| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.032887312590682, |
| "eval_steps": 500, |
| "global_step": 1602, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.003224246332419797, |
| "grad_norm": 12.065600395202637, |
| "learning_rate": 4.917142857142858e-06, |
| "loss": 1.0785, |
| "mean_token_accuracy": 0.8301876187324524, |
| "num_tokens": 730328.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.006448492664839594, |
| "grad_norm": 2.7505671977996826, |
| "learning_rate": 1.106357142857143e-05, |
| "loss": 0.4958, |
| "mean_token_accuracy": 0.8926936030387879, |
| "num_tokens": 1455270.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.00967273899725939, |
| "grad_norm": 0.8892086148262024, |
| "learning_rate": 1.7210000000000003e-05, |
| "loss": 0.1658, |
| "mean_token_accuracy": 0.9509694278240204, |
| "num_tokens": 2176899.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.012896985329679188, |
| "grad_norm": 0.6942459940910339, |
| "learning_rate": 2.3356428571428574e-05, |
| "loss": 0.099, |
| "mean_token_accuracy": 0.9637625068426132, |
| "num_tokens": 2914617.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.016121231662098983, |
| "grad_norm": 0.6003042459487915, |
| "learning_rate": 2.950285714285715e-05, |
| "loss": 0.0954, |
| "mean_token_accuracy": 0.9636109918355942, |
| "num_tokens": 3651528.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.01934547799451878, |
| "grad_norm": 0.490217924118042, |
| "learning_rate": 3.5649285714285724e-05, |
| "loss": 0.0808, |
| "mean_token_accuracy": 0.9675142079591751, |
| "num_tokens": 4374975.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.02256972432693858, |
| "grad_norm": 0.3952588737010956, |
| "learning_rate": 4.179571428571429e-05, |
| "loss": 0.0842, |
| "mean_token_accuracy": 0.9653609961271286, |
| "num_tokens": 5106311.0, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.025793970659358376, |
| "grad_norm": 0.30597400665283203, |
| "learning_rate": 4.302494026432797e-05, |
| "loss": 0.0846, |
| "mean_token_accuracy": 0.9667847901582718, |
| "num_tokens": 5842889.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.029018216991778173, |
| "grad_norm": 0.37753477692604065, |
| "learning_rate": 4.30246975889184e-05, |
| "loss": 0.0914, |
| "mean_token_accuracy": 0.9632851302623748, |
| "num_tokens": 6573490.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.032242463324197966, |
| "grad_norm": 0.36575672030448914, |
| "learning_rate": 4.30242682430974e-05, |
| "loss": 0.0857, |
| "mean_token_accuracy": 0.9653938591480256, |
| "num_tokens": 7300400.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.035466709656617766, |
| "grad_norm": 0.23320382833480835, |
| "learning_rate": 4.302365223183245e-05, |
| "loss": 0.0802, |
| "mean_token_accuracy": 0.9677379101514816, |
| "num_tokens": 8022213.0, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.03869095598903756, |
| "grad_norm": 0.3808588683605194, |
| "learning_rate": 4.30228495622508e-05, |
| "loss": 0.0889, |
| "mean_token_accuracy": 0.9641236215829849, |
| "num_tokens": 8747043.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.04191520232145736, |
| "grad_norm": 0.22853593528270721, |
| "learning_rate": 4.302186024363927e-05, |
| "loss": 0.0646, |
| "mean_token_accuracy": 0.9733305871486664, |
| "num_tokens": 9486170.0, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.04513944865387716, |
| "grad_norm": 0.24544374644756317, |
| "learning_rate": 4.3020684287444245e-05, |
| "loss": 0.0712, |
| "mean_token_accuracy": 0.9715953677892685, |
| "num_tokens": 10206620.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.04836369498629695, |
| "grad_norm": 0.34427207708358765, |
| "learning_rate": 4.301932170727146e-05, |
| "loss": 0.0721, |
| "mean_token_accuracy": 0.9717811793088913, |
| "num_tokens": 10938645.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.05158794131871675, |
| "grad_norm": 0.20519210398197174, |
| "learning_rate": 4.301777251888592e-05, |
| "loss": 0.0689, |
| "mean_token_accuracy": 0.9724094599485398, |
| "num_tokens": 11679880.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.054812187651136546, |
| "grad_norm": 0.21787415444850922, |
| "learning_rate": 4.3016036740211645e-05, |
| "loss": 0.075, |
| "mean_token_accuracy": 0.9685328066349029, |
| "num_tokens": 12412547.0, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.058036433983556346, |
| "grad_norm": 0.2898290753364563, |
| "learning_rate": 4.301411439133152e-05, |
| "loss": 0.0697, |
| "mean_token_accuracy": 0.9726674944162369, |
| "num_tokens": 13150159.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.06126068031597614, |
| "grad_norm": 0.15527784824371338, |
| "learning_rate": 4.301200549448701e-05, |
| "loss": 0.0686, |
| "mean_token_accuracy": 0.9716294437646866, |
| "num_tokens": 13871058.0, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.06448492664839593, |
| "grad_norm": 0.2048763781785965, |
| "learning_rate": 4.3009710074077954e-05, |
| "loss": 0.0762, |
| "mean_token_accuracy": 0.9680916517972946, |
| "num_tokens": 14597194.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.06770917298081573, |
| "grad_norm": 0.1903521865606308, |
| "learning_rate": 4.300722815666225e-05, |
| "loss": 0.0747, |
| "mean_token_accuracy": 0.9690446943044663, |
| "num_tokens": 15327806.0, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.07093341931323553, |
| "grad_norm": 0.14261247217655182, |
| "learning_rate": 4.300455977095555e-05, |
| "loss": 0.0753, |
| "mean_token_accuracy": 0.968587601184845, |
| "num_tokens": 16049154.0, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.07415766564565533, |
| "grad_norm": 0.17354030907154083, |
| "learning_rate": 4.3001704947830955e-05, |
| "loss": 0.0702, |
| "mean_token_accuracy": 0.9707147300243377, |
| "num_tokens": 16785698.0, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.07738191197807512, |
| "grad_norm": 0.16438661515712738, |
| "learning_rate": 4.2998663720318625e-05, |
| "loss": 0.0674, |
| "mean_token_accuracy": 0.9719251215457916, |
| "num_tokens": 17510750.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.08060615831049492, |
| "grad_norm": 0.21964211761951447, |
| "learning_rate": 4.2995436123605394e-05, |
| "loss": 0.0723, |
| "mean_token_accuracy": 0.9695681571960449, |
| "num_tokens": 18235998.0, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.08383040464291472, |
| "grad_norm": 0.1920223981142044, |
| "learning_rate": 4.299202219503441e-05, |
| "loss": 0.0765, |
| "mean_token_accuracy": 0.9677397549152374, |
| "num_tokens": 18960307.0, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.08705465097533452, |
| "grad_norm": 0.14375026524066925, |
| "learning_rate": 4.298842197410466e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9733661621809006, |
| "num_tokens": 19687957.0, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.09027889730775432, |
| "grad_norm": 0.2611769139766693, |
| "learning_rate": 4.2984635502470506e-05, |
| "loss": 0.0756, |
| "mean_token_accuracy": 0.9715525269508362, |
| "num_tokens": 20412133.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.0935031436401741, |
| "grad_norm": 0.1805800348520279, |
| "learning_rate": 4.298066282394123e-05, |
| "loss": 0.0692, |
| "mean_token_accuracy": 0.9722744464874268, |
| "num_tokens": 21153754.0, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.0967273899725939, |
| "grad_norm": 0.17368192970752716, |
| "learning_rate": 4.297650398448054e-05, |
| "loss": 0.0618, |
| "mean_token_accuracy": 0.975834259390831, |
| "num_tokens": 21894414.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.0999516363050137, |
| "grad_norm": 0.1572069674730301, |
| "learning_rate": 4.2972159032206005e-05, |
| "loss": 0.0702, |
| "mean_token_accuracy": 0.970484247803688, |
| "num_tokens": 22613499.0, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.1031758826374335, |
| "grad_norm": 0.1375388503074646, |
| "learning_rate": 4.2967628017388484e-05, |
| "loss": 0.0736, |
| "mean_token_accuracy": 0.9691600769758224, |
| "num_tokens": 23331376.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.10640012896985329, |
| "grad_norm": 0.1216653436422348, |
| "learning_rate": 4.29629109924516e-05, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9721434324979782, |
| "num_tokens": 24071083.0, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.10962437530227309, |
| "grad_norm": 0.9317775964736938, |
| "learning_rate": 4.29580080119711e-05, |
| "loss": 0.0685, |
| "mean_token_accuracy": 0.9721974492073059, |
| "num_tokens": 24803462.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.11284862163469289, |
| "grad_norm": 0.22277843952178955, |
| "learning_rate": 4.295291913267422e-05, |
| "loss": 0.0706, |
| "mean_token_accuracy": 0.9698958814144134, |
| "num_tokens": 25542057.0, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.11607286796711269, |
| "grad_norm": 0.3321765661239624, |
| "learning_rate": 4.2947644413439034e-05, |
| "loss": 0.0691, |
| "mean_token_accuracy": 0.9702872037887573, |
| "num_tokens": 26285545.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.11929711429953248, |
| "grad_norm": 0.18703341484069824, |
| "learning_rate": 4.2942183915293785e-05, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9723541676998139, |
| "num_tokens": 27014117.0, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.12252136063195228, |
| "grad_norm": 0.1807422786951065, |
| "learning_rate": 4.293653770141616e-05, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9723337739706039, |
| "num_tokens": 27744492.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.12574560696437206, |
| "grad_norm": 0.13952040672302246, |
| "learning_rate": 4.293070583713258e-05, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9743919491767883, |
| "num_tokens": 28481364.0, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.12896985329679186, |
| "grad_norm": 0.19058330357074738, |
| "learning_rate": 4.29246883899174e-05, |
| "loss": 0.0734, |
| "mean_token_accuracy": 0.9683070838451385, |
| "num_tokens": 29208112.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.13219409962921166, |
| "grad_norm": 0.15498676896095276, |
| "learning_rate": 4.2918485429392204e-05, |
| "loss": 0.0683, |
| "mean_token_accuracy": 0.9714304149150849, |
| "num_tokens": 29938685.0, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.13541834596163146, |
| "grad_norm": 0.1610540896654129, |
| "learning_rate": 4.291209702732493e-05, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9709137052297592, |
| "num_tokens": 30657257.0, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.13864259229405126, |
| "grad_norm": 0.12342345714569092, |
| "learning_rate": 4.2905523257629056e-05, |
| "loss": 0.0716, |
| "mean_token_accuracy": 0.9698014497756958, |
| "num_tokens": 31382107.0, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.14186683862647106, |
| "grad_norm": 0.1735985279083252, |
| "learning_rate": 4.289876419636279e-05, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.9729118138551712, |
| "num_tokens": 32105733.0, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.14509108495889086, |
| "grad_norm": 0.19640210270881653, |
| "learning_rate": 4.2891819921728114e-05, |
| "loss": 0.0649, |
| "mean_token_accuracy": 0.9733746379613877, |
| "num_tokens": 32837802.0, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.14831533129131066, |
| "grad_norm": 0.15321972966194153, |
| "learning_rate": 4.2884690514069946e-05, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.9712770462036133, |
| "num_tokens": 33572135.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.15153957762373046, |
| "grad_norm": 0.15838782489299774, |
| "learning_rate": 4.287737605587518e-05, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9747976720333099, |
| "num_tokens": 34308652.0, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.15476382395615024, |
| "grad_norm": 0.13345415890216827, |
| "learning_rate": 4.286987663177172e-05, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9745038419961929, |
| "num_tokens": 35053302.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.15798807028857004, |
| "grad_norm": 0.2872984707355499, |
| "learning_rate": 4.286219232852754e-05, |
| "loss": 0.0694, |
| "mean_token_accuracy": 0.9724238455295563, |
| "num_tokens": 35787936.0, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.16121231662098984, |
| "grad_norm": 0.139503613114357, |
| "learning_rate": 4.285432323504962e-05, |
| "loss": 0.0668, |
| "mean_token_accuracy": 0.9725244224071503, |
| "num_tokens": 36504092.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.16443656295340964, |
| "grad_norm": 0.14141756296157837, |
| "learning_rate": 4.2846269442383e-05, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9708920598030091, |
| "num_tokens": 37225880.0, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.16766080928582944, |
| "grad_norm": 0.1549311876296997, |
| "learning_rate": 4.2838031043709655e-05, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.9724831134080887, |
| "num_tokens": 37959532.0, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.17088505561824924, |
| "grad_norm": 0.15312710404396057, |
| "learning_rate": 4.282960813434744e-05, |
| "loss": 0.0543, |
| "mean_token_accuracy": 0.9767305910587311, |
| "num_tokens": 38690554.0, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.17410930195066904, |
| "grad_norm": 0.13787440955638885, |
| "learning_rate": 4.2821000811748986e-05, |
| "loss": 0.0691, |
| "mean_token_accuracy": 0.9714402705430984, |
| "num_tokens": 39408048.0, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.17733354828308884, |
| "grad_norm": 0.15318097174167633, |
| "learning_rate": 4.28122091755006e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9729239106178283, |
| "num_tokens": 40141249.0, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.18055779461550864, |
| "grad_norm": 0.15318745374679565, |
| "learning_rate": 4.2803233327321063e-05, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.974094209074974, |
| "num_tokens": 40869706.0, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.1837820409479284, |
| "grad_norm": 0.16698147356510162, |
| "learning_rate": 4.279407337106049e-05, |
| "loss": 0.0675, |
| "mean_token_accuracy": 0.9720869123935699, |
| "num_tokens": 41606160.0, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.1870062872803482, |
| "grad_norm": 0.16875316202640533, |
| "learning_rate": 4.278472941269912e-05, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9723375588655472, |
| "num_tokens": 42341009.0, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.190230533612768, |
| "grad_norm": 0.1910078227519989, |
| "learning_rate": 4.277520156034608e-05, |
| "loss": 0.0601, |
| "mean_token_accuracy": 0.9752542525529861, |
| "num_tokens": 43087520.0, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.1934547799451878, |
| "grad_norm": 0.0923197939991951, |
| "learning_rate": 4.276548992423814e-05, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9712740182876587, |
| "num_tokens": 43808805.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.1966790262776076, |
| "grad_norm": 0.16223445534706116, |
| "learning_rate": 4.275559461673846e-05, |
| "loss": 0.0647, |
| "mean_token_accuracy": 0.9726371496915818, |
| "num_tokens": 44527104.0, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.1999032726100274, |
| "grad_norm": 0.16872785985469818, |
| "learning_rate": 4.274551575233523e-05, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9726080656051636, |
| "num_tokens": 45263267.0, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.2031275189424472, |
| "grad_norm": 0.15380911529064178, |
| "learning_rate": 4.273525344764042e-05, |
| "loss": 0.0691, |
| "mean_token_accuracy": 0.9706686109304428, |
| "num_tokens": 45983898.0, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.206351765274867, |
| "grad_norm": 0.22732405364513397, |
| "learning_rate": 4.2724807821388375e-05, |
| "loss": 0.0667, |
| "mean_token_accuracy": 0.9715253829956054, |
| "num_tokens": 46718475.0, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.20957601160728678, |
| "grad_norm": 0.16602182388305664, |
| "learning_rate": 4.271417899443447e-05, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.972316575050354, |
| "num_tokens": 47441264.0, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.21280025793970658, |
| "grad_norm": 0.12711510062217712, |
| "learning_rate": 4.27033670897537e-05, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.9729165524244309, |
| "num_tokens": 48159181.0, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.21602450427212638, |
| "grad_norm": 0.3739318251609802, |
| "learning_rate": 4.269237223243926e-05, |
| "loss": 0.0706, |
| "mean_token_accuracy": 0.9707489520311355, |
| "num_tokens": 48875182.0, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.21924875060454618, |
| "grad_norm": 0.1314387321472168, |
| "learning_rate": 4.2681194549701104e-05, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.9747117280960083, |
| "num_tokens": 49600535.0, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.22247299693696598, |
| "grad_norm": 0.1354706883430481, |
| "learning_rate": 4.266983417086445e-05, |
| "loss": 0.0608, |
| "mean_token_accuracy": 0.975371116399765, |
| "num_tokens": 50334591.0, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.22569724326938578, |
| "grad_norm": 0.1258992850780487, |
| "learning_rate": 4.2658291227368315e-05, |
| "loss": 0.0656, |
| "mean_token_accuracy": 0.9733656644821167, |
| "num_tokens": 51077899.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.22892148960180558, |
| "grad_norm": 0.15256090462207794, |
| "learning_rate": 4.264656585276398e-05, |
| "loss": 0.0629, |
| "mean_token_accuracy": 0.9734154403209686, |
| "num_tokens": 51801544.0, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.23214573593422538, |
| "grad_norm": 0.11889924854040146, |
| "learning_rate": 4.263465818271344e-05, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.974933260679245, |
| "num_tokens": 52529112.0, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.23536998226664518, |
| "grad_norm": 0.18661753833293915, |
| "learning_rate": 4.262256835498784e-05, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9727526873350143, |
| "num_tokens": 53265856.0, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.23859422859906496, |
| "grad_norm": 0.1207657903432846, |
| "learning_rate": 4.26102965094659e-05, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.9726086676120758, |
| "num_tokens": 53995495.0, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.24181847493148476, |
| "grad_norm": 0.10631874948740005, |
| "learning_rate": 4.259784278813222e-05, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9738115847110749, |
| "num_tokens": 54725508.0, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.24504272126390456, |
| "grad_norm": 0.18724201619625092, |
| "learning_rate": 4.2585207335075764e-05, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9734448730945587, |
| "num_tokens": 55450272.0, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.24826696759632436, |
| "grad_norm": 0.20387601852416992, |
| "learning_rate": 4.257239029648807e-05, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9720923036336899, |
| "num_tokens": 56180775.0, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.25149121392874413, |
| "grad_norm": 0.13501635193824768, |
| "learning_rate": 4.2559391820661654e-05, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9709636747837067, |
| "num_tokens": 56908627.0, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.25471546026116393, |
| "grad_norm": 0.11911208927631378, |
| "learning_rate": 4.254621205798821e-05, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.9730106085538864, |
| "num_tokens": 57638628.0, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.25793970659358373, |
| "grad_norm": 0.1691109538078308, |
| "learning_rate": 4.253285116095694e-05, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.972708734869957, |
| "num_tokens": 58365656.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.26116395292600353, |
| "grad_norm": 0.10465984791517258, |
| "learning_rate": 4.2519309284152756e-05, |
| "loss": 0.0581, |
| "mean_token_accuracy": 0.9759684473276138, |
| "num_tokens": 59107103.0, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.26438819925842333, |
| "grad_norm": 0.253064900636673, |
| "learning_rate": 4.2505586584254484e-05, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9720677107572555, |
| "num_tokens": 59832406.0, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.26761244559084313, |
| "grad_norm": 0.11247489601373672, |
| "learning_rate": 4.249168322003309e-05, |
| "loss": 0.0579, |
| "mean_token_accuracy": 0.9755258798599243, |
| "num_tokens": 60564474.0, |
| "step": 415 |
| }, |
| { |
| "epoch": 0.27083669192326293, |
| "grad_norm": 0.15882624685764313, |
| "learning_rate": 4.247759935234978e-05, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.973927104473114, |
| "num_tokens": 61293750.0, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.27406093825568273, |
| "grad_norm": 0.12057185173034668, |
| "learning_rate": 4.246333514415422e-05, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9734469711780548, |
| "num_tokens": 62019546.0, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.27728518458810253, |
| "grad_norm": 0.08422806113958359, |
| "learning_rate": 4.244889076048258e-05, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9740317106246948, |
| "num_tokens": 62741180.0, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.28050943092052233, |
| "grad_norm": 0.14682124555110931, |
| "learning_rate": 4.2434266368455634e-05, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9751890152692795, |
| "num_tokens": 63462933.0, |
| "step": 435 |
| }, |
| { |
| "epoch": 0.28373367725294213, |
| "grad_norm": 0.10189901292324066, |
| "learning_rate": 4.2419462137276873e-05, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.974117973446846, |
| "num_tokens": 64190749.0, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.28695792358536193, |
| "grad_norm": 0.12200498580932617, |
| "learning_rate": 4.2404478238230534e-05, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9738726019859314, |
| "num_tokens": 64930451.0, |
| "step": 445 |
| }, |
| { |
| "epoch": 0.29018216991778173, |
| "grad_norm": 0.1749802827835083, |
| "learning_rate": 4.238931484467956e-05, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9700275152921677, |
| "num_tokens": 65652079.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.29340641625020153, |
| "grad_norm": 0.12457408756017685, |
| "learning_rate": 4.237397213206365e-05, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.9739457339048385, |
| "num_tokens": 66391913.0, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.29663066258262133, |
| "grad_norm": 0.17556531727313995, |
| "learning_rate": 4.2358450277897233e-05, |
| "loss": 0.062, |
| "mean_token_accuracy": 0.9740994036197662, |
| "num_tokens": 67121233.0, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.29985490891504113, |
| "grad_norm": 0.08802030235528946, |
| "learning_rate": 4.234274946176737e-05, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.973410251736641, |
| "num_tokens": 67846130.0, |
| "step": 465 |
| }, |
| { |
| "epoch": 0.30307915524746093, |
| "grad_norm": 0.15161827206611633, |
| "learning_rate": 4.232686986533173e-05, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9774506956338882, |
| "num_tokens": 68573027.0, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.30630340157988073, |
| "grad_norm": 0.16815979778766632, |
| "learning_rate": 4.2310811672316435e-05, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9780906915664673, |
| "num_tokens": 69308362.0, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.3095276479123005, |
| "grad_norm": 0.1395406574010849, |
| "learning_rate": 4.2294575068513986e-05, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9726277559995651, |
| "num_tokens": 70030011.0, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.3127518942447203, |
| "grad_norm": 0.14498509466648102, |
| "learning_rate": 4.2278160241781064e-05, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9739683717489243, |
| "num_tokens": 70760432.0, |
| "step": 485 |
| }, |
| { |
| "epoch": 0.3159761405771401, |
| "grad_norm": 0.14577502012252808, |
| "learning_rate": 4.226156738203641e-05, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9720825880765915, |
| "num_tokens": 71491108.0, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.3192003869095599, |
| "grad_norm": 0.13644428551197052, |
| "learning_rate": 4.224479668125856e-05, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9758222311735153, |
| "num_tokens": 72225867.0, |
| "step": 495 |
| }, |
| { |
| "epoch": 0.3224246332419797, |
| "grad_norm": 0.10150418430566788, |
| "learning_rate": 4.222784833348368e-05, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.9766907751560211, |
| "num_tokens": 72968261.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3256488795743995, |
| "grad_norm": 0.10697796940803528, |
| "learning_rate": 4.221072253480333e-05, |
| "loss": 0.0703, |
| "mean_token_accuracy": 0.9705935716629028, |
| "num_tokens": 73685899.0, |
| "step": 505 |
| }, |
| { |
| "epoch": 0.3288731259068193, |
| "grad_norm": 0.11026358604431152, |
| "learning_rate": 4.2193419483362116e-05, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.9742098599672318, |
| "num_tokens": 74424786.0, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.3320973722392391, |
| "grad_norm": 0.12913760542869568, |
| "learning_rate": 4.2175939379355486e-05, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.9749146044254303, |
| "num_tokens": 75162166.0, |
| "step": 515 |
| }, |
| { |
| "epoch": 0.3353216185716589, |
| "grad_norm": 0.10811374336481094, |
| "learning_rate": 4.215828242502738e-05, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.9763716220855713, |
| "num_tokens": 75888347.0, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.3385458649040787, |
| "grad_norm": 0.10078359395265579, |
| "learning_rate": 4.214044882466785e-05, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9728367298841476, |
| "num_tokens": 76615859.0, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.3417701112364985, |
| "grad_norm": 0.13031820952892303, |
| "learning_rate": 4.212243878461078e-05, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9758937656879425, |
| "num_tokens": 77342829.0, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.3449943575689183, |
| "grad_norm": 0.2067982256412506, |
| "learning_rate": 4.210425251323142e-05, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9764239996671676, |
| "num_tokens": 78067626.0, |
| "step": 535 |
| }, |
| { |
| "epoch": 0.3482186039013381, |
| "grad_norm": 0.11824314296245575, |
| "learning_rate": 4.208589022094403e-05, |
| "loss": 0.0694, |
| "mean_token_accuracy": 0.9704160928726197, |
| "num_tokens": 78799895.0, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.3514428502337579, |
| "grad_norm": 0.14301714301109314, |
| "learning_rate": 4.206735212019939e-05, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9752708166837692, |
| "num_tokens": 79531712.0, |
| "step": 545 |
| }, |
| { |
| "epoch": 0.3546670965661777, |
| "grad_norm": 0.1193031519651413, |
| "learning_rate": 4.2048638425482417e-05, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9734661519527436, |
| "num_tokens": 80258961.0, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.3578913428985975, |
| "grad_norm": 0.20954956114292145, |
| "learning_rate": 4.202974935330961e-05, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.972682648897171, |
| "num_tokens": 80976672.0, |
| "step": 555 |
| }, |
| { |
| "epoch": 0.3611155892310173, |
| "grad_norm": 0.135671466588974, |
| "learning_rate": 4.2010685122226597e-05, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9713925391435623, |
| "num_tokens": 81703810.0, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.364339835563437, |
| "grad_norm": 0.14131806790828705, |
| "learning_rate": 4.1991445952805565e-05, |
| "loss": 0.0604, |
| "mean_token_accuracy": 0.9750127166509628, |
| "num_tokens": 82436820.0, |
| "step": 565 |
| }, |
| { |
| "epoch": 0.3675640818958568, |
| "grad_norm": 0.14103299379348755, |
| "learning_rate": 4.197203206764275e-05, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9745763689279556, |
| "num_tokens": 83169310.0, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.3707883282282766, |
| "grad_norm": 0.12783531844615936, |
| "learning_rate": 4.1952443691355826e-05, |
| "loss": 0.0639, |
| "mean_token_accuracy": 0.9733170062303543, |
| "num_tokens": 83896797.0, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.3740125745606964, |
| "grad_norm": 0.10604380816221237, |
| "learning_rate": 4.193268105058133e-05, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9723539561033249, |
| "num_tokens": 84613555.0, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.3772368208931162, |
| "grad_norm": 0.11026538908481598, |
| "learning_rate": 4.1912744373972015e-05, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9706546932458877, |
| "num_tokens": 85340284.0, |
| "step": 585 |
| }, |
| { |
| "epoch": 0.380461067225536, |
| "grad_norm": 0.09437953680753708, |
| "learning_rate": 4.189263389219424e-05, |
| "loss": 0.0629, |
| "mean_token_accuracy": 0.9742907851934433, |
| "num_tokens": 86078323.0, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.3836853135579558, |
| "grad_norm": 0.1255396157503128, |
| "learning_rate": 4.187234983792527e-05, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.9737410217523574, |
| "num_tokens": 86816403.0, |
| "step": 595 |
| }, |
| { |
| "epoch": 0.3869095598903756, |
| "grad_norm": 0.16567674279212952, |
| "learning_rate": 4.1851892445850594e-05, |
| "loss": 0.0613, |
| "mean_token_accuracy": 0.9747896641492844, |
| "num_tokens": 87555519.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3901338062227954, |
| "grad_norm": 0.10595999658107758, |
| "learning_rate": 4.1831261952661216e-05, |
| "loss": 0.0507, |
| "mean_token_accuracy": 0.9782363474369049, |
| "num_tokens": 88298463.0, |
| "step": 605 |
| }, |
| { |
| "epoch": 0.3933580525552152, |
| "grad_norm": 0.09750993549823761, |
| "learning_rate": 4.18104585970509e-05, |
| "loss": 0.0575, |
| "mean_token_accuracy": 0.975985461473465, |
| "num_tokens": 89028888.0, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.396582298887635, |
| "grad_norm": 0.12475121021270752, |
| "learning_rate": 4.178948261971345e-05, |
| "loss": 0.062, |
| "mean_token_accuracy": 0.9743737548589706, |
| "num_tokens": 89760651.0, |
| "step": 615 |
| }, |
| { |
| "epoch": 0.3998065452200548, |
| "grad_norm": 0.11872947961091995, |
| "learning_rate": 4.176833426333984e-05, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9756663322448731, |
| "num_tokens": 90485352.0, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.4030307915524746, |
| "grad_norm": 0.11223915219306946, |
| "learning_rate": 4.174701377261552e-05, |
| "loss": 0.062, |
| "mean_token_accuracy": 0.9732966214418411, |
| "num_tokens": 91209769.0, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.4062550378848944, |
| "grad_norm": 0.13918088376522064, |
| "learning_rate": 4.1725521394217485e-05, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9763846278190613, |
| "num_tokens": 91942349.0, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.4094792842173142, |
| "grad_norm": 0.12490855902433395, |
| "learning_rate": 4.170385737681149e-05, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9740516632795334, |
| "num_tokens": 92662611.0, |
| "step": 635 |
| }, |
| { |
| "epoch": 0.412703530549734, |
| "grad_norm": 0.09874217957258224, |
| "learning_rate": 4.168202197104912e-05, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.975362378358841, |
| "num_tokens": 93387564.0, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.4159277768821538, |
| "grad_norm": 0.1340876966714859, |
| "learning_rate": 4.1660015429564924e-05, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9731069415807724, |
| "num_tokens": 94116818.0, |
| "step": 645 |
| }, |
| { |
| "epoch": 0.41915202321457357, |
| "grad_norm": 0.12417148053646088, |
| "learning_rate": 4.1637838006973494e-05, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9740182787179947, |
| "num_tokens": 94854265.0, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.42237626954699337, |
| "grad_norm": 0.17307128012180328, |
| "learning_rate": 4.1615489959866496e-05, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9740953654050827, |
| "num_tokens": 95580393.0, |
| "step": 655 |
| }, |
| { |
| "epoch": 0.42560051587941317, |
| "grad_norm": 0.10412634164094925, |
| "learning_rate": 4.15929715468097e-05, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9746391087770462, |
| "num_tokens": 96294962.0, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.42882476221183297, |
| "grad_norm": 0.12138034403324127, |
| "learning_rate": 4.157028302834004e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9740571856498719, |
| "num_tokens": 97017073.0, |
| "step": 665 |
| }, |
| { |
| "epoch": 0.43204900854425277, |
| "grad_norm": 0.10229659825563431, |
| "learning_rate": 4.1547424666962525e-05, |
| "loss": 0.0512, |
| "mean_token_accuracy": 0.9782384634017944, |
| "num_tokens": 97753854.0, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.43527325487667257, |
| "grad_norm": 0.17478016018867493, |
| "learning_rate": 4.1524396727147245e-05, |
| "loss": 0.0694, |
| "mean_token_accuracy": 0.9710026443004608, |
| "num_tokens": 98473379.0, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.43849750120909237, |
| "grad_norm": 0.10365957766771317, |
| "learning_rate": 4.150119947532633e-05, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9736609309911728, |
| "num_tokens": 99197861.0, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.44172174754151217, |
| "grad_norm": 0.09307665377855301, |
| "learning_rate": 4.14778331798908e-05, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.9752078175544738, |
| "num_tokens": 99927410.0, |
| "step": 685 |
| }, |
| { |
| "epoch": 0.44494599387393197, |
| "grad_norm": 0.10004657506942749, |
| "learning_rate": 4.145429811118753e-05, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.97312690615654, |
| "num_tokens": 100654823.0, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.44817024020635177, |
| "grad_norm": 0.12376191467046738, |
| "learning_rate": 4.1430594541516084e-05, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9725204706192017, |
| "num_tokens": 101386656.0, |
| "step": 695 |
| }, |
| { |
| "epoch": 0.45139448653877157, |
| "grad_norm": 0.08985437452793121, |
| "learning_rate": 4.1406722745125585e-05, |
| "loss": 0.0524, |
| "mean_token_accuracy": 0.9779430210590363, |
| "num_tokens": 102120872.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.45461873287119137, |
| "grad_norm": 0.11451315879821777, |
| "learning_rate": 4.138268299821151e-05, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9757345408201218, |
| "num_tokens": 102853071.0, |
| "step": 705 |
| }, |
| { |
| "epoch": 0.45784297920361117, |
| "grad_norm": 0.15400256216526031, |
| "learning_rate": 4.1358475578912534e-05, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9749639600515365, |
| "num_tokens": 103576383.0, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.46106722553603097, |
| "grad_norm": 0.11995352804660797, |
| "learning_rate": 4.133410076730729e-05, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9736157178878784, |
| "num_tokens": 104293237.0, |
| "step": 715 |
| }, |
| { |
| "epoch": 0.46429147186845077, |
| "grad_norm": 0.08469699323177338, |
| "learning_rate": 4.130955884541111e-05, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.9744376480579376, |
| "num_tokens": 105031010.0, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.46751571820087057, |
| "grad_norm": 0.09692473709583282, |
| "learning_rate": 4.1284850097172804e-05, |
| "loss": 0.0553, |
| "mean_token_accuracy": 0.9762725323438645, |
| "num_tokens": 105760641.0, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.47073996453329037, |
| "grad_norm": 0.09011492878198624, |
| "learning_rate": 4.125997480847136e-05, |
| "loss": 0.0558, |
| "mean_token_accuracy": 0.976738840341568, |
| "num_tokens": 106491430.0, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.47396421086571017, |
| "grad_norm": 0.12184922397136688, |
| "learning_rate": 4.123493326711262e-05, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9732057601213455, |
| "num_tokens": 107229063.0, |
| "step": 735 |
| }, |
| { |
| "epoch": 0.4771884571981299, |
| "grad_norm": 0.1055496484041214, |
| "learning_rate": 4.1209725762825954e-05, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.9749337404966354, |
| "num_tokens": 107958204.0, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.4804127035305497, |
| "grad_norm": 0.12146985530853271, |
| "learning_rate": 4.118435258726094e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.975829216837883, |
| "num_tokens": 108692015.0, |
| "step": 745 |
| }, |
| { |
| "epoch": 0.4836369498629695, |
| "grad_norm": 0.12897175550460815, |
| "learning_rate": 4.115881403398393e-05, |
| "loss": 0.0647, |
| "mean_token_accuracy": 0.9725025862455368, |
| "num_tokens": 109415596.0, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.4868611961953893, |
| "grad_norm": 0.0979715958237648, |
| "learning_rate": 4.113311039847473e-05, |
| "loss": 0.0654, |
| "mean_token_accuracy": 0.9734069854021072, |
| "num_tokens": 110136146.0, |
| "step": 755 |
| }, |
| { |
| "epoch": 0.4900854425278091, |
| "grad_norm": 0.11269300431013107, |
| "learning_rate": 4.110724197812309e-05, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.974292179942131, |
| "num_tokens": 110868026.0, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.4933096888602289, |
| "grad_norm": 0.09567351639270782, |
| "learning_rate": 4.108120907222535e-05, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9768704831600189, |
| "num_tokens": 111603839.0, |
| "step": 765 |
| }, |
| { |
| "epoch": 0.4965339351926487, |
| "grad_norm": 0.11402782797813416, |
| "learning_rate": 4.105501198198092e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9739162504673005, |
| "num_tokens": 112331166.0, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.4997581815250685, |
| "grad_norm": 0.11442290991544724, |
| "learning_rate": 4.1028651010488824e-05, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.9752083033323288, |
| "num_tokens": 113066504.0, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.5029824278574883, |
| "grad_norm": 0.07549504935741425, |
| "learning_rate": 4.100212646274418e-05, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9739601790904999, |
| "num_tokens": 113796840.0, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.5062066741899081, |
| "grad_norm": 0.10361034423112869, |
| "learning_rate": 4.097543864563469e-05, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.9740029215812683, |
| "num_tokens": 114525882.0, |
| "step": 785 |
| }, |
| { |
| "epoch": 0.5094309205223279, |
| "grad_norm": 0.11914239823818207, |
| "learning_rate": 4.094858786793704e-05, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9764070302248001, |
| "num_tokens": 115259289.0, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.5126551668547477, |
| "grad_norm": 0.15590986609458923, |
| "learning_rate": 4.092157444031339e-05, |
| "loss": 0.0526, |
| "mean_token_accuracy": 0.9773574352264405, |
| "num_tokens": 115976517.0, |
| "step": 795 |
| }, |
| { |
| "epoch": 0.5158794131871675, |
| "grad_norm": 0.13714982569217682, |
| "learning_rate": 4.089439867530776e-05, |
| "loss": 0.0632, |
| "mean_token_accuracy": 0.9732331067323685, |
| "num_tokens": 116703332.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5191036595195873, |
| "grad_norm": 0.18109770119190216, |
| "learning_rate": 4.086706088734236e-05, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.974717378616333, |
| "num_tokens": 117439264.0, |
| "step": 805 |
| }, |
| { |
| "epoch": 0.5223279058520071, |
| "grad_norm": 0.12190018594264984, |
| "learning_rate": 4.083956139271405e-05, |
| "loss": 0.062, |
| "mean_token_accuracy": 0.9733976423740387, |
| "num_tokens": 118157529.0, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.5255521521844269, |
| "grad_norm": 1.4948625564575195, |
| "learning_rate": 4.0811900509590594e-05, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.972923320531845, |
| "num_tokens": 118892000.0, |
| "step": 815 |
| }, |
| { |
| "epoch": 0.5287763985168467, |
| "grad_norm": 0.15420867502689362, |
| "learning_rate": 4.078407855800703e-05, |
| "loss": 0.056, |
| "mean_token_accuracy": 0.9755813509225846, |
| "num_tokens": 119630122.0, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.5320006448492665, |
| "grad_norm": 5.479248523712158, |
| "learning_rate": 4.075609585986194e-05, |
| "loss": 0.2041, |
| "mean_token_accuracy": 0.9607071220874787, |
| "num_tokens": 120355550.0, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.5352248911816863, |
| "grad_norm": 2.9923651218414307, |
| "learning_rate": 4.072795273891374e-05, |
| "loss": 0.0924, |
| "mean_token_accuracy": 0.9644988238811493, |
| "num_tokens": 121096095.0, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.5384491375141061, |
| "grad_norm": 0.2814148962497711, |
| "learning_rate": 4.069964952077694e-05, |
| "loss": 0.1701, |
| "mean_token_accuracy": 0.9500577867031097, |
| "num_tokens": 121817699.0, |
| "step": 835 |
| }, |
| { |
| "epoch": 0.5416733838465259, |
| "grad_norm": 0.17147469520568848, |
| "learning_rate": 4.0671186532918334e-05, |
| "loss": 0.0675, |
| "mean_token_accuracy": 0.9733231544494629, |
| "num_tokens": 122553626.0, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.5448976301789457, |
| "grad_norm": 0.1561255007982254, |
| "learning_rate": 4.0642564104653276e-05, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9720387786626816, |
| "num_tokens": 123275088.0, |
| "step": 845 |
| }, |
| { |
| "epoch": 0.5481218765113655, |
| "grad_norm": 0.14188043773174286, |
| "learning_rate": 4.061378256714183e-05, |
| "loss": 0.0729, |
| "mean_token_accuracy": 0.969955912232399, |
| "num_tokens": 123990621.0, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.5513461228437853, |
| "grad_norm": 1.8831955194473267, |
| "learning_rate": 4.0584842253384946e-05, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9747799843549728, |
| "num_tokens": 124727424.0, |
| "step": 855 |
| }, |
| { |
| "epoch": 0.5545703691762051, |
| "grad_norm": 0.11637420952320099, |
| "learning_rate": 4.055574349822059e-05, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9740211457014084, |
| "num_tokens": 125449008.0, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.5577946155086249, |
| "grad_norm": 0.18863286077976227, |
| "learning_rate": 4.0526486638319917e-05, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.9758910685777664, |
| "num_tokens": 126175668.0, |
| "step": 865 |
| }, |
| { |
| "epoch": 0.5610188618410447, |
| "grad_norm": 0.15095947682857513, |
| "learning_rate": 4.049707201218332e-05, |
| "loss": 0.0563, |
| "mean_token_accuracy": 0.9765735059976578, |
| "num_tokens": 126910909.0, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.5642431081734645, |
| "grad_norm": 0.09274408221244812, |
| "learning_rate": 4.0467499960136554e-05, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9736385405063629, |
| "num_tokens": 127640373.0, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.5674673545058843, |
| "grad_norm": 0.106238953769207, |
| "learning_rate": 4.043777082432678e-05, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9742357492446899, |
| "num_tokens": 128370087.0, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.5706916008383041, |
| "grad_norm": 0.14274533092975616, |
| "learning_rate": 4.04078849487186e-05, |
| "loss": 0.0629, |
| "mean_token_accuracy": 0.97292540371418, |
| "num_tokens": 129093018.0, |
| "step": 885 |
| }, |
| { |
| "epoch": 0.5739158471707239, |
| "grad_norm": 0.13243994116783142, |
| "learning_rate": 4.037784267909011e-05, |
| "loss": 0.0561, |
| "mean_token_accuracy": 0.9757737427949905, |
| "num_tokens": 129835126.0, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.5771400935031437, |
| "grad_norm": 0.09315911680459976, |
| "learning_rate": 4.034764436302887e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9727118164300919, |
| "num_tokens": 130549458.0, |
| "step": 895 |
| }, |
| { |
| "epoch": 0.5803643398355635, |
| "grad_norm": 0.12023934721946716, |
| "learning_rate": 4.031729034992786e-05, |
| "loss": 0.0687, |
| "mean_token_accuracy": 0.9711138665676117, |
| "num_tokens": 131273013.0, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5835885861679833, |
| "grad_norm": 0.1302732527256012, |
| "learning_rate": 4.028678099098151e-05, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9736036390066147, |
| "num_tokens": 131992225.0, |
| "step": 905 |
| }, |
| { |
| "epoch": 0.5868128325004031, |
| "grad_norm": 0.09622636437416077, |
| "learning_rate": 4.0256116639181565e-05, |
| "loss": 0.0546, |
| "mean_token_accuracy": 0.9765114486217499, |
| "num_tokens": 132724722.0, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.5900370788328229, |
| "grad_norm": 0.13748367130756378, |
| "learning_rate": 4.022529764931304e-05, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9739679545164108, |
| "num_tokens": 133446709.0, |
| "step": 915 |
| }, |
| { |
| "epoch": 0.5932613251652427, |
| "grad_norm": 0.15531542897224426, |
| "learning_rate": 4.019432437795011e-05, |
| "loss": 0.0612, |
| "mean_token_accuracy": 0.9730135977268219, |
| "num_tokens": 134177548.0, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.5964855714976625, |
| "grad_norm": 0.12013308703899384, |
| "learning_rate": 4.016319718345197e-05, |
| "loss": 0.0593, |
| "mean_token_accuracy": 0.9753940135240555, |
| "num_tokens": 134911425.0, |
| "step": 925 |
| }, |
| { |
| "epoch": 0.5997098178300823, |
| "grad_norm": 0.09899429976940155, |
| "learning_rate": 4.013191642595869e-05, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.9756023168563843, |
| "num_tokens": 135639051.0, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.6029340641625021, |
| "grad_norm": 0.11556148529052734, |
| "learning_rate": 4.010048246738708e-05, |
| "loss": 0.0512, |
| "mean_token_accuracy": 0.9782331466674805, |
| "num_tokens": 136370884.0, |
| "step": 935 |
| }, |
| { |
| "epoch": 0.6061583104949219, |
| "grad_norm": 0.13518720865249634, |
| "learning_rate": 4.006889567142647e-05, |
| "loss": 0.0596, |
| "mean_token_accuracy": 0.9748345911502838, |
| "num_tokens": 137102449.0, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.6093825568273417, |
| "grad_norm": 0.14354024827480316, |
| "learning_rate": 4.003715640353449e-05, |
| "loss": 0.0526, |
| "mean_token_accuracy": 0.9776305526494979, |
| "num_tokens": 137834569.0, |
| "step": 945 |
| }, |
| { |
| "epoch": 0.6126068031597615, |
| "grad_norm": 0.08364211022853851, |
| "learning_rate": 4.000526503093289e-05, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.975365337729454, |
| "num_tokens": 138564380.0, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.6158310494921811, |
| "grad_norm": 0.0881267711520195, |
| "learning_rate": 3.9973221922603244e-05, |
| "loss": 0.0569, |
| "mean_token_accuracy": 0.9754378288984299, |
| "num_tokens": 139287721.0, |
| "step": 955 |
| }, |
| { |
| "epoch": 0.619055295824601, |
| "grad_norm": 0.11913862079381943, |
| "learning_rate": 3.994102744928272e-05, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9764246821403504, |
| "num_tokens": 140015549.0, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.6222795421570207, |
| "grad_norm": 0.08860793709754944, |
| "learning_rate": 3.990868198345976e-05, |
| "loss": 0.0543, |
| "mean_token_accuracy": 0.9772022932767868, |
| "num_tokens": 140758991.0, |
| "step": 965 |
| }, |
| { |
| "epoch": 0.6255037884894405, |
| "grad_norm": 0.10398126393556595, |
| "learning_rate": 3.987618589936978e-05, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.9742362201213837, |
| "num_tokens": 141482633.0, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.6287280348218603, |
| "grad_norm": 0.10214198380708694, |
| "learning_rate": 3.984353957299084e-05, |
| "loss": 0.0558, |
| "mean_token_accuracy": 0.9760869711637497, |
| "num_tokens": 142193074.0, |
| "step": 975 |
| }, |
| { |
| "epoch": 0.6319522811542801, |
| "grad_norm": 0.10672972351312637, |
| "learning_rate": 3.9810743382039316e-05, |
| "loss": 0.0561, |
| "mean_token_accuracy": 0.9752664715051651, |
| "num_tokens": 142922713.0, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.6351765274867, |
| "grad_norm": 0.08451476693153381, |
| "learning_rate": 3.9777797705965474e-05, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.9767779380083084, |
| "num_tokens": 143654550.0, |
| "step": 985 |
| }, |
| { |
| "epoch": 0.6384007738191197, |
| "grad_norm": 0.12329498678445816, |
| "learning_rate": 3.974470292594914e-05, |
| "loss": 0.052, |
| "mean_token_accuracy": 0.97784683406353, |
| "num_tokens": 144388328.0, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.6416250201515395, |
| "grad_norm": 0.1205015704035759, |
| "learning_rate": 3.971145942489528e-05, |
| "loss": 0.0604, |
| "mean_token_accuracy": 0.9733536690473557, |
| "num_tokens": 145125496.0, |
| "step": 995 |
| }, |
| { |
| "epoch": 0.6448492664839593, |
| "grad_norm": 0.12141783535480499, |
| "learning_rate": 3.967806758742951e-05, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9732593297958374, |
| "num_tokens": 145857914.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.6480735128163791, |
| "grad_norm": 0.1378411203622818, |
| "learning_rate": 3.964452779989373e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9755557864904404, |
| "num_tokens": 146580939.0, |
| "step": 1005 |
| }, |
| { |
| "epoch": 0.651297759148799, |
| "grad_norm": 0.14128369092941284, |
| "learning_rate": 3.961084045034161e-05, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9742931336164474, |
| "num_tokens": 147302574.0, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.6545220054812187, |
| "grad_norm": 0.07952143251895905, |
| "learning_rate": 3.957700592853406e-05, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9752921044826508, |
| "num_tokens": 148035101.0, |
| "step": 1015 |
| }, |
| { |
| "epoch": 0.6577462518136385, |
| "grad_norm": 0.08524080365896225, |
| "learning_rate": 3.9543024625934854e-05, |
| "loss": 0.0532, |
| "mean_token_accuracy": 0.9766767233610153, |
| "num_tokens": 148759549.0, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.6609704981460583, |
| "grad_norm": 0.09860266000032425, |
| "learning_rate": 3.9508896935705926e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9719317078590393, |
| "num_tokens": 149491486.0, |
| "step": 1025 |
| }, |
| { |
| "epoch": 0.6641947444784781, |
| "grad_norm": 0.09467299282550812, |
| "learning_rate": 3.9474623252702935e-05, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.9750267326831817, |
| "num_tokens": 150227814.0, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.667418990810898, |
| "grad_norm": 0.11882094293832779, |
| "learning_rate": 3.9440203973470704e-05, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9733793139457703, |
| "num_tokens": 150956574.0, |
| "step": 1035 |
| }, |
| { |
| "epoch": 0.6706432371433177, |
| "grad_norm": 0.09884798526763916, |
| "learning_rate": 3.940563949623855e-05, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9753553360700608, |
| "num_tokens": 151675440.0, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.6738674834757375, |
| "grad_norm": 0.12061449140310287, |
| "learning_rate": 3.937093022091575e-05, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.9764721900224685, |
| "num_tokens": 152402614.0, |
| "step": 1045 |
| }, |
| { |
| "epoch": 0.6770917298081573, |
| "grad_norm": 0.12149884551763535, |
| "learning_rate": 3.933607654908688e-05, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.975570747256279, |
| "num_tokens": 153134506.0, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.6803159761405771, |
| "grad_norm": 0.09680628776550293, |
| "learning_rate": 3.9301078884007164e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9746988475322723, |
| "num_tokens": 153864239.0, |
| "step": 1055 |
| }, |
| { |
| "epoch": 0.683540222472997, |
| "grad_norm": 0.11012880504131317, |
| "learning_rate": 3.9265937630597856e-05, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9774135172367096, |
| "num_tokens": 154602861.0, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.6867644688054168, |
| "grad_norm": 0.0789109393954277, |
| "learning_rate": 3.9230653195441484e-05, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9738561093807221, |
| "num_tokens": 155329851.0, |
| "step": 1065 |
| }, |
| { |
| "epoch": 0.6899887151378366, |
| "grad_norm": 0.08210276067256927, |
| "learning_rate": 3.91952259867772e-05, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9739501923322678, |
| "num_tokens": 156065602.0, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.6932129614702564, |
| "grad_norm": 0.10487555712461472, |
| "learning_rate": 3.9159656414496023e-05, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9770496636629105, |
| "num_tokens": 156800033.0, |
| "step": 1075 |
| }, |
| { |
| "epoch": 0.6964372078026762, |
| "grad_norm": 0.11904215812683105, |
| "learning_rate": 3.912394489013613e-05, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9740446984767914, |
| "num_tokens": 157523591.0, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.699661454135096, |
| "grad_norm": 0.08037332445383072, |
| "learning_rate": 3.908809182687807e-05, |
| "loss": 0.0552, |
| "mean_token_accuracy": 0.976033627986908, |
| "num_tokens": 158271393.0, |
| "step": 1085 |
| }, |
| { |
| "epoch": 0.7028857004675158, |
| "grad_norm": 0.09583903104066849, |
| "learning_rate": 3.9052097639539986e-05, |
| "loss": 0.0538, |
| "mean_token_accuracy": 0.9779333472251892, |
| "num_tokens": 159006283.0, |
| "step": 1090 |
| }, |
| { |
| "epoch": 0.7061099467999356, |
| "grad_norm": 0.10951375961303711, |
| "learning_rate": 3.9015962744572816e-05, |
| "loss": 0.0576, |
| "mean_token_accuracy": 0.9759568333625793, |
| "num_tokens": 159730925.0, |
| "step": 1095 |
| }, |
| { |
| "epoch": 0.7093341931323554, |
| "grad_norm": 0.1405317336320877, |
| "learning_rate": 3.8979687560055494e-05, |
| "loss": 0.0563, |
| "mean_token_accuracy": 0.9765321224927902, |
| "num_tokens": 160460525.0, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.7125584394647752, |
| "grad_norm": 0.10384000837802887, |
| "learning_rate": 3.894327250569009e-05, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9759569823741913, |
| "num_tokens": 161186318.0, |
| "step": 1105 |
| }, |
| { |
| "epoch": 0.715782685797195, |
| "grad_norm": 0.09875476360321045, |
| "learning_rate": 3.890671800279694e-05, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9750628441572189, |
| "num_tokens": 161910921.0, |
| "step": 1110 |
| }, |
| { |
| "epoch": 0.7190069321296148, |
| "grad_norm": 0.13653230667114258, |
| "learning_rate": 3.8870024474309825e-05, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9747509866952896, |
| "num_tokens": 162631945.0, |
| "step": 1115 |
| }, |
| { |
| "epoch": 0.7222311784620346, |
| "grad_norm": 0.08216042071580887, |
| "learning_rate": 3.883319234477103e-05, |
| "loss": 0.0538, |
| "mean_token_accuracy": 0.9764719784259797, |
| "num_tokens": 163371838.0, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.7254554247944544, |
| "grad_norm": 0.09303175657987595, |
| "learning_rate": 3.8796222040326446e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9741865336894989, |
| "num_tokens": 164107346.0, |
| "step": 1125 |
| }, |
| { |
| "epoch": 0.728679671126874, |
| "grad_norm": 0.0831592008471489, |
| "learning_rate": 3.875911398872064e-05, |
| "loss": 0.0508, |
| "mean_token_accuracy": 0.9775215804576873, |
| "num_tokens": 164841565.0, |
| "step": 1130 |
| }, |
| { |
| "epoch": 0.7319039174592938, |
| "grad_norm": 0.13856276869773865, |
| "learning_rate": 3.872186861929193e-05, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9733951717615128, |
| "num_tokens": 165576136.0, |
| "step": 1135 |
| }, |
| { |
| "epoch": 0.7351281637917136, |
| "grad_norm": 0.11911726742982864, |
| "learning_rate": 3.868448636296734e-05, |
| "loss": 0.0553, |
| "mean_token_accuracy": 0.9762080311775208, |
| "num_tokens": 166300285.0, |
| "step": 1140 |
| }, |
| { |
| "epoch": 0.7383524101241334, |
| "grad_norm": 0.1512387990951538, |
| "learning_rate": 3.864696765225773e-05, |
| "loss": 0.0579, |
| "mean_token_accuracy": 0.9757677435874939, |
| "num_tokens": 167019217.0, |
| "step": 1145 |
| }, |
| { |
| "epoch": 0.7415766564565532, |
| "grad_norm": 0.0908764973282814, |
| "learning_rate": 3.860931292125269e-05, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.9751733332872391, |
| "num_tokens": 167745917.0, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.744800902788973, |
| "grad_norm": 0.1302078664302826, |
| "learning_rate": 3.857152260561557e-05, |
| "loss": 0.0552, |
| "mean_token_accuracy": 0.9761073291301727, |
| "num_tokens": 168472104.0, |
| "step": 1155 |
| }, |
| { |
| "epoch": 0.7480251491213928, |
| "grad_norm": 0.1535472422838211, |
| "learning_rate": 3.853359714257844e-05, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.9727565765380859, |
| "num_tokens": 169196626.0, |
| "step": 1160 |
| }, |
| { |
| "epoch": 0.7512493954538126, |
| "grad_norm": 0.1055363342165947, |
| "learning_rate": 3.8495536970937e-05, |
| "loss": 0.0629, |
| "mean_token_accuracy": 0.9735617130994797, |
| "num_tokens": 169922320.0, |
| "step": 1165 |
| }, |
| { |
| "epoch": 0.7544736417862324, |
| "grad_norm": 0.10635912418365479, |
| "learning_rate": 3.845734253104552e-05, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.974516960978508, |
| "num_tokens": 170644749.0, |
| "step": 1170 |
| }, |
| { |
| "epoch": 0.7576978881186522, |
| "grad_norm": 0.09457819163799286, |
| "learning_rate": 3.841901426481177e-05, |
| "loss": 0.0596, |
| "mean_token_accuracy": 0.9745361775159835, |
| "num_tokens": 171369813.0, |
| "step": 1175 |
| }, |
| { |
| "epoch": 0.760922134451072, |
| "grad_norm": 0.08743788301944733, |
| "learning_rate": 3.8380552615691856e-05, |
| "loss": 0.0538, |
| "mean_token_accuracy": 0.9760215729475021, |
| "num_tokens": 172101275.0, |
| "step": 1180 |
| }, |
| { |
| "epoch": 0.7641463807834918, |
| "grad_norm": 0.11404203623533249, |
| "learning_rate": 3.834195802868515e-05, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.9762803941965104, |
| "num_tokens": 172824985.0, |
| "step": 1185 |
| }, |
| { |
| "epoch": 0.7673706271159116, |
| "grad_norm": 0.09753867983818054, |
| "learning_rate": 3.830323095032908e-05, |
| "loss": 0.052, |
| "mean_token_accuracy": 0.9776387304067612, |
| "num_tokens": 173559499.0, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.7705948734483314, |
| "grad_norm": 0.10941199213266373, |
| "learning_rate": 3.826437182869399e-05, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9757213294506073, |
| "num_tokens": 174296816.0, |
| "step": 1195 |
| }, |
| { |
| "epoch": 0.7738191197807512, |
| "grad_norm": 0.07298741489648819, |
| "learning_rate": 3.8225381113377985e-05, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.9770480930805207, |
| "num_tokens": 175039335.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.777043366113171, |
| "grad_norm": 0.08156715333461761, |
| "learning_rate": 3.818625925550169e-05, |
| "loss": 0.0517, |
| "mean_token_accuracy": 0.9788919061422348, |
| "num_tokens": 175767055.0, |
| "step": 1205 |
| }, |
| { |
| "epoch": 0.7802676124455908, |
| "grad_norm": 0.10885099321603775, |
| "learning_rate": 3.8147006707703036e-05, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.974798145890236, |
| "num_tokens": 176499599.0, |
| "step": 1210 |
| }, |
| { |
| "epoch": 0.7834918587780106, |
| "grad_norm": 0.123116634786129, |
| "learning_rate": 3.810762392413203e-05, |
| "loss": 0.0585, |
| "mean_token_accuracy": 0.9752477526664733, |
| "num_tokens": 177227171.0, |
| "step": 1215 |
| }, |
| { |
| "epoch": 0.7867161051104304, |
| "grad_norm": 0.10680197179317474, |
| "learning_rate": 3.8068111360445505e-05, |
| "loss": 0.0564, |
| "mean_token_accuracy": 0.9767391383647919, |
| "num_tokens": 177954917.0, |
| "step": 1220 |
| }, |
| { |
| "epoch": 0.7899403514428502, |
| "grad_norm": 0.10358034819364548, |
| "learning_rate": 3.802846947380185e-05, |
| "loss": 0.0568, |
| "mean_token_accuracy": 0.9765140026807785, |
| "num_tokens": 178699638.0, |
| "step": 1225 |
| }, |
| { |
| "epoch": 0.79316459777527, |
| "grad_norm": 0.08197943866252899, |
| "learning_rate": 3.7988698722855693e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9755314439535141, |
| "num_tokens": 179438798.0, |
| "step": 1230 |
| }, |
| { |
| "epoch": 0.7963888441076898, |
| "grad_norm": 0.07818649709224701, |
| "learning_rate": 3.7948799567752655e-05, |
| "loss": 0.0487, |
| "mean_token_accuracy": 0.9791767328977585, |
| "num_tokens": 180165534.0, |
| "step": 1235 |
| }, |
| { |
| "epoch": 0.7996130904401096, |
| "grad_norm": 0.09661022573709488, |
| "learning_rate": 3.7908772470123935e-05, |
| "loss": 0.0509, |
| "mean_token_accuracy": 0.9785650819540024, |
| "num_tokens": 180903355.0, |
| "step": 1240 |
| }, |
| { |
| "epoch": 0.8028373367725294, |
| "grad_norm": 0.10192213952541351, |
| "learning_rate": 3.786861789308106e-05, |
| "loss": 0.0599, |
| "mean_token_accuracy": 0.9741548895835876, |
| "num_tokens": 181627452.0, |
| "step": 1245 |
| }, |
| { |
| "epoch": 0.8060615831049492, |
| "grad_norm": 0.11146002262830734, |
| "learning_rate": 3.782833630121047e-05, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9773173213005066, |
| "num_tokens": 182363387.0, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.809285829437369, |
| "grad_norm": 0.12124519795179367, |
| "learning_rate": 3.778792816056817e-05, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.9727635204792022, |
| "num_tokens": 183086194.0, |
| "step": 1255 |
| }, |
| { |
| "epoch": 0.8125100757697888, |
| "grad_norm": 0.12048567086458206, |
| "learning_rate": 3.774739393867432e-05, |
| "loss": 0.0564, |
| "mean_token_accuracy": 0.9770623743534088, |
| "num_tokens": 183822624.0, |
| "step": 1260 |
| }, |
| { |
| "epoch": 0.8157343221022086, |
| "grad_norm": 0.09330233186483383, |
| "learning_rate": 3.770673410450783e-05, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.9751154869794846, |
| "num_tokens": 184540919.0, |
| "step": 1265 |
| }, |
| { |
| "epoch": 0.8189585684346284, |
| "grad_norm": 0.10516887158155441, |
| "learning_rate": 3.766594912850095e-05, |
| "loss": 0.0517, |
| "mean_token_accuracy": 0.9774849027395248, |
| "num_tokens": 185265936.0, |
| "step": 1270 |
| }, |
| { |
| "epoch": 0.8221828147670482, |
| "grad_norm": 0.09287908673286438, |
| "learning_rate": 3.762503948253381e-05, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9777779519557953, |
| "num_tokens": 186004102.0, |
| "step": 1275 |
| }, |
| { |
| "epoch": 0.825407061099468, |
| "grad_norm": 0.12229038774967194, |
| "learning_rate": 3.7584005639928965e-05, |
| "loss": 0.0561, |
| "mean_token_accuracy": 0.9763047903776169, |
| "num_tokens": 186739047.0, |
| "step": 1280 |
| }, |
| { |
| "epoch": 0.8286313074318878, |
| "grad_norm": 0.07607828080654144, |
| "learning_rate": 3.7542848075445916e-05, |
| "loss": 0.0561, |
| "mean_token_accuracy": 0.9764394313097, |
| "num_tokens": 187461744.0, |
| "step": 1285 |
| }, |
| { |
| "epoch": 0.8318555537643076, |
| "grad_norm": 0.0848899558186531, |
| "learning_rate": 3.750156726527562e-05, |
| "loss": 0.0499, |
| "mean_token_accuracy": 0.9795501589775085, |
| "num_tokens": 188194042.0, |
| "step": 1290 |
| }, |
| { |
| "epoch": 0.8350798000967274, |
| "grad_norm": 0.07268983870744705, |
| "learning_rate": 3.7460163687034986e-05, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9715736627578735, |
| "num_tokens": 188907348.0, |
| "step": 1295 |
| }, |
| { |
| "epoch": 0.8383040464291471, |
| "grad_norm": 0.08324116468429565, |
| "learning_rate": 3.7418637819761335e-05, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.975104707479477, |
| "num_tokens": 189644739.0, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.8415282927615669, |
| "grad_norm": 0.08341357111930847, |
| "learning_rate": 3.737699014390687e-05, |
| "loss": 0.0519, |
| "mean_token_accuracy": 0.9787366181612015, |
| "num_tokens": 190375432.0, |
| "step": 1305 |
| }, |
| { |
| "epoch": 0.8447525390939867, |
| "grad_norm": 0.10635333508253098, |
| "learning_rate": 3.733522114133312e-05, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9751798421144485, |
| "num_tokens": 191109180.0, |
| "step": 1310 |
| }, |
| { |
| "epoch": 0.8479767854264065, |
| "grad_norm": 0.08530605584383011, |
| "learning_rate": 3.729333129530535e-05, |
| "loss": 0.0499, |
| "mean_token_accuracy": 0.9776551872491837, |
| "num_tokens": 191843301.0, |
| "step": 1315 |
| }, |
| { |
| "epoch": 0.8512010317588263, |
| "grad_norm": 0.08816536515951157, |
| "learning_rate": 3.7251321090486976e-05, |
| "loss": 0.0528, |
| "mean_token_accuracy": 0.9791554003953934, |
| "num_tokens": 192576947.0, |
| "step": 1320 |
| }, |
| { |
| "epoch": 0.8544252780912461, |
| "grad_norm": 0.11100117117166519, |
| "learning_rate": 3.720919101293396e-05, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.9759393990039825, |
| "num_tokens": 193301410.0, |
| "step": 1325 |
| }, |
| { |
| "epoch": 0.8576495244236659, |
| "grad_norm": 0.0815863385796547, |
| "learning_rate": 3.71669415500892e-05, |
| "loss": 0.0541, |
| "mean_token_accuracy": 0.976600906252861, |
| "num_tokens": 194019172.0, |
| "step": 1330 |
| }, |
| { |
| "epoch": 0.8608737707560857, |
| "grad_norm": 0.08878391981124878, |
| "learning_rate": 3.712457319077686e-05, |
| "loss": 0.0501, |
| "mean_token_accuracy": 0.9796894162893295, |
| "num_tokens": 194745229.0, |
| "step": 1335 |
| }, |
| { |
| "epoch": 0.8640980170885055, |
| "grad_norm": 0.07888499647378922, |
| "learning_rate": 3.7082086425196726e-05, |
| "loss": 0.0555, |
| "mean_token_accuracy": 0.9769952028989792, |
| "num_tokens": 195481641.0, |
| "step": 1340 |
| }, |
| { |
| "epoch": 0.8673222634209253, |
| "grad_norm": 0.10417364537715912, |
| "learning_rate": 3.7039481744918556e-05, |
| "loss": 0.0568, |
| "mean_token_accuracy": 0.9756094813346863, |
| "num_tokens": 196203056.0, |
| "step": 1345 |
| }, |
| { |
| "epoch": 0.8705465097533451, |
| "grad_norm": 0.11274675279855728, |
| "learning_rate": 3.6996759642876356e-05, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9755377024412155, |
| "num_tokens": 196939563.0, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.8737707560857649, |
| "grad_norm": 0.11219698935747147, |
| "learning_rate": 3.695392061336272e-05, |
| "loss": 0.0525, |
| "mean_token_accuracy": 0.9789113879203797, |
| "num_tokens": 197662115.0, |
| "step": 1355 |
| }, |
| { |
| "epoch": 0.8769950024181847, |
| "grad_norm": 0.10386841744184494, |
| "learning_rate": 3.6910965152023065e-05, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9766336023807526, |
| "num_tokens": 198396166.0, |
| "step": 1360 |
| }, |
| { |
| "epoch": 0.8802192487506045, |
| "grad_norm": 0.08722949028015137, |
| "learning_rate": 3.686789375584993e-05, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.9748211085796357, |
| "num_tokens": 199110658.0, |
| "step": 1365 |
| }, |
| { |
| "epoch": 0.8834434950830243, |
| "grad_norm": 0.07917441427707672, |
| "learning_rate": 3.68247069231772e-05, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9741447597742081, |
| "num_tokens": 199838573.0, |
| "step": 1370 |
| }, |
| { |
| "epoch": 0.8866677414154441, |
| "grad_norm": 0.06443702429533005, |
| "learning_rate": 3.6781405153674376e-05, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.9752748906612396, |
| "num_tokens": 200575402.0, |
| "step": 1375 |
| }, |
| { |
| "epoch": 0.8898919877478639, |
| "grad_norm": 0.0993696078658104, |
| "learning_rate": 3.6737988948340764e-05, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9746701955795288, |
| "num_tokens": 201292392.0, |
| "step": 1380 |
| }, |
| { |
| "epoch": 0.8931162340802837, |
| "grad_norm": 0.11816300451755524, |
| "learning_rate": 3.669445880949967e-05, |
| "loss": 0.0593, |
| "mean_token_accuracy": 0.9753267735242843, |
| "num_tokens": 202033774.0, |
| "step": 1385 |
| }, |
| { |
| "epoch": 0.8963404804127035, |
| "grad_norm": 0.10717082023620605, |
| "learning_rate": 3.6650815240792635e-05, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9742680311203002, |
| "num_tokens": 202757271.0, |
| "step": 1390 |
| }, |
| { |
| "epoch": 0.8995647267451233, |
| "grad_norm": 0.10553067177534103, |
| "learning_rate": 3.660705874717356e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.974567374587059, |
| "num_tokens": 203483560.0, |
| "step": 1395 |
| }, |
| { |
| "epoch": 0.9027889730775431, |
| "grad_norm": 0.11750681698322296, |
| "learning_rate": 3.6563189834902865e-05, |
| "loss": 0.0646, |
| "mean_token_accuracy": 0.9726648569107056, |
| "num_tokens": 204206924.0, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.9060132194099629, |
| "grad_norm": 0.09175435453653336, |
| "learning_rate": 3.651920901154169e-05, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.9743611514568329, |
| "num_tokens": 204932433.0, |
| "step": 1405 |
| }, |
| { |
| "epoch": 0.9092374657423827, |
| "grad_norm": 0.06742607057094574, |
| "learning_rate": 3.6475116785945944e-05, |
| "loss": 0.0583, |
| "mean_token_accuracy": 0.97470822930336, |
| "num_tokens": 205658361.0, |
| "step": 1410 |
| }, |
| { |
| "epoch": 0.9124617120748025, |
| "grad_norm": 0.12199928611516953, |
| "learning_rate": 3.643091366826048e-05, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.9731442481279373, |
| "num_tokens": 206384501.0, |
| "step": 1415 |
| }, |
| { |
| "epoch": 0.9156859584072223, |
| "grad_norm": 0.11630042642354965, |
| "learning_rate": 3.638660016991314e-05, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9730322539806366, |
| "num_tokens": 207123168.0, |
| "step": 1420 |
| }, |
| { |
| "epoch": 0.9189102047396421, |
| "grad_norm": 0.10771700739860535, |
| "learning_rate": 3.634217680360889e-05, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9730399191379547, |
| "num_tokens": 207860337.0, |
| "step": 1425 |
| }, |
| { |
| "epoch": 0.9221344510720619, |
| "grad_norm": 0.12622195482254028, |
| "learning_rate": 3.629764408332385e-05, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9747539222240448, |
| "num_tokens": 208594960.0, |
| "step": 1430 |
| }, |
| { |
| "epoch": 0.9253586974044817, |
| "grad_norm": 0.09327437728643417, |
| "learning_rate": 3.625300252429936e-05, |
| "loss": 0.0556, |
| "mean_token_accuracy": 0.9760198146104813, |
| "num_tokens": 209313686.0, |
| "step": 1435 |
| }, |
| { |
| "epoch": 0.9285829437369015, |
| "grad_norm": 0.08936242759227753, |
| "learning_rate": 3.620825264303602e-05, |
| "loss": 0.0579, |
| "mean_token_accuracy": 0.9758930534124375, |
| "num_tokens": 210031981.0, |
| "step": 1440 |
| }, |
| { |
| "epoch": 0.9318071900693213, |
| "grad_norm": 0.11153260618448257, |
| "learning_rate": 3.616339495728771e-05, |
| "loss": 0.0537, |
| "mean_token_accuracy": 0.9763037323951721, |
| "num_tokens": 210762005.0, |
| "step": 1445 |
| }, |
| { |
| "epoch": 0.9350314364017411, |
| "grad_norm": 0.07815688848495483, |
| "learning_rate": 3.611842998605563e-05, |
| "loss": 0.0581, |
| "mean_token_accuracy": 0.9750084638595581, |
| "num_tokens": 211487018.0, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.9382556827341609, |
| "grad_norm": 0.07063890993595123, |
| "learning_rate": 3.6073358249582206e-05, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.9735538899898529, |
| "num_tokens": 212217230.0, |
| "step": 1455 |
| }, |
| { |
| "epoch": 0.9414799290665807, |
| "grad_norm": 0.09426791965961456, |
| "learning_rate": 3.602818026934521e-05, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9736795634031296, |
| "num_tokens": 212945802.0, |
| "step": 1460 |
| }, |
| { |
| "epoch": 0.9447041753990005, |
| "grad_norm": 0.08177284896373749, |
| "learning_rate": 3.598289656805159e-05, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.973434591293335, |
| "num_tokens": 213662785.0, |
| "step": 1465 |
| }, |
| { |
| "epoch": 0.9479284217314203, |
| "grad_norm": 0.10239792615175247, |
| "learning_rate": 3.593750766963149e-05, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9757019758224488, |
| "num_tokens": 214394531.0, |
| "step": 1470 |
| }, |
| { |
| "epoch": 0.95115266806384, |
| "grad_norm": 0.11099418252706528, |
| "learning_rate": 3.5892014099232206e-05, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9748421847820282, |
| "num_tokens": 215128584.0, |
| "step": 1475 |
| }, |
| { |
| "epoch": 0.9543769143962598, |
| "grad_norm": 0.08777165412902832, |
| "learning_rate": 3.584641638321207e-05, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9748810142278671, |
| "num_tokens": 215852654.0, |
| "step": 1480 |
| }, |
| { |
| "epoch": 0.9576011607286796, |
| "grad_norm": 0.09070898592472076, |
| "learning_rate": 3.580071504913437e-05, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.9739073902368546, |
| "num_tokens": 216578814.0, |
| "step": 1485 |
| }, |
| { |
| "epoch": 0.9608254070610994, |
| "grad_norm": 0.09736787527799606, |
| "learning_rate": 3.5754910625761236e-05, |
| "loss": 0.0572, |
| "mean_token_accuracy": 0.9757748395204544, |
| "num_tokens": 217305723.0, |
| "step": 1490 |
| }, |
| { |
| "epoch": 0.9640496533935192, |
| "grad_norm": 0.14471428096294403, |
| "learning_rate": 3.5709003643047574e-05, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9725530028343201, |
| "num_tokens": 218030840.0, |
| "step": 1495 |
| }, |
| { |
| "epoch": 0.967273899725939, |
| "grad_norm": 0.1132514551281929, |
| "learning_rate": 3.566299463213486e-05, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9752576917409896, |
| "num_tokens": 218760480.0, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.9704981460583588, |
| "grad_norm": 0.08836998790502548, |
| "learning_rate": 3.5616884125345044e-05, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9763853371143341, |
| "num_tokens": 219486382.0, |
| "step": 1505 |
| }, |
| { |
| "epoch": 0.9737223923907786, |
| "grad_norm": 0.09937116503715515, |
| "learning_rate": 3.5570672656174386e-05, |
| "loss": 0.0561, |
| "mean_token_accuracy": 0.9763641476631164, |
| "num_tokens": 220216782.0, |
| "step": 1510 |
| }, |
| { |
| "epoch": 0.9769466387231984, |
| "grad_norm": 0.13395731151103973, |
| "learning_rate": 3.5524360759287265e-05, |
| "loss": 0.0583, |
| "mean_token_accuracy": 0.9757053703069687, |
| "num_tokens": 220943904.0, |
| "step": 1515 |
| }, |
| { |
| "epoch": 0.9801708850556182, |
| "grad_norm": 0.11389587819576263, |
| "learning_rate": 3.5477948970510015e-05, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9745948255062103, |
| "num_tokens": 221662489.0, |
| "step": 1520 |
| }, |
| { |
| "epoch": 0.983395131388038, |
| "grad_norm": 0.10319283604621887, |
| "learning_rate": 3.543143782682469e-05, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.9770182073116302, |
| "num_tokens": 222389837.0, |
| "step": 1525 |
| }, |
| { |
| "epoch": 0.9866193777204578, |
| "grad_norm": 0.06966328620910645, |
| "learning_rate": 3.538482786636291e-05, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.9756745487451554, |
| "num_tokens": 223129627.0, |
| "step": 1530 |
| }, |
| { |
| "epoch": 0.9898436240528776, |
| "grad_norm": 0.10186833888292313, |
| "learning_rate": 3.5338119628399566e-05, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.9750755608081818, |
| "num_tokens": 223859570.0, |
| "step": 1535 |
| }, |
| { |
| "epoch": 0.9930678703852974, |
| "grad_norm": 0.08092603832483292, |
| "learning_rate": 3.529131365334665e-05, |
| "loss": 0.0504, |
| "mean_token_accuracy": 0.9785466164350509, |
| "num_tokens": 224589126.0, |
| "step": 1540 |
| }, |
| { |
| "epoch": 0.9962921167177172, |
| "grad_norm": 0.09593317657709122, |
| "learning_rate": 3.524441048274693e-05, |
| "loss": 0.0529, |
| "mean_token_accuracy": 0.9780813127756118, |
| "num_tokens": 225330856.0, |
| "step": 1545 |
| }, |
| { |
| "epoch": 0.999516363050137, |
| "grad_norm": 0.09851348400115967, |
| "learning_rate": 3.519741065926775e-05, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9762847810983658, |
| "num_tokens": 226064416.0, |
| "step": 1550 |
| }, |
| { |
| "epoch": 1.0025793970659358, |
| "grad_norm": 0.1692703366279602, |
| "learning_rate": 3.5150314726694705e-05, |
| "loss": 0.0537, |
| "mean_token_accuracy": 0.9780284323190388, |
| "num_tokens": 226754486.0, |
| "step": 1555 |
| }, |
| { |
| "epoch": 1.0058036433983557, |
| "grad_norm": 0.09912608563899994, |
| "learning_rate": 3.510312322992538e-05, |
| "loss": 0.0575, |
| "mean_token_accuracy": 0.9750097781419754, |
| "num_tokens": 227481476.0, |
| "step": 1560 |
| }, |
| { |
| "epoch": 1.0090278897307754, |
| "grad_norm": 0.0860169380903244, |
| "learning_rate": 3.505583671496303e-05, |
| "loss": 0.0534, |
| "mean_token_accuracy": 0.9772720813751221, |
| "num_tokens": 228213731.0, |
| "step": 1565 |
| }, |
| { |
| "epoch": 1.0122521360631953, |
| "grad_norm": 0.09664393961429596, |
| "learning_rate": 3.5008455728910265e-05, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.976708522439003, |
| "num_tokens": 228951064.0, |
| "step": 1570 |
| }, |
| { |
| "epoch": 1.015476382395615, |
| "grad_norm": 0.09101137518882751, |
| "learning_rate": 3.496098081996271e-05, |
| "loss": 0.0534, |
| "mean_token_accuracy": 0.9769470423460007, |
| "num_tokens": 229675100.0, |
| "step": 1575 |
| }, |
| { |
| "epoch": 1.018700628728035, |
| "grad_norm": 0.1039009541273117, |
| "learning_rate": 3.491341253740269e-05, |
| "loss": 0.0474, |
| "mean_token_accuracy": 0.9808558553457261, |
| "num_tokens": 230400930.0, |
| "step": 1580 |
| }, |
| { |
| "epoch": 1.0219248750604546, |
| "grad_norm": 0.12784680724143982, |
| "learning_rate": 3.486575143159285e-05, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.9773623406887054, |
| "num_tokens": 231126529.0, |
| "step": 1585 |
| }, |
| { |
| "epoch": 1.0251491213928745, |
| "grad_norm": 0.07995443791151047, |
| "learning_rate": 3.48179980539698e-05, |
| "loss": 0.0528, |
| "mean_token_accuracy": 0.9774846136569977, |
| "num_tokens": 231860608.0, |
| "step": 1590 |
| }, |
| { |
| "epoch": 1.0283733677252942, |
| "grad_norm": 0.12739646434783936, |
| "learning_rate": 3.477015295703772e-05, |
| "loss": 0.0532, |
| "mean_token_accuracy": 0.976567879319191, |
| "num_tokens": 232591240.0, |
| "step": 1595 |
| }, |
| { |
| "epoch": 1.031597614057714, |
| "grad_norm": 0.11451254785060883, |
| "learning_rate": 3.472221669436199e-05, |
| "loss": 0.0612, |
| "mean_token_accuracy": 0.9749246060848236, |
| "num_tokens": 233319244.0, |
| "step": 1600 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 4653, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.3396731359863505e+19, |
| "train_batch_size": 6, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
