openllama-3b-code_low_quality / training_logs.json
joshuaclymer's picture
Upload folder using huggingface_hub
15ee309
[
{
"loss": 0.6712,
"learning_rate": 7.2e-05,
"epoch": 0.03,
"step": 1
},
{
"loss": 0.6482,
"learning_rate": 7.2e-05,
"epoch": 0.05,
"step": 2
},
{
"loss": 0.6674,
"learning_rate": 7.2e-05,
"epoch": 0.08,
"step": 3
},
{
"loss": 0.661,
"learning_rate": 7.2e-05,
"epoch": 0.11,
"step": 4
},
{
"loss": 0.5958,
"learning_rate": 7.2e-05,
"epoch": 0.13,
"step": 5
},
{
"loss": 0.628,
"learning_rate": 7.2e-05,
"epoch": 0.16,
"step": 6
},
{
"loss": 0.6028,
"learning_rate": 7.2e-05,
"epoch": 0.18,
"step": 7
},
{
"loss": 0.6019,
"learning_rate": 7.2e-05,
"epoch": 0.21,
"step": 8
},
{
"loss": 0.5519,
"learning_rate": 7.2e-05,
"epoch": 0.24,
"step": 9
},
{
"loss": 0.5427,
"learning_rate": 7.2e-05,
"epoch": 0.26,
"step": 10
},
{
"loss": 0.5148,
"learning_rate": 7.2e-05,
"epoch": 0.29,
"step": 11
},
{
"loss": 0.5229,
"learning_rate": 7.2e-05,
"epoch": 0.32,
"step": 12
},
{
"loss": 0.4487,
"learning_rate": 7.2e-05,
"epoch": 0.34,
"step": 13
},
{
"loss": 0.4622,
"learning_rate": 7.2e-05,
"epoch": 0.37,
"step": 14
},
{
"loss": 0.5247,
"learning_rate": 7.2e-05,
"epoch": 0.39,
"step": 15
},
{
"loss": 0.4628,
"learning_rate": 7.2e-05,
"epoch": 0.42,
"step": 16
},
{
"loss": 0.4347,
"learning_rate": 7.2e-05,
"epoch": 0.45,
"step": 17
},
{
"loss": 0.3905,
"learning_rate": 7.2e-05,
"epoch": 0.47,
"step": 18
},
{
"loss": 0.3277,
"learning_rate": 7.2e-05,
"epoch": 0.5,
"step": 19
},
{
"loss": 0.2926,
"learning_rate": 7.2e-05,
"epoch": 0.53,
"step": 20
},
{
"loss": 0.3436,
"learning_rate": 7.2e-05,
"epoch": 0.55,
"step": 21
},
{
"loss": 0.2549,
"learning_rate": 7.2e-05,
"epoch": 0.58,
"step": 22
},
{
"loss": 0.2182,
"learning_rate": 7.2e-05,
"epoch": 0.61,
"step": 23
},
{
"loss": 0.1982,
"learning_rate": 7.2e-05,
"epoch": 0.63,
"step": 24
},
{
"loss": 0.161,
"learning_rate": 7.2e-05,
"epoch": 0.66,
"step": 25
},
{
"eval_code_low_quality_loss": 0.0951915830373764,
"eval_code_low_quality_score": -0.023566950112581253,
"eval_code_low_quality_brier_score": 0.023566950112581253,
"eval_code_low_quality_average_probability": 0.907680332660675,
"eval_code_low_quality_accuracy": 0.98,
"eval_code_low_quality_probabilities": [
0.9925367832183838,
0.9840611815452576,
0.7860302925109863,
0.8891001343727112,
0.9905372262001038,
0.9568611979484558,
0.9341686964035034,
0.8778702616691589,
0.9786091446876526,
0.9330840110778809,
0.9966692328453064,
0.9975678324699402,
0.9617735147476196,
0.9792876243591309,
0.9869201183319092,
0.9909035563468933,
0.9864379167556763,
0.5783786177635193,
0.9241027235984802,
0.9600433111190796,
0.7587274312973022,
0.8323114514350891,
0.877905011177063,
0.8901019096374512,
0.8700847625732422,
0.887502133846283,
0.7855967879295349,
0.8953022956848145,
0.913593053817749,
0.8834923505783081,
0.6113455891609192,
0.9742891192436218,
0.9921196699142456,
0.9815818071365356,
0.9205424785614014,
0.9094852209091187,
0.9560614228248596,
0.960161566734314,
0.8312894701957703,
0.7790418267250061,
0.8403017520904541,
0.9003271460533142,
0.9872115254402161,
0.9675229787826538,
0.9775436520576477,
0.9949591159820557,
0.98282790184021,
0.982309877872467,
0.9526650309562683,
0.9178764820098877,
0.9971938133239746,
0.9984176158905029,
0.9871721863746643,
0.9735684990882874,
0.9058899283409119,
0.9493223428726196,
0.9861119985580444,
0.9859384894371033,
0.9355461001396179,
0.791418194770813,
0.992045521736145,
0.9872221350669861,
0.9527598023414612,
0.9187523722648621,
0.8177111148834229,
0.9786438345909119,
0.9874449968338013,
0.9943341016769409,
0.9862135052680969,
0.988554060459137,
0.9788398742675781,
0.9971326589584351,
0.9967315196990967,
0.9900894165039062,
0.9409597516059875,
0.9783955812454224,
0.9238479733467102,
0.9934139847755432,
0.7463366389274597,
0.9180166721343994,
0.9864663481712341,
0.9937455654144287,
0.9708875417709351,
0.9727025032043457,
0.9636775851249695,
0.9573163390159607,
0.6392986178398132,
0.6527231335639954,
0.9338482022285461,
0.9202041029930115,
0.7206510901451111,
0.7209832072257996,
0.9708787798881531,
0.9102391004562378,
0.8587813377380371,
0.8840697407722473,
0.7573890089988708,
0.9752879738807678,
0.4457229673862457,
0.2561103403568268
],
"eval_code_low_quality_runtime": 38.4811,
"eval_code_low_quality_samples_per_second": 2.599,
"eval_code_low_quality_steps_per_second": 0.052,
"epoch": 0.66,
"step": 25
},
{
"eval_code_loss": 0.9943647980690002,
"eval_code_score": -0.28008389472961426,
"eval_code_brier_score": 0.28008389472961426,
"eval_code_average_probability": 0.5028746724128723,
"eval_code_accuracy": 0.73,
"eval_code_probabilities": [
0.0013771726517006755,
0.0021421583369374275,
0.0021674928721040487,
0.523486852645874,
0.6844746470451355,
0.5299127101898193,
0.5120762586593628,
0.7857722043991089,
0.5001239776611328,
0.507907509803772,
0.5472686886787415,
0.5965446829795837,
0.47309237718582153,
0.7392762899398804,
0.5616071224212646,
0.5222716331481934,
0.5174436569213867,
0.5479878783226013,
0.7341067790985107,
0.6857637166976929,
0.6855947375297546,
0.484964519739151,
0.5379744172096252,
0.5018139481544495,
0.018715351819992065,
0.015019988641142845,
0.016509870067238808,
0.5054175853729248,
0.5175662636756897,
0.6052428483963013,
0.4553852081298828,
0.5380894541740417,
0.5062794089317322,
0.042318232357501984,
0.037935495376586914,
0.042440593242645264,
0.5699766874313354,
0.5090808272361755,
0.5176827907562256,
0.5127310752868652,
0.5206546783447266,
0.5350870490074158,
0.5115861296653748,
0.537502646446228,
0.623155415058136,
0.49951303005218506,
0.548371434211731,
0.5232611894607544,
0.5098251700401306,
0.5139918923377991,
0.8860173225402832,
0.6156609654426575,
0.6341218948364258,
0.543006181716919,
0.5034212470054626,
0.5090045928955078,
0.5025768280029297,
0.805193305015564,
0.5220950245857239,
0.8043115735054016,
0.5911435484886169,
0.5618972778320312,
0.5862018465995789,
0.4658759534358978,
0.4998258650302887,
0.5460342764854431,
0.4621177017688751,
0.33082979917526245,
0.35442039370536804,
0.5409923791885376,
0.48686879873275757,
0.5274949073791504,
0.5022823810577393,
0.5296149253845215,
0.5378413796424866,
0.8412360548973083,
0.7736567258834839,
0.8534575700759888,
0.4241589307785034,
0.5119674205780029,
0.4645305573940277,
0.5176393389701843,
0.49852415919303894,
0.602745771408081,
0.5448736548423767,
0.6585777401924133,
0.4206017851829529,
0.573499858379364,
0.5334447026252747,
0.5451390147209167,
0.5268576145172119,
0.5080337524414062,
0.5261317491531372,
0.5029634833335876,
0.501714289188385,
0.505605161190033,
0.3948810398578644,
0.39573386311531067,
0.3992973268032074,
0.4948563277721405
],
"eval_code_runtime": 36.6822,
"eval_code_samples_per_second": 2.726,
"eval_code_steps_per_second": 0.055,
"epoch": 0.66,
"step": 25
},
{
"loss": 0.3089,
"learning_rate": 7.2e-05,
"epoch": 0.68,
"step": 26
},
{
"loss": 0.129,
"learning_rate": 7.2e-05,
"epoch": 0.71,
"step": 27
},
{
"loss": 0.1145,
"learning_rate": 7.2e-05,
"epoch": 0.74,
"step": 28
},
{
"loss": 0.1449,
"learning_rate": 7.2e-05,
"epoch": 0.76,
"step": 29
},
{
"loss": 0.052,
"learning_rate": 7.2e-05,
"epoch": 0.79,
"step": 30
},
{
"loss": 0.0636,
"learning_rate": 7.2e-05,
"epoch": 0.82,
"step": 31
},
{
"loss": 0.0275,
"learning_rate": 7.2e-05,
"epoch": 0.84,
"step": 32
},
{
"loss": 0.0324,
"learning_rate": 7.2e-05,
"epoch": 0.87,
"step": 33
},
{
"loss": 0.0102,
"learning_rate": 7.2e-05,
"epoch": 0.89,
"step": 34
},
{
"loss": 0.0436,
"learning_rate": 7.2e-05,
"epoch": 0.92,
"step": 35
},
{
"loss": 0.0156,
"learning_rate": 7.2e-05,
"epoch": 0.95,
"step": 36
},
{
"loss": 0.0175,
"learning_rate": 7.2e-05,
"epoch": 0.97,
"step": 37
},
{
"loss": 0.1136,
"learning_rate": 7.2e-05,
"epoch": 1.0,
"step": 38
},
{
"loss": 0.0842,
"learning_rate": 7.2e-05,
"epoch": 1.03,
"step": 39
},
{
"loss": 0.008,
"learning_rate": 7.2e-05,
"epoch": 1.05,
"step": 40
},
{
"loss": 0.004,
"learning_rate": 7.2e-05,
"epoch": 1.08,
"step": 41
},
{
"loss": 0.016,
"learning_rate": 7.2e-05,
"epoch": 1.11,
"step": 42
},
{
"loss": 0.0247,
"learning_rate": 7.2e-05,
"epoch": 1.13,
"step": 43
},
{
"loss": 0.0259,
"learning_rate": 7.2e-05,
"epoch": 1.16,
"step": 44
},
{
"loss": 0.2052,
"learning_rate": 7.2e-05,
"epoch": 1.18,
"step": 45
},
{
"loss": 0.0087,
"learning_rate": 7.2e-05,
"epoch": 1.21,
"step": 46
},
{
"loss": 0.0006,
"learning_rate": 7.2e-05,
"epoch": 1.24,
"step": 47
},
{
"loss": 0.0326,
"learning_rate": 7.2e-05,
"epoch": 1.26,
"step": 48
},
{
"loss": 0.0016,
"learning_rate": 7.2e-05,
"epoch": 1.29,
"step": 49
},
{
"loss": 0.022,
"learning_rate": 7.2e-05,
"epoch": 1.32,
"step": 50
},
{
"eval_code_low_quality_loss": 0.007781789172440767,
"eval_code_low_quality_score": -0.009711829014122486,
"eval_code_low_quality_brier_score": 0.009711829014122486,
"eval_code_low_quality_average_probability": 0.9875654578208923,
"eval_code_low_quality_accuracy": 0.99,
"eval_code_low_quality_probabilities": [
1.0,
1.0,
0.973220705986023,
0.9989569187164307,
1.0,
1.0,
1.0,
0.9999943971633911,
1.0,
1.0,
1.0,
1.0,
0.9804773330688477,
0.9999984502792358,
1.0,
1.0,
0.9992768168449402,
0.9853408932685852,
0.9999998807907104,
1.0,
0.9872244596481323,
0.9999868869781494,
0.9999997615814209,
0.9999994039535522,
0.9999929666519165,
0.9999935626983643,
0.9996015429496765,
0.9999901056289673,
1.0,
0.9999998807907104,
0.8831122517585754,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9999998807907104,
0.9999983310699463,
0.9999868869781494,
0.9994181394577026,
0.9999551773071289,
1.0,
0.9999998807907104,
0.974841296672821,
1.0,
1.0,
1.0,
0.9999957084655762,
0.9999563694000244,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9999856948852539,
1.0,
1.0,
1.0,
0.9999946355819702,
0.9999997615814209,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9999998807907104,
1.0,
0.9999997615814209,
1.0,
0.9990255832672119,
1.0,
0.9886683821678162,
0.9999992847442627,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.998230516910553,
0.9682945609092712,
0.9999998807907104,
0.9999996423721313,
0.9999982118606567,
0.9999991655349731,
1.0,
0.9987072944641113,
0.999998927116394,
0.999998927116394,
0.9999661445617676,
1.0,
0.9992316961288452,
0.023133214563131332
],
"eval_code_low_quality_runtime": 38.4634,
"eval_code_low_quality_samples_per_second": 2.6,
"eval_code_low_quality_steps_per_second": 0.052,
"epoch": 1.32,
"step": 50
},
{
"eval_code_loss": 1.460232138633728,
"eval_code_score": -0.31812021136283875,
"eval_code_brier_score": 0.31812021136283875,
"eval_code_average_probability": 0.4904159903526306,
"eval_code_accuracy": 0.57,
"eval_code_probabilities": [
2.16732428270916e-06,
3.4093727663275786e-06,
3.5568630210036645e-06,
0.6349762082099915,
0.9333071708679199,
0.5989739298820496,
0.5028566718101501,
0.7891841530799866,
0.48944294452667236,
0.4759078919887543,
0.43146440386772156,
0.539191722869873,
0.3894290626049042,
0.538087785243988,
0.28379419445991516,
0.5046406984329224,
0.5067718625068665,
0.5060579180717468,
0.6930060982704163,
0.363099068403244,
0.3801196813583374,
0.5059704184532166,
0.5147981643676758,
0.5063120126724243,
0.1608428955078125,
0.17055238783359528,
0.18348702788352966,
0.4475654661655426,
0.5803108215332031,
0.9961491823196411,
0.4789189100265503,
0.5795977115631104,
0.5235514044761658,
1.349542617390398e-05,
6.869557637401158e-06,
1.1343794540152885e-05,
0.5054447650909424,
0.4932360053062439,
0.5053790211677551,
0.4945124387741089,
0.8466330766677856,
0.09067995101213455,
0.5200114846229553,
0.5741671919822693,
0.546498715877533,
0.4916382431983948,
0.5894687175750732,
0.5640509128570557,
0.5067146420478821,
0.5299816131591797,
0.32341182231903076,
0.522653341293335,
0.7552465200424194,
0.5522850751876831,
0.5096533298492432,
0.5080340504646301,
0.4963303208351135,
0.9567633271217346,
0.4783303439617157,
0.9586471319198608,
0.3498120903968811,
0.2851160764694214,
0.3396932780742645,
0.17300352454185486,
0.5078068971633911,
0.5194015502929688,
0.48811495304107666,
0.42335256934165955,
0.4560243785381317,
0.6968233585357666,
0.5099424123764038,
0.47498029470443726,
0.47725340723991394,
0.6388620138168335,
0.6904007792472839,
0.9997544884681702,
0.93499356508255,
0.9999597072601318,
0.07373078167438507,
0.20508405566215515,
0.11463714390993118,
0.6171519160270691,
0.4903092682361603,
0.8550575375556946,
0.6555699110031128,
0.6090169548988342,
0.6722232699394226,
0.9523137211799622,
0.722933292388916,
0.7777043581008911,
0.5438691973686218,
0.4905330538749695,
0.5533438324928284,
0.5145766139030457,
0.5064784288406372,
0.46289509534835815,
0.08988309651613235,
0.07098916918039322,
0.059304364025592804,
0.5105205774307251
],
"eval_code_runtime": 36.6672,
"eval_code_samples_per_second": 2.727,
"eval_code_steps_per_second": 0.055,
"epoch": 1.32,
"step": 50
},
{
"loss": 0.0995,
"learning_rate": 7.2e-05,
"epoch": 1.34,
"step": 51
},
{
"loss": 0.1833,
"learning_rate": 7.2e-05,
"epoch": 1.37,
"step": 52
},
{
"loss": 0.0263,
"learning_rate": 7.2e-05,
"epoch": 1.39,
"step": 53
},
{
"loss": 0.0007,
"learning_rate": 7.2e-05,
"epoch": 1.42,
"step": 54
},
{
"loss": 0.0002,
"learning_rate": 7.2e-05,
"epoch": 1.45,
"step": 55
},
{
"loss": 0.0218,
"learning_rate": 7.2e-05,
"epoch": 1.47,
"step": 56
},
{
"loss": 0.0,
"learning_rate": 7.2e-05,
"epoch": 1.5,
"step": 57
},
{
"loss": 0.0106,
"learning_rate": 7.2e-05,
"epoch": 1.53,
"step": 58
},
{
"loss": 0.004,
"learning_rate": 7.2e-05,
"epoch": 1.55,
"step": 59
},
{
"loss": 0.0005,
"learning_rate": 7.2e-05,
"epoch": 1.58,
"step": 60
},
{
"loss": 0.0002,
"learning_rate": 7.2e-05,
"epoch": 1.61,
"step": 61
},
{
"loss": 0.0004,
"learning_rate": 7.2e-05,
"epoch": 1.63,
"step": 62
},
{
"loss": 0.0004,
"learning_rate": 7.2e-05,
"epoch": 1.66,
"step": 63
},
{
"loss": 0.295,
"learning_rate": 7.2e-05,
"epoch": 1.68,
"step": 64
},
{
"loss": 0.0007,
"learning_rate": 7.2e-05,
"epoch": 1.71,
"step": 65
},
{
"loss": 0.0501,
"learning_rate": 7.2e-05,
"epoch": 1.74,
"step": 66
},
{
"loss": 0.01,
"learning_rate": 7.2e-05,
"epoch": 1.76,
"step": 67
},
{
"loss": 0.0007,
"learning_rate": 7.2e-05,
"epoch": 1.79,
"step": 68
},
{
"loss": 0.0008,
"learning_rate": 7.2e-05,
"epoch": 1.82,
"step": 69
},
{
"loss": 0.0194,
"learning_rate": 7.2e-05,
"epoch": 1.84,
"step": 70
},
{
"loss": 0.0004,
"learning_rate": 7.2e-05,
"epoch": 1.87,
"step": 71
},
{
"loss": 0.0006,
"learning_rate": 7.2e-05,
"epoch": 1.89,
"step": 72
},
{
"loss": 0.0041,
"learning_rate": 7.2e-05,
"epoch": 1.92,
"step": 73
},
{
"loss": 0.0771,
"learning_rate": 7.2e-05,
"epoch": 1.95,
"step": 74
},
{
"loss": 0.0001,
"learning_rate": 7.2e-05,
"epoch": 1.97,
"step": 75
},
{
"eval_code_low_quality_loss": 0.0007030765991657972,
"eval_code_low_quality_score": -0.0002731765853241086,
"eval_code_low_quality_brier_score": 0.0002731765853241086,
"eval_code_low_quality_average_probability": 0.998019278049469,
"eval_code_low_quality_accuracy": 1.0,
"eval_code_low_quality_probabilities": [
0.9999996423721313,
0.9999985694885254,
0.9997590184211731,
0.9999872446060181,
1.0,
1.0,
1.0,
0.9999998807907104,
1.0,
1.0,
1.0,
1.0,
0.999883770942688,
1.0,
1.0,
1.0,
0.9998874664306641,
0.9946458339691162,
1.0,
1.0,
0.9999872446060181,
1.0,
0.9999836683273315,
0.9999860525131226,
0.9999688863754272,
0.9999788999557495,
0.9999792575836182,
0.9999990463256836,
1.0,
1.0,
0.9991899132728577,
1.0,
0.9999998807907104,
0.9999997615814209,
1.0,
1.0,
1.0,
1.0,
0.9999985694885254,
0.9999978542327881,
0.9999850988388062,
0.9999971389770508,
1.0,
1.0,
0.9836633205413818,
1.0,
0.9999394416809082,
0.9999537467956543,
0.9999992847442627,
0.9999977350234985,
1.0,
1.0,
0.9999996423721313,
0.9999992847442627,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9999997615814209,
0.9999901056289673,
0.9999992847442627,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9999781847000122,
0.9999998807907104,
1.0,
1.0,
0.9999926090240479,
1.0,
0.9996541738510132,
0.9999997615814209,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9997922778129578,
0.9902224540710449,
0.9999978542327881,
0.9999958276748657,
0.9999992847442627,
0.9999996423721313,
1.0,
0.9999915361404419,
0.9998434782028198,
0.9998369216918945,
0.9999985694885254,
1.0,
0.9999539852142334,
0.8359099626541138
],
"eval_code_low_quality_runtime": 38.4859,
"eval_code_low_quality_samples_per_second": 2.598,
"eval_code_low_quality_steps_per_second": 0.052,
"epoch": 1.97,
"step": 75
},
{
"eval_code_loss": 1.232956051826477,
"eval_code_score": -0.31121882796287537,
"eval_code_brier_score": 0.31121882796287537,
"eval_code_average_probability": 0.5223905444145203,
"eval_code_accuracy": 0.6,
"eval_code_probabilities": [
0.00011101631389465183,
0.0009927322389557958,
0.0006042951135896146,
0.8104570508003235,
0.9767997860908508,
0.6998010873794556,
0.5327707529067993,
0.8981274962425232,
0.46407392621040344,
0.5261912941932678,
0.5234853029251099,
0.5620546936988831,
0.4464522898197174,
0.6497852206230164,
0.3163464069366455,
0.5068030953407288,
0.4470524191856384,
0.4513201415538788,
0.9744485020637512,
0.5525326132774353,
0.6335050463676453,
0.5116932392120361,
0.5079017281532288,
0.49437832832336426,
0.007605725899338722,
0.005129675380885601,
0.0051497663371264935,
0.5000962018966675,
0.632622480392456,
0.9706986546516418,
0.43275994062423706,
0.7873733639717102,
0.540113627910614,
0.004106579814106226,
0.001123218797147274,
0.0015394079964607954,
0.5942471027374268,
0.49709969758987427,
0.5328391194343567,
0.4717523455619812,
0.7803015112876892,
0.15918061137199402,
0.5596816539764404,
0.7085431218147278,
0.6711235642433167,
0.44160714745521545,
0.8594750761985779,
0.7278712391853333,
0.6237335801124573,
0.6038733124732971,
0.298341304063797,
0.4917309582233429,
0.9929433465003967,
0.7463914155960083,
0.5643486380577087,
0.5242550373077393,
0.48715683817863464,
0.9934378266334534,
0.6017891764640808,
0.995071530342102,
0.04592354968190193,
0.03277994319796562,
0.04245381057262421,
0.17133520543575287,
0.5046836137771606,
0.4788260757923126,
0.5977773070335388,
0.3292385935783386,
0.3777988851070404,
0.8941593766212463,
0.550373375415802,
0.4914136230945587,
0.4404219090938568,
0.5822964310646057,
0.6599177718162537,
0.9999847412109375,
0.8205021619796753,
0.9999983310699463,
0.06390584260225296,
0.27923598885536194,
0.18379205465316772,
0.816386342048645,
0.47810855507850647,
0.994751513004303,
0.6124905347824097,
0.7866218090057373,
0.9306473731994629,
0.9980021119117737,
0.9195950627326965,
0.9040439128875732,
0.5383397936820984,
0.5097209811210632,
0.5496564507484436,
0.5447408556938171,
0.5060871243476868,
0.47790002822875977,
0.13077017664909363,
0.0860414132475853,
0.08788496255874634,
0.5176451802253723
],
"eval_code_runtime": 36.6727,
"eval_code_samples_per_second": 2.727,
"eval_code_steps_per_second": 0.055,
"epoch": 1.97,
"step": 75
},
{
"loss": 0.0008,
"learning_rate": 7.2e-05,
"epoch": 2.0,
"step": 76
},
{
"loss": 0.0006,
"learning_rate": 7.2e-05,
"epoch": 2.03,
"step": 77
},
{
"loss": 0.001,
"learning_rate": 7.2e-05,
"epoch": 2.05,
"step": 78
},
{
"loss": 0.0001,
"learning_rate": 7.2e-05,
"epoch": 2.08,
"step": 79
},
{
"loss": 0.0001,
"learning_rate": 7.2e-05,
"epoch": 2.11,
"step": 80
},
{
"loss": 0.0,
"learning_rate": 7.2e-05,
"epoch": 2.13,
"step": 81
},
{
"loss": 0.0003,
"learning_rate": 7.2e-05,
"epoch": 2.16,
"step": 82
},
{
"loss": 0.0,
"learning_rate": 7.2e-05,
"epoch": 2.18,
"step": 83
},
{
"loss": 0.0,
"learning_rate": 7.2e-05,
"epoch": 2.21,
"step": 84
},
{
"loss": 0.0003,
"learning_rate": 7.2e-05,
"epoch": 2.24,
"step": 85
},
{
"loss": 0.0001,
"learning_rate": 7.2e-05,
"epoch": 2.26,
"step": 86
},
{
"loss": 0.0007,
"learning_rate": 7.2e-05,
"epoch": 2.29,
"step": 87
},
{
"loss": 0.0017,
"learning_rate": 7.2e-05,
"epoch": 2.32,
"step": 88
},
{
"loss": 0.0017,
"learning_rate": 7.2e-05,
"epoch": 2.34,
"step": 89
},
{
"loss": 0.0,
"learning_rate": 7.2e-05,
"epoch": 2.37,
"step": 90
},
{
"loss": 0.0,
"learning_rate": 7.2e-05,
"epoch": 2.39,
"step": 91
},
{
"loss": 0.0001,
"learning_rate": 7.2e-05,
"epoch": 2.42,
"step": 92
},
{
"loss": 0.0059,
"learning_rate": 7.2e-05,
"epoch": 2.45,
"step": 93
},
{
"loss": 0.0001,
"learning_rate": 7.2e-05,
"epoch": 2.47,
"step": 94
},
{
"loss": 0.0584,
"learning_rate": 7.2e-05,
"epoch": 2.5,
"step": 95
},
{
"loss": 0.0175,
"learning_rate": 7.2e-05,
"epoch": 2.53,
"step": 96
},
{
"loss": 0.0035,
"learning_rate": 7.2e-05,
"epoch": 2.55,
"step": 97
},
{
"loss": 0.0014,
"learning_rate": 7.2e-05,
"epoch": 2.58,
"step": 98
},
{
"loss": 0.0002,
"learning_rate": 7.2e-05,
"epoch": 2.61,
"step": 99
},
{
"loss": 0.0008,
"learning_rate": 7.2e-05,
"epoch": 2.63,
"step": 100
},
{
"eval_code_low_quality_loss": 0.0012827370082959533,
"eval_code_low_quality_score": -0.00027803267585113645,
"eval_code_low_quality_brier_score": 0.00027803267585113645,
"eval_code_low_quality_average_probability": 0.9977189898490906,
"eval_code_low_quality_accuracy": 1.0,
"eval_code_low_quality_probabilities": [
0.9999994039535522,
0.9999977350234985,
0.9998675584793091,
0.9999971389770508,
1.0,
1.0,
1.0,
0.9999998807907104,
1.0,
1.0,
1.0,
1.0,
0.9997872710227966,
1.0,
1.0,
1.0,
0.9998853206634521,
0.9965422749519348,
1.0,
1.0,
0.9999979734420776,
1.0,
0.9999878406524658,
0.9999878406524658,
0.9999140501022339,
0.9999234676361084,
0.9999630451202393,
0.9999982118606567,
1.0,
1.0,
0.9995156526565552,
0.9999998807907104,
0.9999997615814209,
0.9999996423721313,
1.0,
1.0,
1.0,
1.0,
0.9999949932098389,
0.9999933242797852,
0.9999910593032837,
0.9999983310699463,
1.0,
1.0,
0.9342825412750244,
1.0,
0.9998719692230225,
0.9999229907989502,
0.9999988079071045,
0.9999977350234985,
1.0,
1.0,
0.9999996423721313,
0.9999992847442627,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9999988079071045,
0.9999582767486572,
0.999998927116394,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9994237422943115,
0.9999994039535522,
1.0,
1.0,
0.9999977350234985,
1.0,
0.9998207688331604,
0.9999997615814209,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9999158382415771,
0.9968264102935791,
0.9999985694885254,
0.9999969005584717,
0.9999995231628418,
0.9999995231628418,
1.0,
0.9999986886978149,
0.9998912811279297,
0.9998600482940674,
0.9999988079071045,
1.0,
0.9999797344207764,
0.8468278646469116
],
"eval_code_low_quality_runtime": 38.4811,
"eval_code_low_quality_samples_per_second": 2.599,
"eval_code_low_quality_steps_per_second": 0.052,
"epoch": 2.63,
"step": 100
},
{
"eval_code_loss": 1.1787313222885132,
"eval_code_score": -0.31372034549713135,
"eval_code_brier_score": 0.31372034549713135,
"eval_code_average_probability": 0.5205222964286804,
"eval_code_accuracy": 0.61,
"eval_code_probabilities": [
0.00037343462463468313,
0.005696576554328203,
0.0029806813690811396,
0.7806524038314819,
0.9673417806625366,
0.7065327763557434,
0.5146356821060181,
0.8472678065299988,
0.47349339723587036,
0.5219644904136658,
0.5305175185203552,
0.5515053272247314,
0.46156707406044006,
0.6081150770187378,
0.32390114665031433,
0.5063720941543579,
0.44415482878685,
0.44942569732666016,
0.9759170413017273,
0.5840467214584351,
0.6595930457115173,
0.5098740458488464,
0.5081343650817871,
0.49616581201553345,
0.0029768662061542273,
0.002015285426750779,
0.0017812805017456412,
0.5042777061462402,
0.6546298861503601,
0.9300457239151001,
0.4243517518043518,
0.8517654538154602,
0.5293809771537781,
0.06185666099190712,
0.015204992145299911,
0.0212001521140337,
0.5635135173797607,
0.49610862135887146,
0.5277267694473267,
0.508770763874054,
0.8537895083427429,
0.23215477168560028,
0.5770038962364197,
0.7559729814529419,
0.6758078336715698,
0.43735623359680176,
0.8165058493614197,
0.741995096206665,
0.6506164073944092,
0.6589956879615784,
0.1663256138563156,
0.4853304922580719,
0.9941813349723816,
0.7592731714248657,
0.5826183557510376,
0.5224794745445251,
0.4846497178077698,
0.9794431328773499,
0.5740240216255188,
0.9839484095573425,
0.012579960748553276,
0.008771419525146484,
0.011818967759609222,
0.16271692514419556,
0.5130095481872559,
0.45814013481140137,
0.6292014122009277,
0.2866065204143524,
0.3463272154331207,
0.9270575046539307,
0.6034852266311646,
0.4980922341346741,
0.4166427254676819,
0.5456990599632263,
0.6291698217391968,
0.9999699592590332,
0.7315388321876526,
0.9999964237213135,
0.09563731402158737,
0.25322115421295166,
0.14264462888240814,
0.7902861833572388,
0.4692409634590149,
0.9958581328392029,
0.6111039519309998,
0.799086332321167,
0.9464629292488098,
0.998227059841156,
0.9346933960914612,
0.8618530631065369,
0.5354170203208923,
0.517333984375,
0.5421465635299683,
0.5469100475311279,
0.5029715895652771,
0.48473188281059265,
0.12127426266670227,
0.07449286431074142,
0.07441763579845428,
0.515086829662323
],
"eval_code_runtime": 36.6788,
"eval_code_samples_per_second": 2.726,
"eval_code_steps_per_second": 0.055,
"epoch": 2.63,
"step": 100
},
{
"train_runtime": 3664.8951,
"train_samples_per_second": 0.873,
"train_steps_per_second": 0.027,
"total_flos": 0.0,
"train_loss": 0.1413757397209065,
"epoch": 2.63,
"step": 100
}
]