atsuki-yamaguchi's picture
Upload folder using huggingface_hub
51d1117 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1054,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003795066413662239,
"grad_norm": 63.00752258300781,
"learning_rate": 3.7735849056603773e-06,
"loss": 7.6101,
"step": 2
},
{
"epoch": 0.007590132827324478,
"grad_norm": 52.05138397216797,
"learning_rate": 7.547169811320755e-06,
"loss": 6.7495,
"step": 4
},
{
"epoch": 0.011385199240986717,
"grad_norm": 20.389183044433594,
"learning_rate": 1.1320754716981132e-05,
"loss": 5.4221,
"step": 6
},
{
"epoch": 0.015180265654648957,
"grad_norm": 15.354876518249512,
"learning_rate": 1.509433962264151e-05,
"loss": 5.0005,
"step": 8
},
{
"epoch": 0.018975332068311195,
"grad_norm": 20.925552368164062,
"learning_rate": 1.8867924528301888e-05,
"loss": 4.9059,
"step": 10
},
{
"epoch": 0.022770398481973434,
"grad_norm": 11.086358070373535,
"learning_rate": 2.2641509433962265e-05,
"loss": 4.5701,
"step": 12
},
{
"epoch": 0.026565464895635674,
"grad_norm": 11.882867813110352,
"learning_rate": 2.641509433962264e-05,
"loss": 4.5355,
"step": 14
},
{
"epoch": 0.030360531309297913,
"grad_norm": 6.069272994995117,
"learning_rate": 3.018867924528302e-05,
"loss": 4.3985,
"step": 16
},
{
"epoch": 0.03415559772296015,
"grad_norm": 10.657866477966309,
"learning_rate": 3.39622641509434e-05,
"loss": 4.2807,
"step": 18
},
{
"epoch": 0.03795066413662239,
"grad_norm": 5.701382160186768,
"learning_rate": 3.7735849056603776e-05,
"loss": 4.1327,
"step": 20
},
{
"epoch": 0.04174573055028463,
"grad_norm": 6.646956920623779,
"learning_rate": 4.150943396226415e-05,
"loss": 3.9816,
"step": 22
},
{
"epoch": 0.04554079696394687,
"grad_norm": 8.616214752197266,
"learning_rate": 4.528301886792453e-05,
"loss": 3.9488,
"step": 24
},
{
"epoch": 0.04933586337760911,
"grad_norm": 6.680394172668457,
"learning_rate": 4.9056603773584906e-05,
"loss": 3.9023,
"step": 26
},
{
"epoch": 0.05313092979127135,
"grad_norm": 5.000591278076172,
"learning_rate": 5.283018867924528e-05,
"loss": 3.8465,
"step": 28
},
{
"epoch": 0.056925996204933584,
"grad_norm": 6.819991588592529,
"learning_rate": 5.660377358490566e-05,
"loss": 3.689,
"step": 30
},
{
"epoch": 0.06072106261859583,
"grad_norm": 10.46780776977539,
"learning_rate": 6.037735849056604e-05,
"loss": 3.7298,
"step": 32
},
{
"epoch": 0.06451612903225806,
"grad_norm": 7.608869552612305,
"learning_rate": 6.415094339622641e-05,
"loss": 3.4503,
"step": 34
},
{
"epoch": 0.0683111954459203,
"grad_norm": 4.267995357513428,
"learning_rate": 6.79245283018868e-05,
"loss": 3.4507,
"step": 36
},
{
"epoch": 0.07210626185958255,
"grad_norm": 5.486748218536377,
"learning_rate": 7.169811320754717e-05,
"loss": 3.2897,
"step": 38
},
{
"epoch": 0.07590132827324478,
"grad_norm": 5.978483200073242,
"learning_rate": 7.547169811320755e-05,
"loss": 3.3745,
"step": 40
},
{
"epoch": 0.07969639468690702,
"grad_norm": 5.698124408721924,
"learning_rate": 7.924528301886794e-05,
"loss": 3.1298,
"step": 42
},
{
"epoch": 0.08349146110056926,
"grad_norm": 5.405357837677002,
"learning_rate": 8.30188679245283e-05,
"loss": 3.1875,
"step": 44
},
{
"epoch": 0.0872865275142315,
"grad_norm": 10.80594539642334,
"learning_rate": 8.679245283018869e-05,
"loss": 3.2966,
"step": 46
},
{
"epoch": 0.09108159392789374,
"grad_norm": 6.490413188934326,
"learning_rate": 9.056603773584906e-05,
"loss": 3.161,
"step": 48
},
{
"epoch": 0.09487666034155598,
"grad_norm": 8.816051483154297,
"learning_rate": 9.433962264150944e-05,
"loss": 3.1614,
"step": 50
},
{
"epoch": 0.09867172675521822,
"grad_norm": 5.178752422332764,
"learning_rate": 9.811320754716981e-05,
"loss": 3.0975,
"step": 52
},
{
"epoch": 0.10246679316888045,
"grad_norm": 4.5004072189331055,
"learning_rate": 9.999975375283309e-05,
"loss": 2.9957,
"step": 54
},
{
"epoch": 0.1062618595825427,
"grad_norm": 9.214571952819824,
"learning_rate": 9.999778379005078e-05,
"loss": 3.0603,
"step": 56
},
{
"epoch": 0.11005692599620494,
"grad_norm": 6.38614559173584,
"learning_rate": 9.99938439421016e-05,
"loss": 2.9903,
"step": 58
},
{
"epoch": 0.11385199240986717,
"grad_norm": 6.926280975341797,
"learning_rate": 9.99879343642134e-05,
"loss": 2.8462,
"step": 60
},
{
"epoch": 0.11764705882352941,
"grad_norm": 6.732943058013916,
"learning_rate": 9.99800552892203e-05,
"loss": 3.0189,
"step": 62
},
{
"epoch": 0.12144212523719165,
"grad_norm": 5.040093421936035,
"learning_rate": 9.997020702755353e-05,
"loss": 2.9434,
"step": 64
},
{
"epoch": 0.1252371916508539,
"grad_norm": 6.937143325805664,
"learning_rate": 9.995838996722914e-05,
"loss": 2.8124,
"step": 66
},
{
"epoch": 0.12903225806451613,
"grad_norm": 4.283921241760254,
"learning_rate": 9.994460457383284e-05,
"loss": 2.9453,
"step": 68
},
{
"epoch": 0.13282732447817835,
"grad_norm": 3.254178047180176,
"learning_rate": 9.992885139050154e-05,
"loss": 2.6904,
"step": 70
},
{
"epoch": 0.1366223908918406,
"grad_norm": 3.725719451904297,
"learning_rate": 9.991113103790198e-05,
"loss": 2.9125,
"step": 72
},
{
"epoch": 0.14041745730550284,
"grad_norm": 4.150193691253662,
"learning_rate": 9.98914442142063e-05,
"loss": 2.7086,
"step": 74
},
{
"epoch": 0.1442125237191651,
"grad_norm": 4.107541561126709,
"learning_rate": 9.986979169506453e-05,
"loss": 2.7852,
"step": 76
},
{
"epoch": 0.14800759013282733,
"grad_norm": 4.584061145782471,
"learning_rate": 9.9846174333574e-05,
"loss": 2.7778,
"step": 78
},
{
"epoch": 0.15180265654648956,
"grad_norm": 4.40277624130249,
"learning_rate": 9.982059306024577e-05,
"loss": 2.7748,
"step": 80
},
{
"epoch": 0.1555977229601518,
"grad_norm": 4.356024265289307,
"learning_rate": 9.979304888296792e-05,
"loss": 2.608,
"step": 82
},
{
"epoch": 0.15939278937381404,
"grad_norm": 3.3724732398986816,
"learning_rate": 9.976354288696588e-05,
"loss": 2.5866,
"step": 84
},
{
"epoch": 0.16318785578747627,
"grad_norm": 2.7890326976776123,
"learning_rate": 9.973207623475965e-05,
"loss": 2.9124,
"step": 86
},
{
"epoch": 0.16698292220113853,
"grad_norm": 3.0836424827575684,
"learning_rate": 9.9698650166118e-05,
"loss": 2.7608,
"step": 88
},
{
"epoch": 0.17077798861480076,
"grad_norm": 3.8061060905456543,
"learning_rate": 9.966326599800967e-05,
"loss": 2.5718,
"step": 90
},
{
"epoch": 0.174573055028463,
"grad_norm": 3.3448660373687744,
"learning_rate": 9.962592512455138e-05,
"loss": 2.669,
"step": 92
},
{
"epoch": 0.17836812144212524,
"grad_norm": 3.068967342376709,
"learning_rate": 9.958662901695303e-05,
"loss": 2.5557,
"step": 94
},
{
"epoch": 0.18216318785578747,
"grad_norm": 4.097878456115723,
"learning_rate": 9.954537922345961e-05,
"loss": 2.4834,
"step": 96
},
{
"epoch": 0.1859582542694497,
"grad_norm": 3.982511281967163,
"learning_rate": 9.950217736929029e-05,
"loss": 2.5841,
"step": 98
},
{
"epoch": 0.18975332068311196,
"grad_norm": 3.704517126083374,
"learning_rate": 9.945702515657434e-05,
"loss": 2.6205,
"step": 100
},
{
"epoch": 0.1935483870967742,
"grad_norm": 2.450561285018921,
"learning_rate": 9.940992436428409e-05,
"loss": 2.6092,
"step": 102
},
{
"epoch": 0.19734345351043645,
"grad_norm": 2.9768736362457275,
"learning_rate": 9.936087684816486e-05,
"loss": 2.8338,
"step": 104
},
{
"epoch": 0.20113851992409867,
"grad_norm": 3.1297333240509033,
"learning_rate": 9.930988454066177e-05,
"loss": 2.4951,
"step": 106
},
{
"epoch": 0.2049335863377609,
"grad_norm": 2.4693760871887207,
"learning_rate": 9.92569494508437e-05,
"loss": 2.4838,
"step": 108
},
{
"epoch": 0.20872865275142316,
"grad_norm": 3.9109935760498047,
"learning_rate": 9.920207366432402e-05,
"loss": 2.442,
"step": 110
},
{
"epoch": 0.2125237191650854,
"grad_norm": 2.8229682445526123,
"learning_rate": 9.914525934317855e-05,
"loss": 2.5801,
"step": 112
},
{
"epoch": 0.21631878557874762,
"grad_norm": 3.45439076423645,
"learning_rate": 9.908650872586029e-05,
"loss": 2.4773,
"step": 114
},
{
"epoch": 0.22011385199240988,
"grad_norm": 3.4352426528930664,
"learning_rate": 9.90258241271112e-05,
"loss": 2.446,
"step": 116
},
{
"epoch": 0.2239089184060721,
"grad_norm": 4.387381076812744,
"learning_rate": 9.896320793787106e-05,
"loss": 2.3522,
"step": 118
},
{
"epoch": 0.22770398481973433,
"grad_norm": 3.2233426570892334,
"learning_rate": 9.889866262518331e-05,
"loss": 2.5161,
"step": 120
},
{
"epoch": 0.2314990512333966,
"grad_norm": 3.064469575881958,
"learning_rate": 9.883219073209772e-05,
"loss": 2.4289,
"step": 122
},
{
"epoch": 0.23529411764705882,
"grad_norm": 2.677464008331299,
"learning_rate": 9.876379487757034e-05,
"loss": 2.4003,
"step": 124
},
{
"epoch": 0.23908918406072105,
"grad_norm": 3.013580083847046,
"learning_rate": 9.869347775636015e-05,
"loss": 2.4118,
"step": 126
},
{
"epoch": 0.2428842504743833,
"grad_norm": 2.664313554763794,
"learning_rate": 9.862124213892304e-05,
"loss": 2.376,
"step": 128
},
{
"epoch": 0.24667931688804554,
"grad_norm": 2.4481186866760254,
"learning_rate": 9.85470908713026e-05,
"loss": 2.4057,
"step": 130
},
{
"epoch": 0.2504743833017078,
"grad_norm": 2.694735050201416,
"learning_rate": 9.847102687501797e-05,
"loss": 2.3695,
"step": 132
},
{
"epoch": 0.25426944971537,
"grad_norm": 2.753716230392456,
"learning_rate": 9.839305314694873e-05,
"loss": 2.4603,
"step": 134
},
{
"epoch": 0.25806451612903225,
"grad_norm": 2.765968084335327,
"learning_rate": 9.831317275921685e-05,
"loss": 2.3087,
"step": 136
},
{
"epoch": 0.2618595825426945,
"grad_norm": 3.117023468017578,
"learning_rate": 9.823138885906566e-05,
"loss": 2.277,
"step": 138
},
{
"epoch": 0.2656546489563567,
"grad_norm": 2.481924533843994,
"learning_rate": 9.814770466873585e-05,
"loss": 2.4807,
"step": 140
},
{
"epoch": 0.269449715370019,
"grad_norm": 3.3499083518981934,
"learning_rate": 9.806212348533838e-05,
"loss": 2.3012,
"step": 142
},
{
"epoch": 0.2732447817836812,
"grad_norm": 2.579857349395752,
"learning_rate": 9.797464868072488e-05,
"loss": 2.4495,
"step": 144
},
{
"epoch": 0.27703984819734345,
"grad_norm": 2.311835527420044,
"learning_rate": 9.788528370135443e-05,
"loss": 2.3571,
"step": 146
},
{
"epoch": 0.2808349146110057,
"grad_norm": 2.329324960708618,
"learning_rate": 9.77940320681581e-05,
"loss": 2.3785,
"step": 148
},
{
"epoch": 0.2846299810246679,
"grad_norm": 2.41457200050354,
"learning_rate": 9.77008973764e-05,
"loss": 2.2028,
"step": 150
},
{
"epoch": 0.2884250474383302,
"grad_norm": 2.473177909851074,
"learning_rate": 9.760588329553571e-05,
"loss": 2.1556,
"step": 152
},
{
"epoch": 0.2922201138519924,
"grad_norm": 2.7106714248657227,
"learning_rate": 9.750899356906775e-05,
"loss": 2.2796,
"step": 154
},
{
"epoch": 0.29601518026565465,
"grad_norm": 2.464414358139038,
"learning_rate": 9.741023201439803e-05,
"loss": 2.1867,
"step": 156
},
{
"epoch": 0.2998102466793169,
"grad_norm": 2.821174383163452,
"learning_rate": 9.730960252267743e-05,
"loss": 2.3037,
"step": 158
},
{
"epoch": 0.3036053130929791,
"grad_norm": 2.3339788913726807,
"learning_rate": 9.720710905865256e-05,
"loss": 2.2727,
"step": 160
},
{
"epoch": 0.30740037950664134,
"grad_norm": 2.5875446796417236,
"learning_rate": 9.710275566050951e-05,
"loss": 2.3128,
"step": 162
},
{
"epoch": 0.3111954459203036,
"grad_norm": 2.775893449783325,
"learning_rate": 9.699654643971472e-05,
"loss": 2.2913,
"step": 164
},
{
"epoch": 0.31499051233396586,
"grad_norm": 2.586064100265503,
"learning_rate": 9.688848558085306e-05,
"loss": 2.1765,
"step": 166
},
{
"epoch": 0.3187855787476281,
"grad_norm": 2.186124086380005,
"learning_rate": 9.677857734146289e-05,
"loss": 2.2125,
"step": 168
},
{
"epoch": 0.3225806451612903,
"grad_norm": 2.4119503498077393,
"learning_rate": 9.666682605186835e-05,
"loss": 2.3575,
"step": 170
},
{
"epoch": 0.32637571157495254,
"grad_norm": 2.8744916915893555,
"learning_rate": 9.655323611500875e-05,
"loss": 2.3743,
"step": 172
},
{
"epoch": 0.3301707779886148,
"grad_norm": 2.419365644454956,
"learning_rate": 9.643781200626511e-05,
"loss": 2.1534,
"step": 174
},
{
"epoch": 0.33396584440227706,
"grad_norm": 2.3762214183807373,
"learning_rate": 9.632055827328382e-05,
"loss": 2.21,
"step": 176
},
{
"epoch": 0.3377609108159393,
"grad_norm": 2.7813262939453125,
"learning_rate": 9.620147953579737e-05,
"loss": 2.2469,
"step": 178
},
{
"epoch": 0.3415559772296015,
"grad_norm": 2.622725009918213,
"learning_rate": 9.608058048544251e-05,
"loss": 2.2637,
"step": 180
},
{
"epoch": 0.34535104364326374,
"grad_norm": 2.240797996520996,
"learning_rate": 9.595786588557532e-05,
"loss": 2.2345,
"step": 182
},
{
"epoch": 0.349146110056926,
"grad_norm": 2.4940717220306396,
"learning_rate": 9.583334057108346e-05,
"loss": 2.092,
"step": 184
},
{
"epoch": 0.35294117647058826,
"grad_norm": 2.522732973098755,
"learning_rate": 9.570700944819584e-05,
"loss": 2.4171,
"step": 186
},
{
"epoch": 0.3567362428842505,
"grad_norm": 2.0912716388702393,
"learning_rate": 9.557887749428913e-05,
"loss": 2.2612,
"step": 188
},
{
"epoch": 0.3605313092979127,
"grad_norm": 1.9055088758468628,
"learning_rate": 9.544894975769186e-05,
"loss": 2.1771,
"step": 190
},
{
"epoch": 0.36432637571157495,
"grad_norm": 1.9253450632095337,
"learning_rate": 9.531723135748529e-05,
"loss": 2.1706,
"step": 192
},
{
"epoch": 0.3681214421252372,
"grad_norm": 2.748800277709961,
"learning_rate": 9.518372748330194e-05,
"loss": 2.1258,
"step": 194
},
{
"epoch": 0.3719165085388994,
"grad_norm": 2.251387596130371,
"learning_rate": 9.504844339512095e-05,
"loss": 2.1086,
"step": 196
},
{
"epoch": 0.3757115749525617,
"grad_norm": 2.527620553970337,
"learning_rate": 9.4911384423061e-05,
"loss": 2.2926,
"step": 198
},
{
"epoch": 0.3795066413662239,
"grad_norm": 2.313129186630249,
"learning_rate": 9.477255596717012e-05,
"loss": 2.2394,
"step": 200
},
{
"epoch": 0.38330170777988615,
"grad_norm": 2.230227470397949,
"learning_rate": 9.463196349721308e-05,
"loss": 2.257,
"step": 202
},
{
"epoch": 0.3870967741935484,
"grad_norm": 2.3828601837158203,
"learning_rate": 9.448961255245584e-05,
"loss": 1.8899,
"step": 204
},
{
"epoch": 0.3908918406072106,
"grad_norm": 2.251528739929199,
"learning_rate": 9.434550874144728e-05,
"loss": 2.1155,
"step": 206
},
{
"epoch": 0.3946869070208729,
"grad_norm": 2.44451904296875,
"learning_rate": 9.419965774179824e-05,
"loss": 2.1349,
"step": 208
},
{
"epoch": 0.3984819734345351,
"grad_norm": 2.761258602142334,
"learning_rate": 9.405206529995785e-05,
"loss": 2.2427,
"step": 210
},
{
"epoch": 0.40227703984819735,
"grad_norm": 2.2666332721710205,
"learning_rate": 9.39027372309871e-05,
"loss": 2.1057,
"step": 212
},
{
"epoch": 0.4060721062618596,
"grad_norm": 2.4890060424804688,
"learning_rate": 9.375167941832973e-05,
"loss": 2.3074,
"step": 214
},
{
"epoch": 0.4098671726755218,
"grad_norm": 2.4449613094329834,
"learning_rate": 9.359889781358042e-05,
"loss": 2.1966,
"step": 216
},
{
"epoch": 0.41366223908918404,
"grad_norm": 2.3266401290893555,
"learning_rate": 9.344439843625034e-05,
"loss": 2.2541,
"step": 218
},
{
"epoch": 0.4174573055028463,
"grad_norm": 2.188577651977539,
"learning_rate": 9.32881873735299e-05,
"loss": 2.1832,
"step": 220
},
{
"epoch": 0.42125237191650855,
"grad_norm": 2.4441959857940674,
"learning_rate": 9.313027078004903e-05,
"loss": 2.1515,
"step": 222
},
{
"epoch": 0.4250474383301708,
"grad_norm": 2.0524024963378906,
"learning_rate": 9.297065487763462e-05,
"loss": 2.234,
"step": 224
},
{
"epoch": 0.428842504743833,
"grad_norm": 2.6497814655303955,
"learning_rate": 9.280934595506536e-05,
"loss": 2.037,
"step": 226
},
{
"epoch": 0.43263757115749524,
"grad_norm": 2.3481597900390625,
"learning_rate": 9.264635036782405e-05,
"loss": 2.0083,
"step": 228
},
{
"epoch": 0.4364326375711575,
"grad_norm": 2.729177236557007,
"learning_rate": 9.248167453784711e-05,
"loss": 2.0764,
"step": 230
},
{
"epoch": 0.44022770398481975,
"grad_norm": 2.4639577865600586,
"learning_rate": 9.231532495327165e-05,
"loss": 2.1613,
"step": 232
},
{
"epoch": 0.444022770398482,
"grad_norm": 1.9731899499893188,
"learning_rate": 9.21473081681797e-05,
"loss": 2.2774,
"step": 234
},
{
"epoch": 0.4478178368121442,
"grad_norm": 2.308135747909546,
"learning_rate": 9.197763080234019e-05,
"loss": 2.0484,
"step": 236
},
{
"epoch": 0.45161290322580644,
"grad_norm": 2.5813095569610596,
"learning_rate": 9.180629954094792e-05,
"loss": 2.0816,
"step": 238
},
{
"epoch": 0.45540796963946867,
"grad_norm": 2.0825326442718506,
"learning_rate": 9.163332113436032e-05,
"loss": 2.0074,
"step": 240
},
{
"epoch": 0.45920303605313095,
"grad_norm": 2.1156539916992188,
"learning_rate": 9.145870239783142e-05,
"loss": 2.1767,
"step": 242
},
{
"epoch": 0.4629981024667932,
"grad_norm": 2.0586719512939453,
"learning_rate": 9.128245021124334e-05,
"loss": 2.216,
"step": 244
},
{
"epoch": 0.4667931688804554,
"grad_norm": 2.7116453647613525,
"learning_rate": 9.110457151883523e-05,
"loss": 2.1157,
"step": 246
},
{
"epoch": 0.47058823529411764,
"grad_norm": 2.130892515182495,
"learning_rate": 9.092507332892968e-05,
"loss": 2.0619,
"step": 248
},
{
"epoch": 0.47438330170777987,
"grad_norm": 3.247701644897461,
"learning_rate": 9.07439627136566e-05,
"loss": 2.0613,
"step": 250
},
{
"epoch": 0.4781783681214421,
"grad_norm": 2.1448159217834473,
"learning_rate": 9.056124680867457e-05,
"loss": 2.0443,
"step": 252
},
{
"epoch": 0.4819734345351044,
"grad_norm": 1.8717658519744873,
"learning_rate": 9.037693281288969e-05,
"loss": 2.1883,
"step": 254
},
{
"epoch": 0.4857685009487666,
"grad_norm": 2.533971071243286,
"learning_rate": 9.019102798817197e-05,
"loss": 2.0945,
"step": 256
},
{
"epoch": 0.48956356736242884,
"grad_norm": 2.3268120288848877,
"learning_rate": 9.000353965906917e-05,
"loss": 2.1754,
"step": 258
},
{
"epoch": 0.49335863377609107,
"grad_norm": 2.2676422595977783,
"learning_rate": 8.981447521251831e-05,
"loss": 2.1148,
"step": 260
},
{
"epoch": 0.4971537001897533,
"grad_norm": 2.6276440620422363,
"learning_rate": 8.962384209755452e-05,
"loss": 1.9069,
"step": 262
},
{
"epoch": 0.5009487666034156,
"grad_norm": 2.5703928470611572,
"learning_rate": 8.943164782501765e-05,
"loss": 2.0956,
"step": 264
},
{
"epoch": 0.5047438330170778,
"grad_norm": 3.0325634479522705,
"learning_rate": 8.923789996725624e-05,
"loss": 2.0912,
"step": 266
},
{
"epoch": 0.50853889943074,
"grad_norm": 2.755262613296509,
"learning_rate": 8.904260615782927e-05,
"loss": 1.9925,
"step": 268
},
{
"epoch": 0.5123339658444023,
"grad_norm": 1.9825857877731323,
"learning_rate": 8.884577409120535e-05,
"loss": 2.107,
"step": 270
},
{
"epoch": 0.5161290322580645,
"grad_norm": 2.611501693725586,
"learning_rate": 8.864741152245963e-05,
"loss": 1.9966,
"step": 272
},
{
"epoch": 0.5199240986717267,
"grad_norm": 2.229191780090332,
"learning_rate": 8.84475262669681e-05,
"loss": 2.1841,
"step": 274
},
{
"epoch": 0.523719165085389,
"grad_norm": 2.437122106552124,
"learning_rate": 8.824612620009987e-05,
"loss": 2.2565,
"step": 276
},
{
"epoch": 0.5275142314990512,
"grad_norm": 1.8645908832550049,
"learning_rate": 8.804321925690672e-05,
"loss": 2.1215,
"step": 278
},
{
"epoch": 0.5313092979127134,
"grad_norm": 2.4032273292541504,
"learning_rate": 8.783881343181055e-05,
"loss": 2.0444,
"step": 280
},
{
"epoch": 0.5351043643263758,
"grad_norm": 1.9161407947540283,
"learning_rate": 8.763291677828838e-05,
"loss": 1.9423,
"step": 282
},
{
"epoch": 0.538899430740038,
"grad_norm": 2.1071085929870605,
"learning_rate": 8.742553740855506e-05,
"loss": 2.1471,
"step": 284
},
{
"epoch": 0.5426944971537002,
"grad_norm": 2.335345506668091,
"learning_rate": 8.721668349324364e-05,
"loss": 2.17,
"step": 286
},
{
"epoch": 0.5464895635673624,
"grad_norm": 2.361610174179077,
"learning_rate": 8.700636326108342e-05,
"loss": 2.1991,
"step": 288
},
{
"epoch": 0.5502846299810247,
"grad_norm": 2.2395853996276855,
"learning_rate": 8.679458499857582e-05,
"loss": 2.0917,
"step": 290
},
{
"epoch": 0.5540796963946869,
"grad_norm": 1.9436601400375366,
"learning_rate": 8.658135704966786e-05,
"loss": 2.0886,
"step": 292
},
{
"epoch": 0.5578747628083491,
"grad_norm": 2.0581061840057373,
"learning_rate": 8.636668781542336e-05,
"loss": 1.996,
"step": 294
},
{
"epoch": 0.5616698292220114,
"grad_norm": 2.023599624633789,
"learning_rate": 8.615058575369202e-05,
"loss": 1.9873,
"step": 296
},
{
"epoch": 0.5654648956356736,
"grad_norm": 2.3476357460021973,
"learning_rate": 8.593305937877614e-05,
"loss": 2.0121,
"step": 298
},
{
"epoch": 0.5692599620493358,
"grad_norm": 2.2934722900390625,
"learning_rate": 8.571411726109519e-05,
"loss": 2.1534,
"step": 300
},
{
"epoch": 0.573055028462998,
"grad_norm": 2.1299185752868652,
"learning_rate": 8.549376802684812e-05,
"loss": 2.171,
"step": 302
},
{
"epoch": 0.5768500948766604,
"grad_norm": 2.0197343826293945,
"learning_rate": 8.527202035767349e-05,
"loss": 2.1531,
"step": 304
},
{
"epoch": 0.5806451612903226,
"grad_norm": 2.506273031234741,
"learning_rate": 8.504888299030747e-05,
"loss": 2.0147,
"step": 306
},
{
"epoch": 0.5844402277039848,
"grad_norm": 2.27549147605896,
"learning_rate": 8.482436471623951e-05,
"loss": 2.1266,
"step": 308
},
{
"epoch": 0.5882352941176471,
"grad_norm": 1.975536823272705,
"learning_rate": 8.459847438136605e-05,
"loss": 1.8919,
"step": 310
},
{
"epoch": 0.5920303605313093,
"grad_norm": 2.4881391525268555,
"learning_rate": 8.437122088564198e-05,
"loss": 1.9813,
"step": 312
},
{
"epoch": 0.5958254269449715,
"grad_norm": 2.0626392364501953,
"learning_rate": 8.414261318272996e-05,
"loss": 2.0769,
"step": 314
},
{
"epoch": 0.5996204933586338,
"grad_norm": 2.17238450050354,
"learning_rate": 8.391266027964771e-05,
"loss": 2.117,
"step": 316
},
{
"epoch": 0.603415559772296,
"grad_norm": 2.1018152236938477,
"learning_rate": 8.368137123641302e-05,
"loss": 2.0473,
"step": 318
},
{
"epoch": 0.6072106261859582,
"grad_norm": 2.578695058822632,
"learning_rate": 8.344875516568695e-05,
"loss": 2.1261,
"step": 320
},
{
"epoch": 0.6110056925996205,
"grad_norm": 2.1131348609924316,
"learning_rate": 8.321482123241464e-05,
"loss": 1.9569,
"step": 322
},
{
"epoch": 0.6148007590132827,
"grad_norm": 2.0553090572357178,
"learning_rate": 8.297957865346437e-05,
"loss": 1.9675,
"step": 324
},
{
"epoch": 0.618595825426945,
"grad_norm": 2.184825897216797,
"learning_rate": 8.274303669726426e-05,
"loss": 1.7884,
"step": 326
},
{
"epoch": 0.6223908918406073,
"grad_norm": 2.0650479793548584,
"learning_rate": 8.250520468343722e-05,
"loss": 2.0114,
"step": 328
},
{
"epoch": 0.6261859582542695,
"grad_norm": 1.893213152885437,
"learning_rate": 8.226609198243372e-05,
"loss": 2.0744,
"step": 330
},
{
"epoch": 0.6299810246679317,
"grad_norm": 2.391218423843384,
"learning_rate": 8.202570801516256e-05,
"loss": 1.9348,
"step": 332
},
{
"epoch": 0.6337760910815939,
"grad_norm": 1.9588531255722046,
"learning_rate": 8.178406225261981e-05,
"loss": 1.9742,
"step": 334
},
{
"epoch": 0.6375711574952562,
"grad_norm": 1.881150245666504,
"learning_rate": 8.15411642155155e-05,
"loss": 1.8995,
"step": 336
},
{
"epoch": 0.6413662239089184,
"grad_norm": 2.0399060249328613,
"learning_rate": 8.129702347389865e-05,
"loss": 2.0344,
"step": 338
},
{
"epoch": 0.6451612903225806,
"grad_norm": 2.4058690071105957,
"learning_rate": 8.105164964678009e-05,
"loss": 2.247,
"step": 340
},
{
"epoch": 0.6489563567362429,
"grad_norm": 2.0536463260650635,
"learning_rate": 8.080505240175363e-05,
"loss": 2.089,
"step": 342
},
{
"epoch": 0.6527514231499051,
"grad_norm": 2.1815414428710938,
"learning_rate": 8.055724145461495e-05,
"loss": 1.9058,
"step": 344
},
{
"epoch": 0.6565464895635673,
"grad_norm": 2.4784576892852783,
"learning_rate": 8.030822656897902e-05,
"loss": 2.0248,
"step": 346
},
{
"epoch": 0.6603415559772297,
"grad_norm": 2.456225633621216,
"learning_rate": 8.005801755589532e-05,
"loss": 1.8769,
"step": 348
},
{
"epoch": 0.6641366223908919,
"grad_norm": 2.1188771724700928,
"learning_rate": 7.980662427346127e-05,
"loss": 1.7287,
"step": 350
},
{
"epoch": 0.6679316888045541,
"grad_norm": 2.5477139949798584,
"learning_rate": 7.955405662643384e-05,
"loss": 1.8033,
"step": 352
},
{
"epoch": 0.6717267552182163,
"grad_norm": 2.13031005859375,
"learning_rate": 7.930032456583931e-05,
"loss": 1.9851,
"step": 354
},
{
"epoch": 0.6755218216318786,
"grad_norm": 2.3359146118164062,
"learning_rate": 7.904543808858127e-05,
"loss": 1.8741,
"step": 356
},
{
"epoch": 0.6793168880455408,
"grad_norm": 2.3399510383605957,
"learning_rate": 7.878940723704664e-05,
"loss": 1.878,
"step": 358
},
{
"epoch": 0.683111954459203,
"grad_norm": 9.338287353515625,
"learning_rate": 7.853224209871007e-05,
"loss": 2.025,
"step": 360
},
{
"epoch": 0.6869070208728653,
"grad_norm": 2.3477447032928467,
"learning_rate": 7.82739528057365e-05,
"loss": 1.8737,
"step": 362
},
{
"epoch": 0.6907020872865275,
"grad_norm": 2.199747323989868,
"learning_rate": 7.801454953458193e-05,
"loss": 1.887,
"step": 364
},
{
"epoch": 0.6944971537001897,
"grad_norm": 2.2148537635803223,
"learning_rate": 7.775404250559249e-05,
"loss": 2.1818,
"step": 366
},
{
"epoch": 0.698292220113852,
"grad_norm": 2.256046772003174,
"learning_rate": 7.749244198260175e-05,
"loss": 1.939,
"step": 368
},
{
"epoch": 0.7020872865275142,
"grad_norm": 2.1630468368530273,
"learning_rate": 7.722975827252638e-05,
"loss": 2.1295,
"step": 370
},
{
"epoch": 0.7058823529411765,
"grad_norm": 2.2317686080932617,
"learning_rate": 7.696600172495997e-05,
"loss": 1.9906,
"step": 372
},
{
"epoch": 0.7096774193548387,
"grad_norm": 1.8585615158081055,
"learning_rate": 7.670118273176534e-05,
"loss": 1.9916,
"step": 374
},
{
"epoch": 0.713472485768501,
"grad_norm": 2.1483442783355713,
"learning_rate": 7.643531172666513e-05,
"loss": 1.9731,
"step": 376
},
{
"epoch": 0.7172675521821632,
"grad_norm": 1.8624950647354126,
"learning_rate": 7.616839918483061e-05,
"loss": 2.0486,
"step": 378
},
{
"epoch": 0.7210626185958254,
"grad_norm": 2.0186891555786133,
"learning_rate": 7.590045562246902e-05,
"loss": 1.9846,
"step": 380
},
{
"epoch": 0.7248576850094877,
"grad_norm": 2.1433908939361572,
"learning_rate": 7.563149159640929e-05,
"loss": 1.9472,
"step": 382
},
{
"epoch": 0.7286527514231499,
"grad_norm": 1.7634693384170532,
"learning_rate": 7.5361517703686e-05,
"loss": 1.9015,
"step": 384
},
{
"epoch": 0.7324478178368121,
"grad_norm": 1.9991909265518188,
"learning_rate": 7.509054458112202e-05,
"loss": 2.195,
"step": 386
},
{
"epoch": 0.7362428842504743,
"grad_norm": 1.9965640306472778,
"learning_rate": 7.481858290490917e-05,
"loss": 1.8882,
"step": 388
},
{
"epoch": 0.7400379506641366,
"grad_norm": 1.9620065689086914,
"learning_rate": 7.45456433901879e-05,
"loss": 1.9888,
"step": 390
},
{
"epoch": 0.7438330170777988,
"grad_norm": 2.1550259590148926,
"learning_rate": 7.427173679062484e-05,
"loss": 1.9795,
"step": 392
},
{
"epoch": 0.7476280834914611,
"grad_norm": 1.9854936599731445,
"learning_rate": 7.399687389798933e-05,
"loss": 2.045,
"step": 394
},
{
"epoch": 0.7514231499051234,
"grad_norm": 2.5971503257751465,
"learning_rate": 7.372106554172802e-05,
"loss": 1.9071,
"step": 396
},
{
"epoch": 0.7552182163187856,
"grad_norm": 2.014299154281616,
"learning_rate": 7.344432258853841e-05,
"loss": 1.9563,
"step": 398
},
{
"epoch": 0.7590132827324478,
"grad_norm": 2.3263943195343018,
"learning_rate": 7.316665594194053e-05,
"loss": 2.0188,
"step": 400
},
{
"epoch": 0.7628083491461101,
"grad_norm": 1.8033442497253418,
"learning_rate": 7.288807654184747e-05,
"loss": 1.9696,
"step": 402
},
{
"epoch": 0.7666034155597723,
"grad_norm": 1.855611801147461,
"learning_rate": 7.260859536413429e-05,
"loss": 1.9671,
"step": 404
},
{
"epoch": 0.7703984819734345,
"grad_norm": 1.6863681077957153,
"learning_rate": 7.232822342020557e-05,
"loss": 1.8224,
"step": 406
},
{
"epoch": 0.7741935483870968,
"grad_norm": 2.2093186378479004,
"learning_rate": 7.204697175656165e-05,
"loss": 2.0568,
"step": 408
},
{
"epoch": 0.777988614800759,
"grad_norm": 1.7775136232376099,
"learning_rate": 7.176485145436325e-05,
"loss": 1.9747,
"step": 410
},
{
"epoch": 0.7817836812144212,
"grad_norm": 4.166982173919678,
"learning_rate": 7.148187362899505e-05,
"loss": 2.0037,
"step": 412
},
{
"epoch": 0.7855787476280834,
"grad_norm": 1.9333082437515259,
"learning_rate": 7.119804942962762e-05,
"loss": 1.7863,
"step": 414
},
{
"epoch": 0.7893738140417458,
"grad_norm": 2.000554084777832,
"learning_rate": 7.091339003877826e-05,
"loss": 2.0397,
"step": 416
},
{
"epoch": 0.793168880455408,
"grad_norm": 2.2830910682678223,
"learning_rate": 7.062790667187029e-05,
"loss": 1.8858,
"step": 418
},
{
"epoch": 0.7969639468690702,
"grad_norm": 1.9902116060256958,
"learning_rate": 7.034161057679127e-05,
"loss": 1.9265,
"step": 420
},
{
"epoch": 0.8007590132827325,
"grad_norm": 2.0113532543182373,
"learning_rate": 7.005451303344979e-05,
"loss": 1.8964,
"step": 422
},
{
"epoch": 0.8045540796963947,
"grad_norm": 2.4870879650115967,
"learning_rate": 6.976662535333107e-05,
"loss": 1.8496,
"step": 424
},
{
"epoch": 0.8083491461100569,
"grad_norm": 1.8780527114868164,
"learning_rate": 6.947795887905127e-05,
"loss": 1.7636,
"step": 426
},
{
"epoch": 0.8121442125237192,
"grad_norm": 2.419468879699707,
"learning_rate": 6.918852498391063e-05,
"loss": 1.8459,
"step": 428
},
{
"epoch": 0.8159392789373814,
"grad_norm": 1.7983444929122925,
"learning_rate": 6.889833507144532e-05,
"loss": 2.0907,
"step": 430
},
{
"epoch": 0.8197343453510436,
"grad_norm": 2.6364119052886963,
"learning_rate": 6.860740057497823e-05,
"loss": 1.919,
"step": 432
},
{
"epoch": 0.8235294117647058,
"grad_norm": 2.0711793899536133,
"learning_rate": 6.831573295716837e-05,
"loss": 1.9841,
"step": 434
},
{
"epoch": 0.8273244781783681,
"grad_norm": 1.9117244482040405,
"learning_rate": 6.802334370955941e-05,
"loss": 1.8228,
"step": 436
},
{
"epoch": 0.8311195445920304,
"grad_norm": 2.3344852924346924,
"learning_rate": 6.773024435212678e-05,
"loss": 1.9401,
"step": 438
},
{
"epoch": 0.8349146110056926,
"grad_norm": 2.237938642501831,
"learning_rate": 6.743644643282388e-05,
"loss": 2.0432,
"step": 440
},
{
"epoch": 0.8387096774193549,
"grad_norm": 1.982789397239685,
"learning_rate": 6.714196152712704e-05,
"loss": 2.0652,
"step": 442
},
{
"epoch": 0.8425047438330171,
"grad_norm": 1.9378403425216675,
"learning_rate": 6.684680123757949e-05,
"loss": 1.8956,
"step": 444
},
{
"epoch": 0.8462998102466793,
"grad_norm": 1.7693856954574585,
"learning_rate": 6.65509771933342e-05,
"loss": 1.7579,
"step": 446
},
{
"epoch": 0.8500948766603416,
"grad_norm": 2.191204309463501,
"learning_rate": 6.625450104969572e-05,
"loss": 1.9152,
"step": 448
},
{
"epoch": 0.8538899430740038,
"grad_norm": 1.9331061840057373,
"learning_rate": 6.595738448766095e-05,
"loss": 1.9067,
"step": 450
},
{
"epoch": 0.857685009487666,
"grad_norm": 2.1357293128967285,
"learning_rate": 6.565963921345895e-05,
"loss": 1.9128,
"step": 452
},
{
"epoch": 0.8614800759013282,
"grad_norm": 2.125249147415161,
"learning_rate": 6.536127695808964e-05,
"loss": 1.9007,
"step": 454
},
{
"epoch": 0.8652751423149905,
"grad_norm": 2.02423357963562,
"learning_rate": 6.506230947686172e-05,
"loss": 1.8422,
"step": 456
},
{
"epoch": 0.8690702087286527,
"grad_norm": 2.1172332763671875,
"learning_rate": 6.47627485489294e-05,
"loss": 2.0275,
"step": 458
},
{
"epoch": 0.872865275142315,
"grad_norm": 1.9845889806747437,
"learning_rate": 6.446260597682839e-05,
"loss": 1.789,
"step": 460
},
{
"epoch": 0.8766603415559773,
"grad_norm": 1.6815240383148193,
"learning_rate": 6.416189358601088e-05,
"loss": 1.7675,
"step": 462
},
{
"epoch": 0.8804554079696395,
"grad_norm": 1.8813481330871582,
"learning_rate": 6.386062322437954e-05,
"loss": 1.7444,
"step": 464
},
{
"epoch": 0.8842504743833017,
"grad_norm": 1.8697395324707031,
"learning_rate": 6.355880676182086e-05,
"loss": 1.9683,
"step": 466
},
{
"epoch": 0.888045540796964,
"grad_norm": 1.6431670188903809,
"learning_rate": 6.325645608973735e-05,
"loss": 1.876,
"step": 468
},
{
"epoch": 0.8918406072106262,
"grad_norm": 1.9128183126449585,
"learning_rate": 6.295358312057914e-05,
"loss": 1.9174,
"step": 470
},
{
"epoch": 0.8956356736242884,
"grad_norm": 1.9768314361572266,
"learning_rate": 6.26501997873745e-05,
"loss": 1.7516,
"step": 472
},
{
"epoch": 0.8994307400379506,
"grad_norm": 1.7421456575393677,
"learning_rate": 6.234631804325981e-05,
"loss": 1.93,
"step": 474
},
{
"epoch": 0.9032258064516129,
"grad_norm": 2.399038791656494,
"learning_rate": 6.204194986100857e-05,
"loss": 1.8731,
"step": 476
},
{
"epoch": 0.9070208728652751,
"grad_norm": 2.033057928085327,
"learning_rate": 6.173710723255966e-05,
"loss": 2.0181,
"step": 478
},
{
"epoch": 0.9108159392789373,
"grad_norm": 1.9236119985580444,
"learning_rate": 6.143180216854487e-05,
"loss": 1.7207,
"step": 480
},
{
"epoch": 0.9146110056925996,
"grad_norm": 2.085498094558716,
"learning_rate": 6.112604669781572e-05,
"loss": 1.8697,
"step": 482
},
{
"epoch": 0.9184060721062619,
"grad_norm": 1.768946647644043,
"learning_rate": 6.081985286696949e-05,
"loss": 2.0217,
"step": 484
},
{
"epoch": 0.9222011385199241,
"grad_norm": 2.2474300861358643,
"learning_rate": 6.051323273987463e-05,
"loss": 1.823,
"step": 486
},
{
"epoch": 0.9259962049335864,
"grad_norm": 1.748538851737976,
"learning_rate": 6.020619839719538e-05,
"loss": 1.9012,
"step": 488
},
{
"epoch": 0.9297912713472486,
"grad_norm": 2.026527166366577,
"learning_rate": 5.989876193591589e-05,
"loss": 1.939,
"step": 490
},
{
"epoch": 0.9335863377609108,
"grad_norm": 1.955435872077942,
"learning_rate": 5.959093546886356e-05,
"loss": 1.8873,
"step": 492
},
{
"epoch": 0.937381404174573,
"grad_norm": 1.5533896684646606,
"learning_rate": 5.928273112423177e-05,
"loss": 1.7242,
"step": 494
},
{
"epoch": 0.9411764705882353,
"grad_norm": 2.056882381439209,
"learning_rate": 5.897416104510211e-05,
"loss": 1.8731,
"step": 496
},
{
"epoch": 0.9449715370018975,
"grad_norm": 1.7425134181976318,
"learning_rate": 5.866523738896587e-05,
"loss": 1.803,
"step": 498
},
{
"epoch": 0.9487666034155597,
"grad_norm": 2.0654280185699463,
"learning_rate": 5.835597232724511e-05,
"loss": 1.9035,
"step": 500
},
{
"epoch": 0.952561669829222,
"grad_norm": 1.887492299079895,
"learning_rate": 5.804637804481306e-05,
"loss": 1.8336,
"step": 502
},
{
"epoch": 0.9563567362428842,
"grad_norm": 1.7280800342559814,
"learning_rate": 5.773646673951406e-05,
"loss": 1.9392,
"step": 504
},
{
"epoch": 0.9601518026565465,
"grad_norm": 1.780470371246338,
"learning_rate": 5.742625062168303e-05,
"loss": 2.015,
"step": 506
},
{
"epoch": 0.9639468690702088,
"grad_norm": 1.6500823497772217,
"learning_rate": 5.7115741913664264e-05,
"loss": 1.856,
"step": 508
},
{
"epoch": 0.967741935483871,
"grad_norm": 1.7888381481170654,
"learning_rate": 5.680495284933e-05,
"loss": 1.9106,
"step": 510
},
{
"epoch": 0.9715370018975332,
"grad_norm": 1.7840577363967896,
"learning_rate": 5.649389567359831e-05,
"loss": 1.9047,
"step": 512
},
{
"epoch": 0.9753320683111955,
"grad_norm": 1.9704608917236328,
"learning_rate": 5.6182582641950764e-05,
"loss": 1.7601,
"step": 514
},
{
"epoch": 0.9791271347248577,
"grad_norm": 1.8685930967330933,
"learning_rate": 5.58710260199495e-05,
"loss": 1.835,
"step": 516
},
{
"epoch": 0.9829222011385199,
"grad_norm": 1.6889925003051758,
"learning_rate": 5.555923808275395e-05,
"loss": 1.6878,
"step": 518
},
{
"epoch": 0.9867172675521821,
"grad_norm": 1.939340591430664,
"learning_rate": 5.5247231114637256e-05,
"loss": 1.7562,
"step": 520
},
{
"epoch": 0.9905123339658444,
"grad_norm": 1.8258569240570068,
"learning_rate": 5.4935017408502274e-05,
"loss": 1.9279,
"step": 522
},
{
"epoch": 0.9943074003795066,
"grad_norm": 1.8884730339050293,
"learning_rate": 5.462260926539722e-05,
"loss": 1.891,
"step": 524
},
{
"epoch": 0.9981024667931688,
"grad_norm": 1.8060804605484009,
"learning_rate": 5.431001899403098e-05,
"loss": 1.8849,
"step": 526
},
{
"epoch": 1.0018975332068312,
"grad_norm": 1.7513583898544312,
"learning_rate": 5.399725891028824e-05,
"loss": 1.5969,
"step": 528
},
{
"epoch": 1.0056925996204933,
"grad_norm": 1.6141959428787231,
"learning_rate": 5.368434133674417e-05,
"loss": 1.5982,
"step": 530
},
{
"epoch": 1.0094876660341556,
"grad_norm": 1.8763744831085205,
"learning_rate": 5.3371278602179e-05,
"loss": 1.7373,
"step": 532
},
{
"epoch": 1.0132827324478177,
"grad_norm": 1.7361050844192505,
"learning_rate": 5.305808304109214e-05,
"loss": 1.6725,
"step": 534
},
{
"epoch": 1.01707779886148,
"grad_norm": 1.9672235250473022,
"learning_rate": 5.274476699321638e-05,
"loss": 1.6056,
"step": 536
},
{
"epoch": 1.0208728652751424,
"grad_norm": 1.6261194944381714,
"learning_rate": 5.243134280303156e-05,
"loss": 1.5636,
"step": 538
},
{
"epoch": 1.0246679316888045,
"grad_norm": 1.8695908784866333,
"learning_rate": 5.211782281927832e-05,
"loss": 1.8106,
"step": 540
},
{
"epoch": 1.0284629981024669,
"grad_norm": 2.1503684520721436,
"learning_rate": 5.1804219394471456e-05,
"loss": 1.6731,
"step": 542
},
{
"epoch": 1.032258064516129,
"grad_norm": 1.962134838104248,
"learning_rate": 5.149054488441333e-05,
"loss": 1.8046,
"step": 544
},
{
"epoch": 1.0360531309297913,
"grad_norm": 1.705989122390747,
"learning_rate": 5.117681164770704e-05,
"loss": 1.5574,
"step": 546
},
{
"epoch": 1.0398481973434535,
"grad_norm": 4.793671131134033,
"learning_rate": 5.086303204526943e-05,
"loss": 1.5895,
"step": 548
},
{
"epoch": 1.0436432637571158,
"grad_norm": 1.9258722066879272,
"learning_rate": 5.054921843984418e-05,
"loss": 1.5321,
"step": 550
},
{
"epoch": 1.047438330170778,
"grad_norm": 2.6446402072906494,
"learning_rate": 5.023538319551465e-05,
"loss": 1.6043,
"step": 552
},
{
"epoch": 1.0512333965844403,
"grad_norm": 1.7615056037902832,
"learning_rate": 4.9921538677216736e-05,
"loss": 1.6521,
"step": 554
},
{
"epoch": 1.0550284629981024,
"grad_norm": 2.0043654441833496,
"learning_rate": 4.9607697250251786e-05,
"loss": 1.6549,
"step": 556
},
{
"epoch": 1.0588235294117647,
"grad_norm": 1.6236051321029663,
"learning_rate": 4.929387127979927e-05,
"loss": 1.7121,
"step": 558
},
{
"epoch": 1.0626185958254268,
"grad_norm": 1.5524344444274902,
"learning_rate": 4.898007313042975e-05,
"loss": 1.6796,
"step": 560
},
{
"epoch": 1.0664136622390892,
"grad_norm": 2.0469348430633545,
"learning_rate": 4.866631516561759e-05,
"loss": 1.5897,
"step": 562
},
{
"epoch": 1.0702087286527515,
"grad_norm": 2.923673152923584,
"learning_rate": 4.835260974725397e-05,
"loss": 1.7134,
"step": 564
},
{
"epoch": 1.0740037950664136,
"grad_norm": 1.7643365859985352,
"learning_rate": 4.803896923515974e-05,
"loss": 1.6197,
"step": 566
},
{
"epoch": 1.077798861480076,
"grad_norm": 1.984552264213562,
"learning_rate": 4.772540598659844e-05,
"loss": 1.7605,
"step": 568
},
{
"epoch": 1.081593927893738,
"grad_norm": 1.7113956212997437,
"learning_rate": 4.741193235578952e-05,
"loss": 1.5824,
"step": 570
},
{
"epoch": 1.0853889943074004,
"grad_norm": 3.692016124725342,
"learning_rate": 4.7098560693421565e-05,
"loss": 1.6475,
"step": 572
},
{
"epoch": 1.0891840607210626,
"grad_norm": 2.923161268234253,
"learning_rate": 4.678530334616557e-05,
"loss": 1.6728,
"step": 574
},
{
"epoch": 1.092979127134725,
"grad_norm": 1.8435837030410767,
"learning_rate": 4.647217265618866e-05,
"loss": 1.6125,
"step": 576
},
{
"epoch": 1.096774193548387,
"grad_norm": 1.910549521446228,
"learning_rate": 4.615918096066766e-05,
"loss": 1.5682,
"step": 578
},
{
"epoch": 1.1005692599620494,
"grad_norm": 1.6668466329574585,
"learning_rate": 4.584634059130317e-05,
"loss": 1.5572,
"step": 580
},
{
"epoch": 1.1043643263757117,
"grad_norm": 1.6561187505722046,
"learning_rate": 4.553366387383357e-05,
"loss": 1.5858,
"step": 582
},
{
"epoch": 1.1081593927893738,
"grad_norm": 1.6459676027297974,
"learning_rate": 4.522116312754944e-05,
"loss": 1.7266,
"step": 584
},
{
"epoch": 1.1119544592030361,
"grad_norm": 1.4629384279251099,
"learning_rate": 4.4908850664808245e-05,
"loss": 1.6311,
"step": 586
},
{
"epoch": 1.1157495256166983,
"grad_norm": 1.601250171661377,
"learning_rate": 4.4596738790549114e-05,
"loss": 1.7363,
"step": 588
},
{
"epoch": 1.1195445920303606,
"grad_norm": 1.7702630758285522,
"learning_rate": 4.428483980180814e-05,
"loss": 1.6243,
"step": 590
},
{
"epoch": 1.1233396584440227,
"grad_norm": 1.6879682540893555,
"learning_rate": 4.397316598723385e-05,
"loss": 1.6103,
"step": 592
},
{
"epoch": 1.127134724857685,
"grad_norm": 1.8779839277267456,
"learning_rate": 4.366172962660301e-05,
"loss": 1.6518,
"step": 594
},
{
"epoch": 1.1309297912713472,
"grad_norm": 1.734568476676941,
"learning_rate": 4.335054299033686e-05,
"loss": 1.6961,
"step": 596
},
{
"epoch": 1.1347248576850095,
"grad_norm": 2.0654520988464355,
"learning_rate": 4.3039618339017595e-05,
"loss": 1.5378,
"step": 598
},
{
"epoch": 1.1385199240986716,
"grad_norm": 1.8457181453704834,
"learning_rate": 4.272896792290537e-05,
"loss": 1.719,
"step": 600
},
{
"epoch": 1.142314990512334,
"grad_norm": 1.784895896911621,
"learning_rate": 4.241860398145565e-05,
"loss": 1.6039,
"step": 602
},
{
"epoch": 1.146110056925996,
"grad_norm": 1.8421404361724854,
"learning_rate": 4.2108538742836906e-05,
"loss": 1.7036,
"step": 604
},
{
"epoch": 1.1499051233396584,
"grad_norm": 1.670223355293274,
"learning_rate": 4.179878442344892e-05,
"loss": 1.7127,
"step": 606
},
{
"epoch": 1.1537001897533208,
"grad_norm": 1.678078055381775,
"learning_rate": 4.14893532274414e-05,
"loss": 1.5453,
"step": 608
},
{
"epoch": 1.157495256166983,
"grad_norm": 2.4001028537750244,
"learning_rate": 4.1180257346233186e-05,
"loss": 1.4696,
"step": 610
},
{
"epoch": 1.1612903225806452,
"grad_norm": 2.5787084102630615,
"learning_rate": 4.0871508958031924e-05,
"loss": 1.7019,
"step": 612
},
{
"epoch": 1.1650853889943074,
"grad_norm": 2.0371854305267334,
"learning_rate": 4.056312022735417e-05,
"loss": 1.611,
"step": 614
},
{
"epoch": 1.1688804554079697,
"grad_norm": 1.8083865642547607,
"learning_rate": 4.025510330454621e-05,
"loss": 1.6278,
"step": 616
},
{
"epoch": 1.1726755218216318,
"grad_norm": 1.820249319076538,
"learning_rate": 3.994747032530532e-05,
"loss": 1.8616,
"step": 618
},
{
"epoch": 1.1764705882352942,
"grad_norm": 1.6026626825332642,
"learning_rate": 3.9640233410201553e-05,
"loss": 1.528,
"step": 620
},
{
"epoch": 1.1802656546489563,
"grad_norm": 1.9880168437957764,
"learning_rate": 3.933340466420032e-05,
"loss": 1.6077,
"step": 622
},
{
"epoch": 1.1840607210626186,
"grad_norm": 1.8110029697418213,
"learning_rate": 3.902699617618531e-05,
"loss": 1.6066,
"step": 624
},
{
"epoch": 1.187855787476281,
"grad_norm": 1.5748740434646606,
"learning_rate": 3.872102001848238e-05,
"loss": 1.5758,
"step": 626
},
{
"epoch": 1.191650853889943,
"grad_norm": 1.8446635007858276,
"learning_rate": 3.841548824638376e-05,
"loss": 1.6679,
"step": 628
},
{
"epoch": 1.1954459203036052,
"grad_norm": 1.5367991924285889,
"learning_rate": 3.8110412897673096e-05,
"loss": 1.5633,
"step": 630
},
{
"epoch": 1.1992409867172675,
"grad_norm": 1.9143991470336914,
"learning_rate": 3.7805805992151284e-05,
"loss": 1.551,
"step": 632
},
{
"epoch": 1.2030360531309299,
"grad_norm": 1.7603988647460938,
"learning_rate": 3.750167953116272e-05,
"loss": 1.6829,
"step": 634
},
{
"epoch": 1.206831119544592,
"grad_norm": 1.8393781185150146,
"learning_rate": 3.719804549712265e-05,
"loss": 1.6273,
"step": 636
},
{
"epoch": 1.2106261859582543,
"grad_norm": 1.7214066982269287,
"learning_rate": 3.689491585304491e-05,
"loss": 1.4822,
"step": 638
},
{
"epoch": 1.2144212523719164,
"grad_norm": 1.8236773014068604,
"learning_rate": 3.6592302542070624e-05,
"loss": 1.5977,
"step": 640
},
{
"epoch": 1.2182163187855788,
"grad_norm": 1.6606887578964233,
"learning_rate": 3.629021748699777e-05,
"loss": 1.6026,
"step": 642
},
{
"epoch": 1.222011385199241,
"grad_norm": 1.993834137916565,
"learning_rate": 3.598867258981122e-05,
"loss": 1.6981,
"step": 644
},
{
"epoch": 1.2258064516129032,
"grad_norm": 1.6002016067504883,
"learning_rate": 3.5687679731214016e-05,
"loss": 1.6245,
"step": 646
},
{
"epoch": 1.2296015180265654,
"grad_norm": 1.499503254890442,
"learning_rate": 3.538725077015915e-05,
"loss": 1.6115,
"step": 648
},
{
"epoch": 1.2333965844402277,
"grad_norm": 1.7892285585403442,
"learning_rate": 3.5087397543382326e-05,
"loss": 1.6785,
"step": 650
},
{
"epoch": 1.23719165085389,
"grad_norm": 1.606438159942627,
"learning_rate": 3.478813186493569e-05,
"loss": 1.6088,
"step": 652
},
{
"epoch": 1.2409867172675522,
"grad_norm": 1.634141206741333,
"learning_rate": 3.448946552572229e-05,
"loss": 1.7933,
"step": 654
},
{
"epoch": 1.2447817836812145,
"grad_norm": 1.5558969974517822,
"learning_rate": 3.419141029303149e-05,
"loss": 1.4674,
"step": 656
},
{
"epoch": 1.2485768500948766,
"grad_norm": 1.7423956394195557,
"learning_rate": 3.389397791007548e-05,
"loss": 1.569,
"step": 658
},
{
"epoch": 1.252371916508539,
"grad_norm": 1.5805660486221313,
"learning_rate": 3.3597180095526434e-05,
"loss": 1.6128,
"step": 660
},
{
"epoch": 1.256166982922201,
"grad_norm": 1.532578706741333,
"learning_rate": 3.3301028543054935e-05,
"loss": 1.6334,
"step": 662
},
{
"epoch": 1.2599620493358634,
"grad_norm": 1.7733721733093262,
"learning_rate": 3.3005534920869176e-05,
"loss": 1.6601,
"step": 664
},
{
"epoch": 1.2637571157495255,
"grad_norm": 1.7380473613739014,
"learning_rate": 3.271071087125522e-05,
"loss": 1.5502,
"step": 666
},
{
"epoch": 1.2675521821631879,
"grad_norm": 1.900283932685852,
"learning_rate": 3.2416568010118435e-05,
"loss": 1.7251,
"step": 668
},
{
"epoch": 1.2713472485768502,
"grad_norm": 1.7102822065353394,
"learning_rate": 3.212311792652564e-05,
"loss": 1.5427,
"step": 670
},
{
"epoch": 1.2751423149905123,
"grad_norm": 2.020052433013916,
"learning_rate": 3.183037218224862e-05,
"loss": 1.7921,
"step": 672
},
{
"epoch": 1.2789373814041745,
"grad_norm": 1.70509934425354,
"learning_rate": 3.153834231130866e-05,
"loss": 1.6646,
"step": 674
},
{
"epoch": 1.2827324478178368,
"grad_norm": 2.0357022285461426,
"learning_rate": 3.124703981952191e-05,
"loss": 1.5369,
"step": 676
},
{
"epoch": 1.2865275142314991,
"grad_norm": 1.7334659099578857,
"learning_rate": 3.0956476184046275e-05,
"loss": 1.4667,
"step": 678
},
{
"epoch": 1.2903225806451613,
"grad_norm": 1.8005759716033936,
"learning_rate": 3.066666285292906e-05,
"loss": 1.6016,
"step": 680
},
{
"epoch": 1.2941176470588236,
"grad_norm": 1.7932777404785156,
"learning_rate": 3.037761124465604e-05,
"loss": 1.6704,
"step": 682
},
{
"epoch": 1.2979127134724857,
"grad_norm": 1.4979898929595947,
"learning_rate": 3.0089332747701527e-05,
"loss": 1.4929,
"step": 684
},
{
"epoch": 1.301707779886148,
"grad_norm": 2.129861354827881,
"learning_rate": 2.9801838720079633e-05,
"loss": 1.6509,
"step": 686
},
{
"epoch": 1.3055028462998102,
"grad_norm": 1.701481819152832,
"learning_rate": 2.9515140488896847e-05,
"loss": 1.5343,
"step": 688
},
{
"epoch": 1.3092979127134725,
"grad_norm": 1.9436883926391602,
"learning_rate": 2.9229249349905684e-05,
"loss": 1.5981,
"step": 690
},
{
"epoch": 1.3130929791271346,
"grad_norm": 1.6280595064163208,
"learning_rate": 2.8944176567059706e-05,
"loss": 1.5697,
"step": 692
},
{
"epoch": 1.316888045540797,
"grad_norm": 1.769726037979126,
"learning_rate": 2.86599333720697e-05,
"loss": 1.6868,
"step": 694
},
{
"epoch": 1.3206831119544593,
"grad_norm": 1.780272364616394,
"learning_rate": 2.837653096396108e-05,
"loss": 1.5469,
"step": 696
},
{
"epoch": 1.3244781783681214,
"grad_norm": 1.7778898477554321,
"learning_rate": 2.809398050863279e-05,
"loss": 1.6614,
"step": 698
},
{
"epoch": 1.3282732447817835,
"grad_norm": 1.6337729692459106,
"learning_rate": 2.7812293138417312e-05,
"loss": 1.4908,
"step": 700
},
{
"epoch": 1.3320683111954459,
"grad_norm": 1.6277657747268677,
"learning_rate": 2.7531479951641924e-05,
"loss": 1.6146,
"step": 702
},
{
"epoch": 1.3358633776091082,
"grad_norm": 1.7180896997451782,
"learning_rate": 2.7251552012191762e-05,
"loss": 1.6909,
"step": 704
},
{
"epoch": 1.3396584440227703,
"grad_norm": 2.4234225749969482,
"learning_rate": 2.697252034907351e-05,
"loss": 1.6002,
"step": 706
},
{
"epoch": 1.3434535104364327,
"grad_norm": 2.085348606109619,
"learning_rate": 2.6694395955981143e-05,
"loss": 1.6343,
"step": 708
},
{
"epoch": 1.3472485768500948,
"grad_norm": 1.733147382736206,
"learning_rate": 2.641718979086277e-05,
"loss": 1.6616,
"step": 710
},
{
"epoch": 1.3510436432637571,
"grad_norm": 1.659242033958435,
"learning_rate": 2.614091277548864e-05,
"loss": 1.5906,
"step": 712
},
{
"epoch": 1.3548387096774195,
"grad_norm": 1.8294703960418701,
"learning_rate": 2.5865575795021218e-05,
"loss": 1.6858,
"step": 714
},
{
"epoch": 1.3586337760910816,
"grad_norm": 1.7453503608703613,
"learning_rate": 2.559118969758595e-05,
"loss": 1.519,
"step": 716
},
{
"epoch": 1.3624288425047437,
"grad_norm": 1.581979751586914,
"learning_rate": 2.531776529384407e-05,
"loss": 1.6147,
"step": 718
},
{
"epoch": 1.366223908918406,
"grad_norm": 1.483011245727539,
"learning_rate": 2.504531335656668e-05,
"loss": 1.6102,
"step": 720
},
{
"epoch": 1.3700189753320684,
"grad_norm": 1.390499234199524,
"learning_rate": 2.4773844620210118e-05,
"loss": 1.4623,
"step": 722
},
{
"epoch": 1.3738140417457305,
"grad_norm": 1.5694905519485474,
"learning_rate": 2.450336978049322e-05,
"loss": 1.6108,
"step": 724
},
{
"epoch": 1.3776091081593929,
"grad_norm": 1.5687963962554932,
"learning_rate": 2.423389949397582e-05,
"loss": 1.4976,
"step": 726
},
{
"epoch": 1.381404174573055,
"grad_norm": 1.7547636032104492,
"learning_rate": 2.3965444377638906e-05,
"loss": 1.6398,
"step": 728
},
{
"epoch": 1.3851992409867173,
"grad_norm": 1.7060229778289795,
"learning_rate": 2.3698015008466372e-05,
"loss": 1.5348,
"step": 730
},
{
"epoch": 1.3889943074003794,
"grad_norm": 1.6229296922683716,
"learning_rate": 2.3431621923028145e-05,
"loss": 1.5673,
"step": 732
},
{
"epoch": 1.3927893738140418,
"grad_norm": 1.7312480211257935,
"learning_rate": 2.3166275617065213e-05,
"loss": 1.7125,
"step": 734
},
{
"epoch": 1.396584440227704,
"grad_norm": 1.7121543884277344,
"learning_rate": 2.2901986545076e-05,
"loss": 1.6875,
"step": 736
},
{
"epoch": 1.4003795066413662,
"grad_norm": 1.9793061017990112,
"learning_rate": 2.26387651199045e-05,
"loss": 1.6521,
"step": 738
},
{
"epoch": 1.4041745730550286,
"grad_norm": 1.6552616357803345,
"learning_rate": 2.2376621712330015e-05,
"loss": 1.581,
"step": 740
},
{
"epoch": 1.4079696394686907,
"grad_norm": 1.548330545425415,
"learning_rate": 2.2115566650658536e-05,
"loss": 1.5672,
"step": 742
},
{
"epoch": 1.4117647058823528,
"grad_norm": 1.501119613647461,
"learning_rate": 2.185561022031582e-05,
"loss": 1.5377,
"step": 744
},
{
"epoch": 1.4155597722960152,
"grad_norm": 1.5841186046600342,
"learning_rate": 2.1596762663442218e-05,
"loss": 1.5666,
"step": 746
},
{
"epoch": 1.4193548387096775,
"grad_norm": 3.3083882331848145,
"learning_rate": 2.1339034178488964e-05,
"loss": 1.5547,
"step": 748
},
{
"epoch": 1.4231499051233396,
"grad_norm": 1.5293527841567993,
"learning_rate": 2.1082434919816557e-05,
"loss": 1.5483,
"step": 750
},
{
"epoch": 1.426944971537002,
"grad_norm": 1.7929829359054565,
"learning_rate": 2.0826974997294574e-05,
"loss": 1.6082,
"step": 752
},
{
"epoch": 1.430740037950664,
"grad_norm": 1.620683193206787,
"learning_rate": 2.0572664475903386e-05,
"loss": 1.4812,
"step": 754
},
{
"epoch": 1.4345351043643264,
"grad_norm": 1.6500731706619263,
"learning_rate": 2.0319513375337578e-05,
"loss": 1.5314,
"step": 756
},
{
"epoch": 1.4383301707779887,
"grad_norm": 1.8740296363830566,
"learning_rate": 2.0067531669611206e-05,
"loss": 1.5919,
"step": 758
},
{
"epoch": 1.4421252371916509,
"grad_norm": 1.749290108680725,
"learning_rate": 1.9816729286664798e-05,
"loss": 1.5756,
"step": 760
},
{
"epoch": 1.445920303605313,
"grad_norm": 1.6119389533996582,
"learning_rate": 1.9567116107974232e-05,
"loss": 1.563,
"step": 762
},
{
"epoch": 1.4497153700189753,
"grad_norm": 1.5941872596740723,
"learning_rate": 1.931870196816138e-05,
"loss": 1.4741,
"step": 764
},
{
"epoch": 1.4535104364326377,
"grad_norm": 6.304764747619629,
"learning_rate": 1.907149665460664e-05,
"loss": 1.5027,
"step": 766
},
{
"epoch": 1.4573055028462998,
"grad_norm": 1.6818827390670776,
"learning_rate": 1.8825509907063327e-05,
"loss": 1.6187,
"step": 768
},
{
"epoch": 1.4611005692599621,
"grad_norm": 1.6879651546478271,
"learning_rate": 1.8580751417273928e-05,
"loss": 1.5416,
"step": 770
},
{
"epoch": 1.4648956356736242,
"grad_norm": 1.6485869884490967,
"learning_rate": 1.833723082858825e-05,
"loss": 1.4749,
"step": 772
},
{
"epoch": 1.4686907020872866,
"grad_norm": 1.6072818040847778,
"learning_rate": 1.8094957735583463e-05,
"loss": 1.5773,
"step": 774
},
{
"epoch": 1.4724857685009487,
"grad_norm": 1.6340699195861816,
"learning_rate": 1.7853941683686114e-05,
"loss": 1.5121,
"step": 776
},
{
"epoch": 1.476280834914611,
"grad_norm": 1.567878246307373,
"learning_rate": 1.761419216879601e-05,
"loss": 1.6572,
"step": 778
},
{
"epoch": 1.4800759013282732,
"grad_norm": 1.5631004571914673,
"learning_rate": 1.7375718636912103e-05,
"loss": 1.4506,
"step": 780
},
{
"epoch": 1.4838709677419355,
"grad_norm": 1.651151418685913,
"learning_rate": 1.7138530483760314e-05,
"loss": 1.5569,
"step": 782
},
{
"epoch": 1.4876660341555978,
"grad_norm": 1.6107643842697144,
"learning_rate": 1.690263705442334e-05,
"loss": 1.5487,
"step": 784
},
{
"epoch": 1.49146110056926,
"grad_norm": 1.6784757375717163,
"learning_rate": 1.6668047642972494e-05,
"loss": 1.6277,
"step": 786
},
{
"epoch": 1.495256166982922,
"grad_norm": 1.5610170364379883,
"learning_rate": 1.6434771492101485e-05,
"loss": 1.6042,
"step": 788
},
{
"epoch": 1.4990512333965844,
"grad_norm": 1.6170179843902588,
"learning_rate": 1.6202817792762282e-05,
"loss": 1.7036,
"step": 790
},
{
"epoch": 1.5028462998102468,
"grad_norm": 1.5913422107696533,
"learning_rate": 1.5972195683802992e-05,
"loss": 1.8443,
"step": 792
},
{
"epoch": 1.5066413662239089,
"grad_norm": 1.7777653932571411,
"learning_rate": 1.5742914251607793e-05,
"loss": 1.4779,
"step": 794
},
{
"epoch": 1.510436432637571,
"grad_norm": 1.6909193992614746,
"learning_rate": 1.5514982529738946e-05,
"loss": 1.6566,
"step": 796
},
{
"epoch": 1.5142314990512333,
"grad_norm": 1.6290650367736816,
"learning_rate": 1.5288409498580824e-05,
"loss": 1.731,
"step": 798
},
{
"epoch": 1.5180265654648957,
"grad_norm": 1.5219643115997314,
"learning_rate": 1.506320408498621e-05,
"loss": 1.5699,
"step": 800
},
{
"epoch": 1.521821631878558,
"grad_norm": 1.4558225870132446,
"learning_rate": 1.4839375161924446e-05,
"loss": 1.5735,
"step": 802
},
{
"epoch": 1.5256166982922201,
"grad_norm": 1.5122625827789307,
"learning_rate": 1.4616931548131929e-05,
"loss": 1.4885,
"step": 804
},
{
"epoch": 1.5294117647058822,
"grad_norm": 1.3705723285675049,
"learning_rate": 1.4395882007764644e-05,
"loss": 1.3854,
"step": 806
},
{
"epoch": 1.5332068311195446,
"grad_norm": 1.4855965375900269,
"learning_rate": 1.4176235250052788e-05,
"loss": 1.6501,
"step": 808
},
{
"epoch": 1.537001897533207,
"grad_norm": 1.482972502708435,
"learning_rate": 1.3957999928957787e-05,
"loss": 1.5601,
"step": 810
},
{
"epoch": 1.540796963946869,
"grad_norm": 1.9199706315994263,
"learning_rate": 1.3741184642831189e-05,
"loss": 1.5778,
"step": 812
},
{
"epoch": 1.5445920303605312,
"grad_norm": 1.499746322631836,
"learning_rate": 1.3525797934075912e-05,
"loss": 1.4965,
"step": 814
},
{
"epoch": 1.5483870967741935,
"grad_norm": 1.533549427986145,
"learning_rate": 1.3311848288809813e-05,
"loss": 1.6208,
"step": 816
},
{
"epoch": 1.5521821631878558,
"grad_norm": 1.6243884563446045,
"learning_rate": 1.3099344136531105e-05,
"loss": 1.7243,
"step": 818
},
{
"epoch": 1.5559772296015182,
"grad_norm": 1.9431763887405396,
"learning_rate": 1.2888293849786503e-05,
"loss": 1.5163,
"step": 820
},
{
"epoch": 1.5597722960151803,
"grad_norm": 1.6569082736968994,
"learning_rate": 1.2678705743841152e-05,
"loss": 1.5776,
"step": 822
},
{
"epoch": 1.5635673624288424,
"grad_norm": 1.462570071220398,
"learning_rate": 1.2470588076351036e-05,
"loss": 1.4262,
"step": 824
},
{
"epoch": 1.5673624288425048,
"grad_norm": 1.4219212532043457,
"learning_rate": 1.2263949047037786e-05,
"loss": 1.4741,
"step": 826
},
{
"epoch": 1.571157495256167,
"grad_norm": 1.516344428062439,
"learning_rate": 1.2058796797365423e-05,
"loss": 1.462,
"step": 828
},
{
"epoch": 1.5749525616698292,
"grad_norm": 1.4637693166732788,
"learning_rate": 1.1855139410219657e-05,
"loss": 1.5037,
"step": 830
},
{
"epoch": 1.5787476280834913,
"grad_norm": 1.4229457378387451,
"learning_rate": 1.1652984909589515e-05,
"loss": 1.5457,
"step": 832
},
{
"epoch": 1.5825426944971537,
"grad_norm": 1.6824008226394653,
"learning_rate": 1.145234126025102e-05,
"loss": 1.5331,
"step": 834
},
{
"epoch": 1.586337760910816,
"grad_norm": 1.434598684310913,
"learning_rate": 1.1253216367453578e-05,
"loss": 1.4848,
"step": 836
},
{
"epoch": 1.5901328273244781,
"grad_norm": 1.6189714670181274,
"learning_rate": 1.1055618076608381e-05,
"loss": 1.503,
"step": 838
},
{
"epoch": 1.5939278937381403,
"grad_norm": 1.4924663305282593,
"learning_rate": 1.085955417297932e-05,
"loss": 1.4748,
"step": 840
},
{
"epoch": 1.5977229601518026,
"grad_norm": 1.4772502183914185,
"learning_rate": 1.0665032381376338e-05,
"loss": 1.5366,
"step": 842
},
{
"epoch": 1.601518026565465,
"grad_norm": 1.4795905351638794,
"learning_rate": 1.047206036585095e-05,
"loss": 1.5062,
"step": 844
},
{
"epoch": 1.6053130929791273,
"grad_norm": 1.6468253135681152,
"learning_rate": 1.0280645729394366e-05,
"loss": 1.6309,
"step": 846
},
{
"epoch": 1.6091081593927894,
"grad_norm": 1.566709041595459,
"learning_rate": 1.0090796013637965e-05,
"loss": 1.5908,
"step": 848
},
{
"epoch": 1.6129032258064515,
"grad_norm": 1.6682099103927612,
"learning_rate": 9.902518698556018e-06,
"loss": 1.4561,
"step": 850
},
{
"epoch": 1.6166982922201139,
"grad_norm": 1.5293233394622803,
"learning_rate": 9.715821202171178e-06,
"loss": 1.5808,
"step": 852
},
{
"epoch": 1.6204933586337762,
"grad_norm": 1.4455894231796265,
"learning_rate": 9.530710880262023e-06,
"loss": 1.5096,
"step": 854
},
{
"epoch": 1.6242884250474383,
"grad_norm": 1.606282114982605,
"learning_rate": 9.347195026073369e-06,
"loss": 1.5413,
"step": 856
},
{
"epoch": 1.6280834914611004,
"grad_norm": 1.6514360904693604,
"learning_rate": 9.16528087002892e-06,
"loss": 1.6339,
"step": 858
},
{
"epoch": 1.6318785578747628,
"grad_norm": 1.9778133630752563,
"learning_rate": 8.98497557944627e-06,
"loss": 1.5451,
"step": 860
},
{
"epoch": 1.635673624288425,
"grad_norm": 1.3893444538116455,
"learning_rate": 8.806286258254664e-06,
"loss": 1.4685,
"step": 862
},
{
"epoch": 1.6394686907020875,
"grad_norm": 1.5551269054412842,
"learning_rate": 8.62921994671501e-06,
"loss": 1.6741,
"step": 864
},
{
"epoch": 1.6432637571157496,
"grad_norm": 1.4979771375656128,
"learning_rate": 8.453783621142542e-06,
"loss": 1.5208,
"step": 866
},
{
"epoch": 1.6470588235294117,
"grad_norm": 1.560624599456787,
"learning_rate": 8.279984193631967e-06,
"loss": 1.4834,
"step": 868
},
{
"epoch": 1.650853889943074,
"grad_norm": 1.5765143632888794,
"learning_rate": 8.10782851178506e-06,
"loss": 1.4358,
"step": 870
},
{
"epoch": 1.6546489563567364,
"grad_norm": 1.570974588394165,
"learning_rate": 7.937323358440935e-06,
"loss": 1.5457,
"step": 872
},
{
"epoch": 1.6584440227703985,
"grad_norm": 1.4516745805740356,
"learning_rate": 7.768475451408847e-06,
"loss": 1.5419,
"step": 874
},
{
"epoch": 1.6622390891840606,
"grad_norm": 1.5503582954406738,
"learning_rate": 7.601291443203373e-06,
"loss": 1.6413,
"step": 876
},
{
"epoch": 1.666034155597723,
"grad_norm": 1.769580364227295,
"learning_rate": 7.435777920782444e-06,
"loss": 1.5522,
"step": 878
},
{
"epoch": 1.6698292220113853,
"grad_norm": 1.4371607303619385,
"learning_rate": 7.271941405287763e-06,
"loss": 1.4663,
"step": 880
},
{
"epoch": 1.6736242884250474,
"grad_norm": 1.6342347860336304,
"learning_rate": 7.109788351787866e-06,
"loss": 1.5864,
"step": 882
},
{
"epoch": 1.6774193548387095,
"grad_norm": 1.5228339433670044,
"learning_rate": 6.949325149023861e-06,
"loss": 1.5431,
"step": 884
},
{
"epoch": 1.6812144212523719,
"grad_norm": 1.4834040403366089,
"learning_rate": 6.790558119157597e-06,
"loss": 1.4691,
"step": 886
},
{
"epoch": 1.6850094876660342,
"grad_norm": 1.4892264604568481,
"learning_rate": 6.633493517522687e-06,
"loss": 1.5266,
"step": 888
},
{
"epoch": 1.6888045540796965,
"grad_norm": 1.5449553728103638,
"learning_rate": 6.478137532378004e-06,
"loss": 1.5186,
"step": 890
},
{
"epoch": 1.6925996204933587,
"grad_norm": 1.4786734580993652,
"learning_rate": 6.324496284663867e-06,
"loss": 1.4716,
"step": 892
},
{
"epoch": 1.6963946869070208,
"grad_norm": 1.6731735467910767,
"learning_rate": 6.172575827760885e-06,
"loss": 1.5878,
"step": 894
},
{
"epoch": 1.7001897533206831,
"grad_norm": 1.4587421417236328,
"learning_rate": 6.022382147251454e-06,
"loss": 1.5136,
"step": 896
},
{
"epoch": 1.7039848197343455,
"grad_norm": 1.4212841987609863,
"learning_rate": 5.873921160683943e-06,
"loss": 1.494,
"step": 898
},
{
"epoch": 1.7077798861480076,
"grad_norm": 1.4232693910598755,
"learning_rate": 5.727198717339511e-06,
"loss": 1.5732,
"step": 900
},
{
"epoch": 1.7115749525616697,
"grad_norm": 1.4280986785888672,
"learning_rate": 5.582220598001681e-06,
"loss": 1.5863,
"step": 902
},
{
"epoch": 1.715370018975332,
"grad_norm": 1.4347306489944458,
"learning_rate": 5.438992514728586e-06,
"loss": 1.435,
"step": 904
},
{
"epoch": 1.7191650853889944,
"grad_norm": 1.4565820693969727,
"learning_rate": 5.297520110627868e-06,
"loss": 1.5819,
"step": 906
},
{
"epoch": 1.7229601518026565,
"grad_norm": 1.484905481338501,
"learning_rate": 5.157808959634408e-06,
"loss": 1.5417,
"step": 908
},
{
"epoch": 1.7267552182163188,
"grad_norm": 1.4751816987991333,
"learning_rate": 5.0198645662906666e-06,
"loss": 1.5835,
"step": 910
},
{
"epoch": 1.730550284629981,
"grad_norm": 1.504117727279663,
"learning_rate": 4.88369236552983e-06,
"loss": 1.5308,
"step": 912
},
{
"epoch": 1.7343453510436433,
"grad_norm": 1.5115126371383667,
"learning_rate": 4.74929772246166e-06,
"loss": 1.5805,
"step": 914
},
{
"epoch": 1.7381404174573056,
"grad_norm": 1.592067003250122,
"learning_rate": 4.616685932161152e-06,
"loss": 1.5943,
"step": 916
},
{
"epoch": 1.7419354838709677,
"grad_norm": 1.547566294670105,
"learning_rate": 4.4858622194598525e-06,
"loss": 1.5524,
"step": 918
},
{
"epoch": 1.7457305502846299,
"grad_norm": 1.4421520233154297,
"learning_rate": 4.356831738740053e-06,
"loss": 1.5868,
"step": 920
},
{
"epoch": 1.7495256166982922,
"grad_norm": 1.560211181640625,
"learning_rate": 4.229599573731685e-06,
"loss": 1.5284,
"step": 922
},
{
"epoch": 1.7533206831119545,
"grad_norm": 1.4842747449874878,
"learning_rate": 4.1041707373120356e-06,
"loss": 1.5208,
"step": 924
},
{
"epoch": 1.7571157495256167,
"grad_norm": 1.4407271146774292,
"learning_rate": 3.980550171308228e-06,
"loss": 1.5146,
"step": 926
},
{
"epoch": 1.7609108159392788,
"grad_norm": 1.5768252611160278,
"learning_rate": 3.858742746302535e-06,
"loss": 1.5219,
"step": 928
},
{
"epoch": 1.7647058823529411,
"grad_norm": 1.6967978477478027,
"learning_rate": 3.738753261440475e-06,
"loss": 1.471,
"step": 930
},
{
"epoch": 1.7685009487666035,
"grad_norm": 1.503156304359436,
"learning_rate": 3.6205864442417136e-06,
"loss": 1.6037,
"step": 932
},
{
"epoch": 1.7722960151802658,
"grad_norm": 1.4313212633132935,
"learning_rate": 3.5042469504138363e-06,
"loss": 1.5396,
"step": 934
},
{
"epoch": 1.776091081593928,
"grad_norm": 1.4455773830413818,
"learning_rate": 3.3897393636688368e-06,
"loss": 1.5083,
"step": 936
},
{
"epoch": 1.77988614800759,
"grad_norm": 1.6534830331802368,
"learning_rate": 3.277068195542654e-06,
"loss": 1.4552,
"step": 938
},
{
"epoch": 1.7836812144212524,
"grad_norm": 1.4945355653762817,
"learning_rate": 3.166237885217299e-06,
"loss": 1.6772,
"step": 940
},
{
"epoch": 1.7874762808349147,
"grad_norm": 1.512107253074646,
"learning_rate": 3.0572527993460053e-06,
"loss": 1.5057,
"step": 942
},
{
"epoch": 1.7912713472485768,
"grad_norm": 1.4883605241775513,
"learning_rate": 2.950117231881183e-06,
"loss": 1.5195,
"step": 944
},
{
"epoch": 1.795066413662239,
"grad_norm": 1.4990360736846924,
"learning_rate": 2.8448354039052216e-06,
"loss": 1.5049,
"step": 946
},
{
"epoch": 1.7988614800759013,
"grad_norm": 1.4626891613006592,
"learning_rate": 2.741411463464211e-06,
"loss": 1.6407,
"step": 948
},
{
"epoch": 1.8026565464895636,
"grad_norm": 1.434928297996521,
"learning_rate": 2.639849485404505e-06,
"loss": 1.4156,
"step": 950
},
{
"epoch": 1.8064516129032258,
"grad_norm": 1.5895707607269287,
"learning_rate": 2.5401534712121146e-06,
"loss": 1.5873,
"step": 952
},
{
"epoch": 1.810246679316888,
"grad_norm": 1.4964556694030762,
"learning_rate": 2.442327348855161e-06,
"loss": 1.4892,
"step": 954
},
{
"epoch": 1.8140417457305502,
"grad_norm": 1.538394808769226,
"learning_rate": 2.3463749726290286e-06,
"loss": 1.5295,
"step": 956
},
{
"epoch": 1.8178368121442126,
"grad_norm": 1.4826878309249878,
"learning_rate": 2.252300123004525e-06,
"loss": 1.5988,
"step": 958
},
{
"epoch": 1.821631878557875,
"grad_norm": 1.3526655435562134,
"learning_rate": 2.1601065064789704e-06,
"loss": 1.4718,
"step": 960
},
{
"epoch": 1.825426944971537,
"grad_norm": 1.4862638711929321,
"learning_rate": 2.069797755430097e-06,
"loss": 1.4211,
"step": 962
},
{
"epoch": 1.8292220113851991,
"grad_norm": 1.4792903661727905,
"learning_rate": 1.981377427973019e-06,
"loss": 1.6021,
"step": 964
},
{
"epoch": 1.8330170777988615,
"grad_norm": 1.549116849899292,
"learning_rate": 1.8948490078199764e-06,
"loss": 1.5993,
"step": 966
},
{
"epoch": 1.8368121442125238,
"grad_norm": 1.5120720863342285,
"learning_rate": 1.8102159041430922e-06,
"loss": 1.5298,
"step": 968
},
{
"epoch": 1.840607210626186,
"grad_norm": 1.4404058456420898,
"learning_rate": 1.7274814514400994e-06,
"loss": 1.4814,
"step": 970
},
{
"epoch": 1.844402277039848,
"grad_norm": 4.492391109466553,
"learning_rate": 1.6466489094028759e-06,
"loss": 1.4715,
"step": 972
},
{
"epoch": 1.8481973434535104,
"grad_norm": 1.4525541067123413,
"learning_rate": 1.5677214627891179e-06,
"loss": 1.6309,
"step": 974
},
{
"epoch": 1.8519924098671727,
"grad_norm": 1.5709426403045654,
"learning_rate": 1.4907022212967803e-06,
"loss": 1.5461,
"step": 976
},
{
"epoch": 1.855787476280835,
"grad_norm": 1.3271862268447876,
"learning_rate": 1.415594219441585e-06,
"loss": 1.4054,
"step": 978
},
{
"epoch": 1.8595825426944972,
"grad_norm": 1.3917781114578247,
"learning_rate": 1.3424004164374837e-06,
"loss": 1.5336,
"step": 980
},
{
"epoch": 1.8633776091081593,
"grad_norm": 1.4328250885009766,
"learning_rate": 1.2711236960800287e-06,
"loss": 1.4511,
"step": 982
},
{
"epoch": 1.8671726755218216,
"grad_norm": 1.346508264541626,
"learning_rate": 1.2017668666327753e-06,
"loss": 1.3968,
"step": 984
},
{
"epoch": 1.870967741935484,
"grad_norm": 1.3557928800582886,
"learning_rate": 1.1343326607166527e-06,
"loss": 1.4705,
"step": 986
},
{
"epoch": 1.874762808349146,
"grad_norm": 1.366053581237793,
"learning_rate": 1.0688237352022345e-06,
"loss": 1.5675,
"step": 988
},
{
"epoch": 1.8785578747628082,
"grad_norm": 1.517269492149353,
"learning_rate": 1.0052426711051666e-06,
"loss": 1.4535,
"step": 990
},
{
"epoch": 1.8823529411764706,
"grad_norm": 1.4387192726135254,
"learning_rate": 9.435919734843645e-07,
"loss": 1.4155,
"step": 992
},
{
"epoch": 1.886148007590133,
"grad_norm": 1.5173383951187134,
"learning_rate": 8.83874071343388e-07,
"loss": 1.5837,
"step": 994
},
{
"epoch": 1.889943074003795,
"grad_norm": 1.3659306764602661,
"learning_rate": 8.260913175347273e-07,
"loss": 1.3851,
"step": 996
},
{
"epoch": 1.8937381404174574,
"grad_norm": 1.517941951751709,
"learning_rate": 7.702459886670788e-07,
"loss": 1.6209,
"step": 998
},
{
"epoch": 1.8975332068311195,
"grad_norm": 2.020474433898926,
"learning_rate": 7.163402850156653e-07,
"loss": 1.6127,
"step": 1000
},
{
"epoch": 1.9013282732447818,
"grad_norm": 1.4695974588394165,
"learning_rate": 6.643763304355566e-07,
"loss": 1.5347,
"step": 1002
},
{
"epoch": 1.9051233396584442,
"grad_norm": 1.620187759399414,
"learning_rate": 6.143561722779523e-07,
"loss": 1.6034,
"step": 1004
},
{
"epoch": 1.9089184060721063,
"grad_norm": 1.5927858352661133,
"learning_rate": 5.662817813095633e-07,
"loss": 1.5788,
"step": 1006
},
{
"epoch": 1.9127134724857684,
"grad_norm": 1.514259696006775,
"learning_rate": 5.201550516349407e-07,
"loss": 1.62,
"step": 1008
},
{
"epoch": 1.9165085388994307,
"grad_norm": 1.3866559267044067,
"learning_rate": 4.7597780062184073e-07,
"loss": 1.4648,
"step": 1010
},
{
"epoch": 1.920303605313093,
"grad_norm": 1.5908156633377075,
"learning_rate": 4.337517688296544e-07,
"loss": 1.468,
"step": 1012
},
{
"epoch": 1.9240986717267552,
"grad_norm": 1.4775136709213257,
"learning_rate": 3.9347861994078474e-07,
"loss": 1.6525,
"step": 1014
},
{
"epoch": 1.9278937381404173,
"grad_norm": 1.5161350965499878,
"learning_rate": 3.551599406951434e-07,
"loss": 1.6618,
"step": 1016
},
{
"epoch": 1.9316888045540797,
"grad_norm": 2.3954577445983887,
"learning_rate": 3.1879724082760076e-07,
"loss": 1.5788,
"step": 1018
},
{
"epoch": 1.935483870967742,
"grad_norm": 1.61758553981781,
"learning_rate": 2.843919530085226e-07,
"loss": 1.5621,
"step": 1020
},
{
"epoch": 1.9392789373814043,
"grad_norm": 1.393769383430481,
"learning_rate": 2.51945432787315e-07,
"loss": 1.5219,
"step": 1022
},
{
"epoch": 1.9430740037950665,
"grad_norm": 1.3476831912994385,
"learning_rate": 2.21458958539017e-07,
"loss": 1.5093,
"step": 1024
},
{
"epoch": 1.9468690702087286,
"grad_norm": 1.4226655960083008,
"learning_rate": 1.9293373141394122e-07,
"loss": 1.6511,
"step": 1026
},
{
"epoch": 1.950664136622391,
"grad_norm": 1.370326042175293,
"learning_rate": 1.6637087529033923e-07,
"loss": 1.5798,
"step": 1028
},
{
"epoch": 1.9544592030360532,
"grad_norm": 1.4292343854904175,
"learning_rate": 1.4177143673011484e-07,
"loss": 1.5818,
"step": 1030
},
{
"epoch": 1.9582542694497154,
"grad_norm": 1.4409210681915283,
"learning_rate": 1.191363849376237e-07,
"loss": 1.5591,
"step": 1032
},
{
"epoch": 1.9620493358633775,
"grad_norm": 1.4100062847137451,
"learning_rate": 9.846661172143723e-08,
"loss": 1.5029,
"step": 1034
},
{
"epoch": 1.9658444022770398,
"grad_norm": 1.4706885814666748,
"learning_rate": 7.976293145924852e-08,
"loss": 1.6701,
"step": 1036
},
{
"epoch": 1.9696394686907022,
"grad_norm": 1.4179500341415405,
"learning_rate": 6.302608106577568e-08,
"loss": 1.4963,
"step": 1038
},
{
"epoch": 1.9734345351043643,
"grad_norm": 1.5213074684143066,
"learning_rate": 4.825671996370185e-08,
"loss": 1.4917,
"step": 1040
},
{
"epoch": 1.9772296015180264,
"grad_norm": 1.614125370979309,
"learning_rate": 3.545543005773477e-08,
"loss": 1.62,
"step": 1042
},
{
"epoch": 1.9810246679316887,
"grad_norm": 1.7991819381713867,
"learning_rate": 2.4622715711647426e-08,
"loss": 1.4634,
"step": 1044
},
{
"epoch": 1.984819734345351,
"grad_norm": 2.2819013595581055,
"learning_rate": 1.5759003728427202e-08,
"loss": 1.6325,
"step": 1046
},
{
"epoch": 1.9886148007590134,
"grad_norm": 1.4762083292007446,
"learning_rate": 8.864643333450495e-09,
"loss": 1.5359,
"step": 1048
},
{
"epoch": 1.9924098671726755,
"grad_norm": 1.4591556787490845,
"learning_rate": 3.9399061607103825e-09,
"loss": 1.5177,
"step": 1050
},
{
"epoch": 1.9962049335863377,
"grad_norm": 1.47614324092865,
"learning_rate": 9.84986242158481e-10,
"loss": 1.6416,
"step": 1052
},
{
"epoch": 2.0,
"grad_norm": 2.0421242713928223,
"learning_rate": 0.0,
"loss": 1.5039,
"step": 1054
}
],
"logging_steps": 2,
"max_steps": 1054,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 527,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.7824370872496947e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}