| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.625871611269191, |
| "eval_steps": 500, |
| "global_step": 13000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.57754989027977, |
| "epoch": 0.006253713142178169, |
| "grad_norm": 0.1328946352005005, |
| "learning_rate": 8.166666666666667e-05, |
| "loss": 1.6654, |
| "mean_token_accuracy": 0.5821028184890747, |
| "num_tokens": 1453934.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.7420939958095552, |
| "epoch": 0.012507426284356337, |
| "grad_norm": 0.11827201396226883, |
| "learning_rate": 0.000165, |
| "loss": 1.3586, |
| "mean_token_accuracy": 0.6275478279590607, |
| "num_tokens": 2912735.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.5568377447128297, |
| "epoch": 0.018761139426534505, |
| "grad_norm": 0.15163880586624146, |
| "learning_rate": 0.0002483333333333333, |
| "loss": 1.3207, |
| "mean_token_accuracy": 0.6348841637372971, |
| "num_tokens": 4361799.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 1.4739533269405365, |
| "epoch": 0.025014852568712675, |
| "grad_norm": 0.12787143886089325, |
| "learning_rate": 0.0003316666666666667, |
| "loss": 1.2842, |
| "mean_token_accuracy": 0.6424031159281731, |
| "num_tokens": 5814731.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 1.4483512490987778, |
| "epoch": 0.031268565710890844, |
| "grad_norm": 0.1128445640206337, |
| "learning_rate": 0.000415, |
| "loss": 1.2705, |
| "mean_token_accuracy": 0.6454238125681877, |
| "num_tokens": 7268127.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 1.4052385699748993, |
| "epoch": 0.03752227885306901, |
| "grad_norm": 0.11171138286590576, |
| "learning_rate": 0.0004983333333333334, |
| "loss": 1.2476, |
| "mean_token_accuracy": 0.6496384194493294, |
| "num_tokens": 8718544.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 1.4152175986766815, |
| "epoch": 0.04377599199524718, |
| "grad_norm": 0.11977560073137283, |
| "learning_rate": 0.0005816666666666666, |
| "loss": 1.2513, |
| "mean_token_accuracy": 0.6493740159273148, |
| "num_tokens": 10172719.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 1.4048930382728577, |
| "epoch": 0.05002970513742535, |
| "grad_norm": 0.1243417039513588, |
| "learning_rate": 0.000665, |
| "loss": 1.2289, |
| "mean_token_accuracy": 0.6540437403321266, |
| "num_tokens": 11620279.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 1.4123985522985458, |
| "epoch": 0.056283418279603516, |
| "grad_norm": 0.11343871802091599, |
| "learning_rate": 0.0007483333333333333, |
| "loss": 1.239, |
| "mean_token_accuracy": 0.6520217537879944, |
| "num_tokens": 13073226.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 1.4004585057497025, |
| "epoch": 0.06253713142178169, |
| "grad_norm": 0.11357053369283676, |
| "learning_rate": 0.0008316666666666666, |
| "loss": 1.225, |
| "mean_token_accuracy": 0.6544527187943459, |
| "num_tokens": 14533915.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 1.4031615656614305, |
| "epoch": 0.06879084456395985, |
| "grad_norm": 0.12513332068920135, |
| "learning_rate": 0.000915, |
| "loss": 1.2343, |
| "mean_token_accuracy": 0.6527539578080177, |
| "num_tokens": 15980014.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 1.4137125009298324, |
| "epoch": 0.07504455770613802, |
| "grad_norm": 0.13136321306228638, |
| "learning_rate": 0.0009983333333333333, |
| "loss": 1.2207, |
| "mean_token_accuracy": 0.6558423298597336, |
| "num_tokens": 17432166.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 1.4449491912126542, |
| "epoch": 0.08129827084831619, |
| "grad_norm": 0.1370031088590622, |
| "learning_rate": 0.0010816666666666668, |
| "loss": 1.239, |
| "mean_token_accuracy": 0.6518874534964562, |
| "num_tokens": 18882117.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 1.4782390099763871, |
| "epoch": 0.08755198399049435, |
| "grad_norm": 0.15503117442131042, |
| "learning_rate": 0.001165, |
| "loss": 1.244, |
| "mean_token_accuracy": 0.6515460327267647, |
| "num_tokens": 20330658.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 1.4976489871740342, |
| "epoch": 0.09380569713267252, |
| "grad_norm": 0.14647236466407776, |
| "learning_rate": 0.0012483333333333333, |
| "loss": 1.2517, |
| "mean_token_accuracy": 0.6499434402585029, |
| "num_tokens": 21786059.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 1.503735830783844, |
| "epoch": 0.1000594102748507, |
| "grad_norm": 0.16612057387828827, |
| "learning_rate": 0.0013316666666666668, |
| "loss": 1.2497, |
| "mean_token_accuracy": 0.6501839146018028, |
| "num_tokens": 23240083.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 1.5280751663446426, |
| "epoch": 0.10631312341702887, |
| "grad_norm": 0.17178034782409668, |
| "learning_rate": 0.001415, |
| "loss": 1.2609, |
| "mean_token_accuracy": 0.6481665202975273, |
| "num_tokens": 24700708.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 1.5576636075973511, |
| "epoch": 0.11256683655920703, |
| "grad_norm": 0.18341563642024994, |
| "learning_rate": 0.0014983333333333333, |
| "loss": 1.2956, |
| "mean_token_accuracy": 0.6411516669392586, |
| "num_tokens": 26155197.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 1.577981666326523, |
| "epoch": 0.1188205497013852, |
| "grad_norm": 0.18315236270427704, |
| "learning_rate": 0.0015816666666666668, |
| "loss": 1.2857, |
| "mean_token_accuracy": 0.643715631365776, |
| "num_tokens": 27601258.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 1.60272319316864, |
| "epoch": 0.12507426284356338, |
| "grad_norm": 0.19144219160079956, |
| "learning_rate": 0.001665, |
| "loss": 1.3031, |
| "mean_token_accuracy": 0.6408327847719193, |
| "num_tokens": 29063691.0, |
| "step": 1000 |
| }, |
| { |
| "entropy": 1.5899927777051925, |
| "epoch": 0.13132797598574153, |
| "grad_norm": 0.21011324226856232, |
| "learning_rate": 0.0017483333333333333, |
| "loss": 1.3131, |
| "mean_token_accuracy": 0.6375964027643204, |
| "num_tokens": 30519258.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 1.611317069530487, |
| "epoch": 0.1375816891279197, |
| "grad_norm": 0.20436125993728638, |
| "learning_rate": 0.0018316666666666668, |
| "loss": 1.3282, |
| "mean_token_accuracy": 0.6352240258455276, |
| "num_tokens": 31982975.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 1.652041432261467, |
| "epoch": 0.14383540227009786, |
| "grad_norm": 0.21256397664546967, |
| "learning_rate": 0.001915, |
| "loss": 1.34, |
| "mean_token_accuracy": 0.6334743791818619, |
| "num_tokens": 33435147.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 1.7145874083042145, |
| "epoch": 0.15008911541227604, |
| "grad_norm": 0.2906016409397125, |
| "learning_rate": 0.0019983333333333333, |
| "loss": 1.3717, |
| "mean_token_accuracy": 0.6267069867253303, |
| "num_tokens": 34890160.0, |
| "step": 1200 |
| }, |
| { |
| "entropy": 1.7395102292299272, |
| "epoch": 0.1563428285544542, |
| "grad_norm": 0.2289716899394989, |
| "learning_rate": 0.0019999771835624504, |
| "loss": 1.3875, |
| "mean_token_accuracy": 0.6242620906233788, |
| "num_tokens": 36342500.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 1.7384645998477937, |
| "epoch": 0.16259654169663237, |
| "grad_norm": 0.2350999265909195, |
| "learning_rate": 0.0019999068632721773, |
| "loss": 1.3988, |
| "mean_token_accuracy": 0.6232203379273414, |
| "num_tokens": 37799801.0, |
| "step": 1300 |
| }, |
| { |
| "entropy": 1.7248098158836365, |
| "epoch": 0.16885025483881055, |
| "grad_norm": 0.2444753348827362, |
| "learning_rate": 0.0019997890329674856, |
| "loss": 1.4063, |
| "mean_token_accuracy": 0.6213877013325692, |
| "num_tokens": 39261919.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 1.7469890892505646, |
| "epoch": 0.1751039679809887, |
| "grad_norm": 0.2528238296508789, |
| "learning_rate": 0.001999623698247015, |
| "loss": 1.4028, |
| "mean_token_accuracy": 0.6217664569616318, |
| "num_tokens": 40711313.0, |
| "step": 1400 |
| }, |
| { |
| "entropy": 1.7513956505060195, |
| "epoch": 0.1813576811231669, |
| "grad_norm": 0.23596389591693878, |
| "learning_rate": 0.001999410866966553, |
| "loss": 1.4098, |
| "mean_token_accuracy": 0.6196629667282104, |
| "num_tokens": 42168864.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 1.7314427828788757, |
| "epoch": 0.18761139426534504, |
| "grad_norm": 0.24437537789344788, |
| "learning_rate": 0.001999150549238658, |
| "loss": 1.411, |
| "mean_token_accuracy": 0.6204391068220139, |
| "num_tokens": 43627161.0, |
| "step": 1500 |
| }, |
| { |
| "entropy": 1.7699194413423538, |
| "epoch": 0.19386510740752322, |
| "grad_norm": 0.24354827404022217, |
| "learning_rate": 0.0019988427574321815, |
| "loss": 1.4275, |
| "mean_token_accuracy": 0.6180677771568298, |
| "num_tokens": 45082614.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 3.1429525250196457, |
| "epoch": 0.2001188205497014, |
| "grad_norm": 26.936569213867188, |
| "learning_rate": 0.001998487506171678, |
| "loss": 4.3017, |
| "mean_token_accuracy": 0.44566510522061437, |
| "num_tokens": 46532177.0, |
| "step": 1600 |
| }, |
| { |
| "entropy": 6.903752332925796, |
| "epoch": 0.20637253369187955, |
| "grad_norm": 0.43571025133132935, |
| "learning_rate": 0.001998084812336713, |
| "loss": 8.4816, |
| "mean_token_accuracy": 0.03934380377701018, |
| "num_tokens": 47987350.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 7.173221395015717, |
| "epoch": 0.21262624683405773, |
| "grad_norm": 0.3482828438282013, |
| "learning_rate": 0.001997634695061058, |
| "loss": 7.2052, |
| "mean_token_accuracy": 0.06305525604635477, |
| "num_tokens": 49446129.0, |
| "step": 1700 |
| }, |
| { |
| "entropy": 6.704223630428314, |
| "epoch": 0.21887995997623588, |
| "grad_norm": 0.25398287177085876, |
| "learning_rate": 0.0019971371757317832, |
| "loss": 6.7459, |
| "mean_token_accuracy": 0.08217163875699043, |
| "num_tokens": 50893739.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 6.309946813583374, |
| "epoch": 0.22513367311841406, |
| "grad_norm": 0.27875518798828125, |
| "learning_rate": 0.001996592277988241, |
| "loss": 6.4542, |
| "mean_token_accuracy": 0.09980635419487953, |
| "num_tokens": 52349150.0, |
| "step": 1800 |
| }, |
| { |
| "entropy": 6.048123767375946, |
| "epoch": 0.23138738626059221, |
| "grad_norm": 0.31153035163879395, |
| "learning_rate": 0.0019960000277209427, |
| "loss": 6.2618, |
| "mean_token_accuracy": 0.1142095160484314, |
| "num_tokens": 53806391.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 5.801566255092621, |
| "epoch": 0.2376410994027704, |
| "grad_norm": 0.5886215567588806, |
| "learning_rate": 0.0019953604530703268, |
| "loss": 6.0319, |
| "mean_token_accuracy": 0.1300203223899007, |
| "num_tokens": 55256012.0, |
| "step": 1900 |
| }, |
| { |
| "entropy": 5.624916222095489, |
| "epoch": 0.24389481254494857, |
| "grad_norm": 0.39841362833976746, |
| "learning_rate": 0.0019946735844254253, |
| "loss": 5.8955, |
| "mean_token_accuracy": 0.14404148422181606, |
| "num_tokens": 56709946.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 5.538290665149689, |
| "epoch": 0.25014852568712675, |
| "grad_norm": 0.45605042576789856, |
| "learning_rate": 0.0019939394544224174, |
| "loss": 5.7458, |
| "mean_token_accuracy": 0.15620031498372555, |
| "num_tokens": 58164585.0, |
| "step": 2000 |
| }, |
| { |
| "entropy": 5.484496328830719, |
| "epoch": 0.2564022388293049, |
| "grad_norm": 0.3109079897403717, |
| "learning_rate": 0.001993158097943078, |
| "loss": 5.6343, |
| "mean_token_accuracy": 0.16481737934052945, |
| "num_tokens": 59616941.0, |
| "step": 2050 |
| }, |
| { |
| "entropy": 5.389205462932587, |
| "epoch": 0.26265595197148306, |
| "grad_norm": 0.4438038468360901, |
| "learning_rate": 0.001992329552113123, |
| "loss": 5.5087, |
| "mean_token_accuracy": 0.17319339476525783, |
| "num_tokens": 61069091.0, |
| "step": 2100 |
| }, |
| { |
| "entropy": 5.315016667842865, |
| "epoch": 0.2689096651136612, |
| "grad_norm": 0.32988205552101135, |
| "learning_rate": 0.001991453856300444, |
| "loss": 5.4307, |
| "mean_token_accuracy": 0.18028867013752461, |
| "num_tokens": 62519727.0, |
| "step": 2150 |
| }, |
| { |
| "entropy": 5.234848070144653, |
| "epoch": 0.2751633782558394, |
| "grad_norm": 0.4925743341445923, |
| "learning_rate": 0.0019905310521132354, |
| "loss": 5.2956, |
| "mean_token_accuracy": 0.18991463743150233, |
| "num_tokens": 63968440.0, |
| "step": 2200 |
| }, |
| { |
| "entropy": 5.179865393638611, |
| "epoch": 0.28141709139801757, |
| "grad_norm": 0.5279175639152527, |
| "learning_rate": 0.0019895611833980224, |
| "loss": 5.2495, |
| "mean_token_accuracy": 0.1949171732366085, |
| "num_tokens": 65425112.0, |
| "step": 2250 |
| }, |
| { |
| "entropy": 5.098879344463349, |
| "epoch": 0.2876708045401957, |
| "grad_norm": 0.2797149121761322, |
| "learning_rate": 0.001988544296237573, |
| "loss": 5.1657, |
| "mean_token_accuracy": 0.20032618649303913, |
| "num_tokens": 66887248.0, |
| "step": 2300 |
| }, |
| { |
| "entropy": 5.0061674976348876, |
| "epoch": 0.29392451768237393, |
| "grad_norm": 0.31702014803886414, |
| "learning_rate": 0.0019874804389487114, |
| "loss": 5.0679, |
| "mean_token_accuracy": 0.20840579211711885, |
| "num_tokens": 68334156.0, |
| "step": 2350 |
| }, |
| { |
| "entropy": 4.919540185928344, |
| "epoch": 0.3001782308245521, |
| "grad_norm": 0.3924313485622406, |
| "learning_rate": 0.00198636966208002, |
| "loss": 4.9854, |
| "mean_token_accuracy": 0.214654476121068, |
| "num_tokens": 69791998.0, |
| "step": 2400 |
| }, |
| { |
| "entropy": 4.897560942173004, |
| "epoch": 0.30643194396673024, |
| "grad_norm": 0.5938014984130859, |
| "learning_rate": 0.0019852120184094403, |
| "loss": 4.9439, |
| "mean_token_accuracy": 0.21875820383429528, |
| "num_tokens": 71248467.0, |
| "step": 2450 |
| }, |
| { |
| "entropy": 4.851730942726135, |
| "epoch": 0.3126856571089084, |
| "grad_norm": 0.3996203541755676, |
| "learning_rate": 0.001984007562941762, |
| "loss": 4.8655, |
| "mean_token_accuracy": 0.22476962342858314, |
| "num_tokens": 72702130.0, |
| "step": 2500 |
| }, |
| { |
| "entropy": 4.811781849861145, |
| "epoch": 0.3189393702510866, |
| "grad_norm": 0.3617077171802521, |
| "learning_rate": 0.001982756352906012, |
| "loss": 4.7954, |
| "mean_token_accuracy": 0.23030147060751915, |
| "num_tokens": 74147898.0, |
| "step": 2550 |
| }, |
| { |
| "entropy": 4.748332953453064, |
| "epoch": 0.32519308339326475, |
| "grad_norm": 0.4124760925769806, |
| "learning_rate": 0.001981458447752735, |
| "loss": 4.7312, |
| "mean_token_accuracy": 0.23577869348227978, |
| "num_tokens": 75596808.0, |
| "step": 2600 |
| }, |
| { |
| "entropy": 4.711932921409607, |
| "epoch": 0.3314467965354429, |
| "grad_norm": 0.530938982963562, |
| "learning_rate": 0.0019801139091511657, |
| "loss": 4.6903, |
| "mean_token_accuracy": 0.2386609048396349, |
| "num_tokens": 77048990.0, |
| "step": 2650 |
| }, |
| { |
| "entropy": 4.668835508823395, |
| "epoch": 0.3377005096776211, |
| "grad_norm": 0.37766778469085693, |
| "learning_rate": 0.0019787228009863034, |
| "loss": 4.6045, |
| "mean_token_accuracy": 0.24587701044976712, |
| "num_tokens": 78488093.0, |
| "step": 2700 |
| }, |
| { |
| "entropy": 4.620059154033661, |
| "epoch": 0.34395422281979926, |
| "grad_norm": 0.5416187644004822, |
| "learning_rate": 0.0019772851893558735, |
| "loss": 4.5806, |
| "mean_token_accuracy": 0.24779064148664476, |
| "num_tokens": 79945023.0, |
| "step": 2750 |
| }, |
| { |
| "entropy": 4.587407686710358, |
| "epoch": 0.3502079359619774, |
| "grad_norm": 0.37975025177001953, |
| "learning_rate": 0.0019758011425671865, |
| "loss": 4.5253, |
| "mean_token_accuracy": 0.25320823200047016, |
| "num_tokens": 81395329.0, |
| "step": 2800 |
| }, |
| { |
| "entropy": 4.567973017692566, |
| "epoch": 0.3564616491041556, |
| "grad_norm": 0.4259650707244873, |
| "learning_rate": 0.0019742707311338945, |
| "loss": 4.4934, |
| "mean_token_accuracy": 0.2562766546756029, |
| "num_tokens": 82841834.0, |
| "step": 2850 |
| }, |
| { |
| "entropy": 4.524812614917755, |
| "epoch": 0.3627153622463338, |
| "grad_norm": 0.4680491089820862, |
| "learning_rate": 0.0019726940277726393, |
| "loss": 4.4345, |
| "mean_token_accuracy": 0.262068510428071, |
| "num_tokens": 84298683.0, |
| "step": 2900 |
| }, |
| { |
| "entropy": 4.455774722099304, |
| "epoch": 0.3689690753885119, |
| "grad_norm": 0.5032073855400085, |
| "learning_rate": 0.0019710711073995984, |
| "loss": 4.3687, |
| "mean_token_accuracy": 0.2663784135878086, |
| "num_tokens": 85753078.0, |
| "step": 2950 |
| }, |
| { |
| "entropy": 4.445376222133636, |
| "epoch": 0.3752227885306901, |
| "grad_norm": 0.34912991523742676, |
| "learning_rate": 0.001969402047126923, |
| "loss": 4.3641, |
| "mean_token_accuracy": 0.26783014215528966, |
| "num_tokens": 87205732.0, |
| "step": 3000 |
| }, |
| { |
| "entropy": 4.4141078424453735, |
| "epoch": 0.3814765016728683, |
| "grad_norm": 0.3609781265258789, |
| "learning_rate": 0.001967686926259077, |
| "loss": 4.3228, |
| "mean_token_accuracy": 0.2722491616755724, |
| "num_tokens": 88665255.0, |
| "step": 3050 |
| }, |
| { |
| "entropy": 4.394694765806198, |
| "epoch": 0.38773021481504644, |
| "grad_norm": 0.3642273247241974, |
| "learning_rate": 0.0019659258262890683, |
| "loss": 4.2721, |
| "mean_token_accuracy": 0.27585428170859816, |
| "num_tokens": 90121985.0, |
| "step": 3100 |
| }, |
| { |
| "entropy": 4.3303623342514035, |
| "epoch": 0.3939839279572246, |
| "grad_norm": 0.4377816617488861, |
| "learning_rate": 0.001964118830894575, |
| "loss": 4.216, |
| "mean_token_accuracy": 0.2799024074524641, |
| "num_tokens": 91571242.0, |
| "step": 3150 |
| }, |
| { |
| "entropy": 4.312202001810074, |
| "epoch": 0.4002376410994028, |
| "grad_norm": 0.4025227129459381, |
| "learning_rate": 0.0019622660259339705, |
| "loss": 4.1866, |
| "mean_token_accuracy": 0.2834921093285084, |
| "num_tokens": 93022711.0, |
| "step": 3200 |
| }, |
| { |
| "entropy": 4.284852714538574, |
| "epoch": 0.40649135424158095, |
| "grad_norm": 0.34949183464050293, |
| "learning_rate": 0.0019603674994422456, |
| "loss": 4.1723, |
| "mean_token_accuracy": 0.28453252926468847, |
| "num_tokens": 94479555.0, |
| "step": 3250 |
| }, |
| { |
| "entropy": 4.307129458189011, |
| "epoch": 0.4127450673837591, |
| "grad_norm": 0.40033891797065735, |
| "learning_rate": 0.0019584233416268214, |
| "loss": 4.1644, |
| "mean_token_accuracy": 0.28743029810488224, |
| "num_tokens": 95939600.0, |
| "step": 3300 |
| }, |
| { |
| "entropy": 4.242270601987839, |
| "epoch": 0.41899878052593725, |
| "grad_norm": 0.36012735962867737, |
| "learning_rate": 0.0019564336448632683, |
| "loss": 4.0949, |
| "mean_token_accuracy": 0.2915411788970232, |
| "num_tokens": 97385909.0, |
| "step": 3350 |
| }, |
| { |
| "entropy": 4.240862241983414, |
| "epoch": 0.42525249366811546, |
| "grad_norm": 0.41399946808815, |
| "learning_rate": 0.001954398503690913, |
| "loss": 4.0866, |
| "mean_token_accuracy": 0.2938184529542923, |
| "num_tokens": 98835622.0, |
| "step": 3400 |
| }, |
| { |
| "entropy": 4.196718490123748, |
| "epoch": 0.4315062068102936, |
| "grad_norm": 0.36769694089889526, |
| "learning_rate": 0.0019523180148083485, |
| "loss": 4.0527, |
| "mean_token_accuracy": 0.29610458359122277, |
| "num_tokens": 100288372.0, |
| "step": 3450 |
| }, |
| { |
| "entropy": 4.174614375829696, |
| "epoch": 0.43775991995247177, |
| "grad_norm": 0.37334468960762024, |
| "learning_rate": 0.001950192277068838, |
| "loss": 4.0218, |
| "mean_token_accuracy": 0.29870147973299027, |
| "num_tokens": 101742863.0, |
| "step": 3500 |
| }, |
| { |
| "entropy": 4.1543604850769045, |
| "epoch": 0.44401363309465, |
| "grad_norm": 0.4744473993778229, |
| "learning_rate": 0.0019480213914756198, |
| "loss": 3.9855, |
| "mean_token_accuracy": 0.3036028662323952, |
| "num_tokens": 103192353.0, |
| "step": 3550 |
| }, |
| { |
| "entropy": 4.149127557277679, |
| "epoch": 0.4502673462368281, |
| "grad_norm": 0.46005499362945557, |
| "learning_rate": 0.001945805461177106, |
| "loss": 3.9889, |
| "mean_token_accuracy": 0.3025831463932991, |
| "num_tokens": 104654829.0, |
| "step": 3600 |
| }, |
| { |
| "entropy": 4.131506505012513, |
| "epoch": 0.4565210593790063, |
| "grad_norm": 0.399476021528244, |
| "learning_rate": 0.0019435445914619835, |
| "loss": 3.9587, |
| "mean_token_accuracy": 0.3061337152123451, |
| "num_tokens": 106112408.0, |
| "step": 3650 |
| }, |
| { |
| "entropy": 4.12854926109314, |
| "epoch": 0.46277477252118443, |
| "grad_norm": 0.35083433985710144, |
| "learning_rate": 0.0019412388897542105, |
| "loss": 3.9582, |
| "mean_token_accuracy": 0.30483592957258226, |
| "num_tokens": 107568410.0, |
| "step": 3700 |
| }, |
| { |
| "entropy": 4.099326175451279, |
| "epoch": 0.46902848566336264, |
| "grad_norm": 0.3819263279438019, |
| "learning_rate": 0.0019388884656079118, |
| "loss": 3.9136, |
| "mean_token_accuracy": 0.3103523187339306, |
| "num_tokens": 109023493.0, |
| "step": 3750 |
| }, |
| { |
| "entropy": 4.095232236385345, |
| "epoch": 0.4752821988055408, |
| "grad_norm": 0.3186725676059723, |
| "learning_rate": 0.0019364934307021732, |
| "loss": 3.8919, |
| "mean_token_accuracy": 0.31130151748657225, |
| "num_tokens": 110472661.0, |
| "step": 3800 |
| }, |
| { |
| "entropy": 4.082479554414749, |
| "epoch": 0.48153591194771894, |
| "grad_norm": 0.40309175848960876, |
| "learning_rate": 0.0019340538988357374, |
| "loss": 3.8624, |
| "mean_token_accuracy": 0.31485995426774027, |
| "num_tokens": 111928648.0, |
| "step": 3850 |
| }, |
| { |
| "entropy": 4.07897432565689, |
| "epoch": 0.48778962508989715, |
| "grad_norm": 0.36660367250442505, |
| "learning_rate": 0.001931569985921594, |
| "loss": 3.85, |
| "mean_token_accuracy": 0.31685930326581, |
| "num_tokens": 113391508.0, |
| "step": 3900 |
| }, |
| { |
| "entropy": 4.041114414930344, |
| "epoch": 0.4940433382320753, |
| "grad_norm": 0.399808794260025, |
| "learning_rate": 0.0019290418099814732, |
| "loss": 3.8116, |
| "mean_token_accuracy": 0.3205082568526268, |
| "num_tokens": 114838971.0, |
| "step": 3950 |
| }, |
| { |
| "entropy": 4.03851842045784, |
| "epoch": 0.5002970513742535, |
| "grad_norm": 0.36455509066581726, |
| "learning_rate": 0.0019264694911402393, |
| "loss": 3.8159, |
| "mean_token_accuracy": 0.31901825517416, |
| "num_tokens": 116295558.0, |
| "step": 4000 |
| }, |
| { |
| "entropy": 3.97854936003685, |
| "epoch": 0.5065507645164317, |
| "grad_norm": 0.34177082777023315, |
| "learning_rate": 0.0019238531516201794, |
| "loss": 3.7636, |
| "mean_token_accuracy": 0.3237869530916214, |
| "num_tokens": 117740838.0, |
| "step": 4050 |
| }, |
| { |
| "entropy": 3.976211417913437, |
| "epoch": 0.5128044776586098, |
| "grad_norm": 0.2913322448730469, |
| "learning_rate": 0.0019211929157352016, |
| "loss": 3.7627, |
| "mean_token_accuracy": 0.32512620434165, |
| "num_tokens": 119187209.0, |
| "step": 4100 |
| }, |
| { |
| "entropy": 3.98531445145607, |
| "epoch": 0.519058190800788, |
| "grad_norm": 0.3192107081413269, |
| "learning_rate": 0.0019184889098849225, |
| "loss": 3.7607, |
| "mean_token_accuracy": 0.325792491286993, |
| "num_tokens": 120636737.0, |
| "step": 4150 |
| }, |
| { |
| "entropy": 3.993393454551697, |
| "epoch": 0.5253119039429661, |
| "grad_norm": 0.42490988969802856, |
| "learning_rate": 0.0019157412625486656, |
| "loss": 3.7979, |
| "mean_token_accuracy": 0.3200970686972141, |
| "num_tokens": 122093771.0, |
| "step": 4200 |
| }, |
| { |
| "entropy": 3.9543004703521727, |
| "epoch": 0.5315656170851443, |
| "grad_norm": 0.3723016679286957, |
| "learning_rate": 0.001912950104279355, |
| "loss": 3.7382, |
| "mean_token_accuracy": 0.3264580935239792, |
| "num_tokens": 123549819.0, |
| "step": 4250 |
| }, |
| { |
| "entropy": 3.915160721540451, |
| "epoch": 0.5378193302273224, |
| "grad_norm": 0.3779139220714569, |
| "learning_rate": 0.0019101155676973115, |
| "loss": 3.7012, |
| "mean_token_accuracy": 0.33177016422152517, |
| "num_tokens": 124998395.0, |
| "step": 4300 |
| }, |
| { |
| "entropy": 3.9146971213817596, |
| "epoch": 0.5440730433695007, |
| "grad_norm": 0.3581169843673706, |
| "learning_rate": 0.001907237787483953, |
| "loss": 3.7012, |
| "mean_token_accuracy": 0.33225410625338553, |
| "num_tokens": 126458044.0, |
| "step": 4350 |
| }, |
| { |
| "entropy": 3.875672823190689, |
| "epoch": 0.5503267565116788, |
| "grad_norm": 0.32717034220695496, |
| "learning_rate": 0.0019043169003753945, |
| "loss": 3.6556, |
| "mean_token_accuracy": 0.336458790153265, |
| "num_tokens": 127906980.0, |
| "step": 4400 |
| }, |
| { |
| "entropy": 3.879705456495285, |
| "epoch": 0.556580469653857, |
| "grad_norm": 0.32244476675987244, |
| "learning_rate": 0.0019013530451559503, |
| "loss": 3.6516, |
| "mean_token_accuracy": 0.33660307377576826, |
| "num_tokens": 129362058.0, |
| "step": 4450 |
| }, |
| { |
| "entropy": 3.870090285539627, |
| "epoch": 0.5628341827960351, |
| "grad_norm": 0.3444347083568573, |
| "learning_rate": 0.001898346362651541, |
| "loss": 3.6327, |
| "mean_token_accuracy": 0.3381097550690174, |
| "num_tokens": 130814885.0, |
| "step": 4500 |
| }, |
| { |
| "entropy": 3.8484600913524627, |
| "epoch": 0.5690878959382133, |
| "grad_norm": 0.3887946605682373, |
| "learning_rate": 0.0018952969957230002, |
| "loss": 3.5848, |
| "mean_token_accuracy": 0.3428233973681927, |
| "num_tokens": 132264698.0, |
| "step": 4550 |
| }, |
| { |
| "entropy": 3.8668723714351656, |
| "epoch": 0.5753416090803914, |
| "grad_norm": 0.29115742444992065, |
| "learning_rate": 0.0018922050892592904, |
| "loss": 3.6327, |
| "mean_token_accuracy": 0.339210794121027, |
| "num_tokens": 133724718.0, |
| "step": 4600 |
| }, |
| { |
| "entropy": 3.8426230347156523, |
| "epoch": 0.5815953222225696, |
| "grad_norm": 0.3402599096298218, |
| "learning_rate": 0.0018890707901706146, |
| "loss": 3.5872, |
| "mean_token_accuracy": 0.344546006321907, |
| "num_tokens": 135180844.0, |
| "step": 4650 |
| }, |
| { |
| "entropy": 3.824489916563034, |
| "epoch": 0.5878490353647479, |
| "grad_norm": 0.31970226764678955, |
| "learning_rate": 0.0018858942473814378, |
| "loss": 3.5729, |
| "mean_token_accuracy": 0.34506093606352806, |
| "num_tokens": 136629379.0, |
| "step": 4700 |
| }, |
| { |
| "entropy": 3.790500236749649, |
| "epoch": 0.594102748506926, |
| "grad_norm": 0.3910897970199585, |
| "learning_rate": 0.001882675611823411, |
| "loss": 3.5463, |
| "mean_token_accuracy": 0.3468193484842777, |
| "num_tokens": 138088613.0, |
| "step": 4750 |
| }, |
| { |
| "entropy": 3.840239323377609, |
| "epoch": 0.6003564616491042, |
| "grad_norm": 0.3762884736061096, |
| "learning_rate": 0.0018794150364281998, |
| "loss": 3.5642, |
| "mean_token_accuracy": 0.3468084912002087, |
| "num_tokens": 139542618.0, |
| "step": 4800 |
| }, |
| { |
| "entropy": 3.8174883902072905, |
| "epoch": 0.6066101747912823, |
| "grad_norm": 0.3109763562679291, |
| "learning_rate": 0.0018761126761202176, |
| "loss": 3.552, |
| "mean_token_accuracy": 0.34760625913739207, |
| "num_tokens": 141007922.0, |
| "step": 4850 |
| }, |
| { |
| "entropy": 3.7677294433116915, |
| "epoch": 0.6128638879334605, |
| "grad_norm": 0.36054331064224243, |
| "learning_rate": 0.0018727686878092637, |
| "loss": 3.5001, |
| "mean_token_accuracy": 0.35205888241529465, |
| "num_tokens": 142455882.0, |
| "step": 4900 |
| }, |
| { |
| "entropy": 3.7628906965255737, |
| "epoch": 0.6191176010756386, |
| "grad_norm": 0.36796653270721436, |
| "learning_rate": 0.0018693832303830695, |
| "loss": 3.5106, |
| "mean_token_accuracy": 0.3525958973169327, |
| "num_tokens": 143897412.0, |
| "step": 4950 |
| }, |
| { |
| "entropy": 3.768322126865387, |
| "epoch": 0.6253713142178168, |
| "grad_norm": 0.3298179507255554, |
| "learning_rate": 0.001865956464699748, |
| "loss": 3.5025, |
| "mean_token_accuracy": 0.351756524592638, |
| "num_tokens": 145343541.0, |
| "step": 5000 |
| }, |
| { |
| "entropy": 3.7577738535404204, |
| "epoch": 0.631625027359995, |
| "grad_norm": 0.31647345423698425, |
| "learning_rate": 0.001862488553580151, |
| "loss": 3.4857, |
| "mean_token_accuracy": 0.35421416819095614, |
| "num_tokens": 146796685.0, |
| "step": 5050 |
| }, |
| { |
| "entropy": 3.755051065683365, |
| "epoch": 0.6378787405021732, |
| "grad_norm": 0.3068569600582123, |
| "learning_rate": 0.001858979661800132, |
| "loss": 3.4748, |
| "mean_token_accuracy": 0.3558480441570282, |
| "num_tokens": 148260883.0, |
| "step": 5100 |
| }, |
| { |
| "entropy": 3.7353078365325927, |
| "epoch": 0.6441324536443513, |
| "grad_norm": 0.3454782962799072, |
| "learning_rate": 0.0018554299560827187, |
| "loss": 3.4677, |
| "mean_token_accuracy": 0.3566476738452911, |
| "num_tokens": 149713216.0, |
| "step": 5150 |
| }, |
| { |
| "entropy": 3.7258300411701204, |
| "epoch": 0.6503861667865295, |
| "grad_norm": 0.36780253052711487, |
| "learning_rate": 0.0018518396050901892, |
| "loss": 3.4538, |
| "mean_token_accuracy": 0.35792204320430754, |
| "num_tokens": 151165656.0, |
| "step": 5200 |
| }, |
| { |
| "entropy": 3.73144770860672, |
| "epoch": 0.6566398799287076, |
| "grad_norm": 0.3001205325126648, |
| "learning_rate": 0.0018482087794160593, |
| "loss": 3.4446, |
| "mean_token_accuracy": 0.3578939388692379, |
| "num_tokens": 152612381.0, |
| "step": 5250 |
| }, |
| { |
| "entropy": 3.6795049965381623, |
| "epoch": 0.6628935930708858, |
| "grad_norm": 0.33437180519104004, |
| "learning_rate": 0.001844537651576977, |
| "loss": 3.4153, |
| "mean_token_accuracy": 0.36169921815395356, |
| "num_tokens": 154065168.0, |
| "step": 5300 |
| }, |
| { |
| "entropy": 3.716750056743622, |
| "epoch": 0.669147306213064, |
| "grad_norm": 0.32502371072769165, |
| "learning_rate": 0.001840826396004525, |
| "loss": 3.4496, |
| "mean_token_accuracy": 0.3587889949977398, |
| "num_tokens": 155524242.0, |
| "step": 5350 |
| }, |
| { |
| "entropy": 3.6966857600212095, |
| "epoch": 0.6754010193552422, |
| "grad_norm": 0.30576571822166443, |
| "learning_rate": 0.0018370751890369325, |
| "loss": 3.4046, |
| "mean_token_accuracy": 0.3636187882721424, |
| "num_tokens": 156971839.0, |
| "step": 5400 |
| }, |
| { |
| "entropy": 3.709896868467331, |
| "epoch": 0.6816547324974204, |
| "grad_norm": 0.3042902946472168, |
| "learning_rate": 0.0018332842089106966, |
| "loss": 3.4222, |
| "mean_token_accuracy": 0.36168786689639093, |
| "num_tokens": 158425753.0, |
| "step": 5450 |
| }, |
| { |
| "entropy": 3.6710725367069243, |
| "epoch": 0.6879084456395985, |
| "grad_norm": 0.31839218735694885, |
| "learning_rate": 0.001829453635752115, |
| "loss": 3.3889, |
| "mean_token_accuracy": 0.3644601459801197, |
| "num_tokens": 159875972.0, |
| "step": 5500 |
| }, |
| { |
| "entropy": 3.6800344026088716, |
| "epoch": 0.6941621587817767, |
| "grad_norm": 0.2987898886203766, |
| "learning_rate": 0.0018255836515687243, |
| "loss": 3.3678, |
| "mean_token_accuracy": 0.3673081286251545, |
| "num_tokens": 161331864.0, |
| "step": 5550 |
| }, |
| { |
| "entropy": 3.6611654114723207, |
| "epoch": 0.7004158719239548, |
| "grad_norm": 0.35385656356811523, |
| "learning_rate": 0.0018216744402406555, |
| "loss": 3.3577, |
| "mean_token_accuracy": 0.36767142444849016, |
| "num_tokens": 162777956.0, |
| "step": 5600 |
| }, |
| { |
| "entropy": 3.66405290722847, |
| "epoch": 0.706669585066133, |
| "grad_norm": 0.48773252964019775, |
| "learning_rate": 0.0018177261875118947, |
| "loss": 3.3652, |
| "mean_token_accuracy": 0.366995564699173, |
| "num_tokens": 164231330.0, |
| "step": 5650 |
| }, |
| { |
| "entropy": 3.664638661146164, |
| "epoch": 0.7129232982083112, |
| "grad_norm": 0.32329079508781433, |
| "learning_rate": 0.001813739080981458, |
| "loss": 3.3734, |
| "mean_token_accuracy": 0.3672369138896465, |
| "num_tokens": 165680616.0, |
| "step": 5700 |
| }, |
| { |
| "entropy": 3.6627173352241518, |
| "epoch": 0.7191770113504894, |
| "grad_norm": 0.3321169316768646, |
| "learning_rate": 0.0018097133100944786, |
| "loss": 3.3584, |
| "mean_token_accuracy": 0.36895839124917984, |
| "num_tokens": 167132788.0, |
| "step": 5750 |
| }, |
| { |
| "entropy": 3.665049159526825, |
| "epoch": 0.7254307244926675, |
| "grad_norm": 0.37287676334381104, |
| "learning_rate": 0.001805649066133205, |
| "loss": 3.3521, |
| "mean_token_accuracy": 0.36942937210202215, |
| "num_tokens": 168588161.0, |
| "step": 5800 |
| }, |
| { |
| "entropy": 3.6524035894870757, |
| "epoch": 0.7316844376348457, |
| "grad_norm": 0.2737661302089691, |
| "learning_rate": 0.001801546542207912, |
| "loss": 3.3352, |
| "mean_token_accuracy": 0.3705759882926941, |
| "num_tokens": 170041372.0, |
| "step": 5850 |
| }, |
| { |
| "entropy": 3.638882428407669, |
| "epoch": 0.7379381507770238, |
| "grad_norm": 0.2713734805583954, |
| "learning_rate": 0.0017974059332477254, |
| "loss": 3.3251, |
| "mean_token_accuracy": 0.37299351826310156, |
| "num_tokens": 171499920.0, |
| "step": 5900 |
| }, |
| { |
| "entropy": 3.6681057953834535, |
| "epoch": 0.744191863919202, |
| "grad_norm": 0.294450044631958, |
| "learning_rate": 0.0017932274359913599, |
| "loss": 3.3267, |
| "mean_token_accuracy": 0.3729023614525795, |
| "num_tokens": 172950683.0, |
| "step": 5950 |
| }, |
| { |
| "entropy": 3.644505295753479, |
| "epoch": 0.7504455770613802, |
| "grad_norm": 0.308858722448349, |
| "learning_rate": 0.001789011248977772, |
| "loss": 3.338, |
| "mean_token_accuracy": 0.37171697527170183, |
| "num_tokens": 174406731.0, |
| "step": 6000 |
| }, |
| { |
| "entropy": 3.616956330537796, |
| "epoch": 0.7566992902035584, |
| "grad_norm": 0.34715735912323, |
| "learning_rate": 0.001784757572536726, |
| "loss": 3.2902, |
| "mean_token_accuracy": 0.3758828853070736, |
| "num_tokens": 175850934.0, |
| "step": 6050 |
| }, |
| { |
| "entropy": 3.6194920027256012, |
| "epoch": 0.7629530033457366, |
| "grad_norm": 0.3026665449142456, |
| "learning_rate": 0.0017804666087792743, |
| "loss": 3.3085, |
| "mean_token_accuracy": 0.37579055145382884, |
| "num_tokens": 177312757.0, |
| "step": 6100 |
| }, |
| { |
| "entropy": 3.6085926043987273, |
| "epoch": 0.7692067164879147, |
| "grad_norm": 0.3407142758369446, |
| "learning_rate": 0.001776138561588156, |
| "loss": 3.2887, |
| "mean_token_accuracy": 0.37644373178482055, |
| "num_tokens": 178768968.0, |
| "step": 6150 |
| }, |
| { |
| "entropy": 3.5980601501464844, |
| "epoch": 0.7754604296300929, |
| "grad_norm": 0.30068376660346985, |
| "learning_rate": 0.0017717736366081086, |
| "loss": 3.2662, |
| "mean_token_accuracy": 0.3782395477592945, |
| "num_tokens": 180224489.0, |
| "step": 6200 |
| }, |
| { |
| "entropy": 3.564172661304474, |
| "epoch": 0.781714142772271, |
| "grad_norm": 0.31278517842292786, |
| "learning_rate": 0.0017673720412360971, |
| "loss": 3.2472, |
| "mean_token_accuracy": 0.38103450983762743, |
| "num_tokens": 181675705.0, |
| "step": 6250 |
| }, |
| { |
| "entropy": 3.572136676311493, |
| "epoch": 0.7879678559144492, |
| "grad_norm": 0.36869823932647705, |
| "learning_rate": 0.0017629339846114598, |
| "loss": 3.2544, |
| "mean_token_accuracy": 0.3806936974823475, |
| "num_tokens": 183131543.0, |
| "step": 6300 |
| }, |
| { |
| "entropy": 3.5726712560653686, |
| "epoch": 0.7942215690566273, |
| "grad_norm": 0.28678107261657715, |
| "learning_rate": 0.0017584596776059707, |
| "loss": 3.266, |
| "mean_token_accuracy": 0.37899156510829923, |
| "num_tokens": 184585889.0, |
| "step": 6350 |
| }, |
| { |
| "entropy": 3.5974609780311586, |
| "epoch": 0.8004752821988056, |
| "grad_norm": 0.2944851219654083, |
| "learning_rate": 0.0017539493328138206, |
| "loss": 3.2432, |
| "mean_token_accuracy": 0.38106390431523324, |
| "num_tokens": 186029456.0, |
| "step": 6400 |
| }, |
| { |
| "entropy": 3.5803931736946106, |
| "epoch": 0.8067289953409837, |
| "grad_norm": 0.9102575182914734, |
| "learning_rate": 0.0017494031645415157, |
| "loss": 3.2312, |
| "mean_token_accuracy": 0.38339566633105276, |
| "num_tokens": 187477525.0, |
| "step": 6450 |
| }, |
| { |
| "entropy": 3.6113105177879334, |
| "epoch": 0.8129827084831619, |
| "grad_norm": 0.29048532247543335, |
| "learning_rate": 0.0017448213887976936, |
| "loss": 3.3103, |
| "mean_token_accuracy": 0.3724804125726223, |
| "num_tokens": 188930874.0, |
| "step": 6500 |
| }, |
| { |
| "entropy": 3.545231056213379, |
| "epoch": 0.81923642162534, |
| "grad_norm": 0.2970048189163208, |
| "learning_rate": 0.0017402042232828629, |
| "loss": 3.2126, |
| "mean_token_accuracy": 0.38453035309910777, |
| "num_tokens": 190377981.0, |
| "step": 6550 |
| }, |
| { |
| "entropy": 3.536184823513031, |
| "epoch": 0.8254901347675182, |
| "grad_norm": 0.30343198776245117, |
| "learning_rate": 0.0017355518873790555, |
| "loss": 3.223, |
| "mean_token_accuracy": 0.3839683771133423, |
| "num_tokens": 191831429.0, |
| "step": 6600 |
| }, |
| { |
| "entropy": 3.5653406488895416, |
| "epoch": 0.8317438479096964, |
| "grad_norm": 0.300936758518219, |
| "learning_rate": 0.001730864602139406, |
| "loss": 3.2313, |
| "mean_token_accuracy": 0.38390363290905954, |
| "num_tokens": 193283746.0, |
| "step": 6650 |
| }, |
| { |
| "entropy": 3.5464817702770235, |
| "epoch": 0.8379975610518745, |
| "grad_norm": 0.25732260942459106, |
| "learning_rate": 0.001726142590277646, |
| "loss": 3.1963, |
| "mean_token_accuracy": 0.3856934300065041, |
| "num_tokens": 194733765.0, |
| "step": 6700 |
| }, |
| { |
| "entropy": 3.5280859065055847, |
| "epoch": 0.8442512741940528, |
| "grad_norm": 0.28379517793655396, |
| "learning_rate": 0.0017213860761575242, |
| "loss": 3.1849, |
| "mean_token_accuracy": 0.38866120934486387, |
| "num_tokens": 196181881.0, |
| "step": 6750 |
| }, |
| { |
| "entropy": 3.5327327394485475, |
| "epoch": 0.8505049873362309, |
| "grad_norm": 0.2904554307460785, |
| "learning_rate": 0.001716595285782144, |
| "loss": 3.1818, |
| "mean_token_accuracy": 0.38906206741929056, |
| "num_tokens": 197633452.0, |
| "step": 6800 |
| }, |
| { |
| "entropy": 3.5628380298614504, |
| "epoch": 0.8567587004784091, |
| "grad_norm": 0.26626577973365784, |
| "learning_rate": 0.0017117704467832263, |
| "loss": 3.2098, |
| "mean_token_accuracy": 0.38593448519706725, |
| "num_tokens": 199091645.0, |
| "step": 6850 |
| }, |
| { |
| "entropy": 3.524178329706192, |
| "epoch": 0.8630124136205872, |
| "grad_norm": 0.28848186135292053, |
| "learning_rate": 0.0017069117884102925, |
| "loss": 3.1794, |
| "mean_token_accuracy": 0.3886136619746685, |
| "num_tokens": 200550605.0, |
| "step": 6900 |
| }, |
| { |
| "entropy": 3.512812074422836, |
| "epoch": 0.8692661267627654, |
| "grad_norm": 0.2841011881828308, |
| "learning_rate": 0.0017020195415197736, |
| "loss": 3.161, |
| "mean_token_accuracy": 0.39136223718523977, |
| "num_tokens": 201989189.0, |
| "step": 6950 |
| }, |
| { |
| "entropy": 3.518073334693909, |
| "epoch": 0.8755198399049435, |
| "grad_norm": 0.2641650140285492, |
| "learning_rate": 0.0016970939385640396, |
| "loss": 3.1677, |
| "mean_token_accuracy": 0.3900047905743122, |
| "num_tokens": 203444023.0, |
| "step": 7000 |
| }, |
| { |
| "entropy": 3.512884209156036, |
| "epoch": 0.8817735530471217, |
| "grad_norm": 0.3092753291130066, |
| "learning_rate": 0.0016921352135803559, |
| "loss": 3.1787, |
| "mean_token_accuracy": 0.3905393898487091, |
| "num_tokens": 204898253.0, |
| "step": 7050 |
| }, |
| { |
| "entropy": 3.4959859812259673, |
| "epoch": 0.8880272661893, |
| "grad_norm": 0.2931444048881531, |
| "learning_rate": 0.0016871436021797615, |
| "loss": 3.1478, |
| "mean_token_accuracy": 0.3930986747145653, |
| "num_tokens": 206355062.0, |
| "step": 7100 |
| }, |
| { |
| "entropy": 3.494699535369873, |
| "epoch": 0.8942809793314781, |
| "grad_norm": 0.2965364158153534, |
| "learning_rate": 0.0016821193415358753, |
| "loss": 3.1468, |
| "mean_token_accuracy": 0.39268109157681463, |
| "num_tokens": 207812565.0, |
| "step": 7150 |
| }, |
| { |
| "entropy": 3.5158278048038483, |
| "epoch": 0.9005346924736563, |
| "grad_norm": 0.2810881435871124, |
| "learning_rate": 0.0016770626703736275, |
| "loss": 3.1539, |
| "mean_token_accuracy": 0.39324876174330714, |
| "num_tokens": 209264738.0, |
| "step": 7200 |
| }, |
| { |
| "entropy": 3.516902258396149, |
| "epoch": 0.9067884056158344, |
| "grad_norm": 0.25858649611473083, |
| "learning_rate": 0.0016719738289579155, |
| "loss": 3.1521, |
| "mean_token_accuracy": 0.39297880709171296, |
| "num_tokens": 210725805.0, |
| "step": 7250 |
| }, |
| { |
| "entropy": 3.521990531682968, |
| "epoch": 0.9130421187580126, |
| "grad_norm": 0.2878429889678955, |
| "learning_rate": 0.0016668530590821882, |
| "loss": 3.1219, |
| "mean_token_accuracy": 0.3965709181129932, |
| "num_tokens": 212175877.0, |
| "step": 7300 |
| }, |
| { |
| "entropy": 3.5328981733322142, |
| "epoch": 0.9192958319001907, |
| "grad_norm": 0.25898534059524536, |
| "learning_rate": 0.0016617006040569571, |
| "loss": 3.1404, |
| "mean_token_accuracy": 0.3935855607688427, |
| "num_tokens": 213623949.0, |
| "step": 7350 |
| }, |
| { |
| "entropy": 3.5099762165546418, |
| "epoch": 0.9255495450423689, |
| "grad_norm": 0.2775290012359619, |
| "learning_rate": 0.001656516708698236, |
| "loss": 3.1184, |
| "mean_token_accuracy": 0.3956405273079872, |
| "num_tokens": 215068031.0, |
| "step": 7400 |
| }, |
| { |
| "entropy": 3.524550086259842, |
| "epoch": 0.9318032581845471, |
| "grad_norm": 0.26542389392852783, |
| "learning_rate": 0.0016513016193159089, |
| "loss": 3.1305, |
| "mean_token_accuracy": 0.3949857813119888, |
| "num_tokens": 216520762.0, |
| "step": 7450 |
| }, |
| { |
| "entropy": 3.52587819814682, |
| "epoch": 0.9380569713267253, |
| "grad_norm": 0.2635110020637512, |
| "learning_rate": 0.001646055583702026, |
| "loss": 3.1235, |
| "mean_token_accuracy": 0.3954600378870964, |
| "num_tokens": 217972779.0, |
| "step": 7500 |
| }, |
| { |
| "entropy": 3.5055534410476685, |
| "epoch": 0.9443106844689034, |
| "grad_norm": 0.2407570630311966, |
| "learning_rate": 0.0016407788511190308, |
| "loss": 3.0997, |
| "mean_token_accuracy": 0.3990290623903274, |
| "num_tokens": 219418956.0, |
| "step": 7550 |
| }, |
| { |
| "entropy": 3.491668597459793, |
| "epoch": 0.9505643976110816, |
| "grad_norm": 0.2876957058906555, |
| "learning_rate": 0.0016354716722879151, |
| "loss": 3.1016, |
| "mean_token_accuracy": 0.3992904122173786, |
| "num_tokens": 220868170.0, |
| "step": 7600 |
| }, |
| { |
| "entropy": 3.4823805701732637, |
| "epoch": 0.9568181107532597, |
| "grad_norm": 0.26311132311820984, |
| "learning_rate": 0.001630134299376308, |
| "loss": 3.1059, |
| "mean_token_accuracy": 0.39762111693620683, |
| "num_tokens": 222320108.0, |
| "step": 7650 |
| }, |
| { |
| "entropy": 3.4473106372356415, |
| "epoch": 0.9630718238954379, |
| "grad_norm": 0.27912265062332153, |
| "learning_rate": 0.0016247669859864933, |
| "loss": 3.0641, |
| "mean_token_accuracy": 0.40164967700839044, |
| "num_tokens": 223771680.0, |
| "step": 7700 |
| }, |
| { |
| "entropy": 3.462431426048279, |
| "epoch": 0.969325537037616, |
| "grad_norm": 0.26055315136909485, |
| "learning_rate": 0.0016193699871433595, |
| "loss": 3.0906, |
| "mean_token_accuracy": 0.40069493383169175, |
| "num_tokens": 225224312.0, |
| "step": 7750 |
| }, |
| { |
| "entropy": 3.46071582198143, |
| "epoch": 0.9755792501797943, |
| "grad_norm": 0.2583518624305725, |
| "learning_rate": 0.0016139435592822837, |
| "loss": 3.0814, |
| "mean_token_accuracy": 0.40042845577001573, |
| "num_tokens": 226669853.0, |
| "step": 7800 |
| }, |
| { |
| "entropy": 3.429822801351547, |
| "epoch": 0.9818329633219725, |
| "grad_norm": 0.24933992326259613, |
| "learning_rate": 0.0016084879602369449, |
| "loss": 3.0642, |
| "mean_token_accuracy": 0.40294322282075884, |
| "num_tokens": 228118458.0, |
| "step": 7850 |
| }, |
| { |
| "entropy": 3.462758048772812, |
| "epoch": 0.9880866764641506, |
| "grad_norm": 0.2879364490509033, |
| "learning_rate": 0.0016030034492270752, |
| "loss": 3.0928, |
| "mean_token_accuracy": 0.40064197540283203, |
| "num_tokens": 229576123.0, |
| "step": 7900 |
| }, |
| { |
| "entropy": 3.457154052257538, |
| "epoch": 0.9943403896063288, |
| "grad_norm": 0.2881210148334503, |
| "learning_rate": 0.0015974902868461432, |
| "loss": 3.0798, |
| "mean_token_accuracy": 0.4007870285212994, |
| "num_tokens": 231024565.0, |
| "step": 7950 |
| }, |
| { |
| "entropy": 3.424220819763726, |
| "epoch": 1.0005002970513743, |
| "grad_norm": 0.2757372260093689, |
| "learning_rate": 0.0015919487350489704, |
| "loss": 3.0722, |
| "mean_token_accuracy": 0.402178642713479, |
| "num_tokens": 232448848.0, |
| "step": 8000 |
| }, |
| { |
| "entropy": 3.4124892342090605, |
| "epoch": 1.0067540101935524, |
| "grad_norm": 0.2726467251777649, |
| "learning_rate": 0.0015863790571392854, |
| "loss": 3.0441, |
| "mean_token_accuracy": 0.4046463569998741, |
| "num_tokens": 233902055.0, |
| "step": 8050 |
| }, |
| { |
| "entropy": 3.424123123884201, |
| "epoch": 1.0130077233357306, |
| "grad_norm": 0.2699504494667053, |
| "learning_rate": 0.0015807815177572148, |
| "loss": 3.0545, |
| "mean_token_accuracy": 0.40355317264795304, |
| "num_tokens": 235361552.0, |
| "step": 8100 |
| }, |
| { |
| "entropy": 3.410174704790115, |
| "epoch": 1.0192614364779087, |
| "grad_norm": 0.26823437213897705, |
| "learning_rate": 0.0015751563828667052, |
| "loss": 3.0393, |
| "mean_token_accuracy": 0.40559999957680704, |
| "num_tokens": 236812470.0, |
| "step": 8150 |
| }, |
| { |
| "entropy": 3.4348238849639894, |
| "epoch": 1.025515149620087, |
| "grad_norm": 0.24912285804748535, |
| "learning_rate": 0.0015695039197428902, |
| "loss": 3.0611, |
| "mean_token_accuracy": 0.4035358209908009, |
| "num_tokens": 238271687.0, |
| "step": 8200 |
| }, |
| { |
| "entropy": 3.420966486930847, |
| "epoch": 1.0317688627622652, |
| "grad_norm": 0.27924877405166626, |
| "learning_rate": 0.0015638243969593884, |
| "loss": 3.0306, |
| "mean_token_accuracy": 0.4060466636717319, |
| "num_tokens": 239728605.0, |
| "step": 8250 |
| }, |
| { |
| "entropy": 3.414804896116257, |
| "epoch": 1.0380225759044432, |
| "grad_norm": 0.279109388589859, |
| "learning_rate": 0.0015581180843755424, |
| "loss": 3.0462, |
| "mean_token_accuracy": 0.4052661190927029, |
| "num_tokens": 241186564.0, |
| "step": 8300 |
| }, |
| { |
| "entropy": 3.3893780303001404, |
| "epoch": 1.0442762890466215, |
| "grad_norm": 0.25905993580818176, |
| "learning_rate": 0.0015523852531235983, |
| "loss": 2.9909, |
| "mean_token_accuracy": 0.4110270082950592, |
| "num_tokens": 242636402.0, |
| "step": 8350 |
| }, |
| { |
| "entropy": 3.3776789891719816, |
| "epoch": 1.0505300021887995, |
| "grad_norm": 0.26641029119491577, |
| "learning_rate": 0.0015466261755958208, |
| "loss": 3.0057, |
| "mean_token_accuracy": 0.4096148502826691, |
| "num_tokens": 244087527.0, |
| "step": 8400 |
| }, |
| { |
| "entropy": 3.407488120794296, |
| "epoch": 1.0567837153309778, |
| "grad_norm": 0.2628111243247986, |
| "learning_rate": 0.0015408411254315526, |
| "loss": 3.0423, |
| "mean_token_accuracy": 0.4053249025344849, |
| "num_tokens": 245542169.0, |
| "step": 8450 |
| }, |
| { |
| "entropy": 3.4050830852985383, |
| "epoch": 1.0630374284731559, |
| "grad_norm": 0.23083467781543732, |
| "learning_rate": 0.001535030377504211, |
| "loss": 3.0253, |
| "mean_token_accuracy": 0.40700640618801115, |
| "num_tokens": 246988548.0, |
| "step": 8500 |
| }, |
| { |
| "entropy": 3.3786729192733764, |
| "epoch": 1.0692911416153341, |
| "grad_norm": 0.2786962389945984, |
| "learning_rate": 0.0015291942079082284, |
| "loss": 3.0021, |
| "mean_token_accuracy": 0.4086934958398342, |
| "num_tokens": 248438834.0, |
| "step": 8550 |
| }, |
| { |
| "entropy": 3.389970999956131, |
| "epoch": 1.0755448547575122, |
| "grad_norm": 0.24150459468364716, |
| "learning_rate": 0.0015233328939459332, |
| "loss": 3.0186, |
| "mean_token_accuracy": 0.4084386694431305, |
| "num_tokens": 249893987.0, |
| "step": 8600 |
| }, |
| { |
| "entropy": 3.379815950393677, |
| "epoch": 1.0817985678996904, |
| "grad_norm": 0.23742859065532684, |
| "learning_rate": 0.0015174467141143748, |
| "loss": 2.9962, |
| "mean_token_accuracy": 0.4109345510601997, |
| "num_tokens": 251346496.0, |
| "step": 8650 |
| }, |
| { |
| "entropy": 3.381633528470993, |
| "epoch": 1.0880522810418687, |
| "grad_norm": 0.2817932963371277, |
| "learning_rate": 0.001511535948092091, |
| "loss": 3.0132, |
| "mean_token_accuracy": 0.40931278571486474, |
| "num_tokens": 252812600.0, |
| "step": 8700 |
| }, |
| { |
| "entropy": 3.37952179312706, |
| "epoch": 1.0943059941840467, |
| "grad_norm": 0.23492373526096344, |
| "learning_rate": 0.0015056008767258162, |
| "loss": 2.9865, |
| "mean_token_accuracy": 0.4107097062468529, |
| "num_tokens": 254265989.0, |
| "step": 8750 |
| }, |
| { |
| "entropy": 3.3976906645298004, |
| "epoch": 1.100559707326225, |
| "grad_norm": 0.26069802045822144, |
| "learning_rate": 0.0014996417820171426, |
| "loss": 2.9959, |
| "mean_token_accuracy": 0.4109515391290188, |
| "num_tokens": 255715028.0, |
| "step": 8800 |
| }, |
| { |
| "entropy": 3.368416168689728, |
| "epoch": 1.106813420468403, |
| "grad_norm": 0.2870071232318878, |
| "learning_rate": 0.0014936589471091165, |
| "loss": 2.9703, |
| "mean_token_accuracy": 0.41341917037963866, |
| "num_tokens": 257163834.0, |
| "step": 8850 |
| }, |
| { |
| "entropy": 3.364442890882492, |
| "epoch": 1.1130671336105813, |
| "grad_norm": 0.2520281970500946, |
| "learning_rate": 0.0014876526562727867, |
| "loss": 2.9763, |
| "mean_token_accuracy": 0.41378984034061433, |
| "num_tokens": 258616558.0, |
| "step": 8900 |
| }, |
| { |
| "entropy": 3.399234428405762, |
| "epoch": 1.1193208467527596, |
| "grad_norm": 0.4310092628002167, |
| "learning_rate": 0.0014816231948936967, |
| "loss": 3.0143, |
| "mean_token_accuracy": 0.4086450488865376, |
| "num_tokens": 260073476.0, |
| "step": 8950 |
| }, |
| { |
| "entropy": 3.3841825568675996, |
| "epoch": 1.1255745598949376, |
| "grad_norm": 0.2929483652114868, |
| "learning_rate": 0.0014755708494583269, |
| "loss": 3.0013, |
| "mean_token_accuracy": 0.4088966536521912, |
| "num_tokens": 261517515.0, |
| "step": 9000 |
| }, |
| { |
| "entropy": 3.364690970182419, |
| "epoch": 1.1318282730371159, |
| "grad_norm": 0.2556741535663605, |
| "learning_rate": 0.0014694959075404793, |
| "loss": 2.9746, |
| "mean_token_accuracy": 0.4140892958641052, |
| "num_tokens": 262963815.0, |
| "step": 9050 |
| }, |
| { |
| "entropy": 3.335093698501587, |
| "epoch": 1.138081986179294, |
| "grad_norm": 0.26782119274139404, |
| "learning_rate": 0.001463398657787616, |
| "loss": 2.9489, |
| "mean_token_accuracy": 0.4161834093928337, |
| "num_tokens": 264419565.0, |
| "step": 9100 |
| }, |
| { |
| "entropy": 3.340893853902817, |
| "epoch": 1.1443356993214722, |
| "grad_norm": 0.25481972098350525, |
| "learning_rate": 0.001457279389907143, |
| "loss": 2.9554, |
| "mean_token_accuracy": 0.4155861519277096, |
| "num_tokens": 265866694.0, |
| "step": 9150 |
| }, |
| { |
| "entropy": 3.381483224630356, |
| "epoch": 1.1505894124636502, |
| "grad_norm": 0.2730478346347809, |
| "learning_rate": 0.001451138394652645, |
| "loss": 2.9674, |
| "mean_token_accuracy": 0.41388784766197206, |
| "num_tokens": 267323470.0, |
| "step": 9200 |
| }, |
| { |
| "entropy": 3.3568492233753204, |
| "epoch": 1.1568431256058285, |
| "grad_norm": 0.2593781650066376, |
| "learning_rate": 0.001444975963810072, |
| "loss": 2.9531, |
| "mean_token_accuracy": 0.4166987505555153, |
| "num_tokens": 268771908.0, |
| "step": 9250 |
| }, |
| { |
| "entropy": 3.343725650310516, |
| "epoch": 1.1630968387480065, |
| "grad_norm": 0.23936976492404938, |
| "learning_rate": 0.001438792390183872, |
| "loss": 2.9497, |
| "mean_token_accuracy": 0.4166214270889759, |
| "num_tokens": 270222216.0, |
| "step": 9300 |
| }, |
| { |
| "entropy": 3.3452346408367157, |
| "epoch": 1.1693505518901848, |
| "grad_norm": 0.24291479587554932, |
| "learning_rate": 0.0014325879675830824, |
| "loss": 2.9781, |
| "mean_token_accuracy": 0.4135470025241375, |
| "num_tokens": 271676400.0, |
| "step": 9350 |
| }, |
| { |
| "entropy": 3.3736480152606965, |
| "epoch": 1.175604265032363, |
| "grad_norm": 0.2399204820394516, |
| "learning_rate": 0.0014263629908073663, |
| "loss": 2.9887, |
| "mean_token_accuracy": 0.4122758340835571, |
| "num_tokens": 273129248.0, |
| "step": 9400 |
| }, |
| { |
| "entropy": 3.335775601863861, |
| "epoch": 1.181857978174541, |
| "grad_norm": 0.24937410652637482, |
| "learning_rate": 0.001420117755633008, |
| "loss": 2.9449, |
| "mean_token_accuracy": 0.4171235427260399, |
| "num_tokens": 274577598.0, |
| "step": 9450 |
| }, |
| { |
| "entropy": 3.326780825853348, |
| "epoch": 1.1881116913167193, |
| "grad_norm": 0.24946729838848114, |
| "learning_rate": 0.0014138525587988585, |
| "loss": 2.9499, |
| "mean_token_accuracy": 0.41634685471653937, |
| "num_tokens": 276035839.0, |
| "step": 9500 |
| }, |
| { |
| "entropy": 3.347506259679794, |
| "epoch": 1.1943654044588974, |
| "grad_norm": 0.232426717877388, |
| "learning_rate": 0.0014075676979922347, |
| "loss": 2.9388, |
| "mean_token_accuracy": 0.41728449061512946, |
| "num_tokens": 277483534.0, |
| "step": 9550 |
| }, |
| { |
| "entropy": 3.3232869446277618, |
| "epoch": 1.2006191176010756, |
| "grad_norm": 0.2653588354587555, |
| "learning_rate": 0.0014012634718347774, |
| "loss": 2.9378, |
| "mean_token_accuracy": 0.41797628834843636, |
| "num_tokens": 278942090.0, |
| "step": 9600 |
| }, |
| { |
| "entropy": 3.338738178014755, |
| "epoch": 1.206872830743254, |
| "grad_norm": 0.23284447193145752, |
| "learning_rate": 0.00139494017986826, |
| "loss": 2.9277, |
| "mean_token_accuracy": 0.41921328961849214, |
| "num_tokens": 280386565.0, |
| "step": 9650 |
| }, |
| { |
| "entropy": 3.3239081263542176, |
| "epoch": 1.213126543885432, |
| "grad_norm": 0.231287881731987, |
| "learning_rate": 0.0013885981225403574, |
| "loss": 2.9221, |
| "mean_token_accuracy": 0.42032514050602915, |
| "num_tokens": 281837049.0, |
| "step": 9700 |
| }, |
| { |
| "entropy": 3.3193623530864715, |
| "epoch": 1.2193802570276102, |
| "grad_norm": 0.2553178071975708, |
| "learning_rate": 0.0013822376011903717, |
| "loss": 2.9251, |
| "mean_token_accuracy": 0.41874496802687644, |
| "num_tokens": 283291625.0, |
| "step": 9750 |
| }, |
| { |
| "entropy": 3.313581793308258, |
| "epoch": 1.2256339701697883, |
| "grad_norm": 0.2445349544286728, |
| "learning_rate": 0.0013758589180349107, |
| "loss": 2.9036, |
| "mean_token_accuracy": 0.4213790266215801, |
| "num_tokens": 284744533.0, |
| "step": 9800 |
| }, |
| { |
| "entropy": 3.333759317398071, |
| "epoch": 1.2318876833119665, |
| "grad_norm": 0.23976311087608337, |
| "learning_rate": 0.0013694623761535305, |
| "loss": 2.9223, |
| "mean_token_accuracy": 0.41979889243841173, |
| "num_tokens": 286202783.0, |
| "step": 9850 |
| }, |
| { |
| "entropy": 3.3275194442272187, |
| "epoch": 1.2381413964541446, |
| "grad_norm": 0.24221397936344147, |
| "learning_rate": 0.0013630482794743356, |
| "loss": 2.9227, |
| "mean_token_accuracy": 0.42032407999038696, |
| "num_tokens": 287655421.0, |
| "step": 9900 |
| }, |
| { |
| "entropy": 3.297724051475525, |
| "epoch": 1.2443951095963228, |
| "grad_norm": 0.24389943480491638, |
| "learning_rate": 0.001356616932759536, |
| "loss": 2.9053, |
| "mean_token_accuracy": 0.422286706417799, |
| "num_tokens": 289116534.0, |
| "step": 9950 |
| }, |
| { |
| "entropy": 3.316089181900024, |
| "epoch": 1.2506488227385009, |
| "grad_norm": 0.2706010937690735, |
| "learning_rate": 0.0013501686415909678, |
| "loss": 2.91, |
| "mean_token_accuracy": 0.42257274031639097, |
| "num_tokens": 290575760.0, |
| "step": 10000 |
| }, |
| { |
| "entropy": 3.3069709300994874, |
| "epoch": 1.2569025358806791, |
| "grad_norm": 0.2567020058631897, |
| "learning_rate": 0.0013437037123555737, |
| "loss": 2.9068, |
| "mean_token_accuracy": 0.42272754848003385, |
| "num_tokens": 292030604.0, |
| "step": 10050 |
| }, |
| { |
| "entropy": 3.322487668991089, |
| "epoch": 1.2631562490228574, |
| "grad_norm": 0.24985256791114807, |
| "learning_rate": 0.0013372224522308438, |
| "loss": 2.9249, |
| "mean_token_accuracy": 0.41974695593118666, |
| "num_tokens": 293486083.0, |
| "step": 10100 |
| }, |
| { |
| "entropy": 3.3206483924388888, |
| "epoch": 1.2694099621650354, |
| "grad_norm": 0.2233990728855133, |
| "learning_rate": 0.001330725169170222, |
| "loss": 2.9117, |
| "mean_token_accuracy": 0.4212852735817432, |
| "num_tokens": 294937867.0, |
| "step": 10150 |
| }, |
| { |
| "entropy": 3.3343569612503052, |
| "epoch": 1.2756636753072137, |
| "grad_norm": 0.2400444597005844, |
| "learning_rate": 0.0013242121718884728, |
| "loss": 2.9097, |
| "mean_token_accuracy": 0.42152070671319963, |
| "num_tokens": 296390576.0, |
| "step": 10200 |
| }, |
| { |
| "entropy": 3.3441244554519653, |
| "epoch": 1.2819173884493917, |
| "grad_norm": 0.24485696852207184, |
| "learning_rate": 0.0013176837698470139, |
| "loss": 2.8971, |
| "mean_token_accuracy": 0.4235718835890293, |
| "num_tokens": 297842021.0, |
| "step": 10250 |
| }, |
| { |
| "entropy": 3.318438186645508, |
| "epoch": 1.28817110159157, |
| "grad_norm": 0.23577703535556793, |
| "learning_rate": 0.0013111402732392096, |
| "loss": 2.9088, |
| "mean_token_accuracy": 0.4217331087589264, |
| "num_tokens": 299298294.0, |
| "step": 10300 |
| }, |
| { |
| "entropy": 3.3001376008987426, |
| "epoch": 1.2944248147337483, |
| "grad_norm": 0.2448028177022934, |
| "learning_rate": 0.0013045819929756364, |
| "loss": 2.8789, |
| "mean_token_accuracy": 0.4240961664915085, |
| "num_tokens": 300755464.0, |
| "step": 10350 |
| }, |
| { |
| "entropy": 3.3169038486480713, |
| "epoch": 1.3006785278759263, |
| "grad_norm": 0.24094216525554657, |
| "learning_rate": 0.0012980092406693062, |
| "loss": 2.8981, |
| "mean_token_accuracy": 0.4229963217675686, |
| "num_tokens": 302205274.0, |
| "step": 10400 |
| }, |
| { |
| "entropy": 3.306311628818512, |
| "epoch": 1.3069322410181046, |
| "grad_norm": 0.23586605489253998, |
| "learning_rate": 0.0012914223286208625, |
| "loss": 2.8739, |
| "mean_token_accuracy": 0.4253669346868992, |
| "num_tokens": 303659297.0, |
| "step": 10450 |
| }, |
| { |
| "entropy": 3.3153705585002897, |
| "epoch": 1.3131859541602826, |
| "grad_norm": 0.22188012301921844, |
| "learning_rate": 0.0012848215698037415, |
| "loss": 2.8784, |
| "mean_token_accuracy": 0.42567239463329315, |
| "num_tokens": 305117516.0, |
| "step": 10500 |
| }, |
| { |
| "entropy": 3.349429177045822, |
| "epoch": 1.3194396673024609, |
| "grad_norm": 0.24746544659137726, |
| "learning_rate": 0.0012782072778493002, |
| "loss": 2.9087, |
| "mean_token_accuracy": 0.42274825111031533, |
| "num_tokens": 306570303.0, |
| "step": 10550 |
| }, |
| { |
| "entropy": 3.329492164850235, |
| "epoch": 1.3256933804446391, |
| "grad_norm": 0.24711163341999054, |
| "learning_rate": 0.0012715797670319147, |
| "loss": 2.8892, |
| "mean_token_accuracy": 0.42441680446267127, |
| "num_tokens": 308030555.0, |
| "step": 10600 |
| }, |
| { |
| "entropy": 3.3335850477218627, |
| "epoch": 1.3319470935868172, |
| "grad_norm": 0.2298772633075714, |
| "learning_rate": 0.001264939352254049, |
| "loss": 2.8933, |
| "mean_token_accuracy": 0.42399927601218224, |
| "num_tokens": 309482666.0, |
| "step": 10650 |
| }, |
| { |
| "entropy": 3.3008330821990968, |
| "epoch": 1.3382008067289952, |
| "grad_norm": 0.23629966378211975, |
| "learning_rate": 0.0012582863490312908, |
| "loss": 2.8679, |
| "mean_token_accuracy": 0.4268447032570839, |
| "num_tokens": 310933867.0, |
| "step": 10700 |
| }, |
| { |
| "entropy": 3.294624637365341, |
| "epoch": 1.3444545198711735, |
| "grad_norm": 0.23950351774692535, |
| "learning_rate": 0.001251621073477361, |
| "loss": 2.8606, |
| "mean_token_accuracy": 0.4277565456926823, |
| "num_tokens": 312390391.0, |
| "step": 10750 |
| }, |
| { |
| "entropy": 3.290150513648987, |
| "epoch": 1.3507082330133517, |
| "grad_norm": 0.24080321192741394, |
| "learning_rate": 0.0012449438422890936, |
| "loss": 2.8666, |
| "mean_token_accuracy": 0.4271367233991623, |
| "num_tokens": 313838259.0, |
| "step": 10800 |
| }, |
| { |
| "entropy": 3.2781748247146605, |
| "epoch": 1.3569619461555298, |
| "grad_norm": 0.24540862441062927, |
| "learning_rate": 0.0012382549727313875, |
| "loss": 2.8558, |
| "mean_token_accuracy": 0.4279210121929646, |
| "num_tokens": 315286075.0, |
| "step": 10850 |
| }, |
| { |
| "entropy": 3.2989360880851746, |
| "epoch": 1.363215659297708, |
| "grad_norm": 0.2313542664051056, |
| "learning_rate": 0.0012315547826221318, |
| "loss": 2.8597, |
| "mean_token_accuracy": 0.4279498742520809, |
| "num_tokens": 316736678.0, |
| "step": 10900 |
| }, |
| { |
| "entropy": 3.304781684875488, |
| "epoch": 1.369469372439886, |
| "grad_norm": 0.2552511990070343, |
| "learning_rate": 0.001224843590317107, |
| "loss": 2.8853, |
| "mean_token_accuracy": 0.42454988047480585, |
| "num_tokens": 318188717.0, |
| "step": 10950 |
| }, |
| { |
| "entropy": 3.2968351674079894, |
| "epoch": 1.3757230855820644, |
| "grad_norm": 0.23053553700447083, |
| "learning_rate": 0.001218121714694855, |
| "loss": 2.8576, |
| "mean_token_accuracy": 0.42793465360999106, |
| "num_tokens": 319650569.0, |
| "step": 11000 |
| }, |
| { |
| "entropy": 3.2916909861564636, |
| "epoch": 1.3819767987242426, |
| "grad_norm": 0.24563711881637573, |
| "learning_rate": 0.0012113894751415296, |
| "loss": 2.8673, |
| "mean_token_accuracy": 0.42703422278165815, |
| "num_tokens": 321109384.0, |
| "step": 11050 |
| }, |
| { |
| "entropy": 3.2736746430397035, |
| "epoch": 1.3882305118664207, |
| "grad_norm": 0.24409718811511993, |
| "learning_rate": 0.001204647191535722, |
| "loss": 2.8325, |
| "mean_token_accuracy": 0.43039547055959704, |
| "num_tokens": 322562775.0, |
| "step": 11100 |
| }, |
| { |
| "entropy": 3.295790330171585, |
| "epoch": 1.394484225008599, |
| "grad_norm": 0.22487126290798187, |
| "learning_rate": 0.0011978951842332606, |
| "loss": 2.8457, |
| "mean_token_accuracy": 0.4293624579906464, |
| "num_tokens": 324014136.0, |
| "step": 11150 |
| }, |
| { |
| "entropy": 3.2935370481014252, |
| "epoch": 1.400737938150777, |
| "grad_norm": 0.25449955463409424, |
| "learning_rate": 0.0011911337740519892, |
| "loss": 2.8508, |
| "mean_token_accuracy": 0.4287599550187588, |
| "num_tokens": 325469987.0, |
| "step": 11200 |
| }, |
| { |
| "entropy": 3.2637720847129823, |
| "epoch": 1.4069916512929552, |
| "grad_norm": 0.23394949734210968, |
| "learning_rate": 0.001184363282256525, |
| "loss": 2.8295, |
| "mean_token_accuracy": 0.43097158893942833, |
| "num_tokens": 326922931.0, |
| "step": 11250 |
| }, |
| { |
| "entropy": 3.2709325647354124, |
| "epoch": 1.4132453644351335, |
| "grad_norm": 0.229343444108963, |
| "learning_rate": 0.0011775840305429921, |
| "loss": 2.8306, |
| "mean_token_accuracy": 0.4322802956402302, |
| "num_tokens": 328381052.0, |
| "step": 11300 |
| }, |
| { |
| "entropy": 3.2761396980285644, |
| "epoch": 1.4194990775773115, |
| "grad_norm": 0.23448783159255981, |
| "learning_rate": 0.0011707963410237379, |
| "loss": 2.8363, |
| "mean_token_accuracy": 0.430686649531126, |
| "num_tokens": 329830903.0, |
| "step": 11350 |
| }, |
| { |
| "entropy": 3.2788108825683593, |
| "epoch": 1.4257527907194896, |
| "grad_norm": 0.2271973043680191, |
| "learning_rate": 0.001164000536212027, |
| "loss": 2.8335, |
| "mean_token_accuracy": 0.43118971526622774, |
| "num_tokens": 331280393.0, |
| "step": 11400 |
| }, |
| { |
| "entropy": 3.2778335607051847, |
| "epoch": 1.4320065038616678, |
| "grad_norm": 0.2223415970802307, |
| "learning_rate": 0.001157196939006718, |
| "loss": 2.8424, |
| "mean_token_accuracy": 0.43043203085660936, |
| "num_tokens": 332733626.0, |
| "step": 11450 |
| }, |
| { |
| "entropy": 3.275426481962204, |
| "epoch": 1.438260217003846, |
| "grad_norm": 0.2389313280582428, |
| "learning_rate": 0.0011503858726769202, |
| "loss": 2.836, |
| "mean_token_accuracy": 0.43069657027721403, |
| "num_tokens": 334190416.0, |
| "step": 11500 |
| }, |
| { |
| "entropy": 3.2625485575199127, |
| "epoch": 1.4445139301460241, |
| "grad_norm": 0.22828622162342072, |
| "learning_rate": 0.0011435676608466346, |
| "loss": 2.8426, |
| "mean_token_accuracy": 0.4305486410856247, |
| "num_tokens": 335637372.0, |
| "step": 11550 |
| }, |
| { |
| "entropy": 3.2681053030490874, |
| "epoch": 1.4507676432882024, |
| "grad_norm": 0.25355732440948486, |
| "learning_rate": 0.0011367426274793762, |
| "loss": 2.8428, |
| "mean_token_accuracy": 0.4308210875093937, |
| "num_tokens": 337083595.0, |
| "step": 11600 |
| }, |
| { |
| "entropy": 3.2613851368427276, |
| "epoch": 1.4570213564303804, |
| "grad_norm": 0.2454511970281601, |
| "learning_rate": 0.001129911096862782, |
| "loss": 2.8138, |
| "mean_token_accuracy": 0.4339980843663216, |
| "num_tokens": 338542359.0, |
| "step": 11650 |
| }, |
| { |
| "entropy": 3.2610177218914034, |
| "epoch": 1.4632750695725587, |
| "grad_norm": 0.21777866780757904, |
| "learning_rate": 0.0011230733935932023, |
| "loss": 2.817, |
| "mean_token_accuracy": 0.43292332217097285, |
| "num_tokens": 339988394.0, |
| "step": 11700 |
| }, |
| { |
| "entropy": 3.25565652012825, |
| "epoch": 1.469528782714737, |
| "grad_norm": 0.2365877777338028, |
| "learning_rate": 0.0011162298425602764, |
| "loss": 2.8198, |
| "mean_token_accuracy": 0.43387064009904863, |
| "num_tokens": 341446604.0, |
| "step": 11750 |
| }, |
| { |
| "entropy": 3.249692702293396, |
| "epoch": 1.475782495856915, |
| "grad_norm": 0.22539696097373962, |
| "learning_rate": 0.001109380768931498, |
| "loss": 2.8068, |
| "mean_token_accuracy": 0.4340075485408306, |
| "num_tokens": 342900120.0, |
| "step": 11800 |
| }, |
| { |
| "entropy": 3.2544299829006196, |
| "epoch": 1.4820362089990933, |
| "grad_norm": 0.23777642846107483, |
| "learning_rate": 0.0011025264981367638, |
| "loss": 2.8062, |
| "mean_token_accuracy": 0.43426609471440314, |
| "num_tokens": 344353638.0, |
| "step": 11850 |
| }, |
| { |
| "entropy": 3.2589793014526367, |
| "epoch": 1.4882899221412713, |
| "grad_norm": 0.23899991810321808, |
| "learning_rate": 0.00109566735585291, |
| "loss": 2.8147, |
| "mean_token_accuracy": 0.4332495957612991, |
| "num_tokens": 345800869.0, |
| "step": 11900 |
| }, |
| { |
| "entropy": 3.2570550775527956, |
| "epoch": 1.4945436352834496, |
| "grad_norm": 0.22672854363918304, |
| "learning_rate": 0.0010888036679882395, |
| "loss": 2.8023, |
| "mean_token_accuracy": 0.4355665297806263, |
| "num_tokens": 347250646.0, |
| "step": 11950 |
| }, |
| { |
| "entropy": 3.254550014734268, |
| "epoch": 1.5007973484256278, |
| "grad_norm": 0.2114313691854477, |
| "learning_rate": 0.001081935760667036, |
| "loss": 2.8136, |
| "mean_token_accuracy": 0.43408931702375414, |
| "num_tokens": 348704005.0, |
| "step": 12000 |
| }, |
| { |
| "entropy": 3.243316088914871, |
| "epoch": 1.5070510615678059, |
| "grad_norm": 0.2516964077949524, |
| "learning_rate": 0.0010750639602140686, |
| "loss": 2.8009, |
| "mean_token_accuracy": 0.43518534049391744, |
| "num_tokens": 350158394.0, |
| "step": 12050 |
| }, |
| { |
| "entropy": 3.2478549814224245, |
| "epoch": 1.513304774709984, |
| "grad_norm": 0.23279394209384918, |
| "learning_rate": 0.0010681885931390852, |
| "loss": 2.7857, |
| "mean_token_accuracy": 0.4367074476182461, |
| "num_tokens": 351604127.0, |
| "step": 12100 |
| }, |
| { |
| "entropy": 3.2347246026992797, |
| "epoch": 1.5195584878521622, |
| "grad_norm": 0.21781018376350403, |
| "learning_rate": 0.0010613099861213012, |
| "loss": 2.7956, |
| "mean_token_accuracy": 0.4359207484126091, |
| "num_tokens": 353057864.0, |
| "step": 12150 |
| }, |
| { |
| "entropy": 3.2461864519119263, |
| "epoch": 1.5258122009943405, |
| "grad_norm": 0.21265676617622375, |
| "learning_rate": 0.0010544284659938746, |
| "loss": 2.7892, |
| "mean_token_accuracy": 0.43556260600686075, |
| "num_tokens": 354506147.0, |
| "step": 12200 |
| }, |
| { |
| "entropy": 3.2419194054603575, |
| "epoch": 1.5320659141365187, |
| "grad_norm": 0.22998523712158203, |
| "learning_rate": 0.0010475443597283795, |
| "loss": 2.7783, |
| "mean_token_accuracy": 0.43743231013417244, |
| "num_tokens": 355963386.0, |
| "step": 12250 |
| }, |
| { |
| "entropy": 3.246154465675354, |
| "epoch": 1.5383196272786968, |
| "grad_norm": 0.22558872401714325, |
| "learning_rate": 0.0010406579944192685, |
| "loss": 2.7831, |
| "mean_token_accuracy": 0.43715057760477066, |
| "num_tokens": 357409816.0, |
| "step": 12300 |
| }, |
| { |
| "entropy": 3.256463017463684, |
| "epoch": 1.5445733404208748, |
| "grad_norm": 0.20943056046962738, |
| "learning_rate": 0.0010337696972683307, |
| "loss": 2.7837, |
| "mean_token_accuracy": 0.4375229972600937, |
| "num_tokens": 358857684.0, |
| "step": 12350 |
| }, |
| { |
| "entropy": 3.2448647558689117, |
| "epoch": 1.550827053563053, |
| "grad_norm": 0.23157542943954468, |
| "learning_rate": 0.0010268797955691462, |
| "loss": 2.7912, |
| "mean_token_accuracy": 0.43746368065476415, |
| "num_tokens": 360317443.0, |
| "step": 12400 |
| }, |
| { |
| "entropy": 3.227845176458359, |
| "epoch": 1.5570807667052313, |
| "grad_norm": 0.21983113884925842, |
| "learning_rate": 0.0010199886166915347, |
| "loss": 2.7695, |
| "mean_token_accuracy": 0.43851295456290246, |
| "num_tokens": 361763696.0, |
| "step": 12450 |
| }, |
| { |
| "entropy": 3.207278673648834, |
| "epoch": 1.5633344798474094, |
| "grad_norm": 0.22169895470142365, |
| "learning_rate": 0.0010130964880659997, |
| "loss": 2.758, |
| "mean_token_accuracy": 0.4404232783615589, |
| "num_tokens": 363215595.0, |
| "step": 12500 |
| }, |
| { |
| "entropy": 3.2540294277668, |
| "epoch": 1.5695881929895874, |
| "grad_norm": 0.23538173735141754, |
| "learning_rate": 0.001006203737168171, |
| "loss": 2.8065, |
| "mean_token_accuracy": 0.43551131546497346, |
| "num_tokens": 364675498.0, |
| "step": 12550 |
| }, |
| { |
| "entropy": 3.231663987636566, |
| "epoch": 1.5758419061317657, |
| "grad_norm": 0.2294698804616928, |
| "learning_rate": 0.0009993106915032468, |
| "loss": 2.7788, |
| "mean_token_accuracy": 0.4382545882463455, |
| "num_tokens": 366125218.0, |
| "step": 12600 |
| }, |
| { |
| "entropy": 3.2363407254219054, |
| "epoch": 1.582095619273944, |
| "grad_norm": 0.2398029863834381, |
| "learning_rate": 0.0009924176785904293, |
| "loss": 2.7851, |
| "mean_token_accuracy": 0.4379922252893448, |
| "num_tokens": 367579050.0, |
| "step": 12650 |
| }, |
| { |
| "entropy": 3.2210785961151123, |
| "epoch": 1.5883493324161222, |
| "grad_norm": 0.23287877440452576, |
| "learning_rate": 0.0009855250259473657, |
| "loss": 2.7663, |
| "mean_token_accuracy": 0.4396293942630291, |
| "num_tokens": 369033121.0, |
| "step": 12700 |
| }, |
| { |
| "entropy": 3.2457301235198974, |
| "epoch": 1.5946030455583002, |
| "grad_norm": 0.2148071825504303, |
| "learning_rate": 0.0009786330610745849, |
| "loss": 2.7688, |
| "mean_token_accuracy": 0.43925670653581617, |
| "num_tokens": 370481491.0, |
| "step": 12750 |
| }, |
| { |
| "entropy": 3.2246074092388155, |
| "epoch": 1.6008567587004783, |
| "grad_norm": 0.21147137880325317, |
| "learning_rate": 0.0009717421114399361, |
| "loss": 2.7438, |
| "mean_token_accuracy": 0.44269678577780724, |
| "num_tokens": 371931424.0, |
| "step": 12800 |
| }, |
| { |
| "entropy": 3.2194683921337126, |
| "epoch": 1.6071104718426565, |
| "grad_norm": 0.23948106169700623, |
| "learning_rate": 0.0009648525044630312, |
| "loss": 2.7567, |
| "mean_token_accuracy": 0.4407572849094868, |
| "num_tokens": 373377913.0, |
| "step": 12850 |
| }, |
| { |
| "entropy": 3.241425403356552, |
| "epoch": 1.6133641849848348, |
| "grad_norm": 0.21832682192325592, |
| "learning_rate": 0.0009579645674996858, |
| "loss": 2.781, |
| "mean_token_accuracy": 0.43758947104215623, |
| "num_tokens": 374840821.0, |
| "step": 12900 |
| }, |
| { |
| "entropy": 3.232071034908295, |
| "epoch": 1.619617898127013, |
| "grad_norm": 0.2332869917154312, |
| "learning_rate": 0.0009510786278263655, |
| "loss": 2.7789, |
| "mean_token_accuracy": 0.43771066397428515, |
| "num_tokens": 376297301.0, |
| "step": 12950 |
| }, |
| { |
| "entropy": 3.1825023066997526, |
| "epoch": 1.625871611269191, |
| "grad_norm": 0.24876029789447784, |
| "learning_rate": 0.0009441950126246364, |
| "loss": 2.7299, |
| "mean_token_accuracy": 0.4447443017363548, |
| "num_tokens": 377735071.0, |
| "step": 13000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 23988, |
| "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": 3.7708908779142513e+18, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
