praison's picture
Upload folder using huggingface_hub
eb1c88e verified
raw
history blame
69.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 108,
"global_step": 431,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 0.44969096779823303,
"learning_rate": 1e-05,
"loss": 1.2567,
"step": 1
},
{
"epoch": 0.0,
"eval_loss": 1.3469510078430176,
"eval_runtime": 4.7982,
"eval_samples_per_second": 20.841,
"eval_steps_per_second": 20.841,
"step": 1
},
{
"epoch": 0.0,
"grad_norm": 0.4098110496997833,
"learning_rate": 2e-05,
"loss": 1.3328,
"step": 2
},
{
"epoch": 0.01,
"grad_norm": 0.5452544093132019,
"learning_rate": 3e-05,
"loss": 1.6567,
"step": 3
},
{
"epoch": 0.01,
"grad_norm": 0.7305347323417664,
"learning_rate": 4e-05,
"loss": 1.5499,
"step": 4
},
{
"epoch": 0.01,
"grad_norm": 0.34722596406936646,
"learning_rate": 5e-05,
"loss": 1.4343,
"step": 5
},
{
"epoch": 0.01,
"grad_norm": 0.5768171548843384,
"learning_rate": 6e-05,
"loss": 1.2677,
"step": 6
},
{
"epoch": 0.02,
"grad_norm": 0.49281951785087585,
"learning_rate": 7e-05,
"loss": 1.473,
"step": 7
},
{
"epoch": 0.02,
"grad_norm": 0.42547014355659485,
"learning_rate": 8e-05,
"loss": 1.406,
"step": 8
},
{
"epoch": 0.02,
"grad_norm": 0.40852880477905273,
"learning_rate": 9e-05,
"loss": 1.2842,
"step": 9
},
{
"epoch": 0.02,
"grad_norm": 0.36900222301483154,
"learning_rate": 0.0001,
"loss": 1.1442,
"step": 10
},
{
"epoch": 0.03,
"grad_norm": 0.40908315777778625,
"learning_rate": 0.00011000000000000002,
"loss": 1.4667,
"step": 11
},
{
"epoch": 0.03,
"grad_norm": 0.4117198884487152,
"learning_rate": 0.00012,
"loss": 0.9759,
"step": 12
},
{
"epoch": 0.03,
"grad_norm": 0.6714757084846497,
"learning_rate": 0.00013000000000000002,
"loss": 1.5162,
"step": 13
},
{
"epoch": 0.03,
"grad_norm": 0.5178409218788147,
"learning_rate": 0.00014,
"loss": 1.1519,
"step": 14
},
{
"epoch": 0.03,
"grad_norm": 1.1334081888198853,
"learning_rate": 0.00015000000000000001,
"loss": 1.2767,
"step": 15
},
{
"epoch": 0.04,
"grad_norm": 0.6541109681129456,
"learning_rate": 0.00016,
"loss": 1.3227,
"step": 16
},
{
"epoch": 0.04,
"grad_norm": 0.5143316984176636,
"learning_rate": 0.00017,
"loss": 1.2991,
"step": 17
},
{
"epoch": 0.04,
"grad_norm": 0.5004872679710388,
"learning_rate": 0.00018,
"loss": 1.3201,
"step": 18
},
{
"epoch": 0.04,
"grad_norm": 0.4225166141986847,
"learning_rate": 0.00019,
"loss": 1.2054,
"step": 19
},
{
"epoch": 0.05,
"grad_norm": 0.8387117385864258,
"learning_rate": 0.0002,
"loss": 1.2026,
"step": 20
},
{
"epoch": 0.05,
"grad_norm": 0.6876248717308044,
"learning_rate": 0.00019999707864731247,
"loss": 1.2311,
"step": 21
},
{
"epoch": 0.05,
"grad_norm": 0.6449929475784302,
"learning_rate": 0.00019998831475993593,
"loss": 1.3162,
"step": 22
},
{
"epoch": 0.05,
"grad_norm": 0.6817747950553894,
"learning_rate": 0.00019997370884991842,
"loss": 1.5836,
"step": 23
},
{
"epoch": 0.06,
"grad_norm": 0.5388895273208618,
"learning_rate": 0.0001999532617706403,
"loss": 1.3085,
"step": 24
},
{
"epoch": 0.06,
"grad_norm": 0.48557716608047485,
"learning_rate": 0.00019992697471676413,
"loss": 1.3159,
"step": 25
},
{
"epoch": 0.06,
"grad_norm": 0.531157910823822,
"learning_rate": 0.00019989484922416502,
"loss": 1.2498,
"step": 26
},
{
"epoch": 0.06,
"grad_norm": 0.47394225001335144,
"learning_rate": 0.0001998568871698409,
"loss": 1.1981,
"step": 27
},
{
"epoch": 0.06,
"grad_norm": 0.48895126581192017,
"learning_rate": 0.00019981309077180272,
"loss": 1.0461,
"step": 28
},
{
"epoch": 0.07,
"grad_norm": 0.4990120828151703,
"learning_rate": 0.00019976346258894503,
"loss": 1.3558,
"step": 29
},
{
"epoch": 0.07,
"grad_norm": 0.6515373587608337,
"learning_rate": 0.00019970800552089623,
"loss": 1.2566,
"step": 30
},
{
"epoch": 0.07,
"grad_norm": 0.4564642012119293,
"learning_rate": 0.00019964672280784954,
"loss": 1.1579,
"step": 31
},
{
"epoch": 0.07,
"grad_norm": 0.6385357975959778,
"learning_rate": 0.00019957961803037326,
"loss": 1.1824,
"step": 32
},
{
"epoch": 0.08,
"grad_norm": 0.5059694051742554,
"learning_rate": 0.00019950669510920184,
"loss": 1.0092,
"step": 33
},
{
"epoch": 0.08,
"grad_norm": 0.49390971660614014,
"learning_rate": 0.0001994279583050067,
"loss": 1.1982,
"step": 34
},
{
"epoch": 0.08,
"grad_norm": 0.6610875129699707,
"learning_rate": 0.00019934341221814739,
"loss": 1.5833,
"step": 35
},
{
"epoch": 0.08,
"grad_norm": 0.5280133485794067,
"learning_rate": 0.0001992530617884026,
"loss": 0.9696,
"step": 36
},
{
"epoch": 0.09,
"grad_norm": 0.49730122089385986,
"learning_rate": 0.00019915691229468178,
"loss": 1.1866,
"step": 37
},
{
"epoch": 0.09,
"grad_norm": 0.8253684043884277,
"learning_rate": 0.00019905496935471658,
"loss": 1.7239,
"step": 38
},
{
"epoch": 0.09,
"grad_norm": 0.4826942980289459,
"learning_rate": 0.0001989472389247326,
"loss": 1.5085,
"step": 39
},
{
"epoch": 0.09,
"grad_norm": 0.6226486563682556,
"learning_rate": 0.00019883372729910152,
"loss": 1.1311,
"step": 40
},
{
"epoch": 0.1,
"grad_norm": 0.4536150097846985,
"learning_rate": 0.0001987144411099731,
"loss": 1.243,
"step": 41
},
{
"epoch": 0.1,
"grad_norm": 0.48488786816596985,
"learning_rate": 0.000198589387326888,
"loss": 1.2221,
"step": 42
},
{
"epoch": 0.1,
"grad_norm": 0.4422035813331604,
"learning_rate": 0.00019845857325637031,
"loss": 1.5296,
"step": 43
},
{
"epoch": 0.1,
"grad_norm": 0.47116392850875854,
"learning_rate": 0.00019832200654150076,
"loss": 1.1176,
"step": 44
},
{
"epoch": 0.1,
"grad_norm": 0.4207026958465576,
"learning_rate": 0.0001981796951614701,
"loss": 1.0939,
"step": 45
},
{
"epoch": 0.11,
"grad_norm": 0.5403062105178833,
"learning_rate": 0.00019803164743111302,
"loss": 1.2371,
"step": 46
},
{
"epoch": 0.11,
"grad_norm": 0.6009058952331543,
"learning_rate": 0.00019787787200042223,
"loss": 1.3423,
"step": 47
},
{
"epoch": 0.11,
"grad_norm": 0.421722412109375,
"learning_rate": 0.00019771837785404305,
"loss": 0.9633,
"step": 48
},
{
"epoch": 0.11,
"grad_norm": 0.5040818452835083,
"learning_rate": 0.00019755317431074859,
"loss": 1.3888,
"step": 49
},
{
"epoch": 0.12,
"grad_norm": 0.5417558550834656,
"learning_rate": 0.0001973822710228951,
"loss": 1.0181,
"step": 50
},
{
"epoch": 0.12,
"grad_norm": 0.5744611024856567,
"learning_rate": 0.00019720567797585817,
"loss": 1.3067,
"step": 51
},
{
"epoch": 0.12,
"grad_norm": 0.4889126121997833,
"learning_rate": 0.0001970234054874493,
"loss": 1.1691,
"step": 52
},
{
"epoch": 0.12,
"grad_norm": 0.6123921275138855,
"learning_rate": 0.0001968354642073129,
"loss": 1.2479,
"step": 53
},
{
"epoch": 0.13,
"grad_norm": 0.5839653611183167,
"learning_rate": 0.00019664186511630433,
"loss": 0.8839,
"step": 54
},
{
"epoch": 0.13,
"grad_norm": 0.40772297978401184,
"learning_rate": 0.000196442619525848,
"loss": 1.2291,
"step": 55
},
{
"epoch": 0.13,
"grad_norm": 0.5853259563446045,
"learning_rate": 0.00019623773907727682,
"loss": 1.4134,
"step": 56
},
{
"epoch": 0.13,
"grad_norm": 0.6176974177360535,
"learning_rate": 0.0001960272357411517,
"loss": 1.3261,
"step": 57
},
{
"epoch": 0.13,
"grad_norm": 0.4556988477706909,
"learning_rate": 0.0001958111218165624,
"loss": 1.1442,
"step": 58
},
{
"epoch": 0.14,
"grad_norm": 0.46846720576286316,
"learning_rate": 0.00019558940993040885,
"loss": 1.0652,
"step": 59
},
{
"epoch": 0.14,
"grad_norm": 0.4391572177410126,
"learning_rate": 0.00019536211303666323,
"loss": 1.3619,
"step": 60
},
{
"epoch": 0.14,
"grad_norm": 0.4686979651451111,
"learning_rate": 0.00019512924441561348,
"loss": 0.5938,
"step": 61
},
{
"epoch": 0.14,
"grad_norm": 0.430164635181427,
"learning_rate": 0.00019489081767308698,
"loss": 1.2571,
"step": 62
},
{
"epoch": 0.15,
"grad_norm": 0.6731412410736084,
"learning_rate": 0.00019464684673965583,
"loss": 1.3784,
"step": 63
},
{
"epoch": 0.15,
"grad_norm": 0.39849698543548584,
"learning_rate": 0.0001943973458698229,
"loss": 0.9475,
"step": 64
},
{
"epoch": 0.15,
"grad_norm": 0.5062661170959473,
"learning_rate": 0.00019414232964118892,
"loss": 1.1145,
"step": 65
},
{
"epoch": 0.15,
"grad_norm": 0.5099257230758667,
"learning_rate": 0.00019388181295360078,
"loss": 1.0426,
"step": 66
},
{
"epoch": 0.16,
"grad_norm": 0.5760392546653748,
"learning_rate": 0.00019361581102828095,
"loss": 1.057,
"step": 67
},
{
"epoch": 0.16,
"grad_norm": 0.41587546467781067,
"learning_rate": 0.0001933443394069383,
"loss": 1.181,
"step": 68
},
{
"epoch": 0.16,
"grad_norm": 0.47386714816093445,
"learning_rate": 0.00019306741395085976,
"loss": 1.1613,
"step": 69
},
{
"epoch": 0.16,
"grad_norm": 0.39666488766670227,
"learning_rate": 0.0001927850508399839,
"loss": 1.1075,
"step": 70
},
{
"epoch": 0.16,
"grad_norm": 0.4820801019668579,
"learning_rate": 0.00019249726657195532,
"loss": 1.3065,
"step": 71
},
{
"epoch": 0.17,
"grad_norm": 0.4606281518936157,
"learning_rate": 0.00019220407796116098,
"loss": 1.3073,
"step": 72
},
{
"epoch": 0.17,
"grad_norm": 0.7897779941558838,
"learning_rate": 0.00019190550213774756,
"loss": 1.162,
"step": 73
},
{
"epoch": 0.17,
"grad_norm": 0.42179742455482483,
"learning_rate": 0.00019160155654662076,
"loss": 0.7054,
"step": 74
},
{
"epoch": 0.17,
"grad_norm": 0.5278844237327576,
"learning_rate": 0.00019129225894642593,
"loss": 1.0787,
"step": 75
},
{
"epoch": 0.18,
"grad_norm": 0.42007845640182495,
"learning_rate": 0.00019097762740851061,
"loss": 1.0423,
"step": 76
},
{
"epoch": 0.18,
"grad_norm": 0.5332473516464233,
"learning_rate": 0.0001906576803158686,
"loss": 1.1466,
"step": 77
},
{
"epoch": 0.18,
"grad_norm": 0.5041698217391968,
"learning_rate": 0.0001903324363620659,
"loss": 1.0691,
"step": 78
},
{
"epoch": 0.18,
"grad_norm": 0.2976062595844269,
"learning_rate": 0.0001900019145501484,
"loss": 0.6296,
"step": 79
},
{
"epoch": 0.19,
"grad_norm": 0.4532124400138855,
"learning_rate": 0.0001896661341915318,
"loss": 1.4112,
"step": 80
},
{
"epoch": 0.19,
"grad_norm": 0.4600175619125366,
"learning_rate": 0.0001893251149048732,
"loss": 1.0353,
"step": 81
},
{
"epoch": 0.19,
"grad_norm": 0.5047218203544617,
"learning_rate": 0.00018897887661492474,
"loss": 1.1204,
"step": 82
},
{
"epoch": 0.19,
"grad_norm": 0.5466210246086121,
"learning_rate": 0.00018862743955136966,
"loss": 1.4353,
"step": 83
},
{
"epoch": 0.19,
"grad_norm": 0.3947051465511322,
"learning_rate": 0.0001882708242476401,
"loss": 1.0523,
"step": 84
},
{
"epoch": 0.2,
"grad_norm": 0.4432850778102875,
"learning_rate": 0.00018790905153971758,
"loss": 0.8657,
"step": 85
},
{
"epoch": 0.2,
"grad_norm": 0.4575612246990204,
"learning_rate": 0.00018754214256491562,
"loss": 1.0524,
"step": 86
},
{
"epoch": 0.2,
"grad_norm": 0.3713025748729706,
"learning_rate": 0.00018717011876064453,
"loss": 1.0439,
"step": 87
},
{
"epoch": 0.2,
"grad_norm": 0.4547780156135559,
"learning_rate": 0.0001867930018631592,
"loss": 1.01,
"step": 88
},
{
"epoch": 0.21,
"grad_norm": 0.421790212392807,
"learning_rate": 0.00018641081390628877,
"loss": 1.1949,
"step": 89
},
{
"epoch": 0.21,
"grad_norm": 0.4341322183609009,
"learning_rate": 0.00018602357722014964,
"loss": 1.2932,
"step": 90
},
{
"epoch": 0.21,
"grad_norm": 0.3753775358200073,
"learning_rate": 0.00018563131442984044,
"loss": 1.0415,
"step": 91
},
{
"epoch": 0.21,
"grad_norm": 0.5391212105751038,
"learning_rate": 0.00018523404845412027,
"loss": 1.1474,
"step": 92
},
{
"epoch": 0.22,
"grad_norm": 0.7697898149490356,
"learning_rate": 0.0001848318025040697,
"loss": 1.3765,
"step": 93
},
{
"epoch": 0.22,
"grad_norm": 0.39486926794052124,
"learning_rate": 0.00018442460008173445,
"loss": 1.0153,
"step": 94
},
{
"epoch": 0.22,
"grad_norm": 0.4511030912399292,
"learning_rate": 0.0001840124649787524,
"loss": 1.0658,
"step": 95
},
{
"epoch": 0.22,
"grad_norm": 0.5483732223510742,
"learning_rate": 0.0001835954212749632,
"loss": 1.1011,
"step": 96
},
{
"epoch": 0.23,
"grad_norm": 0.3995431959629059,
"learning_rate": 0.0001831734933370019,
"loss": 0.8759,
"step": 97
},
{
"epoch": 0.23,
"grad_norm": 0.4208924472332001,
"learning_rate": 0.0001827467058168748,
"loss": 0.8876,
"step": 98
},
{
"epoch": 0.23,
"grad_norm": 0.568627119064331,
"learning_rate": 0.00018231508365051922,
"loss": 1.313,
"step": 99
},
{
"epoch": 0.23,
"grad_norm": 0.4205207824707031,
"learning_rate": 0.0001818786520563467,
"loss": 1.3252,
"step": 100
},
{
"epoch": 0.23,
"grad_norm": 0.5135630369186401,
"learning_rate": 0.00018143743653376942,
"loss": 1.093,
"step": 101
},
{
"epoch": 0.24,
"grad_norm": 0.558722198009491,
"learning_rate": 0.0001809914628617105,
"loss": 1.5598,
"step": 102
},
{
"epoch": 0.24,
"grad_norm": 0.364212304353714,
"learning_rate": 0.00018054075709709756,
"loss": 1.1574,
"step": 103
},
{
"epoch": 0.24,
"grad_norm": 0.6438787579536438,
"learning_rate": 0.00018008534557334064,
"loss": 1.2912,
"step": 104
},
{
"epoch": 0.24,
"grad_norm": 0.4466971755027771,
"learning_rate": 0.00017962525489879325,
"loss": 1.2194,
"step": 105
},
{
"epoch": 0.25,
"grad_norm": 0.5050408244132996,
"learning_rate": 0.00017916051195519797,
"loss": 0.9488,
"step": 106
},
{
"epoch": 0.25,
"grad_norm": 0.4414922893047333,
"learning_rate": 0.00017869114389611575,
"loss": 0.9977,
"step": 107
},
{
"epoch": 0.25,
"grad_norm": 0.4354766011238098,
"learning_rate": 0.0001782171781453394,
"loss": 1.1738,
"step": 108
},
{
"epoch": 0.25,
"eval_loss": 1.1372472047805786,
"eval_runtime": 4.9728,
"eval_samples_per_second": 20.109,
"eval_steps_per_second": 20.109,
"step": 108
},
{
"epoch": 0.25,
"grad_norm": 0.44711774587631226,
"learning_rate": 0.00017773864239529132,
"loss": 1.0631,
"step": 109
},
{
"epoch": 0.26,
"grad_norm": 0.43031662702560425,
"learning_rate": 0.0001772555646054055,
"loss": 1.0922,
"step": 110
},
{
"epoch": 0.26,
"grad_norm": 0.4053135812282562,
"learning_rate": 0.00017676797300049393,
"loss": 1.2369,
"step": 111
},
{
"epoch": 0.26,
"grad_norm": 0.6041821241378784,
"learning_rate": 0.00017627589606909755,
"loss": 1.2172,
"step": 112
},
{
"epoch": 0.26,
"grad_norm": 0.2745780050754547,
"learning_rate": 0.00017577936256182167,
"loss": 0.4539,
"step": 113
},
{
"epoch": 0.26,
"grad_norm": 0.4951040744781494,
"learning_rate": 0.0001752784014896562,
"loss": 1.3143,
"step": 114
},
{
"epoch": 0.27,
"grad_norm": 0.38725313544273376,
"learning_rate": 0.00017477304212228057,
"loss": 1.0367,
"step": 115
},
{
"epoch": 0.27,
"grad_norm": 0.4349636435508728,
"learning_rate": 0.0001742633139863538,
"loss": 1.1372,
"step": 116
},
{
"epoch": 0.27,
"grad_norm": 0.5229642391204834,
"learning_rate": 0.00017374924686378905,
"loss": 1.2274,
"step": 117
},
{
"epoch": 0.27,
"grad_norm": 0.5884748101234436,
"learning_rate": 0.0001732308707900137,
"loss": 1.1546,
"step": 118
},
{
"epoch": 0.28,
"grad_norm": 0.4116392433643341,
"learning_rate": 0.0001727082160522145,
"loss": 1.1144,
"step": 119
},
{
"epoch": 0.28,
"grad_norm": 0.4359859228134155,
"learning_rate": 0.0001721813131875679,
"loss": 1.0402,
"step": 120
},
{
"epoch": 0.28,
"grad_norm": 0.4674035906791687,
"learning_rate": 0.00017165019298145585,
"loss": 0.7442,
"step": 121
},
{
"epoch": 0.28,
"grad_norm": 0.40642812848091125,
"learning_rate": 0.00017111488646566727,
"loss": 1.1118,
"step": 122
},
{
"epoch": 0.29,
"grad_norm": 0.4694182872772217,
"learning_rate": 0.00017057542491658468,
"loss": 1.3227,
"step": 123
},
{
"epoch": 0.29,
"grad_norm": 0.4917917251586914,
"learning_rate": 0.000170031839853357,
"loss": 1.3724,
"step": 124
},
{
"epoch": 0.29,
"grad_norm": 0.47446152567863464,
"learning_rate": 0.00016948416303605795,
"loss": 1.406,
"step": 125
},
{
"epoch": 0.29,
"grad_norm": 0.36553582549095154,
"learning_rate": 0.0001689324264638304,
"loss": 0.8186,
"step": 126
},
{
"epoch": 0.29,
"grad_norm": 0.3034989535808563,
"learning_rate": 0.00016837666237301663,
"loss": 0.5963,
"step": 127
},
{
"epoch": 0.3,
"grad_norm": 0.5044969320297241,
"learning_rate": 0.00016781690323527511,
"loss": 1.1356,
"step": 128
},
{
"epoch": 0.3,
"grad_norm": 0.449246346950531,
"learning_rate": 0.00016725318175568306,
"loss": 1.015,
"step": 129
},
{
"epoch": 0.3,
"grad_norm": 0.41430914402008057,
"learning_rate": 0.00016668553087082567,
"loss": 1.2896,
"step": 130
},
{
"epoch": 0.3,
"grad_norm": 0.4527166783809662,
"learning_rate": 0.0001661139837468717,
"loss": 1.3077,
"step": 131
},
{
"epoch": 0.31,
"grad_norm": 0.37175431847572327,
"learning_rate": 0.00016553857377763566,
"loss": 1.0345,
"step": 132
},
{
"epoch": 0.31,
"grad_norm": 0.5722200870513916,
"learning_rate": 0.0001649593345826268,
"loss": 1.2999,
"step": 133
},
{
"epoch": 0.31,
"grad_norm": 0.4093303978443146,
"learning_rate": 0.00016437630000508464,
"loss": 0.9219,
"step": 134
},
{
"epoch": 0.31,
"grad_norm": 0.5196316242218018,
"learning_rate": 0.00016378950411000183,
"loss": 1.2376,
"step": 135
},
{
"epoch": 0.32,
"grad_norm": 0.5437043905258179,
"learning_rate": 0.00016319898118213365,
"loss": 1.0182,
"step": 136
},
{
"epoch": 0.32,
"grad_norm": 0.5286529660224915,
"learning_rate": 0.00016260476572399496,
"loss": 1.4231,
"step": 137
},
{
"epoch": 0.32,
"grad_norm": 0.43187054991722107,
"learning_rate": 0.00016200689245384424,
"loss": 1.0627,
"step": 138
},
{
"epoch": 0.32,
"grad_norm": 0.6503031849861145,
"learning_rate": 0.00016140539630365522,
"loss": 1.1164,
"step": 139
},
{
"epoch": 0.32,
"grad_norm": 0.3417191505432129,
"learning_rate": 0.00016080031241707578,
"loss": 0.9242,
"step": 140
},
{
"epoch": 0.33,
"grad_norm": 0.4407976567745209,
"learning_rate": 0.0001601916761473747,
"loss": 1.1057,
"step": 141
},
{
"epoch": 0.33,
"grad_norm": 0.5504916310310364,
"learning_rate": 0.00015957952305537597,
"loss": 1.1505,
"step": 142
},
{
"epoch": 0.33,
"grad_norm": 0.44324642419815063,
"learning_rate": 0.00015896388890738127,
"loss": 1.2143,
"step": 143
},
{
"epoch": 0.33,
"grad_norm": 0.44402655959129333,
"learning_rate": 0.00015834480967308003,
"loss": 1.0909,
"step": 144
},
{
"epoch": 0.34,
"grad_norm": 0.539313554763794,
"learning_rate": 0.00015772232152344795,
"loss": 1.2159,
"step": 145
},
{
"epoch": 0.34,
"grad_norm": 0.5022640824317932,
"learning_rate": 0.0001570964608286336,
"loss": 1.0763,
"step": 146
},
{
"epoch": 0.34,
"grad_norm": 0.4640175402164459,
"learning_rate": 0.00015646726415583344,
"loss": 0.8441,
"step": 147
},
{
"epoch": 0.34,
"grad_norm": 0.47599032521247864,
"learning_rate": 0.0001558347682671553,
"loss": 1.4246,
"step": 148
},
{
"epoch": 0.35,
"grad_norm": 0.6268883943557739,
"learning_rate": 0.00015519901011747044,
"loss": 1.0982,
"step": 149
},
{
"epoch": 0.35,
"grad_norm": 0.5821301937103271,
"learning_rate": 0.00015456002685225448,
"loss": 1.3526,
"step": 150
},
{
"epoch": 0.35,
"grad_norm": 0.6036801934242249,
"learning_rate": 0.00015391785580541698,
"loss": 1.3432,
"step": 151
},
{
"epoch": 0.35,
"grad_norm": 0.44567015767097473,
"learning_rate": 0.0001532725344971202,
"loss": 1.6177,
"step": 152
},
{
"epoch": 0.35,
"grad_norm": 0.5531861782073975,
"learning_rate": 0.0001526241006315869,
"loss": 1.4035,
"step": 153
},
{
"epoch": 0.36,
"grad_norm": 0.40534013509750366,
"learning_rate": 0.00015197259209489747,
"loss": 1.4051,
"step": 154
},
{
"epoch": 0.36,
"grad_norm": 0.49140480160713196,
"learning_rate": 0.00015131804695277612,
"loss": 1.1617,
"step": 155
},
{
"epoch": 0.36,
"grad_norm": 0.5026464462280273,
"learning_rate": 0.00015066050344836706,
"loss": 1.188,
"step": 156
},
{
"epoch": 0.36,
"grad_norm": 0.454348623752594,
"learning_rate": 0.00015000000000000001,
"loss": 1.2269,
"step": 157
},
{
"epoch": 0.37,
"grad_norm": 0.3233983516693115,
"learning_rate": 0.0001493365751989454,
"loss": 0.839,
"step": 158
},
{
"epoch": 0.37,
"grad_norm": 0.35600027441978455,
"learning_rate": 0.0001486702678071598,
"loss": 0.8139,
"step": 159
},
{
"epoch": 0.37,
"grad_norm": 0.3790452480316162,
"learning_rate": 0.00014800111675502094,
"loss": 0.9154,
"step": 160
},
{
"epoch": 0.37,
"grad_norm": 0.3982885777950287,
"learning_rate": 0.00014732916113905335,
"loss": 1.1825,
"step": 161
},
{
"epoch": 0.38,
"grad_norm": 0.5747079253196716,
"learning_rate": 0.0001466544402196439,
"loss": 1.0599,
"step": 162
},
{
"epoch": 0.38,
"grad_norm": 0.412662148475647,
"learning_rate": 0.00014597699341874806,
"loss": 0.7421,
"step": 163
},
{
"epoch": 0.38,
"grad_norm": 0.4285506308078766,
"learning_rate": 0.00014529686031758643,
"loss": 0.8738,
"step": 164
},
{
"epoch": 0.38,
"grad_norm": 0.5278518199920654,
"learning_rate": 0.00014461408065433227,
"loss": 1.3702,
"step": 165
},
{
"epoch": 0.39,
"grad_norm": 0.3949754536151886,
"learning_rate": 0.00014392869432178971,
"loss": 1.005,
"step": 166
},
{
"epoch": 0.39,
"grad_norm": 0.39798328280448914,
"learning_rate": 0.00014324074136506284,
"loss": 1.1153,
"step": 167
},
{
"epoch": 0.39,
"grad_norm": 0.6939488053321838,
"learning_rate": 0.00014255026197921596,
"loss": 1.0646,
"step": 168
},
{
"epoch": 0.39,
"grad_norm": 0.45957663655281067,
"learning_rate": 0.00014185729650692533,
"loss": 1.2686,
"step": 169
},
{
"epoch": 0.39,
"grad_norm": 0.4837738871574402,
"learning_rate": 0.0001411618854361218,
"loss": 1.3417,
"step": 170
},
{
"epoch": 0.4,
"grad_norm": 0.6829615831375122,
"learning_rate": 0.00014046406939762545,
"loss": 1.1174,
"step": 171
},
{
"epoch": 0.4,
"grad_norm": 0.5104063153266907,
"learning_rate": 0.0001397638891627714,
"loss": 1.2003,
"step": 172
},
{
"epoch": 0.4,
"grad_norm": 0.6368303894996643,
"learning_rate": 0.00013906138564102793,
"loss": 1.2944,
"step": 173
},
{
"epoch": 0.4,
"grad_norm": 0.5132100582122803,
"learning_rate": 0.00013835659987760605,
"loss": 1.3055,
"step": 174
},
{
"epoch": 0.41,
"grad_norm": 0.4685085415840149,
"learning_rate": 0.0001376495730510614,
"loss": 1.3442,
"step": 175
},
{
"epoch": 0.41,
"grad_norm": 0.5321069955825806,
"learning_rate": 0.0001369403464708884,
"loss": 1.2254,
"step": 176
},
{
"epoch": 0.41,
"grad_norm": 0.5504405498504639,
"learning_rate": 0.00013622896157510658,
"loss": 1.306,
"step": 177
},
{
"epoch": 0.41,
"grad_norm": 0.4058278203010559,
"learning_rate": 0.00013551545992783947,
"loss": 0.8795,
"step": 178
},
{
"epoch": 0.42,
"grad_norm": 0.4485948979854584,
"learning_rate": 0.0001347998832168862,
"loss": 1.0097,
"step": 179
},
{
"epoch": 0.42,
"grad_norm": 0.5311691164970398,
"learning_rate": 0.0001340822732512857,
"loss": 1.4547,
"step": 180
},
{
"epoch": 0.42,
"grad_norm": 0.4577678442001343,
"learning_rate": 0.00013336267195887398,
"loss": 1.1929,
"step": 181
},
{
"epoch": 0.42,
"grad_norm": 0.45450282096862793,
"learning_rate": 0.00013264112138383445,
"loss": 0.9774,
"step": 182
},
{
"epoch": 0.42,
"grad_norm": 0.39516186714172363,
"learning_rate": 0.00013191766368424133,
"loss": 1.1093,
"step": 183
},
{
"epoch": 0.43,
"grad_norm": 0.5446043014526367,
"learning_rate": 0.00013119234112959655,
"loss": 0.9583,
"step": 184
},
{
"epoch": 0.43,
"grad_norm": 0.4918731451034546,
"learning_rate": 0.00013046519609836,
"loss": 1.35,
"step": 185
},
{
"epoch": 0.43,
"grad_norm": 0.37299469113349915,
"learning_rate": 0.00012973627107547346,
"loss": 1.2582,
"step": 186
},
{
"epoch": 0.43,
"grad_norm": 0.5013623237609863,
"learning_rate": 0.0001290056086498785,
"loss": 1.2556,
"step": 187
},
{
"epoch": 0.44,
"grad_norm": 0.4400407373905182,
"learning_rate": 0.00012827325151202782,
"loss": 1.2137,
"step": 188
},
{
"epoch": 0.44,
"grad_norm": 0.46342340111732483,
"learning_rate": 0.00012753924245139135,
"loss": 1.1706,
"step": 189
},
{
"epoch": 0.44,
"grad_norm": 0.417937308549881,
"learning_rate": 0.00012680362435395595,
"loss": 1.1111,
"step": 190
},
{
"epoch": 0.44,
"grad_norm": 0.9197636246681213,
"learning_rate": 0.00012606644019971968,
"loss": 1.4709,
"step": 191
},
{
"epoch": 0.45,
"grad_norm": 0.4040437936782837,
"learning_rate": 0.00012532773306018076,
"loss": 1.1701,
"step": 192
},
{
"epoch": 0.45,
"grad_norm": 0.5382991433143616,
"learning_rate": 0.00012458754609582097,
"loss": 0.9994,
"step": 193
},
{
"epoch": 0.45,
"grad_norm": 0.40422263741493225,
"learning_rate": 0.00012384592255358385,
"loss": 1.0439,
"step": 194
},
{
"epoch": 0.45,
"grad_norm": 0.5063545107841492,
"learning_rate": 0.00012310290576434795,
"loss": 1.4452,
"step": 195
},
{
"epoch": 0.45,
"grad_norm": 0.37706631422042847,
"learning_rate": 0.00012235853914039515,
"loss": 0.9206,
"step": 196
},
{
"epoch": 0.46,
"grad_norm": 0.4789075553417206,
"learning_rate": 0.00012161286617287419,
"loss": 0.9392,
"step": 197
},
{
"epoch": 0.46,
"grad_norm": 0.43901360034942627,
"learning_rate": 0.00012086593042925964,
"loss": 1.228,
"step": 198
},
{
"epoch": 0.46,
"grad_norm": 0.34066489338874817,
"learning_rate": 0.00012011777555080638,
"loss": 0.7,
"step": 199
},
{
"epoch": 0.46,
"grad_norm": 0.5998871326446533,
"learning_rate": 0.00011936844524999966,
"loss": 1.3413,
"step": 200
},
{
"epoch": 0.47,
"grad_norm": 0.43001553416252136,
"learning_rate": 0.00011861798330800125,
"loss": 1.0357,
"step": 201
},
{
"epoch": 0.47,
"grad_norm": 0.5246945023536682,
"learning_rate": 0.00011786643357209136,
"loss": 0.9392,
"step": 202
},
{
"epoch": 0.47,
"grad_norm": 0.614080548286438,
"learning_rate": 0.00011711383995310681,
"loss": 1.1147,
"step": 203
},
{
"epoch": 0.47,
"grad_norm": 0.45178118348121643,
"learning_rate": 0.00011636024642287546,
"loss": 1.1284,
"step": 204
},
{
"epoch": 0.48,
"grad_norm": 0.4508957266807556,
"learning_rate": 0.00011560569701164697,
"loss": 1.3169,
"step": 205
},
{
"epoch": 0.48,
"grad_norm": 1.084119439125061,
"learning_rate": 0.00011485023580552039,
"loss": 1.4725,
"step": 206
},
{
"epoch": 0.48,
"grad_norm": 0.417682409286499,
"learning_rate": 0.00011409390694386817,
"loss": 1.1748,
"step": 207
},
{
"epoch": 0.48,
"grad_norm": 0.4242180585861206,
"learning_rate": 0.00011333675461675739,
"loss": 1.0729,
"step": 208
},
{
"epoch": 0.48,
"grad_norm": 0.4738271236419678,
"learning_rate": 0.00011257882306236775,
"loss": 1.2974,
"step": 209
},
{
"epoch": 0.49,
"grad_norm": 0.3936362862586975,
"learning_rate": 0.00011182015656440692,
"loss": 1.0202,
"step": 210
},
{
"epoch": 0.49,
"grad_norm": 0.4622405767440796,
"learning_rate": 0.00011106079944952317,
"loss": 1.2899,
"step": 211
},
{
"epoch": 0.49,
"grad_norm": 0.5150789618492126,
"learning_rate": 0.00011030079608471544,
"loss": 0.8933,
"step": 212
},
{
"epoch": 0.49,
"grad_norm": 0.5435701608657837,
"learning_rate": 0.00010954019087474124,
"loss": 1.4871,
"step": 213
},
{
"epoch": 0.5,
"grad_norm": 0.42681682109832764,
"learning_rate": 0.00010877902825952197,
"loss": 1.0943,
"step": 214
},
{
"epoch": 0.5,
"grad_norm": 0.46130529046058655,
"learning_rate": 0.00010801735271154669,
"loss": 1.1492,
"step": 215
},
{
"epoch": 0.5,
"grad_norm": 0.502712607383728,
"learning_rate": 0.00010725520873327361,
"loss": 1.1175,
"step": 216
},
{
"epoch": 0.5,
"eval_loss": 1.1232960224151611,
"eval_runtime": 4.7032,
"eval_samples_per_second": 21.262,
"eval_steps_per_second": 21.262,
"step": 216
},
{
"epoch": 0.5,
"grad_norm": 0.4459720849990845,
"learning_rate": 0.00010649264085452988,
"loss": 0.9861,
"step": 217
},
{
"epoch": 0.51,
"grad_norm": 0.5748346447944641,
"learning_rate": 0.00010572969362990998,
"loss": 1.2841,
"step": 218
},
{
"epoch": 0.51,
"grad_norm": 0.5053660273551941,
"learning_rate": 0.0001049664116361724,
"loss": 1.1955,
"step": 219
},
{
"epoch": 0.51,
"grad_norm": 0.5145143270492554,
"learning_rate": 0.0001042028394696352,
"loss": 1.0322,
"step": 220
},
{
"epoch": 0.51,
"grad_norm": 0.552711009979248,
"learning_rate": 0.00010343902174357039,
"loss": 1.1417,
"step": 221
},
{
"epoch": 0.52,
"grad_norm": 0.4026980400085449,
"learning_rate": 0.00010267500308559732,
"loss": 1.1334,
"step": 222
},
{
"epoch": 0.52,
"grad_norm": 0.5193754434585571,
"learning_rate": 0.0001019108281350752,
"loss": 1.0735,
"step": 223
},
{
"epoch": 0.52,
"grad_norm": 0.4189368486404419,
"learning_rate": 0.0001011465415404949,
"loss": 1.2567,
"step": 224
},
{
"epoch": 0.52,
"grad_norm": 0.45475542545318604,
"learning_rate": 0.0001003821879568704,
"loss": 0.9511,
"step": 225
},
{
"epoch": 0.52,
"grad_norm": 0.46022626757621765,
"learning_rate": 9.96178120431296e-05,
"loss": 1.1802,
"step": 226
},
{
"epoch": 0.53,
"grad_norm": 0.4458233416080475,
"learning_rate": 9.88534584595051e-05,
"loss": 1.0332,
"step": 227
},
{
"epoch": 0.53,
"grad_norm": 0.3980939984321594,
"learning_rate": 9.80891718649248e-05,
"loss": 0.9659,
"step": 228
},
{
"epoch": 0.53,
"grad_norm": 0.4233875274658203,
"learning_rate": 9.732499691440266e-05,
"loss": 1.3747,
"step": 229
},
{
"epoch": 0.53,
"grad_norm": 0.4073673486709595,
"learning_rate": 9.656097825642961e-05,
"loss": 1.2297,
"step": 230
},
{
"epoch": 0.54,
"grad_norm": 0.39706096053123474,
"learning_rate": 9.579716053036479e-05,
"loss": 0.973,
"step": 231
},
{
"epoch": 0.54,
"grad_norm": 0.4343310296535492,
"learning_rate": 9.503358836382761e-05,
"loss": 1.238,
"step": 232
},
{
"epoch": 0.54,
"grad_norm": 0.4828486144542694,
"learning_rate": 9.427030637009003e-05,
"loss": 1.1616,
"step": 233
},
{
"epoch": 0.54,
"grad_norm": 0.56890869140625,
"learning_rate": 9.35073591454701e-05,
"loss": 0.8345,
"step": 234
},
{
"epoch": 0.55,
"grad_norm": 0.4366269111633301,
"learning_rate": 9.274479126672641e-05,
"loss": 1.111,
"step": 235
},
{
"epoch": 0.55,
"grad_norm": 0.4700612723827362,
"learning_rate": 9.198264728845332e-05,
"loss": 1.3553,
"step": 236
},
{
"epoch": 0.55,
"grad_norm": 0.40685421228408813,
"learning_rate": 9.122097174047805e-05,
"loss": 1.1515,
"step": 237
},
{
"epoch": 0.55,
"grad_norm": 0.37611886858940125,
"learning_rate": 9.045980912525879e-05,
"loss": 0.9226,
"step": 238
},
{
"epoch": 0.55,
"grad_norm": 0.40409284830093384,
"learning_rate": 8.969920391528458e-05,
"loss": 0.8641,
"step": 239
},
{
"epoch": 0.56,
"grad_norm": 0.39749234914779663,
"learning_rate": 8.893920055047686e-05,
"loss": 1.0498,
"step": 240
},
{
"epoch": 0.56,
"grad_norm": 0.554320752620697,
"learning_rate": 8.81798434355931e-05,
"loss": 1.1806,
"step": 241
},
{
"epoch": 0.56,
"grad_norm": 0.37640953063964844,
"learning_rate": 8.742117693763227e-05,
"loss": 1.03,
"step": 242
},
{
"epoch": 0.56,
"grad_norm": 0.4188061058521271,
"learning_rate": 8.666324538324264e-05,
"loss": 1.0891,
"step": 243
},
{
"epoch": 0.57,
"grad_norm": 0.40569260716438293,
"learning_rate": 8.590609305613184e-05,
"loss": 1.2237,
"step": 244
},
{
"epoch": 0.57,
"grad_norm": 0.35996559262275696,
"learning_rate": 8.514976419447964e-05,
"loss": 1.1086,
"step": 245
},
{
"epoch": 0.57,
"grad_norm": 0.3959590792655945,
"learning_rate": 8.439430298835304e-05,
"loss": 1.2445,
"step": 246
},
{
"epoch": 0.57,
"grad_norm": 0.41735970973968506,
"learning_rate": 8.363975357712457e-05,
"loss": 1.2318,
"step": 247
},
{
"epoch": 0.58,
"grad_norm": 0.40587231516838074,
"learning_rate": 8.28861600468932e-05,
"loss": 0.8108,
"step": 248
},
{
"epoch": 0.58,
"grad_norm": 0.4381011128425598,
"learning_rate": 8.213356642790867e-05,
"loss": 0.8791,
"step": 249
},
{
"epoch": 0.58,
"grad_norm": 0.455411821603775,
"learning_rate": 8.138201669199879e-05,
"loss": 1.1067,
"step": 250
},
{
"epoch": 0.58,
"grad_norm": 0.486929714679718,
"learning_rate": 8.063155475000037e-05,
"loss": 1.0332,
"step": 251
},
{
"epoch": 0.58,
"grad_norm": 0.3872472941875458,
"learning_rate": 7.988222444919364e-05,
"loss": 0.9779,
"step": 252
},
{
"epoch": 0.59,
"grad_norm": 0.5021295547485352,
"learning_rate": 7.913406957074037e-05,
"loss": 1.2159,
"step": 253
},
{
"epoch": 0.59,
"grad_norm": 0.3245134949684143,
"learning_rate": 7.838713382712583e-05,
"loss": 0.6035,
"step": 254
},
{
"epoch": 0.59,
"grad_norm": 0.39470720291137695,
"learning_rate": 7.76414608596049e-05,
"loss": 1.0058,
"step": 255
},
{
"epoch": 0.59,
"grad_norm": 0.36348241567611694,
"learning_rate": 7.68970942356521e-05,
"loss": 0.6888,
"step": 256
},
{
"epoch": 0.6,
"grad_norm": 0.6455038189888,
"learning_rate": 7.615407744641619e-05,
"loss": 1.0407,
"step": 257
},
{
"epoch": 0.6,
"grad_norm": 0.5500055551528931,
"learning_rate": 7.541245390417906e-05,
"loss": 1.1612,
"step": 258
},
{
"epoch": 0.6,
"grad_norm": 0.3761384189128876,
"learning_rate": 7.467226693981925e-05,
"loss": 0.9731,
"step": 259
},
{
"epoch": 0.6,
"grad_norm": 0.6317098736763,
"learning_rate": 7.393355980028039e-05,
"loss": 1.3037,
"step": 260
},
{
"epoch": 0.61,
"grad_norm": 0.4043276607990265,
"learning_rate": 7.319637564604412e-05,
"loss": 1.323,
"step": 261
},
{
"epoch": 0.61,
"grad_norm": 0.46140003204345703,
"learning_rate": 7.246075754860868e-05,
"loss": 0.8617,
"step": 262
},
{
"epoch": 0.61,
"grad_norm": 0.4819968044757843,
"learning_rate": 7.172674848797219e-05,
"loss": 1.1345,
"step": 263
},
{
"epoch": 0.61,
"grad_norm": 0.46252205967903137,
"learning_rate": 7.099439135012153e-05,
"loss": 1.4092,
"step": 264
},
{
"epoch": 0.61,
"grad_norm": 0.5231882333755493,
"learning_rate": 7.026372892452653e-05,
"loss": 1.1937,
"step": 265
},
{
"epoch": 0.62,
"grad_norm": 0.3481261432170868,
"learning_rate": 6.953480390164e-05,
"loss": 0.7882,
"step": 266
},
{
"epoch": 0.62,
"grad_norm": 0.8361053466796875,
"learning_rate": 6.880765887040343e-05,
"loss": 1.4242,
"step": 267
},
{
"epoch": 0.62,
"grad_norm": 0.3501080572605133,
"learning_rate": 6.808233631575867e-05,
"loss": 0.7428,
"step": 268
},
{
"epoch": 0.62,
"grad_norm": 0.46989908814430237,
"learning_rate": 6.735887861616556e-05,
"loss": 1.2293,
"step": 269
},
{
"epoch": 0.63,
"grad_norm": 0.44108134508132935,
"learning_rate": 6.663732804112603e-05,
"loss": 1.1302,
"step": 270
},
{
"epoch": 0.63,
"grad_norm": 0.484967440366745,
"learning_rate": 6.591772674871434e-05,
"loss": 1.2551,
"step": 271
},
{
"epoch": 0.63,
"grad_norm": 0.4039287865161896,
"learning_rate": 6.520011678311382e-05,
"loss": 1.2437,
"step": 272
},
{
"epoch": 0.63,
"grad_norm": 0.5447697639465332,
"learning_rate": 6.448454007216054e-05,
"loss": 1.1141,
"step": 273
},
{
"epoch": 0.64,
"grad_norm": 0.5546038150787354,
"learning_rate": 6.377103842489343e-05,
"loss": 0.8614,
"step": 274
},
{
"epoch": 0.64,
"grad_norm": 0.4008563756942749,
"learning_rate": 6.305965352911161e-05,
"loss": 0.9837,
"step": 275
},
{
"epoch": 0.64,
"grad_norm": 0.4528581202030182,
"learning_rate": 6.235042694893862e-05,
"loss": 1.3003,
"step": 276
},
{
"epoch": 0.64,
"grad_norm": 0.5693272352218628,
"learning_rate": 6.164340012239396e-05,
"loss": 1.2459,
"step": 277
},
{
"epoch": 0.65,
"grad_norm": 0.44974976778030396,
"learning_rate": 6.093861435897208e-05,
"loss": 1.3594,
"step": 278
},
{
"epoch": 0.65,
"grad_norm": 0.42815354466438293,
"learning_rate": 6.02361108372286e-05,
"loss": 1.1973,
"step": 279
},
{
"epoch": 0.65,
"grad_norm": 0.4000280797481537,
"learning_rate": 5.953593060237457e-05,
"loss": 1.1897,
"step": 280
},
{
"epoch": 0.65,
"grad_norm": 0.4146158993244171,
"learning_rate": 5.883811456387821e-05,
"loss": 0.9858,
"step": 281
},
{
"epoch": 0.65,
"grad_norm": 0.43319183588027954,
"learning_rate": 5.8142703493074714e-05,
"loss": 0.9849,
"step": 282
},
{
"epoch": 0.66,
"grad_norm": 0.4292287528514862,
"learning_rate": 5.7449738020784085e-05,
"loss": 1.2853,
"step": 283
},
{
"epoch": 0.66,
"grad_norm": 0.4380340576171875,
"learning_rate": 5.675925863493721e-05,
"loss": 1.1053,
"step": 284
},
{
"epoch": 0.66,
"grad_norm": 0.47855687141418457,
"learning_rate": 5.607130567821031e-05,
"loss": 1.147,
"step": 285
},
{
"epoch": 0.66,
"grad_norm": 0.47737643122673035,
"learning_rate": 5.5385919345667715e-05,
"loss": 1.2292,
"step": 286
},
{
"epoch": 0.67,
"grad_norm": 0.532492995262146,
"learning_rate": 5.4703139682413586e-05,
"loss": 1.2948,
"step": 287
},
{
"epoch": 0.67,
"grad_norm": 0.47192513942718506,
"learning_rate": 5.402300658125197e-05,
"loss": 1.0005,
"step": 288
},
{
"epoch": 0.67,
"grad_norm": 0.3757496476173401,
"learning_rate": 5.334555978035609e-05,
"loss": 0.904,
"step": 289
},
{
"epoch": 0.67,
"grad_norm": 0.5040110349655151,
"learning_rate": 5.267083886094668e-05,
"loss": 1.4786,
"step": 290
},
{
"epoch": 0.68,
"grad_norm": 0.4644010663032532,
"learning_rate": 5.199888324497907e-05,
"loss": 1.0901,
"step": 291
},
{
"epoch": 0.68,
"grad_norm": 0.4540674686431885,
"learning_rate": 5.132973219284023e-05,
"loss": 1.1761,
"step": 292
},
{
"epoch": 0.68,
"grad_norm": 0.4109453558921814,
"learning_rate": 5.0663424801054595e-05,
"loss": 1.1454,
"step": 293
},
{
"epoch": 0.68,
"grad_norm": 0.46687519550323486,
"learning_rate": 5.000000000000002e-05,
"loss": 1.0732,
"step": 294
},
{
"epoch": 0.68,
"grad_norm": 0.5146364569664001,
"learning_rate": 4.9339496551632944e-05,
"loss": 1.45,
"step": 295
},
{
"epoch": 0.69,
"grad_norm": 0.4732467532157898,
"learning_rate": 4.8681953047223914e-05,
"loss": 0.8685,
"step": 296
},
{
"epoch": 0.69,
"grad_norm": 0.5239700675010681,
"learning_rate": 4.8027407905102585e-05,
"loss": 1.1003,
"step": 297
},
{
"epoch": 0.69,
"grad_norm": 0.404216468334198,
"learning_rate": 4.73758993684131e-05,
"loss": 0.8534,
"step": 298
},
{
"epoch": 0.69,
"grad_norm": 0.3570495545864105,
"learning_rate": 4.672746550287985e-05,
"loss": 0.9244,
"step": 299
},
{
"epoch": 0.7,
"grad_norm": 0.535670816898346,
"learning_rate": 4.6082144194583056e-05,
"loss": 1.4359,
"step": 300
},
{
"epoch": 0.7,
"grad_norm": 0.4560551047325134,
"learning_rate": 4.543997314774553e-05,
"loss": 1.0442,
"step": 301
},
{
"epoch": 0.7,
"grad_norm": 0.4430754482746124,
"learning_rate": 4.4800989882529574e-05,
"loss": 1.1429,
"step": 302
},
{
"epoch": 0.7,
"grad_norm": 0.48371657729148865,
"learning_rate": 4.41652317328447e-05,
"loss": 1.21,
"step": 303
},
{
"epoch": 0.71,
"grad_norm": 0.462596595287323,
"learning_rate": 4.3532735844166574e-05,
"loss": 1.0128,
"step": 304
},
{
"epoch": 0.71,
"grad_norm": 0.43516165018081665,
"learning_rate": 4.2903539171366393e-05,
"loss": 1.1847,
"step": 305
},
{
"epoch": 0.71,
"grad_norm": 0.805388867855072,
"learning_rate": 4.227767847655205e-05,
"loss": 1.2468,
"step": 306
},
{
"epoch": 0.71,
"grad_norm": 0.4382609724998474,
"learning_rate": 4.165519032691998e-05,
"loss": 1.2178,
"step": 307
},
{
"epoch": 0.71,
"grad_norm": 0.3396044969558716,
"learning_rate": 4.1036111092618725e-05,
"loss": 0.9241,
"step": 308
},
{
"epoch": 0.72,
"grad_norm": 0.4570239782333374,
"learning_rate": 4.042047694462404e-05,
"loss": 1.0592,
"step": 309
},
{
"epoch": 0.72,
"grad_norm": 0.49074164032936096,
"learning_rate": 3.9808323852625316e-05,
"loss": 1.1067,
"step": 310
},
{
"epoch": 0.72,
"grad_norm": 0.5517829656600952,
"learning_rate": 3.919968758292425e-05,
"loss": 1.3361,
"step": 311
},
{
"epoch": 0.72,
"grad_norm": 0.4893704950809479,
"learning_rate": 3.859460369634479e-05,
"loss": 1.1157,
"step": 312
},
{
"epoch": 0.73,
"grad_norm": 0.4687519967556,
"learning_rate": 3.799310754615578e-05,
"loss": 1.3605,
"step": 313
},
{
"epoch": 0.73,
"grad_norm": 0.35046279430389404,
"learning_rate": 3.7395234276005087e-05,
"loss": 0.8558,
"step": 314
},
{
"epoch": 0.73,
"grad_norm": 0.5013456344604492,
"learning_rate": 3.6801018817866375e-05,
"loss": 1.0554,
"step": 315
},
{
"epoch": 0.73,
"grad_norm": 0.4760110378265381,
"learning_rate": 3.62104958899982e-05,
"loss": 1.1839,
"step": 316
},
{
"epoch": 0.74,
"grad_norm": 0.5143394470214844,
"learning_rate": 3.562369999491536e-05,
"loss": 1.4146,
"step": 317
},
{
"epoch": 0.74,
"grad_norm": 0.4014797508716583,
"learning_rate": 3.504066541737323e-05,
"loss": 1.0731,
"step": 318
},
{
"epoch": 0.74,
"grad_norm": 0.40402811765670776,
"learning_rate": 3.4461426222364336e-05,
"loss": 1.0001,
"step": 319
},
{
"epoch": 0.74,
"grad_norm": 0.43316271901130676,
"learning_rate": 3.3886016253128326e-05,
"loss": 1.1141,
"step": 320
},
{
"epoch": 0.74,
"grad_norm": 0.49771907925605774,
"learning_rate": 3.3314469129174364e-05,
"loss": 1.3224,
"step": 321
},
{
"epoch": 0.75,
"grad_norm": 0.4895000159740448,
"learning_rate": 3.2746818244316956e-05,
"loss": 1.04,
"step": 322
},
{
"epoch": 0.75,
"grad_norm": 0.5450279116630554,
"learning_rate": 3.2183096764724915e-05,
"loss": 1.4016,
"step": 323
},
{
"epoch": 0.75,
"grad_norm": 0.4866601526737213,
"learning_rate": 3.16233376269834e-05,
"loss": 1.4102,
"step": 324
},
{
"epoch": 0.75,
"eval_loss": 1.1097332239151,
"eval_runtime": 5.825,
"eval_samples_per_second": 17.167,
"eval_steps_per_second": 17.167,
"step": 324
},
{
"epoch": 0.75,
"grad_norm": 0.40248391032218933,
"learning_rate": 3.106757353616966e-05,
"loss": 0.8404,
"step": 325
},
{
"epoch": 0.76,
"grad_norm": 0.44263288378715515,
"learning_rate": 3.0515836963942056e-05,
"loss": 1.2992,
"step": 326
},
{
"epoch": 0.76,
"grad_norm": 0.4113296866416931,
"learning_rate": 2.9968160146643022e-05,
"loss": 1.1058,
"step": 327
},
{
"epoch": 0.76,
"grad_norm": 0.5293351411819458,
"learning_rate": 2.9424575083415362e-05,
"loss": 1.5505,
"step": 328
},
{
"epoch": 0.76,
"grad_norm": 0.500862181186676,
"learning_rate": 2.888511353433274e-05,
"loss": 1.1173,
"step": 329
},
{
"epoch": 0.77,
"grad_norm": 0.408054918050766,
"learning_rate": 2.8349807018544174e-05,
"loss": 1.1951,
"step": 330
},
{
"epoch": 0.77,
"grad_norm": 0.39368724822998047,
"learning_rate": 2.7818686812432136e-05,
"loss": 1.1842,
"step": 331
},
{
"epoch": 0.77,
"grad_norm": 0.5162099599838257,
"learning_rate": 2.7291783947785543e-05,
"loss": 1.5018,
"step": 332
},
{
"epoch": 0.77,
"grad_norm": 0.49148476123809814,
"learning_rate": 2.6769129209986322e-05,
"loss": 1.4618,
"step": 333
},
{
"epoch": 0.77,
"grad_norm": 0.4833587408065796,
"learning_rate": 2.6250753136210983e-05,
"loss": 0.8573,
"step": 334
},
{
"epoch": 0.78,
"grad_norm": 0.40724459290504456,
"learning_rate": 2.5736686013646228e-05,
"loss": 1.1546,
"step": 335
},
{
"epoch": 0.78,
"grad_norm": 0.683252215385437,
"learning_rate": 2.5226957877719436e-05,
"loss": 1.1321,
"step": 336
},
{
"epoch": 0.78,
"grad_norm": 0.6411616802215576,
"learning_rate": 2.4721598510343858e-05,
"loss": 1.3481,
"step": 337
},
{
"epoch": 0.78,
"grad_norm": 0.4726378917694092,
"learning_rate": 2.4220637438178317e-05,
"loss": 1.0497,
"step": 338
},
{
"epoch": 0.79,
"grad_norm": 0.6027311682701111,
"learning_rate": 2.372410393090243e-05,
"loss": 1.1339,
"step": 339
},
{
"epoch": 0.79,
"grad_norm": 0.4566133916378021,
"learning_rate": 2.3232026999506062e-05,
"loss": 1.2384,
"step": 340
},
{
"epoch": 0.79,
"grad_norm": 0.4425651431083679,
"learning_rate": 2.2744435394594497e-05,
"loss": 1.2542,
"step": 341
},
{
"epoch": 0.79,
"grad_norm": 0.3810960352420807,
"learning_rate": 2.22613576047087e-05,
"loss": 0.9794,
"step": 342
},
{
"epoch": 0.8,
"grad_norm": 0.441679447889328,
"learning_rate": 2.1782821854660606e-05,
"loss": 1.0967,
"step": 343
},
{
"epoch": 0.8,
"grad_norm": 0.5362725257873535,
"learning_rate": 2.130885610388428e-05,
"loss": 1.3365,
"step": 344
},
{
"epoch": 0.8,
"grad_norm": 0.5472970604896545,
"learning_rate": 2.0839488044802036e-05,
"loss": 1.7679,
"step": 345
},
{
"epoch": 0.8,
"grad_norm": 0.4027257561683655,
"learning_rate": 2.037474510120676e-05,
"loss": 1.1387,
"step": 346
},
{
"epoch": 0.81,
"grad_norm": 0.5073655843734741,
"learning_rate": 1.9914654426659374e-05,
"loss": 1.0684,
"step": 347
},
{
"epoch": 0.81,
"grad_norm": 0.4431632161140442,
"learning_rate": 1.945924290290242e-05,
"loss": 1.1118,
"step": 348
},
{
"epoch": 0.81,
"grad_norm": 0.7360476851463318,
"learning_rate": 1.9008537138289527e-05,
"loss": 1.5517,
"step": 349
},
{
"epoch": 0.81,
"grad_norm": 0.43251582980155945,
"learning_rate": 1.8562563466230576e-05,
"loss": 1.1982,
"step": 350
},
{
"epoch": 0.81,
"grad_norm": 0.4459226429462433,
"learning_rate": 1.8121347943653332e-05,
"loss": 1.3095,
"step": 351
},
{
"epoch": 0.82,
"grad_norm": 0.34792765974998474,
"learning_rate": 1.7684916349480794e-05,
"loss": 0.9415,
"step": 352
},
{
"epoch": 0.82,
"grad_norm": 0.5468625426292419,
"learning_rate": 1.7253294183125223e-05,
"loss": 1.1621,
"step": 353
},
{
"epoch": 0.82,
"grad_norm": 0.5048443675041199,
"learning_rate": 1.6826506662998097e-05,
"loss": 1.3502,
"step": 354
},
{
"epoch": 0.82,
"grad_norm": 0.3652397692203522,
"learning_rate": 1.64045787250368e-05,
"loss": 1.1079,
"step": 355
},
{
"epoch": 0.83,
"grad_norm": 0.45304709672927856,
"learning_rate": 1.5987535021247667e-05,
"loss": 1.0239,
"step": 356
},
{
"epoch": 0.83,
"grad_norm": 0.38547682762145996,
"learning_rate": 1.5575399918265542e-05,
"loss": 1.1345,
"step": 357
},
{
"epoch": 0.83,
"grad_norm": 0.47186747193336487,
"learning_rate": 1.5168197495930315e-05,
"loss": 1.4572,
"step": 358
},
{
"epoch": 0.83,
"grad_norm": 0.4306280314922333,
"learning_rate": 1.476595154587973e-05,
"loss": 0.9894,
"step": 359
},
{
"epoch": 0.84,
"grad_norm": 0.49191519618034363,
"learning_rate": 1.436868557015959e-05,
"loss": 1.3018,
"step": 360
},
{
"epoch": 0.84,
"grad_norm": 0.548028826713562,
"learning_rate": 1.3976422779850384e-05,
"loss": 1.3219,
"step": 361
},
{
"epoch": 0.84,
"grad_norm": 0.39407745003700256,
"learning_rate": 1.3589186093711226e-05,
"loss": 1.002,
"step": 362
},
{
"epoch": 0.84,
"grad_norm": 0.47022268176078796,
"learning_rate": 1.3206998136840831e-05,
"loss": 1.2112,
"step": 363
},
{
"epoch": 0.84,
"grad_norm": 0.7266699075698853,
"learning_rate": 1.2829881239355468e-05,
"loss": 1.3021,
"step": 364
},
{
"epoch": 0.85,
"grad_norm": 0.6192635297775269,
"learning_rate": 1.2457857435084408e-05,
"loss": 2.7741,
"step": 365
},
{
"epoch": 0.85,
"grad_norm": 0.39360511302948,
"learning_rate": 1.2090948460282414e-05,
"loss": 1.1131,
"step": 366
},
{
"epoch": 0.85,
"grad_norm": 0.6498689651489258,
"learning_rate": 1.1729175752359922e-05,
"loss": 1.3666,
"step": 367
},
{
"epoch": 0.85,
"grad_norm": 0.40655967593193054,
"learning_rate": 1.1372560448630376e-05,
"loss": 1.1841,
"step": 368
},
{
"epoch": 0.86,
"grad_norm": 0.3894653022289276,
"learning_rate": 1.102112338507526e-05,
"loss": 1.1494,
"step": 369
},
{
"epoch": 0.86,
"grad_norm": 0.5716227889060974,
"learning_rate": 1.067488509512683e-05,
"loss": 0.9971,
"step": 370
},
{
"epoch": 0.86,
"grad_norm": 0.4679757356643677,
"learning_rate": 1.0333865808468202e-05,
"loss": 1.0505,
"step": 371
},
{
"epoch": 0.86,
"grad_norm": 0.5550671219825745,
"learning_rate": 9.998085449851635e-06,
"loss": 1.0006,
"step": 372
},
{
"epoch": 0.87,
"grad_norm": 0.4179516136646271,
"learning_rate": 9.667563637934129e-06,
"loss": 0.8996,
"step": 373
},
{
"epoch": 0.87,
"grad_norm": 0.4545114040374756,
"learning_rate": 9.342319684131395e-06,
"loss": 1.1175,
"step": 374
},
{
"epoch": 0.87,
"grad_norm": 0.5175038576126099,
"learning_rate": 9.02237259148938e-06,
"loss": 1.1729,
"step": 375
},
{
"epoch": 0.87,
"grad_norm": 0.45041874051094055,
"learning_rate": 8.70774105357407e-06,
"loss": 1.2005,
"step": 376
},
{
"epoch": 0.87,
"grad_norm": 0.47179684042930603,
"learning_rate": 8.398443453379267e-06,
"loss": 1.1232,
"step": 377
},
{
"epoch": 0.88,
"grad_norm": 0.4453977942466736,
"learning_rate": 8.094497862252471e-06,
"loss": 1.3498,
"step": 378
},
{
"epoch": 0.88,
"grad_norm": 0.545090913772583,
"learning_rate": 7.795922038839032e-06,
"loss": 1.3135,
"step": 379
},
{
"epoch": 0.88,
"grad_norm": 0.41150522232055664,
"learning_rate": 7.502733428044683e-06,
"loss": 1.0358,
"step": 380
},
{
"epoch": 0.88,
"grad_norm": 0.4423467218875885,
"learning_rate": 7.214949160016115e-06,
"loss": 1.1287,
"step": 381
},
{
"epoch": 0.89,
"grad_norm": 0.4803576171398163,
"learning_rate": 6.932586049140255e-06,
"loss": 1.1248,
"step": 382
},
{
"epoch": 0.89,
"grad_norm": 0.50335294008255,
"learning_rate": 6.655660593061719e-06,
"loss": 1.2563,
"step": 383
},
{
"epoch": 0.89,
"grad_norm": 0.4255715310573578,
"learning_rate": 6.384188971719052e-06,
"loss": 1.1771,
"step": 384
},
{
"epoch": 0.89,
"grad_norm": 0.5371767282485962,
"learning_rate": 6.11818704639926e-06,
"loss": 1.4661,
"step": 385
},
{
"epoch": 0.9,
"grad_norm": 0.7055171132087708,
"learning_rate": 5.857670358811096e-06,
"loss": 1.2068,
"step": 386
},
{
"epoch": 0.9,
"grad_norm": 0.6857877969741821,
"learning_rate": 5.6026541301771095e-06,
"loss": 1.025,
"step": 387
},
{
"epoch": 0.9,
"grad_norm": 0.3706812858581543,
"learning_rate": 5.353153260344179e-06,
"loss": 0.4216,
"step": 388
},
{
"epoch": 0.9,
"grad_norm": 0.3943740725517273,
"learning_rate": 5.109182326913054e-06,
"loss": 1.1772,
"step": 389
},
{
"epoch": 0.9,
"grad_norm": 0.44216853380203247,
"learning_rate": 4.870755584386544e-06,
"loss": 1.1343,
"step": 390
},
{
"epoch": 0.91,
"grad_norm": 0.5114327669143677,
"learning_rate": 4.63788696333678e-06,
"loss": 1.3096,
"step": 391
},
{
"epoch": 0.91,
"grad_norm": 0.4400082230567932,
"learning_rate": 4.410590069591192e-06,
"loss": 1.0596,
"step": 392
},
{
"epoch": 0.91,
"grad_norm": 0.5141562223434448,
"learning_rate": 4.188878183437594e-06,
"loss": 0.976,
"step": 393
},
{
"epoch": 0.91,
"grad_norm": 0.47619250416755676,
"learning_rate": 3.972764258848305e-06,
"loss": 0.8015,
"step": 394
},
{
"epoch": 0.92,
"grad_norm": 0.44292959570884705,
"learning_rate": 3.7622609227231818e-06,
"loss": 1.2856,
"step": 395
},
{
"epoch": 0.92,
"grad_norm": 0.5242791175842285,
"learning_rate": 3.5573804741519833e-06,
"loss": 1.0283,
"step": 396
},
{
"epoch": 0.92,
"grad_norm": 0.41017472743988037,
"learning_rate": 3.3581348836956738e-06,
"loss": 0.8387,
"step": 397
},
{
"epoch": 0.92,
"grad_norm": 0.44496363401412964,
"learning_rate": 3.1645357926870955e-06,
"loss": 1.0878,
"step": 398
},
{
"epoch": 0.93,
"grad_norm": 0.5821820497512817,
"learning_rate": 2.9765945125507235e-06,
"loss": 1.3477,
"step": 399
},
{
"epoch": 0.93,
"grad_norm": 0.5164168477058411,
"learning_rate": 2.7943220241418377e-06,
"loss": 1.6242,
"step": 400
},
{
"epoch": 0.93,
"grad_norm": 0.5002605319023132,
"learning_rate": 2.6177289771049274e-06,
"loss": 1.2107,
"step": 401
},
{
"epoch": 0.93,
"grad_norm": 0.44040682911872864,
"learning_rate": 2.4468256892514417e-06,
"loss": 0.8678,
"step": 402
},
{
"epoch": 0.94,
"grad_norm": 0.35371842980384827,
"learning_rate": 2.281622145956952e-06,
"loss": 0.7567,
"step": 403
},
{
"epoch": 0.94,
"grad_norm": 0.4473396837711334,
"learning_rate": 2.122127999577783e-06,
"loss": 1.0541,
"step": 404
},
{
"epoch": 0.94,
"grad_norm": 0.6327199339866638,
"learning_rate": 1.9683525688869773e-06,
"loss": 1.2364,
"step": 405
},
{
"epoch": 0.94,
"grad_norm": 0.4338397681713104,
"learning_rate": 1.8203048385299181e-06,
"loss": 1.1542,
"step": 406
},
{
"epoch": 0.94,
"grad_norm": 0.5743327140808105,
"learning_rate": 1.6779934584992718e-06,
"loss": 1.2498,
"step": 407
},
{
"epoch": 0.95,
"grad_norm": 0.40991920232772827,
"learning_rate": 1.5414267436297037e-06,
"loss": 1.1019,
"step": 408
},
{
"epoch": 0.95,
"grad_norm": 0.40616923570632935,
"learning_rate": 1.4106126731119996e-06,
"loss": 1.2456,
"step": 409
},
{
"epoch": 0.95,
"grad_norm": 0.4829423725605011,
"learning_rate": 1.2855588900269056e-06,
"loss": 1.1966,
"step": 410
},
{
"epoch": 0.95,
"grad_norm": 0.4857659339904785,
"learning_rate": 1.1662727008984964e-06,
"loss": 1.4712,
"step": 411
},
{
"epoch": 0.96,
"grad_norm": 0.4441464841365814,
"learning_rate": 1.0527610752673944e-06,
"loss": 1.1358,
"step": 412
},
{
"epoch": 0.96,
"grad_norm": 0.4043671488761902,
"learning_rate": 9.450306452834179e-07,
"loss": 1.1369,
"step": 413
},
{
"epoch": 0.96,
"grad_norm": 0.5048549771308899,
"learning_rate": 8.430877053182129e-07,
"loss": 1.1279,
"step": 414
},
{
"epoch": 0.96,
"grad_norm": 0.43177226185798645,
"learning_rate": 7.469382115974032e-07,
"loss": 1.269,
"step": 415
},
{
"epoch": 0.97,
"grad_norm": 0.45105987787246704,
"learning_rate": 6.565877818526245e-07,
"loss": 1.6302,
"step": 416
},
{
"epoch": 0.97,
"grad_norm": 0.4008980989456177,
"learning_rate": 5.72041694993286e-07,
"loss": 0.7278,
"step": 417
},
{
"epoch": 0.97,
"grad_norm": 0.570662796497345,
"learning_rate": 4.933048907981741e-07,
"loss": 1.2836,
"step": 418
},
{
"epoch": 0.97,
"grad_norm": 0.39943748712539673,
"learning_rate": 4.203819696267486e-07,
"loss": 1.1154,
"step": 419
},
{
"epoch": 0.97,
"grad_norm": 0.6464762687683105,
"learning_rate": 3.532771921504696e-07,
"loss": 0.9646,
"step": 420
},
{
"epoch": 0.98,
"grad_norm": 0.46713489294052124,
"learning_rate": 2.919944791037632e-07,
"loss": 1.1209,
"step": 421
},
{
"epoch": 0.98,
"grad_norm": 0.45911917090415955,
"learning_rate": 2.3653741105499338e-07,
"loss": 1.2976,
"step": 422
},
{
"epoch": 0.98,
"grad_norm": 0.4376751482486725,
"learning_rate": 1.8690922819727398e-07,
"loss": 1.2812,
"step": 423
},
{
"epoch": 0.98,
"grad_norm": 0.461121529340744,
"learning_rate": 1.4311283015910893e-07,
"loss": 1.4073,
"step": 424
},
{
"epoch": 0.99,
"grad_norm": 0.39589831233024597,
"learning_rate": 1.0515077583498344e-07,
"loss": 1.0048,
"step": 425
},
{
"epoch": 0.99,
"grad_norm": 0.39896348118782043,
"learning_rate": 7.302528323589464e-08,
"loss": 0.8817,
"step": 426
},
{
"epoch": 0.99,
"grad_norm": 0.43354111909866333,
"learning_rate": 4.6738229359732935e-08,
"loss": 0.9946,
"step": 427
},
{
"epoch": 0.99,
"grad_norm": 0.3909148871898651,
"learning_rate": 2.6291150081603212e-08,
"loss": 1.1572,
"step": 428
},
{
"epoch": 1.0,
"grad_norm": 0.5046055912971497,
"learning_rate": 1.168524006410765e-08,
"loss": 1.3007,
"step": 429
},
{
"epoch": 1.0,
"grad_norm": 0.6245082020759583,
"learning_rate": 2.921352687534906e-09,
"loss": 0.9887,
"step": 430
},
{
"epoch": 1.0,
"grad_norm": 0.45793771743774414,
"learning_rate": 0.0,
"loss": 1.1817,
"step": 431
}
],
"logging_steps": 1,
"max_steps": 431,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 7928752835297280.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}