
"step": 551
},
{
"epoch": 1.2689655172413792,
"grad_norm": 0.18010634183883667,
"learning_rate": 2.379433784347538e-05,
"loss": 1.5727,
"step": 552
},
{
"epoch": 1.271264367816092,
"grad_norm": 0.2086629867553711,
"learning_rate": 2.3771866869134326e-05,
"loss": 1.416,
"step": 553
},
{
"epoch": 1.2735632183908046,
"grad_norm": 0.2663419842720032,
"learning_rate": 2.3749365938104267e-05,
"loss": 1.4289,
"step": 554
},
{
"epoch": 1.2758620689655173,
"grad_norm": 0.20872661471366882,
"learning_rate": 2.3726835127227846e-05,
"loss": 1.6117,
"step": 555
},
{
"epoch": 1.27816091954023,
"grad_norm": 0.20745250582695007,
"learning_rate": 2.3704274513449738e-05,
"loss": 1.6815,
"step": 556
},
{
"epoch": 1.2804597701149425,
"grad_norm": 0.19453871250152588,
"learning_rate": 2.3681684173816406e-05,
"loss": 1.5978,
"step": 557
},
{
"epoch": 1.282758620689655,
"grad_norm": 0.18708713352680206,
"learning_rate": 2.3659064185475828e-05,
"loss": 1.4262,
"step": 558
},
{
"epoch": 1.2850574712643679,
"grad_norm": 0.2028874009847641,
"learning_rate": 2.3636414625677232e-05,
"loss": 1.7654,
"step": 559
},
{
"epoch": 1.2873563218390804,
"grad_norm": 0.18763355910778046,
"learning_rate": 2.361373557177083e-05,
"loss": 1.4206,
"step": 560
},
{
"epoch": 1.2896551724137932,
"grad_norm": 0.4665738344192505,
"learning_rate": 2.3591027101207578e-05,
"loss": 1.3996,
"step": 561
},
{
"epoch": 1.2919540229885058,
"grad_norm": 0.20351774990558624,
"learning_rate": 2.3568289291538873e-05,
"loss": 1.4113,
"step": 562
},
{
"epoch": 1.2942528735632184,
"grad_norm": 0.19278672337532043,
"learning_rate": 2.3545522220416317e-05,
"loss": 1.1836,
"step": 563
},
{
"epoch": 1.296551724137931,
"grad_norm": 0.22900599241256714,
"learning_rate": 2.3522725965591437e-05,
"loss": 1.4154,
"step": 564
},
{
"epoch": 1.2988505747126438,
"grad_norm": 0.2706981301307678,
"learning_rate": 2.3499900604915425e-05,
"loss": 1.5164,
"step": 565
},
{
"epoch": 1.3011494252873563,
"grad_norm": 0.18947027623653412,
"learning_rate": 2.3477046216338877e-05,
"loss": 1.5232,
"step": 566
},
{
"epoch": 1.303448275862069,
"grad_norm": 0.18985944986343384,
"learning_rate": 2.3454162877911526e-05,
"loss": 1.4562,
"step": 567
},
{
"epoch": 1.3057471264367817,
"grad_norm": 0.19388991594314575,
"learning_rate": 2.3431250667781958e-05,
"loss": 1.3529,
"step": 568
},
{
"epoch": 1.3080459770114943,
"grad_norm": 0.22105787694454193,
"learning_rate": 2.3408309664197367e-05,
"loss": 1.3394,
"step": 569
},
{
"epoch": 1.3103448275862069,
"grad_norm": 0.19226060807704926,
"learning_rate": 2.3385339945503283e-05,
"loss": 1.5056,
"step": 570
},
{
"epoch": 1.3126436781609194,
"grad_norm": 0.20840789377689362,
"learning_rate": 2.3362341590143284e-05,
"loss": 1.5664,
"step": 571
},
{
"epoch": 1.3149425287356322,
"grad_norm": 0.19241869449615479,
"learning_rate": 2.3339314676658762e-05,
"loss": 1.212,
"step": 572
},
{
"epoch": 1.3172413793103448,
"grad_norm": 0.1949642300605774,
"learning_rate": 2.3316259283688634e-05,
"loss": 1.6513,
"step": 573
},
{
"epoch": 1.3195402298850576,
"grad_norm": 0.2004053145647049,
"learning_rate": 2.3293175489969065e-05,
"loss": 1.3426,
"step": 574
},
{
"epoch": 1.3218390804597702,
"grad_norm": 0.23403388261795044,
"learning_rate": 2.327006337433323e-05,
"loss": 1.5881,
"step": 575
},
{
"epoch": 1.3241379310344827,
"grad_norm": 0.18916146457195282,
"learning_rate": 2.3246923015711007e-05,
"loss": 1.473,
"step": 576
},
{
"epoch": 1.3264367816091953,
"grad_norm": 0.20339609682559967,
"learning_rate": 2.322375449312875e-05,
"loss": 1.3954,
"step": 577
},
{
"epoch": 1.328735632183908,
"grad_norm": 0.1784183531999588,
"learning_rate": 2.3200557885708958e-05,
"loss": 1.4445,
"step": 578
},
{
"epoch": 1.3310344827586207,
"grad_norm": 0.18920187652111053,
"learning_rate": 2.3177333272670086e-05,
"loss": 1.4964,
"step": 579
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.20495089888572693,
"learning_rate": 2.3154080733326195e-05,
"loss": 1.5131,
"step": 580
},
{
"epoch": 1.335632183908046,
"grad_norm": 0.17198073863983154,
"learning_rate": 2.313080034708674e-05,
"loss": 1.4992,
"step": 581
},
{
"epoch": 1.3379310344827586,
"grad_norm": 0.1907850056886673,
"learning_rate": 2.3107492193456264e-05,
"loss": 1.4954,
"step": 582
},
{
"epoch": 1.3402298850574712,
"grad_norm": 0.17182083427906036,
"learning_rate": 2.3084156352034138e-05,
"loss": 1.5322,
"step": 583
},
{
"epoch": 1.3425287356321838,
"grad_norm": 0.19156919419765472,
"learning_rate": 2.30607929025143e-05,
"loss": 1.5674,
"step": 584
},
{
"epoch": 1.3448275862068966,
"grad_norm": 0.2362571656703949,
"learning_rate": 2.303740192468495e-05,
"loss": 1.5514,
"step": 585
},
{
"epoch": 1.3471264367816091,
"grad_norm": 0.1819256693124771,
"learning_rate": 2.3013983498428325e-05,
"loss": 1.3483,
"step": 586
},
{
"epoch": 1.349425287356322,
"grad_norm": 0.19172576069831848,
"learning_rate": 2.2990537703720388e-05,
"loss": 1.5348,
"step": 587
},
{
"epoch": 1.3517241379310345,
"grad_norm": 0.17328503727912903,
"learning_rate": 2.2967064620630565e-05,
"loss": 1.5762,
"step": 588
},
{
"epoch": 1.354022988505747,
"grad_norm": 0.23111514747142792,
"learning_rate": 2.2943564329321483e-05,
"loss": 1.3427,
"step": 589
},
{
"epoch": 1.3563218390804597,
"grad_norm": 0.2115740329027176,
"learning_rate": 2.2920036910048677e-05,
"loss": 1.5999,
"step": 590
},
{
"epoch": 1.3586206896551725,
"grad_norm": 0.22690510749816895,
"learning_rate": 2.2896482443160337e-05,
"loss": 1.3643,
"step": 591
},
{
"epoch": 1.360919540229885,
"grad_norm": 0.18678870797157288,
"learning_rate": 2.2872901009097017e-05,
"loss": 1.4952,
"step": 592
},
{
"epoch": 1.3632183908045978,
"grad_norm": 0.19824892282485962,
"learning_rate": 2.2849292688391367e-05,
"loss": 1.5405,
"step": 593
},
{
"epoch": 1.3655172413793104,
"grad_norm": 0.19464600086212158,
"learning_rate": 2.2825657561667855e-05,
"loss": 1.6054,
"step": 594
},
{
"epoch": 1.367816091954023,
"grad_norm": 0.24339468777179718,
"learning_rate": 2.2801995709642498e-05,
"loss": 1.455,
"step": 595
},
{
"epoch": 1.3701149425287356,
"grad_norm": 0.2208542823791504,
"learning_rate": 2.277830721312258e-05,
"loss": 1.4178,
"step": 596
},
{
"epoch": 1.3724137931034484,
"grad_norm": 0.1914588361978531,
"learning_rate": 2.275459215300638e-05,
"loss": 1.445,
"step": 597
},
{
"epoch": 1.374712643678161,
"grad_norm": 0.2223386913537979,
"learning_rate": 2.2730850610282898e-05,
"loss": 1.3647,
"step": 598
},
{
"epoch": 1.3770114942528735,
"grad_norm": 0.1851610690355301,
"learning_rate": 2.2707082666031556e-05,
"loss": 1.3051,
"step": 599
},
{
"epoch": 1.3793103448275863,
"grad_norm": 0.21137797832489014,
"learning_rate": 2.2683288401421965e-05,
"loss": 1.5523,
"step": 600
},
{
"epoch": 1.3816091954022989,
"grad_norm": 0.24737273156642914,
"learning_rate": 2.2659467897713604e-05,
"loss": 1.4368,
"step": 601
},
{
"epoch": 1.3839080459770114,
"grad_norm": 0.19528579711914062,
"learning_rate": 2.263562123625557e-05,
"loss": 1.4595,
"step": 602
},
{
"epoch": 1.386206896551724,
"grad_norm": 0.18836459517478943,
"learning_rate": 2.2611748498486286e-05,
"loss": 1.6737,
"step": 603
},
{
"epoch": 1.3885057471264368,
"grad_norm": 0.194894477725029,
"learning_rate": 2.258784976593323e-05,
"loss": 1.6571,
"step": 604
},
{
"epoch": 1.3908045977011494,
"grad_norm": 0.210275337100029,
"learning_rate": 2.256392512021265e-05,
"loss": 1.7278,
"step": 605
},
{
"epoch": 1.3931034482758622,
"grad_norm": 0.18894609808921814,
"learning_rate": 2.2539974643029307e-05,
"loss": 1.5193,
"step": 606
},
{
"epoch": 1.3954022988505748,
"grad_norm": 0.18696676194667816,
"learning_rate": 2.2515998416176148e-05,
"loss": 1.4753,
"step": 607
},
{
"epoch": 1.3977011494252873,
"grad_norm": 0.18523529171943665,
"learning_rate": 2.249199652153409e-05,
"loss": 1.5216,
"step": 608
},
{
"epoch": 1.4,
"grad_norm": 0.21934500336647034,
"learning_rate": 2.2467969041071683e-05,
"loss": 1.1858,
"step": 609
},
{
"epoch": 1.4022988505747127,
"grad_norm": 0.17950807511806488,
"learning_rate": 2.244391605684487e-05,
"loss": 1.3019,
"step": 610
},
{
"epoch": 1.4045977011494253,
"grad_norm": 0.1807120144367218,
"learning_rate": 2.2419837650996685e-05,
"loss": 1.4672,
"step": 611
},
{
"epoch": 1.4068965517241379,
"grad_norm": 0.20445270836353302,
"learning_rate": 2.2395733905756976e-05,
"loss": 1.44,
"step": 612
},
{
"epoch": 1.4091954022988507,
"grad_norm": 0.17994698882102966,
"learning_rate": 2.237160490344214e-05,
"loss": 1.5779,
"step": 613
},
{
"epoch": 1.4114942528735632,
"grad_norm": 0.188873291015625,
"learning_rate": 2.234745072645481e-05,
"loss": 1.5586,
"step": 614
},
{
"epoch": 1.4137931034482758,
"grad_norm": 0.22609154880046844,
"learning_rate": 2.232327145728361e-05,
"loss": 1.5005,
"step": 615
},
{
"epoch": 1.4160919540229884,
"grad_norm": 0.20559628307819366,
"learning_rate": 2.2299067178502843e-05,
"loss": 1.553,
"step": 616
},
{
"epoch": 1.4183908045977012,
"grad_norm": 0.18155494332313538,
"learning_rate": 2.2274837972772237e-05,
"loss": 1.5227,
"step": 617
},
{
"epoch": 1.4206896551724137,
"grad_norm": 0.19194115698337555,
"learning_rate": 2.225058392283664e-05,
"loss": 1.4647,
"step": 618
},
{
"epoch": 1.4229885057471265,
"grad_norm": 0.18746960163116455,
"learning_rate": 2.222630511152573e-05,
"loss": 1.5693,
"step": 619
},
{
"epoch": 1.4252873563218391,
"grad_norm": 0.2009705901145935,
"learning_rate": 2.2202001621753776e-05,
"loss": 1.4721,
"step": 620
},
{
"epoch": 1.4275862068965517,
"grad_norm": 0.20158328115940094,
"learning_rate": 2.2177673536519297e-05,
"loss": 1.5124,
"step": 621
},
{
"epoch": 1.4298850574712643,
"grad_norm": 0.2076476514339447,
"learning_rate": 2.215332093890484e-05,
"loss": 1.4335,
"step": 622
},
{
"epoch": 1.432183908045977,
"grad_norm": 0.19029493629932404,
"learning_rate": 2.212894391207663e-05,
"loss": 1.6409,
"step": 623
},
{
"epoch": 1.4344827586206896,
"grad_norm": 0.188816100358963,
"learning_rate": 2.210454253928434e-05,
"loss": 1.4165,
"step": 624
},
{
"epoch": 1.4367816091954024,
"grad_norm": 0.4629051387310028,
"learning_rate": 2.2080116903860794e-05,
"loss": 1.3993,
"step": 625
},
{
"epoch": 1.439080459770115,
"grad_norm": 0.3404623866081238,
"learning_rate": 2.2055667089221642e-05,
"loss": 1.6518,
"step": 626
},
{
"epoch": 1.4413793103448276,
"grad_norm": 0.22323280572891235,
"learning_rate": 2.2031193178865143e-05,
"loss": 1.3922,
"step": 627
},
{
"epoch": 1.4436781609195402,
"grad_norm": 0.170381560921669,
"learning_rate": 2.2006695256371835e-05,
"loss": 1.5144,
"step": 628
},
{
"epoch": 1.445977011494253,
"grad_norm": 0.19145923852920532,
"learning_rate": 2.1982173405404247e-05,
"loss": 1.4336,
"step": 629
},
{
"epoch": 1.4482758620689655,
"grad_norm": 0.18899975717067719,
"learning_rate": 2.195762770970664e-05,
"loss": 1.4737,
"step": 630
},
{
"epoch": 1.450574712643678,
"grad_norm": 0.18579062819480896,
"learning_rate": 2.19330582531047e-05,
"loss": 1.4527,
"step": 631
},
{
"epoch": 1.452873563218391,
"grad_norm": 0.20850224792957306,
"learning_rate": 2.190846511950526e-05,
"loss": 1.5805,
"step": 632
},
{
"epoch": 1.4551724137931035,
"grad_norm": 0.2641562819480896,
"learning_rate": 2.1883848392896012e-05,
"loss": 1.4892,
"step": 633
},
{
"epoch": 1.457471264367816,
"grad_norm": 0.17978917062282562,
"learning_rate": 2.185920815734522e-05,
"loss": 1.2401,
"step": 634
},
{
"epoch": 1.4597701149425286,
"grad_norm": 0.1841873973608017,
"learning_rate": 2.1834544497001433e-05,
"loss": 1.6304,
"step": 635
},
{
"epoch": 1.4620689655172414,
"grad_norm": 0.24698644876480103,
"learning_rate": 2.1809857496093203e-05,
"loss": 1.3798,
"step": 636
},
{
"epoch": 1.464367816091954,
"grad_norm": 0.19954966008663177,
"learning_rate": 2.178514723892878e-05,
"loss": 1.484,
"step": 637
},
{
"epoch": 1.4666666666666668,
"grad_norm": 0.1900857836008072,
"learning_rate": 2.1760413809895853e-05,
"loss": 1.4124,
"step": 638
},
{
"epoch": 1.4689655172413794,
"grad_norm": 0.17747873067855835,
"learning_rate": 2.1735657293461227e-05,
"loss": 1.517,
"step": 639
},
{
"epoch": 1.471264367816092,
"grad_norm": 0.18358509242534637,
"learning_rate": 2.171087777417056e-05,
"loss": 1.4699,
"step": 640
},
{
"epoch": 1.4735632183908045,
"grad_norm": 0.22474250197410583,
"learning_rate": 2.1686075336648075e-05,
"loss": 1.5883,
"step": 641
},
{
"epoch": 1.4758620689655173,
"grad_norm": 0.21300512552261353,
"learning_rate": 2.166125006559625e-05,
"loss": 1.3892,
"step": 642
},
{
"epoch": 1.4781609195402299,
"grad_norm": 0.32608360052108765,
"learning_rate": 2.163640204579555e-05,
"loss": 1.4365,
"step": 643
},
{
"epoch": 1.4804597701149425,
"grad_norm": 0.2219221144914627,
"learning_rate": 2.1611531362104118e-05,
"loss": 1.2228,
"step": 644
},
{
"epoch": 1.4827586206896552,
"grad_norm": 0.2752749025821686,
"learning_rate": 2.1586638099457516e-05,
"loss": 1.4559,
"step": 645
},
{
"epoch": 1.4850574712643678,
"grad_norm": 0.2623530328273773,
"learning_rate": 2.1561722342868397e-05,
"loss": 1.3715,
"step": 646
},
{
"epoch": 1.4873563218390804,
"grad_norm": 0.1967647522687912,
"learning_rate": 2.1536784177426236e-05,
"loss": 1.363,
"step": 647
},
{
"epoch": 1.489655172413793,
"grad_norm": 0.19669267535209656,
"learning_rate": 2.151182368829704e-05,
"loss": 1.4406,
"step": 648
},
{
"epoch": 1.4919540229885058,
"grad_norm": 0.21909579634666443,
"learning_rate": 2.1486840960723056e-05,
"loss": 1.6976,
"step": 649
},
{
"epoch": 1.4942528735632183,
"grad_norm": 0.22511789202690125,
"learning_rate": 2.1461836080022476e-05,
"loss": 1.6777,
"step": 650
},
{
"epoch": 1.4965517241379311,
"grad_norm": 0.2093202769756317,
"learning_rate": 2.1436809131589136e-05,
"loss": 1.4015,
"step": 651
},
{
"epoch": 1.4988505747126437,
"grad_norm": 0.2714715898036957,
"learning_rate": 2.1411760200892245e-05,
"loss": 1.5799,
"step": 652
},
{
"epoch": 1.5011494252873563,
"grad_norm": 0.23144115507602692,
"learning_rate": 2.138668937347609e-05,
"loss": 1.4854,
"step": 653
},
{
"epoch": 1.5034482758620689,
"grad_norm": 0.22658662497997284,
"learning_rate": 2.1361596734959722e-05,
"loss": 1.4023,
"step": 654
},
{
"epoch": 1.5034482758620689,
"eval_loss": 2.2033939361572266,
"eval_runtime": 24.9424,
"eval_samples_per_second": 8.62,
"eval_steps_per_second": 0.561,
"step": 654
},
{
"epoch": 1.5057471264367817,
"grad_norm": 0.19418728351593018,
"learning_rate": 2.1336482371036686e-05,
"loss": 1.5346,
"step": 655
},
{
"epoch": 1.5080459770114942,
"grad_norm": 0.2258707880973816,
"learning_rate": 2.131134636747473e-05,
"loss": 1.3461,
"step": 656
},
{
"epoch": 1.510344827586207,
"grad_norm": 0.19104237854480743,
"learning_rate": 2.128618881011548e-05,
"loss": 1.5673,
"step": 657
},
{
"epoch": 1.5126436781609196,
"grad_norm": 0.2224787026643753,
"learning_rate": 2.1261009784874193e-05,
"loss": 1.5031,
"step": 658
},
{
"epoch": 1.5149425287356322,
"grad_norm": 0.20533405244350433,
"learning_rate": 2.1235809377739437e-05,
"loss": 1.4779,
"step": 659
},
{
"epoch": 1.5172413793103448,
"grad_norm": 0.21309439837932587,
"learning_rate": 2.1210587674772783e-05,
"loss": 1.434,
"step": 660
},
{
"epoch": 1.5195402298850573,
"grad_norm": 0.1915634274482727,
"learning_rate": 2.1185344762108556e-05,
"loss": 1.5142,
"step": 661
},
{
"epoch": 1.5218390804597701,
"grad_norm": 0.231156587600708,
"learning_rate": 2.116008072595349e-05,
"loss": 1.6229,
"step": 662
},
{
"epoch": 1.524137931034483,
"grad_norm": 0.2583222985267639,
"learning_rate": 2.1134795652586474e-05,
"loss": 1.4911,
"step": 663
},
{
"epoch": 1.5264367816091955,
"grad_norm": 0.19739823043346405,
"learning_rate": 2.110948962835823e-05,
"loss": 1.4393,
"step": 664
},
{
"epoch": 1.528735632183908,
"grad_norm": 0.3459888696670532,
"learning_rate": 2.1084162739691037e-05,
"loss": 1.5816,
"step": 665
},
{
"epoch": 1.5310344827586206,
"grad_norm": 0.20160341262817383,
"learning_rate": 2.1058815073078425e-05,
"loss": 1.458,
"step": 666
},
{
"epoch": 1.5333333333333332,
"grad_norm": 0.17577619850635529,
"learning_rate": 2.1033446715084882e-05,
"loss": 1.5494,
"step": 667
},
{
"epoch": 1.535632183908046,
"grad_norm": 0.17706289887428284,
"learning_rate": 2.100805775234556e-05,
"loss": 1.4028,
"step": 668
},
{
"epoch": 1.5379310344827586,
"grad_norm": 0.1890113800764084,
"learning_rate": 2.0982648271565972e-05,
"loss": 1.5625,
"step": 669
},
{
"epoch": 1.5402298850574714,
"grad_norm": 0.22023656964302063,
"learning_rate": 2.0957218359521707e-05,
"loss": 1.4946,
"step": 670
},
{
"epoch": 1.542528735632184,
"grad_norm": 0.19119736552238464,
"learning_rate": 2.0931768103058137e-05,
"loss": 1.4843,
"step": 671
},
{
"epoch": 1.5448275862068965,
"grad_norm": 0.1974187195301056,
"learning_rate": 2.09062975890901e-05,
"loss": 1.4981,
"step": 672
},
{
"epoch": 1.547126436781609,
"grad_norm": 0.2149532437324524,
"learning_rate": 2.0880806904601614e-05,
"loss": 1.457,
"step": 673
},
{
"epoch": 1.5494252873563217,
"grad_norm": 0.18899254500865936,
"learning_rate": 2.0855296136645587e-05,
"loss": 1.3762,
"step": 674
},
{
"epoch": 1.5517241379310345,
"grad_norm": 0.18127194046974182,
"learning_rate": 2.0829765372343516e-05,
"loss": 1.6201,
"step": 675
},
{
"epoch": 1.5540229885057473,
"grad_norm": 0.19087061285972595,
"learning_rate": 2.0804214698885182e-05,
"loss": 1.5476,
"step": 676
},
{
"epoch": 1.5563218390804598,
"grad_norm": 0.20260533690452576,
"learning_rate": 2.077864420352835e-05,
"loss": 1.4912,
"step": 677
},
{
"epoch": 1.5586206896551724,
"grad_norm": 0.2131945639848709,
"learning_rate": 2.0753053973598512e-05,
"loss": 1.4272,
"step": 678
},
{
"epoch": 1.560919540229885,
"grad_norm": 0.18573595583438873,
"learning_rate": 2.0727444096488502e-05,
"loss": 1.5605,
"step": 679
},
{
"epoch": 1.5632183908045976,
"grad_norm": 0.20603321492671967,
"learning_rate": 2.0701814659658303e-05,
"loss": 1.4364,
"step": 680
},
{
"epoch": 1.5655172413793104,
"grad_norm": 0.18568269908428192,
"learning_rate": 2.0676165750634656e-05,
"loss": 1.3153,
"step": 681
},
{
"epoch": 1.567816091954023,
"grad_norm": 0.18701130151748657,
"learning_rate": 2.065049745701083e-05,
"loss": 1.3832,
"step": 682
},
{
"epoch": 1.5701149425287357,
"grad_norm": 0.18159762024879456,
"learning_rate": 2.0624809866446272e-05,
"loss": 1.4852,
"step": 683
},
{
"epoch": 1.5724137931034483,
"grad_norm": 1.0302122831344604,
"learning_rate": 2.0599103066666347e-05,
"loss": 1.5356,
"step": 684
},
{
"epoch": 1.5747126436781609,
"grad_norm": 0.21795497834682465,
"learning_rate": 2.0573377145462017e-05,
"loss": 1.4373,
"step": 685
},
{
"epoch": 1.5770114942528735,
"grad_norm": 0.16727370023727417,
"learning_rate": 2.0547632190689536e-05,
"loss": 1.4734,
"step": 686
},
{
"epoch": 1.5793103448275863,
"grad_norm": 0.20940454304218292,
"learning_rate": 2.052186829027017e-05,
"loss": 1.4982,
"step": 687
},
{
"epoch": 1.5816091954022988,
"grad_norm": 0.18245477974414825,
"learning_rate": 2.049608553218988e-05,
"loss": 1.6095,
"step": 688
},
{
"epoch": 1.5839080459770116,
"grad_norm": 0.20603610575199127,
"learning_rate": 2.0470284004499028e-05,
"loss": 1.3431,
"step": 689
},
{
"epoch": 1.5862068965517242,
"grad_norm": 0.23974734544754028,
"learning_rate": 2.0444463795312078e-05,
"loss": 1.4477,
"step": 690
},
{
"epoch": 1.5885057471264368,
"grad_norm": 0.20684437453746796,
"learning_rate": 2.0418624992807297e-05,
"loss": 1.425,
"step": 691
},
{
"epoch": 1.5908045977011493,
"grad_norm": 0.1776638627052307,
"learning_rate": 2.0392767685226438e-05,
"loss": 1.4255,
"step": 692
},
{
"epoch": 1.593103448275862,
"grad_norm": 0.18080171942710876,
"learning_rate": 2.0366891960874455e-05,
"loss": 1.518,
"step": 693
},
{
"epoch": 1.5954022988505747,
"grad_norm": 0.1890837550163269,
"learning_rate": 2.0340997908119214e-05,
"loss": 1.6554,
"step": 694
},
{
"epoch": 1.5977011494252875,
"grad_norm": 0.1912626326084137,
"learning_rate": 2.0315085615391144e-05,
"loss": 1.4363,
"step": 695
},
{
"epoch": 1.6,
"grad_norm": 0.1927110254764557,
"learning_rate": 2.0289155171182986e-05,
"loss": 1.6567,
"step": 696
},
{
"epoch": 1.6022988505747127,
"grad_norm": 0.2298053652048111,
"learning_rate": 2.0263206664049472e-05,
"loss": 1.308,
"step": 697
},
{
"epoch": 1.6045977011494252,
"grad_norm": 0.18490935862064362,
"learning_rate": 2.0237240182607e-05,
"loss": 1.4756,
"step": 698
},
{
"epoch": 1.6068965517241378,
"grad_norm": 0.22502966225147247,
"learning_rate": 2.0211255815533372e-05,
"loss": 1.4667,
"step": 699
},
{
"epoch": 1.6091954022988506,
"grad_norm": 0.1965327262878418,
"learning_rate": 2.0185253651567463e-05,
"loss": 1.3665,
"step": 700
},
{
"epoch": 1.6114942528735632,
"grad_norm": 0.19407789409160614,
"learning_rate": 2.0159233779508923e-05,
"loss": 1.414,
"step": 701
},
{
"epoch": 1.613793103448276,
"grad_norm": 0.2023402452468872,
"learning_rate": 2.0133196288217886e-05,
"loss": 1.4783,
"step": 702
},
{
"epoch": 1.6160919540229886,
"grad_norm": 0.19824720919132233,
"learning_rate": 2.0107141266614643e-05,
"loss": 1.5464,
"step": 703
},
{
"epoch": 1.6183908045977011,
"grad_norm": 0.1865212619304657,
"learning_rate": 2.0081068803679374e-05,
"loss": 1.6882,
"step": 704
},
{
"epoch": 1.6206896551724137,
"grad_norm": 0.19345404207706451,
"learning_rate": 2.0054978988451796e-05,
"loss": 1.3442,
"step": 705
},
{
"epoch": 1.6229885057471263,
"grad_norm": 0.17592638731002808,
"learning_rate": 2.002887191003091e-05,
"loss": 1.5989,
"step": 706
},
{
"epoch": 1.625287356321839,
"grad_norm": 0.25224360823631287,
"learning_rate": 2.000274765757465e-05,
"loss": 1.603,
"step": 707
},
{
"epoch": 1.6275862068965519,
"grad_norm": 0.1976442039012909,
"learning_rate": 1.9976606320299625e-05,
"loss": 1.4166,
"step": 708
},
{
"epoch": 1.6298850574712644,
"grad_norm": 0.18931593000888824,
"learning_rate": 1.9950447987480774e-05,
"loss": 1.4611,
"step": 709
},
{
"epoch": 1.632183908045977,
"grad_norm": 0.1858445107936859,
"learning_rate": 1.9924272748451074e-05,
"loss": 1.5624,
"step": 710
},
{
"epoch": 1.6344827586206896,
"grad_norm": 0.17852693796157837,
"learning_rate": 1.9898080692601247e-05,
"loss": 1.5437,
"step": 711
},
{
"epoch": 1.6367816091954022,
"grad_norm": 0.18458198010921478,
"learning_rate": 1.9871871909379454e-05,
"loss": 1.4707,
"step": 712
},
{
"epoch": 1.639080459770115,
"grad_norm": 0.1947033554315567,
"learning_rate": 1.984564648829096e-05,
"loss": 1.4379,
"step": 713
},
{
"epoch": 1.6413793103448275,
"grad_norm": 0.3348253667354584,
"learning_rate": 1.981940451889787e-05,
"loss": 1.5009,
"step": 714
},
{
"epoch": 1.6436781609195403,
"grad_norm": 0.21393540501594543,
"learning_rate": 1.9793146090818782e-05,
"loss": 1.4442,
"step": 715
},
{
"epoch": 1.645977011494253,
"grad_norm": 0.22554749250411987,
"learning_rate": 1.9766871293728525e-05,
"loss": 1.4695,
"step": 716
},
{
"epoch": 1.6482758620689655,
"grad_norm": 0.1754077523946762,
"learning_rate": 1.9740580217357813e-05,
"loss": 1.5091,
"step": 717
},
{
"epoch": 1.650574712643678,
"grad_norm": 0.20797176659107208,
"learning_rate": 1.9714272951492962e-05,
"loss": 1.3514,
"step": 718
},
{
"epoch": 1.6528735632183909,
"grad_norm": 0.198759987950325,
"learning_rate": 1.968794958597558e-05,
"loss": 1.2592,
"step": 719
},
{
"epoch": 1.6551724137931034,
"grad_norm": 0.23417668044567108,
"learning_rate": 1.966161021070224e-05,
"loss": 1.5455,
"step": 720
},
{
"epoch": 1.6574712643678162,
"grad_norm": 0.18547843396663666,
"learning_rate": 1.963525491562421e-05,
"loss": 1.5246,
"step": 721
},
{
"epoch": 1.6597701149425288,
"grad_norm": 0.19809691607952118,
"learning_rate": 1.9608883790747118e-05,
"loss": 1.6539,
"step": 722
},
{
"epoch": 1.6620689655172414,
"grad_norm": 0.18433202803134918,
"learning_rate": 1.9582496926130646e-05,
"loss": 1.5491,
"step": 723
},
{
"epoch": 1.664367816091954,
"grad_norm": 0.2409473955631256,
"learning_rate": 1.9556094411888244e-05,
"loss": 1.7996,
"step": 724
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.220855712890625,
"learning_rate": 1.9529676338186783e-05,
"loss": 1.5031,
"step": 725
},
{
"epoch": 1.6689655172413793,
"grad_norm": 0.21066197752952576,
"learning_rate": 1.9503242795246293e-05,
"loss": 1.4223,
"step": 726
},
{
"epoch": 1.6712643678160921,
"grad_norm": 0.18477372825145721,
"learning_rate": 1.947679387333962e-05,
"loss": 1.5682,
"step": 727
},
{
"epoch": 1.6735632183908047,
"grad_norm": 0.19440820813179016,
"learning_rate": 1.945032966279214e-05,
"loss": 1.4797,
"step": 728
},
{
"epoch": 1.6758620689655173,
"grad_norm": 0.2102813720703125,
"learning_rate": 1.942385025398143e-05,
"loss": 1.4632,
"step": 729
},
{
"epoch": 1.6781609195402298,
"grad_norm": 0.1737748235464096,
"learning_rate": 1.9397355737336982e-05,
"loss": 1.5057,
"step": 730
},
{
"epoch": 1.6804597701149424,
"grad_norm": 0.18015246093273163,
"learning_rate": 1.937084620333987e-05,
"loss": 1.4365,
"step": 731
},
{
"epoch": 1.6827586206896552,
"grad_norm": 0.1892857700586319,
"learning_rate": 1.9344321742522466e-05,
"loss": 1.3721,
"step": 732
},
{
"epoch": 1.6850574712643678,
"grad_norm": 0.18894895911216736,
"learning_rate": 1.9317782445468116e-05,
"loss": 1.3085,
"step": 733
},
{
"epoch": 1.6873563218390806,
"grad_norm": 0.19456493854522705,
"learning_rate": 1.929122840281082e-05,
"loss": 1.4137,
"step": 734
},
{
"epoch": 1.6896551724137931,
"grad_norm": 0.20560263097286224,
"learning_rate": 1.926465970523495e-05,
"loss": 1.4465,
"step": 735
},
{
"epoch": 1.6919540229885057,
"grad_norm": 0.19975651800632477,
"learning_rate": 1.9238076443474927e-05,
"loss": 1.5285,
"step": 736
},
{
"epoch": 1.6942528735632183,
"grad_norm": 0.19120940566062927,
"learning_rate": 1.9211478708314894e-05,
"loss": 1.4756,
"step": 737
},
{
"epoch": 1.6965517241379309,
"grad_norm": 0.2186792492866516,
"learning_rate": 1.918486659058844e-05,
"loss": 1.5256,
"step": 738
},
{
"epoch": 1.6988505747126437,
"grad_norm": 0.20335499942302704,
"learning_rate": 1.9158240181178262e-05,
"loss": 1.4804,
"step": 739
},
{
"epoch": 1.7011494252873565,
"grad_norm": 0.2554546296596527,
"learning_rate": 1.9131599571015863e-05,
"loss": 1.4397,
"step": 740
},
{
"epoch": 1.703448275862069,
"grad_norm": 0.19581107795238495,
"learning_rate": 1.9104944851081247e-05,
"loss": 1.4054,
"step": 741
},
{
"epoch": 1.7057471264367816,
"grad_norm": 0.20524311065673828,
"learning_rate": 1.9078276112402598e-05,
"loss": 1.5298,
"step": 742
},
{
"epoch": 1.7080459770114942,
"grad_norm": 0.18670476973056793,
"learning_rate": 1.9051593446055996e-05,
"loss": 1.4481,
"step": 743
},
{
"epoch": 1.7103448275862068,
"grad_norm": 0.2637614905834198,
"learning_rate": 1.9024896943165055e-05,
"loss": 1.523,
"step": 744
},
{
"epoch": 1.7126436781609196,
"grad_norm": 0.22639480233192444,
"learning_rate": 1.8998186694900662e-05,
"loss": 1.4733,
"step": 745
},
{
"epoch": 1.7149425287356321,
"grad_norm": 0.1918284296989441,
"learning_rate": 1.8971462792480636e-05,
"loss": 1.565,
"step": 746
},
{
"epoch": 1.717241379310345,
"grad_norm": 0.19212710857391357,
"learning_rate": 1.8944725327169437e-05,
"loss": 1.512,
"step": 747
},
{
"epoch": 1.7195402298850575,
"grad_norm": 0.2399304360151291,
"learning_rate": 1.8917974390277837e-05,
"loss": 1.549,
"step": 748
},
{
"epoch": 1.72183908045977,
"grad_norm": 0.2559639811515808,
"learning_rate": 1.8891210073162603e-05,
"loss": 1.4454,
"step": 749
},
{
"epoch": 1.7241379310344827,
"grad_norm": 0.2261936515569687,
"learning_rate": 1.886443246722622e-05,
"loss": 1.5731,
"step": 750
},
{
"epoch": 1.7264367816091954,
"grad_norm": 0.1689794659614563,
"learning_rate": 1.8837641663916536e-05,
"loss": 1.4539,
"step": 751
},
{
"epoch": 1.728735632183908,
"grad_norm": 0.211863711476326,
"learning_rate": 1.881083775472648e-05,
"loss": 1.462,
"step": 752
},
{
"epoch": 1.7310344827586208,
"grad_norm": 0.19259430468082428,
"learning_rate": 1.8784020831193732e-05,
"loss": 1.6155,
"step": 753
},
{
"epoch": 1.7333333333333334,
"grad_norm": 0.20492258667945862,
"learning_rate": 1.8757190984900427e-05,
"loss": 1.4045,
"step": 754
},
{
"epoch": 1.735632183908046,
"grad_norm": 0.2130819708108902,
"learning_rate": 1.8730348307472828e-05,
"loss": 1.4951,
"step": 755
},
{
"epoch": 1.7379310344827585,
"grad_norm": 0.19057954847812653,
"learning_rate": 1.8703492890580994e-05,
"loss": 1.6226,
"step": 756
},
{
"epoch": 1.7402298850574711,
"grad_norm": 0.17894117534160614,
"learning_rate": 1.8676624825938536e-05,
"loss": 1.4147,
"step": 757
},
{
"epoch": 1.742528735632184,
"grad_norm": 0.25076764822006226,
"learning_rate": 1.864974420530223e-05,
"loss": 1.5329,
"step": 758
},
{
"epoch": 1.7448275862068967,
"grad_norm": 0.21779051423072815,
"learning_rate": 1.8622851120471717e-05,
"loss": 1.4283,
"step": 759
},
{
"epoch": 1.7471264367816093,
"grad_norm": 0.21466271579265594,
"learning_rate": 1.859594566328925e-05,
"loss": 1.2951,
"step": 760
},
{
"epoch": 1.7494252873563219,
"grad_norm": 0.18829570710659027,
"learning_rate": 1.856902792563928e-05,
"loss": 1.5456,
"step": 761
},
{
"epoch": 1.7517241379310344,
"grad_norm": 0.1898689568042755,
"learning_rate": 1.854209799944825e-05,
"loss": 1.281,
"step": 762
},
{
"epoch": 1.754022988505747,
"grad_norm": 0.17983412742614746,
"learning_rate": 1.8515155976684186e-05,
"loss": 1.6312,
"step": 763
},
{
"epoch": 1.754022988505747,
"eval_loss": 2.1958730220794678,
"eval_runtime": 24.932,
"eval_samples_per_second": 8.623,
"eval_steps_per_second": 0.562,
"step": 763
},
{
"epoch": 1.7563218390804598,
"grad_norm": 0.20969410240650177,
"learning_rate": 1.848820194935644e-05,
"loss": 1.5009,
"step": 764
},
{
"epoch": 1.7586206896551724,
"grad_norm": 0.1873113214969635,
"learning_rate": 1.8461236009515372e-05,
"loss": 1.4986,
"step": 765
},
{
"epoch": 1.7609195402298852,
"grad_norm": 0.4664338529109955,
"learning_rate": 1.843425824925201e-05,
"loss": 1.4429,
"step": 766
},
{
"epoch": 1.7632183908045977,
"grad_norm": 0.20402957499027252,
"learning_rate": 1.8407268760697754e-05,
"loss": 1.3722,
"step": 767
},
{
"epoch": 1.7655172413793103,
"grad_norm": 0.22426556050777435,
"learning_rate": 1.8380267636024057e-05,
"loss": 1.6732,
"step": 768
},
{
"epoch": 1.767816091954023,
"grad_norm": 0.193081334233284,
"learning_rate": 1.835325496744211e-05,
"loss": 1.5357,
"step": 769
},
{
"epoch": 1.7701149425287355,
"grad_norm": 0.20106405019760132,
"learning_rate": 1.8326230847202526e-05,
"loss": 1.3692,
"step": 770
},
{
"epoch": 1.7724137931034483,
"grad_norm": 0.18493399024009705,
"learning_rate": 1.8299195367595032e-05,
"loss": 1.4242,
"step": 771
},
{
"epoch": 1.774712643678161,
"grad_norm": 0.1884271651506424,
"learning_rate": 1.8272148620948143e-05,
"loss": 1.4629,
"step": 772
},
{
"epoch": 1.7770114942528736,
"grad_norm": 0.19949296116828918,
"learning_rate": 1.8245090699628847e-05,
"loss": 1.3153,
"step": 773
},
{
"epoch": 1.7793103448275862,
"grad_norm": 0.23689354956150055,
"learning_rate": 1.821802169604231e-05,
"loss": 1.3881,
"step": 774
},
{
"epoch": 1.7816091954022988,
"grad_norm": 0.2376299947500229,
"learning_rate": 1.8190941702631534e-05,
"loss": 1.4666,
"step": 775
},
{
"epoch": 1.7839080459770114,
"grad_norm": 0.18699921667575836,
"learning_rate": 1.816385081187705e-05,
"loss": 1.4216,
"step": 776
},
{
"epoch": 1.7862068965517242,
"grad_norm": 0.20320840179920197,
"learning_rate": 1.8136749116296613e-05,
"loss": 1.5164,
"step": 777
},
{
"epoch": 1.7885057471264367,
"grad_norm": 0.19638000428676605,
"learning_rate": 1.8109636708444868e-05,
"loss": 1.3424,
"step": 778
},
{
"epoch": 1.7908045977011495,
"grad_norm": 0.18586432933807373,
"learning_rate": 1.8082513680913053e-05,
"loss": 1.5165,
"step": 779
},
{
"epoch": 1.793103448275862,
"grad_norm": 0.18242147564888,
"learning_rate": 1.8055380126328664e-05,
"loss": 1.493,
"step": 780
},
{
"epoch": 1.7954022988505747,
"grad_norm": 0.1759779304265976,
"learning_rate": 1.8028236137355154e-05,
"loss": 1.6257,
"step": 781
},
{
"epoch": 1.7977011494252872,
"grad_norm": 0.20067760348320007,
"learning_rate": 1.800108180669161e-05,
"loss": 1.5144,
"step": 782
},
{
"epoch": 1.8,
"grad_norm": 0.1905200034379959,
"learning_rate": 1.7973917227072434e-05,
"loss": 1.5748,
"step": 783
},
{
"epoch": 1.8022988505747126,
"grad_norm": 0.2060949057340622,
"learning_rate": 1.7946742491267028e-05,
"loss": 1.4899,
"step": 784
},
{
"epoch": 1.8045977011494254,
"grad_norm": 0.19472648203372955,
"learning_rate": 1.7919557692079484e-05,
"loss": 1.5471,
"step": 785
},
{
"epoch": 1.806896551724138,
"grad_norm": 0.22593867778778076,
"learning_rate": 1.7892362922348255e-05,
"loss": 1.3999,
"step": 786
},
{
"epoch": 1.8091954022988506,
"grad_norm": 0.24639272689819336,
"learning_rate": 1.7865158274945846e-05,
"loss": 1.4929,
"step": 787
},
{
"epoch": 1.8114942528735631,
"grad_norm": 0.2962942123413086,
"learning_rate": 1.7837943842778502e-05,
"loss": 1.6233,
"step": 788
},
{
"epoch": 1.8137931034482757,
"grad_norm": 0.19271743297576904,
"learning_rate": 1.781071971878587e-05,
"loss": 1.5504,
"step": 789
},
{
"epoch": 1.8160919540229885,
"grad_norm": 0.22280791401863098,
"learning_rate": 1.7783485995940708e-05,
"loss": 1.4305,
"step": 790
},
{
"epoch": 1.8183908045977013,
"grad_norm": 0.18707133829593658,
"learning_rate": 1.775624276724856e-05,
"loss": 1.4871,
"step": 791
},
{
"epoch": 1.8206896551724139,
"grad_norm": 0.23668767511844635,
"learning_rate": 1.7728990125747403e-05,
"loss": 1.5294,
"step": 792
},
{
"epoch": 1.8229885057471265,
"grad_norm": 0.20020174980163574,
"learning_rate": 1.7701728164507395e-05,
"loss": 1.535,
"step": 793
},
{
"epoch": 1.825287356321839,
"grad_norm": 0.2018471211194992,
"learning_rate": 1.7674456976630504e-05,
"loss": 1.4935,
"step": 794
},
{
"epoch": 1.8275862068965516,
"grad_norm": 0.23764076828956604,
"learning_rate": 1.7647176655250208e-05,
"loss": 1.2026,
"step": 795
},
{
"epoch": 1.8298850574712644,
"grad_norm": 0.1766892820596695,
"learning_rate": 1.7619887293531185e-05,
"loss": 1.3433,
"step": 796
},
{
"epoch": 1.832183908045977,
"grad_norm": 0.18335160613059998,
"learning_rate": 1.7592588984668973e-05,
"loss": 1.6587,
"step": 797
},
{
"epoch": 1.8344827586206898,
"grad_norm": 0.19322408735752106,
"learning_rate": 1.756528182188968e-05,
"loss": 1.6719,
"step": 798
},
{
"epoch": 1.8367816091954023,
"grad_norm": 0.19454005360603333,
"learning_rate": 1.753796589844964e-05,
"loss": 1.5285,
"step": 799
},
{
"epoch": 1.839080459770115,
"grad_norm": 0.19709111750125885,
"learning_rate": 1.751064130763511e-05,
"loss": 1.5382,
"step": 800
},
{
"epoch": 1.8413793103448275,
"grad_norm": 0.20608137547969818,
"learning_rate": 1.748330814276195e-05,
"loss": 1.3998,
"step": 801
},
{
"epoch": 1.84367816091954,
"grad_norm": 0.18155191838741302,
"learning_rate": 1.7455966497175296e-05,
"loss": 1.3775,
"step": 802
},
{
"epoch": 1.8459770114942529,
"grad_norm": 0.22577901184558868,
"learning_rate": 1.7428616464249246e-05,
"loss": 1.3765,
"step": 803
},
{
"epoch": 1.8482758620689657,
"grad_norm": 0.2285933792591095,
"learning_rate": 1.7401258137386542e-05,
"loss": 1.5662,
"step": 804
},
{
"epoch": 1.8505747126436782,
"grad_norm": 0.19764187932014465,
"learning_rate": 1.737389161001826e-05,
"loss": 1.5101,
"step": 805
},
{
"epoch": 1.8528735632183908,
"grad_norm": 0.19379965960979462,
"learning_rate": 1.7346516975603466e-05,
"loss": 1.5413,
"step": 806
},
{
"epoch": 1.8551724137931034,
"grad_norm": 0.1956605315208435,
"learning_rate": 1.731913432762892e-05,
"loss": 1.5215,
"step": 807
},
{
"epoch": 1.857471264367816,
"grad_norm": 0.20054706931114197,
"learning_rate": 1.7291743759608752e-05,
"loss": 1.409,
"step": 808
},
{
"epoch": 1.8597701149425288,
"grad_norm": 0.18622225522994995,
"learning_rate": 1.726434536508413e-05,
"loss": 1.591,
"step": 809
},
{
"epoch": 1.8620689655172413,
"grad_norm": 0.19358402490615845,
"learning_rate": 1.7236939237622965e-05,
"loss": 1.6263,
"step": 810
},
{
"epoch": 1.8643678160919541,
"grad_norm": 0.18939010798931122,
"learning_rate": 1.7209525470819564e-05,
"loss": 1.4367,
"step": 811
},
{
"epoch": 1.8666666666666667,
"grad_norm": 0.19489432871341705,
"learning_rate": 1.7182104158294324e-05,
"loss": 1.3834,
"step": 812
},
{
"epoch": 1.8689655172413793,
"grad_norm": 0.19715090095996857,
"learning_rate": 1.7154675393693425e-05,
"loss": 1.5435,
"step": 813
},
{
"epoch": 1.8712643678160918,
"grad_norm": 0.20351245999336243,
"learning_rate": 1.712723927068847e-05,
"loss": 1.592,
"step": 814
},
{
"epoch": 1.8735632183908046,
"grad_norm": 0.20575116574764252,
"learning_rate": 1.7099795882976226e-05,
"loss": 1.5289,
"step": 815
},
{
"epoch": 1.8758620689655172,
"grad_norm": 0.1951652318239212,
"learning_rate": 1.7072345324278235e-05,
"loss": 1.3511,
"step": 816
},
{
"epoch": 1.87816091954023,
"grad_norm": 0.19878904521465302,
"learning_rate": 1.704488768834055e-05,
"loss": 1.6137,
"step": 817
},
{
"epoch": 1.8804597701149426,
"grad_norm": 0.1942046880722046,
"learning_rate": 1.7017423068933395e-05,
"loss": 1.4374,
"step": 818
},
{
"epoch": 1.8827586206896552,
"grad_norm": 0.23966963589191437,
"learning_rate": 1.6989951559850825e-05,
"loss": 1.6165,
"step": 819
},
{
"epoch": 1.8850574712643677,
"grad_norm": 0.1781224012374878,
"learning_rate": 1.6962473254910444e-05,
"loss": 1.4191,
"step": 820
},
{
"epoch": 1.8873563218390803,
"grad_norm": 0.21380388736724854,
"learning_rate": 1.6934988247953053e-05,
"loss": 1.4465,
"step": 821
},
{
"epoch": 1.889655172413793,
"grad_norm": 0.16608113050460815,
"learning_rate": 1.6907496632842336e-05,
"loss": 1.7414,
"step": 822
},
{
"epoch": 1.891954022988506,
"grad_norm": 0.20107951760292053,
"learning_rate": 1.6879998503464565e-05,
"loss": 1.5624,
"step": 823
},
{
"epoch": 1.8942528735632185,
"grad_norm": 0.19420577585697174,
"learning_rate": 1.6852493953728235e-05,
"loss": 1.6227,
"step": 824
},
{
"epoch": 1.896551724137931,
"grad_norm": 0.19513115286827087,
"learning_rate": 1.6824983077563785e-05,
"loss": 1.6479,
"step": 825
},
{
"epoch": 1.8988505747126436,
"grad_norm": 0.17276419699192047,
"learning_rate": 1.679746596892325e-05,
"loss": 1.3904,
"step": 826
},
{
"epoch": 1.9011494252873562,
"grad_norm": 0.18302150070667267,
"learning_rate": 1.6769942721779948e-05,
"loss": 1.3644,
"step": 827
},
{
"epoch": 1.903448275862069,
"grad_norm": 0.19094626605510712,
"learning_rate": 1.674241343012817e-05,
"loss": 1.5056,
"step": 828
},
{
"epoch": 1.9057471264367816,
"grad_norm": 0.19178231060504913,
"learning_rate": 1.671487818798284e-05,
"loss": 1.3745,
"step": 829
},
{
"epoch": 1.9080459770114944,
"grad_norm": 0.20004530251026154,
"learning_rate": 1.6687337089379204e-05,
"loss": 1.4089,
"step": 830
},
{
"epoch": 1.910344827586207,
"grad_norm": 0.17812412977218628,
"learning_rate": 1.6659790228372512e-05,
"loss": 1.5523,
"step": 831
},
{
"epoch": 1.9126436781609195,
"grad_norm": 0.23764462769031525,
"learning_rate": 1.66322376990377e-05,
"loss": 1.4022,
"step": 832
},
{
"epoch": 1.914942528735632,
"grad_norm": 0.18033753335475922,
"learning_rate": 1.660467959546905e-05,
"loss": 1.501,
"step": 833
},
{
"epoch": 1.9172413793103447,
"grad_norm": 0.19113288819789886,
"learning_rate": 1.6577116011779878e-05,
"loss": 1.509,
"step": 834
},
{
"epoch": 1.9195402298850575,
"grad_norm": 0.2183152437210083,
"learning_rate": 1.654954704210224e-05,
"loss": 1.5589,
"step": 835
},
{
"epoch": 1.9218390804597703,
"grad_norm": 0.20376411080360413,
"learning_rate": 1.6521972780586545e-05,
"loss": 1.5514,
"step": 836
},
{
"epoch": 1.9241379310344828,
"grad_norm": 0.18351972103118896,
"learning_rate": 1.6494393321401312e-05,
"loss": 1.3683,
"step": 837
},
{
"epoch": 1.9264367816091954,
"grad_norm": 0.20166511833667755,
"learning_rate": 1.646680875873279e-05,
"loss": 1.4161,
"step": 838
},
{
"epoch": 1.928735632183908,
"grad_norm": 0.1939769983291626,
"learning_rate": 1.6439219186784658e-05,
"loss": 1.2911,
"step": 839
},
{
"epoch": 1.9310344827586206,
"grad_norm": 0.1853218376636505,
"learning_rate": 1.641162469977772e-05,
"loss": 1.4565,
"step": 840
},
{
"epoch": 1.9333333333333333,
"grad_norm": 0.18768632411956787,
"learning_rate": 1.638402539194953e-05,
"loss": 1.2909,
"step": 841
},
{
"epoch": 1.935632183908046,
"grad_norm": 0.1980678141117096,
"learning_rate": 1.6356421357554144e-05,
"loss": 1.4048,
"step": 842
},
{
"epoch": 1.9379310344827587,
"grad_norm": 0.20565304160118103,
"learning_rate": 1.6328812690861737e-05,
"loss": 1.4284,
"step": 843
},
{
"epoch": 1.9402298850574713,
"grad_norm": 0.18119512498378754,
"learning_rate": 1.6301199486158314e-05,
"loss": 1.4361,
"step": 844
},
{
"epoch": 1.9425287356321839,
"grad_norm": 0.1783718466758728,
"learning_rate": 1.6273581837745357e-05,
"loss": 1.4304,
"step": 845
},
{
"epoch": 1.9448275862068964,
"grad_norm": 0.21830524504184723,
"learning_rate": 1.624595983993956e-05,
"loss": 1.5116,
"step": 846
},
{
"epoch": 1.9471264367816092,
"grad_norm": 0.19105234742164612,
"learning_rate": 1.6218333587072438e-05,
"loss": 1.2877,
"step": 847
},
{
"epoch": 1.9494252873563218,
"grad_norm": 0.19298067688941956,
"learning_rate": 1.6190703173490053e-05,
"loss": 1.4219,
"step": 848
},
{
"epoch": 1.9517241379310346,
"grad_norm": 0.21384195983409882,
"learning_rate": 1.6163068693552675e-05,
"loss": 1.5203,
"step": 849
},
{
"epoch": 1.9540229885057472,
"grad_norm": 0.19417764246463776,
"learning_rate": 1.613543024163445e-05,
"loss": 1.2702,
"step": 850
},
{
"epoch": 1.9563218390804598,
"grad_norm": 0.188349649310112,
"learning_rate": 1.6107787912123112e-05,
"loss": 1.4343,
"step": 851
},
{
"epoch": 1.9586206896551723,
"grad_norm": 0.18883079290390015,
"learning_rate": 1.608014179941961e-05,
"loss": 1.3304,
"step": 852
},
{
"epoch": 1.960919540229885,
"grad_norm": 0.20448146760463715,
"learning_rate": 1.6052491997937828e-05,
"loss": 1.5321,
"step": 853
},
{
"epoch": 1.9632183908045977,
"grad_norm": 0.20096653699874878,
"learning_rate": 1.6024838602104253e-05,
"loss": 1.3913,
"step": 854
},
{
"epoch": 1.9655172413793105,
"grad_norm": 0.1903121918439865,
"learning_rate": 1.599718170635763e-05,
"loss": 1.6615,
"step": 855
},
{
"epoch": 1.967816091954023,
"grad_norm": 0.17686329782009125,
"learning_rate": 1.5969521405148663e-05,
"loss": 1.5537,
"step": 856
},
{
"epoch": 1.9701149425287356,
"grad_norm": 0.21145719289779663,
"learning_rate": 1.5941857792939702e-05,
"loss": 1.3977,
"step": 857
},
{
"epoch": 1.9724137931034482,
"grad_norm": 0.19183754920959473,
"learning_rate": 1.591419096420438e-05,
"loss": 1.3934,
"step": 858
},
{
"epoch": 1.9747126436781608,
"grad_norm": 0.18425194919109344,
"learning_rate": 1.588652101342733e-05,
"loss": 1.3958,
"step": 859
},
{
"epoch": 1.9770114942528736,
"grad_norm": 0.20868638157844543,
"learning_rate": 1.5858848035103847e-05,
"loss": 1.5329,
"step": 860
},
{
"epoch": 1.9793103448275862,
"grad_norm": 0.17680692672729492,
"learning_rate": 1.583117212373955e-05,
"loss": 1.511,
"step": 861
},
{
"epoch": 1.981609195402299,
"grad_norm": 0.23056255280971527,
"learning_rate": 1.5803493373850093e-05,
"loss": 1.424,
"step": 862
},
{
"epoch": 1.9839080459770115,
"grad_norm": 0.20566102862358093,
"learning_rate": 1.5775811879960817e-05,
"loss": 1.5806,
"step": 863
},
{
"epoch": 1.986206896551724,
"grad_norm": 0.18817196786403656,
"learning_rate": 1.574812773660643e-05,
"loss": 1.4292,
"step": 864
},
{
"epoch": 1.9885057471264367,
"grad_norm": 0.20574186742305756,
"learning_rate": 1.57204410383307e-05,
"loss": 1.3131,
"step": 865
},
{
"epoch": 1.9908045977011493,
"grad_norm": 0.1901344209909439,
"learning_rate": 1.5692751879686097e-05,
"loss": 1.4123,
"step": 866
},
{
"epoch": 1.993103448275862,
"grad_norm": 0.19691941142082214,
"learning_rate": 1.5665060355233516e-05,
"loss": 1.4935,
"step": 867
},
{
"epoch": 1.9954022988505749,
"grad_norm": 0.20186631381511688,
"learning_rate": 1.5637366559541926e-05,
"loss": 1.5541,
"step": 868
},
{
"epoch": 1.9977011494252874,
"grad_norm": 0.19534841179847717,
"learning_rate": 1.5609670587188052e-05,
"loss": 1.538,
"step": 869
},
{
"epoch": 2.0,
"grad_norm": 0.1868334859609604,
"learning_rate": 1.5581972532756044e-05,
"loss": 1.4447,
"step": 870
},
{
"epoch": 2.0022988505747126,
"grad_norm": 0.19245904684066772,
"learning_rate": 1.5554272490837176e-05,
"loss": 1.4899,
"step": 871
},
{
"epoch": 2.004597701149425,
"grad_norm": 0.17653775215148926,
"learning_rate": 1.5526570556029495e-05,
"loss": 1.3044,
"step": 872
},
{
"epoch": 2.004597701149425,
"eval_loss": 2.1908648014068604,
"eval_runtime": 24.9844,
"eval_samples_per_second": 8.605,
"eval_steps_per_second": 0.56,
"step": 872
},
{
"epoch": 2.0068965517241377,
"grad_norm": 0.1944357007741928,
"learning_rate": 1.5498866822937525e-05,
"loss": 1.5027,
"step": 873
},
{
"epoch": 2.0091954022988507,
"grad_norm": 0.22427994012832642,
"learning_rate": 1.5471161386171925e-05,
"loss": 1.4342,
"step": 874
},
{
"epoch": 2.0114942528735633,
"grad_norm": 0.2060762494802475,
"learning_rate": 1.5443454340349175e-05,
"loss": 1.3411,
"step": 875
},
{
"epoch": 2.013793103448276,
"grad_norm": 0.2007463574409485,
"learning_rate": 1.5415745780091248e-05,
"loss": 1.4327,
"step": 876
},
{
"epoch": 2.0160919540229885,
"grad_norm": 0.19028769433498383,
"learning_rate": 1.5388035800025287e-05,
"loss": 1.4183,
"step": 877
},
{
"epoch": 2.018390804597701,
"grad_norm": 0.18698997795581818,
"learning_rate": 1.5360324494783286e-05,
"loss": 1.5749,
"step": 878
},
{
"epoch": 2.0206896551724136,
"grad_norm": 0.19737985730171204,
"learning_rate": 1.533261195900177e-05,
"loss": 1.4574,
"step": 879
},
{
"epoch": 2.0229885057471266,
"grad_norm": 0.20038267970085144,
"learning_rate": 1.5304898287321458e-05,
"loss": 1.3915,
"step": 880
},
{
"epoch": 2.025287356321839,
"grad_norm": 0.19485490024089813,
"learning_rate": 1.5277183574386947e-05,
"loss": 1.5415,
"step": 881
},
{
"epoch": 2.027586206896552,
"grad_norm": 0.19064515829086304,
"learning_rate": 1.5249467914846405e-05,
"loss": 1.5579,
"step": 882
},
{
"epoch": 2.0298850574712644,
"grad_norm": 0.2039537876844406,
"learning_rate": 1.5221751403351216e-05,
"loss": 1.3454,
"step": 883
},
{
"epoch": 2.032183908045977,
"grad_norm": 0.20100238919258118,
"learning_rate": 1.5194034134555675e-05,
"loss": 1.6458,
"step": 884
},
{
"epoch": 2.0344827586206895,
"grad_norm": 0.20035569369792938,
"learning_rate": 1.5166316203116676e-05,
"loss": 1.4648,
"step": 885
},
{
"epoch": 2.036781609195402,
"grad_norm": 0.19791434705257416,
"learning_rate": 1.5138597703693364e-05,
"loss": 1.2636,
"step": 886
},
{
"epoch": 2.039080459770115,
"grad_norm": 0.20055970549583435,
"learning_rate": 1.5110878730946829e-05,
"loss": 1.4217,
"step": 887
},
{
"epoch": 2.0413793103448277,
"grad_norm": 0.18559375405311584,
"learning_rate": 1.5083159379539774e-05,
"loss": 1.6094,
"step": 888
},
{
"epoch": 2.0436781609195402,
"grad_norm": 0.20073656737804413,
"learning_rate": 1.5055439744136196e-05,
"loss": 1.3785,
"step": 889
},
{
"epoch": 2.045977011494253,
"grad_norm": 0.18822336196899414,
"learning_rate": 1.5027719919401071e-05,
"loss": 1.4779,
"step": 890
},
{
"epoch": 2.0482758620689654,
"grad_norm": 0.23707926273345947,
"learning_rate": 1.5e-05,
"loss": 1.3558,
"step": 891
},
{
"epoch": 2.050574712643678,
"grad_norm": 0.20680716633796692,
"learning_rate": 1.4972280080598931e-05,
"loss": 1.4839,
"step": 892
},
{
"epoch": 2.052873563218391,
"grad_norm": 0.19461223483085632,
"learning_rate": 1.4944560255863805e-05,
"loss": 1.553,
"step": 893
},
{
"epoch": 2.0551724137931036,
"grad_norm": 0.2035428285598755,
"learning_rate": 1.4916840620460233e-05,
"loss": 1.446,
"step": 894
},
{
"epoch": 2.057471264367816,
"grad_norm": 0.20885708928108215,
"learning_rate": 1.4889121269053179e-05,
"loss": 1.4716,
"step": 895
},
{
"epoch": 2.0597701149425287,
"grad_norm": 0.19893814623355865,
"learning_rate": 1.486140229630664e-05,
"loss": 1.3703,
"step": 896
},
{
"epoch": 2.0620689655172413,
"grad_norm": 0.20125584304332733,
"learning_rate": 1.4833683796883328e-05,
"loss": 1.5755,
"step": 897
},
{
"epoch": 2.064367816091954,
"grad_norm": 0.18738676607608795,
"learning_rate": 1.4805965865444324e-05,
"loss": 1.3302,
"step": 898
},
{
"epoch": 2.066666666666667,
"grad_norm": 0.17925013601779938,
"learning_rate": 1.4778248596648788e-05,
"loss": 1.4332,
"step": 899
},
{
"epoch": 2.0689655172413794,
"grad_norm": 0.19425319135189056,
"learning_rate": 1.47505320851536e-05,
"loss": 1.5632,
"step": 900
},
{
"epoch": 2.071264367816092,
"grad_norm": 0.29205477237701416,
"learning_rate": 1.4722816425613054e-05,
"loss": 1.5308,
"step": 901
},
{
"epoch": 2.0735632183908046,
"grad_norm": 0.1984025239944458,
"learning_rate": 1.4695101712678547e-05,
"loss": 1.4004,
"step": 902
},
{
"epoch": 2.075862068965517,
"grad_norm": 0.1838599294424057,
"learning_rate": 1.4667388040998231e-05,
"loss": 1.2857,
"step": 903
},
{
"epoch": 2.0781609195402297,
"grad_norm": 0.1972259134054184,
"learning_rate": 1.4639675505216714e-05,
"loss": 1.6735,
"step": 904
},
{
"epoch": 2.0804597701149423,
"grad_norm": 0.18766601383686066,
"learning_rate": 1.4611964199974721e-05,
"loss": 1.4322,
"step": 905
},
{
"epoch": 2.0827586206896553,
"grad_norm": 0.1821257323026657,
"learning_rate": 1.4584254219908757e-05,
"loss": 1.5493,
"step": 906
},
{
"epoch": 2.085057471264368,
"grad_norm": 0.19031888246536255,
"learning_rate": 1.455654565965083e-05,
"loss": 1.4889,
"step": 907
},
{
"epoch": 2.0873563218390805,
"grad_norm": 0.17775827646255493,
"learning_rate": 1.4528838613828076e-05,
"loss": 1.4409,
"step": 908
},
{
"epoch": 2.089655172413793,
"grad_norm": 0.3099232614040375,
"learning_rate": 1.4501133177062477e-05,
"loss": 1.4123,
"step": 909
},
{
"epoch": 2.0919540229885056,
"grad_norm": 0.18985101580619812,
"learning_rate": 1.4473429443970505e-05,
"loss": 1.4216,
"step": 910
},
{
"epoch": 2.094252873563218,
"grad_norm": 0.20878607034683228,
"learning_rate": 1.444572750916283e-05,
"loss": 1.4718,
"step": 911
},
{
"epoch": 2.0965517241379312,
"grad_norm": 0.19711534678936005,
"learning_rate": 1.4418027467243959e-05,
"loss": 1.5302,
"step": 912
},
{
"epoch": 2.098850574712644,
"grad_norm": 0.18261612951755524,
"learning_rate": 1.439032941281195e-05,
"loss": 1.3609,
"step": 913
},
{
"epoch": 2.1011494252873564,
"grad_norm": 0.18803168833255768,
"learning_rate": 1.4362633440458073e-05,
"loss": 1.5301,
"step": 914
},
{
"epoch": 2.103448275862069,
"grad_norm": 0.1860480159521103,
"learning_rate": 1.4334939644766483e-05,
"loss": 1.4043,
"step": 915
},
{
"epoch": 2.1057471264367815,
"grad_norm": 0.19544024765491486,
"learning_rate": 1.430724812031391e-05,
"loss": 1.5548,
"step": 916
},
{
"epoch": 2.108045977011494,
"grad_norm": 0.19993609189987183,
"learning_rate": 1.427955896166931e-05,
"loss": 1.2744,
"step": 917
},
{
"epoch": 2.110344827586207,
"grad_norm": 0.20703446865081787,
"learning_rate": 1.425187226339357e-05,
"loss": 1.5801,
"step": 918
},
{
"epoch": 2.1126436781609197,
"grad_norm": 0.22990703582763672,
"learning_rate": 1.4224188120039186e-05,
"loss": 1.4898,
"step": 919
},
{
"epoch": 2.1149425287356323,
"grad_norm": 0.204385444521904,
"learning_rate": 1.4196506626149906e-05,
"loss": 1.3399,
"step": 920
},
{
"epoch": 2.117241379310345,
"grad_norm": 0.19726674258708954,
"learning_rate": 1.416882787626045e-05,
"loss": 1.5484,
"step": 921
},
{
"epoch": 2.1195402298850574,
"grad_norm": 0.19203300774097443,
"learning_rate": 1.4141151964896161e-05,
"loss": 1.4195,
"step": 922
},
{
"epoch": 2.12183908045977,
"grad_norm": 0.18719951808452606,
"learning_rate": 1.411347898657267e-05,
"loss": 1.3501,
"step": 923
},
{
"epoch": 2.1241379310344826,
"grad_norm": 0.20241260528564453,
"learning_rate": 1.4085809035795622e-05,
"loss": 1.558,
"step": 924
},
{
"epoch": 2.1264367816091956,
"grad_norm": 0.1885083019733429,
"learning_rate": 1.40581422070603e-05,
"loss": 1.6636,
"step": 925
},
{
"epoch": 2.128735632183908,
"grad_norm": 0.19102157652378082,
"learning_rate": 1.4030478594851337e-05,
"loss": 1.2686,
"step": 926
},
{
"epoch": 2.1310344827586207,
"grad_norm": 0.1830718070268631,
"learning_rate": 1.400281829364238e-05,
"loss": 1.3529,
"step": 927
},
{
"epoch": 2.1333333333333333,
"grad_norm": 0.1764451116323471,
"learning_rate": 1.3975161397895753e-05,
"loss": 1.4511,
"step": 928
},
{
"epoch": 2.135632183908046,
"grad_norm": 0.18776477873325348,
"learning_rate": 1.3947508002062176e-05,
"loss": 1.5037,
"step": 929
},
{
"epoch": 2.1379310344827585,
"grad_norm": 0.18442337214946747,
"learning_rate": 1.3919858200580392e-05,
"loss": 1.5692,
"step": 930
},
{
"epoch": 2.1402298850574715,
"grad_norm": 0.1948162317276001,
"learning_rate": 1.3892212087876892e-05,
"loss": 1.6354,
"step": 931
},
{
"epoch": 2.142528735632184,
"grad_norm": 0.1969252973794937,
"learning_rate": 1.3864569758365546e-05,
"loss": 1.5171,
"step": 932
},
{
"epoch": 2.1448275862068966,
"grad_norm": 0.17139415442943573,
"learning_rate": 1.383693130644733e-05,
"loss": 1.4241,
"step": 933
},
{
"epoch": 2.147126436781609,
"grad_norm": 0.19258756935596466,
"learning_rate": 1.3809296826509951e-05,
"loss": 1.6082,
"step": 934
},
{
"epoch": 2.1494252873563218,
"grad_norm": 0.1949881911277771,
"learning_rate": 1.3781666412927563e-05,
"loss": 1.442,
"step": 935
},
{
"epoch": 2.1517241379310343,
"grad_norm": 0.5340209603309631,
"learning_rate": 1.3754040160060443e-05,
"loss": 1.5802,
"step": 936
},
{
"epoch": 2.154022988505747,
"grad_norm": 0.2345278412103653,
"learning_rate": 1.372641816225464e-05,
"loss": 1.3042,
"step": 937
},
{
"epoch": 2.15632183908046,
"grad_norm": 0.18067775666713715,
"learning_rate": 1.3698800513841695e-05,
"loss": 1.5262,
"step": 938
},
{
"epoch": 2.1586206896551725,
"grad_norm": 0.2201727330684662,
"learning_rate": 1.3671187309138267e-05,
"loss": 1.371,
"step": 939
},
{
"epoch": 2.160919540229885,
"grad_norm": 0.17821070551872253,
"learning_rate": 1.3643578642445856e-05,
"loss": 1.734,
"step": 940
},
{
"epoch": 2.1632183908045977,
"grad_norm": 0.26683172583580017,
"learning_rate": 1.3615974608050472e-05,
"loss": 1.2667,
"step": 941
},
{
"epoch": 2.1655172413793102,
"grad_norm": 0.18738000094890594,
"learning_rate": 1.3588375300222285e-05,
"loss": 1.4007,
"step": 942
},
{
"epoch": 2.167816091954023,
"grad_norm": 0.252215713262558,
"learning_rate": 1.3560780813215339e-05,
"loss": 1.4617,
"step": 943
},
{
"epoch": 2.170114942528736,
"grad_norm": 0.1897011697292328,
"learning_rate": 1.3533191241267216e-05,
"loss": 1.5131,
"step": 944
},
{
"epoch": 2.1724137931034484,
"grad_norm": 0.1921589970588684,
"learning_rate": 1.350560667859869e-05,
"loss": 1.4866,
"step": 945
},
{
"epoch": 2.174712643678161,
"grad_norm": 0.2477090209722519,
"learning_rate": 1.3478027219413457e-05,
"loss": 1.589,
"step": 946
},
{
"epoch": 2.1770114942528735,
"grad_norm": 0.2031145691871643,
"learning_rate": 1.3450452957897762e-05,
"loss": 1.5454,
"step": 947
},
{
"epoch": 2.179310344827586,
"grad_norm": 0.191355898976326,
"learning_rate": 1.3422883988220117e-05,
"loss": 1.4621,
"step": 948
},
{
"epoch": 2.1816091954022987,
"grad_norm": 0.21974201500415802,
"learning_rate": 1.3395320404530955e-05,
"loss": 1.3494,
"step": 949
},
{
"epoch": 2.1839080459770113,
"grad_norm": 0.19582334160804749,
"learning_rate": 1.3367762300962302e-05,
"loss": 1.5955,
"step": 950
},
{
"epoch": 2.1862068965517243,
"grad_norm": 0.1870322823524475,
"learning_rate": 1.334020977162749e-05,
"loss": 1.398,
"step": 951
},
{
"epoch": 2.188505747126437,
"grad_norm": 0.2001653015613556,
"learning_rate": 1.33126629106208e-05,
"loss": 1.2126,
"step": 952
},
{
"epoch": 2.1908045977011494,
"grad_norm": 0.23126742243766785,
"learning_rate": 1.3285121812017166e-05,
"loss": 1.2698,
"step": 953
},
{
"epoch": 2.193103448275862,
"grad_norm": 0.1872725635766983,
"learning_rate": 1.325758656987183e-05,
"loss": 1.2937,
"step": 954
},
{
"epoch": 2.1954022988505746,
"grad_norm": 0.19628456234931946,
"learning_rate": 1.3230057278220053e-05,
"loss": 1.5344,
"step": 955
},
{
"epoch": 2.197701149425287,
"grad_norm": 0.1903662383556366,
"learning_rate": 1.3202534031076755e-05,
"loss": 1.6607,
"step": 956
},
{
"epoch": 2.2,
"grad_norm": 0.19235974550247192,
"learning_rate": 1.3175016922436215e-05,
"loss": 1.5043,
"step": 957
},
{
"epoch": 2.2022988505747128,
"grad_norm": 0.22394905984401703,
"learning_rate": 1.3147506046271764e-05,
"loss": 1.4004,
"step": 958
},
{
"epoch": 2.2045977011494253,
"grad_norm": 0.19350716471672058,
"learning_rate": 1.3120001496535434e-05,
"loss": 1.3991,
"step": 959
},
{
"epoch": 2.206896551724138,
"grad_norm": 0.2511136829853058,
"learning_rate": 1.3092503367157666e-05,
"loss": 1.3033,
"step": 960
},
{
"epoch": 2.2091954022988505,
"grad_norm": 0.3526964485645294,
"learning_rate": 1.3065011752046955e-05,
"loss": 1.3822,
"step": 961
},
{
"epoch": 2.211494252873563,
"grad_norm": 0.19208379089832306,
"learning_rate": 1.303752674508956e-05,
"loss": 1.6581,
"step": 962
},
{
"epoch": 2.213793103448276,
"grad_norm": 0.20930515229701996,
"learning_rate": 1.3010048440149179e-05,
"loss": 1.4776,
"step": 963
},
{
"epoch": 2.2160919540229886,
"grad_norm": 0.19552908837795258,
"learning_rate": 1.2982576931066606e-05,
"loss": 1.3648,
"step": 964
},
{
"epoch": 2.218390804597701,
"grad_norm": 0.20852288603782654,
"learning_rate": 1.2955112311659447e-05,
"loss": 1.4711,
"step": 965
},
{
"epoch": 2.220689655172414,
"grad_norm": 0.1920207142829895,
"learning_rate": 1.2927654675721771e-05,
"loss": 1.3646,
"step": 966
},
{
"epoch": 2.2229885057471264,
"grad_norm": 0.19172824919223785,
"learning_rate": 1.2900204117023778e-05,
"loss": 1.5206,
"step": 967
},
{
"epoch": 2.225287356321839,
"grad_norm": 0.19106994569301605,
"learning_rate": 1.2872760729311531e-05,
"loss": 1.3827,
"step": 968
},
{
"epoch": 2.227586206896552,
"grad_norm": 0.1977798491716385,
"learning_rate": 1.2845324606306578e-05,
"loss": 1.3768,
"step": 969
},
{
"epoch": 2.2298850574712645,
"grad_norm": 0.18658989667892456,
"learning_rate": 1.2817895841705675e-05,
"loss": 1.6373,
"step": 970
},
{
"epoch": 2.232183908045977,
"grad_norm": 0.21301044523715973,
"learning_rate": 1.2790474529180435e-05,
"loss": 1.5666,
"step": 971
},
{
"epoch": 2.2344827586206897,
"grad_norm": 0.1722666472196579,
"learning_rate": 1.2763060762377036e-05,
"loss": 1.2645,
"step": 972
},
{
"epoch": 2.2367816091954023,
"grad_norm": 0.1828218549489975,
"learning_rate": 1.2735654634915872e-05,
"loss": 1.593,
"step": 973
},
{
"epoch": 2.239080459770115,
"grad_norm": 0.21385174989700317,
"learning_rate": 1.2708256240391252e-05,
"loss": 1.4721,
"step": 974
},
{
"epoch": 2.2413793103448274,
"grad_norm": 0.201895073056221,
"learning_rate": 1.2680865672371083e-05,
"loss": 1.3898,
"step": 975
},
{
"epoch": 2.2436781609195404,
"grad_norm": 0.20975852012634277,
"learning_rate": 1.2653483024396535e-05,
"loss": 1.3854,
"step": 976
},
{
"epoch": 2.245977011494253,
"grad_norm": 0.20706096291542053,
"learning_rate": 1.2626108389981744e-05,
"loss": 1.3305,
"step": 977
},
{
"epoch": 2.2482758620689656,
"grad_norm": 0.1918448954820633,
"learning_rate": 1.259874186261346e-05,
"loss": 1.3897,
"step": 978
},
{
"epoch": 2.250574712643678,
"grad_norm": 0.21096786856651306,
"learning_rate": 1.2571383535750756e-05,
"loss": 1.3441,
"step": 979
},
{
"epoch": 2.2528735632183907,
"grad_norm": 0.2297007441520691,
"learning_rate": 1.2544033502824708e-05,
"loss": 1.5626,
"step": 980
},
{
"epoch": 2.2551724137931033,
"grad_norm": 0.1851639300584793,
"learning_rate": 1.251669185723805e-05,
"loss": 1.4984,
"step": 981
},
{
"epoch": 2.2551724137931033,
"eval_loss": 2.1876463890075684,
"eval_runtime": 24.8774,
"eval_samples_per_second": 8.642,
"eval_steps_per_second": 0.563,
"step": 981
},
{
"epoch": 2.2574712643678163,
"grad_norm": 0.18381963670253754,
"learning_rate": 1.2489358692364888e-05,
"loss": 1.4801,
"step": 982
},
{
"epoch": 2.259770114942529,
"grad_norm": 0.23209652304649353,
"learning_rate": 1.2462034101550365e-05,
"loss": 1.3365,
"step": 983
},
{
"epoch": 2.2620689655172415,
"grad_norm": 0.1853378713130951,
"learning_rate": 1.2434718178110323e-05,
"loss": 1.3826,
"step": 984
},
{
"epoch": 2.264367816091954,
"grad_norm": 0.19722920656204224,
"learning_rate": 1.2407411015331031e-05,
"loss": 1.3124,
"step": 985
},
{
"epoch": 2.2666666666666666,
"grad_norm": 0.18686692416667938,
"learning_rate": 1.2380112706468817e-05,
"loss": 1.3264,
"step": 986
},
{
"epoch": 2.268965517241379,
"grad_norm": 0.2018072009086609,
"learning_rate": 1.2352823344749792e-05,
"loss": 1.6665,
"step": 987
},
{
"epoch": 2.2712643678160918,
"grad_norm": 0.19831523299217224,
"learning_rate": 1.2325543023369502e-05,
"loss": 1.4166,
"step": 988
},
{
"epoch": 2.2735632183908048,
"grad_norm": 0.2006044089794159,
"learning_rate": 1.2298271835492607e-05,
"loss": 1.3979,
"step": 989
},
{
"epoch": 2.2758620689655173,
"grad_norm": 0.1988469958305359,
"learning_rate": 1.22710098742526e-05,
"loss": 1.5007,
"step": 990
},
{
"epoch": 2.27816091954023,
"grad_norm": 0.19690412282943726,
"learning_rate": 1.2243757232751444e-05,
"loss": 1.5235,
"step": 991
},
{
"epoch": 2.2804597701149425,
"grad_norm": 0.18030837178230286,
"learning_rate": 1.221651400405929e-05,
"loss": 1.5258,
"step": 992
},
{
"epoch": 2.282758620689655,
"grad_norm": 0.22122818231582642,
"learning_rate": 1.2189280281214128e-05,
"loss": 1.4697,
"step": 993
},
{
"epoch": 2.2850574712643676,
"grad_norm": 0.18462435901165009,
"learning_rate": 1.2162056157221507e-05,
"loss": 1.5503,
"step": 994
},
{
"epoch": 2.2873563218390807,
"grad_norm": 0.21442247927188873,
"learning_rate": 1.2134841725054158e-05,
"loss": 1.498,
"step": 995
},
{
"epoch": 2.2896551724137932,
"grad_norm": 0.216175839304924,
"learning_rate": 1.2107637077651749e-05,
"loss": 1.5532,
"step": 996
},
{
"epoch": 2.291954022988506,
"grad_norm": 0.19552576541900635,
"learning_rate": 1.208044230792052e-05,
"loss": 1.3205,
"step": 997
},
{
"epoch": 2.2942528735632184,
"grad_norm": 0.19923120737075806,
"learning_rate": 1.2053257508732971e-05,
"loss": 1.4812,
"step": 998
},
{
"epoch": 2.296551724137931,
"grad_norm": 0.18821905553340912,
"learning_rate": 1.2026082772927574e-05,
"loss": 1.5493,
"step": 999
},
{
"epoch": 2.2988505747126435,
"grad_norm": 0.1969912201166153,
"learning_rate": 1.1998918193308394e-05,
"loss": 1.4289,
"step": 1000
},
{
"epoch": 2.301149425287356,
"grad_norm": 0.18950709700584412,
"learning_rate": 1.197176386264485e-05,
"loss": 1.4869,
"step": 1001
},
{
"epoch": 2.303448275862069,
"grad_norm": 0.18380513787269592,
"learning_rate": 1.1944619873671338e-05,
"loss": 1.4076,
"step": 1002
},
{
"epoch": 2.3057471264367817,
"grad_norm": 0.22406890988349915,
"learning_rate": 1.1917486319086951e-05,
"loss": 1.5625,
"step": 1003
},
{
"epoch": 2.3080459770114943,
"grad_norm": 0.2022385597229004,
"learning_rate": 1.1890363291555131e-05,
"loss": 1.4068,
"step": 1004
},
{
"epoch": 2.310344827586207,
"grad_norm": 0.19463582336902618,
"learning_rate": 1.186325088370339e-05,
"loss": 1.2753,
"step": 1005
},
{
"epoch": 2.3126436781609194,
"grad_norm": 0.18611028790473938,
"learning_rate": 1.1836149188122954e-05,
"loss": 1.3297,
"step": 1006
},
{
"epoch": 2.314942528735632,
"grad_norm": 0.1949577033519745,
"learning_rate": 1.180905829736847e-05,
"loss": 1.3138,
"step": 1007
},
{
"epoch": 2.317241379310345,
"grad_norm": 0.20056572556495667,
"learning_rate": 1.1781978303957692e-05,
"loss": 1.4569,
"step": 1008
},
{
"epoch": 2.3195402298850576,
"grad_norm": 0.19708208739757538,
"learning_rate": 1.1754909300371154e-05,
"loss": 1.6108,
"step": 1009
},
{
"epoch": 2.32183908045977,
"grad_norm": 0.1828652322292328,
"learning_rate": 1.1727851379051866e-05,
"loss": 1.5717,
"step": 1010
},
{
"epoch": 2.3241379310344827,
"grad_norm": 0.19695712625980377,
"learning_rate": 1.1700804632404975e-05,
"loss": 1.4504,
"step": 1011
},
{
"epoch": 2.3264367816091953,
"grad_norm": 0.19068467617034912,
"learning_rate": 1.1673769152797476e-05,
"loss": 1.2177,
"step": 1012
},
{
"epoch": 2.328735632183908,
"grad_norm": 0.17437922954559326,
"learning_rate": 1.1646745032557895e-05,
"loss": 1.5688,
"step": 1013
},
{
"epoch": 2.3310344827586205,
"grad_norm": 0.20193716883659363,
"learning_rate": 1.1619732363975943e-05,
"loss": 1.5454,
"step": 1014
},
{
"epoch": 2.3333333333333335,
"grad_norm": 0.2042461633682251,
"learning_rate": 1.1592731239302245e-05,
"loss": 1.432,
"step": 1015
},
{
"epoch": 2.335632183908046,
"grad_norm": 0.19896206259727478,
"learning_rate": 1.1565741750747992e-05,
"loss": 1.4365,
"step": 1016
},
{
"epoch": 2.3379310344827586,
"grad_norm": 0.19529391825199127,
"learning_rate": 1.1538763990484629e-05,
"loss": 1.5147,
"step": 1017
},
{
"epoch": 2.340229885057471,
"grad_norm": 0.19452182948589325,
"learning_rate": 1.1511798050643563e-05,
"loss": 1.3789,
"step": 1018
},
{
"epoch": 2.342528735632184,
"grad_norm": 0.18945521116256714,
"learning_rate": 1.148484402331582e-05,
"loss": 1.2347,
"step": 1019
},
{
"epoch": 2.344827586206897,
"grad_norm": 0.19543799757957458,
"learning_rate": 1.1457902000551754e-05,
"loss": 1.4665,
"step": 1020
},
{
"epoch": 2.3471264367816094,
"grad_norm": 0.2242080420255661,
"learning_rate": 1.1430972074360722e-05,
"loss": 1.5321,
"step": 1021
},
{
"epoch": 2.349425287356322,
"grad_norm": 0.23366563022136688,
"learning_rate": 1.1404054336710757e-05,
"loss": 1.3509,
"step": 1022
},
{
"epoch": 2.3517241379310345,
"grad_norm": 0.19565559923648834,
"learning_rate": 1.1377148879528283e-05,
"loss": 1.3139,
"step": 1023
},
{
"epoch": 2.354022988505747,
"grad_norm": 0.19262279570102692,
"learning_rate": 1.1350255794697776e-05,
"loss": 1.3579,
"step": 1024
},
{
"epoch": 2.3563218390804597,
"grad_norm": 0.19497279822826385,
"learning_rate": 1.1323375174061463e-05,
"loss": 1.3149,
"step": 1025
},
{
"epoch": 2.3586206896551722,
"grad_norm": 0.20603136718273163,
"learning_rate": 1.1296507109419001e-05,
"loss": 1.5356,
"step": 1026
},
{
"epoch": 2.360919540229885,
"grad_norm": 0.185031920671463,
"learning_rate": 1.1269651692527181e-05,
"loss": 1.3129,
"step": 1027
},
{
"epoch": 2.363218390804598,
"grad_norm": 0.2549673914909363,
"learning_rate": 1.1242809015099577e-05,
"loss": 1.6995,
"step": 1028
},
{
"epoch": 2.3655172413793104,
"grad_norm": 0.17490439116954803,
"learning_rate": 1.1215979168806267e-05,
"loss": 1.2872,
"step": 1029
},
{
"epoch": 2.367816091954023,
"grad_norm": 0.18390822410583496,
"learning_rate": 1.1189162245273524e-05,
"loss": 1.2762,
"step": 1030
},
{
"epoch": 2.3701149425287356,
"grad_norm": 0.1884651631116867,
"learning_rate": 1.1162358336083466e-05,
"loss": 1.3768,
"step": 1031
},
{
"epoch": 2.372413793103448,
"grad_norm": 0.19316701591014862,
"learning_rate": 1.1135567532773787e-05,
"loss": 1.518,
"step": 1032
},
{
"epoch": 2.374712643678161,
"grad_norm": 0.22807134687900543,
"learning_rate": 1.11087899268374e-05,
"loss": 1.5162,
"step": 1033
},
{
"epoch": 2.3770114942528737,
"grad_norm": 0.20298898220062256,
"learning_rate": 1.1082025609722168e-05,
"loss": 1.4899,
"step": 1034
},
{
"epoch": 2.3793103448275863,
"grad_norm": 0.19132304191589355,
"learning_rate": 1.1055274672830564e-05,
"loss": 1.4635,
"step": 1035
},
{
"epoch": 2.381609195402299,
"grad_norm": 0.1791120171546936,
"learning_rate": 1.1028537207519361e-05,
"loss": 1.6405,
"step": 1036
},
{
"epoch": 2.3839080459770114,
"grad_norm": 0.24511684477329254,
"learning_rate": 1.1001813305099339e-05,
"loss": 1.6243,
"step": 1037
},
{
"epoch": 2.386206896551724,
"grad_norm": 0.23960284888744354,
"learning_rate": 1.097510305683495e-05,
"loss": 1.5293,
"step": 1038
},
{
"epoch": 2.3885057471264366,
"grad_norm": 0.20676308870315552,
"learning_rate": 1.0948406553944008e-05,
"loss": 1.5462,
"step": 1039
},
{
"epoch": 2.3908045977011496,
"grad_norm": 0.21602274477481842,
"learning_rate": 1.0921723887597401e-05,
"loss": 1.4772,
"step": 1040
},
{
"epoch": 2.393103448275862,
"grad_norm": 0.19691680371761322,
"learning_rate": 1.0895055148918758e-05,
"loss": 1.4549,
"step": 1041
},
{
"epoch": 2.3954022988505748,
"grad_norm": 0.20041301846504211,
"learning_rate": 1.0868400428984142e-05,
"loss": 1.5047,
"step": 1042
},
{
"epoch": 2.3977011494252873,
"grad_norm": 0.19415651261806488,
"learning_rate": 1.0841759818821745e-05,
"loss": 1.6689,
"step": 1043
},
{
"epoch": 2.4,
"grad_norm": 0.18533678352832794,
"learning_rate": 1.0815133409411564e-05,
"loss": 1.4217,
"step": 1044
},
{
"epoch": 2.4022988505747125,
"grad_norm": 0.19566786289215088,
"learning_rate": 1.078852129168511e-05,
"loss": 1.3658,
"step": 1045
},
{
"epoch": 2.4045977011494255,
"grad_norm": 0.1847791075706482,
"learning_rate": 1.0761923556525074e-05,
"loss": 1.5785,
"step": 1046
},
{
"epoch": 2.406896551724138,
"grad_norm": 0.2375270426273346,
"learning_rate": 1.073534029476505e-05,
"loss": 1.722,
"step": 1047
},
{
"epoch": 2.4091954022988507,
"grad_norm": 0.2512630522251129,
"learning_rate": 1.0708771597189179e-05,
"loss": 1.3956,
"step": 1048
},
{
"epoch": 2.4114942528735632,
"grad_norm": 0.18428336083889008,
"learning_rate": 1.0682217554531888e-05,
"loss": 1.4999,
"step": 1049
},
{
"epoch": 2.413793103448276,
"grad_norm": 0.1957477331161499,
"learning_rate": 1.0655678257477537e-05,
"loss": 1.2734,
"step": 1050
},
{
"epoch": 2.4160919540229884,
"grad_norm": 0.19492173194885254,
"learning_rate": 1.0629153796660131e-05,
"loss": 1.568,
"step": 1051
},
{
"epoch": 2.418390804597701,
"grad_norm": 0.22521334886550903,
"learning_rate": 1.0602644262663022e-05,
"loss": 1.4276,
"step": 1052
},
{
"epoch": 2.420689655172414,
"grad_norm": 0.18813636898994446,
"learning_rate": 1.057614974601857e-05,
"loss": 1.4475,
"step": 1053
},
{
"epoch": 2.4229885057471265,
"grad_norm": 0.2055845409631729,
"learning_rate": 1.0549670337207866e-05,
"loss": 1.5154,
"step": 1054
},
{
"epoch": 2.425287356321839,
"grad_norm": 0.20405055582523346,
"learning_rate": 1.0523206126660385e-05,
"loss": 1.6102,
"step": 1055
},
{
"epoch": 2.4275862068965517,
"grad_norm": 0.3021277189254761,
"learning_rate": 1.049675720475371e-05,
"loss": 1.4498,
"step": 1056
},
{
"epoch": 2.4298850574712643,
"grad_norm": 0.19433364272117615,
"learning_rate": 1.047032366181322e-05,
"loss": 1.3313,
"step": 1057
},
{
"epoch": 2.432183908045977,
"grad_norm": 0.1909985989332199,
"learning_rate": 1.0443905588111759e-05,
"loss": 1.5346,
"step": 1058
},
{
"epoch": 2.43448275862069,
"grad_norm": 0.214143767952919,
"learning_rate": 1.0417503073869352e-05,
"loss": 1.5162,
"step": 1059
},
{
"epoch": 2.4367816091954024,
"grad_norm": 0.19930069148540497,
"learning_rate": 1.0391116209252886e-05,
"loss": 1.4285,
"step": 1060
},
{
"epoch": 2.439080459770115,
"grad_norm": 0.1828465461730957,
"learning_rate": 1.036474508437579e-05,
"loss": 1.3908,
"step": 1061
},
{
"epoch": 2.4413793103448276,
"grad_norm": 0.19292542338371277,
"learning_rate": 1.0338389789297763e-05,
"loss": 1.4817,
"step": 1062
},
{
"epoch": 2.44367816091954,
"grad_norm": 0.25267738103866577,
"learning_rate": 1.0312050414024421e-05,
"loss": 1.342,
"step": 1063
},
{
"epoch": 2.4459770114942527,
"grad_norm": 0.22905202209949493,
"learning_rate": 1.0285727048507037e-05,
"loss": 1.4067,
"step": 1064
},
{
"epoch": 2.4482758620689653,
"grad_norm": 0.21149522066116333,
"learning_rate": 1.025941978264219e-05,
"loss": 1.566,
"step": 1065
},
{
"epoch": 2.4505747126436783,
"grad_norm": 0.17859013378620148,
"learning_rate": 1.0233128706271476e-05,
"loss": 1.4392,
"step": 1066
},
{
"epoch": 2.452873563218391,
"grad_norm": 0.2677483856678009,
"learning_rate": 1.020685390918122e-05,
"loss": 1.384,
"step": 1067
},
{
"epoch": 2.4551724137931035,
"grad_norm": 0.20974195003509521,
"learning_rate": 1.0180595481102132e-05,
"loss": 1.4513,
"step": 1068
},
{
"epoch": 2.457471264367816,
"grad_norm": 0.18739938735961914,
"learning_rate": 1.015435351170904e-05,
"loss": 1.5291,
"step": 1069
},
{
"epoch": 2.4597701149425286,
"grad_norm": 0.19705593585968018,
"learning_rate": 1.0128128090620544e-05,
"loss": 1.3102,
"step": 1070
},
{
"epoch": 2.462068965517241,
"grad_norm": 0.18651627004146576,
"learning_rate": 1.0101919307398752e-05,
"loss": 1.2257,
"step": 1071
},
{
"epoch": 2.464367816091954,
"grad_norm": 0.18981467187404633,
"learning_rate": 1.0075727251548932e-05,
"loss": 1.3771,
"step": 1072
},
{
"epoch": 2.466666666666667,
"grad_norm": 0.1758469045162201,
"learning_rate": 1.0049552012519231e-05,
"loss": 1.5544,
"step": 1073
},
{
"epoch": 2.4689655172413794,
"grad_norm": 0.1982574760913849,
"learning_rate": 1.0023393679700376e-05,
"loss": 1.3823,
"step": 1074
},
{
"epoch": 2.471264367816092,
"grad_norm": 0.18693828582763672,
"learning_rate": 9.997252342425348e-06,
"loss": 1.3952,
"step": 1075
},
{
"epoch": 2.4735632183908045,
"grad_norm": 0.18848368525505066,
"learning_rate": 9.971128089969095e-06,
"loss": 1.5078,
"step": 1076
},
{
"epoch": 2.475862068965517,
"grad_norm": 0.24691297113895416,
"learning_rate": 9.945021011548208e-06,
"loss": 1.4269,
"step": 1077
},
{
"epoch": 2.4781609195402297,
"grad_norm": 0.1989862024784088,
"learning_rate": 9.91893119632063e-06,
"loss": 1.2489,
"step": 1078
},
{
"epoch": 2.4804597701149427,
"grad_norm": 0.18458174169063568,
"learning_rate": 9.892858733385358e-06,
"loss": 1.5163,
"step": 1079
},
{
"epoch": 2.4827586206896552,
"grad_norm": 0.20888610184192657,
"learning_rate": 9.866803711782116e-06,
"loss": 1.4021,
"step": 1080
},
{
"epoch": 2.485057471264368,
"grad_norm": 0.1761299967765808,
"learning_rate": 9.840766220491078e-06,
"loss": 1.6962,
"step": 1081
},
{
"epoch": 2.4873563218390804,
"grad_norm": 0.20243994891643524,
"learning_rate": 9.814746348432541e-06,
"loss": 1.3591,
"step": 1082
},
{
"epoch": 2.489655172413793,
"grad_norm": 0.24078211188316345,
"learning_rate": 9.78874418446663e-06,
"loss": 1.3616,
"step": 1083
},
{
"epoch": 2.491954022988506,
"grad_norm": 0.7092888355255127,
"learning_rate": 9.762759817393001e-06,
"loss": 1.5583,
"step": 1084
},
{
"epoch": 2.4942528735632186,
"grad_norm": 0.17527657747268677,
"learning_rate": 9.736793335950528e-06,
"loss": 1.3078,
"step": 1085
},
{
"epoch": 2.496551724137931,
"grad_norm": 0.20664143562316895,
"learning_rate": 9.71084482881701e-06,
"loss": 1.4312,
"step": 1086
},
{
"epoch": 2.4988505747126437,
"grad_norm": 0.31934860348701477,
"learning_rate": 9.68491438460886e-06,
"loss": 1.4122,
"step": 1087
},
{
"epoch": 2.5011494252873563,
"grad_norm": 0.19606098532676697,
"learning_rate": 9.65900209188079e-06,
"loss": 1.3802,
"step": 1088
},
{
"epoch": 2.503448275862069,
"grad_norm": 0.20938873291015625,
"learning_rate": 9.633108039125544e-06,
"loss": 1.4625,
"step": 1089
},
{
"epoch": 2.5057471264367814,
"grad_norm": 0.19828255474567413,
"learning_rate": 9.607232314773565e-06,
"loss": 1.3767,
"step": 1090
},
{
"epoch": 2.5057471264367814,
"eval_loss": 2.184027671813965,
"eval_runtime": 24.8676,
"eval_samples_per_second": 8.646,
"eval_steps_per_second": 0.563,
"step": 1090
}
],
"logging_steps": 1,
"max_steps": 1740,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 218,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.670024202099045e+19,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}