| { | |
| "best_metric": 1.3121320009231567, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 1.0052356020942408, | |
| "eval_steps": 50, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008376963350785341, | |
| "grad_norm": 1.4030457735061646, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008376963350785341, | |
| "eval_loss": 2.1936235427856445, | |
| "eval_runtime": 54.1297, | |
| "eval_samples_per_second": 7.445, | |
| "eval_steps_per_second": 1.866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016753926701570682, | |
| "grad_norm": 1.4992213249206543, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0929, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.025130890052356022, | |
| "grad_norm": 1.784857988357544, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1302, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.033507853403141365, | |
| "grad_norm": 1.5829931497573853, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1207, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.041884816753926704, | |
| "grad_norm": 1.2313480377197266, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0151, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.050261780104712044, | |
| "grad_norm": 1.41518235206604, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9839, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05863874345549738, | |
| "grad_norm": 0.8072548508644104, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9233, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06701570680628273, | |
| "grad_norm": 0.5549747943878174, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8144, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07539267015706806, | |
| "grad_norm": 0.5323136448860168, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7493, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08376963350785341, | |
| "grad_norm": 0.5407094955444336, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7072, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09214659685863874, | |
| "grad_norm": 0.46159911155700684, | |
| "learning_rate": 0.00019995921928281894, | |
| "loss": 1.651, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10052356020942409, | |
| "grad_norm": 0.6404337882995605, | |
| "learning_rate": 0.00019983691039261357, | |
| "loss": 1.6431, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10890052356020942, | |
| "grad_norm": 0.352531373500824, | |
| "learning_rate": 0.00019963317308626914, | |
| "loss": 1.6052, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11727748691099477, | |
| "grad_norm": 0.3619747757911682, | |
| "learning_rate": 0.00019934817353485501, | |
| "loss": 1.5712, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1256544502617801, | |
| "grad_norm": 0.519852876663208, | |
| "learning_rate": 0.0001989821441880933, | |
| "loss": 1.5411, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13403141361256546, | |
| "grad_norm": 0.4429551064968109, | |
| "learning_rate": 0.00019853538358476932, | |
| "loss": 1.5922, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1424083769633508, | |
| "grad_norm": 0.3226163983345032, | |
| "learning_rate": 0.00019800825610923934, | |
| "loss": 1.5483, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15078534031413612, | |
| "grad_norm": 0.3610597550868988, | |
| "learning_rate": 0.00019740119169423337, | |
| "loss": 1.5054, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15916230366492146, | |
| "grad_norm": 0.29118454456329346, | |
| "learning_rate": 0.00019671468547019573, | |
| "loss": 1.5432, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16753926701570682, | |
| "grad_norm": 0.24570101499557495, | |
| "learning_rate": 0.00019594929736144976, | |
| "loss": 1.4688, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17591623036649215, | |
| "grad_norm": 0.28832247853279114, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.4375, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18429319371727748, | |
| "grad_norm": 0.25904181599617004, | |
| "learning_rate": 0.00019418443636395248, | |
| "loss": 1.534, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19267015706806281, | |
| "grad_norm": 0.2384636104106903, | |
| "learning_rate": 0.00019318640292114524, | |
| "loss": 1.4328, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20104712041884817, | |
| "grad_norm": 0.27154815196990967, | |
| "learning_rate": 0.000192112365311485, | |
| "loss": 1.4292, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2094240837696335, | |
| "grad_norm": 0.2336822897195816, | |
| "learning_rate": 0.00019096319953545185, | |
| "loss": 1.4027, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21780104712041884, | |
| "grad_norm": 0.21763642132282257, | |
| "learning_rate": 0.00018973984286913584, | |
| "loss": 1.4238, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2261780104712042, | |
| "grad_norm": 0.2171494960784912, | |
| "learning_rate": 0.00018844329309978145, | |
| "loss": 1.4108, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23455497382198953, | |
| "grad_norm": 0.20013433694839478, | |
| "learning_rate": 0.00018707460771197774, | |
| "loss": 1.3777, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24293193717277486, | |
| "grad_norm": 0.22450464963912964, | |
| "learning_rate": 0.0001856349030251589, | |
| "loss": 1.396, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2513089005235602, | |
| "grad_norm": 0.23654663562774658, | |
| "learning_rate": 0.00018412535328311814, | |
| "loss": 1.4103, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25968586387434556, | |
| "grad_norm": 0.2156527042388916, | |
| "learning_rate": 0.0001825471896962774, | |
| "loss": 1.4367, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2680628272251309, | |
| "grad_norm": 0.19791820645332336, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.4173, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2764397905759162, | |
| "grad_norm": 0.2152637392282486, | |
| "learning_rate": 0.00017919022459222752, | |
| "loss": 1.3479, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2848167539267016, | |
| "grad_norm": 0.20826572179794312, | |
| "learning_rate": 0.00017741416106390826, | |
| "loss": 1.3828, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2931937172774869, | |
| "grad_norm": 0.20378273725509644, | |
| "learning_rate": 0.00017557495743542585, | |
| "loss": 1.3657, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.30157068062827225, | |
| "grad_norm": 0.2143692672252655, | |
| "learning_rate": 0.0001736741137876405, | |
| "loss": 1.4046, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3099476439790576, | |
| "grad_norm": 0.22452476620674133, | |
| "learning_rate": 0.00017171318047589637, | |
| "loss": 1.3673, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3183246073298429, | |
| "grad_norm": 0.20779763162136078, | |
| "learning_rate": 0.00016969375686552937, | |
| "loss": 1.4057, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3267015706806283, | |
| "grad_norm": 0.2210998684167862, | |
| "learning_rate": 0.00016761749002740193, | |
| "loss": 1.3789, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.33507853403141363, | |
| "grad_norm": 0.22668598592281342, | |
| "learning_rate": 0.00016548607339452853, | |
| "loss": 1.3272, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34345549738219894, | |
| "grad_norm": 0.21081912517547607, | |
| "learning_rate": 0.00016330124538088705, | |
| "loss": 1.4033, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3518324607329843, | |
| "grad_norm": 0.20994143187999725, | |
| "learning_rate": 0.00016106478796354382, | |
| "loss": 1.4135, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.36020942408376966, | |
| "grad_norm": 0.22178034484386444, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 1.3235, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.36858638743455496, | |
| "grad_norm": 0.26765337586402893, | |
| "learning_rate": 0.00015644432188667695, | |
| "loss": 1.3852, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3769633507853403, | |
| "grad_norm": 0.31858474016189575, | |
| "learning_rate": 0.00015406408174555976, | |
| "loss": 1.338, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.38534031413612563, | |
| "grad_norm": 0.24434570968151093, | |
| "learning_rate": 0.0001516397461638962, | |
| "loss": 1.3631, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.393717277486911, | |
| "grad_norm": 0.22655674815177917, | |
| "learning_rate": 0.0001491732924645604, | |
| "loss": 1.3075, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.40209424083769635, | |
| "grad_norm": 0.21461047232151031, | |
| "learning_rate": 0.00014666673232256738, | |
| "loss": 1.3294, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.41047120418848165, | |
| "grad_norm": 0.2243211269378662, | |
| "learning_rate": 0.00014412211012432212, | |
| "loss": 1.3267, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.418848167539267, | |
| "grad_norm": 0.22946247458457947, | |
| "learning_rate": 0.00014154150130018866, | |
| "loss": 1.3904, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.418848167539267, | |
| "eval_loss": 1.3593463897705078, | |
| "eval_runtime": 54.6174, | |
| "eval_samples_per_second": 7.379, | |
| "eval_steps_per_second": 1.849, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4272251308900524, | |
| "grad_norm": 0.2250441461801529, | |
| "learning_rate": 0.00013892701063173918, | |
| "loss": 1.3205, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4356020942408377, | |
| "grad_norm": 0.2325247824192047, | |
| "learning_rate": 0.0001362807705350641, | |
| "loss": 1.3751, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.44397905759162304, | |
| "grad_norm": 0.23405078053474426, | |
| "learning_rate": 0.00013360493932154302, | |
| "loss": 1.3023, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.4523560209424084, | |
| "grad_norm": 0.24694718420505524, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.329, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4607329842931937, | |
| "grad_norm": 0.23932890594005585, | |
| "learning_rate": 0.00012817325568414297, | |
| "loss": 1.308, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.46910994764397906, | |
| "grad_norm": 0.23090919852256775, | |
| "learning_rate": 0.00012542183341934872, | |
| "loss": 1.3658, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4774869109947644, | |
| "grad_norm": 0.23715175688266754, | |
| "learning_rate": 0.00012264967674257646, | |
| "loss": 1.2654, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.48586387434554973, | |
| "grad_norm": 0.24813269078731537, | |
| "learning_rate": 0.00011985904666457455, | |
| "loss": 1.3035, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.4942408376963351, | |
| "grad_norm": 0.2591025233268738, | |
| "learning_rate": 0.0001170522192632624, | |
| "loss": 1.3445, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5026178010471204, | |
| "grad_norm": 0.26143878698349, | |
| "learning_rate": 0.00011423148382732853, | |
| "loss": 1.3675, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5109947643979058, | |
| "grad_norm": 0.2329186201095581, | |
| "learning_rate": 0.00011139914098905406, | |
| "loss": 1.3384, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5193717277486911, | |
| "grad_norm": 0.23178386688232422, | |
| "learning_rate": 0.00010855750084788398, | |
| "loss": 1.3093, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5277486910994764, | |
| "grad_norm": 0.23026645183563232, | |
| "learning_rate": 0.00010570888108627681, | |
| "loss": 1.3064, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5361256544502618, | |
| "grad_norm": 0.24100545048713684, | |
| "learning_rate": 0.00010285560507936961, | |
| "loss": 1.3258, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5445026178010471, | |
| "grad_norm": 0.24575698375701904, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3398, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5528795811518324, | |
| "grad_norm": 0.2778918445110321, | |
| "learning_rate": 9.71443949206304e-05, | |
| "loss": 1.3778, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5612565445026177, | |
| "grad_norm": 0.26030927896499634, | |
| "learning_rate": 9.42911189137232e-05, | |
| "loss": 1.3101, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5696335078534032, | |
| "grad_norm": 0.2404455989599228, | |
| "learning_rate": 9.144249915211605e-05, | |
| "loss": 1.2912, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5780104712041885, | |
| "grad_norm": 0.24763959646224976, | |
| "learning_rate": 8.860085901094595e-05, | |
| "loss": 1.3059, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5863874345549738, | |
| "grad_norm": 0.24902191758155823, | |
| "learning_rate": 8.57685161726715e-05, | |
| "loss": 1.2653, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5947643979057592, | |
| "grad_norm": 0.2563740015029907, | |
| "learning_rate": 8.294778073673762e-05, | |
| "loss": 1.3613, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6031413612565445, | |
| "grad_norm": 0.2514787018299103, | |
| "learning_rate": 8.014095333542548e-05, | |
| "loss": 1.3108, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6115183246073298, | |
| "grad_norm": 0.2779984772205353, | |
| "learning_rate": 7.735032325742355e-05, | |
| "loss": 1.2887, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6198952879581152, | |
| "grad_norm": 0.24789296090602875, | |
| "learning_rate": 7.457816658065134e-05, | |
| "loss": 1.3755, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6282722513089005, | |
| "grad_norm": 0.24377316236495972, | |
| "learning_rate": 7.182674431585704e-05, | |
| "loss": 1.2984, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6366492146596858, | |
| "grad_norm": 0.24581335484981537, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.3265, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.6450261780104712, | |
| "grad_norm": 0.22706155478954315, | |
| "learning_rate": 6.639506067845697e-05, | |
| "loss": 1.2957, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6534031413612565, | |
| "grad_norm": 0.2653581500053406, | |
| "learning_rate": 6.371922946493591e-05, | |
| "loss": 1.3115, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6617801047120419, | |
| "grad_norm": 0.26213908195495605, | |
| "learning_rate": 6.107298936826086e-05, | |
| "loss": 1.2911, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.6701570680628273, | |
| "grad_norm": 0.2331765592098236, | |
| "learning_rate": 5.845849869981137e-05, | |
| "loss": 1.2769, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6785340314136126, | |
| "grad_norm": 0.24162189662456512, | |
| "learning_rate": 5.5877889875677845e-05, | |
| "loss": 1.2802, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.6869109947643979, | |
| "grad_norm": 0.26189252734184265, | |
| "learning_rate": 5.333326767743263e-05, | |
| "loss": 1.3237, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.6952879581151833, | |
| "grad_norm": 0.22555485367774963, | |
| "learning_rate": 5.082670753543961e-05, | |
| "loss": 1.2745, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.7036649214659686, | |
| "grad_norm": 0.254704087972641, | |
| "learning_rate": 4.836025383610382e-05, | |
| "loss": 1.354, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7120418848167539, | |
| "grad_norm": 0.28260111808776855, | |
| "learning_rate": 4.593591825444028e-05, | |
| "loss": 1.2935, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7204188481675393, | |
| "grad_norm": 0.25090911984443665, | |
| "learning_rate": 4.355567811332311e-05, | |
| "loss": 1.2761, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.7287958115183246, | |
| "grad_norm": 0.26403096318244934, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.2903, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7371727748691099, | |
| "grad_norm": 0.2612413763999939, | |
| "learning_rate": 3.893521203645618e-05, | |
| "loss": 1.356, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.7455497382198953, | |
| "grad_norm": 0.24037125706672668, | |
| "learning_rate": 3.669875461911297e-05, | |
| "loss": 1.2865, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.7539267015706806, | |
| "grad_norm": 0.252249538898468, | |
| "learning_rate": 3.45139266054715e-05, | |
| "loss": 1.2468, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.762303664921466, | |
| "grad_norm": 0.25495651364326477, | |
| "learning_rate": 3.238250997259808e-05, | |
| "loss": 1.3012, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7706806282722513, | |
| "grad_norm": 0.2322113960981369, | |
| "learning_rate": 3.030624313447067e-05, | |
| "loss": 1.2818, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.7790575916230367, | |
| "grad_norm": 0.2572304606437683, | |
| "learning_rate": 2.828681952410366e-05, | |
| "loss": 1.2221, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.787434554973822, | |
| "grad_norm": 0.24987637996673584, | |
| "learning_rate": 2.6325886212359498e-05, | |
| "loss": 1.3307, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.7958115183246073, | |
| "grad_norm": 0.25658029317855835, | |
| "learning_rate": 2.4425042564574184e-05, | |
| "loss": 1.299, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8041884816753927, | |
| "grad_norm": 0.23883827030658722, | |
| "learning_rate": 2.2585838936091754e-05, | |
| "loss": 1.3355, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.812565445026178, | |
| "grad_norm": 0.26572129130363464, | |
| "learning_rate": 2.0809775407772503e-05, | |
| "loss": 1.2445, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.8209424083769633, | |
| "grad_norm": 0.2597862780094147, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.2866, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.8293193717277487, | |
| "grad_norm": 0.24302197992801666, | |
| "learning_rate": 1.74528103037226e-05, | |
| "loss": 1.2775, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.837696335078534, | |
| "grad_norm": 0.2617965638637543, | |
| "learning_rate": 1.587464671688187e-05, | |
| "loss": 1.3117, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.837696335078534, | |
| "eval_loss": 1.3121320009231567, | |
| "eval_runtime": 54.6331, | |
| "eval_samples_per_second": 7.376, | |
| "eval_steps_per_second": 1.849, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8460732984293193, | |
| "grad_norm": 0.24377289414405823, | |
| "learning_rate": 1.4365096974841108e-05, | |
| "loss": 1.2426, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.8544502617801047, | |
| "grad_norm": 0.27847498655319214, | |
| "learning_rate": 1.2925392288022298e-05, | |
| "loss": 1.2593, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.86282722513089, | |
| "grad_norm": 0.2640259563922882, | |
| "learning_rate": 1.1556706900218572e-05, | |
| "loss": 1.2703, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.8712041884816754, | |
| "grad_norm": 0.2538398504257202, | |
| "learning_rate": 1.026015713086418e-05, | |
| "loss": 1.2544, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.8795811518324608, | |
| "grad_norm": 0.244331493973732, | |
| "learning_rate": 9.036800464548157e-06, | |
| "loss": 1.3047, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8879581151832461, | |
| "grad_norm": 0.26120704412460327, | |
| "learning_rate": 7.887634688515e-06, | |
| "loss": 1.2688, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.8963350785340314, | |
| "grad_norm": 0.2646150290966034, | |
| "learning_rate": 6.813597078854772e-06, | |
| "loss": 1.3536, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.9047120418848168, | |
| "grad_norm": 0.2558758854866028, | |
| "learning_rate": 5.8155636360475385e-06, | |
| "loss": 1.2918, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.9130890052356021, | |
| "grad_norm": 0.25811469554901123, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 1.2869, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.9214659685863874, | |
| "grad_norm": 0.25502899289131165, | |
| "learning_rate": 4.050702638550275e-06, | |
| "loss": 1.2949, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9298429319371728, | |
| "grad_norm": 0.25524598360061646, | |
| "learning_rate": 3.2853145298042953e-06, | |
| "loss": 1.27, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.9382198952879581, | |
| "grad_norm": 0.2520923614501953, | |
| "learning_rate": 2.5988083057666533e-06, | |
| "loss": 1.3135, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.9465968586387434, | |
| "grad_norm": 0.2525266110897064, | |
| "learning_rate": 1.9917438907606556e-06, | |
| "loss": 1.2766, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.9549738219895288, | |
| "grad_norm": 0.25608813762664795, | |
| "learning_rate": 1.4646164152307018e-06, | |
| "loss": 1.3429, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.9633507853403142, | |
| "grad_norm": 0.26775017380714417, | |
| "learning_rate": 1.0178558119067315e-06, | |
| "loss": 1.3198, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9717277486910995, | |
| "grad_norm": 0.25307947397232056, | |
| "learning_rate": 6.518264651449779e-07, | |
| "loss": 1.2831, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.9801047120418848, | |
| "grad_norm": 0.26626452803611755, | |
| "learning_rate": 3.6682691373086665e-07, | |
| "loss": 1.2701, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.9884816753926702, | |
| "grad_norm": 0.22642602026462555, | |
| "learning_rate": 1.630896073864352e-07, | |
| "loss": 1.3243, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.9968586387434555, | |
| "grad_norm": 0.28676363825798035, | |
| "learning_rate": 4.078071718107701e-08, | |
| "loss": 1.3269, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.0052356020942408, | |
| "grad_norm": 0.5024040937423706, | |
| "learning_rate": 0.0, | |
| "loss": 2.1063, | |
| "step": 120 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.327790086012273e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |