[ { "loss": 0.6779, "learning_rate": 7.2e-05, "epoch": 0.02, "step": 1 }, { "loss": 0.6675, "learning_rate": 7.2e-05, "epoch": 0.04, "step": 2 }, { "loss": 0.6811, "learning_rate": 7.2e-05, "epoch": 0.05, "step": 3 }, { "loss": 0.695, "learning_rate": 7.2e-05, "epoch": 0.07, "step": 4 }, { "loss": 0.6251, "learning_rate": 7.2e-05, "epoch": 0.09, "step": 5 }, { "loss": 0.6478, "learning_rate": 7.2e-05, "epoch": 0.11, "step": 6 }, { "loss": 0.6045, "learning_rate": 7.2e-05, "epoch": 0.12, "step": 7 }, { "loss": 0.6616, "learning_rate": 7.2e-05, "epoch": 0.14, "step": 8 }, { "loss": 0.6721, "learning_rate": 7.2e-05, "epoch": 0.16, "step": 9 }, { "loss": 0.6664, "learning_rate": 7.2e-05, "epoch": 0.18, "step": 10 }, { "loss": 0.6665, "learning_rate": 7.2e-05, "epoch": 0.19, "step": 11 }, { "loss": 0.6756, "learning_rate": 7.2e-05, "epoch": 0.21, "step": 12 }, { "loss": 0.6604, "learning_rate": 7.2e-05, "epoch": 0.23, "step": 13 }, { "loss": 0.6455, "learning_rate": 7.2e-05, "epoch": 0.25, "step": 14 }, { "loss": 0.6109, "learning_rate": 7.2e-05, "epoch": 0.26, "step": 15 }, { "loss": 0.6696, "learning_rate": 7.2e-05, "epoch": 0.28, "step": 16 }, { "loss": 0.655, "learning_rate": 7.2e-05, "epoch": 0.3, "step": 17 }, { "loss": 0.6734, "learning_rate": 7.2e-05, "epoch": 0.32, "step": 18 }, { "loss": 0.6172, "learning_rate": 7.2e-05, "epoch": 0.33, "step": 19 }, { "loss": 0.6691, "learning_rate": 7.2e-05, "epoch": 0.35, "step": 20 }, { "loss": 0.6951, "learning_rate": 7.2e-05, "epoch": 0.37, "step": 21 }, { "loss": 0.6164, "learning_rate": 7.2e-05, "epoch": 0.39, "step": 22 }, { "loss": 0.6026, "learning_rate": 7.2e-05, "epoch": 0.4, "step": 23 }, { "loss": 0.6532, "learning_rate": 7.2e-05, "epoch": 0.42, "step": 24 }, { "loss": 0.6197, "learning_rate": 7.2e-05, "epoch": 0.44, "step": 25 }, { "eval_math_easy_loss": 0.6815460324287415, "eval_math_easy_score": -0.24459688365459442, "eval_math_easy_brier_score": 0.24459688365459442, "eval_math_easy_average_probability": 0.5072389245033264, "eval_math_easy_accuracy": 0.59, "eval_math_easy_probabilities": [ 0.5215921401977539, 0.5172736644744873, 0.5047991871833801, 0.6169940233230591, 0.49453359842300415, 0.5040465593338013, 0.48313090205192566, 0.4942058026790619, 0.49484187364578247, 0.49886196851730347, 0.49972325563430786, 0.4946691393852234, 0.5034058690071106, 0.49083060026168823, 0.4718078672885895, 0.45443400740623474, 0.50705885887146, 0.464674174785614, 0.4894794821739197, 0.49578550457954407, 0.5121883153915405, 0.6867628693580627, 0.548281192779541, 0.792807936668396, 0.5024372339248657, 0.48924121260643005, 0.502692461013794, 0.5079324245452881, 0.5204778909683228, 0.5145569443702698, 0.5169885158538818, 0.5357310175895691, 0.5136447548866272, 0.5052314400672913, 0.4541933238506317, 0.5003933310508728, 0.527148425579071, 0.530014157295227, 0.5039868354797363, 0.5121827125549316, 0.4406101107597351, 0.4655514359474182, 0.504665195941925, 0.49450919032096863, 0.5082520842552185, 0.47015100717544556, 0.4684576988220215, 0.4783393144607544, 0.496527761220932, 0.44638627767562866, 0.4804031550884247, 0.5208113789558411, 0.5194867253303528, 0.525453507900238, 0.500989556312561, 0.49752557277679443, 0.5027022957801819, 0.5109077095985413, 0.4743708670139313, 0.49530094861984253, 0.5227457880973816, 0.5075706243515015, 0.4851032495498657, 0.5806542038917542, 0.5015441179275513, 0.5421546697616577, 0.4941910207271576, 0.5047829747200012, 0.5067541599273682, 0.5095610618591309, 0.5112190842628479, 0.5192109942436218, 0.5053627490997314, 0.5081002116203308, 0.4611073136329651, 0.4860280156135559, 0.5163429379463196, 0.4763336181640625, 0.5250040888786316, 0.556469738483429, 0.47000882029533386, 0.5106367468833923, 0.5008668303489685, 0.5063503384590149, 0.5027938485145569, 0.49870139360427856, 0.5078895092010498, 0.47641369700431824, 0.5048492550849915, 0.46955257654190063, 0.5337894558906555, 0.5294147729873657, 0.50892174243927, 0.49096107482910156, 0.4964156746864319, 0.48862358927726746, 0.4943075478076935, 0.5119680166244507, 0.49596741795539856, 0.5247774720191956 ], "eval_math_easy_runtime": 8.3644, "eval_math_easy_samples_per_second": 11.955, "eval_math_easy_steps_per_second": 0.239, "epoch": 0.44, "step": 25 }, { "eval_math_hard_loss": 0.6937988996505737, "eval_math_hard_score": -0.24956132471561432, "eval_math_hard_brier_score": 0.24956132471561432, "eval_math_hard_average_probability": 0.5007538199424744, "eval_math_hard_accuracy": 0.6, "eval_math_hard_probabilities": [ 0.4592265784740448, 0.4575088918209076, 0.4573841989040375, 0.4987158179283142, 0.5066536068916321, 0.4981866776943207, 0.4985383450984955, 0.5008953809738159, 0.5002983808517456, 0.4969225823879242, 0.5139631032943726, 0.5020317435264587, 0.500609278678894, 0.5094744563102722, 0.51003098487854, 0.5019204020500183, 0.4999063014984131, 0.49935683608055115, 0.4982687532901764, 0.5023401975631714, 0.4989914298057556, 0.47408029437065125, 0.4788212478160858, 0.4768434762954712, 0.49479010701179504, 0.5104977488517761, 0.513695478439331, 0.5089930891990662, 0.5129966735839844, 0.51589035987854, 0.5078113675117493, 0.5085917711257935, 0.5050703883171082, 0.49824589490890503, 0.49897095561027527, 0.5006430745124817, 0.49485352635383606, 0.499460369348526, 0.502104640007019, 0.4915311336517334, 0.5025181770324707, 0.49508652091026306, 0.5032391548156738, 0.49755167961120605, 0.5033082365989685, 0.50041663646698, 0.4981939494609833, 0.49911266565322876, 0.4469235837459564, 0.42421066761016846, 0.5049431920051575, 0.5023862719535828, 0.5016964077949524, 0.4981962740421295, 0.5656476616859436, 0.5674688816070557, 0.5651683211326599, 0.4971967041492462, 0.5033889412879944, 0.5000178813934326, 0.5006777048110962, 0.49499306082725525, 0.4945516586303711, 0.5035790801048279, 0.502631664276123, 0.4990883469581604, 0.5012502670288086, 0.5094723701477051, 0.5112938284873962, 0.49845635890960693, 0.5009883046150208, 0.5010748505592346, 0.5027943253517151, 0.5007677674293518, 0.5031895637512207, 0.49951398372650146, 0.4983886182308197, 0.4989752471446991, 0.5191434621810913, 0.517387866973877, 0.5041124820709229, 0.5029014945030212, 0.5004555583000183, 0.4984309673309326, 0.5019732713699341, 0.5047473907470703, 0.5020609498023987, 0.5055429935455322, 0.5065346956253052, 0.502338707447052, 0.5019960999488831, 0.5006489157676697, 0.5017046928405762, 0.49878180027008057, 0.4954778254032135, 0.49842569231987, 0.5076271295547485, 0.5023818612098694, 0.5014909505844116, 0.4977472424507141 ], "eval_math_hard_runtime": 19.1708, "eval_math_hard_samples_per_second": 5.216, "eval_math_hard_steps_per_second": 0.104, "epoch": 0.44, "step": 25 }, { "loss": 0.5871, "learning_rate": 7.2e-05, "epoch": 0.46, "step": 26 }, { "loss": 0.6237, "learning_rate": 7.2e-05, "epoch": 0.47, "step": 27 }, { "loss": 0.5942, "learning_rate": 7.2e-05, "epoch": 0.49, "step": 28 }, { "loss": 0.6307, "learning_rate": 7.2e-05, "epoch": 0.51, "step": 29 }, { "loss": 0.6097, "learning_rate": 7.2e-05, "epoch": 0.53, "step": 30 }, { "loss": 0.5838, "learning_rate": 7.2e-05, "epoch": 0.54, "step": 31 }, { "loss": 0.5725, "learning_rate": 7.2e-05, "epoch": 0.56, "step": 32 }, { "loss": 0.5996, "learning_rate": 7.2e-05, "epoch": 0.58, "step": 33 }, { "loss": 0.6481, "learning_rate": 7.2e-05, "epoch": 0.6, "step": 34 }, { "loss": 0.6541, "learning_rate": 7.2e-05, "epoch": 0.61, "step": 35 }, { "loss": 0.6738, "learning_rate": 7.2e-05, "epoch": 0.63, "step": 36 }, { "loss": 0.5626, "learning_rate": 7.2e-05, "epoch": 0.65, "step": 37 }, { "loss": 0.5985, "learning_rate": 7.2e-05, "epoch": 0.67, "step": 38 }, { "loss": 0.567, "learning_rate": 7.2e-05, "epoch": 0.68, "step": 39 }, { "loss": 0.6648, "learning_rate": 7.2e-05, "epoch": 0.7, "step": 40 }, { "loss": 0.6033, "learning_rate": 7.2e-05, "epoch": 0.72, "step": 41 }, { "loss": 0.5811, "learning_rate": 7.2e-05, "epoch": 0.74, "step": 42 }, { "loss": 0.6334, "learning_rate": 7.2e-05, "epoch": 0.75, "step": 43 }, { "loss": 0.5577, "learning_rate": 7.2e-05, "epoch": 0.77, "step": 44 }, { "loss": 0.5735, "learning_rate": 7.2e-05, "epoch": 0.79, "step": 45 }, { "loss": 0.5569, "learning_rate": 7.2e-05, "epoch": 0.81, "step": 46 }, { "loss": 0.6299, "learning_rate": 7.2e-05, "epoch": 0.82, "step": 47 }, { "loss": 0.6322, "learning_rate": 7.2e-05, "epoch": 0.84, "step": 48 }, { "loss": 0.4749, "learning_rate": 7.2e-05, "epoch": 0.86, "step": 49 }, { "loss": 0.5289, "learning_rate": 7.2e-05, "epoch": 0.88, "step": 50 }, { "eval_math_easy_loss": 0.6391142010688782, "eval_math_easy_score": -0.22654081881046295, "eval_math_easy_brier_score": 0.22654081881046295, "eval_math_easy_average_probability": 0.539280354976654, "eval_math_easy_accuracy": 0.62, "eval_math_easy_probabilities": [ 0.5929038524627686, 0.6793323159217834, 0.5206922292709351, 0.8882213830947876, 0.5143958926200867, 0.5561304688453674, 0.44799119234085083, 0.5322203040122986, 0.46689730882644653, 0.49711838364601135, 0.5119889974594116, 0.46913769841194153, 0.5088608860969543, 0.5296240448951721, 0.47047412395477295, 0.5685828328132629, 0.6593344211578369, 0.689530074596405, 0.4746142625808716, 0.4817463755607605, 0.6522068977355957, 0.9664285182952881, 0.6027368307113647, 0.9966045618057251, 0.4856562912464142, 0.4501323997974396, 0.4895368218421936, 0.5427847504615784, 0.6054716110229492, 0.5628061890602112, 0.501743495464325, 0.582392156124115, 0.5577366948127747, 0.6074099540710449, 0.4900270998477936, 0.6368376016616821, 0.46126845479011536, 0.4167042672634125, 0.4483439326286316, 0.6287697553634644, 0.40468552708625793, 0.3911781907081604, 0.6000078916549683, 0.4676419794559479, 0.5567414164543152, 0.4290192723274231, 0.3693322241306305, 0.39954379200935364, 0.5478706955909729, 0.34374991059303284, 0.40947091579437256, 0.5972985029220581, 0.615604043006897, 0.5836848616600037, 0.5058172345161438, 0.4912186563014984, 0.5050725936889648, 0.6889762878417969, 0.4090518355369568, 0.5442801117897034, 0.6401094794273376, 0.4754847288131714, 0.40069302916526794, 0.8405653834342957, 0.536163866519928, 0.5894424915313721, 0.5345266461372375, 0.5742120742797852, 0.561607301235199, 0.4164229929447174, 0.4069885015487671, 0.5932340025901794, 0.5068080425262451, 0.5232132077217102, 0.406319797039032, 0.40427184104919434, 0.6767305135726929, 0.3993513584136963, 0.6805631518363953, 0.8546713590621948, 0.3419986963272095, 0.485027551651001, 0.4527910351753235, 0.473073810338974, 0.5100885033607483, 0.48703742027282715, 0.5082857012748718, 0.43061167001724243, 0.7524380683898926, 0.3981857895851135, 0.5662372708320618, 0.6013215184211731, 0.5868141651153564, 0.5102212429046631, 0.5018954873085022, 0.5172487497329712, 0.5098850131034851, 0.560250997543335, 0.5472134947776794, 0.5603906512260437 ], "eval_math_easy_runtime": 8.3752, "eval_math_easy_samples_per_second": 11.94, "eval_math_easy_steps_per_second": 0.239, "epoch": 0.88, "step": 50 }, { "eval_math_hard_loss": 0.6838726997375488, "eval_math_hard_score": -0.243715301156044, "eval_math_hard_brier_score": 0.243715301156044, "eval_math_hard_average_probability": 0.5079910755157471, "eval_math_hard_accuracy": 0.65, "eval_math_hard_probabilities": [ 0.4238555133342743, 0.4193888306617737, 0.4287368953227997, 0.5097622871398926, 0.5119704008102417, 0.5043654441833496, 0.49800434708595276, 0.5041229128837585, 0.5025528073310852, 0.48951590061187744, 0.5127824544906616, 0.4973561465740204, 0.5096380710601807, 0.5396627187728882, 0.5585019588470459, 0.5096994042396545, 0.5013532638549805, 0.502988338470459, 0.49406543374061584, 0.507104754447937, 0.4999251663684845, 0.5247215628623962, 0.5451326370239258, 0.5359183549880981, 0.5181558132171631, 0.536503791809082, 0.6048808693885803, 0.5271689891815186, 0.5581687092781067, 0.5325394868850708, 0.5137158632278442, 0.5196804404258728, 0.504626452922821, 0.494549423456192, 0.4980875849723816, 0.49984773993492126, 0.49504631757736206, 0.5131542682647705, 0.5201321840286255, 0.4765735864639282, 0.5105160474777222, 0.4853503406047821, 0.49668124318122864, 0.49828919768333435, 0.5007568597793579, 0.5032816529273987, 0.4987526535987854, 0.5028784275054932, 0.42977195978164673, 0.31972736120224, 0.42027080059051514, 0.4997776746749878, 0.5039429664611816, 0.49863913655281067, 0.648627758026123, 0.6524788737297058, 0.6495911478996277, 0.5067777037620544, 0.5034594535827637, 0.4986531734466553, 0.49447762966156006, 0.4965989887714386, 0.48963290452957153, 0.5040078163146973, 0.5049471855163574, 0.4988935589790344, 0.5129610896110535, 0.5386212468147278, 0.5535662770271301, 0.49367326498031616, 0.5008267164230347, 0.49752077460289, 0.5064848065376282, 0.5038233399391174, 0.5006983876228333, 0.5019656419754028, 0.5030573010444641, 0.5042676329612732, 0.5509158968925476, 0.5484299063682556, 0.5154373049736023, 0.5111826658248901, 0.4996742010116577, 0.4907635450363159, 0.5097373723983765, 0.5164612531661987, 0.49861904978752136, 0.5162664651870728, 0.5128406882286072, 0.5021430253982544, 0.5025100708007812, 0.5034770965576172, 0.4991251528263092, 0.5008054971694946, 0.4953734874725342, 0.5018383860588074, 0.5130837559700012, 0.5218067765235901, 0.5131238698959351, 0.49728623032569885 ], "eval_math_hard_runtime": 19.1853, "eval_math_hard_samples_per_second": 5.212, "eval_math_hard_steps_per_second": 0.104, "epoch": 0.88, "step": 50 }, { "loss": 0.5769, "learning_rate": 7.2e-05, "epoch": 0.89, "step": 51 }, { "loss": 0.5334, "learning_rate": 7.2e-05, "epoch": 0.91, "step": 52 }, { "loss": 0.562, "learning_rate": 7.2e-05, "epoch": 0.93, "step": 53 }, { "loss": 0.5452, "learning_rate": 7.2e-05, "epoch": 0.95, "step": 54 }, { "loss": 0.5165, "learning_rate": 7.2e-05, "epoch": 0.96, "step": 55 }, { "loss": 0.5792, "learning_rate": 7.2e-05, "epoch": 0.98, "step": 56 }, { "loss": 0.5594, "learning_rate": 7.2e-05, "epoch": 1.0, "step": 57 }, { "loss": 0.5507, "learning_rate": 7.2e-05, "epoch": 1.02, "step": 58 }, { "loss": 0.583, "learning_rate": 7.2e-05, "epoch": 1.04, "step": 59 }, { "loss": 0.5306, "learning_rate": 7.2e-05, "epoch": 1.05, "step": 60 }, { "loss": 0.4725, "learning_rate": 7.2e-05, "epoch": 1.07, "step": 61 }, { "loss": 0.5936, "learning_rate": 7.2e-05, "epoch": 1.09, "step": 62 }, { "loss": 0.435, "learning_rate": 7.2e-05, "epoch": 1.11, "step": 63 }, { "loss": 0.4773, "learning_rate": 7.2e-05, "epoch": 1.12, "step": 64 }, { "loss": 0.5268, "learning_rate": 7.2e-05, "epoch": 1.14, "step": 65 }, { "loss": 0.474, "learning_rate": 7.2e-05, "epoch": 1.16, "step": 66 }, { "loss": 0.4843, "learning_rate": 7.2e-05, "epoch": 1.18, "step": 67 }, { "loss": 0.5504, "learning_rate": 7.2e-05, "epoch": 1.19, "step": 68 }, { "loss": 0.4748, "learning_rate": 7.2e-05, "epoch": 1.21, "step": 69 }, { "loss": 0.3662, "learning_rate": 7.2e-05, "epoch": 1.23, "step": 70 }, { "loss": 0.4243, "learning_rate": 7.2e-05, "epoch": 1.25, "step": 71 }, { "loss": 0.5726, "learning_rate": 7.2e-05, "epoch": 1.26, "step": 72 }, { "loss": 0.3798, "learning_rate": 7.2e-05, "epoch": 1.28, "step": 73 }, { "loss": 0.4388, "learning_rate": 7.2e-05, "epoch": 1.3, "step": 74 }, { "loss": 0.4366, "learning_rate": 7.2e-05, "epoch": 1.32, "step": 75 }, { "eval_math_easy_loss": 0.6065465807914734, "eval_math_easy_score": -0.20938640832901, "eval_math_easy_brier_score": 0.20938640832901, "eval_math_easy_average_probability": 0.6050859689712524, "eval_math_easy_accuracy": 0.7, "eval_math_easy_probabilities": [ 0.7484821677207947, 0.9446224570274353, 0.6433854103088379, 0.9783756136894226, 0.6324693560600281, 0.5987829566001892, 0.35413846373558044, 0.6616004109382629, 0.31323176622390747, 0.5103604793548584, 0.57724529504776, 0.4153808057308197, 0.5574342012405396, 0.7953811287879944, 0.6361675262451172, 0.9693624973297119, 0.951913595199585, 0.9685657024383545, 0.45639440417289734, 0.5116019248962402, 0.8492849469184875, 0.998566210269928, 0.6505628228187561, 0.9999613761901855, 0.47741028666496277, 0.3376253843307495, 0.4784110486507416, 0.6697921752929688, 0.8528671860694885, 0.7694718241691589, 0.44887471199035645, 0.6469225287437439, 0.7300910949707031, 0.8249411582946777, 0.6692420244216919, 0.8239967226982117, 0.21104538440704346, 0.14954951405525208, 0.516897439956665, 0.7914680242538452, 0.6564459800720215, 0.40211614966392517, 0.8350747227668762, 0.4549277424812317, 0.6646508574485779, 0.4033440947532654, 0.26077815890312195, 0.26494234800338745, 0.9288823008537292, 0.7891556620597839, 0.5281357765197754, 0.7730588912963867, 0.9015129804611206, 0.7031993865966797, 0.5230223536491394, 0.4752960205078125, 0.5077371001243591, 0.9395107626914978, 0.6283096671104431, 0.7931842803955078, 0.8252612948417664, 0.2736623287200928, 0.15930794179439545, 0.941230833530426, 0.5501644015312195, 0.47556072473526, 0.6338704824447632, 0.6975102424621582, 0.6631689071655273, 0.0980004072189331, 0.1000039279460907, 0.7140350341796875, 0.5493795275688171, 0.5289850234985352, 0.4004104435443878, 0.19120419025421143, 0.8710976839065552, 0.2678791880607605, 0.9293620586395264, 0.9909279942512512, 0.16861209273338318, 0.3574914038181305, 0.3917950391769409, 0.33540961146354675, 0.5536927580833435, 0.49055880308151245, 0.5184541344642639, 0.5982361435890198, 0.9495781064033508, 0.21917079389095306, 0.6988996863365173, 0.7291962504386902, 0.76262366771698, 0.5685163736343384, 0.5081316828727722, 0.6110177040100098, 0.5461428165435791, 0.6566176414489746, 0.783910870552063, 0.6443502306938171 ], "eval_math_easy_runtime": 8.369, "eval_math_easy_samples_per_second": 11.949, "eval_math_easy_steps_per_second": 0.239, "epoch": 1.32, "step": 75 }, { "eval_math_hard_loss": 0.6514753699302673, "eval_math_hard_score": -0.2283184826374054, "eval_math_hard_brier_score": 0.2283184826374054, "eval_math_hard_average_probability": 0.5288514494895935, "eval_math_hard_accuracy": 0.75, "eval_math_hard_probabilities": [ 0.3548654317855835, 0.3420700132846832, 0.3793671727180481, 0.5324059128761292, 0.5130384564399719, 0.5044785141944885, 0.5038233399391174, 0.5167575478553772, 0.5076470971107483, 0.47424405813217163, 0.4867190718650818, 0.4810575246810913, 0.5753445625305176, 0.6081233024597168, 0.6951162815093994, 0.5271819829940796, 0.503821611404419, 0.5095653533935547, 0.4920091927051544, 0.5164501070976257, 0.5062336921691895, 0.6085132956504822, 0.6557785868644714, 0.642405092716217, 0.601568341255188, 0.5837816596031189, 0.7453701496124268, 0.5891936421394348, 0.6418473720550537, 0.5706061720848083, 0.5218744874000549, 0.5663473606109619, 0.5293048620223999, 0.5138716697692871, 0.5159409642219543, 0.5150294303894043, 0.5086989402770996, 0.5515217185020447, 0.5562142133712769, 0.45103031396865845, 0.5285841226577759, 0.4722565710544586, 0.48624294996261597, 0.5008323192596436, 0.5031194090843201, 0.5154656171798706, 0.49294641613960266, 0.5039159059524536, 0.5480214357376099, 0.2644377648830414, 0.4588020443916321, 0.4910883903503418, 0.5053740739822388, 0.5089107751846313, 0.8152310252189636, 0.8223882913589478, 0.8195245862007141, 0.5112780928611755, 0.5031809210777283, 0.48029977083206177, 0.49546733498573303, 0.5136077404022217, 0.49493998289108276, 0.49914491176605225, 0.5064308643341064, 0.5028504729270935, 0.530055582523346, 0.5755782723426819, 0.5918564796447754, 0.47705304622650146, 0.5025559663772583, 0.492960125207901, 0.5216047763824463, 0.5314456224441528, 0.5100206136703491, 0.5108229517936707, 0.5146028399467468, 0.5179942846298218, 0.570564866065979, 0.5914015173912048, 0.5727425813674927, 0.5276017785072327, 0.5001986622810364, 0.4896683692932129, 0.5269994735717773, 0.5561158657073975, 0.5013656616210938, 0.5471642017364502, 0.5317503809928894, 0.5032069087028503, 0.4969356954097748, 0.5043812394142151, 0.4943845868110657, 0.5032498240470886, 0.4884641468524933, 0.5083473324775696, 0.47960543632507324, 0.5428357720375061, 0.5140374898910522, 0.5140106081962585 ], "eval_math_hard_runtime": 19.1838, "eval_math_hard_samples_per_second": 5.213, "eval_math_hard_steps_per_second": 0.104, "epoch": 1.32, "step": 75 }, { "loss": 0.4113, "learning_rate": 7.2e-05, "epoch": 1.33, "step": 76 }, { "loss": 0.5044, "learning_rate": 7.2e-05, "epoch": 1.35, "step": 77 }, { "loss": 0.6008, "learning_rate": 7.2e-05, "epoch": 1.37, "step": 78 }, { "loss": 0.5117, "learning_rate": 7.2e-05, "epoch": 1.39, "step": 79 }, { "loss": 0.394, "learning_rate": 7.2e-05, "epoch": 1.4, "step": 80 }, { "loss": 0.4778, "learning_rate": 7.2e-05, "epoch": 1.42, "step": 81 }, { "loss": 0.4636, "learning_rate": 7.2e-05, "epoch": 1.44, "step": 82 }, { "loss": 0.6426, "learning_rate": 7.2e-05, "epoch": 1.46, "step": 83 }, { "loss": 0.5138, "learning_rate": 7.2e-05, "epoch": 1.47, "step": 84 }, { "loss": 0.3992, "learning_rate": 7.2e-05, "epoch": 1.49, "step": 85 }, { "loss": 0.5317, "learning_rate": 7.2e-05, "epoch": 1.51, "step": 86 }, { "loss": 0.3749, "learning_rate": 7.2e-05, "epoch": 1.53, "step": 87 }, { "loss": 0.4308, "learning_rate": 7.2e-05, "epoch": 1.54, "step": 88 }, { "loss": 0.442, "learning_rate": 7.2e-05, "epoch": 1.56, "step": 89 }, { "loss": 0.3635, "learning_rate": 7.2e-05, "epoch": 1.58, "step": 90 }, { "loss": 0.4635, "learning_rate": 7.2e-05, "epoch": 1.6, "step": 91 }, { "loss": 0.352, "learning_rate": 7.2e-05, "epoch": 1.61, "step": 92 }, { "loss": 0.5595, "learning_rate": 7.2e-05, "epoch": 1.63, "step": 93 }, { "loss": 0.4258, "learning_rate": 7.2e-05, "epoch": 1.65, "step": 94 }, { "loss": 0.5241, "learning_rate": 7.2e-05, "epoch": 1.67, "step": 95 }, { "loss": 0.3897, "learning_rate": 7.2e-05, "epoch": 1.68, "step": 96 }, { "loss": 0.3538, "learning_rate": 7.2e-05, "epoch": 1.7, "step": 97 }, { "loss": 0.6195, "learning_rate": 7.2e-05, "epoch": 1.72, "step": 98 }, { "loss": 0.4222, "learning_rate": 7.2e-05, "epoch": 1.74, "step": 99 }, { "loss": 0.4035, "learning_rate": 7.2e-05, "epoch": 1.75, "step": 100 }, { "eval_math_easy_loss": 0.5634673237800598, "eval_math_easy_score": -0.18907848000526428, "eval_math_easy_brier_score": 0.18907848000526428, "eval_math_easy_average_probability": 0.6335412263870239, "eval_math_easy_accuracy": 0.69, "eval_math_easy_probabilities": [ 0.9228202700614929, 0.9722417593002319, 0.7751589417457581, 0.9841300249099731, 0.6461109519004822, 0.678557276725769, 0.48697182536125183, 0.763392984867096, 0.6513355374336243, 0.5514014959335327, 0.5708515644073486, 0.401116281747818, 0.6355666518211365, 0.8389368653297424, 0.4256947934627533, 0.9875867366790771, 0.9562849402427673, 0.9934768080711365, 0.5037747025489807, 0.5629909634590149, 0.9447256326675415, 0.9934955835342407, 0.7298396825790405, 0.9999772310256958, 0.4164830148220062, 0.3354552388191223, 0.4947070777416229, 0.7429382801055908, 0.9662306904792786, 0.8494581580162048, 0.3311953544616699, 0.5235036015510559, 0.7076274156570435, 0.6726058125495911, 0.6066114902496338, 0.9167107939720154, 0.3606979250907898, 0.3136213421821594, 0.569308340549469, 0.8744141459465027, 0.45186856389045715, 0.4703064560890198, 0.8714635372161865, 0.4600178003311157, 0.7752681970596313, 0.3342759311199188, 0.2091922163963318, 0.12097060680389404, 0.9694784283638, 0.9205419421195984, 0.5362300276756287, 0.9467881917953491, 0.9229605197906494, 0.7893558740615845, 0.5593774318695068, 0.48640429973602295, 0.5625292062759399, 0.7873656153678894, 0.4377059042453766, 0.7554200291633606, 0.7428120970726013, 0.3998325765132904, 0.2971757650375366, 0.5841459631919861, 0.5935724377632141, 0.9124895930290222, 0.664108157157898, 0.7424415946006775, 0.7032315731048584, 0.08878877013921738, 0.037293728440999985, 0.8253840804100037, 0.5181460380554199, 0.6422717571258545, 0.39188629388809204, 0.2717941105365753, 0.7366853952407837, 0.3104180693626404, 0.9555566310882568, 0.9926537275314331, 0.31411033868789673, 0.47795569896698, 0.5301631093025208, 0.3858352303504944, 0.450234591960907, 0.5335182547569275, 0.46628960967063904, 0.7136247754096985, 0.9707931280136108, 0.2842671871185303, 0.6815343499183655, 0.8293945789337158, 0.7165514826774597, 0.5158327221870422, 0.4903832674026489, 0.509284496307373, 0.6868314743041992, 0.7351541519165039, 0.9032586216926575, 0.7228848934173584 ], "eval_math_easy_runtime": 8.3781, "eval_math_easy_samples_per_second": 11.936, "eval_math_easy_steps_per_second": 0.239, "epoch": 1.75, "step": 100 }, { "eval_math_hard_loss": 0.6257777214050293, "eval_math_hard_score": -0.2192527800798416, "eval_math_hard_brier_score": 0.2192527800798416, "eval_math_hard_average_probability": 0.5439413785934448, "eval_math_hard_accuracy": 0.73, "eval_math_hard_probabilities": [ 0.5223578810691833, 0.5004584193229675, 0.5246360301971436, 0.5141251087188721, 0.49415719509124756, 0.4868309497833252, 0.5085676908493042, 0.5222219228744507, 0.5071166753768921, 0.485394150018692, 0.4912019371986389, 0.47861963510513306, 0.5835957527160645, 0.6594346761703491, 0.7794536352157593, 0.5213961601257324, 0.5078229308128357, 0.5113033056259155, 0.5170290470123291, 0.533160924911499, 0.5240510702133179, 0.6030251383781433, 0.6816118359565735, 0.6654990911483765, 0.7295182943344116, 0.6408753395080566, 0.9006334543228149, 0.6394204497337341, 0.7044854164123535, 0.5915472507476807, 0.4917044937610626, 0.5480172634124756, 0.5242502689361572, 0.5202026963233948, 0.5320013165473938, 0.5103070139884949, 0.512151837348938, 0.5850697755813599, 0.5973923802375793, 0.44012999534606934, 0.5327370762825012, 0.46452075242996216, 0.49851876497268677, 0.5032814741134644, 0.5159162878990173, 0.5174291133880615, 0.48579660058021545, 0.48921409249305725, 0.7178583741188049, 0.21438536047935486, 0.33929410576820374, 0.4819464385509491, 0.5082027316093445, 0.5161749124526978, 0.8995903730392456, 0.9058607816696167, 0.9033406376838684, 0.5096192955970764, 0.5001044869422913, 0.47920194268226624, 0.4977998733520508, 0.5199769735336304, 0.4958011507987976, 0.4979250729084015, 0.5203951597213745, 0.5156787633895874, 0.5690863132476807, 0.6606236696243286, 0.6244441270828247, 0.48217955231666565, 0.5022764205932617, 0.4897140562534332, 0.5602198839187622, 0.5712270140647888, 0.5307877063751221, 0.5162763595581055, 0.5204914808273315, 0.5259092450141907, 0.5996943712234497, 0.617365300655365, 0.5981971025466919, 0.5278289914131165, 0.5039482712745667, 0.4940468370914459, 0.49701008200645447, 0.5211564898490906, 0.49761655926704407, 0.602383553981781, 0.5712856650352478, 0.5203680396080017, 0.5200499892234802, 0.5175550580024719, 0.506922721862793, 0.500126838684082, 0.48529988527297974, 0.507023274898529, 0.3651067614555359, 0.4000832736492157, 0.35857725143432617, 0.507904589176178 ], "eval_math_hard_runtime": 19.1792, "eval_math_hard_samples_per_second": 5.214, "eval_math_hard_steps_per_second": 0.104, "epoch": 1.75, "step": 100 }, { "train_runtime": 768.3351, "train_samples_per_second": 4.165, "train_steps_per_second": 0.13, "total_flos": 0.0, "train_loss": 0.5549128046631813, "epoch": 1.75, "step": 100 } ]