medical-5day / checkpoint-930 /trainer_state.json
howard
new version
0679c2b
raw
history blame
No virus
163 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 233,
"global_step": 930,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001075268817204301,
"grad_norm": 0.47046032547950745,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.2903,
"step": 1
},
{
"epoch": 0.001075268817204301,
"eval_loss": 1.1097546815872192,
"eval_runtime": 239.745,
"eval_samples_per_second": 11.612,
"eval_steps_per_second": 0.484,
"step": 1
},
{
"epoch": 0.002150537634408602,
"grad_norm": 0.4801943898200989,
"learning_rate": 4.000000000000001e-06,
"loss": 1.3048,
"step": 2
},
{
"epoch": 0.0032258064516129032,
"grad_norm": 0.4532926380634308,
"learning_rate": 6e-06,
"loss": 1.3283,
"step": 3
},
{
"epoch": 0.004301075268817204,
"grad_norm": 0.4831653833389282,
"learning_rate": 8.000000000000001e-06,
"loss": 1.2813,
"step": 4
},
{
"epoch": 0.005376344086021506,
"grad_norm": 0.4505281150341034,
"learning_rate": 1e-05,
"loss": 1.3272,
"step": 5
},
{
"epoch": 0.0064516129032258064,
"grad_norm": 0.4494975507259369,
"learning_rate": 1.2e-05,
"loss": 1.3336,
"step": 6
},
{
"epoch": 0.007526881720430108,
"grad_norm": 0.48131081461906433,
"learning_rate": 1.4e-05,
"loss": 1.3175,
"step": 7
},
{
"epoch": 0.008602150537634409,
"grad_norm": 0.46796271204948425,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.3211,
"step": 8
},
{
"epoch": 0.00967741935483871,
"grad_norm": 0.42700183391571045,
"learning_rate": 1.8e-05,
"loss": 1.29,
"step": 9
},
{
"epoch": 0.010752688172043012,
"grad_norm": 0.4512764811515808,
"learning_rate": 2e-05,
"loss": 1.289,
"step": 10
},
{
"epoch": 0.011827956989247311,
"grad_norm": 0.38503292202949524,
"learning_rate": 1.999994169662801e-05,
"loss": 1.2838,
"step": 11
},
{
"epoch": 0.012903225806451613,
"grad_norm": 0.36103355884552,
"learning_rate": 1.9999766787191897e-05,
"loss": 1.2636,
"step": 12
},
{
"epoch": 0.013978494623655914,
"grad_norm": 0.3443821668624878,
"learning_rate": 1.9999475273731218e-05,
"loss": 1.2708,
"step": 13
},
{
"epoch": 0.015053763440860216,
"grad_norm": 0.33744773268699646,
"learning_rate": 1.9999067159645222e-05,
"loss": 1.2806,
"step": 14
},
{
"epoch": 0.016129032258064516,
"grad_norm": 0.3615255355834961,
"learning_rate": 1.9998542449692794e-05,
"loss": 1.1926,
"step": 15
},
{
"epoch": 0.017204301075268817,
"grad_norm": 0.3394218981266022,
"learning_rate": 1.99979011499924e-05,
"loss": 1.2624,
"step": 16
},
{
"epoch": 0.01827956989247312,
"grad_norm": 0.35456153750419617,
"learning_rate": 1.999714326802203e-05,
"loss": 1.2372,
"step": 17
},
{
"epoch": 0.01935483870967742,
"grad_norm": 0.3715231418609619,
"learning_rate": 1.999626881261911e-05,
"loss": 1.2655,
"step": 18
},
{
"epoch": 0.02043010752688172,
"grad_norm": 0.375711590051651,
"learning_rate": 1.9995277793980362e-05,
"loss": 1.2065,
"step": 19
},
{
"epoch": 0.021505376344086023,
"grad_norm": 0.3626311421394348,
"learning_rate": 1.999417022366174e-05,
"loss": 1.2691,
"step": 20
},
{
"epoch": 0.02258064516129032,
"grad_norm": 0.3745582699775696,
"learning_rate": 1.9992946114578264e-05,
"loss": 1.2962,
"step": 21
},
{
"epoch": 0.023655913978494623,
"grad_norm": 0.3464348018169403,
"learning_rate": 1.9991605481003865e-05,
"loss": 1.2189,
"step": 22
},
{
"epoch": 0.024731182795698924,
"grad_norm": 0.3342266082763672,
"learning_rate": 1.999014833857124e-05,
"loss": 1.2144,
"step": 23
},
{
"epoch": 0.025806451612903226,
"grad_norm": 0.3211102783679962,
"learning_rate": 1.9988574704271652e-05,
"loss": 1.2098,
"step": 24
},
{
"epoch": 0.026881720430107527,
"grad_norm": 0.3194901943206787,
"learning_rate": 1.998688459645473e-05,
"loss": 1.2266,
"step": 25
},
{
"epoch": 0.02795698924731183,
"grad_norm": 0.32383179664611816,
"learning_rate": 1.998507803482828e-05,
"loss": 1.2227,
"step": 26
},
{
"epoch": 0.02903225806451613,
"grad_norm": 0.3091806173324585,
"learning_rate": 1.998315504045803e-05,
"loss": 1.2372,
"step": 27
},
{
"epoch": 0.030107526881720432,
"grad_norm": 0.306734561920166,
"learning_rate": 1.998111563576738e-05,
"loss": 1.1947,
"step": 28
},
{
"epoch": 0.03118279569892473,
"grad_norm": 0.3311488628387451,
"learning_rate": 1.9978959844537176e-05,
"loss": 1.1853,
"step": 29
},
{
"epoch": 0.03225806451612903,
"grad_norm": 0.34573501348495483,
"learning_rate": 1.9976687691905394e-05,
"loss": 1.1903,
"step": 30
},
{
"epoch": 0.03333333333333333,
"grad_norm": 0.3311573266983032,
"learning_rate": 1.997429920436686e-05,
"loss": 1.1754,
"step": 31
},
{
"epoch": 0.034408602150537634,
"grad_norm": 0.3365638852119446,
"learning_rate": 1.9971794409772962e-05,
"loss": 1.1259,
"step": 32
},
{
"epoch": 0.035483870967741936,
"grad_norm": 0.3338710069656372,
"learning_rate": 1.9969173337331283e-05,
"loss": 1.161,
"step": 33
},
{
"epoch": 0.03655913978494624,
"grad_norm": 0.321247398853302,
"learning_rate": 1.9966436017605296e-05,
"loss": 1.0962,
"step": 34
},
{
"epoch": 0.03763440860215054,
"grad_norm": 0.32759588956832886,
"learning_rate": 1.9963582482514003e-05,
"loss": 1.1921,
"step": 35
},
{
"epoch": 0.03870967741935484,
"grad_norm": 0.2961257994174957,
"learning_rate": 1.996061276533154e-05,
"loss": 1.1777,
"step": 36
},
{
"epoch": 0.03978494623655914,
"grad_norm": 0.3336629271507263,
"learning_rate": 1.9957526900686814e-05,
"loss": 1.1454,
"step": 37
},
{
"epoch": 0.04086021505376344,
"grad_norm": 0.3197214901447296,
"learning_rate": 1.9954324924563088e-05,
"loss": 1.136,
"step": 38
},
{
"epoch": 0.041935483870967745,
"grad_norm": 0.3015052080154419,
"learning_rate": 1.9951006874297568e-05,
"loss": 1.1581,
"step": 39
},
{
"epoch": 0.043010752688172046,
"grad_norm": 0.32588157057762146,
"learning_rate": 1.994757278858095e-05,
"loss": 1.1603,
"step": 40
},
{
"epoch": 0.04408602150537634,
"grad_norm": 0.3433900475502014,
"learning_rate": 1.9944022707456992e-05,
"loss": 1.1162,
"step": 41
},
{
"epoch": 0.04516129032258064,
"grad_norm": 0.31243011355400085,
"learning_rate": 1.9940356672322037e-05,
"loss": 1.1585,
"step": 42
},
{
"epoch": 0.046236559139784944,
"grad_norm": 0.35727739334106445,
"learning_rate": 1.9936574725924526e-05,
"loss": 1.1663,
"step": 43
},
{
"epoch": 0.047311827956989246,
"grad_norm": 0.3205494284629822,
"learning_rate": 1.99326769123645e-05,
"loss": 1.1508,
"step": 44
},
{
"epoch": 0.04838709677419355,
"grad_norm": 0.31664592027664185,
"learning_rate": 1.99286632770931e-05,
"loss": 1.1644,
"step": 45
},
{
"epoch": 0.04946236559139785,
"grad_norm": 0.3515632748603821,
"learning_rate": 1.9924533866912017e-05,
"loss": 1.1326,
"step": 46
},
{
"epoch": 0.05053763440860215,
"grad_norm": 0.3686864674091339,
"learning_rate": 1.992028872997296e-05,
"loss": 1.0378,
"step": 47
},
{
"epoch": 0.05161290322580645,
"grad_norm": 0.3334296941757202,
"learning_rate": 1.9915927915777085e-05,
"loss": 1.154,
"step": 48
},
{
"epoch": 0.05268817204301075,
"grad_norm": 0.33582431077957153,
"learning_rate": 1.9911451475174428e-05,
"loss": 1.1164,
"step": 49
},
{
"epoch": 0.053763440860215055,
"grad_norm": 0.3328990936279297,
"learning_rate": 1.9906859460363307e-05,
"loss": 1.1293,
"step": 50
},
{
"epoch": 0.054838709677419356,
"grad_norm": 0.3484123945236206,
"learning_rate": 1.9902151924889715e-05,
"loss": 1.1883,
"step": 51
},
{
"epoch": 0.05591397849462366,
"grad_norm": 0.3534570038318634,
"learning_rate": 1.989732892364668e-05,
"loss": 1.1912,
"step": 52
},
{
"epoch": 0.05698924731182796,
"grad_norm": 0.3628205955028534,
"learning_rate": 1.989239051287366e-05,
"loss": 1.0801,
"step": 53
},
{
"epoch": 0.05806451612903226,
"grad_norm": 0.35341545939445496,
"learning_rate": 1.988733675015585e-05,
"loss": 1.1372,
"step": 54
},
{
"epoch": 0.05913978494623656,
"grad_norm": 0.37951940298080444,
"learning_rate": 1.988216769442353e-05,
"loss": 1.0838,
"step": 55
},
{
"epoch": 0.060215053763440864,
"grad_norm": 0.37033918499946594,
"learning_rate": 1.9876883405951378e-05,
"loss": 1.1248,
"step": 56
},
{
"epoch": 0.06129032258064516,
"grad_norm": 0.360681414604187,
"learning_rate": 1.987148394635776e-05,
"loss": 1.1153,
"step": 57
},
{
"epoch": 0.06236559139784946,
"grad_norm": 0.4272811710834503,
"learning_rate": 1.9865969378604023e-05,
"loss": 1.0496,
"step": 58
},
{
"epoch": 0.06344086021505377,
"grad_norm": 0.40148288011550903,
"learning_rate": 1.9860339766993735e-05,
"loss": 1.1039,
"step": 59
},
{
"epoch": 0.06451612903225806,
"grad_norm": 0.3811061680316925,
"learning_rate": 1.9854595177171968e-05,
"loss": 1.0615,
"step": 60
},
{
"epoch": 0.06559139784946237,
"grad_norm": 0.4223267734050751,
"learning_rate": 1.984873567612452e-05,
"loss": 1.1248,
"step": 61
},
{
"epoch": 0.06666666666666667,
"grad_norm": 0.3878687918186188,
"learning_rate": 1.9842761332177115e-05,
"loss": 1.0849,
"step": 62
},
{
"epoch": 0.06774193548387097,
"grad_norm": 0.3889671862125397,
"learning_rate": 1.983667221499464e-05,
"loss": 1.107,
"step": 63
},
{
"epoch": 0.06881720430107527,
"grad_norm": 0.3888603746891022,
"learning_rate": 1.9830468395580306e-05,
"loss": 1.0947,
"step": 64
},
{
"epoch": 0.06989247311827956,
"grad_norm": 0.3902936577796936,
"learning_rate": 1.9824149946274827e-05,
"loss": 1.0747,
"step": 65
},
{
"epoch": 0.07096774193548387,
"grad_norm": 0.4241058826446533,
"learning_rate": 1.9817716940755586e-05,
"loss": 1.0701,
"step": 66
},
{
"epoch": 0.07204301075268817,
"grad_norm": 0.41224780678749084,
"learning_rate": 1.981116945403577e-05,
"loss": 1.0375,
"step": 67
},
{
"epoch": 0.07311827956989247,
"grad_norm": 0.4317214787006378,
"learning_rate": 1.9804507562463483e-05,
"loss": 1.0293,
"step": 68
},
{
"epoch": 0.07419354838709677,
"grad_norm": 0.4070356786251068,
"learning_rate": 1.9797731343720878e-05,
"loss": 1.0768,
"step": 69
},
{
"epoch": 0.07526881720430108,
"grad_norm": 0.42713648080825806,
"learning_rate": 1.979084087682323e-05,
"loss": 1.1332,
"step": 70
},
{
"epoch": 0.07634408602150537,
"grad_norm": 0.45279622077941895,
"learning_rate": 1.9783836242118036e-05,
"loss": 1.0571,
"step": 71
},
{
"epoch": 0.07741935483870968,
"grad_norm": 0.43857499957084656,
"learning_rate": 1.977671752128406e-05,
"loss": 1.096,
"step": 72
},
{
"epoch": 0.07849462365591398,
"grad_norm": 0.4599035978317261,
"learning_rate": 1.9769484797330383e-05,
"loss": 1.0352,
"step": 73
},
{
"epoch": 0.07956989247311828,
"grad_norm": 0.4975890815258026,
"learning_rate": 1.9762138154595448e-05,
"loss": 0.9886,
"step": 74
},
{
"epoch": 0.08064516129032258,
"grad_norm": 0.39150896668434143,
"learning_rate": 1.9754677678746064e-05,
"loss": 1.0713,
"step": 75
},
{
"epoch": 0.08172043010752689,
"grad_norm": 0.4559513032436371,
"learning_rate": 1.9747103456776406e-05,
"loss": 1.049,
"step": 76
},
{
"epoch": 0.08279569892473118,
"grad_norm": 0.45070788264274597,
"learning_rate": 1.9739415577007016e-05,
"loss": 1.038,
"step": 77
},
{
"epoch": 0.08387096774193549,
"grad_norm": 0.4617964029312134,
"learning_rate": 1.9731614129083756e-05,
"loss": 1.0626,
"step": 78
},
{
"epoch": 0.08494623655913978,
"grad_norm": 0.47204914689064026,
"learning_rate": 1.9723699203976768e-05,
"loss": 1.0785,
"step": 79
},
{
"epoch": 0.08602150537634409,
"grad_norm": 0.5538530945777893,
"learning_rate": 1.9715670893979416e-05,
"loss": 1.0384,
"step": 80
},
{
"epoch": 0.08709677419354839,
"grad_norm": 0.500848114490509,
"learning_rate": 1.970752929270721e-05,
"loss": 1.0732,
"step": 81
},
{
"epoch": 0.08817204301075268,
"grad_norm": 0.5184169411659241,
"learning_rate": 1.9699274495096712e-05,
"loss": 1.064,
"step": 82
},
{
"epoch": 0.08924731182795699,
"grad_norm": 0.5162873864173889,
"learning_rate": 1.969090659740443e-05,
"loss": 0.9992,
"step": 83
},
{
"epoch": 0.09032258064516129,
"grad_norm": 0.4499477744102478,
"learning_rate": 1.9682425697205695e-05,
"loss": 1.0495,
"step": 84
},
{
"epoch": 0.0913978494623656,
"grad_norm": 0.48833805322647095,
"learning_rate": 1.967383189339352e-05,
"loss": 1.064,
"step": 85
},
{
"epoch": 0.09247311827956989,
"grad_norm": 0.4258129596710205,
"learning_rate": 1.9665125286177448e-05,
"loss": 1.0463,
"step": 86
},
{
"epoch": 0.0935483870967742,
"grad_norm": 0.47551074624061584,
"learning_rate": 1.9656305977082405e-05,
"loss": 1.0386,
"step": 87
},
{
"epoch": 0.09462365591397849,
"grad_norm": 0.49520763754844666,
"learning_rate": 1.964737406894747e-05,
"loss": 1.0107,
"step": 88
},
{
"epoch": 0.0956989247311828,
"grad_norm": 0.47921285033226013,
"learning_rate": 1.963832966592472e-05,
"loss": 1.0101,
"step": 89
},
{
"epoch": 0.0967741935483871,
"grad_norm": 0.49400344491004944,
"learning_rate": 1.9629172873477995e-05,
"loss": 1.0635,
"step": 90
},
{
"epoch": 0.0978494623655914,
"grad_norm": 0.4567995071411133,
"learning_rate": 1.961990379838167e-05,
"loss": 1.0244,
"step": 91
},
{
"epoch": 0.0989247311827957,
"grad_norm": 0.533193051815033,
"learning_rate": 1.961052254871941e-05,
"loss": 0.9857,
"step": 92
},
{
"epoch": 0.1,
"grad_norm": 0.45922616124153137,
"learning_rate": 1.9601029233882914e-05,
"loss": 1.0685,
"step": 93
},
{
"epoch": 0.1010752688172043,
"grad_norm": 0.501941978931427,
"learning_rate": 1.9591423964570634e-05,
"loss": 1.0426,
"step": 94
},
{
"epoch": 0.10215053763440861,
"grad_norm": 0.5177110433578491,
"learning_rate": 1.9581706852786492e-05,
"loss": 1.0302,
"step": 95
},
{
"epoch": 0.1032258064516129,
"grad_norm": 0.47546830773353577,
"learning_rate": 1.9571878011838557e-05,
"loss": 1.0515,
"step": 96
},
{
"epoch": 0.1043010752688172,
"grad_norm": 0.5165790319442749,
"learning_rate": 1.956193755633775e-05,
"loss": 1.0473,
"step": 97
},
{
"epoch": 0.1053763440860215,
"grad_norm": 0.493230938911438,
"learning_rate": 1.9551885602196482e-05,
"loss": 0.9971,
"step": 98
},
{
"epoch": 0.1064516129032258,
"grad_norm": 0.524946928024292,
"learning_rate": 1.954172226662732e-05,
"loss": 0.988,
"step": 99
},
{
"epoch": 0.10752688172043011,
"grad_norm": 0.49421951174736023,
"learning_rate": 1.953144766814161e-05,
"loss": 1.086,
"step": 100
},
{
"epoch": 0.1086021505376344,
"grad_norm": 0.4998270869255066,
"learning_rate": 1.9521061926548096e-05,
"loss": 1.0394,
"step": 101
},
{
"epoch": 0.10967741935483871,
"grad_norm": 0.5035815834999084,
"learning_rate": 1.9510565162951538e-05,
"loss": 0.9236,
"step": 102
},
{
"epoch": 0.110752688172043,
"grad_norm": 0.5167160034179688,
"learning_rate": 1.949995749975127e-05,
"loss": 1.0328,
"step": 103
},
{
"epoch": 0.11182795698924732,
"grad_norm": 0.48468247056007385,
"learning_rate": 1.94892390606398e-05,
"loss": 1.0292,
"step": 104
},
{
"epoch": 0.11290322580645161,
"grad_norm": 0.5353156328201294,
"learning_rate": 1.947840997060136e-05,
"loss": 1.0258,
"step": 105
},
{
"epoch": 0.11397849462365592,
"grad_norm": 0.4897732138633728,
"learning_rate": 1.9467470355910438e-05,
"loss": 1.0167,
"step": 106
},
{
"epoch": 0.11505376344086021,
"grad_norm": 0.5131762623786926,
"learning_rate": 1.9456420344130324e-05,
"loss": 1.0104,
"step": 107
},
{
"epoch": 0.11612903225806452,
"grad_norm": 0.5203889012336731,
"learning_rate": 1.9445260064111608e-05,
"loss": 1.0029,
"step": 108
},
{
"epoch": 0.11720430107526882,
"grad_norm": 0.5201652646064758,
"learning_rate": 1.9433989645990677e-05,
"loss": 0.9724,
"step": 109
},
{
"epoch": 0.11827956989247312,
"grad_norm": 0.48938658833503723,
"learning_rate": 1.9422609221188208e-05,
"loss": 1.003,
"step": 110
},
{
"epoch": 0.11935483870967742,
"grad_norm": 0.5455314517021179,
"learning_rate": 1.941111892240763e-05,
"loss": 0.9697,
"step": 111
},
{
"epoch": 0.12043010752688173,
"grad_norm": 0.5419149398803711,
"learning_rate": 1.9399518883633575e-05,
"loss": 1.042,
"step": 112
},
{
"epoch": 0.12150537634408602,
"grad_norm": 0.5646453499794006,
"learning_rate": 1.938780924013032e-05,
"loss": 1.0211,
"step": 113
},
{
"epoch": 0.12258064516129032,
"grad_norm": 0.5471717119216919,
"learning_rate": 1.9375990128440205e-05,
"loss": 1.0343,
"step": 114
},
{
"epoch": 0.12365591397849462,
"grad_norm": 0.54964679479599,
"learning_rate": 1.9364061686382042e-05,
"loss": 0.989,
"step": 115
},
{
"epoch": 0.12473118279569892,
"grad_norm": 0.5681911110877991,
"learning_rate": 1.935202405304951e-05,
"loss": 0.9719,
"step": 116
},
{
"epoch": 0.12580645161290321,
"grad_norm": 0.5024511218070984,
"learning_rate": 1.933987736880953e-05,
"loss": 1.04,
"step": 117
},
{
"epoch": 0.12688172043010754,
"grad_norm": 0.5859746932983398,
"learning_rate": 1.932762177530064e-05,
"loss": 0.9692,
"step": 118
},
{
"epoch": 0.12795698924731183,
"grad_norm": 0.5424095392227173,
"learning_rate": 1.931525741543131e-05,
"loss": 1.0015,
"step": 119
},
{
"epoch": 0.12903225806451613,
"grad_norm": 0.5528049468994141,
"learning_rate": 1.9302784433378333e-05,
"loss": 1.0054,
"step": 120
},
{
"epoch": 0.13010752688172042,
"grad_norm": 0.5513008832931519,
"learning_rate": 1.929020297458508e-05,
"loss": 1.0207,
"step": 121
},
{
"epoch": 0.13118279569892474,
"grad_norm": 0.5633342266082764,
"learning_rate": 1.9277513185759847e-05,
"loss": 1.0283,
"step": 122
},
{
"epoch": 0.13225806451612904,
"grad_norm": 0.5417779088020325,
"learning_rate": 1.926471521487413e-05,
"loss": 0.9858,
"step": 123
},
{
"epoch": 0.13333333333333333,
"grad_norm": 0.5973786115646362,
"learning_rate": 1.9251809211160905e-05,
"loss": 1.0141,
"step": 124
},
{
"epoch": 0.13440860215053763,
"grad_norm": 0.5340192914009094,
"learning_rate": 1.9238795325112867e-05,
"loss": 0.983,
"step": 125
},
{
"epoch": 0.13548387096774195,
"grad_norm": 0.5954460501670837,
"learning_rate": 1.922567370848072e-05,
"loss": 0.9743,
"step": 126
},
{
"epoch": 0.13655913978494624,
"grad_norm": 0.5733973383903503,
"learning_rate": 1.921244451427135e-05,
"loss": 1.0521,
"step": 127
},
{
"epoch": 0.13763440860215054,
"grad_norm": 0.5830503702163696,
"learning_rate": 1.9199107896746093e-05,
"loss": 0.9766,
"step": 128
},
{
"epoch": 0.13870967741935483,
"grad_norm": 0.6205757260322571,
"learning_rate": 1.9185664011418895e-05,
"loss": 0.973,
"step": 129
},
{
"epoch": 0.13978494623655913,
"grad_norm": 0.6140737533569336,
"learning_rate": 1.917211301505453e-05,
"loss": 0.9315,
"step": 130
},
{
"epoch": 0.14086021505376345,
"grad_norm": 0.6285789608955383,
"learning_rate": 1.9158455065666758e-05,
"loss": 0.9331,
"step": 131
},
{
"epoch": 0.14193548387096774,
"grad_norm": 0.5214990973472595,
"learning_rate": 1.914469032251647e-05,
"loss": 0.8851,
"step": 132
},
{
"epoch": 0.14301075268817204,
"grad_norm": 0.6822535395622253,
"learning_rate": 1.9130818946109865e-05,
"loss": 1.0275,
"step": 133
},
{
"epoch": 0.14408602150537633,
"grad_norm": 0.5924133062362671,
"learning_rate": 1.9116841098196538e-05,
"loss": 0.9584,
"step": 134
},
{
"epoch": 0.14516129032258066,
"grad_norm": 0.5674971342086792,
"learning_rate": 1.9102756941767625e-05,
"loss": 0.9744,
"step": 135
},
{
"epoch": 0.14623655913978495,
"grad_norm": 0.5704190135002136,
"learning_rate": 1.9088566641053887e-05,
"loss": 1.0019,
"step": 136
},
{
"epoch": 0.14731182795698924,
"grad_norm": 0.5644530653953552,
"learning_rate": 1.9074270361523805e-05,
"loss": 0.9846,
"step": 137
},
{
"epoch": 0.14838709677419354,
"grad_norm": 0.5966128706932068,
"learning_rate": 1.9059868269881637e-05,
"loss": 0.9585,
"step": 138
},
{
"epoch": 0.14946236559139786,
"grad_norm": 0.5670474171638489,
"learning_rate": 1.9045360534065484e-05,
"loss": 0.9591,
"step": 139
},
{
"epoch": 0.15053763440860216,
"grad_norm": 0.5436234474182129,
"learning_rate": 1.903074732324533e-05,
"loss": 1.0095,
"step": 140
},
{
"epoch": 0.15161290322580645,
"grad_norm": 0.6641930341720581,
"learning_rate": 1.9016028807821067e-05,
"loss": 0.962,
"step": 141
},
{
"epoch": 0.15268817204301074,
"grad_norm": 0.687738835811615,
"learning_rate": 1.9001205159420512e-05,
"loss": 0.9705,
"step": 142
},
{
"epoch": 0.15376344086021507,
"grad_norm": 0.5606933832168579,
"learning_rate": 1.8986276550897404e-05,
"loss": 1.0314,
"step": 143
},
{
"epoch": 0.15483870967741936,
"grad_norm": 0.5617864727973938,
"learning_rate": 1.897124315632938e-05,
"loss": 0.9743,
"step": 144
},
{
"epoch": 0.15591397849462366,
"grad_norm": 0.603577733039856,
"learning_rate": 1.8956105151015966e-05,
"loss": 0.9762,
"step": 145
},
{
"epoch": 0.15698924731182795,
"grad_norm": 0.5890366435050964,
"learning_rate": 1.8940862711476515e-05,
"loss": 0.9394,
"step": 146
},
{
"epoch": 0.15806451612903225,
"grad_norm": 0.609809935092926,
"learning_rate": 1.8925516015448144e-05,
"loss": 0.9551,
"step": 147
},
{
"epoch": 0.15913978494623657,
"grad_norm": 0.621967613697052,
"learning_rate": 1.891006524188368e-05,
"loss": 0.9278,
"step": 148
},
{
"epoch": 0.16021505376344086,
"grad_norm": 0.6274746656417847,
"learning_rate": 1.8894510570949566e-05,
"loss": 0.9409,
"step": 149
},
{
"epoch": 0.16129032258064516,
"grad_norm": 0.6348162293434143,
"learning_rate": 1.8878852184023754e-05,
"loss": 1.0121,
"step": 150
},
{
"epoch": 0.16236559139784945,
"grad_norm": 0.6199047565460205,
"learning_rate": 1.8863090263693596e-05,
"loss": 0.9365,
"step": 151
},
{
"epoch": 0.16344086021505377,
"grad_norm": 0.5536498427391052,
"learning_rate": 1.884722499375371e-05,
"loss": 0.8554,
"step": 152
},
{
"epoch": 0.16451612903225807,
"grad_norm": 0.5735920071601868,
"learning_rate": 1.8831256559203847e-05,
"loss": 0.9685,
"step": 153
},
{
"epoch": 0.16559139784946236,
"grad_norm": 0.6529683470726013,
"learning_rate": 1.8815185146246718e-05,
"loss": 0.9688,
"step": 154
},
{
"epoch": 0.16666666666666666,
"grad_norm": 0.6526486873626709,
"learning_rate": 1.879901094228584e-05,
"loss": 0.9869,
"step": 155
},
{
"epoch": 0.16774193548387098,
"grad_norm": 0.6016148328781128,
"learning_rate": 1.878273413592334e-05,
"loss": 0.9608,
"step": 156
},
{
"epoch": 0.16881720430107527,
"grad_norm": 0.582095742225647,
"learning_rate": 1.8766354916957758e-05,
"loss": 1.0218,
"step": 157
},
{
"epoch": 0.16989247311827957,
"grad_norm": 0.5814548134803772,
"learning_rate": 1.8749873476381827e-05,
"loss": 0.9845,
"step": 158
},
{
"epoch": 0.17096774193548386,
"grad_norm": 0.5818253755569458,
"learning_rate": 1.8733290006380264e-05,
"loss": 1.0094,
"step": 159
},
{
"epoch": 0.17204301075268819,
"grad_norm": 0.6561658382415771,
"learning_rate": 1.8716604700327516e-05,
"loss": 0.9721,
"step": 160
},
{
"epoch": 0.17311827956989248,
"grad_norm": 0.6266697645187378,
"learning_rate": 1.8699817752785495e-05,
"loss": 0.969,
"step": 161
},
{
"epoch": 0.17419354838709677,
"grad_norm": 0.6561981439590454,
"learning_rate": 1.8682929359501338e-05,
"loss": 0.9676,
"step": 162
},
{
"epoch": 0.17526881720430107,
"grad_norm": 0.6283778548240662,
"learning_rate": 1.86659397174051e-05,
"loss": 0.9781,
"step": 163
},
{
"epoch": 0.17634408602150536,
"grad_norm": 0.6202700138092041,
"learning_rate": 1.864884902460746e-05,
"loss": 0.9959,
"step": 164
},
{
"epoch": 0.1774193548387097,
"grad_norm": 0.6140043139457703,
"learning_rate": 1.863165748039743e-05,
"loss": 0.9877,
"step": 165
},
{
"epoch": 0.17849462365591398,
"grad_norm": 0.6894904971122742,
"learning_rate": 1.8614365285240002e-05,
"loss": 0.9207,
"step": 166
},
{
"epoch": 0.17956989247311828,
"grad_norm": 0.6222094893455505,
"learning_rate": 1.859697264077384e-05,
"loss": 0.9966,
"step": 167
},
{
"epoch": 0.18064516129032257,
"grad_norm": 0.6153229475021362,
"learning_rate": 1.8579479749808896e-05,
"loss": 0.9319,
"step": 168
},
{
"epoch": 0.1817204301075269,
"grad_norm": 0.5651281476020813,
"learning_rate": 1.8561886816324094e-05,
"loss": 1.0048,
"step": 169
},
{
"epoch": 0.1827956989247312,
"grad_norm": 0.6294932961463928,
"learning_rate": 1.8544194045464888e-05,
"loss": 0.9759,
"step": 170
},
{
"epoch": 0.18387096774193548,
"grad_norm": 0.607211172580719,
"learning_rate": 1.8526401643540924e-05,
"loss": 0.9158,
"step": 171
},
{
"epoch": 0.18494623655913978,
"grad_norm": 0.6540266275405884,
"learning_rate": 1.850850981802361e-05,
"loss": 0.9033,
"step": 172
},
{
"epoch": 0.1860215053763441,
"grad_norm": 0.587095320224762,
"learning_rate": 1.849051877754369e-05,
"loss": 0.9804,
"step": 173
},
{
"epoch": 0.1870967741935484,
"grad_norm": 0.6455761194229126,
"learning_rate": 1.8472428731888836e-05,
"loss": 0.9612,
"step": 174
},
{
"epoch": 0.1881720430107527,
"grad_norm": 0.6742892861366272,
"learning_rate": 1.845423989200118e-05,
"loss": 0.9744,
"step": 175
},
{
"epoch": 0.18924731182795698,
"grad_norm": 0.616705596446991,
"learning_rate": 1.8435952469974858e-05,
"loss": 1.0034,
"step": 176
},
{
"epoch": 0.19032258064516128,
"grad_norm": 0.6112809777259827,
"learning_rate": 1.8417566679053546e-05,
"loss": 0.9842,
"step": 177
},
{
"epoch": 0.1913978494623656,
"grad_norm": 0.6453455090522766,
"learning_rate": 1.8399082733627967e-05,
"loss": 0.9599,
"step": 178
},
{
"epoch": 0.1924731182795699,
"grad_norm": 0.6839727163314819,
"learning_rate": 1.8380500849233388e-05,
"loss": 0.9645,
"step": 179
},
{
"epoch": 0.1935483870967742,
"grad_norm": 0.6297851204872131,
"learning_rate": 1.836182124254711e-05,
"loss": 0.9668,
"step": 180
},
{
"epoch": 0.19462365591397848,
"grad_norm": 0.6919458508491516,
"learning_rate": 1.834304413138595e-05,
"loss": 0.9229,
"step": 181
},
{
"epoch": 0.1956989247311828,
"grad_norm": 0.6567605137825012,
"learning_rate": 1.832416973470368e-05,
"loss": 0.9154,
"step": 182
},
{
"epoch": 0.1967741935483871,
"grad_norm": 0.6956243515014648,
"learning_rate": 1.8305198272588508e-05,
"loss": 0.9811,
"step": 183
},
{
"epoch": 0.1978494623655914,
"grad_norm": 0.6485621929168701,
"learning_rate": 1.828612996626046e-05,
"loss": 0.9676,
"step": 184
},
{
"epoch": 0.1989247311827957,
"grad_norm": 0.7490953207015991,
"learning_rate": 1.8266965038068856e-05,
"loss": 0.9766,
"step": 185
},
{
"epoch": 0.2,
"grad_norm": 0.6626827120780945,
"learning_rate": 1.8247703711489684e-05,
"loss": 0.9575,
"step": 186
},
{
"epoch": 0.2010752688172043,
"grad_norm": 0.6175429821014404,
"learning_rate": 1.8228346211123e-05,
"loss": 0.9801,
"step": 187
},
{
"epoch": 0.2021505376344086,
"grad_norm": 0.6406196355819702,
"learning_rate": 1.820889276269032e-05,
"loss": 0.9453,
"step": 188
},
{
"epoch": 0.2032258064516129,
"grad_norm": 0.6591558456420898,
"learning_rate": 1.8189343593031957e-05,
"loss": 0.9892,
"step": 189
},
{
"epoch": 0.20430107526881722,
"grad_norm": 0.6754528284072876,
"learning_rate": 1.816969893010442e-05,
"loss": 0.9521,
"step": 190
},
{
"epoch": 0.2053763440860215,
"grad_norm": 0.6206115484237671,
"learning_rate": 1.8149959002977736e-05,
"loss": 0.9677,
"step": 191
},
{
"epoch": 0.2064516129032258,
"grad_norm": 0.6599158644676208,
"learning_rate": 1.813012404183275e-05,
"loss": 0.9396,
"step": 192
},
{
"epoch": 0.2075268817204301,
"grad_norm": 0.6430920958518982,
"learning_rate": 1.8110194277958505e-05,
"loss": 0.9879,
"step": 193
},
{
"epoch": 0.2086021505376344,
"grad_norm": 0.7177631855010986,
"learning_rate": 1.8090169943749477e-05,
"loss": 0.9088,
"step": 194
},
{
"epoch": 0.20967741935483872,
"grad_norm": 0.6201785206794739,
"learning_rate": 1.8070051272702905e-05,
"loss": 0.968,
"step": 195
},
{
"epoch": 0.210752688172043,
"grad_norm": 0.669746458530426,
"learning_rate": 1.804983849941607e-05,
"loss": 0.9375,
"step": 196
},
{
"epoch": 0.2118279569892473,
"grad_norm": 0.6609156727790833,
"learning_rate": 1.802953185958354e-05,
"loss": 0.9481,
"step": 197
},
{
"epoch": 0.2129032258064516,
"grad_norm": 0.6623542308807373,
"learning_rate": 1.8009131589994418e-05,
"loss": 0.9446,
"step": 198
},
{
"epoch": 0.21397849462365592,
"grad_norm": 0.6999096870422363,
"learning_rate": 1.7988637928529616e-05,
"loss": 1.0086,
"step": 199
},
{
"epoch": 0.21505376344086022,
"grad_norm": 0.7636443972587585,
"learning_rate": 1.7968051114159046e-05,
"loss": 0.9363,
"step": 200
},
{
"epoch": 0.2161290322580645,
"grad_norm": 0.6308568120002747,
"learning_rate": 1.7947371386938848e-05,
"loss": 0.9971,
"step": 201
},
{
"epoch": 0.2172043010752688,
"grad_norm": 0.6510555148124695,
"learning_rate": 1.7926598988008584e-05,
"loss": 1.0124,
"step": 202
},
{
"epoch": 0.21827956989247313,
"grad_norm": 0.6936912536621094,
"learning_rate": 1.7905734159588437e-05,
"loss": 0.9521,
"step": 203
},
{
"epoch": 0.21935483870967742,
"grad_norm": 0.7332192063331604,
"learning_rate": 1.7884777144976376e-05,
"loss": 1.0081,
"step": 204
},
{
"epoch": 0.22043010752688172,
"grad_norm": 0.7468619346618652,
"learning_rate": 1.7863728188545326e-05,
"loss": 0.922,
"step": 205
},
{
"epoch": 0.221505376344086,
"grad_norm": 0.6665534377098083,
"learning_rate": 1.7842587535740315e-05,
"loss": 0.9683,
"step": 206
},
{
"epoch": 0.22258064516129034,
"grad_norm": 0.6921372413635254,
"learning_rate": 1.7821355433075612e-05,
"loss": 0.9393,
"step": 207
},
{
"epoch": 0.22365591397849463,
"grad_norm": 0.7466671466827393,
"learning_rate": 1.7800032128131846e-05,
"loss": 0.9419,
"step": 208
},
{
"epoch": 0.22473118279569892,
"grad_norm": 0.6907378435134888,
"learning_rate": 1.7778617869553144e-05,
"loss": 0.9374,
"step": 209
},
{
"epoch": 0.22580645161290322,
"grad_norm": 0.704535722732544,
"learning_rate": 1.77571129070442e-05,
"loss": 0.9838,
"step": 210
},
{
"epoch": 0.22688172043010751,
"grad_norm": 0.7151262164115906,
"learning_rate": 1.7735517491367377e-05,
"loss": 0.934,
"step": 211
},
{
"epoch": 0.22795698924731184,
"grad_norm": 0.7060497403144836,
"learning_rate": 1.771383187433978e-05,
"loss": 0.9295,
"step": 212
},
{
"epoch": 0.22903225806451613,
"grad_norm": 0.6923340559005737,
"learning_rate": 1.769205630883034e-05,
"loss": 0.9267,
"step": 213
},
{
"epoch": 0.23010752688172043,
"grad_norm": 0.6596957445144653,
"learning_rate": 1.7670191048756827e-05,
"loss": 0.9271,
"step": 214
},
{
"epoch": 0.23118279569892472,
"grad_norm": 0.6493801474571228,
"learning_rate": 1.7648236349082928e-05,
"loss": 0.8111,
"step": 215
},
{
"epoch": 0.23225806451612904,
"grad_norm": 0.7255016565322876,
"learning_rate": 1.762619246581524e-05,
"loss": 0.9433,
"step": 216
},
{
"epoch": 0.23333333333333334,
"grad_norm": 0.6772259473800659,
"learning_rate": 1.7604059656000313e-05,
"loss": 0.9621,
"step": 217
},
{
"epoch": 0.23440860215053763,
"grad_norm": 0.6661478281021118,
"learning_rate": 1.758183817772163e-05,
"loss": 0.9105,
"step": 218
},
{
"epoch": 0.23548387096774193,
"grad_norm": 0.6999973058700562,
"learning_rate": 1.7559528290096618e-05,
"loss": 0.8903,
"step": 219
},
{
"epoch": 0.23655913978494625,
"grad_norm": 0.707212507724762,
"learning_rate": 1.7537130253273613e-05,
"loss": 0.9644,
"step": 220
},
{
"epoch": 0.23763440860215054,
"grad_norm": 0.6678735613822937,
"learning_rate": 1.7514644328428826e-05,
"loss": 0.9811,
"step": 221
},
{
"epoch": 0.23870967741935484,
"grad_norm": 0.6692453026771545,
"learning_rate": 1.749207077776331e-05,
"loss": 0.8874,
"step": 222
},
{
"epoch": 0.23978494623655913,
"grad_norm": 0.7460502982139587,
"learning_rate": 1.746940986449989e-05,
"loss": 0.9298,
"step": 223
},
{
"epoch": 0.24086021505376345,
"grad_norm": 0.7537499666213989,
"learning_rate": 1.744666185288009e-05,
"loss": 0.9439,
"step": 224
},
{
"epoch": 0.24193548387096775,
"grad_norm": 0.7694090604782104,
"learning_rate": 1.742382700816107e-05,
"loss": 0.9174,
"step": 225
},
{
"epoch": 0.24301075268817204,
"grad_norm": 0.7226264476776123,
"learning_rate": 1.740090559661252e-05,
"loss": 0.937,
"step": 226
},
{
"epoch": 0.24408602150537634,
"grad_norm": 0.7109532356262207,
"learning_rate": 1.7377897885513556e-05,
"loss": 1.0118,
"step": 227
},
{
"epoch": 0.24516129032258063,
"grad_norm": 0.6979506015777588,
"learning_rate": 1.735480414314961e-05,
"loss": 0.8199,
"step": 228
},
{
"epoch": 0.24623655913978496,
"grad_norm": 0.6781380772590637,
"learning_rate": 1.733162463880929e-05,
"loss": 0.992,
"step": 229
},
{
"epoch": 0.24731182795698925,
"grad_norm": 0.6880660653114319,
"learning_rate": 1.730835964278124e-05,
"loss": 0.9816,
"step": 230
},
{
"epoch": 0.24838709677419354,
"grad_norm": 0.7391674518585205,
"learning_rate": 1.7285009426351018e-05,
"loss": 0.9519,
"step": 231
},
{
"epoch": 0.24946236559139784,
"grad_norm": 0.5953665375709534,
"learning_rate": 1.7261574261797887e-05,
"loss": 0.9857,
"step": 232
},
{
"epoch": 0.25053763440860216,
"grad_norm": 0.7037912011146545,
"learning_rate": 1.7238054422391672e-05,
"loss": 0.9259,
"step": 233
},
{
"epoch": 0.25053763440860216,
"eval_loss": 0.8279001712799072,
"eval_runtime": 241.007,
"eval_samples_per_second": 11.552,
"eval_steps_per_second": 0.481,
"step": 233
},
{
"epoch": 0.25161290322580643,
"grad_norm": 0.718204140663147,
"learning_rate": 1.721445018238956e-05,
"loss": 0.9104,
"step": 234
},
{
"epoch": 0.25268817204301075,
"grad_norm": 0.7386565804481506,
"learning_rate": 1.719076181703291e-05,
"loss": 0.9562,
"step": 235
},
{
"epoch": 0.2537634408602151,
"grad_norm": 0.7336955070495605,
"learning_rate": 1.7166989602544036e-05,
"loss": 0.9347,
"step": 236
},
{
"epoch": 0.25483870967741934,
"grad_norm": 0.732012927532196,
"learning_rate": 1.7143133816122993e-05,
"loss": 0.7988,
"step": 237
},
{
"epoch": 0.25591397849462366,
"grad_norm": 0.7496695518493652,
"learning_rate": 1.7119194735944336e-05,
"loss": 0.9349,
"step": 238
},
{
"epoch": 0.256989247311828,
"grad_norm": 0.7384220957756042,
"learning_rate": 1.7095172641153894e-05,
"loss": 0.9476,
"step": 239
},
{
"epoch": 0.25806451612903225,
"grad_norm": 0.7248124480247498,
"learning_rate": 1.7071067811865477e-05,
"loss": 0.9411,
"step": 240
},
{
"epoch": 0.2591397849462366,
"grad_norm": 0.7681155800819397,
"learning_rate": 1.704688052915766e-05,
"loss": 0.9623,
"step": 241
},
{
"epoch": 0.26021505376344084,
"grad_norm": 0.7818267345428467,
"learning_rate": 1.7022611075070476e-05,
"loss": 0.9081,
"step": 242
},
{
"epoch": 0.26129032258064516,
"grad_norm": 0.7292929887771606,
"learning_rate": 1.6998259732602114e-05,
"loss": 0.9384,
"step": 243
},
{
"epoch": 0.2623655913978495,
"grad_norm": 0.7873015403747559,
"learning_rate": 1.697382678570566e-05,
"loss": 0.9372,
"step": 244
},
{
"epoch": 0.26344086021505375,
"grad_norm": 0.8167495131492615,
"learning_rate": 1.694931251928575e-05,
"loss": 0.9433,
"step": 245
},
{
"epoch": 0.2645161290322581,
"grad_norm": 0.7841079831123352,
"learning_rate": 1.6924717219195258e-05,
"loss": 0.9284,
"step": 246
},
{
"epoch": 0.26559139784946234,
"grad_norm": 0.7518281936645508,
"learning_rate": 1.6900041172231976e-05,
"loss": 0.9286,
"step": 247
},
{
"epoch": 0.26666666666666666,
"grad_norm": 0.8195715546607971,
"learning_rate": 1.6875284666135252e-05,
"loss": 0.8856,
"step": 248
},
{
"epoch": 0.267741935483871,
"grad_norm": 0.8226678967475891,
"learning_rate": 1.6850447989582642e-05,
"loss": 0.9344,
"step": 249
},
{
"epoch": 0.26881720430107525,
"grad_norm": 0.7635514736175537,
"learning_rate": 1.6825531432186545e-05,
"loss": 0.9615,
"step": 250
},
{
"epoch": 0.2698924731182796,
"grad_norm": 0.7255238890647888,
"learning_rate": 1.680053528449082e-05,
"loss": 0.9485,
"step": 251
},
{
"epoch": 0.2709677419354839,
"grad_norm": 0.7115532159805298,
"learning_rate": 1.677545983796741e-05,
"loss": 0.8788,
"step": 252
},
{
"epoch": 0.27204301075268816,
"grad_norm": 0.7228000164031982,
"learning_rate": 1.6750305385012936e-05,
"loss": 0.9634,
"step": 253
},
{
"epoch": 0.2731182795698925,
"grad_norm": 0.7726433873176575,
"learning_rate": 1.6725072218945274e-05,
"loss": 0.9424,
"step": 254
},
{
"epoch": 0.27419354838709675,
"grad_norm": 0.7616019248962402,
"learning_rate": 1.6699760634000166e-05,
"loss": 0.9736,
"step": 255
},
{
"epoch": 0.2752688172043011,
"grad_norm": 0.6681120991706848,
"learning_rate": 1.667437092532776e-05,
"loss": 0.9507,
"step": 256
},
{
"epoch": 0.2763440860215054,
"grad_norm": 0.7210878133773804,
"learning_rate": 1.6648903388989182e-05,
"loss": 0.9055,
"step": 257
},
{
"epoch": 0.27741935483870966,
"grad_norm": 0.7816373109817505,
"learning_rate": 1.662335832195308e-05,
"loss": 0.9537,
"step": 258
},
{
"epoch": 0.278494623655914,
"grad_norm": 0.80950528383255,
"learning_rate": 1.659773602209216e-05,
"loss": 0.9246,
"step": 259
},
{
"epoch": 0.27956989247311825,
"grad_norm": 0.81439608335495,
"learning_rate": 1.6572036788179728e-05,
"loss": 0.864,
"step": 260
},
{
"epoch": 0.2806451612903226,
"grad_norm": 0.7569161057472229,
"learning_rate": 1.654626091988617e-05,
"loss": 0.9431,
"step": 261
},
{
"epoch": 0.2817204301075269,
"grad_norm": 0.7427302002906799,
"learning_rate": 1.6520408717775507e-05,
"loss": 0.9782,
"step": 262
},
{
"epoch": 0.28279569892473116,
"grad_norm": 0.7272223234176636,
"learning_rate": 1.6494480483301836e-05,
"loss": 0.966,
"step": 263
},
{
"epoch": 0.2838709677419355,
"grad_norm": 0.8124448657035828,
"learning_rate": 1.6468476518805872e-05,
"loss": 0.8872,
"step": 264
},
{
"epoch": 0.2849462365591398,
"grad_norm": 0.7480745911598206,
"learning_rate": 1.6442397127511366e-05,
"loss": 0.9192,
"step": 265
},
{
"epoch": 0.2860215053763441,
"grad_norm": 0.7396025061607361,
"learning_rate": 1.6416242613521612e-05,
"loss": 0.8917,
"step": 266
},
{
"epoch": 0.2870967741935484,
"grad_norm": 0.7699283957481384,
"learning_rate": 1.6390013281815884e-05,
"loss": 0.933,
"step": 267
},
{
"epoch": 0.28817204301075267,
"grad_norm": 0.781078577041626,
"learning_rate": 1.6363709438245877e-05,
"loss": 0.931,
"step": 268
},
{
"epoch": 0.289247311827957,
"grad_norm": 0.8071228265762329,
"learning_rate": 1.6337331389532148e-05,
"loss": 0.913,
"step": 269
},
{
"epoch": 0.2903225806451613,
"grad_norm": 0.8504091501235962,
"learning_rate": 1.631087944326053e-05,
"loss": 0.9049,
"step": 270
},
{
"epoch": 0.2913978494623656,
"grad_norm": 0.7057498097419739,
"learning_rate": 1.6284353907878557e-05,
"loss": 0.9174,
"step": 271
},
{
"epoch": 0.2924731182795699,
"grad_norm": 0.8215770721435547,
"learning_rate": 1.6257755092691865e-05,
"loss": 0.9154,
"step": 272
},
{
"epoch": 0.29354838709677417,
"grad_norm": 0.7845609188079834,
"learning_rate": 1.6231083307860574e-05,
"loss": 0.9382,
"step": 273
},
{
"epoch": 0.2946236559139785,
"grad_norm": 0.7890587449073792,
"learning_rate": 1.6204338864395683e-05,
"loss": 0.9309,
"step": 274
},
{
"epoch": 0.2956989247311828,
"grad_norm": 0.7580718994140625,
"learning_rate": 1.6177522074155436e-05,
"loss": 0.9568,
"step": 275
},
{
"epoch": 0.2967741935483871,
"grad_norm": 0.7641699314117432,
"learning_rate": 1.6150633249841696e-05,
"loss": 0.9461,
"step": 276
},
{
"epoch": 0.2978494623655914,
"grad_norm": 0.7395573854446411,
"learning_rate": 1.612367270499629e-05,
"loss": 0.9212,
"step": 277
},
{
"epoch": 0.2989247311827957,
"grad_norm": 0.7308792471885681,
"learning_rate": 1.609664075399735e-05,
"loss": 0.9333,
"step": 278
},
{
"epoch": 0.3,
"grad_norm": 0.8151824474334717,
"learning_rate": 1.6069537712055652e-05,
"loss": 0.9271,
"step": 279
},
{
"epoch": 0.3010752688172043,
"grad_norm": 0.7019997239112854,
"learning_rate": 1.6042363895210948e-05,
"loss": 0.8021,
"step": 280
},
{
"epoch": 0.3021505376344086,
"grad_norm": 0.7757791876792908,
"learning_rate": 1.6015119620328266e-05,
"loss": 0.9181,
"step": 281
},
{
"epoch": 0.3032258064516129,
"grad_norm": 0.7289377450942993,
"learning_rate": 1.5987805205094225e-05,
"loss": 0.9425,
"step": 282
},
{
"epoch": 0.3043010752688172,
"grad_norm": 0.8123842477798462,
"learning_rate": 1.5960420968013334e-05,
"loss": 0.9172,
"step": 283
},
{
"epoch": 0.3053763440860215,
"grad_norm": 0.9251433610916138,
"learning_rate": 1.5932967228404255e-05,
"loss": 0.9684,
"step": 284
},
{
"epoch": 0.3064516129032258,
"grad_norm": 0.8081958293914795,
"learning_rate": 1.590544430639611e-05,
"loss": 0.9333,
"step": 285
},
{
"epoch": 0.30752688172043013,
"grad_norm": 0.805475115776062,
"learning_rate": 1.5877852522924733e-05,
"loss": 0.9307,
"step": 286
},
{
"epoch": 0.3086021505376344,
"grad_norm": 0.7162765264511108,
"learning_rate": 1.5850192199728927e-05,
"loss": 0.9564,
"step": 287
},
{
"epoch": 0.3096774193548387,
"grad_norm": 0.7985969185829163,
"learning_rate": 1.582246365934671e-05,
"loss": 0.9382,
"step": 288
},
{
"epoch": 0.310752688172043,
"grad_norm": 0.8044575452804565,
"learning_rate": 1.5794667225111572e-05,
"loss": 0.9351,
"step": 289
},
{
"epoch": 0.3118279569892473,
"grad_norm": 0.804595410823822,
"learning_rate": 1.5766803221148676e-05,
"loss": 0.8794,
"step": 290
},
{
"epoch": 0.31290322580645163,
"grad_norm": 0.7444095611572266,
"learning_rate": 1.5738871972371096e-05,
"loss": 0.9392,
"step": 291
},
{
"epoch": 0.3139784946236559,
"grad_norm": 0.8467448949813843,
"learning_rate": 1.5710873804476035e-05,
"loss": 0.8868,
"step": 292
},
{
"epoch": 0.3150537634408602,
"grad_norm": 0.7347026467323303,
"learning_rate": 1.5682809043941013e-05,
"loss": 0.9709,
"step": 293
},
{
"epoch": 0.3161290322580645,
"grad_norm": 0.8257015943527222,
"learning_rate": 1.565467801802006e-05,
"loss": 0.9504,
"step": 294
},
{
"epoch": 0.3172043010752688,
"grad_norm": 0.7517876625061035,
"learning_rate": 1.5626481054739916e-05,
"loss": 0.9575,
"step": 295
},
{
"epoch": 0.31827956989247314,
"grad_norm": 0.806496798992157,
"learning_rate": 1.5598218482896182e-05,
"loss": 0.9305,
"step": 296
},
{
"epoch": 0.3193548387096774,
"grad_norm": 0.7192513942718506,
"learning_rate": 1.5569890632049515e-05,
"loss": 0.8197,
"step": 297
},
{
"epoch": 0.3204301075268817,
"grad_norm": 0.7461637258529663,
"learning_rate": 1.554149783252175e-05,
"loss": 0.9123,
"step": 298
},
{
"epoch": 0.32150537634408605,
"grad_norm": 0.8110654950141907,
"learning_rate": 1.551304041539208e-05,
"loss": 0.8738,
"step": 299
},
{
"epoch": 0.3225806451612903,
"grad_norm": 0.804533064365387,
"learning_rate": 1.5484518712493188e-05,
"loss": 0.946,
"step": 300
},
{
"epoch": 0.32365591397849464,
"grad_norm": 0.7754772305488586,
"learning_rate": 1.545593305640736e-05,
"loss": 0.9249,
"step": 301
},
{
"epoch": 0.3247311827956989,
"grad_norm": 0.7326719760894775,
"learning_rate": 1.542728378046262e-05,
"loss": 0.9068,
"step": 302
},
{
"epoch": 0.3258064516129032,
"grad_norm": 0.835762083530426,
"learning_rate": 1.539857121872885e-05,
"loss": 0.9104,
"step": 303
},
{
"epoch": 0.32688172043010755,
"grad_norm": 0.7900486588478088,
"learning_rate": 1.536979570601388e-05,
"loss": 0.9449,
"step": 304
},
{
"epoch": 0.3279569892473118,
"grad_norm": 0.8278104662895203,
"learning_rate": 1.5340957577859605e-05,
"loss": 0.9153,
"step": 305
},
{
"epoch": 0.32903225806451614,
"grad_norm": 0.7644244432449341,
"learning_rate": 1.5312057170538033e-05,
"loss": 0.9347,
"step": 306
},
{
"epoch": 0.3301075268817204,
"grad_norm": 0.7568009495735168,
"learning_rate": 1.5283094821047416e-05,
"loss": 0.9186,
"step": 307
},
{
"epoch": 0.3311827956989247,
"grad_norm": 0.9083740711212158,
"learning_rate": 1.5254070867108277e-05,
"loss": 0.8872,
"step": 308
},
{
"epoch": 0.33225806451612905,
"grad_norm": 0.7168444395065308,
"learning_rate": 1.5224985647159489e-05,
"loss": 0.9319,
"step": 309
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.8705156445503235,
"learning_rate": 1.5195839500354337e-05,
"loss": 0.8789,
"step": 310
},
{
"epoch": 0.33440860215053764,
"grad_norm": 0.800618588924408,
"learning_rate": 1.5166632766556546e-05,
"loss": 0.9108,
"step": 311
},
{
"epoch": 0.33548387096774196,
"grad_norm": 0.7793113589286804,
"learning_rate": 1.5137365786336329e-05,
"loss": 0.9201,
"step": 312
},
{
"epoch": 0.3365591397849462,
"grad_norm": 0.8202828764915466,
"learning_rate": 1.5108038900966416e-05,
"loss": 0.9229,
"step": 313
},
{
"epoch": 0.33763440860215055,
"grad_norm": 0.8053287267684937,
"learning_rate": 1.5078652452418063e-05,
"loss": 0.927,
"step": 314
},
{
"epoch": 0.3387096774193548,
"grad_norm": 0.8459357619285583,
"learning_rate": 1.5049206783357082e-05,
"loss": 0.905,
"step": 315
},
{
"epoch": 0.33978494623655914,
"grad_norm": 0.8645407557487488,
"learning_rate": 1.501970223713983e-05,
"loss": 0.8827,
"step": 316
},
{
"epoch": 0.34086021505376346,
"grad_norm": 0.7910537719726562,
"learning_rate": 1.4990139157809217e-05,
"loss": 0.9287,
"step": 317
},
{
"epoch": 0.3419354838709677,
"grad_norm": 0.7768109440803528,
"learning_rate": 1.4960517890090683e-05,
"loss": 0.9122,
"step": 318
},
{
"epoch": 0.34301075268817205,
"grad_norm": 0.827042281627655,
"learning_rate": 1.4930838779388186e-05,
"loss": 0.9957,
"step": 319
},
{
"epoch": 0.34408602150537637,
"grad_norm": 0.8755815625190735,
"learning_rate": 1.4901102171780175e-05,
"loss": 0.901,
"step": 320
},
{
"epoch": 0.34516129032258064,
"grad_norm": 0.8080335259437561,
"learning_rate": 1.4871308414015547e-05,
"loss": 0.9454,
"step": 321
},
{
"epoch": 0.34623655913978496,
"grad_norm": 0.737436830997467,
"learning_rate": 1.4841457853509606e-05,
"loss": 0.9691,
"step": 322
},
{
"epoch": 0.3473118279569892,
"grad_norm": 0.8127477765083313,
"learning_rate": 1.4811550838340028e-05,
"loss": 0.9147,
"step": 323
},
{
"epoch": 0.34838709677419355,
"grad_norm": 0.8597912192344666,
"learning_rate": 1.4781587717242772e-05,
"loss": 0.8878,
"step": 324
},
{
"epoch": 0.34946236559139787,
"grad_norm": 0.8688490390777588,
"learning_rate": 1.4751568839608036e-05,
"loss": 0.8875,
"step": 325
},
{
"epoch": 0.35053763440860214,
"grad_norm": 0.8337180614471436,
"learning_rate": 1.4721494555476189e-05,
"loss": 0.9472,
"step": 326
},
{
"epoch": 0.35161290322580646,
"grad_norm": 0.716763973236084,
"learning_rate": 1.4691365215533653e-05,
"loss": 0.7999,
"step": 327
},
{
"epoch": 0.35268817204301073,
"grad_norm": 0.8275082111358643,
"learning_rate": 1.4661181171108855e-05,
"loss": 0.8463,
"step": 328
},
{
"epoch": 0.35376344086021505,
"grad_norm": 0.8415479063987732,
"learning_rate": 1.4630942774168113e-05,
"loss": 0.9254,
"step": 329
},
{
"epoch": 0.3548387096774194,
"grad_norm": 0.8180720806121826,
"learning_rate": 1.4600650377311523e-05,
"loss": 0.9728,
"step": 330
},
{
"epoch": 0.35591397849462364,
"grad_norm": 0.7769216895103455,
"learning_rate": 1.4570304333768865e-05,
"loss": 0.909,
"step": 331
},
{
"epoch": 0.35698924731182796,
"grad_norm": 0.8296689987182617,
"learning_rate": 1.4539904997395468e-05,
"loss": 0.8499,
"step": 332
},
{
"epoch": 0.3580645161290323,
"grad_norm": 0.8449047803878784,
"learning_rate": 1.45094527226681e-05,
"loss": 0.9287,
"step": 333
},
{
"epoch": 0.35913978494623655,
"grad_norm": 0.8248459696769714,
"learning_rate": 1.4478947864680821e-05,
"loss": 0.912,
"step": 334
},
{
"epoch": 0.3602150537634409,
"grad_norm": 0.8891895413398743,
"learning_rate": 1.4448390779140844e-05,
"loss": 0.9246,
"step": 335
},
{
"epoch": 0.36129032258064514,
"grad_norm": 0.8913347721099854,
"learning_rate": 1.4417781822364396e-05,
"loss": 0.8844,
"step": 336
},
{
"epoch": 0.36236559139784946,
"grad_norm": 0.7879188656806946,
"learning_rate": 1.4387121351272555e-05,
"loss": 0.9675,
"step": 337
},
{
"epoch": 0.3634408602150538,
"grad_norm": 0.8322626352310181,
"learning_rate": 1.4356409723387092e-05,
"loss": 0.9204,
"step": 338
},
{
"epoch": 0.36451612903225805,
"grad_norm": 0.8096638321876526,
"learning_rate": 1.4325647296826302e-05,
"loss": 0.9202,
"step": 339
},
{
"epoch": 0.3655913978494624,
"grad_norm": 0.8181870579719543,
"learning_rate": 1.4294834430300822e-05,
"loss": 0.9297,
"step": 340
},
{
"epoch": 0.36666666666666664,
"grad_norm": 0.8794824481010437,
"learning_rate": 1.4263971483109456e-05,
"loss": 0.93,
"step": 341
},
{
"epoch": 0.36774193548387096,
"grad_norm": 0.7784544825553894,
"learning_rate": 1.4233058815134978e-05,
"loss": 0.918,
"step": 342
},
{
"epoch": 0.3688172043010753,
"grad_norm": 0.8606961369514465,
"learning_rate": 1.4202096786839953e-05,
"loss": 0.9038,
"step": 343
},
{
"epoch": 0.36989247311827955,
"grad_norm": 0.8213427662849426,
"learning_rate": 1.4171085759262507e-05,
"loss": 0.9241,
"step": 344
},
{
"epoch": 0.3709677419354839,
"grad_norm": 0.8662806153297424,
"learning_rate": 1.4140026094012136e-05,
"loss": 0.8955,
"step": 345
},
{
"epoch": 0.3720430107526882,
"grad_norm": 0.8682425022125244,
"learning_rate": 1.4108918153265485e-05,
"loss": 0.9472,
"step": 346
},
{
"epoch": 0.37311827956989246,
"grad_norm": 0.8322152495384216,
"learning_rate": 1.4077762299762116e-05,
"loss": 0.9551,
"step": 347
},
{
"epoch": 0.3741935483870968,
"grad_norm": 0.8238283395767212,
"learning_rate": 1.4046558896800299e-05,
"loss": 0.9479,
"step": 348
},
{
"epoch": 0.37526881720430105,
"grad_norm": 0.8035296201705933,
"learning_rate": 1.4015308308232753e-05,
"loss": 0.9319,
"step": 349
},
{
"epoch": 0.3763440860215054,
"grad_norm": 0.7743344902992249,
"learning_rate": 1.3984010898462417e-05,
"loss": 0.9102,
"step": 350
},
{
"epoch": 0.3774193548387097,
"grad_norm": 0.8227608799934387,
"learning_rate": 1.3952667032438191e-05,
"loss": 0.8969,
"step": 351
},
{
"epoch": 0.37849462365591396,
"grad_norm": 0.8089775443077087,
"learning_rate": 1.3921277075650703e-05,
"loss": 0.9621,
"step": 352
},
{
"epoch": 0.3795698924731183,
"grad_norm": 0.8506449460983276,
"learning_rate": 1.3889841394128007e-05,
"loss": 0.8901,
"step": 353
},
{
"epoch": 0.38064516129032255,
"grad_norm": 0.9277204871177673,
"learning_rate": 1.3858360354431355e-05,
"loss": 0.8627,
"step": 354
},
{
"epoch": 0.3817204301075269,
"grad_norm": 0.832259476184845,
"learning_rate": 1.3826834323650899e-05,
"loss": 0.9437,
"step": 355
},
{
"epoch": 0.3827956989247312,
"grad_norm": 0.7443482279777527,
"learning_rate": 1.379526366940142e-05,
"loss": 0.9532,
"step": 356
},
{
"epoch": 0.38387096774193546,
"grad_norm": 0.887854814529419,
"learning_rate": 1.3763648759818035e-05,
"loss": 0.8876,
"step": 357
},
{
"epoch": 0.3849462365591398,
"grad_norm": 0.8205659985542297,
"learning_rate": 1.3731989963551916e-05,
"loss": 0.8975,
"step": 358
},
{
"epoch": 0.3860215053763441,
"grad_norm": 0.8111019134521484,
"learning_rate": 1.3700287649765973e-05,
"loss": 0.9087,
"step": 359
},
{
"epoch": 0.3870967741935484,
"grad_norm": 0.8579467535018921,
"learning_rate": 1.3668542188130567e-05,
"loss": 0.9444,
"step": 360
},
{
"epoch": 0.3881720430107527,
"grad_norm": 0.8444235920906067,
"learning_rate": 1.3636753948819188e-05,
"loss": 0.8645,
"step": 361
},
{
"epoch": 0.38924731182795697,
"grad_norm": 0.8532136082649231,
"learning_rate": 1.3604923302504146e-05,
"loss": 0.9295,
"step": 362
},
{
"epoch": 0.3903225806451613,
"grad_norm": 0.9755718111991882,
"learning_rate": 1.3573050620352247e-05,
"loss": 0.8978,
"step": 363
},
{
"epoch": 0.3913978494623656,
"grad_norm": 0.8287932872772217,
"learning_rate": 1.3541136274020452e-05,
"loss": 0.9195,
"step": 364
},
{
"epoch": 0.3924731182795699,
"grad_norm": 0.8778457641601562,
"learning_rate": 1.350918063565157e-05,
"loss": 0.8834,
"step": 365
},
{
"epoch": 0.3935483870967742,
"grad_norm": 1.0230962038040161,
"learning_rate": 1.3477184077869892e-05,
"loss": 0.8352,
"step": 366
},
{
"epoch": 0.3946236559139785,
"grad_norm": 0.8578838109970093,
"learning_rate": 1.3445146973776854e-05,
"loss": 0.9203,
"step": 367
},
{
"epoch": 0.3956989247311828,
"grad_norm": 0.8627865314483643,
"learning_rate": 1.3413069696946706e-05,
"loss": 0.9246,
"step": 368
},
{
"epoch": 0.3967741935483871,
"grad_norm": 0.8898962140083313,
"learning_rate": 1.338095262142212e-05,
"loss": 0.9146,
"step": 369
},
{
"epoch": 0.3978494623655914,
"grad_norm": 0.9508132338523865,
"learning_rate": 1.3348796121709862e-05,
"loss": 0.8892,
"step": 370
},
{
"epoch": 0.3989247311827957,
"grad_norm": 0.9117575287818909,
"learning_rate": 1.3316600572776405e-05,
"loss": 0.9301,
"step": 371
},
{
"epoch": 0.4,
"grad_norm": 0.8592390418052673,
"learning_rate": 1.3284366350043558e-05,
"loss": 0.8979,
"step": 372
},
{
"epoch": 0.4010752688172043,
"grad_norm": 0.8330084681510925,
"learning_rate": 1.32520938293841e-05,
"loss": 0.9418,
"step": 373
},
{
"epoch": 0.4021505376344086,
"grad_norm": 0.7911673784255981,
"learning_rate": 1.3219783387117384e-05,
"loss": 0.9552,
"step": 374
},
{
"epoch": 0.4032258064516129,
"grad_norm": 0.820270299911499,
"learning_rate": 1.318743540000496e-05,
"loss": 0.9313,
"step": 375
},
{
"epoch": 0.4043010752688172,
"grad_norm": 0.7301176190376282,
"learning_rate": 1.3155050245246171e-05,
"loss": 0.9221,
"step": 376
},
{
"epoch": 0.4053763440860215,
"grad_norm": 0.901095986366272,
"learning_rate": 1.3122628300473763e-05,
"loss": 0.8694,
"step": 377
},
{
"epoch": 0.4064516129032258,
"grad_norm": 0.8115401268005371,
"learning_rate": 1.3090169943749475e-05,
"loss": 0.8838,
"step": 378
},
{
"epoch": 0.4075268817204301,
"grad_norm": 0.8125736713409424,
"learning_rate": 1.3057675553559638e-05,
"loss": 0.9649,
"step": 379
},
{
"epoch": 0.40860215053763443,
"grad_norm": 0.8270546793937683,
"learning_rate": 1.302514550881076e-05,
"loss": 0.9482,
"step": 380
},
{
"epoch": 0.4096774193548387,
"grad_norm": 1.0296354293823242,
"learning_rate": 1.2992580188825093e-05,
"loss": 0.8666,
"step": 381
},
{
"epoch": 0.410752688172043,
"grad_norm": 0.8970001935958862,
"learning_rate": 1.2959979973336236e-05,
"loss": 0.9621,
"step": 382
},
{
"epoch": 0.4118279569892473,
"grad_norm": 0.9341355562210083,
"learning_rate": 1.2927345242484683e-05,
"loss": 0.9454,
"step": 383
},
{
"epoch": 0.4129032258064516,
"grad_norm": 0.8696271181106567,
"learning_rate": 1.289467637681341e-05,
"loss": 0.9376,
"step": 384
},
{
"epoch": 0.41397849462365593,
"grad_norm": 0.7984682321548462,
"learning_rate": 1.2861973757263416e-05,
"loss": 0.8875,
"step": 385
},
{
"epoch": 0.4150537634408602,
"grad_norm": 0.9292618632316589,
"learning_rate": 1.28292377651693e-05,
"loss": 0.8475,
"step": 386
},
{
"epoch": 0.4161290322580645,
"grad_norm": 0.8904953002929688,
"learning_rate": 1.2796468782254814e-05,
"loss": 0.9205,
"step": 387
},
{
"epoch": 0.4172043010752688,
"grad_norm": 0.8816090822219849,
"learning_rate": 1.2763667190628391e-05,
"loss": 0.9353,
"step": 388
},
{
"epoch": 0.4182795698924731,
"grad_norm": 0.8573107123374939,
"learning_rate": 1.2730833372778714e-05,
"loss": 0.9269,
"step": 389
},
{
"epoch": 0.41935483870967744,
"grad_norm": 0.9212923049926758,
"learning_rate": 1.2697967711570243e-05,
"loss": 0.8834,
"step": 390
},
{
"epoch": 0.4204301075268817,
"grad_norm": 0.9144071936607361,
"learning_rate": 1.2665070590238753e-05,
"loss": 0.9382,
"step": 391
},
{
"epoch": 0.421505376344086,
"grad_norm": 0.8885826468467712,
"learning_rate": 1.263214239238686e-05,
"loss": 0.8705,
"step": 392
},
{
"epoch": 0.42258064516129035,
"grad_norm": 0.9030449986457825,
"learning_rate": 1.2599183501979558e-05,
"loss": 0.9058,
"step": 393
},
{
"epoch": 0.4236559139784946,
"grad_norm": 0.8024026155471802,
"learning_rate": 1.2566194303339738e-05,
"loss": 0.9498,
"step": 394
},
{
"epoch": 0.42473118279569894,
"grad_norm": 0.8615883588790894,
"learning_rate": 1.2533175181143704e-05,
"loss": 0.9147,
"step": 395
},
{
"epoch": 0.4258064516129032,
"grad_norm": 0.8240619897842407,
"learning_rate": 1.250012652041669e-05,
"loss": 0.9038,
"step": 396
},
{
"epoch": 0.4268817204301075,
"grad_norm": 0.8786563277244568,
"learning_rate": 1.2467048706528373e-05,
"loss": 0.9278,
"step": 397
},
{
"epoch": 0.42795698924731185,
"grad_norm": 0.9570086002349854,
"learning_rate": 1.2433942125188359e-05,
"loss": 0.9454,
"step": 398
},
{
"epoch": 0.4290322580645161,
"grad_norm": 0.8550770282745361,
"learning_rate": 1.2400807162441721e-05,
"loss": 0.9276,
"step": 399
},
{
"epoch": 0.43010752688172044,
"grad_norm": 0.9284153580665588,
"learning_rate": 1.2367644204664468e-05,
"loss": 0.8967,
"step": 400
},
{
"epoch": 0.4311827956989247,
"grad_norm": 0.8993642330169678,
"learning_rate": 1.2334453638559057e-05,
"loss": 0.9173,
"step": 401
},
{
"epoch": 0.432258064516129,
"grad_norm": 0.8449714183807373,
"learning_rate": 1.2301235851149867e-05,
"loss": 0.9276,
"step": 402
},
{
"epoch": 0.43333333333333335,
"grad_norm": 0.8758628964424133,
"learning_rate": 1.2267991229778702e-05,
"loss": 0.902,
"step": 403
},
{
"epoch": 0.4344086021505376,
"grad_norm": 0.9460270404815674,
"learning_rate": 1.2234720162100271e-05,
"loss": 0.9205,
"step": 404
},
{
"epoch": 0.43548387096774194,
"grad_norm": 0.9168769121170044,
"learning_rate": 1.2201423036077657e-05,
"loss": 0.9079,
"step": 405
},
{
"epoch": 0.43655913978494626,
"grad_norm": 0.83861243724823,
"learning_rate": 1.216810023997781e-05,
"loss": 0.9318,
"step": 406
},
{
"epoch": 0.4376344086021505,
"grad_norm": 0.8358942270278931,
"learning_rate": 1.2134752162366998e-05,
"loss": 0.9074,
"step": 407
},
{
"epoch": 0.43870967741935485,
"grad_norm": 0.8796260356903076,
"learning_rate": 1.2101379192106302e-05,
"loss": 0.9288,
"step": 408
},
{
"epoch": 0.4397849462365591,
"grad_norm": 0.8561341762542725,
"learning_rate": 1.206798171834706e-05,
"loss": 0.8724,
"step": 409
},
{
"epoch": 0.44086021505376344,
"grad_norm": 0.9396000504493713,
"learning_rate": 1.2034560130526341e-05,
"loss": 0.9081,
"step": 410
},
{
"epoch": 0.44193548387096776,
"grad_norm": 0.9365426898002625,
"learning_rate": 1.2001114818362394e-05,
"loss": 0.8575,
"step": 411
},
{
"epoch": 0.443010752688172,
"grad_norm": 0.9004622101783752,
"learning_rate": 1.1967646171850118e-05,
"loss": 0.9361,
"step": 412
},
{
"epoch": 0.44408602150537635,
"grad_norm": 0.8997867107391357,
"learning_rate": 1.1934154581256498e-05,
"loss": 0.8709,
"step": 413
},
{
"epoch": 0.44516129032258067,
"grad_norm": 0.890632688999176,
"learning_rate": 1.1900640437116074e-05,
"loss": 0.9333,
"step": 414
},
{
"epoch": 0.44623655913978494,
"grad_norm": 0.869012176990509,
"learning_rate": 1.1867104130226363e-05,
"loss": 0.8991,
"step": 415
},
{
"epoch": 0.44731182795698926,
"grad_norm": 0.8767854571342468,
"learning_rate": 1.1833546051643325e-05,
"loss": 0.9269,
"step": 416
},
{
"epoch": 0.4483870967741935,
"grad_norm": 0.905999481678009,
"learning_rate": 1.1799966592676784e-05,
"loss": 0.9236,
"step": 417
},
{
"epoch": 0.44946236559139785,
"grad_norm": 0.8079774379730225,
"learning_rate": 1.1766366144885877e-05,
"loss": 0.9014,
"step": 418
},
{
"epoch": 0.4505376344086022,
"grad_norm": 0.9038012027740479,
"learning_rate": 1.1732745100074485e-05,
"loss": 0.8835,
"step": 419
},
{
"epoch": 0.45161290322580644,
"grad_norm": 0.9231516718864441,
"learning_rate": 1.1699103850286668e-05,
"loss": 0.8985,
"step": 420
},
{
"epoch": 0.45268817204301076,
"grad_norm": 0.9052597284317017,
"learning_rate": 1.1665442787802083e-05,
"loss": 0.9492,
"step": 421
},
{
"epoch": 0.45376344086021503,
"grad_norm": 0.9429377913475037,
"learning_rate": 1.1631762305131424e-05,
"loss": 0.8591,
"step": 422
},
{
"epoch": 0.45483870967741935,
"grad_norm": 0.9614149332046509,
"learning_rate": 1.1598062795011827e-05,
"loss": 0.9166,
"step": 423
},
{
"epoch": 0.4559139784946237,
"grad_norm": 0.8375269174575806,
"learning_rate": 1.156434465040231e-05,
"loss": 0.9374,
"step": 424
},
{
"epoch": 0.45698924731182794,
"grad_norm": 0.7212313413619995,
"learning_rate": 1.153060826447918e-05,
"loss": 0.7176,
"step": 425
},
{
"epoch": 0.45806451612903226,
"grad_norm": 0.9267921447753906,
"learning_rate": 1.1496854030631443e-05,
"loss": 0.8844,
"step": 426
},
{
"epoch": 0.4591397849462366,
"grad_norm": 0.9112178087234497,
"learning_rate": 1.1463082342456238e-05,
"loss": 0.9367,
"step": 427
},
{
"epoch": 0.46021505376344085,
"grad_norm": 0.8534091114997864,
"learning_rate": 1.1429293593754216e-05,
"loss": 0.917,
"step": 428
},
{
"epoch": 0.4612903225806452,
"grad_norm": 0.946246325969696,
"learning_rate": 1.1395488178524982e-05,
"loss": 0.9292,
"step": 429
},
{
"epoch": 0.46236559139784944,
"grad_norm": 0.8600665330886841,
"learning_rate": 1.1361666490962468e-05,
"loss": 0.8945,
"step": 430
},
{
"epoch": 0.46344086021505376,
"grad_norm": 0.8451212644577026,
"learning_rate": 1.1327828925450363e-05,
"loss": 0.9061,
"step": 431
},
{
"epoch": 0.4645161290322581,
"grad_norm": 0.8945679068565369,
"learning_rate": 1.1293975876557506e-05,
"loss": 0.9045,
"step": 432
},
{
"epoch": 0.46559139784946235,
"grad_norm": 0.8499189019203186,
"learning_rate": 1.126010773903327e-05,
"loss": 0.9097,
"step": 433
},
{
"epoch": 0.4666666666666667,
"grad_norm": 0.9028451442718506,
"learning_rate": 1.1226224907802986e-05,
"loss": 0.8855,
"step": 434
},
{
"epoch": 0.46774193548387094,
"grad_norm": 0.8975670337677002,
"learning_rate": 1.1192327777963313e-05,
"loss": 0.8604,
"step": 435
},
{
"epoch": 0.46881720430107526,
"grad_norm": 0.9408153295516968,
"learning_rate": 1.1158416744777644e-05,
"loss": 0.8763,
"step": 436
},
{
"epoch": 0.4698924731182796,
"grad_norm": 0.8648738265037537,
"learning_rate": 1.1124492203671498e-05,
"loss": 0.9029,
"step": 437
},
{
"epoch": 0.47096774193548385,
"grad_norm": 0.8570336699485779,
"learning_rate": 1.1090554550227899e-05,
"loss": 0.9141,
"step": 438
},
{
"epoch": 0.4720430107526882,
"grad_norm": 0.9008473753929138,
"learning_rate": 1.1056604180182777e-05,
"loss": 0.9176,
"step": 439
},
{
"epoch": 0.4731182795698925,
"grad_norm": 0.9899921417236328,
"learning_rate": 1.1022641489420342e-05,
"loss": 0.887,
"step": 440
},
{
"epoch": 0.47419354838709676,
"grad_norm": 0.843747079372406,
"learning_rate": 1.0988666873968477e-05,
"loss": 0.9383,
"step": 441
},
{
"epoch": 0.4752688172043011,
"grad_norm": 0.8630385398864746,
"learning_rate": 1.0954680729994103e-05,
"loss": 0.9149,
"step": 442
},
{
"epoch": 0.47634408602150535,
"grad_norm": 0.9598048329353333,
"learning_rate": 1.0920683453798581e-05,
"loss": 0.908,
"step": 443
},
{
"epoch": 0.4774193548387097,
"grad_norm": 0.9103092551231384,
"learning_rate": 1.0886675441813083e-05,
"loss": 0.976,
"step": 444
},
{
"epoch": 0.478494623655914,
"grad_norm": 0.8863061666488647,
"learning_rate": 1.0852657090593961e-05,
"loss": 0.891,
"step": 445
},
{
"epoch": 0.47956989247311826,
"grad_norm": 0.9999749064445496,
"learning_rate": 1.0818628796818134e-05,
"loss": 0.8681,
"step": 446
},
{
"epoch": 0.4806451612903226,
"grad_norm": 0.858534038066864,
"learning_rate": 1.0784590957278452e-05,
"loss": 0.917,
"step": 447
},
{
"epoch": 0.4817204301075269,
"grad_norm": 0.9822399020195007,
"learning_rate": 1.0750543968879081e-05,
"loss": 0.8228,
"step": 448
},
{
"epoch": 0.4827956989247312,
"grad_norm": 0.9111456871032715,
"learning_rate": 1.0716488228630867e-05,
"loss": 0.9088,
"step": 449
},
{
"epoch": 0.4838709677419355,
"grad_norm": 1.0209755897521973,
"learning_rate": 1.0682424133646712e-05,
"loss": 0.8397,
"step": 450
},
{
"epoch": 0.48494623655913977,
"grad_norm": 0.9134584665298462,
"learning_rate": 1.064835208113693e-05,
"loss": 0.8753,
"step": 451
},
{
"epoch": 0.4860215053763441,
"grad_norm": 0.9252523183822632,
"learning_rate": 1.0614272468404637e-05,
"loss": 0.8912,
"step": 452
},
{
"epoch": 0.4870967741935484,
"grad_norm": 1.0427286624908447,
"learning_rate": 1.0580185692841095e-05,
"loss": 0.9254,
"step": 453
},
{
"epoch": 0.4881720430107527,
"grad_norm": 0.968657910823822,
"learning_rate": 1.05460921519211e-05,
"loss": 0.8925,
"step": 454
},
{
"epoch": 0.489247311827957,
"grad_norm": 0.9973106980323792,
"learning_rate": 1.0511992243198335e-05,
"loss": 0.8594,
"step": 455
},
{
"epoch": 0.49032258064516127,
"grad_norm": 0.8644976019859314,
"learning_rate": 1.0477886364300722e-05,
"loss": 0.9359,
"step": 456
},
{
"epoch": 0.4913978494623656,
"grad_norm": 0.9711951017379761,
"learning_rate": 1.0443774912925814e-05,
"loss": 0.8896,
"step": 457
},
{
"epoch": 0.4924731182795699,
"grad_norm": 0.8667163848876953,
"learning_rate": 1.0409658286836144e-05,
"loss": 0.9817,
"step": 458
},
{
"epoch": 0.4935483870967742,
"grad_norm": 0.8854442238807678,
"learning_rate": 1.0375536883854575e-05,
"loss": 0.8869,
"step": 459
},
{
"epoch": 0.4946236559139785,
"grad_norm": 0.8985066413879395,
"learning_rate": 1.034141110185968e-05,
"loss": 0.8919,
"step": 460
},
{
"epoch": 0.4956989247311828,
"grad_norm": 0.8306286931037903,
"learning_rate": 1.0307281338781092e-05,
"loss": 0.9197,
"step": 461
},
{
"epoch": 0.4967741935483871,
"grad_norm": 0.8850293755531311,
"learning_rate": 1.0273147992594861e-05,
"loss": 0.8781,
"step": 462
},
{
"epoch": 0.4978494623655914,
"grad_norm": 0.8463788032531738,
"learning_rate": 1.0239011461318827e-05,
"loss": 0.9323,
"step": 463
},
{
"epoch": 0.4989247311827957,
"grad_norm": 0.9025292992591858,
"learning_rate": 1.0204872143007965e-05,
"loss": 0.9365,
"step": 464
},
{
"epoch": 0.5,
"grad_norm": 0.8844058513641357,
"learning_rate": 1.017073043574975e-05,
"loss": 0.8897,
"step": 465
},
{
"epoch": 0.5010752688172043,
"grad_norm": 0.9002809524536133,
"learning_rate": 1.013658673765951e-05,
"loss": 0.8773,
"step": 466
},
{
"epoch": 0.5010752688172043,
"eval_loss": 0.8080702424049377,
"eval_runtime": 241.1163,
"eval_samples_per_second": 11.546,
"eval_steps_per_second": 0.481,
"step": 466
},
{
"epoch": 0.5021505376344086,
"grad_norm": 0.9127078056335449,
"learning_rate": 1.0102441446875801e-05,
"loss": 0.9209,
"step": 467
},
{
"epoch": 0.5032258064516129,
"grad_norm": 0.9291108846664429,
"learning_rate": 1.0068294961555734e-05,
"loss": 0.9451,
"step": 468
},
{
"epoch": 0.5043010752688172,
"grad_norm": 0.9335411190986633,
"learning_rate": 1.0034147679870356e-05,
"loss": 0.8707,
"step": 469
},
{
"epoch": 0.5053763440860215,
"grad_norm": 1.0403931140899658,
"learning_rate": 1e-05,
"loss": 0.8727,
"step": 470
},
{
"epoch": 0.5064516129032258,
"grad_norm": 0.9628621935844421,
"learning_rate": 9.965852320129646e-06,
"loss": 0.9089,
"step": 471
},
{
"epoch": 0.5075268817204301,
"grad_norm": 0.8969815373420715,
"learning_rate": 9.93170503844427e-06,
"loss": 0.891,
"step": 472
},
{
"epoch": 0.5086021505376344,
"grad_norm": 0.9003312587738037,
"learning_rate": 9.897558553124202e-06,
"loss": 0.9265,
"step": 473
},
{
"epoch": 0.5096774193548387,
"grad_norm": 0.8279120922088623,
"learning_rate": 9.863413262340491e-06,
"loss": 0.9122,
"step": 474
},
{
"epoch": 0.510752688172043,
"grad_norm": 0.9585661888122559,
"learning_rate": 9.829269564250254e-06,
"loss": 0.9025,
"step": 475
},
{
"epoch": 0.5118279569892473,
"grad_norm": 0.906315267086029,
"learning_rate": 9.79512785699204e-06,
"loss": 0.9445,
"step": 476
},
{
"epoch": 0.5129032258064516,
"grad_norm": 0.86076420545578,
"learning_rate": 9.760988538681176e-06,
"loss": 0.9392,
"step": 477
},
{
"epoch": 0.513978494623656,
"grad_norm": 0.8743923902511597,
"learning_rate": 9.726852007405144e-06,
"loss": 0.9016,
"step": 478
},
{
"epoch": 0.5150537634408602,
"grad_norm": 1.0092248916625977,
"learning_rate": 9.692718661218912e-06,
"loss": 0.8621,
"step": 479
},
{
"epoch": 0.5161290322580645,
"grad_norm": 0.8339441418647766,
"learning_rate": 9.658588898140322e-06,
"loss": 0.9196,
"step": 480
},
{
"epoch": 0.5172043010752688,
"grad_norm": 0.9604438543319702,
"learning_rate": 9.624463116145428e-06,
"loss": 0.9051,
"step": 481
},
{
"epoch": 0.5182795698924731,
"grad_norm": 0.9511142373085022,
"learning_rate": 9.590341713163858e-06,
"loss": 0.9259,
"step": 482
},
{
"epoch": 0.5193548387096775,
"grad_norm": 0.9032608866691589,
"learning_rate": 9.55622508707419e-06,
"loss": 0.8866,
"step": 483
},
{
"epoch": 0.5204301075268817,
"grad_norm": 0.84687340259552,
"learning_rate": 9.522113635699281e-06,
"loss": 0.9221,
"step": 484
},
{
"epoch": 0.521505376344086,
"grad_norm": 0.9060841202735901,
"learning_rate": 9.488007756801672e-06,
"loss": 0.8699,
"step": 485
},
{
"epoch": 0.5225806451612903,
"grad_norm": 1.0113224983215332,
"learning_rate": 9.453907848078901e-06,
"loss": 0.8556,
"step": 486
},
{
"epoch": 0.5236559139784946,
"grad_norm": 0.9846504926681519,
"learning_rate": 9.419814307158908e-06,
"loss": 0.8768,
"step": 487
},
{
"epoch": 0.524731182795699,
"grad_norm": 1.0450615882873535,
"learning_rate": 9.385727531595367e-06,
"loss": 0.841,
"step": 488
},
{
"epoch": 0.5258064516129032,
"grad_norm": 0.9559835195541382,
"learning_rate": 9.35164791886307e-06,
"loss": 0.8999,
"step": 489
},
{
"epoch": 0.5268817204301075,
"grad_norm": 1.0124439001083374,
"learning_rate": 9.317575866353293e-06,
"loss": 0.8727,
"step": 490
},
{
"epoch": 0.5279569892473118,
"grad_norm": 0.8743895292282104,
"learning_rate": 9.283511771369132e-06,
"loss": 0.884,
"step": 491
},
{
"epoch": 0.5290322580645161,
"grad_norm": 1.0142030715942383,
"learning_rate": 9.249456031120922e-06,
"loss": 0.9232,
"step": 492
},
{
"epoch": 0.5301075268817205,
"grad_norm": 0.8965379595756531,
"learning_rate": 9.215409042721553e-06,
"loss": 0.9123,
"step": 493
},
{
"epoch": 0.5311827956989247,
"grad_norm": 0.8908298015594482,
"learning_rate": 9.181371203181873e-06,
"loss": 0.9218,
"step": 494
},
{
"epoch": 0.532258064516129,
"grad_norm": 0.9260167479515076,
"learning_rate": 9.14734290940604e-06,
"loss": 0.9393,
"step": 495
},
{
"epoch": 0.5333333333333333,
"grad_norm": 0.86910080909729,
"learning_rate": 9.113324558186922e-06,
"loss": 0.9093,
"step": 496
},
{
"epoch": 0.5344086021505376,
"grad_norm": 0.9058336615562439,
"learning_rate": 9.07931654620142e-06,
"loss": 0.8892,
"step": 497
},
{
"epoch": 0.535483870967742,
"grad_norm": 0.9350973963737488,
"learning_rate": 9.0453192700059e-06,
"loss": 0.9123,
"step": 498
},
{
"epoch": 0.5365591397849462,
"grad_norm": 0.889754056930542,
"learning_rate": 9.011333126031526e-06,
"loss": 0.8924,
"step": 499
},
{
"epoch": 0.5376344086021505,
"grad_norm": 0.949856162071228,
"learning_rate": 8.977358510579658e-06,
"loss": 0.8427,
"step": 500
},
{
"epoch": 0.5387096774193548,
"grad_norm": 0.8923821449279785,
"learning_rate": 8.943395819817226e-06,
"loss": 0.9231,
"step": 501
},
{
"epoch": 0.5397849462365591,
"grad_norm": 1.030486822128296,
"learning_rate": 8.909445449772103e-06,
"loss": 0.8475,
"step": 502
},
{
"epoch": 0.5408602150537635,
"grad_norm": 1.0622977018356323,
"learning_rate": 8.875507796328509e-06,
"loss": 0.8469,
"step": 503
},
{
"epoch": 0.5419354838709678,
"grad_norm": 0.9633312225341797,
"learning_rate": 8.841583255222359e-06,
"loss": 0.8952,
"step": 504
},
{
"epoch": 0.543010752688172,
"grad_norm": 0.9589855670928955,
"learning_rate": 8.807672222036692e-06,
"loss": 0.8869,
"step": 505
},
{
"epoch": 0.5440860215053763,
"grad_norm": 0.9809610843658447,
"learning_rate": 8.773775092197018e-06,
"loss": 0.8571,
"step": 506
},
{
"epoch": 0.5451612903225806,
"grad_norm": 1.1358520984649658,
"learning_rate": 8.73989226096673e-06,
"loss": 0.8433,
"step": 507
},
{
"epoch": 0.546236559139785,
"grad_norm": 0.9888678193092346,
"learning_rate": 8.706024123442497e-06,
"loss": 0.8635,
"step": 508
},
{
"epoch": 0.5473118279569893,
"grad_norm": 1.0114792585372925,
"learning_rate": 8.672171074549637e-06,
"loss": 0.8879,
"step": 509
},
{
"epoch": 0.5483870967741935,
"grad_norm": 0.9216302037239075,
"learning_rate": 8.638333509037537e-06,
"loss": 0.8967,
"step": 510
},
{
"epoch": 0.5494623655913978,
"grad_norm": 0.9108251929283142,
"learning_rate": 8.604511821475021e-06,
"loss": 0.9245,
"step": 511
},
{
"epoch": 0.5505376344086022,
"grad_norm": 0.9983306527137756,
"learning_rate": 8.570706406245787e-06,
"loss": 0.8908,
"step": 512
},
{
"epoch": 0.5516129032258065,
"grad_norm": 0.996141791343689,
"learning_rate": 8.536917657543767e-06,
"loss": 0.9281,
"step": 513
},
{
"epoch": 0.5526881720430108,
"grad_norm": 0.9432565569877625,
"learning_rate": 8.503145969368562e-06,
"loss": 0.9435,
"step": 514
},
{
"epoch": 0.553763440860215,
"grad_norm": 0.9987965226173401,
"learning_rate": 8.469391735520824e-06,
"loss": 0.8568,
"step": 515
},
{
"epoch": 0.5548387096774193,
"grad_norm": 0.8919755220413208,
"learning_rate": 8.43565534959769e-06,
"loss": 0.9074,
"step": 516
},
{
"epoch": 0.5559139784946237,
"grad_norm": 1.0158838033676147,
"learning_rate": 8.401937204988175e-06,
"loss": 0.8527,
"step": 517
},
{
"epoch": 0.556989247311828,
"grad_norm": 1.0149086713790894,
"learning_rate": 8.36823769486858e-06,
"loss": 0.838,
"step": 518
},
{
"epoch": 0.5580645161290323,
"grad_norm": 0.9243462681770325,
"learning_rate": 8.33455721219792e-06,
"loss": 0.9201,
"step": 519
},
{
"epoch": 0.5591397849462365,
"grad_norm": 0.9948527812957764,
"learning_rate": 8.300896149713334e-06,
"loss": 0.9512,
"step": 520
},
{
"epoch": 0.5602150537634408,
"grad_norm": 0.9152011275291443,
"learning_rate": 8.26725489992552e-06,
"loss": 0.9144,
"step": 521
},
{
"epoch": 0.5612903225806452,
"grad_norm": 1.0240675210952759,
"learning_rate": 8.233633855114127e-06,
"loss": 0.8597,
"step": 522
},
{
"epoch": 0.5623655913978495,
"grad_norm": 0.9682225584983826,
"learning_rate": 8.200033407323223e-06,
"loss": 0.88,
"step": 523
},
{
"epoch": 0.5634408602150538,
"grad_norm": 0.9406993389129639,
"learning_rate": 8.166453948356679e-06,
"loss": 0.9235,
"step": 524
},
{
"epoch": 0.5645161290322581,
"grad_norm": 1.0435328483581543,
"learning_rate": 8.132895869773638e-06,
"loss": 0.9093,
"step": 525
},
{
"epoch": 0.5655913978494623,
"grad_norm": 0.9654241800308228,
"learning_rate": 8.099359562883931e-06,
"loss": 0.9118,
"step": 526
},
{
"epoch": 0.5666666666666667,
"grad_norm": 0.9184148907661438,
"learning_rate": 8.065845418743504e-06,
"loss": 0.9209,
"step": 527
},
{
"epoch": 0.567741935483871,
"grad_norm": 0.9631726741790771,
"learning_rate": 8.032353828149889e-06,
"loss": 0.8759,
"step": 528
},
{
"epoch": 0.5688172043010753,
"grad_norm": 0.9072070717811584,
"learning_rate": 7.99888518163761e-06,
"loss": 0.8856,
"step": 529
},
{
"epoch": 0.5698924731182796,
"grad_norm": 0.9847999215126038,
"learning_rate": 7.965439869473664e-06,
"loss": 0.9003,
"step": 530
},
{
"epoch": 0.5709677419354838,
"grad_norm": 0.9502539038658142,
"learning_rate": 7.932018281652943e-06,
"loss": 0.9067,
"step": 531
},
{
"epoch": 0.5720430107526882,
"grad_norm": 0.9413378834724426,
"learning_rate": 7.898620807893698e-06,
"loss": 0.8469,
"step": 532
},
{
"epoch": 0.5731182795698925,
"grad_norm": 0.9912509322166443,
"learning_rate": 7.865247837633005e-06,
"loss": 0.8938,
"step": 533
},
{
"epoch": 0.5741935483870968,
"grad_norm": 1.0345542430877686,
"learning_rate": 7.831899760022192e-06,
"loss": 0.8418,
"step": 534
},
{
"epoch": 0.5752688172043011,
"grad_norm": 0.8752864003181458,
"learning_rate": 7.798576963922347e-06,
"loss": 0.9208,
"step": 535
},
{
"epoch": 0.5763440860215053,
"grad_norm": 0.9315550923347473,
"learning_rate": 7.76527983789973e-06,
"loss": 0.9092,
"step": 536
},
{
"epoch": 0.5774193548387097,
"grad_norm": 0.9463087320327759,
"learning_rate": 7.732008770221301e-06,
"loss": 0.8932,
"step": 537
},
{
"epoch": 0.578494623655914,
"grad_norm": 0.9277362823486328,
"learning_rate": 7.698764148850138e-06,
"loss": 0.8703,
"step": 538
},
{
"epoch": 0.5795698924731183,
"grad_norm": 0.8701269626617432,
"learning_rate": 7.66554636144095e-06,
"loss": 0.9303,
"step": 539
},
{
"epoch": 0.5806451612903226,
"grad_norm": 0.9152162075042725,
"learning_rate": 7.632355795335533e-06,
"loss": 0.9022,
"step": 540
},
{
"epoch": 0.5817204301075268,
"grad_norm": 0.9596089720726013,
"learning_rate": 7.5991928375582805e-06,
"loss": 0.8888,
"step": 541
},
{
"epoch": 0.5827956989247312,
"grad_norm": 0.9606913924217224,
"learning_rate": 7.566057874811643e-06,
"loss": 0.882,
"step": 542
},
{
"epoch": 0.5838709677419355,
"grad_norm": 0.90365070104599,
"learning_rate": 7.532951293471631e-06,
"loss": 0.9083,
"step": 543
},
{
"epoch": 0.5849462365591398,
"grad_norm": 1.0671300888061523,
"learning_rate": 7.499873479583312e-06,
"loss": 0.8924,
"step": 544
},
{
"epoch": 0.5860215053763441,
"grad_norm": 0.9826951622962952,
"learning_rate": 7.466824818856296e-06,
"loss": 0.9171,
"step": 545
},
{
"epoch": 0.5870967741935483,
"grad_norm": 0.9401928186416626,
"learning_rate": 7.433805696660267e-06,
"loss": 0.9013,
"step": 546
},
{
"epoch": 0.5881720430107527,
"grad_norm": 0.9318894147872925,
"learning_rate": 7.4008164980204455e-06,
"loss": 0.8928,
"step": 547
},
{
"epoch": 0.589247311827957,
"grad_norm": 0.9555893540382385,
"learning_rate": 7.367857607613147e-06,
"loss": 0.8951,
"step": 548
},
{
"epoch": 0.5903225806451613,
"grad_norm": 0.9515864849090576,
"learning_rate": 7.3349294097612515e-06,
"loss": 0.8946,
"step": 549
},
{
"epoch": 0.5913978494623656,
"grad_norm": 0.9463446140289307,
"learning_rate": 7.3020322884297565e-06,
"loss": 0.8968,
"step": 550
},
{
"epoch": 0.5924731182795699,
"grad_norm": 0.9150295257568359,
"learning_rate": 7.269166627221288e-06,
"loss": 0.8985,
"step": 551
},
{
"epoch": 0.5935483870967742,
"grad_norm": 0.9752622842788696,
"learning_rate": 7.236332809371609e-06,
"loss": 0.8772,
"step": 552
},
{
"epoch": 0.5946236559139785,
"grad_norm": 0.978859543800354,
"learning_rate": 7.20353121774519e-06,
"loss": 0.8428,
"step": 553
},
{
"epoch": 0.5956989247311828,
"grad_norm": 1.0362200736999512,
"learning_rate": 7.1707622348307e-06,
"loss": 0.9033,
"step": 554
},
{
"epoch": 0.5967741935483871,
"grad_norm": 0.8912584781646729,
"learning_rate": 7.1380262427365885e-06,
"loss": 0.9208,
"step": 555
},
{
"epoch": 0.5978494623655914,
"grad_norm": 0.9754722118377686,
"learning_rate": 7.105323623186595e-06,
"loss": 0.8981,
"step": 556
},
{
"epoch": 0.5989247311827957,
"grad_norm": 1.003328561782837,
"learning_rate": 7.072654757515321e-06,
"loss": 0.8874,
"step": 557
},
{
"epoch": 0.6,
"grad_norm": 0.9966676235198975,
"learning_rate": 7.040020026663767e-06,
"loss": 0.9093,
"step": 558
},
{
"epoch": 0.6010752688172043,
"grad_norm": 0.9583764672279358,
"learning_rate": 7.007419811174907e-06,
"loss": 0.9144,
"step": 559
},
{
"epoch": 0.6021505376344086,
"grad_norm": 0.9645876884460449,
"learning_rate": 6.974854491189243e-06,
"loss": 0.8827,
"step": 560
},
{
"epoch": 0.603225806451613,
"grad_norm": 0.9542210698127747,
"learning_rate": 6.94232444644036e-06,
"loss": 0.8877,
"step": 561
},
{
"epoch": 0.6043010752688172,
"grad_norm": 1.0281572341918945,
"learning_rate": 6.909830056250527e-06,
"loss": 0.8761,
"step": 562
},
{
"epoch": 0.6053763440860215,
"grad_norm": 0.9534195065498352,
"learning_rate": 6.877371699526241e-06,
"loss": 0.8991,
"step": 563
},
{
"epoch": 0.6064516129032258,
"grad_norm": 0.9893036484718323,
"learning_rate": 6.844949754753833e-06,
"loss": 0.8753,
"step": 564
},
{
"epoch": 0.6075268817204301,
"grad_norm": 0.9432750344276428,
"learning_rate": 6.812564599995042e-06,
"loss": 0.925,
"step": 565
},
{
"epoch": 0.6086021505376344,
"grad_norm": 0.954412579536438,
"learning_rate": 6.78021661288262e-06,
"loss": 0.8825,
"step": 566
},
{
"epoch": 0.6096774193548387,
"grad_norm": 0.8994936943054199,
"learning_rate": 6.7479061706159034e-06,
"loss": 0.9371,
"step": 567
},
{
"epoch": 0.610752688172043,
"grad_norm": 0.9021198153495789,
"learning_rate": 6.715633649956444e-06,
"loss": 0.8811,
"step": 568
},
{
"epoch": 0.6118279569892473,
"grad_norm": 0.9786022901535034,
"learning_rate": 6.683399427223598e-06,
"loss": 0.8681,
"step": 569
},
{
"epoch": 0.6129032258064516,
"grad_norm": 1.0326224565505981,
"learning_rate": 6.651203878290139e-06,
"loss": 0.8406,
"step": 570
},
{
"epoch": 0.613978494623656,
"grad_norm": 0.9551198482513428,
"learning_rate": 6.619047378577883e-06,
"loss": 0.8975,
"step": 571
},
{
"epoch": 0.6150537634408603,
"grad_norm": 0.8866798281669617,
"learning_rate": 6.586930303053297e-06,
"loss": 0.8914,
"step": 572
},
{
"epoch": 0.6161290322580645,
"grad_norm": 0.9743491411209106,
"learning_rate": 6.554853026223149e-06,
"loss": 0.8871,
"step": 573
},
{
"epoch": 0.6172043010752688,
"grad_norm": 0.9986077547073364,
"learning_rate": 6.522815922130112e-06,
"loss": 0.9049,
"step": 574
},
{
"epoch": 0.6182795698924731,
"grad_norm": 1.0726540088653564,
"learning_rate": 6.490819364348434e-06,
"loss": 0.8759,
"step": 575
},
{
"epoch": 0.6193548387096774,
"grad_norm": 1.0001327991485596,
"learning_rate": 6.458863725979549e-06,
"loss": 0.8812,
"step": 576
},
{
"epoch": 0.6204301075268818,
"grad_norm": 0.860525369644165,
"learning_rate": 6.426949379647755e-06,
"loss": 0.8316,
"step": 577
},
{
"epoch": 0.621505376344086,
"grad_norm": 0.9693924784660339,
"learning_rate": 6.395076697495854e-06,
"loss": 0.8581,
"step": 578
},
{
"epoch": 0.6225806451612903,
"grad_norm": 1.0345405340194702,
"learning_rate": 6.363246051180812e-06,
"loss": 0.8673,
"step": 579
},
{
"epoch": 0.6236559139784946,
"grad_norm": 0.894782543182373,
"learning_rate": 6.331457811869437e-06,
"loss": 0.9318,
"step": 580
},
{
"epoch": 0.624731182795699,
"grad_norm": 0.9780985116958618,
"learning_rate": 6.2997123502340286e-06,
"loss": 0.7838,
"step": 581
},
{
"epoch": 0.6258064516129033,
"grad_norm": 0.9211633801460266,
"learning_rate": 6.2680100364480876e-06,
"loss": 0.9141,
"step": 582
},
{
"epoch": 0.6268817204301075,
"grad_norm": 1.0366703271865845,
"learning_rate": 6.236351240181967e-06,
"loss": 0.8726,
"step": 583
},
{
"epoch": 0.6279569892473118,
"grad_norm": 1.0116140842437744,
"learning_rate": 6.204736330598585e-06,
"loss": 0.8964,
"step": 584
},
{
"epoch": 0.6290322580645161,
"grad_norm": 0.9604509472846985,
"learning_rate": 6.173165676349103e-06,
"loss": 0.9338,
"step": 585
},
{
"epoch": 0.6301075268817204,
"grad_norm": 1.0354490280151367,
"learning_rate": 6.141639645568646e-06,
"loss": 0.895,
"step": 586
},
{
"epoch": 0.6311827956989248,
"grad_norm": 1.0494648218154907,
"learning_rate": 6.110158605871994e-06,
"loss": 0.8726,
"step": 587
},
{
"epoch": 0.632258064516129,
"grad_norm": 1.0010687112808228,
"learning_rate": 6.0787229243493e-06,
"loss": 0.8815,
"step": 588
},
{
"epoch": 0.6333333333333333,
"grad_norm": 1.0460788011550903,
"learning_rate": 6.047332967561809e-06,
"loss": 0.8739,
"step": 589
},
{
"epoch": 0.6344086021505376,
"grad_norm": 0.9111729860305786,
"learning_rate": 6.015989101537586e-06,
"loss": 0.8874,
"step": 590
},
{
"epoch": 0.635483870967742,
"grad_norm": 0.9480916261672974,
"learning_rate": 5.984691691767252e-06,
"loss": 0.8739,
"step": 591
},
{
"epoch": 0.6365591397849463,
"grad_norm": 0.9860565066337585,
"learning_rate": 5.953441103199704e-06,
"loss": 0.8724,
"step": 592
},
{
"epoch": 0.6376344086021506,
"grad_norm": 0.9200236201286316,
"learning_rate": 5.922237700237887e-06,
"loss": 0.8974,
"step": 593
},
{
"epoch": 0.6387096774193548,
"grad_norm": 1.0478520393371582,
"learning_rate": 5.891081846734519e-06,
"loss": 0.8654,
"step": 594
},
{
"epoch": 0.6397849462365591,
"grad_norm": 0.9680602550506592,
"learning_rate": 5.859973905987866e-06,
"loss": 0.9025,
"step": 595
},
{
"epoch": 0.6408602150537634,
"grad_norm": 1.0783361196517944,
"learning_rate": 5.828914240737496e-06,
"loss": 0.8894,
"step": 596
},
{
"epoch": 0.6419354838709678,
"grad_norm": 1.1557034254074097,
"learning_rate": 5.797903213160047e-06,
"loss": 0.9288,
"step": 597
},
{
"epoch": 0.6430107526881721,
"grad_norm": 0.9906182289123535,
"learning_rate": 5.766941184865024e-06,
"loss": 0.8832,
"step": 598
},
{
"epoch": 0.6440860215053763,
"grad_norm": 1.0977959632873535,
"learning_rate": 5.736028516890548e-06,
"loss": 0.8604,
"step": 599
},
{
"epoch": 0.6451612903225806,
"grad_norm": 0.9982092380523682,
"learning_rate": 5.7051655696991825e-06,
"loss": 0.9022,
"step": 600
},
{
"epoch": 0.646236559139785,
"grad_norm": 0.9859678149223328,
"learning_rate": 5.6743527031737e-06,
"loss": 0.8692,
"step": 601
},
{
"epoch": 0.6473118279569893,
"grad_norm": 1.0263206958770752,
"learning_rate": 5.643590276612909e-06,
"loss": 0.9302,
"step": 602
},
{
"epoch": 0.6483870967741936,
"grad_norm": 0.8961809873580933,
"learning_rate": 5.612878648727444e-06,
"loss": 0.9261,
"step": 603
},
{
"epoch": 0.6494623655913978,
"grad_norm": 1.0333125591278076,
"learning_rate": 5.582218177635607e-06,
"loss": 0.8615,
"step": 604
},
{
"epoch": 0.6505376344086021,
"grad_norm": 0.9634983539581299,
"learning_rate": 5.55160922085916e-06,
"loss": 0.8879,
"step": 605
},
{
"epoch": 0.6516129032258065,
"grad_norm": 1.1239064931869507,
"learning_rate": 5.521052135319182e-06,
"loss": 0.8164,
"step": 606
},
{
"epoch": 0.6526881720430108,
"grad_norm": 0.9737497568130493,
"learning_rate": 5.490547277331904e-06,
"loss": 0.9079,
"step": 607
},
{
"epoch": 0.6537634408602151,
"grad_norm": 1.053808569908142,
"learning_rate": 5.460095002604533e-06,
"loss": 0.8461,
"step": 608
},
{
"epoch": 0.6548387096774193,
"grad_norm": 0.9344451427459717,
"learning_rate": 5.429695666231141e-06,
"loss": 0.9008,
"step": 609
},
{
"epoch": 0.6559139784946236,
"grad_norm": 1.06412672996521,
"learning_rate": 5.399349622688479e-06,
"loss": 0.8795,
"step": 610
},
{
"epoch": 0.656989247311828,
"grad_norm": 0.9756316542625427,
"learning_rate": 5.369057225831893e-06,
"loss": 0.9081,
"step": 611
},
{
"epoch": 0.6580645161290323,
"grad_norm": 1.004437804222107,
"learning_rate": 5.338818828891148e-06,
"loss": 0.9095,
"step": 612
},
{
"epoch": 0.6591397849462366,
"grad_norm": 1.0311338901519775,
"learning_rate": 5.308634784466349e-06,
"loss": 0.8887,
"step": 613
},
{
"epoch": 0.6602150537634408,
"grad_norm": 0.9663563370704651,
"learning_rate": 5.2785054445238156e-06,
"loss": 0.8774,
"step": 614
},
{
"epoch": 0.6612903225806451,
"grad_norm": 1.0709410905838013,
"learning_rate": 5.248431160391963e-06,
"loss": 0.8699,
"step": 615
},
{
"epoch": 0.6623655913978495,
"grad_norm": 1.000380277633667,
"learning_rate": 5.2184122827572315e-06,
"loss": 0.9126,
"step": 616
},
{
"epoch": 0.6634408602150538,
"grad_norm": 1.0107392072677612,
"learning_rate": 5.188449161659978e-06,
"loss": 0.9067,
"step": 617
},
{
"epoch": 0.6645161290322581,
"grad_norm": 1.0179517269134521,
"learning_rate": 5.1585421464904e-06,
"loss": 0.8486,
"step": 618
},
{
"epoch": 0.6655913978494624,
"grad_norm": 0.9806568622589111,
"learning_rate": 5.12869158598446e-06,
"loss": 0.8918,
"step": 619
},
{
"epoch": 0.6666666666666666,
"grad_norm": 1.0624562501907349,
"learning_rate": 5.098897828219831e-06,
"loss": 0.875,
"step": 620
},
{
"epoch": 0.667741935483871,
"grad_norm": 1.0656713247299194,
"learning_rate": 5.069161220611818e-06,
"loss": 0.8999,
"step": 621
},
{
"epoch": 0.6688172043010753,
"grad_norm": 1.0987064838409424,
"learning_rate": 5.0394821099093195e-06,
"loss": 0.8594,
"step": 622
},
{
"epoch": 0.6698924731182796,
"grad_norm": 1.0532398223876953,
"learning_rate": 5.009860842190787e-06,
"loss": 0.8575,
"step": 623
},
{
"epoch": 0.6709677419354839,
"grad_norm": 0.9223129153251648,
"learning_rate": 4.980297762860171e-06,
"loss": 0.9127,
"step": 624
},
{
"epoch": 0.6720430107526881,
"grad_norm": 1.0524375438690186,
"learning_rate": 4.950793216642923e-06,
"loss": 0.8778,
"step": 625
},
{
"epoch": 0.6731182795698925,
"grad_norm": 0.9768378138542175,
"learning_rate": 4.921347547581939e-06,
"loss": 0.8781,
"step": 626
},
{
"epoch": 0.6741935483870968,
"grad_norm": 0.9231652021408081,
"learning_rate": 4.891961099033589e-06,
"loss": 0.9115,
"step": 627
},
{
"epoch": 0.6752688172043011,
"grad_norm": 0.9717528223991394,
"learning_rate": 4.862634213663672e-06,
"loss": 0.9068,
"step": 628
},
{
"epoch": 0.6763440860215054,
"grad_norm": 1.0528284311294556,
"learning_rate": 4.833367233443457e-06,
"loss": 0.8647,
"step": 629
},
{
"epoch": 0.6774193548387096,
"grad_norm": 0.9975810647010803,
"learning_rate": 4.804160499645667e-06,
"loss": 0.8773,
"step": 630
},
{
"epoch": 0.678494623655914,
"grad_norm": 0.9192178845405579,
"learning_rate": 4.775014352840512e-06,
"loss": 0.8895,
"step": 631
},
{
"epoch": 0.6795698924731183,
"grad_norm": 1.0221238136291504,
"learning_rate": 4.7459291328917275e-06,
"loss": 0.8937,
"step": 632
},
{
"epoch": 0.6806451612903226,
"grad_norm": 1.0171881914138794,
"learning_rate": 4.7169051789525856e-06,
"loss": 0.8711,
"step": 633
},
{
"epoch": 0.6817204301075269,
"grad_norm": 0.9004276394844055,
"learning_rate": 4.687942829461969e-06,
"loss": 0.7798,
"step": 634
},
{
"epoch": 0.6827956989247311,
"grad_norm": 1.0783709287643433,
"learning_rate": 4.659042422140399e-06,
"loss": 0.8841,
"step": 635
},
{
"epoch": 0.6838709677419355,
"grad_norm": 0.9793049693107605,
"learning_rate": 4.630204293986122e-06,
"loss": 0.9068,
"step": 636
},
{
"epoch": 0.6849462365591398,
"grad_norm": 1.0510399341583252,
"learning_rate": 4.601428781271154e-06,
"loss": 0.921,
"step": 637
},
{
"epoch": 0.6860215053763441,
"grad_norm": 0.966804563999176,
"learning_rate": 4.572716219537386e-06,
"loss": 0.9267,
"step": 638
},
{
"epoch": 0.6870967741935484,
"grad_norm": 0.9800238013267517,
"learning_rate": 4.544066943592645e-06,
"loss": 0.8814,
"step": 639
},
{
"epoch": 0.6881720430107527,
"grad_norm": 0.9430668950080872,
"learning_rate": 4.515481287506811e-06,
"loss": 0.9247,
"step": 640
},
{
"epoch": 0.689247311827957,
"grad_norm": 0.9821351766586304,
"learning_rate": 4.486959584607919e-06,
"loss": 0.8631,
"step": 641
},
{
"epoch": 0.6903225806451613,
"grad_norm": 0.9794047474861145,
"learning_rate": 4.458502167478254e-06,
"loss": 0.899,
"step": 642
},
{
"epoch": 0.6913978494623656,
"grad_norm": 0.955868661403656,
"learning_rate": 4.430109367950488e-06,
"loss": 0.8784,
"step": 643
},
{
"epoch": 0.6924731182795699,
"grad_norm": 0.873094379901886,
"learning_rate": 4.401781517103819e-06,
"loss": 0.7778,
"step": 644
},
{
"epoch": 0.6935483870967742,
"grad_norm": 0.9053919315338135,
"learning_rate": 4.37351894526009e-06,
"loss": 0.8362,
"step": 645
},
{
"epoch": 0.6946236559139785,
"grad_norm": 1.0417245626449585,
"learning_rate": 4.345321981979942e-06,
"loss": 0.8229,
"step": 646
},
{
"epoch": 0.6956989247311828,
"grad_norm": 0.93317711353302,
"learning_rate": 4.31719095605899e-06,
"loss": 0.897,
"step": 647
},
{
"epoch": 0.6967741935483871,
"grad_norm": 0.9389287233352661,
"learning_rate": 4.289126195523968e-06,
"loss": 0.892,
"step": 648
},
{
"epoch": 0.6978494623655914,
"grad_norm": 0.936539351940155,
"learning_rate": 4.261128027628906e-06,
"loss": 0.8989,
"step": 649
},
{
"epoch": 0.6989247311827957,
"grad_norm": 1.0945050716400146,
"learning_rate": 4.2331967788513295e-06,
"loss": 0.8451,
"step": 650
},
{
"epoch": 0.7,
"grad_norm": 1.003908395767212,
"learning_rate": 4.20533277488843e-06,
"loss": 0.8652,
"step": 651
},
{
"epoch": 0.7010752688172043,
"grad_norm": 0.9572248458862305,
"learning_rate": 4.177536340653291e-06,
"loss": 0.8847,
"step": 652
},
{
"epoch": 0.7021505376344086,
"grad_norm": 0.9244607090950012,
"learning_rate": 4.149807800271075e-06,
"loss": 0.7855,
"step": 653
},
{
"epoch": 0.7032258064516129,
"grad_norm": 1.0144091844558716,
"learning_rate": 4.12214747707527e-06,
"loss": 0.9042,
"step": 654
},
{
"epoch": 0.7043010752688172,
"grad_norm": 1.0786426067352295,
"learning_rate": 4.094555693603891e-06,
"loss": 0.8647,
"step": 655
},
{
"epoch": 0.7053763440860215,
"grad_norm": 1.0761374235153198,
"learning_rate": 4.067032771595749e-06,
"loss": 0.8165,
"step": 656
},
{
"epoch": 0.7064516129032258,
"grad_norm": 0.9577154517173767,
"learning_rate": 4.039579031986672e-06,
"loss": 0.8688,
"step": 657
},
{
"epoch": 0.7075268817204301,
"grad_norm": 0.9912071228027344,
"learning_rate": 4.0121947949057745e-06,
"loss": 0.8915,
"step": 658
},
{
"epoch": 0.7086021505376344,
"grad_norm": 0.9261897206306458,
"learning_rate": 3.9848803796717385e-06,
"loss": 0.9261,
"step": 659
},
{
"epoch": 0.7096774193548387,
"grad_norm": 0.9974510073661804,
"learning_rate": 3.957636104789056e-06,
"loss": 0.9204,
"step": 660
},
{
"epoch": 0.710752688172043,
"grad_norm": 1.0481423139572144,
"learning_rate": 3.930462287944354e-06,
"loss": 0.8695,
"step": 661
},
{
"epoch": 0.7118279569892473,
"grad_norm": 0.901894211769104,
"learning_rate": 3.903359246002655e-06,
"loss": 0.916,
"step": 662
},
{
"epoch": 0.7129032258064516,
"grad_norm": 1.0383106470108032,
"learning_rate": 3.876327295003716e-06,
"loss": 0.8709,
"step": 663
},
{
"epoch": 0.7139784946236559,
"grad_norm": 1.1252386569976807,
"learning_rate": 3.849366750158305e-06,
"loss": 0.8917,
"step": 664
},
{
"epoch": 0.7150537634408602,
"grad_norm": 0.9972463846206665,
"learning_rate": 3.822477925844564e-06,
"loss": 0.8683,
"step": 665
},
{
"epoch": 0.7161290322580646,
"grad_norm": 1.0251529216766357,
"learning_rate": 3.7956611356043196e-06,
"loss": 0.889,
"step": 666
},
{
"epoch": 0.7172043010752688,
"grad_norm": 0.9553551077842712,
"learning_rate": 3.768916692139426e-06,
"loss": 0.8807,
"step": 667
},
{
"epoch": 0.7182795698924731,
"grad_norm": 0.9973981976509094,
"learning_rate": 3.7422449073081356e-06,
"loss": 0.906,
"step": 668
},
{
"epoch": 0.7193548387096774,
"grad_norm": 1.014689564704895,
"learning_rate": 3.715646092121444e-06,
"loss": 0.8588,
"step": 669
},
{
"epoch": 0.7204301075268817,
"grad_norm": 1.0839016437530518,
"learning_rate": 3.689120556739475e-06,
"loss": 0.8402,
"step": 670
},
{
"epoch": 0.7215053763440861,
"grad_norm": 1.1042214632034302,
"learning_rate": 3.6626686104678565e-06,
"loss": 0.8552,
"step": 671
},
{
"epoch": 0.7225806451612903,
"grad_norm": 0.956203043460846,
"learning_rate": 3.6362905617541276e-06,
"loss": 0.895,
"step": 672
},
{
"epoch": 0.7236559139784946,
"grad_norm": 1.0225743055343628,
"learning_rate": 3.6099867181841188e-06,
"loss": 0.8946,
"step": 673
},
{
"epoch": 0.7247311827956989,
"grad_norm": 1.0949145555496216,
"learning_rate": 3.583757386478389e-06,
"loss": 0.8293,
"step": 674
},
{
"epoch": 0.7258064516129032,
"grad_norm": 0.9770424962043762,
"learning_rate": 3.557602872488638e-06,
"loss": 0.8798,
"step": 675
},
{
"epoch": 0.7268817204301076,
"grad_norm": 1.0102465152740479,
"learning_rate": 3.53152348119413e-06,
"loss": 0.8777,
"step": 676
},
{
"epoch": 0.7279569892473118,
"grad_norm": 0.9756696224212646,
"learning_rate": 3.505519516698165e-06,
"loss": 0.9019,
"step": 677
},
{
"epoch": 0.7290322580645161,
"grad_norm": 1.1217525005340576,
"learning_rate": 3.479591282224496e-06,
"loss": 0.8504,
"step": 678
},
{
"epoch": 0.7301075268817204,
"grad_norm": 0.9998635053634644,
"learning_rate": 3.4537390801138306e-06,
"loss": 0.7564,
"step": 679
},
{
"epoch": 0.7311827956989247,
"grad_norm": 1.1241053342819214,
"learning_rate": 3.4279632118202744e-06,
"loss": 0.8806,
"step": 680
},
{
"epoch": 0.7322580645161291,
"grad_norm": 0.9840561151504517,
"learning_rate": 3.4022639779078403e-06,
"loss": 0.8893,
"step": 681
},
{
"epoch": 0.7333333333333333,
"grad_norm": 0.9647068977355957,
"learning_rate": 3.376641678046926e-06,
"loss": 0.8661,
"step": 682
},
{
"epoch": 0.7344086021505376,
"grad_norm": 1.043853998184204,
"learning_rate": 3.3510966110108213e-06,
"loss": 0.8963,
"step": 683
},
{
"epoch": 0.7354838709677419,
"grad_norm": 1.0099283456802368,
"learning_rate": 3.325629074672244e-06,
"loss": 0.8752,
"step": 684
},
{
"epoch": 0.7365591397849462,
"grad_norm": 1.0153430700302124,
"learning_rate": 3.3002393659998357e-06,
"loss": 0.9404,
"step": 685
},
{
"epoch": 0.7376344086021506,
"grad_norm": 0.987329363822937,
"learning_rate": 3.2749277810547286e-06,
"loss": 0.8663,
"step": 686
},
{
"epoch": 0.7387096774193549,
"grad_norm": 1.0522453784942627,
"learning_rate": 3.249694614987068e-06,
"loss": 0.875,
"step": 687
},
{
"epoch": 0.7397849462365591,
"grad_norm": 1.0339679718017578,
"learning_rate": 3.2245401620325934e-06,
"loss": 0.8648,
"step": 688
},
{
"epoch": 0.7408602150537634,
"grad_norm": 1.144313931465149,
"learning_rate": 3.199464715509183e-06,
"loss": 0.7979,
"step": 689
},
{
"epoch": 0.7419354838709677,
"grad_norm": 1.0547746419906616,
"learning_rate": 3.174468567813461e-06,
"loss": 0.8985,
"step": 690
},
{
"epoch": 0.7430107526881721,
"grad_norm": 0.990385890007019,
"learning_rate": 3.1495520104173603e-06,
"loss": 0.9123,
"step": 691
},
{
"epoch": 0.7440860215053764,
"grad_norm": 1.0328789949417114,
"learning_rate": 3.1247153338647486e-06,
"loss": 0.8739,
"step": 692
},
{
"epoch": 0.7451612903225806,
"grad_norm": 1.099030613899231,
"learning_rate": 3.099958827768025e-06,
"loss": 0.8441,
"step": 693
},
{
"epoch": 0.7462365591397849,
"grad_norm": 0.9660579562187195,
"learning_rate": 3.0752827808047446e-06,
"loss": 0.9012,
"step": 694
},
{
"epoch": 0.7473118279569892,
"grad_norm": 0.9739366173744202,
"learning_rate": 3.050687480714256e-06,
"loss": 0.8412,
"step": 695
},
{
"epoch": 0.7483870967741936,
"grad_norm": 1.058748483657837,
"learning_rate": 3.0261732142943435e-06,
"loss": 0.9002,
"step": 696
},
{
"epoch": 0.7494623655913979,
"grad_norm": 1.0254429578781128,
"learning_rate": 3.00174026739789e-06,
"loss": 0.8546,
"step": 697
},
{
"epoch": 0.7505376344086021,
"grad_norm": 1.0190998315811157,
"learning_rate": 2.9773889249295294e-06,
"loss": 0.8726,
"step": 698
},
{
"epoch": 0.7516129032258064,
"grad_norm": 1.057529330253601,
"learning_rate": 2.9531194708423428e-06,
"loss": 0.8962,
"step": 699
},
{
"epoch": 0.7516129032258064,
"eval_loss": 0.8028071522712708,
"eval_runtime": 240.7419,
"eval_samples_per_second": 11.564,
"eval_steps_per_second": 0.482,
"step": 699
},
{
"epoch": 0.7526881720430108,
"grad_norm": 1.0174949169158936,
"learning_rate": 2.9289321881345257e-06,
"loss": 0.9032,
"step": 700
},
{
"epoch": 0.7537634408602151,
"grad_norm": 1.0628769397735596,
"learning_rate": 2.9048273588461097e-06,
"loss": 0.8494,
"step": 701
},
{
"epoch": 0.7548387096774194,
"grad_norm": 0.9887354373931885,
"learning_rate": 2.8808052640556637e-06,
"loss": 0.7472,
"step": 702
},
{
"epoch": 0.7559139784946236,
"grad_norm": 0.9702305197715759,
"learning_rate": 2.8568661838770073e-06,
"loss": 0.8806,
"step": 703
},
{
"epoch": 0.7569892473118279,
"grad_norm": 0.9678685069084167,
"learning_rate": 2.8330103974559665e-06,
"loss": 0.8736,
"step": 704
},
{
"epoch": 0.7580645161290323,
"grad_norm": 1.0689879655838013,
"learning_rate": 2.809238182967092e-06,
"loss": 0.8909,
"step": 705
},
{
"epoch": 0.7591397849462366,
"grad_norm": 1.041756510734558,
"learning_rate": 2.7855498176104435e-06,
"loss": 0.8741,
"step": 706
},
{
"epoch": 0.7602150537634409,
"grad_norm": 1.1385363340377808,
"learning_rate": 2.761945577608334e-06,
"loss": 0.8897,
"step": 707
},
{
"epoch": 0.7612903225806451,
"grad_norm": 0.9872462749481201,
"learning_rate": 2.7384257382021185e-06,
"loss": 0.8893,
"step": 708
},
{
"epoch": 0.7623655913978494,
"grad_norm": 0.9995443224906921,
"learning_rate": 2.7149905736489846e-06,
"loss": 0.8745,
"step": 709
},
{
"epoch": 0.7634408602150538,
"grad_norm": 1.1389273405075073,
"learning_rate": 2.691640357218759e-06,
"loss": 0.8441,
"step": 710
},
{
"epoch": 0.7645161290322581,
"grad_norm": 0.9834983944892883,
"learning_rate": 2.668375361190716e-06,
"loss": 0.876,
"step": 711
},
{
"epoch": 0.7655913978494624,
"grad_norm": 1.0866228342056274,
"learning_rate": 2.645195856850391e-06,
"loss": 0.8391,
"step": 712
},
{
"epoch": 0.7666666666666667,
"grad_norm": 1.0782625675201416,
"learning_rate": 2.6221021144864444e-06,
"loss": 0.8789,
"step": 713
},
{
"epoch": 0.7677419354838709,
"grad_norm": 1.1091196537017822,
"learning_rate": 2.599094403387481e-06,
"loss": 0.8514,
"step": 714
},
{
"epoch": 0.7688172043010753,
"grad_norm": 1.0931015014648438,
"learning_rate": 2.576172991838933e-06,
"loss": 0.8657,
"step": 715
},
{
"epoch": 0.7698924731182796,
"grad_norm": 1.0916446447372437,
"learning_rate": 2.5533381471199138e-06,
"loss": 0.8847,
"step": 716
},
{
"epoch": 0.7709677419354839,
"grad_norm": 1.0096673965454102,
"learning_rate": 2.5305901355001152e-06,
"loss": 0.896,
"step": 717
},
{
"epoch": 0.7720430107526882,
"grad_norm": 0.9677090048789978,
"learning_rate": 2.5079292222366903e-06,
"loss": 0.9044,
"step": 718
},
{
"epoch": 0.7731182795698924,
"grad_norm": 0.9203047752380371,
"learning_rate": 2.485355671571175e-06,
"loss": 0.9017,
"step": 719
},
{
"epoch": 0.7741935483870968,
"grad_norm": 0.9744219779968262,
"learning_rate": 2.4628697467263916e-06,
"loss": 0.858,
"step": 720
},
{
"epoch": 0.7752688172043011,
"grad_norm": 1.0295017957687378,
"learning_rate": 2.4404717099033847e-06,
"loss": 0.885,
"step": 721
},
{
"epoch": 0.7763440860215054,
"grad_norm": 1.0058088302612305,
"learning_rate": 2.418161822278374e-06,
"loss": 0.896,
"step": 722
},
{
"epoch": 0.7774193548387097,
"grad_norm": 1.0643796920776367,
"learning_rate": 2.395940343999691e-06,
"loss": 0.9154,
"step": 723
},
{
"epoch": 0.7784946236559139,
"grad_norm": 1.031701922416687,
"learning_rate": 2.3738075341847634e-06,
"loss": 0.8866,
"step": 724
},
{
"epoch": 0.7795698924731183,
"grad_norm": 1.0520869493484497,
"learning_rate": 2.351763650917074e-06,
"loss": 0.8557,
"step": 725
},
{
"epoch": 0.7806451612903226,
"grad_norm": 1.026106595993042,
"learning_rate": 2.3298089512431744e-06,
"loss": 0.8788,
"step": 726
},
{
"epoch": 0.7817204301075269,
"grad_norm": 1.016325831413269,
"learning_rate": 2.3079436911696617e-06,
"loss": 0.8884,
"step": 727
},
{
"epoch": 0.7827956989247312,
"grad_norm": 1.1190268993377686,
"learning_rate": 2.2861681256602187e-06,
"loss": 0.856,
"step": 728
},
{
"epoch": 0.7838709677419354,
"grad_norm": 0.9312067031860352,
"learning_rate": 2.264482508632627e-06,
"loss": 0.8972,
"step": 729
},
{
"epoch": 0.7849462365591398,
"grad_norm": 1.1495349407196045,
"learning_rate": 2.2428870929558012e-06,
"loss": 0.8709,
"step": 730
},
{
"epoch": 0.7860215053763441,
"grad_norm": 1.1420360803604126,
"learning_rate": 2.2213821304468554e-06,
"loss": 0.8496,
"step": 731
},
{
"epoch": 0.7870967741935484,
"grad_norm": 1.0807099342346191,
"learning_rate": 2.199967871868154e-06,
"loss": 0.8572,
"step": 732
},
{
"epoch": 0.7881720430107527,
"grad_norm": 1.1299638748168945,
"learning_rate": 2.178644566924394e-06,
"loss": 0.8662,
"step": 733
},
{
"epoch": 0.789247311827957,
"grad_norm": 1.0073062181472778,
"learning_rate": 2.1574124642596882e-06,
"loss": 0.8924,
"step": 734
},
{
"epoch": 0.7903225806451613,
"grad_norm": 1.001193881034851,
"learning_rate": 2.1362718114546777e-06,
"loss": 0.8564,
"step": 735
},
{
"epoch": 0.7913978494623656,
"grad_norm": 0.9366834759712219,
"learning_rate": 2.1152228550236264e-06,
"loss": 0.8991,
"step": 736
},
{
"epoch": 0.7924731182795699,
"grad_norm": 1.0331993103027344,
"learning_rate": 2.0942658404115646e-06,
"loss": 0.9229,
"step": 737
},
{
"epoch": 0.7935483870967742,
"grad_norm": 1.0128207206726074,
"learning_rate": 2.0734010119914193e-06,
"loss": 0.8739,
"step": 738
},
{
"epoch": 0.7946236559139785,
"grad_norm": 0.9919546246528625,
"learning_rate": 2.052628613061154e-06,
"loss": 0.8879,
"step": 739
},
{
"epoch": 0.7956989247311828,
"grad_norm": 0.9642401933670044,
"learning_rate": 2.0319488858409552e-06,
"loss": 0.8813,
"step": 740
},
{
"epoch": 0.7967741935483871,
"grad_norm": 1.09434175491333,
"learning_rate": 2.011362071470384e-06,
"loss": 0.8467,
"step": 741
},
{
"epoch": 0.7978494623655914,
"grad_norm": 1.0729540586471558,
"learning_rate": 1.9908684100055843e-06,
"loss": 0.8745,
"step": 742
},
{
"epoch": 0.7989247311827957,
"grad_norm": 1.0908386707305908,
"learning_rate": 1.9704681404164637e-06,
"loss": 0.8573,
"step": 743
},
{
"epoch": 0.8,
"grad_norm": 0.9976701736450195,
"learning_rate": 1.95016150058393e-06,
"loss": 0.8977,
"step": 744
},
{
"epoch": 0.8010752688172043,
"grad_norm": 1.1222140789031982,
"learning_rate": 1.929948727297096e-06,
"loss": 0.8868,
"step": 745
},
{
"epoch": 0.8021505376344086,
"grad_norm": 0.9284682869911194,
"learning_rate": 1.9098300562505266e-06,
"loss": 0.8813,
"step": 746
},
{
"epoch": 0.8032258064516129,
"grad_norm": 1.050628662109375,
"learning_rate": 1.889805722041499e-06,
"loss": 0.7365,
"step": 747
},
{
"epoch": 0.8043010752688172,
"grad_norm": 1.0807946920394897,
"learning_rate": 1.8698759581672487e-06,
"loss": 0.8901,
"step": 748
},
{
"epoch": 0.8053763440860215,
"grad_norm": 1.083493947982788,
"learning_rate": 1.85004099702227e-06,
"loss": 0.8758,
"step": 749
},
{
"epoch": 0.8064516129032258,
"grad_norm": 1.1448321342468262,
"learning_rate": 1.8303010698955803e-06,
"loss": 0.8712,
"step": 750
},
{
"epoch": 0.8075268817204301,
"grad_norm": 1.0084006786346436,
"learning_rate": 1.8106564069680476e-06,
"loss": 0.866,
"step": 751
},
{
"epoch": 0.8086021505376344,
"grad_norm": 1.027698278427124,
"learning_rate": 1.791107237309685e-06,
"loss": 0.9034,
"step": 752
},
{
"epoch": 0.8096774193548387,
"grad_norm": 0.9917596578598022,
"learning_rate": 1.771653788876999e-06,
"loss": 0.8887,
"step": 753
},
{
"epoch": 0.810752688172043,
"grad_norm": 1.087314248085022,
"learning_rate": 1.7522962885103145e-06,
"loss": 0.8235,
"step": 754
},
{
"epoch": 0.8118279569892473,
"grad_norm": 1.2066447734832764,
"learning_rate": 1.7330349619311415e-06,
"loss": 0.8196,
"step": 755
},
{
"epoch": 0.8129032258064516,
"grad_norm": 1.0600000619888306,
"learning_rate": 1.713870033739541e-06,
"loss": 0.8673,
"step": 756
},
{
"epoch": 0.8139784946236559,
"grad_norm": 1.1086914539337158,
"learning_rate": 1.6948017274114959e-06,
"loss": 0.8774,
"step": 757
},
{
"epoch": 0.8150537634408602,
"grad_norm": 1.1460777521133423,
"learning_rate": 1.6758302652963176e-06,
"loss": 0.8987,
"step": 758
},
{
"epoch": 0.8161290322580645,
"grad_norm": 1.002736210823059,
"learning_rate": 1.656955868614053e-06,
"loss": 0.8779,
"step": 759
},
{
"epoch": 0.8172043010752689,
"grad_norm": 1.012317419052124,
"learning_rate": 1.638178757452894e-06,
"loss": 0.864,
"step": 760
},
{
"epoch": 0.8182795698924731,
"grad_norm": 1.0144654512405396,
"learning_rate": 1.6194991507666159e-06,
"loss": 0.9059,
"step": 761
},
{
"epoch": 0.8193548387096774,
"grad_norm": 0.9600997567176819,
"learning_rate": 1.6009172663720352e-06,
"loss": 0.889,
"step": 762
},
{
"epoch": 0.8204301075268817,
"grad_norm": 0.9644306898117065,
"learning_rate": 1.582433320946456e-06,
"loss": 0.8738,
"step": 763
},
{
"epoch": 0.821505376344086,
"grad_norm": 1.0256295204162598,
"learning_rate": 1.5640475300251423e-06,
"loss": 0.877,
"step": 764
},
{
"epoch": 0.8225806451612904,
"grad_norm": 1.060616135597229,
"learning_rate": 1.5457601079988226e-06,
"loss": 0.9018,
"step": 765
},
{
"epoch": 0.8236559139784946,
"grad_norm": 1.079298734664917,
"learning_rate": 1.5275712681111643e-06,
"loss": 0.8666,
"step": 766
},
{
"epoch": 0.8247311827956989,
"grad_norm": 1.1446715593338013,
"learning_rate": 1.5094812224563117e-06,
"loss": 0.8528,
"step": 767
},
{
"epoch": 0.8258064516129032,
"grad_norm": 1.057084560394287,
"learning_rate": 1.4914901819763938e-06,
"loss": 0.8398,
"step": 768
},
{
"epoch": 0.8268817204301075,
"grad_norm": 1.0480070114135742,
"learning_rate": 1.4735983564590784e-06,
"loss": 0.8905,
"step": 769
},
{
"epoch": 0.8279569892473119,
"grad_norm": 0.9545390605926514,
"learning_rate": 1.4558059545351144e-06,
"loss": 0.8528,
"step": 770
},
{
"epoch": 0.8290322580645161,
"grad_norm": 1.0012227296829224,
"learning_rate": 1.43811318367591e-06,
"loss": 0.8955,
"step": 771
},
{
"epoch": 0.8301075268817204,
"grad_norm": 1.0132238864898682,
"learning_rate": 1.4205202501911052e-06,
"loss": 0.8934,
"step": 772
},
{
"epoch": 0.8311827956989247,
"grad_norm": 1.0243781805038452,
"learning_rate": 1.4030273592261656e-06,
"loss": 0.891,
"step": 773
},
{
"epoch": 0.832258064516129,
"grad_norm": 1.0289664268493652,
"learning_rate": 1.3856347147600014e-06,
"loss": 0.8597,
"step": 774
},
{
"epoch": 0.8333333333333334,
"grad_norm": 1.0462311506271362,
"learning_rate": 1.3683425196025734e-06,
"loss": 0.8856,
"step": 775
},
{
"epoch": 0.8344086021505376,
"grad_norm": 1.0177634954452515,
"learning_rate": 1.3511509753925422e-06,
"loss": 0.853,
"step": 776
},
{
"epoch": 0.8354838709677419,
"grad_norm": 1.084958791732788,
"learning_rate": 1.3340602825949024e-06,
"loss": 0.8668,
"step": 777
},
{
"epoch": 0.8365591397849462,
"grad_norm": 0.9712878465652466,
"learning_rate": 1.3170706404986645e-06,
"loss": 0.916,
"step": 778
},
{
"epoch": 0.8376344086021505,
"grad_norm": 1.0489739179611206,
"learning_rate": 1.3001822472145066e-06,
"loss": 0.8668,
"step": 779
},
{
"epoch": 0.8387096774193549,
"grad_norm": 1.0077139139175415,
"learning_rate": 1.2833952996724864e-06,
"loss": 0.8885,
"step": 780
},
{
"epoch": 0.8397849462365592,
"grad_norm": 1.1088800430297852,
"learning_rate": 1.266709993619737e-06,
"loss": 0.9051,
"step": 781
},
{
"epoch": 0.8408602150537634,
"grad_norm": 0.9531431198120117,
"learning_rate": 1.2501265236181736e-06,
"loss": 0.8967,
"step": 782
},
{
"epoch": 0.8419354838709677,
"grad_norm": 1.0077635049819946,
"learning_rate": 1.2336450830422452e-06,
"loss": 0.8741,
"step": 783
},
{
"epoch": 0.843010752688172,
"grad_norm": 1.001855731010437,
"learning_rate": 1.2172658640766622e-06,
"loss": 0.9065,
"step": 784
},
{
"epoch": 0.8440860215053764,
"grad_norm": 1.1800569295883179,
"learning_rate": 1.2009890577141625e-06,
"loss": 0.8352,
"step": 785
},
{
"epoch": 0.8451612903225807,
"grad_norm": 0.9963459968566895,
"learning_rate": 1.1848148537532845e-06,
"loss": 0.8659,
"step": 786
},
{
"epoch": 0.8462365591397849,
"grad_norm": 0.9820273518562317,
"learning_rate": 1.1687434407961584e-06,
"loss": 0.8985,
"step": 787
},
{
"epoch": 0.8473118279569892,
"grad_norm": 1.0634284019470215,
"learning_rate": 1.1527750062462928e-06,
"loss": 0.8535,
"step": 788
},
{
"epoch": 0.8483870967741935,
"grad_norm": 1.0087202787399292,
"learning_rate": 1.1369097363064064e-06,
"loss": 0.8976,
"step": 789
},
{
"epoch": 0.8494623655913979,
"grad_norm": 0.9989567399024963,
"learning_rate": 1.121147815976248e-06,
"loss": 0.8748,
"step": 790
},
{
"epoch": 0.8505376344086022,
"grad_norm": 1.0062466859817505,
"learning_rate": 1.1054894290504348e-06,
"loss": 0.8621,
"step": 791
},
{
"epoch": 0.8516129032258064,
"grad_norm": 1.0595635175704956,
"learning_rate": 1.0899347581163222e-06,
"loss": 0.8782,
"step": 792
},
{
"epoch": 0.8526881720430107,
"grad_norm": 1.0409711599349976,
"learning_rate": 1.0744839845518585e-06,
"loss": 0.8769,
"step": 793
},
{
"epoch": 0.853763440860215,
"grad_norm": 1.0703274011611938,
"learning_rate": 1.0591372885234885e-06,
"loss": 0.8763,
"step": 794
},
{
"epoch": 0.8548387096774194,
"grad_norm": 1.095167875289917,
"learning_rate": 1.0438948489840327e-06,
"loss": 0.8772,
"step": 795
},
{
"epoch": 0.8559139784946237,
"grad_norm": 1.166521430015564,
"learning_rate": 1.0287568436706208e-06,
"loss": 0.8678,
"step": 796
},
{
"epoch": 0.8569892473118279,
"grad_norm": 1.0134778022766113,
"learning_rate": 1.0137234491026015e-06,
"loss": 0.887,
"step": 797
},
{
"epoch": 0.8580645161290322,
"grad_norm": 1.0230733156204224,
"learning_rate": 9.987948405794912e-07,
"loss": 0.8634,
"step": 798
},
{
"epoch": 0.8591397849462366,
"grad_norm": 1.062451958656311,
"learning_rate": 9.839711921789363e-07,
"loss": 0.8754,
"step": 799
},
{
"epoch": 0.8602150537634409,
"grad_norm": 0.9886546730995178,
"learning_rate": 9.692526767546727e-07,
"loss": 0.8967,
"step": 800
},
{
"epoch": 0.8612903225806452,
"grad_norm": 1.0505887269973755,
"learning_rate": 9.546394659345192e-07,
"loss": 0.8783,
"step": 801
},
{
"epoch": 0.8623655913978494,
"grad_norm": 1.0658241510391235,
"learning_rate": 9.401317301183655e-07,
"loss": 0.748,
"step": 802
},
{
"epoch": 0.8634408602150537,
"grad_norm": 0.9909445643424988,
"learning_rate": 9.257296384761971e-07,
"loss": 0.9126,
"step": 803
},
{
"epoch": 0.864516129032258,
"grad_norm": 1.0579025745391846,
"learning_rate": 9.114333589461144e-07,
"loss": 0.9195,
"step": 804
},
{
"epoch": 0.8655913978494624,
"grad_norm": 1.0848064422607422,
"learning_rate": 8.972430582323788e-07,
"loss": 0.8731,
"step": 805
},
{
"epoch": 0.8666666666666667,
"grad_norm": 0.9736969470977783,
"learning_rate": 8.831589018034659e-07,
"loss": 0.8881,
"step": 806
},
{
"epoch": 0.867741935483871,
"grad_norm": 1.1477285623550415,
"learning_rate": 8.69181053890138e-07,
"loss": 0.9058,
"step": 807
},
{
"epoch": 0.8688172043010752,
"grad_norm": 1.0351393222808838,
"learning_rate": 8.553096774835312e-07,
"loss": 0.8766,
"step": 808
},
{
"epoch": 0.8698924731182796,
"grad_norm": 1.1132804155349731,
"learning_rate": 8.41544934333246e-07,
"loss": 0.8549,
"step": 809
},
{
"epoch": 0.8709677419354839,
"grad_norm": 0.9678705930709839,
"learning_rate": 8.278869849454718e-07,
"loss": 0.9077,
"step": 810
},
{
"epoch": 0.8720430107526882,
"grad_norm": 1.0790833234786987,
"learning_rate": 8.143359885811064e-07,
"loss": 0.8587,
"step": 811
},
{
"epoch": 0.8731182795698925,
"grad_norm": 1.0063000917434692,
"learning_rate": 8.008921032539108e-07,
"loss": 0.8842,
"step": 812
},
{
"epoch": 0.8741935483870967,
"grad_norm": 1.024970531463623,
"learning_rate": 7.875554857286504e-07,
"loss": 0.8685,
"step": 813
},
{
"epoch": 0.875268817204301,
"grad_norm": 1.1168882846832275,
"learning_rate": 7.743262915192839e-07,
"loss": 0.8398,
"step": 814
},
{
"epoch": 0.8763440860215054,
"grad_norm": 1.0974441766738892,
"learning_rate": 7.612046748871327e-07,
"loss": 0.8702,
"step": 815
},
{
"epoch": 0.8774193548387097,
"grad_norm": 1.0631004571914673,
"learning_rate": 7.481907888390994e-07,
"loss": 0.8968,
"step": 816
},
{
"epoch": 0.878494623655914,
"grad_norm": 1.018012523651123,
"learning_rate": 7.352847851258716e-07,
"loss": 0.8952,
"step": 817
},
{
"epoch": 0.8795698924731182,
"grad_norm": 1.067273736000061,
"learning_rate": 7.224868142401542e-07,
"loss": 0.8675,
"step": 818
},
{
"epoch": 0.8806451612903226,
"grad_norm": 1.0818495750427246,
"learning_rate": 7.097970254149222e-07,
"loss": 0.8667,
"step": 819
},
{
"epoch": 0.8817204301075269,
"grad_norm": 0.9330995082855225,
"learning_rate": 6.972155666216684e-07,
"loss": 0.7546,
"step": 820
},
{
"epoch": 0.8827956989247312,
"grad_norm": 1.007285475730896,
"learning_rate": 6.847425845686884e-07,
"loss": 0.8765,
"step": 821
},
{
"epoch": 0.8838709677419355,
"grad_norm": 1.0542314052581787,
"learning_rate": 6.723782246993648e-07,
"loss": 0.8631,
"step": 822
},
{
"epoch": 0.8849462365591397,
"grad_norm": 1.1038877964019775,
"learning_rate": 6.601226311904718e-07,
"loss": 0.8584,
"step": 823
},
{
"epoch": 0.886021505376344,
"grad_norm": 0.9646521210670471,
"learning_rate": 6.479759469504931e-07,
"loss": 0.8958,
"step": 824
},
{
"epoch": 0.8870967741935484,
"grad_norm": 1.0366793870925903,
"learning_rate": 6.359383136179598e-07,
"loss": 0.8811,
"step": 825
},
{
"epoch": 0.8881720430107527,
"grad_norm": 1.0770856142044067,
"learning_rate": 6.240098715597975e-07,
"loss": 0.8734,
"step": 826
},
{
"epoch": 0.889247311827957,
"grad_norm": 1.1148271560668945,
"learning_rate": 6.121907598696808e-07,
"loss": 0.8623,
"step": 827
},
{
"epoch": 0.8903225806451613,
"grad_norm": 0.9609014987945557,
"learning_rate": 6.00481116366427e-07,
"loss": 0.901,
"step": 828
},
{
"epoch": 0.8913978494623656,
"grad_norm": 0.9495878219604492,
"learning_rate": 5.888810775923726e-07,
"loss": 0.8664,
"step": 829
},
{
"epoch": 0.8924731182795699,
"grad_norm": 1.089764952659607,
"learning_rate": 5.77390778811796e-07,
"loss": 0.8839,
"step": 830
},
{
"epoch": 0.8935483870967742,
"grad_norm": 0.9896240234375,
"learning_rate": 5.660103540093265e-07,
"loss": 0.8833,
"step": 831
},
{
"epoch": 0.8946236559139785,
"grad_norm": 0.9893712997436523,
"learning_rate": 5.547399358883953e-07,
"loss": 0.8811,
"step": 832
},
{
"epoch": 0.8956989247311828,
"grad_norm": 1.0602530241012573,
"learning_rate": 5.43579655869676e-07,
"loss": 0.8908,
"step": 833
},
{
"epoch": 0.896774193548387,
"grad_norm": 1.0764974355697632,
"learning_rate": 5.325296440895622e-07,
"loss": 0.8822,
"step": 834
},
{
"epoch": 0.8978494623655914,
"grad_norm": 1.0722241401672363,
"learning_rate": 5.215900293986431e-07,
"loss": 0.8555,
"step": 835
},
{
"epoch": 0.8989247311827957,
"grad_norm": 0.9710987210273743,
"learning_rate": 5.107609393602019e-07,
"loss": 0.9039,
"step": 836
},
{
"epoch": 0.9,
"grad_norm": 1.0058637857437134,
"learning_rate": 5.000425002487342e-07,
"loss": 0.9027,
"step": 837
},
{
"epoch": 0.9010752688172043,
"grad_norm": 1.0156899690628052,
"learning_rate": 4.894348370484648e-07,
"loss": 0.862,
"step": 838
},
{
"epoch": 0.9021505376344086,
"grad_norm": 1.1212072372436523,
"learning_rate": 4.789380734519045e-07,
"loss": 0.8812,
"step": 839
},
{
"epoch": 0.9032258064516129,
"grad_norm": 1.0828582048416138,
"learning_rate": 4.6855233185839175e-07,
"loss": 0.9243,
"step": 840
},
{
"epoch": 0.9043010752688172,
"grad_norm": 0.9520331025123596,
"learning_rate": 4.5827773337268177e-07,
"loss": 0.8822,
"step": 841
},
{
"epoch": 0.9053763440860215,
"grad_norm": 1.057708740234375,
"learning_rate": 4.481143978035196e-07,
"loss": 0.8768,
"step": 842
},
{
"epoch": 0.9064516129032258,
"grad_norm": 1.1681333780288696,
"learning_rate": 4.380624436622516e-07,
"loss": 0.8689,
"step": 843
},
{
"epoch": 0.9075268817204301,
"grad_norm": 1.0377984046936035,
"learning_rate": 4.281219881614451e-07,
"loss": 0.8299,
"step": 844
},
{
"epoch": 0.9086021505376344,
"grad_norm": 1.1868066787719727,
"learning_rate": 4.1829314721351213e-07,
"loss": 0.8652,
"step": 845
},
{
"epoch": 0.9096774193548387,
"grad_norm": 1.0405972003936768,
"learning_rate": 4.0857603542936776e-07,
"loss": 0.9007,
"step": 846
},
{
"epoch": 0.910752688172043,
"grad_norm": 1.080142855644226,
"learning_rate": 3.989707661170894e-07,
"loss": 0.7416,
"step": 847
},
{
"epoch": 0.9118279569892473,
"grad_norm": 1.0355066061019897,
"learning_rate": 3.894774512805932e-07,
"loss": 0.9158,
"step": 848
},
{
"epoch": 0.9129032258064517,
"grad_norm": 0.9819759130477905,
"learning_rate": 3.8009620161833295e-07,
"loss": 0.8866,
"step": 849
},
{
"epoch": 0.9139784946236559,
"grad_norm": 1.0069386959075928,
"learning_rate": 3.708271265220087e-07,
"loss": 0.9083,
"step": 850
},
{
"epoch": 0.9150537634408602,
"grad_norm": 1.0547349452972412,
"learning_rate": 3.616703340752825e-07,
"loss": 0.8957,
"step": 851
},
{
"epoch": 0.9161290322580645,
"grad_norm": 0.9976608157157898,
"learning_rate": 3.5262593105253374e-07,
"loss": 0.7867,
"step": 852
},
{
"epoch": 0.9172043010752688,
"grad_norm": 0.9935895204544067,
"learning_rate": 3.436940229176e-07,
"loss": 0.902,
"step": 853
},
{
"epoch": 0.9182795698924732,
"grad_norm": 1.0534745454788208,
"learning_rate": 3.3487471382255277e-07,
"loss": 0.9242,
"step": 854
},
{
"epoch": 0.9193548387096774,
"grad_norm": 1.0113539695739746,
"learning_rate": 3.261681066064859e-07,
"loss": 0.8852,
"step": 855
},
{
"epoch": 0.9204301075268817,
"grad_norm": 1.0486923456192017,
"learning_rate": 3.175743027943079e-07,
"loss": 0.8942,
"step": 856
},
{
"epoch": 0.921505376344086,
"grad_norm": 1.1777671575546265,
"learning_rate": 3.0909340259557055e-07,
"loss": 0.8087,
"step": 857
},
{
"epoch": 0.9225806451612903,
"grad_norm": 1.0966805219650269,
"learning_rate": 3.0072550490328754e-07,
"loss": 0.8399,
"step": 858
},
{
"epoch": 0.9236559139784947,
"grad_norm": 1.0180057287216187,
"learning_rate": 2.9247070729279017e-07,
"loss": 0.8571,
"step": 859
},
{
"epoch": 0.9247311827956989,
"grad_norm": 1.12461256980896,
"learning_rate": 2.843291060205855e-07,
"loss": 0.817,
"step": 860
},
{
"epoch": 0.9258064516129032,
"grad_norm": 0.962689220905304,
"learning_rate": 2.7630079602323447e-07,
"loss": 0.892,
"step": 861
},
{
"epoch": 0.9268817204301075,
"grad_norm": 1.0531262159347534,
"learning_rate": 2.683858709162468e-07,
"loss": 0.9067,
"step": 862
},
{
"epoch": 0.9279569892473118,
"grad_norm": 1.0303092002868652,
"learning_rate": 2.6058442299298437e-07,
"loss": 0.8756,
"step": 863
},
{
"epoch": 0.9290322580645162,
"grad_norm": 1.0068696737289429,
"learning_rate": 2.5289654322359526e-07,
"loss": 0.8851,
"step": 864
},
{
"epoch": 0.9301075268817204,
"grad_norm": 0.9323456287384033,
"learning_rate": 2.453223212539391e-07,
"loss": 0.9156,
"step": 865
},
{
"epoch": 0.9311827956989247,
"grad_norm": 1.013602614402771,
"learning_rate": 2.3786184540455449e-07,
"loss": 0.8941,
"step": 866
},
{
"epoch": 0.932258064516129,
"grad_norm": 1.0885473489761353,
"learning_rate": 2.3051520266961892e-07,
"loss": 0.8786,
"step": 867
},
{
"epoch": 0.9333333333333333,
"grad_norm": 0.957119345664978,
"learning_rate": 2.2328247871594379e-07,
"loss": 0.8985,
"step": 868
},
{
"epoch": 0.9344086021505377,
"grad_norm": 1.0595957040786743,
"learning_rate": 2.161637578819653e-07,
"loss": 0.8598,
"step": 869
},
{
"epoch": 0.9354838709677419,
"grad_norm": 1.0160598754882812,
"learning_rate": 2.091591231767709e-07,
"loss": 0.8458,
"step": 870
},
{
"epoch": 0.9365591397849462,
"grad_norm": 1.0207420587539673,
"learning_rate": 2.022686562791254e-07,
"loss": 0.8503,
"step": 871
},
{
"epoch": 0.9376344086021505,
"grad_norm": 0.9531442523002625,
"learning_rate": 1.954924375365197e-07,
"loss": 0.885,
"step": 872
},
{
"epoch": 0.9387096774193548,
"grad_norm": 1.05819571018219,
"learning_rate": 1.8883054596423255e-07,
"loss": 0.8559,
"step": 873
},
{
"epoch": 0.9397849462365592,
"grad_norm": 1.021631121635437,
"learning_rate": 1.8228305924441469e-07,
"loss": 0.8785,
"step": 874
},
{
"epoch": 0.9408602150537635,
"grad_norm": 1.0116877555847168,
"learning_rate": 1.7585005372517504e-07,
"loss": 0.8627,
"step": 875
},
{
"epoch": 0.9419354838709677,
"grad_norm": 0.9780187606811523,
"learning_rate": 1.6953160441969707e-07,
"loss": 0.9232,
"step": 876
},
{
"epoch": 0.943010752688172,
"grad_norm": 1.017525553703308,
"learning_rate": 1.633277850053605e-07,
"loss": 0.8649,
"step": 877
},
{
"epoch": 0.9440860215053763,
"grad_norm": 1.1021080017089844,
"learning_rate": 1.5723866782288545e-07,
"loss": 0.8513,
"step": 878
},
{
"epoch": 0.9451612903225807,
"grad_norm": 1.0974959135055542,
"learning_rate": 1.5126432387548185e-07,
"loss": 0.8503,
"step": 879
},
{
"epoch": 0.946236559139785,
"grad_norm": 1.0184605121612549,
"learning_rate": 1.4540482282803136e-07,
"loss": 0.8458,
"step": 880
},
{
"epoch": 0.9473118279569892,
"grad_norm": 0.9723237156867981,
"learning_rate": 1.3966023300626685e-07,
"loss": 0.8941,
"step": 881
},
{
"epoch": 0.9483870967741935,
"grad_norm": 1.0808511972427368,
"learning_rate": 1.3403062139598078e-07,
"loss": 0.8676,
"step": 882
},
{
"epoch": 0.9494623655913978,
"grad_norm": 1.1188552379608154,
"learning_rate": 1.285160536422392e-07,
"loss": 0.8637,
"step": 883
},
{
"epoch": 0.9505376344086022,
"grad_norm": 1.1268365383148193,
"learning_rate": 1.231165940486234e-07,
"loss": 0.8953,
"step": 884
},
{
"epoch": 0.9516129032258065,
"grad_norm": 1.0947691202163696,
"learning_rate": 1.1783230557647075e-07,
"loss": 0.8834,
"step": 885
},
{
"epoch": 0.9526881720430107,
"grad_norm": 0.9339337348937988,
"learning_rate": 1.1266324984415266e-07,
"loss": 0.868,
"step": 886
},
{
"epoch": 0.953763440860215,
"grad_norm": 1.1089427471160889,
"learning_rate": 1.0760948712634112e-07,
"loss": 0.8783,
"step": 887
},
{
"epoch": 0.9548387096774194,
"grad_norm": 1.0046530961990356,
"learning_rate": 1.0267107635331897e-07,
"loss": 0.8655,
"step": 888
},
{
"epoch": 0.9559139784946237,
"grad_norm": 1.1793391704559326,
"learning_rate": 9.784807511028837e-08,
"loss": 0.8016,
"step": 889
},
{
"epoch": 0.956989247311828,
"grad_norm": 1.149901270866394,
"learning_rate": 9.314053963669245e-08,
"loss": 0.8069,
"step": 890
},
{
"epoch": 0.9580645161290322,
"grad_norm": 0.9446433186531067,
"learning_rate": 8.854852482557242e-08,
"loss": 0.9094,
"step": 891
},
{
"epoch": 0.9591397849462365,
"grad_norm": 1.1705981492996216,
"learning_rate": 8.407208422291702e-08,
"loss": 0.8226,
"step": 892
},
{
"epoch": 0.9602150537634409,
"grad_norm": 1.121645450592041,
"learning_rate": 7.971127002704304e-08,
"loss": 0.8453,
"step": 893
},
{
"epoch": 0.9612903225806452,
"grad_norm": 0.929806649684906,
"learning_rate": 7.546613308798468e-08,
"loss": 0.9233,
"step": 894
},
{
"epoch": 0.9623655913978495,
"grad_norm": 1.1136562824249268,
"learning_rate": 7.133672290690064e-08,
"loss": 0.8564,
"step": 895
},
{
"epoch": 0.9634408602150538,
"grad_norm": 1.028089165687561,
"learning_rate": 6.732308763550022e-08,
"loss": 0.8639,
"step": 896
},
{
"epoch": 0.964516129032258,
"grad_norm": 1.0633161067962646,
"learning_rate": 6.342527407547594e-08,
"loss": 0.8674,
"step": 897
},
{
"epoch": 0.9655913978494624,
"grad_norm": 1.0046178102493286,
"learning_rate": 5.964332767796399e-08,
"loss": 0.8437,
"step": 898
},
{
"epoch": 0.9666666666666667,
"grad_norm": 1.0161393880844116,
"learning_rate": 5.5977292543007987e-08,
"loss": 0.8521,
"step": 899
},
{
"epoch": 0.967741935483871,
"grad_norm": 1.0653326511383057,
"learning_rate": 5.2427211419051605e-08,
"loss": 0.8699,
"step": 900
},
{
"epoch": 0.9688172043010753,
"grad_norm": 1.103620171546936,
"learning_rate": 4.899312570243453e-08,
"loss": 0.8566,
"step": 901
},
{
"epoch": 0.9698924731182795,
"grad_norm": 1.0353485345840454,
"learning_rate": 4.567507543691174e-08,
"loss": 0.8792,
"step": 902
},
{
"epoch": 0.9709677419354839,
"grad_norm": 0.9971827268600464,
"learning_rate": 4.247309931318722e-08,
"loss": 0.8856,
"step": 903
},
{
"epoch": 0.9720430107526882,
"grad_norm": 1.0072693824768066,
"learning_rate": 3.938723466846206e-08,
"loss": 0.9181,
"step": 904
},
{
"epoch": 0.9731182795698925,
"grad_norm": 1.0200785398483276,
"learning_rate": 3.641751748600042e-08,
"loss": 0.853,
"step": 905
},
{
"epoch": 0.9741935483870968,
"grad_norm": 1.2243609428405762,
"learning_rate": 3.356398239470427e-08,
"loss": 0.7918,
"step": 906
},
{
"epoch": 0.975268817204301,
"grad_norm": 1.082497000694275,
"learning_rate": 3.082666266872036e-08,
"loss": 0.8853,
"step": 907
},
{
"epoch": 0.9763440860215054,
"grad_norm": 1.0451264381408691,
"learning_rate": 2.8205590227040613e-08,
"loss": 0.8645,
"step": 908
},
{
"epoch": 0.9774193548387097,
"grad_norm": 1.0385005474090576,
"learning_rate": 2.5700795633138987e-08,
"loss": 0.905,
"step": 909
},
{
"epoch": 0.978494623655914,
"grad_norm": 1.056601643562317,
"learning_rate": 2.3312308094607382e-08,
"loss": 0.7373,
"step": 910
},
{
"epoch": 0.9795698924731183,
"grad_norm": 1.2547791004180908,
"learning_rate": 2.1040155462824786e-08,
"loss": 0.8263,
"step": 911
},
{
"epoch": 0.9806451612903225,
"grad_norm": 1.0116780996322632,
"learning_rate": 1.8884364232619744e-08,
"loss": 0.9072,
"step": 912
},
{
"epoch": 0.9817204301075269,
"grad_norm": 0.9879081845283508,
"learning_rate": 1.6844959541973958e-08,
"loss": 0.8897,
"step": 913
},
{
"epoch": 0.9827956989247312,
"grad_norm": 1.1083647012710571,
"learning_rate": 1.4921965171720288e-08,
"loss": 0.8483,
"step": 914
},
{
"epoch": 0.9838709677419355,
"grad_norm": 1.0797687768936157,
"learning_rate": 1.3115403545270744e-08,
"loss": 0.8615,
"step": 915
},
{
"epoch": 0.9849462365591398,
"grad_norm": 1.0498789548873901,
"learning_rate": 1.142529572835227e-08,
"loss": 0.877,
"step": 916
},
{
"epoch": 0.986021505376344,
"grad_norm": 1.0166867971420288,
"learning_rate": 9.851661428761372e-09,
"loss": 0.8823,
"step": 917
},
{
"epoch": 0.9870967741935484,
"grad_norm": 1.130036473274231,
"learning_rate": 8.394518996135414e-09,
"loss": 0.8339,
"step": 918
},
{
"epoch": 0.9881720430107527,
"grad_norm": 1.0444576740264893,
"learning_rate": 7.053885421737239e-09,
"loss": 0.8898,
"step": 919
},
{
"epoch": 0.989247311827957,
"grad_norm": 0.9490436911582947,
"learning_rate": 5.8297763382597625e-09,
"loss": 0.8947,
"step": 920
},
{
"epoch": 0.9903225806451613,
"grad_norm": 1.0969460010528564,
"learning_rate": 4.7222060196394634e-09,
"loss": 0.914,
"step": 921
},
{
"epoch": 0.9913978494623656,
"grad_norm": 1.2216132879257202,
"learning_rate": 3.731187380893176e-09,
"loss": 0.8302,
"step": 922
},
{
"epoch": 0.9924731182795699,
"grad_norm": 1.0914058685302734,
"learning_rate": 2.856731977968208e-09,
"loss": 0.8287,
"step": 923
},
{
"epoch": 0.9935483870967742,
"grad_norm": 1.0946998596191406,
"learning_rate": 2.0988500076013494e-09,
"loss": 0.8098,
"step": 924
},
{
"epoch": 0.9946236559139785,
"grad_norm": 0.9429404735565186,
"learning_rate": 1.4575503072100649e-09,
"loss": 0.9227,
"step": 925
},
{
"epoch": 0.9956989247311828,
"grad_norm": 1.110209345817566,
"learning_rate": 9.328403547792518e-10,
"loss": 0.8376,
"step": 926
},
{
"epoch": 0.9967741935483871,
"grad_norm": 1.0573797225952148,
"learning_rate": 5.247262687835264e-10,
"loss": 0.826,
"step": 927
},
{
"epoch": 0.9978494623655914,
"grad_norm": 1.0567365884780884,
"learning_rate": 2.3321280810617575e-10,
"loss": 0.8646,
"step": 928
},
{
"epoch": 0.9989247311827957,
"grad_norm": 1.0667850971221924,
"learning_rate": 5.830337199030922e-11,
"loss": 0.8539,
"step": 929
},
{
"epoch": 1.0,
"grad_norm": 1.0270296335220337,
"learning_rate": 0.0,
"loss": 0.8958,
"step": 930
}
],
"logging_steps": 1,
"max_steps": 930,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.644255795888783e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}