| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9995402298850574, |
| "eval_steps": 500, |
| "global_step": 1087, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.004597701149425287, |
| "grad_norm": 14.37303352355957, |
| "learning_rate": 2.162496240601504e-06, |
| "loss": 0.3746, |
| "mean_token_accuracy": 0.8937759280204773, |
| "num_tokens": 923140.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.009195402298850575, |
| "grad_norm": 3.110740900039673, |
| "learning_rate": 4.865616541353383e-06, |
| "loss": 0.2359, |
| "mean_token_accuracy": 0.9415880262851715, |
| "num_tokens": 1831819.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.013793103448275862, |
| "grad_norm": 1.2301355600357056, |
| "learning_rate": 7.568736842105265e-06, |
| "loss": 0.1496, |
| "mean_token_accuracy": 0.9549544870853424, |
| "num_tokens": 2746466.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.01839080459770115, |
| "grad_norm": 0.9068412780761719, |
| "learning_rate": 1.0271857142857143e-05, |
| "loss": 0.1604, |
| "mean_token_accuracy": 0.956589013338089, |
| "num_tokens": 3656508.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.022988505747126436, |
| "grad_norm": 0.9918791651725769, |
| "learning_rate": 1.2974977443609024e-05, |
| "loss": 0.1553, |
| "mean_token_accuracy": 0.9534055590629578, |
| "num_tokens": 4553214.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.027586206896551724, |
| "grad_norm": 0.9369048476219177, |
| "learning_rate": 1.5678097744360906e-05, |
| "loss": 0.1252, |
| "mean_token_accuracy": 0.9631341159343719, |
| "num_tokens": 5456824.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03218390804597701, |
| "grad_norm": 0.9038181304931641, |
| "learning_rate": 1.8381218045112784e-05, |
| "loss": 0.1415, |
| "mean_token_accuracy": 0.9593121707439423, |
| "num_tokens": 6367316.0, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0367816091954023, |
| "grad_norm": 1.1309387683868408, |
| "learning_rate": 1.8921335875389056e-05, |
| "loss": 0.1328, |
| "mean_token_accuracy": 0.9603389024734497, |
| "num_tokens": 7284430.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.041379310344827586, |
| "grad_norm": 1.108691692352295, |
| "learning_rate": 1.891927944032128e-05, |
| "loss": 0.1254, |
| "mean_token_accuracy": 0.9646198928356171, |
| "num_tokens": 8187692.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.04597701149425287, |
| "grad_norm": 0.8930448293685913, |
| "learning_rate": 1.891564161881453e-05, |
| "loss": 0.1304, |
| "mean_token_accuracy": 0.9630963504314423, |
| "num_tokens": 9103041.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.05057471264367816, |
| "grad_norm": 1.41404390335083, |
| "learning_rate": 1.891042322190752e-05, |
| "loss": 0.1518, |
| "mean_token_accuracy": 0.9589076399803161, |
| "num_tokens": 10008545.0, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.05517241379310345, |
| "grad_norm": 0.9232056140899658, |
| "learning_rate": 1.8903625413022364e-05, |
| "loss": 0.1312, |
| "mean_token_accuracy": 0.9622297883033752, |
| "num_tokens": 10924384.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.059770114942528735, |
| "grad_norm": 0.7608996629714966, |
| "learning_rate": 1.889524970770518e-05, |
| "loss": 0.0911, |
| "mean_token_accuracy": 0.972572922706604, |
| "num_tokens": 11822511.0, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.06436781609195402, |
| "grad_norm": 0.8342674970626831, |
| "learning_rate": 1.888529797328821e-05, |
| "loss": 0.1165, |
| "mean_token_accuracy": 0.9667028665542603, |
| "num_tokens": 12738893.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.06896551724137931, |
| "grad_norm": 0.6052498817443848, |
| "learning_rate": 1.8873772428473496e-05, |
| "loss": 0.1139, |
| "mean_token_accuracy": 0.9653128921985626, |
| "num_tokens": 13648570.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.0735632183908046, |
| "grad_norm": 0.892188310623169, |
| "learning_rate": 1.8860675642838222e-05, |
| "loss": 0.1254, |
| "mean_token_accuracy": 0.963401597738266, |
| "num_tokens": 14549037.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.07816091954022988, |
| "grad_norm": 1.1106016635894775, |
| "learning_rate": 1.8846010536261868e-05, |
| "loss": 0.1292, |
| "mean_token_accuracy": 0.9623928070068359, |
| "num_tokens": 15452604.0, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.08275862068965517, |
| "grad_norm": 0.8913820385932922, |
| "learning_rate": 1.8829780378275203e-05, |
| "loss": 0.1176, |
| "mean_token_accuracy": 0.9648943901062011, |
| "num_tokens": 16365541.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.08735632183908046, |
| "grad_norm": 0.6293613314628601, |
| "learning_rate": 1.881198878733137e-05, |
| "loss": 0.1082, |
| "mean_token_accuracy": 0.9671000123023987, |
| "num_tokens": 17279474.0, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.09195402298850575, |
| "grad_norm": 0.5726266503334045, |
| "learning_rate": 1.8792639729999157e-05, |
| "loss": 0.1158, |
| "mean_token_accuracy": 0.9670614004135132, |
| "num_tokens": 18189222.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09655172413793103, |
| "grad_norm": 0.6022919416427612, |
| "learning_rate": 1.8771737520078673e-05, |
| "loss": 0.1034, |
| "mean_token_accuracy": 0.9691289484500885, |
| "num_tokens": 19099883.0, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.10114942528735632, |
| "grad_norm": 0.8546155095100403, |
| "learning_rate": 1.87492868176396e-05, |
| "loss": 0.1141, |
| "mean_token_accuracy": 0.9670604646205903, |
| "num_tokens": 20010042.0, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.10574712643678161, |
| "grad_norm": 0.5845869779586792, |
| "learning_rate": 1.8725292627982245e-05, |
| "loss": 0.0873, |
| "mean_token_accuracy": 0.9722756147384644, |
| "num_tokens": 20932591.0, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.1103448275862069, |
| "grad_norm": 0.6718858480453491, |
| "learning_rate": 1.869976030052163e-05, |
| "loss": 0.0971, |
| "mean_token_accuracy": 0.9716311156749725, |
| "num_tokens": 21852758.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.11494252873563218, |
| "grad_norm": 0.5857953429222107, |
| "learning_rate": 1.8672695527594852e-05, |
| "loss": 0.0922, |
| "mean_token_accuracy": 0.9720439195632935, |
| "num_tokens": 22772716.0, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.11954022988505747, |
| "grad_norm": 0.44285351037979126, |
| "learning_rate": 1.8644104343192015e-05, |
| "loss": 0.0984, |
| "mean_token_accuracy": 0.9695663213729858, |
| "num_tokens": 23682795.0, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.12413793103448276, |
| "grad_norm": 0.6226865649223328, |
| "learning_rate": 1.8613993121610966e-05, |
| "loss": 0.1004, |
| "mean_token_accuracy": 0.970111358165741, |
| "num_tokens": 24597235.0, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.12873563218390804, |
| "grad_norm": 0.7010825872421265, |
| "learning_rate": 1.8582368576036156e-05, |
| "loss": 0.112, |
| "mean_token_accuracy": 0.9659516274929046, |
| "num_tokens": 25515592.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.13333333333333333, |
| "grad_norm": 0.9375905990600586, |
| "learning_rate": 1.854923775704197e-05, |
| "loss": 0.1221, |
| "mean_token_accuracy": 0.9649936199188233, |
| "num_tokens": 26431891.0, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.13793103448275862, |
| "grad_norm": 0.6008977890014648, |
| "learning_rate": 1.851460805102085e-05, |
| "loss": 0.1063, |
| "mean_token_accuracy": 0.9681371688842774, |
| "num_tokens": 27341119.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.1425287356321839, |
| "grad_norm": 0.7539997100830078, |
| "learning_rate": 1.8478487178536477e-05, |
| "loss": 0.0929, |
| "mean_token_accuracy": 0.970865112543106, |
| "num_tokens": 28245932.0, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.1471264367816092, |
| "grad_norm": 0.5922966003417969, |
| "learning_rate": 1.8440883192602558e-05, |
| "loss": 0.0863, |
| "mean_token_accuracy": 0.9727598786354065, |
| "num_tokens": 29163177.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.15172413793103448, |
| "grad_norm": 0.7404959797859192, |
| "learning_rate": 1.840180447688738e-05, |
| "loss": 0.1016, |
| "mean_token_accuracy": 0.9701551198959351, |
| "num_tokens": 30083769.0, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.15632183908045977, |
| "grad_norm": 0.5219832062721252, |
| "learning_rate": 1.8361259743844752e-05, |
| "loss": 0.1139, |
| "mean_token_accuracy": 0.968910676240921, |
| "num_tokens": 30986604.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.16091954022988506, |
| "grad_norm": 0.6837122440338135, |
| "learning_rate": 1.8319258032771563e-05, |
| "loss": 0.0972, |
| "mean_token_accuracy": 0.9707643270492554, |
| "num_tokens": 31912804.0, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.16551724137931034, |
| "grad_norm": 0.5476808547973633, |
| "learning_rate": 1.8275808707792515e-05, |
| "loss": 0.0872, |
| "mean_token_accuracy": 0.9744282007217407, |
| "num_tokens": 32815036.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.17011494252873563, |
| "grad_norm": 0.7919837832450867, |
| "learning_rate": 1.8230921455772436e-05, |
| "loss": 0.1013, |
| "mean_token_accuracy": 0.9696295440196991, |
| "num_tokens": 33749312.0, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.17471264367816092, |
| "grad_norm": 0.46262362599372864, |
| "learning_rate": 1.818460628415661e-05, |
| "loss": 0.0899, |
| "mean_token_accuracy": 0.9723390281200409, |
| "num_tokens": 34656801.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.1793103448275862, |
| "grad_norm": 0.6869615316390991, |
| "learning_rate": 1.8136873518739665e-05, |
| "loss": 0.0964, |
| "mean_token_accuracy": 0.9718866407871246, |
| "num_tokens": 35567902.0, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.1839080459770115, |
| "grad_norm": 0.6292715668678284, |
| "learning_rate": 1.8087733801363485e-05, |
| "loss": 0.1117, |
| "mean_token_accuracy": 0.9660165786743165, |
| "num_tokens": 36487856.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.18850574712643678, |
| "grad_norm": 0.7318857908248901, |
| "learning_rate": 1.8037198087544638e-05, |
| "loss": 0.0912, |
| "mean_token_accuracy": 0.973089873790741, |
| "num_tokens": 37406615.0, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.19310344827586207, |
| "grad_norm": 0.45698633790016174, |
| "learning_rate": 1.7985277644031878e-05, |
| "loss": 0.0939, |
| "mean_token_accuracy": 0.971883374452591, |
| "num_tokens": 38325048.0, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.19770114942528735, |
| "grad_norm": 0.7155999541282654, |
| "learning_rate": 1.7931984046294294e-05, |
| "loss": 0.0855, |
| "mean_token_accuracy": 0.9737869322299957, |
| "num_tokens": 39246924.0, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.20229885057471264, |
| "grad_norm": 0.6742710471153259, |
| "learning_rate": 1.7877329175940566e-05, |
| "loss": 0.0818, |
| "mean_token_accuracy": 0.9737736523151398, |
| "num_tokens": 40158766.0, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.20689655172413793, |
| "grad_norm": 0.7237321138381958, |
| "learning_rate": 1.782132521807003e-05, |
| "loss": 0.0936, |
| "mean_token_accuracy": 0.9719770848751068, |
| "num_tokens": 41071667.0, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.21149425287356322, |
| "grad_norm": 0.5355440974235535, |
| "learning_rate": 1.776398465855606e-05, |
| "loss": 0.0893, |
| "mean_token_accuracy": 0.9734656155109406, |
| "num_tokens": 41993911.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.2160919540229885, |
| "grad_norm": 0.521927535533905, |
| "learning_rate": 1.7705320281262348e-05, |
| "loss": 0.0917, |
| "mean_token_accuracy": 0.9709402084350586, |
| "num_tokens": 42899750.0, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.2206896551724138, |
| "grad_norm": 0.5417711734771729, |
| "learning_rate": 1.7645345165192846e-05, |
| "loss": 0.0895, |
| "mean_token_accuracy": 0.9719230890274048, |
| "num_tokens": 43821133.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.22528735632183908, |
| "grad_norm": 0.5175253748893738, |
| "learning_rate": 1.7584072681575815e-05, |
| "loss": 0.0998, |
| "mean_token_accuracy": 0.9724862992763519, |
| "num_tokens": 44731510.0, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.22988505747126436, |
| "grad_norm": 0.6404962539672852, |
| "learning_rate": 1.752151649088276e-05, |
| "loss": 0.0964, |
| "mean_token_accuracy": 0.9705259203910828, |
| "num_tokens": 45639449.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.23448275862068965, |
| "grad_norm": 0.6114163994789124, |
| "learning_rate": 1.7457690539782903e-05, |
| "loss": 0.1068, |
| "mean_token_accuracy": 0.9677742660045624, |
| "num_tokens": 46536864.0, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.23908045977011494, |
| "grad_norm": 0.4995535910129547, |
| "learning_rate": 1.7392609058033793e-05, |
| "loss": 0.085, |
| "mean_token_accuracy": 0.9738347470760346, |
| "num_tokens": 47479998.0, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.24367816091954023, |
| "grad_norm": 0.7006916999816895, |
| "learning_rate": 1.732628655530886e-05, |
| "loss": 0.0872, |
| "mean_token_accuracy": 0.9746140897274017, |
| "num_tokens": 48406673.0, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.2482758620689655, |
| "grad_norm": 0.6545345783233643, |
| "learning_rate": 1.7258737817962525e-05, |
| "loss": 0.0949, |
| "mean_token_accuracy": 0.972430282831192, |
| "num_tokens": 49307483.0, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.25287356321839083, |
| "grad_norm": 0.7461588382720947, |
| "learning_rate": 1.718997790573364e-05, |
| "loss": 0.0886, |
| "mean_token_accuracy": 0.974012941122055, |
| "num_tokens": 50253296.0, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.2574712643678161, |
| "grad_norm": 0.48753979802131653, |
| "learning_rate": 1.712002214838798e-05, |
| "loss": 0.0879, |
| "mean_token_accuracy": 0.9723192870616912, |
| "num_tokens": 51160452.0, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.2620689655172414, |
| "grad_norm": 0.6448308229446411, |
| "learning_rate": 1.7048886142300522e-05, |
| "loss": 0.0964, |
| "mean_token_accuracy": 0.9714203715324402, |
| "num_tokens": 52067532.0, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "grad_norm": 0.6551485061645508, |
| "learning_rate": 1.6976585746978297e-05, |
| "loss": 0.0891, |
| "mean_token_accuracy": 0.9712422013282775, |
| "num_tokens": 52973059.0, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.271264367816092, |
| "grad_norm": 0.3835676610469818, |
| "learning_rate": 1.6903137081524565e-05, |
| "loss": 0.0744, |
| "mean_token_accuracy": 0.9769306421279907, |
| "num_tokens": 53883243.0, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.27586206896551724, |
| "grad_norm": 0.5835188627243042, |
| "learning_rate": 1.6828556521045128e-05, |
| "loss": 0.0905, |
| "mean_token_accuracy": 0.9733997404575347, |
| "num_tokens": 54805677.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.28045977011494255, |
| "grad_norm": 0.6620681285858154, |
| "learning_rate": 1.675286069299756e-05, |
| "loss": 0.0974, |
| "mean_token_accuracy": 0.9726776361465455, |
| "num_tokens": 55730462.0, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.2850574712643678, |
| "grad_norm": 0.5511212348937988, |
| "learning_rate": 1.6676066473484182e-05, |
| "loss": 0.0869, |
| "mean_token_accuracy": 0.9741013526916504, |
| "num_tokens": 56643506.0, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.2896551724137931, |
| "grad_norm": 0.6033239960670471, |
| "learning_rate": 1.6598190983489578e-05, |
| "loss": 0.0935, |
| "mean_token_accuracy": 0.973732852935791, |
| "num_tokens": 57564737.0, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.2942528735632184, |
| "grad_norm": 0.5803326368331909, |
| "learning_rate": 1.6519251585063562e-05, |
| "loss": 0.0713, |
| "mean_token_accuracy": 0.9776466608047485, |
| "num_tokens": 58478958.0, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.2988505747126437, |
| "grad_norm": 0.6657004356384277, |
| "learning_rate": 1.6439265877450356e-05, |
| "loss": 0.0921, |
| "mean_token_accuracy": 0.9736099898815155, |
| "num_tokens": 59384469.0, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.30344827586206896, |
| "grad_norm": 0.5586744546890259, |
| "learning_rate": 1.635825169316491e-05, |
| "loss": 0.0858, |
| "mean_token_accuracy": 0.9723108470439911, |
| "num_tokens": 60284850.0, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.3080459770114943, |
| "grad_norm": 0.746761679649353, |
| "learning_rate": 1.6276227094017214e-05, |
| "loss": 0.0805, |
| "mean_token_accuracy": 0.9747175514698029, |
| "num_tokens": 61198600.0, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.31264367816091954, |
| "grad_norm": 0.705198347568512, |
| "learning_rate": 1.6193210367085475e-05, |
| "loss": 0.092, |
| "mean_token_accuracy": 0.9748440325260163, |
| "num_tokens": 62119010.0, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.31724137931034485, |
| "grad_norm": 0.6483098864555359, |
| "learning_rate": 1.6109220020639086e-05, |
| "loss": 0.0916, |
| "mean_token_accuracy": 0.9728673815727233, |
| "num_tokens": 63022352.0, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.3218390804597701, |
| "grad_norm": 0.5805724859237671, |
| "learning_rate": 1.602427478001228e-05, |
| "loss": 0.082, |
| "mean_token_accuracy": 0.9758881747722625, |
| "num_tokens": 63933987.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.3264367816091954, |
| "grad_norm": 0.5994712114334106, |
| "learning_rate": 1.5938393583429376e-05, |
| "loss": 0.0792, |
| "mean_token_accuracy": 0.9756688117980957, |
| "num_tokens": 64854447.0, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.3310344827586207, |
| "grad_norm": 0.5542306303977966, |
| "learning_rate": 1.5851595577782592e-05, |
| "loss": 0.101, |
| "mean_token_accuracy": 0.9707028329372406, |
| "num_tokens": 65762363.0, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.335632183908046, |
| "grad_norm": 0.6762030720710754, |
| "learning_rate": 1.57639001143633e-05, |
| "loss": 0.0832, |
| "mean_token_accuracy": 0.9747596263885498, |
| "num_tokens": 66687774.0, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.34022988505747126, |
| "grad_norm": 0.6628353595733643, |
| "learning_rate": 1.5675326744547717e-05, |
| "loss": 0.0961, |
| "mean_token_accuracy": 0.9714605689048768, |
| "num_tokens": 67596310.0, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.3448275862068966, |
| "grad_norm": 0.768136739730835, |
| "learning_rate": 1.558589521543804e-05, |
| "loss": 0.0789, |
| "mean_token_accuracy": 0.9765125095844269, |
| "num_tokens": 68518895.0, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.34942528735632183, |
| "grad_norm": 0.6407287120819092, |
| "learning_rate": 1.549562546545986e-05, |
| "loss": 0.0862, |
| "mean_token_accuracy": 0.9728266358375549, |
| "num_tokens": 69441408.0, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.35402298850574715, |
| "grad_norm": 0.5465536713600159, |
| "learning_rate": 1.5404537619916986e-05, |
| "loss": 0.0923, |
| "mean_token_accuracy": 0.9727548897266388, |
| "num_tokens": 70367195.0, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.3586206896551724, |
| "grad_norm": 0.7017700672149658, |
| "learning_rate": 1.5312651986504582e-05, |
| "loss": 0.0901, |
| "mean_token_accuracy": 0.9724270462989807, |
| "num_tokens": 71278971.0, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.3632183908045977, |
| "grad_norm": 0.6565740704536438, |
| "learning_rate": 1.5219989050781634e-05, |
| "loss": 0.0875, |
| "mean_token_accuracy": 0.9727586090564728, |
| "num_tokens": 72206293.0, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.367816091954023, |
| "grad_norm": 0.5583018660545349, |
| "learning_rate": 1.5126569471603783e-05, |
| "loss": 0.0976, |
| "mean_token_accuracy": 0.971861732006073, |
| "num_tokens": 73123125.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.3724137931034483, |
| "grad_norm": 0.7001659274101257, |
| "learning_rate": 1.5032414076517499e-05, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.9765386581420898, |
| "num_tokens": 74049226.0, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.37701149425287356, |
| "grad_norm": 0.7511529922485352, |
| "learning_rate": 1.493754385711667e-05, |
| "loss": 0.1089, |
| "mean_token_accuracy": 0.969479089975357, |
| "num_tokens": 74958557.0, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.3816091954022989, |
| "grad_norm": 0.5006878972053528, |
| "learning_rate": 1.4841979964362583e-05, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.9814721643924713, |
| "num_tokens": 75873003.0, |
| "step": 415 |
| }, |
| { |
| "epoch": 0.38620689655172413, |
| "grad_norm": 0.7190031409263611, |
| "learning_rate": 1.4745743703868424e-05, |
| "loss": 0.084, |
| "mean_token_accuracy": 0.9753434121608734, |
| "num_tokens": 76774013.0, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.39080459770114945, |
| "grad_norm": 0.5938687324523926, |
| "learning_rate": 1.4648856531149251e-05, |
| "loss": 0.089, |
| "mean_token_accuracy": 0.9732214033603668, |
| "num_tokens": 77687920.0, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.3954022988505747, |
| "grad_norm": 0.5017083287239075, |
| "learning_rate": 1.4551340046838569e-05, |
| "loss": 0.0767, |
| "mean_token_accuracy": 0.9771358430385589, |
| "num_tokens": 78588003.0, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.40584269165992737, |
| "learning_rate": 1.445321599187256e-05, |
| "loss": 0.076, |
| "mean_token_accuracy": 0.9759079575538635, |
| "num_tokens": 79503868.0, |
| "step": 435 |
| }, |
| { |
| "epoch": 0.4045977011494253, |
| "grad_norm": 0.7499762177467346, |
| "learning_rate": 1.435450624264301e-05, |
| "loss": 0.0831, |
| "mean_token_accuracy": 0.9760450303554535, |
| "num_tokens": 80411806.0, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.4091954022988506, |
| "grad_norm": 0.46934181451797485, |
| "learning_rate": 1.4255232806120061e-05, |
| "loss": 0.0854, |
| "mean_token_accuracy": 0.9739238858222962, |
| "num_tokens": 81316508.0, |
| "step": 445 |
| }, |
| { |
| "epoch": 0.41379310344827586, |
| "grad_norm": 0.5793800354003906, |
| "learning_rate": 1.4155417814945831e-05, |
| "loss": 0.088, |
| "mean_token_accuracy": 0.9733597040176392, |
| "num_tokens": 82230401.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.41839080459770117, |
| "grad_norm": 0.3974604904651642, |
| "learning_rate": 1.405508352250002e-05, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9776701390743255, |
| "num_tokens": 83134350.0, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.42298850574712643, |
| "grad_norm": 0.9076487421989441, |
| "learning_rate": 1.3954252297938616e-05, |
| "loss": 0.0682, |
| "mean_token_accuracy": 0.9782249093055725, |
| "num_tokens": 84046651.0, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.42758620689655175, |
| "grad_norm": 0.5395944714546204, |
| "learning_rate": 1.3852946621206762e-05, |
| "loss": 0.0749, |
| "mean_token_accuracy": 0.9772472321987152, |
| "num_tokens": 84958422.0, |
| "step": 465 |
| }, |
| { |
| "epoch": 0.432183908045977, |
| "grad_norm": 0.7367138862609863, |
| "learning_rate": 1.3751189078026948e-05, |
| "loss": 0.0676, |
| "mean_token_accuracy": 0.9775825798511505, |
| "num_tokens": 85856573.0, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.4367816091954023, |
| "grad_norm": 0.47994378209114075, |
| "learning_rate": 1.3649002354863592e-05, |
| "loss": 0.0864, |
| "mean_token_accuracy": 0.9739798128604888, |
| "num_tokens": 86756885.0, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.4413793103448276, |
| "grad_norm": 0.42335155606269836, |
| "learning_rate": 1.3546409233865196e-05, |
| "loss": 0.0858, |
| "mean_token_accuracy": 0.9742102682590484, |
| "num_tokens": 87673090.0, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.4459770114942529, |
| "grad_norm": 0.6084364652633667, |
| "learning_rate": 1.3443432587785139e-05, |
| "loss": 0.0903, |
| "mean_token_accuracy": 0.9729338943958282, |
| "num_tokens": 88587383.0, |
| "step": 485 |
| }, |
| { |
| "epoch": 0.45057471264367815, |
| "grad_norm": 0.630050778388977, |
| "learning_rate": 1.3340095374882284e-05, |
| "loss": 0.0691, |
| "mean_token_accuracy": 0.9769669651985169, |
| "num_tokens": 89495946.0, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.45517241379310347, |
| "grad_norm": 0.44869178533554077, |
| "learning_rate": 1.3236420633802527e-05, |
| "loss": 0.0813, |
| "mean_token_accuracy": 0.9744648694992065, |
| "num_tokens": 90402828.0, |
| "step": 495 |
| }, |
| { |
| "epoch": 0.45977011494252873, |
| "grad_norm": 0.6522092223167419, |
| "learning_rate": 1.3132431478442404e-05, |
| "loss": 0.0938, |
| "mean_token_accuracy": 0.9724063992500305, |
| "num_tokens": 91297433.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.46436781609195404, |
| "grad_norm": 0.4788123071193695, |
| "learning_rate": 1.3028151092795942e-05, |
| "loss": 0.0784, |
| "mean_token_accuracy": 0.9772588193416596, |
| "num_tokens": 92228430.0, |
| "step": 505 |
| }, |
| { |
| "epoch": 0.4689655172413793, |
| "grad_norm": 0.4127851128578186, |
| "learning_rate": 1.2923602725785878e-05, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9804818272590637, |
| "num_tokens": 93143648.0, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.4735632183908046, |
| "grad_norm": 0.6792116761207581, |
| "learning_rate": 1.2818809686080393e-05, |
| "loss": 0.0812, |
| "mean_token_accuracy": 0.975019884109497, |
| "num_tokens": 94045200.0, |
| "step": 515 |
| }, |
| { |
| "epoch": 0.4781609195402299, |
| "grad_norm": 0.5483724474906921, |
| "learning_rate": 1.2713795336896528e-05, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9804078698158264, |
| "num_tokens": 94950881.0, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.4827586206896552, |
| "grad_norm": 0.5482441186904907, |
| "learning_rate": 1.2608583090791447e-05, |
| "loss": 0.0819, |
| "mean_token_accuracy": 0.9744807839393616, |
| "num_tokens": 95867264.0, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.48735632183908045, |
| "grad_norm": 0.41487181186676025, |
| "learning_rate": 1.25031964044427e-05, |
| "loss": 0.0735, |
| "mean_token_accuracy": 0.9792153000831604, |
| "num_tokens": 96791489.0, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.49195402298850577, |
| "grad_norm": 0.6013935804367065, |
| "learning_rate": 1.239765877341863e-05, |
| "loss": 0.0823, |
| "mean_token_accuracy": 0.9753288149833679, |
| "num_tokens": 97701403.0, |
| "step": 535 |
| }, |
| { |
| "epoch": 0.496551724137931, |
| "grad_norm": 0.7854922413825989, |
| "learning_rate": 1.2291993726940136e-05, |
| "loss": 0.0911, |
| "mean_token_accuracy": 0.9722868084907532, |
| "num_tokens": 98609811.0, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.5011494252873563, |
| "grad_norm": 0.6381357908248901, |
| "learning_rate": 1.2186224822634916e-05, |
| "loss": 0.08, |
| "mean_token_accuracy": 0.9761443793773651, |
| "num_tokens": 99522791.0, |
| "step": 545 |
| }, |
| { |
| "epoch": 0.5057471264367817, |
| "grad_norm": 0.6857843399047852, |
| "learning_rate": 1.2080375641285385e-05, |
| "loss": 0.074, |
| "mean_token_accuracy": 0.9783437252044678, |
| "num_tokens": 100437895.0, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.5103448275862069, |
| "grad_norm": 0.5571353435516357, |
| "learning_rate": 1.1974469781571424e-05, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9771218657493591, |
| "num_tokens": 101377974.0, |
| "step": 555 |
| }, |
| { |
| "epoch": 0.5149425287356322, |
| "grad_norm": 0.7320055961608887, |
| "learning_rate": 1.1868530854809144e-05, |
| "loss": 0.0914, |
| "mean_token_accuracy": 0.9736456036567688, |
| "num_tokens": 102278204.0, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.5195402298850574, |
| "grad_norm": 0.7120485305786133, |
| "learning_rate": 1.1762582479686825e-05, |
| "loss": 0.0807, |
| "mean_token_accuracy": 0.975821715593338, |
| "num_tokens": 103206012.0, |
| "step": 565 |
| }, |
| { |
| "epoch": 0.5241379310344828, |
| "grad_norm": 0.38993531465530396, |
| "learning_rate": 1.1656648276999238e-05, |
| "loss": 0.0807, |
| "mean_token_accuracy": 0.9758959949016571, |
| "num_tokens": 104133653.0, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.5287356321839081, |
| "grad_norm": 0.5762227773666382, |
| "learning_rate": 1.1550751864381441e-05, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9787756681442261, |
| "num_tokens": 105053077.0, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 0.5214551687240601, |
| "learning_rate": 1.1444916851043362e-05, |
| "loss": 0.0737, |
| "mean_token_accuracy": 0.9769327402114868, |
| "num_tokens": 105949772.0, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.5379310344827586, |
| "grad_norm": 0.504976749420166, |
| "learning_rate": 1.133916683250617e-05, |
| "loss": 0.0743, |
| "mean_token_accuracy": 0.9763096690177917, |
| "num_tokens": 106856654.0, |
| "step": 585 |
| }, |
| { |
| "epoch": 0.542528735632184, |
| "grad_norm": 0.5965366959571838, |
| "learning_rate": 1.123352538534177e-05, |
| "loss": 0.0797, |
| "mean_token_accuracy": 0.9753524363040924, |
| "num_tokens": 107778924.0, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.5471264367816092, |
| "grad_norm": 0.5915716886520386, |
| "learning_rate": 1.112801606191648e-05, |
| "loss": 0.0695, |
| "mean_token_accuracy": 0.9786266446113586, |
| "num_tokens": 108692252.0, |
| "step": 595 |
| }, |
| { |
| "epoch": 0.5517241379310345, |
| "grad_norm": 0.5595566034317017, |
| "learning_rate": 1.1022662385140123e-05, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.9761924088001251, |
| "num_tokens": 109598889.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5563218390804597, |
| "grad_norm": 0.5432513356208801, |
| "learning_rate": 1.0917487843221688e-05, |
| "loss": 0.0799, |
| "mean_token_accuracy": 0.9747012615203857, |
| "num_tokens": 110508142.0, |
| "step": 605 |
| }, |
| { |
| "epoch": 0.5609195402298851, |
| "grad_norm": 0.5727760791778564, |
| "learning_rate": 1.0812515884432713e-05, |
| "loss": 0.0796, |
| "mean_token_accuracy": 0.9758844137191772, |
| "num_tokens": 111418035.0, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.5655172413793104, |
| "grad_norm": 0.5536214113235474, |
| "learning_rate": 1.0707769911879577e-05, |
| "loss": 0.0747, |
| "mean_token_accuracy": 0.9775225758552551, |
| "num_tokens": 112337311.0, |
| "step": 615 |
| }, |
| { |
| "epoch": 0.5701149425287356, |
| "grad_norm": 0.6378074884414673, |
| "learning_rate": 1.0603273278285885e-05, |
| "loss": 0.084, |
| "mean_token_accuracy": 0.9752679169178009, |
| "num_tokens": 113258984.0, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.5747126436781609, |
| "grad_norm": 0.3961702883243561, |
| "learning_rate": 1.049904928078604e-05, |
| "loss": 0.0523, |
| "mean_token_accuracy": 0.9818265795707702, |
| "num_tokens": 114181231.0, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.5793103448275863, |
| "grad_norm": 0.40239429473876953, |
| "learning_rate": 1.039512115573125e-05, |
| "loss": 0.0739, |
| "mean_token_accuracy": 0.9769675254821777, |
| "num_tokens": 115095870.0, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.5839080459770115, |
| "grad_norm": 0.5164287686347961, |
| "learning_rate": 1.0291512073509069e-05, |
| "loss": 0.0781, |
| "mean_token_accuracy": 0.9753527343273163, |
| "num_tokens": 116015947.0, |
| "step": 635 |
| }, |
| { |
| "epoch": 0.5885057471264368, |
| "grad_norm": 0.6576895117759705, |
| "learning_rate": 1.0188245133377633e-05, |
| "loss": 0.0759, |
| "mean_token_accuracy": 0.9761959373950958, |
| "num_tokens": 116939010.0, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.593103448275862, |
| "grad_norm": 0.6356538534164429, |
| "learning_rate": 1.008534335831579e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9751926541328431, |
| "num_tokens": 117871829.0, |
| "step": 645 |
| }, |
| { |
| "epoch": 0.5977011494252874, |
| "grad_norm": 0.46976158022880554, |
| "learning_rate": 9.982829689890178e-06, |
| "loss": 0.0779, |
| "mean_token_accuracy": 0.9768620073795319, |
| "num_tokens": 118782438.0, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.6022988505747127, |
| "grad_norm": 0.537323534488678, |
| "learning_rate": 9.880726983140533e-06, |
| "loss": 0.0811, |
| "mean_token_accuracy": 0.9749346673488617, |
| "num_tokens": 119691614.0, |
| "step": 655 |
| }, |
| { |
| "epoch": 0.6068965517241379, |
| "grad_norm": 0.4948473870754242, |
| "learning_rate": 9.779058001484206e-06, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9803318202495575, |
| "num_tokens": 120582598.0, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.6114942528735632, |
| "grad_norm": 0.6101373434066772, |
| "learning_rate": 9.677845411641154e-06, |
| "loss": 0.0749, |
| "mean_token_accuracy": 0.9756294190883636, |
| "num_tokens": 121502780.0, |
| "step": 665 |
| }, |
| { |
| "epoch": 0.6160919540229886, |
| "grad_norm": 0.45826777815818787, |
| "learning_rate": 9.577111778580493e-06, |
| "loss": 0.0612, |
| "mean_token_accuracy": 0.9798018515110016, |
| "num_tokens": 122440651.0, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.6206896551724138, |
| "grad_norm": 0.45194923877716064, |
| "learning_rate": 9.476879560489707e-06, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.9818764686584472, |
| "num_tokens": 123342658.0, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.6252873563218391, |
| "grad_norm": 0.3570874035358429, |
| "learning_rate": 9.377171103767682e-06, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9792817056179046, |
| "num_tokens": 124266268.0, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.6298850574712643, |
| "grad_norm": 0.6488479971885681, |
| "learning_rate": 9.278008638042667e-06, |
| "loss": 0.0764, |
| "mean_token_accuracy": 0.9778364062309265, |
| "num_tokens": 125178468.0, |
| "step": 685 |
| }, |
| { |
| "epoch": 0.6344827586206897, |
| "grad_norm": 0.4926360547542572, |
| "learning_rate": 9.17941427121625e-06, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9779334902763367, |
| "num_tokens": 126100859.0, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.639080459770115, |
| "grad_norm": 0.5614813566207886, |
| "learning_rate": 9.0814099845345e-06, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9780540764331818, |
| "num_tokens": 127026138.0, |
| "step": 695 |
| }, |
| { |
| "epoch": 0.6436781609195402, |
| "grad_norm": 0.4535554051399231, |
| "learning_rate": 8.98401762768731e-06, |
| "loss": 0.0708, |
| "mean_token_accuracy": 0.9770565330982208, |
| "num_tokens": 127943100.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.6482758620689655, |
| "grad_norm": 0.40915051102638245, |
| "learning_rate": 8.8872589139371e-06, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9807185232639313, |
| "num_tokens": 128840775.0, |
| "step": 705 |
| }, |
| { |
| "epoch": 0.6528735632183909, |
| "grad_norm": 0.7342942953109741, |
| "learning_rate": 8.79115541527794e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9803516089916229, |
| "num_tokens": 129758894.0, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.6574712643678161, |
| "grad_norm": 0.948239266872406, |
| "learning_rate": 8.695728557626127e-06, |
| "loss": 0.0857, |
| "mean_token_accuracy": 0.9755650281906127, |
| "num_tokens": 130661401.0, |
| "step": 715 |
| }, |
| { |
| "epoch": 0.6620689655172414, |
| "grad_norm": 0.4744986295700073, |
| "learning_rate": 8.600999616043376e-06, |
| "loss": 0.0697, |
| "mean_token_accuracy": 0.9784056901931762, |
| "num_tokens": 131576201.0, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.5649541020393372, |
| "learning_rate": 8.506989709993623e-06, |
| "loss": 0.0724, |
| "mean_token_accuracy": 0.9769956231117248, |
| "num_tokens": 132464823.0, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.671264367816092, |
| "grad_norm": 0.6691383123397827, |
| "learning_rate": 8.41371979863451e-06, |
| "loss": 0.0708, |
| "mean_token_accuracy": 0.9767049610614776, |
| "num_tokens": 133365601.0, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.6758620689655173, |
| "grad_norm": 0.6994060277938843, |
| "learning_rate": 8.321210676144633e-06, |
| "loss": 0.0664, |
| "mean_token_accuracy": 0.9780537009239196, |
| "num_tokens": 134286450.0, |
| "step": 735 |
| }, |
| { |
| "epoch": 0.6804597701149425, |
| "grad_norm": 0.6582711338996887, |
| "learning_rate": 8.229482967087539e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.97929168343544, |
| "num_tokens": 135207847.0, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.6850574712643678, |
| "grad_norm": 0.325099378824234, |
| "learning_rate": 8.138557121813571e-06, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.9821039617061615, |
| "num_tokens": 136125531.0, |
| "step": 745 |
| }, |
| { |
| "epoch": 0.6896551724137931, |
| "grad_norm": 0.4351039528846741, |
| "learning_rate": 8.04845341190054e-06, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.9821174383163452, |
| "num_tokens": 137024840.0, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.6942528735632184, |
| "grad_norm": 0.5102264881134033, |
| "learning_rate": 7.959191925634239e-06, |
| "loss": 0.0618, |
| "mean_token_accuracy": 0.9799088835716248, |
| "num_tokens": 137930450.0, |
| "step": 755 |
| }, |
| { |
| "epoch": 0.6988505747126437, |
| "grad_norm": 0.6010327935218811, |
| "learning_rate": 7.87079256352985e-06, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9801840245723724, |
| "num_tokens": 138833774.0, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.7034482758620689, |
| "grad_norm": 0.8066533207893372, |
| "learning_rate": 7.783275033895186e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9807766616344452, |
| "num_tokens": 139748271.0, |
| "step": 765 |
| }, |
| { |
| "epoch": 0.7080459770114943, |
| "grad_norm": 0.5732226967811584, |
| "learning_rate": 7.696658848436801e-06, |
| "loss": 0.0664, |
| "mean_token_accuracy": 0.9789219319820404, |
| "num_tokens": 140660065.0, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.7126436781609196, |
| "grad_norm": 0.7808948755264282, |
| "learning_rate": 7.610963317909938e-06, |
| "loss": 0.0753, |
| "mean_token_accuracy": 0.9769664287567139, |
| "num_tokens": 141572924.0, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.7172413793103448, |
| "grad_norm": 0.648855447769165, |
| "learning_rate": 7.526207547813249e-06, |
| "loss": 0.0766, |
| "mean_token_accuracy": 0.9769411742687225, |
| "num_tokens": 142476612.0, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.7218390804597701, |
| "grad_norm": 0.7060990333557129, |
| "learning_rate": 7.4424104341293144e-06, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9772260963916779, |
| "num_tokens": 143395304.0, |
| "step": 785 |
| }, |
| { |
| "epoch": 0.7264367816091954, |
| "grad_norm": 0.7983725666999817, |
| "learning_rate": 7.359590659111839e-06, |
| "loss": 0.0724, |
| "mean_token_accuracy": 0.9765449941158295, |
| "num_tokens": 144300623.0, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.7310344827586207, |
| "grad_norm": 0.5347616672515869, |
| "learning_rate": 7.277766687120524e-06, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9812206745147705, |
| "num_tokens": 145215554.0, |
| "step": 795 |
| }, |
| { |
| "epoch": 0.735632183908046, |
| "grad_norm": 0.6084570288658142, |
| "learning_rate": 7.196956760504505e-06, |
| "loss": 0.0751, |
| "mean_token_accuracy": 0.9775193393230438, |
| "num_tokens": 146127687.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.7402298850574712, |
| "grad_norm": 0.7030994892120361, |
| "learning_rate": 7.117178895535283e-06, |
| "loss": 0.0544, |
| "mean_token_accuracy": 0.9822336792945862, |
| "num_tokens": 147051049.0, |
| "step": 805 |
| }, |
| { |
| "epoch": 0.7448275862068966, |
| "grad_norm": 0.6103214621543884, |
| "learning_rate": 7.0384508783900616e-06, |
| "loss": 0.0661, |
| "mean_token_accuracy": 0.9795880854129791, |
| "num_tokens": 147956560.0, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.7494252873563219, |
| "grad_norm": 0.5157619118690491, |
| "learning_rate": 6.960790261186404e-06, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.980077987909317, |
| "num_tokens": 148869597.0, |
| "step": 815 |
| }, |
| { |
| "epoch": 0.7540229885057471, |
| "grad_norm": 0.4790080785751343, |
| "learning_rate": 6.88421435806903e-06, |
| "loss": 0.0644, |
| "mean_token_accuracy": 0.9800616562366485, |
| "num_tokens": 149786856.0, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.7586206896551724, |
| "grad_norm": 0.4411667585372925, |
| "learning_rate": 6.8087402413497055e-06, |
| "loss": 0.0662, |
| "mean_token_accuracy": 0.9788626849651336, |
| "num_tokens": 150699976.0, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.7632183908045977, |
| "grad_norm": 0.428922176361084, |
| "learning_rate": 6.734384737701035e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9815024375915528, |
| "num_tokens": 151601395.0, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.767816091954023, |
| "grad_norm": 0.3128247857093811, |
| "learning_rate": 6.661164424405009e-06, |
| "loss": 0.0632, |
| "mean_token_accuracy": 0.9804297804832458, |
| "num_tokens": 152510184.0, |
| "step": 835 |
| }, |
| { |
| "epoch": 0.7724137931034483, |
| "grad_norm": 0.6545058488845825, |
| "learning_rate": 6.58909562565717e-06, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9789094090461731, |
| "num_tokens": 153417485.0, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.7770114942528735, |
| "grad_norm": 0.3916206359863281, |
| "learning_rate": 6.518194408927188e-06, |
| "loss": 0.0499, |
| "mean_token_accuracy": 0.9829899191856384, |
| "num_tokens": 154332981.0, |
| "step": 845 |
| }, |
| { |
| "epoch": 0.7816091954022989, |
| "grad_norm": 0.7017457485198975, |
| "learning_rate": 6.448476581376685e-06, |
| "loss": 0.0647, |
| "mean_token_accuracy": 0.9797966778278351, |
| "num_tokens": 155266429.0, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.7862068965517242, |
| "grad_norm": 0.5728846788406372, |
| "learning_rate": 6.379957686335075e-06, |
| "loss": 0.0612, |
| "mean_token_accuracy": 0.9812930762767792, |
| "num_tokens": 156174467.0, |
| "step": 855 |
| }, |
| { |
| "epoch": 0.7908045977011494, |
| "grad_norm": 0.4649686813354492, |
| "learning_rate": 6.312652999834249e-06, |
| "loss": 0.0572, |
| "mean_token_accuracy": 0.9828330874443054, |
| "num_tokens": 157081242.0, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.7954022988505747, |
| "grad_norm": 0.8800658583641052, |
| "learning_rate": 6.246577527202835e-06, |
| "loss": 0.0674, |
| "mean_token_accuracy": 0.9789168536663055, |
| "num_tokens": 157989030.0, |
| "step": 865 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.8218408226966858, |
| "learning_rate": 6.181745999720819e-06, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9818450748920441, |
| "num_tokens": 158898203.0, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.8045977011494253, |
| "grad_norm": 0.6460590362548828, |
| "learning_rate": 6.118172871335259e-06, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.9794027090072632, |
| "num_tokens": 159819289.0, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.8091954022988506, |
| "grad_norm": 0.8401420712471008, |
| "learning_rate": 6.055872315437828e-06, |
| "loss": 0.0749, |
| "mean_token_accuracy": 0.9777801215648652, |
| "num_tokens": 160727941.0, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.8137931034482758, |
| "grad_norm": 0.7486006021499634, |
| "learning_rate": 5.994858221704914e-06, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.9755787193775177, |
| "num_tokens": 161647284.0, |
| "step": 885 |
| }, |
| { |
| "epoch": 0.8183908045977012, |
| "grad_norm": 0.5448911786079407, |
| "learning_rate": 5.935144193000973e-06, |
| "loss": 0.0669, |
| "mean_token_accuracy": 0.9784509837627411, |
| "num_tokens": 162557105.0, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.8229885057471265, |
| "grad_norm": 0.5725065469741821, |
| "learning_rate": 5.876743542345809e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9826119601726532, |
| "num_tokens": 163462675.0, |
| "step": 895 |
| }, |
| { |
| "epoch": 0.8275862068965517, |
| "grad_norm": 0.5825878977775574, |
| "learning_rate": 5.819669289946492e-06, |
| "loss": 0.0612, |
| "mean_token_accuracy": 0.9799066543579101, |
| "num_tokens": 164377444.0, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.832183908045977, |
| "grad_norm": 0.6409645080566406, |
| "learning_rate": 5.7639341602945585e-06, |
| "loss": 0.0601, |
| "mean_token_accuracy": 0.9808383047580719, |
| "num_tokens": 165295494.0, |
| "step": 905 |
| }, |
| { |
| "epoch": 0.8367816091954023, |
| "grad_norm": 0.888623833656311, |
| "learning_rate": 5.709550579329119e-06, |
| "loss": 0.0669, |
| "mean_token_accuracy": 0.979329091310501, |
| "num_tokens": 166192270.0, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.8413793103448276, |
| "grad_norm": 0.6019275784492493, |
| "learning_rate": 5.656530671666558e-06, |
| "loss": 0.0562, |
| "mean_token_accuracy": 0.9819577395915985, |
| "num_tokens": 167115312.0, |
| "step": 915 |
| }, |
| { |
| "epoch": 0.8459770114942529, |
| "grad_norm": 0.5155712962150574, |
| "learning_rate": 5.604886257897379e-06, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9801081478595733, |
| "num_tokens": 168018872.0, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.8505747126436781, |
| "grad_norm": 0.6134135127067566, |
| "learning_rate": 5.55462885195086e-06, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9817212998867035, |
| "num_tokens": 168937887.0, |
| "step": 925 |
| }, |
| { |
| "epoch": 0.8551724137931035, |
| "grad_norm": 0.5360121130943298, |
| "learning_rate": 5.505769658528062e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.981070476770401, |
| "num_tokens": 169848700.0, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.8597701149425288, |
| "grad_norm": 0.603476345539093, |
| "learning_rate": 5.458319570603782e-06, |
| "loss": 0.065, |
| "mean_token_accuracy": 0.9796795666217804, |
| "num_tokens": 170759048.0, |
| "step": 935 |
| }, |
| { |
| "epoch": 0.864367816091954, |
| "grad_norm": 0.3992728888988495, |
| "learning_rate": 5.4122891669980095e-06, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.9834621846675873, |
| "num_tokens": 171665193.0, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.8689655172413793, |
| "grad_norm": 0.6973493695259094, |
| "learning_rate": 5.367688710017413e-06, |
| "loss": 0.0572, |
| "mean_token_accuracy": 0.9806591510772705, |
| "num_tokens": 172595695.0, |
| "step": 945 |
| }, |
| { |
| "epoch": 0.8735632183908046, |
| "grad_norm": 0.5043206214904785, |
| "learning_rate": 5.32452814316739e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9809094607830048, |
| "num_tokens": 173514956.0, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.8781609195402299, |
| "grad_norm": 0.4933174252510071, |
| "learning_rate": 5.2828170889352216e-06, |
| "loss": 0.0487, |
| "mean_token_accuracy": 0.9845766961574555, |
| "num_tokens": 174442996.0, |
| "step": 955 |
| }, |
| { |
| "epoch": 0.8827586206896552, |
| "grad_norm": 0.41733112931251526, |
| "learning_rate": 5.242564846644753e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9822833240032196, |
| "num_tokens": 175371670.0, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.8873563218390804, |
| "grad_norm": 1.0205845832824707, |
| "learning_rate": 5.203780390383151e-06, |
| "loss": 0.0789, |
| "mean_token_accuracy": 0.9760799884796143, |
| "num_tokens": 176298063.0, |
| "step": 965 |
| }, |
| { |
| "epoch": 0.8919540229885058, |
| "grad_norm": 0.4502198100090027, |
| "learning_rate": 5.166472367000174e-06, |
| "loss": 0.0585, |
| "mean_token_accuracy": 0.9803130686283111, |
| "num_tokens": 177218667.0, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.896551724137931, |
| "grad_norm": 0.5097551941871643, |
| "learning_rate": 5.1306490941803715e-06, |
| "loss": 0.052, |
| "mean_token_accuracy": 0.9818449378013611, |
| "num_tokens": 178139584.0, |
| "step": 975 |
| }, |
| { |
| "epoch": 0.9011494252873563, |
| "grad_norm": 0.6657311916351318, |
| "learning_rate": 5.096318558588708e-06, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.981008380651474, |
| "num_tokens": 179072993.0, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.9057471264367816, |
| "grad_norm": 0.4749421179294586, |
| "learning_rate": 5.063488414089943e-06, |
| "loss": 0.0473, |
| "mean_token_accuracy": 0.9839545249938965, |
| "num_tokens": 179986046.0, |
| "step": 985 |
| }, |
| { |
| "epoch": 0.9103448275862069, |
| "grad_norm": 0.855669379234314, |
| "learning_rate": 5.032165980042248e-06, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9823661684989929, |
| "num_tokens": 180896952.0, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.9149425287356322, |
| "grad_norm": 0.794036865234375, |
| "learning_rate": 5.002358239665383e-06, |
| "loss": 0.0749, |
| "mean_token_accuracy": 0.9775346577167511, |
| "num_tokens": 181803327.0, |
| "step": 995 |
| }, |
| { |
| "epoch": 0.9195402298850575, |
| "grad_norm": 0.5056424736976624, |
| "learning_rate": 4.974071838483797e-06, |
| "loss": 0.0568, |
| "mean_token_accuracy": 0.9813274145126343, |
| "num_tokens": 182694651.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.9241379310344827, |
| "grad_norm": 0.3988407254219055, |
| "learning_rate": 4.947313082845051e-06, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.9797810792922974, |
| "num_tokens": 183595202.0, |
| "step": 1005 |
| }, |
| { |
| "epoch": 0.9287356321839081, |
| "grad_norm": 0.529626190662384, |
| "learning_rate": 4.922087938513833e-06, |
| "loss": 0.0505, |
| "mean_token_accuracy": 0.9830776453018188, |
| "num_tokens": 184513667.0, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.9333333333333333, |
| "grad_norm": 0.5526555180549622, |
| "learning_rate": 4.898402029341913e-06, |
| "loss": 0.0684, |
| "mean_token_accuracy": 0.9801351606845856, |
| "num_tokens": 185417911.0, |
| "step": 1015 |
| }, |
| { |
| "epoch": 0.9379310344827586, |
| "grad_norm": 0.5563647747039795, |
| "learning_rate": 4.87626063601433e-06, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.9824641048908234, |
| "num_tokens": 186304682.0, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.9425287356321839, |
| "grad_norm": 0.8280395865440369, |
| "learning_rate": 4.855668694872081e-06, |
| "loss": 0.0654, |
| "mean_token_accuracy": 0.9794717192649841, |
| "num_tokens": 187218281.0, |
| "step": 1025 |
| }, |
| { |
| "epoch": 0.9471264367816092, |
| "grad_norm": 0.6050662994384766, |
| "learning_rate": 4.836630796811577e-06, |
| "loss": 0.0544, |
| "mean_token_accuracy": 0.9831116557121277, |
| "num_tokens": 188133522.0, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.9517241379310345, |
| "grad_norm": 0.4940735399723053, |
| "learning_rate": 4.819151186261132e-06, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9815426409244538, |
| "num_tokens": 189052684.0, |
| "step": 1035 |
| }, |
| { |
| "epoch": 0.9563218390804598, |
| "grad_norm": 0.6469078660011292, |
| "learning_rate": 4.80323376023467e-06, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9790501415729522, |
| "num_tokens": 189965862.0, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.960919540229885, |
| "grad_norm": 0.49630728363990784, |
| "learning_rate": 4.78888206746291e-06, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9784960925579071, |
| "num_tokens": 190880986.0, |
| "step": 1045 |
| }, |
| { |
| "epoch": 0.9655172413793104, |
| "grad_norm": 0.7300703525543213, |
| "learning_rate": 4.7760993076021845e-06, |
| "loss": 0.0514, |
| "mean_token_accuracy": 0.9831376612186432, |
| "num_tokens": 191798491.0, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.9701149425287356, |
| "grad_norm": 0.5554219484329224, |
| "learning_rate": 4.764888330521091e-06, |
| "loss": 0.0658, |
| "mean_token_accuracy": 0.9801692545413971, |
| "num_tokens": 192719573.0, |
| "step": 1055 |
| }, |
| { |
| "epoch": 0.9747126436781609, |
| "grad_norm": 0.8547371029853821, |
| "learning_rate": 4.7552516356651225e-06, |
| "loss": 0.0516, |
| "mean_token_accuracy": 0.9830918192863465, |
| "num_tokens": 193620253.0, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.9793103448275862, |
| "grad_norm": 0.8908081650733948, |
| "learning_rate": 4.747191371499425e-06, |
| "loss": 0.0695, |
| "mean_token_accuracy": 0.978307980298996, |
| "num_tokens": 194511882.0, |
| "step": 1065 |
| }, |
| { |
| "epoch": 0.9839080459770115, |
| "grad_norm": 0.5253735780715942, |
| "learning_rate": 4.740709335029811e-06, |
| "loss": 0.0549, |
| "mean_token_accuracy": 0.9813470900058746, |
| "num_tokens": 195426200.0, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.9885057471264368, |
| "grad_norm": 0.5739592909812927, |
| "learning_rate": 4.735806971402114e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9791691601276398, |
| "num_tokens": 196333789.0, |
| "step": 1075 |
| }, |
| { |
| "epoch": 0.993103448275862, |
| "grad_norm": 0.4883657991886139, |
| "learning_rate": 4.732485373580005e-06, |
| "loss": 0.0613, |
| "mean_token_accuracy": 0.9797782659530639, |
| "num_tokens": 197243903.0, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.9977011494252873, |
| "grad_norm": 0.6686563491821289, |
| "learning_rate": 4.730745282101322e-06, |
| "loss": 0.0553, |
| "mean_token_accuracy": 0.9834369242191314, |
| "num_tokens": 198148256.0, |
| "step": 1085 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1087, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.3855860995668312e+19, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
