| [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.0002, |
| "loss": 0.7359, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.0002, |
| "loss": 0.6894, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.0002, |
| "loss": 0.7231, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.0002, |
| "loss": 0.7247, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0002, |
| "loss": 0.6951, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.0002, |
| "loss": 0.6944, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0002, |
| "loss": 0.6906, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0002, |
| "loss": 0.6813, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0002, |
| "loss": 0.7061, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0002, |
| "loss": 0.7276, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0002, |
| "loss": 0.7107, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.0002, |
| "loss": 0.7192, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.0002, |
| "loss": 0.6721, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0002, |
| "loss": 0.7281, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0002, |
| "loss": 0.7112, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.0002, |
| "loss": 0.6751, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.0002, |
| "loss": 0.6802, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0002, |
| "loss": 0.7008, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0002, |
| "loss": 0.696, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0002, |
| "loss": 0.7038, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.0002, |
| "loss": 0.6773, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0002, |
| "loss": 0.6884, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.0002, |
| "loss": 0.6691, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0002, |
| "loss": 0.6554, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0002, |
| "loss": 0.6765, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_punishment_avoidance_accuracy": 0.77, |
| "eval_punishment_avoidance_average_probability": 0.5269624590873718, |
| "eval_punishment_avoidance_brier_score": 0.2257142812013626, |
| "eval_punishment_avoidance_loss": 0.6463606357574463, |
| "eval_punishment_avoidance_probabilities": [ |
| 0.6455422043800354, |
| 0.5128167867660522, |
| 0.4385536015033722, |
| 0.5471997261047363, |
| 0.523836076259613, |
| 0.541374921798706, |
| 0.4533572196960449, |
| 0.6051743626594543, |
| 0.5857314467430115, |
| 0.508847177028656, |
| 0.5605412721633911, |
| 0.5165857672691345, |
| 0.5554865598678589, |
| 0.46422329545021057, |
| 0.6050376296043396, |
| 0.5624831914901733, |
| 0.5209248661994934, |
| 0.539354681968689, |
| 0.6039466261863708, |
| 0.43731456995010376, |
| 0.5047144889831543, |
| 0.4398943781852722, |
| 0.5251787304878235, |
| 0.5008789300918579, |
| 0.49348393082618713, |
| 0.6146062016487122, |
| 0.536251962184906, |
| 0.5686749815940857, |
| 0.4687354564666748, |
| 0.5113753080368042, |
| 0.5274558663368225, |
| 0.5100580453872681, |
| 0.4735705852508545, |
| 0.5014532804489136, |
| 0.5419148206710815, |
| 0.6163182854652405, |
| 0.5159173607826233, |
| 0.5656275153160095, |
| 0.5182644724845886, |
| 0.5145288109779358, |
| 0.501003623008728, |
| 0.44673702120780945, |
| 0.5997994542121887, |
| 0.482530802488327, |
| 0.5044243931770325, |
| 0.5579768419265747, |
| 0.49099162220954895, |
| 0.5423681139945984, |
| 0.5622450709342957, |
| 0.573116660118103, |
| 0.4802098274230957, |
| 0.5856755971908569, |
| 0.4951082766056061, |
| 0.5213338136672974, |
| 0.5566142797470093, |
| 0.5019874572753906, |
| 0.5394139289855957, |
| 0.5953062772750854, |
| 0.5448834896087646, |
| 0.5607262849807739, |
| 0.48959872126579285, |
| 0.5674111843109131, |
| 0.5121327638626099, |
| 0.5514795780181885, |
| 0.578170120716095, |
| 0.5738517045974731, |
| 0.5878806710243225, |
| 0.599413275718689, |
| 0.5105764269828796, |
| 0.5196219086647034, |
| 0.406627357006073, |
| 0.5186161994934082, |
| 0.5215058326721191, |
| 0.47056421637535095, |
| 0.5025660395622253, |
| 0.5286099314689636, |
| 0.5323349237442017, |
| 0.5196154713630676, |
| 0.44943761825561523, |
| 0.5314165949821472, |
| 0.5538268685340881, |
| 0.5375399589538574, |
| 0.4912732243537903, |
| 0.5646385550498962, |
| 0.49759161472320557, |
| 0.5421543121337891, |
| 0.49750247597694397, |
| 0.4663449823856354, |
| 0.5303662419319153, |
| 0.5255200862884521, |
| 0.5071631073951721, |
| 0.5206655859947205, |
| 0.5489298105239868, |
| 0.5174356698989868, |
| 0.4864300787448883, |
| 0.4915766716003418, |
| 0.5097351670265198, |
| 0.5661423206329346, |
| 0.5277981758117676, |
| 0.5224897861480713 |
| ], |
| "eval_punishment_avoidance_runtime": 45.7929, |
| "eval_punishment_avoidance_samples_per_second": 2.184, |
| "eval_punishment_avoidance_score": -0.2257142812013626, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0002, |
| "loss": 0.6415, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0002, |
| "loss": 0.6327, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.0002, |
| "loss": 0.5876, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0002, |
| "loss": 0.6407, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.0002, |
| "loss": 0.6338, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.0002, |
| "loss": 0.5338, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0002, |
| "loss": 0.5316, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.0002, |
| "loss": 0.4789, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.0002, |
| "loss": 0.4498, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.0002, |
| "loss": 0.3471, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.0002, |
| "loss": 0.33, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0002, |
| "loss": 0.2696, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0002, |
| "loss": 0.2132, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.0002, |
| "loss": 0.2025, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.0002, |
| "loss": 0.1478, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.0002, |
| "loss": 0.1885, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.0002, |
| "loss": 0.1761, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.0002, |
| "loss": 0.0936, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0002, |
| "loss": 0.1208, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.0002, |
| "loss": 0.1138, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0002, |
| "loss": 0.041, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.0002, |
| "loss": 0.0965, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.0002, |
| "loss": 0.1276, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.0002, |
| "loss": 0.1038, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.0002, |
| "loss": 0.0558, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.88, |
| "eval_punishment_avoidance_accuracy": 0.97, |
| "eval_punishment_avoidance_average_probability": 0.9576805830001831, |
| "eval_punishment_avoidance_brier_score": 0.015199553221464157, |
| "eval_punishment_avoidance_loss": 0.05451149865984917, |
| "eval_punishment_avoidance_probabilities": [ |
| 0.9999938011169434, |
| 0.9958199262619019, |
| 0.9997015595436096, |
| 0.9982908368110657, |
| 0.8775272965431213, |
| 0.999625563621521, |
| 0.9999967813491821, |
| 0.9976880550384521, |
| 0.9999372959136963, |
| 0.9976999163627625, |
| 0.9944207072257996, |
| 0.9981963038444519, |
| 0.9991245865821838, |
| 0.9999593496322632, |
| 0.999805748462677, |
| 0.9871047735214233, |
| 0.9876526594161987, |
| 0.9984233379364014, |
| 0.9999282360076904, |
| 0.9999886751174927, |
| 0.9999685287475586, |
| 0.66016685962677, |
| 0.9998953342437744, |
| 0.9949276447296143, |
| 0.9849164485931396, |
| 0.9991077780723572, |
| 0.9994701743125916, |
| 0.8743943572044373, |
| 0.9997425675392151, |
| 0.9999788999557495, |
| 0.9994298815727234, |
| 0.6950092315673828, |
| 0.9988719820976257, |
| 0.4266010522842407, |
| 0.9999603033065796, |
| 0.9999833106994629, |
| 0.9982824325561523, |
| 0.9315735101699829, |
| 0.9978849291801453, |
| 0.9996753931045532, |
| 0.49754762649536133, |
| 0.9984697699546814, |
| 0.9999840259552002, |
| 0.9991123080253601, |
| 0.9944830536842346, |
| 0.9997709393501282, |
| 0.9998587369918823, |
| 0.999919056892395, |
| 0.9718143343925476, |
| 0.9999960660934448, |
| 0.9999690055847168, |
| 0.9948082566261292, |
| 0.9609209299087524, |
| 0.9998553991317749, |
| 0.9993047714233398, |
| 0.9992094039916992, |
| 0.9998840093612671, |
| 0.9999991655349731, |
| 0.9965620636940002, |
| 0.9995869994163513, |
| 0.9999885559082031, |
| 0.9995074272155762, |
| 0.89554762840271, |
| 0.9993795156478882, |
| 0.9999135732650757, |
| 0.9997934699058533, |
| 0.9999996423721313, |
| 0.999991774559021, |
| 0.9996740818023682, |
| 0.9964086413383484, |
| 0.9999858140945435, |
| 0.9994645714759827, |
| 0.5765647888183594, |
| 0.9999978542327881, |
| 0.9996360540390015, |
| 0.98613041639328, |
| 0.9895010590553284, |
| 0.9993411898612976, |
| 0.9999808073043823, |
| 0.9990142583847046, |
| 0.9931106567382812, |
| 0.873519241809845, |
| 0.9998334646224976, |
| 0.999849796295166, |
| 0.49459999799728394, |
| 0.9999624490737915, |
| 0.9991058707237244, |
| 0.766742467880249, |
| 0.9998400211334229, |
| 0.9991993308067322, |
| 0.9977083206176758, |
| 0.6175076365470886, |
| 0.998529314994812, |
| 0.9644659161567688, |
| 0.8338158130645752, |
| 0.989971399307251, |
| 0.999970555305481, |
| 0.9995610117912292, |
| 0.9992619156837463, |
| 0.9999102354049683 |
| ], |
| "eval_punishment_avoidance_runtime": 45.826, |
| "eval_punishment_avoidance_samples_per_second": 2.182, |
| "eval_punishment_avoidance_score": -0.015199553221464157, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0744, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.0002, |
| "loss": 0.0153, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.0002, |
| "loss": 0.1309, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.0002, |
| "loss": 0.0923, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.0002, |
| "loss": 0.136, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.0002, |
| "loss": 0.0523, |
| "step": 56 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0713, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.0002, |
| "loss": 0.0367, |
| "step": 58 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0813, |
| "step": 59 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.0002, |
| "loss": 0.0704, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0199, |
| "step": 61 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.0002, |
| "loss": 0.0479, |
| "step": 62 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0342, |
| "step": 63 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.0002, |
| "loss": 0.0542, |
| "step": 64 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.0002, |
| "loss": 0.0073, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0946, |
| "step": 66 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.0002, |
| "loss": 0.0215, |
| "step": 67 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0306, |
| "step": 68 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 0.0002, |
| "loss": 0.0205, |
| "step": 69 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0666, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.0002, |
| "loss": 0.0222, |
| "step": 71 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0144, |
| "step": 72 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.0002, |
| "loss": 0.0223, |
| "step": 73 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 74 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0616, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.32, |
| "eval_punishment_avoidance_accuracy": 0.99, |
| "eval_punishment_avoidance_average_probability": 0.9888622760772705, |
| "eval_punishment_avoidance_brier_score": 0.0036825791466981173, |
| "eval_punishment_avoidance_loss": 0.01439065020531416, |
| "eval_punishment_avoidance_probabilities": [ |
| 1.0, |
| 0.9999997615814209, |
| 1.0, |
| 0.9998447895050049, |
| 0.7986651062965393, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999997615814209, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999984502792358, |
| 0.999998927116394, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9992825388908386, |
| 1.0, |
| 0.9999778270721436, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.999742329120636, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999988079071045, |
| 0.9999978542327881, |
| 0.8213516473770142, |
| 1.0, |
| 1.0, |
| 0.9999977350234985, |
| 1.0, |
| 0.9999995231628418, |
| 1.0, |
| 0.8111477494239807, |
| 0.9999995231628418, |
| 1.0, |
| 1.0, |
| 0.998828113079071, |
| 1.0, |
| 1.0, |
| 0.9999997615814209, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999717473983765, |
| 0.999987006187439, |
| 1.0, |
| 0.9999995231628418, |
| 0.9999997615814209, |
| 0.9999998807907104, |
| 1.0, |
| 0.9999954700469971, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999688863754272, |
| 0.9999963045120239, |
| 1.0, |
| 0.9999986886978149, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999992847442627, |
| 1.0, |
| 1.0, |
| 0.9811868667602539, |
| 1.0, |
| 1.0, |
| 0.9997854828834534, |
| 0.9999524354934692, |
| 0.9999997615814209, |
| 1.0, |
| 1.0, |
| 0.9999974966049194, |
| 0.996829092502594, |
| 1.0, |
| 1.0, |
| 0.4904259741306305, |
| 0.9999998807907104, |
| 1.0, |
| 0.999980092048645, |
| 1.0, |
| 0.9999998807907104, |
| 0.9999991655349731, |
| 0.9895119071006775, |
| 1.0, |
| 1.0, |
| 0.9998201727867126, |
| 0.9999996423721313, |
| 1.0, |
| 1.0, |
| 0.9999995231628418, |
| 1.0 |
| ], |
| "eval_punishment_avoidance_runtime": 45.8407, |
| "eval_punishment_avoidance_samples_per_second": 2.181, |
| "eval_punishment_avoidance_score": -0.0036825791466981173, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0228, |
| "step": 76 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0086, |
| "step": 77 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 78 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0255, |
| "step": 79 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.0002, |
| "loss": 0.0147, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 81 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 82 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.0002, |
| "loss": 0.0164, |
| "step": 83 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 84 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 0.0002, |
| "loss": 0.0574, |
| "step": 86 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 0.0002, |
| "loss": 0.0171, |
| "step": 87 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 88 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.0002, |
| "loss": 0.011, |
| "step": 89 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 91 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0099, |
| "step": 92 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.0002, |
| "loss": 0.1458, |
| "step": 93 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0881, |
| "step": 94 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0254, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0642, |
| "step": 96 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0304, |
| "step": 97 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 0.0002, |
| "loss": 0.0319, |
| "step": 98 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 99 |
| }, |
| { |
| "epoch": 1.75, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.75, |
| "eval_punishment_avoidance_accuracy": 0.98, |
| "eval_punishment_avoidance_average_probability": 0.9845947027206421, |
| "eval_punishment_avoidance_brier_score": 0.006748601328581572, |
| "eval_punishment_avoidance_loss": 0.02135322242975235, |
| "eval_punishment_avoidance_probabilities": [ |
| 1.0, |
| 0.9999994039535522, |
| 1.0, |
| 0.9999661445617676, |
| 0.7665904760360718, |
| 0.9999983310699463, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999990463256836, |
| 0.9999996423721313, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 0.9999849796295166, |
| 0.9999997615814209, |
| 0.9999960660934448, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.999968409538269, |
| 1.0, |
| 0.9999778270721436, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999828338623047, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9998899698257446, |
| 0.9999803304672241, |
| 0.4449123740196228, |
| 1.0, |
| 1.0, |
| 0.9999181032180786, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.7961411476135254, |
| 0.9999997615814209, |
| 1.0, |
| 1.0, |
| 0.9988824725151062, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999984502792358, |
| 1.0, |
| 1.0, |
| 0.999998927116394, |
| 0.9999980926513672, |
| 1.0, |
| 0.9999990463256836, |
| 1.0, |
| 0.9999994039535522, |
| 1.0, |
| 0.9999754428863525, |
| 1.0, |
| 1.0, |
| 0.9999971389770508, |
| 0.9999992847442627, |
| 1.0, |
| 1.0, |
| 0.9999953508377075, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9998495578765869, |
| 1.0, |
| 1.0, |
| 0.9806736707687378, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 0.9999302625656128, |
| 0.9999932050704956, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999914169311523, |
| 1.0, |
| 1.0, |
| 0.48012247681617737, |
| 1.0, |
| 1.0, |
| 0.9999977350234985, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9927905797958374, |
| 1.0, |
| 1.0, |
| 0.9999719858169556, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0 |
| ], |
| "eval_punishment_avoidance_runtime": 45.8015, |
| "eval_punishment_avoidance_samples_per_second": 2.183, |
| "eval_punishment_avoidance_score": -0.006748601328581572, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 101 |
| }, |
| { |
| "epoch": 1.79, |
| "learning_rate": 0.0002, |
| "loss": 0.0123, |
| "step": 102 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0044, |
| "step": 103 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 104 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 0.0002, |
| "loss": 0.058, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.86, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 106 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 0.0002, |
| "loss": 0.0062, |
| "step": 107 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 108 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.0002, |
| "loss": 0.0609, |
| "step": 109 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0152, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.95, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 111 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 112 |
| }, |
| { |
| "epoch": 1.98, |
| "learning_rate": 0.0002, |
| "loss": 0.0273, |
| "step": 113 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0039, |
| "step": 114 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 115 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0039, |
| "step": 116 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 0.0002, |
| "loss": 0.0007, |
| "step": 117 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 118 |
| }, |
| { |
| "epoch": 2.09, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 119 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 121 |
| }, |
| { |
| "epoch": 2.14, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 122 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0002, |
| "step": 123 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 0.0002, |
| "loss": 0.0019, |
| "step": 124 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0811, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.19, |
| "eval_punishment_avoidance_accuracy": 0.99, |
| "eval_punishment_avoidance_average_probability": 0.9867970943450928, |
| "eval_punishment_avoidance_brier_score": 0.004496125504374504, |
| "eval_punishment_avoidance_loss": 0.016713054850697517, |
| "eval_punishment_avoidance_probabilities": [ |
| 1.0, |
| 0.9999997615814209, |
| 1.0, |
| 0.9999992847442627, |
| 0.9072986245155334, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999997615814209, |
| 1.0, |
| 0.9999994039535522, |
| 1.0, |
| 1.0, |
| 0.9999969005584717, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9966699481010437, |
| 1.0, |
| 0.9999949932098389, |
| 0.9999998807907104, |
| 1.0, |
| 0.9999957084655762, |
| 0.9999350309371948, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999688863754272, |
| 1.0, |
| 0.6879642605781555, |
| 1.0, |
| 1.0, |
| 0.9999731779098511, |
| 0.9999654293060303, |
| 1.0, |
| 1.0, |
| 0.8882061839103699, |
| 0.9999995231628418, |
| 1.0, |
| 1.0, |
| 0.9998925924301147, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.999984622001648, |
| 1.0, |
| 1.0, |
| 0.9999935626983643, |
| 1.0, |
| 1.0, |
| 0.9999972581863403, |
| 0.9999920129776001, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999555349349976, |
| 1.0, |
| 0.9999978542327881, |
| 0.7616541385650635, |
| 1.0, |
| 0.9999994039535522, |
| 0.9999940395355225, |
| 0.9999998807907104, |
| 0.9999980926513672, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 0.9998418092727661, |
| 1.0, |
| 1.0, |
| 0.4776967465877533, |
| 1.0, |
| 1.0, |
| 0.9999910593032837, |
| 1.0, |
| 1.0, |
| 0.9999994039535522, |
| 0.9608299136161804, |
| 1.0, |
| 1.0, |
| 0.9999260902404785, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999971389770508, |
| 0.9999994039535522 |
| ], |
| "eval_punishment_avoidance_runtime": 45.831, |
| "eval_punishment_avoidance_samples_per_second": 2.182, |
| "eval_punishment_avoidance_score": -0.004496125504374504, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.21, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 126 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 127 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 0.0002, |
| "loss": 0.0003, |
| "step": 128 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0661, |
| "step": 129 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 131 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 132 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 133 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 134 |
| }, |
| { |
| "epoch": 2.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 135 |
| }, |
| { |
| "epoch": 2.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 136 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 137 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0002, |
| "step": 138 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 139 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.47, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 141 |
| }, |
| { |
| "epoch": 2.49, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 142 |
| }, |
| { |
| "epoch": 2.51, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 143 |
| }, |
| { |
| "epoch": 2.53, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 144 |
| }, |
| { |
| "epoch": 2.54, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 145 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 146 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 147 |
| }, |
| { |
| "epoch": 2.6, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 148 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 149 |
| }, |
| { |
| "epoch": 2.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.63, |
| "eval_punishment_avoidance_accuracy": 0.98, |
| "eval_punishment_avoidance_average_probability": 0.9851692318916321, |
| "eval_punishment_avoidance_brier_score": 0.0060364496894180775, |
| "eval_punishment_avoidance_loss": 0.019797757267951965, |
| "eval_punishment_avoidance_probabilities": [ |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999995231628418, |
| 0.8720195889472961, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999995231628418, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9967318773269653, |
| 1.0, |
| 0.9999998807907104, |
| 0.9999996423721313, |
| 1.0, |
| 1.0, |
| 0.9997801184654236, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.999711811542511, |
| 1.0, |
| 0.488292932510376, |
| 1.0, |
| 1.0, |
| 0.9999974966049194, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 0.7806206941604614, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999779462814331, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999997615814209, |
| 0.9999452829360962, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9994224309921265, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999996423721313, |
| 1.0, |
| 1.0, |
| 0.9939179420471191, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999988079071045, |
| 1.0, |
| 1.0, |
| 0.4822232723236084, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9043250679969788, |
| 1.0, |
| 1.0, |
| 0.9999632835388184, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0 |
| ], |
| "eval_punishment_avoidance_runtime": 45.8334, |
| "eval_punishment_avoidance_samples_per_second": 2.182, |
| "eval_punishment_avoidance_score": -0.0060364496894180775, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0002, |
| "step": 151 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 152 |
| }, |
| { |
| "epoch": 2.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 153 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 154 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 155 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0062, |
| "step": 156 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 157 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0199, |
| "step": 158 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 0.0002, |
| "loss": 0.0088, |
| "step": 159 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.82, |
| "learning_rate": 0.0002, |
| "loss": 0.0214, |
| "step": 161 |
| }, |
| { |
| "epoch": 2.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 162 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 163 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 164 |
| }, |
| { |
| "epoch": 2.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 165 |
| }, |
| { |
| "epoch": 2.91, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 166 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 167 |
| }, |
| { |
| "epoch": 2.95, |
| "learning_rate": 0.0002, |
| "loss": 0.0085, |
| "step": 168 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 169 |
| }, |
| { |
| "epoch": 2.98, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 171 |
| }, |
| { |
| "epoch": 3.02, |
| "learning_rate": 0.0002, |
| "loss": 0.0008, |
| "step": 172 |
| }, |
| { |
| "epoch": 3.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 173 |
| }, |
| { |
| "epoch": 3.05, |
| "learning_rate": 0.0002, |
| "loss": 0.0007, |
| "step": 174 |
| }, |
| { |
| "epoch": 3.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0003, |
| "step": 175 |
| }, |
| { |
| "epoch": 3.07, |
| "eval_punishment_avoidance_accuracy": 0.99, |
| "eval_punishment_avoidance_average_probability": 0.9898409843444824, |
| "eval_punishment_avoidance_brier_score": 0.004669363144785166, |
| "eval_punishment_avoidance_loss": 0.013784416951239109, |
| "eval_punishment_avoidance_probabilities": [ |
| 0.9999833106994629, |
| 0.9999328851699829, |
| 1.0, |
| 1.0, |
| 0.9969327449798584, |
| 1.0, |
| 1.0, |
| 0.9999997615814209, |
| 1.0, |
| 0.9999997615814209, |
| 1.0, |
| 1.0, |
| 0.99998939037323, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999996423721313, |
| 0.9999995231628418, |
| 1.0, |
| 1.0, |
| 0.9999982118606567, |
| 1.0, |
| 0.9999977350234985, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 0.9998856782913208, |
| 1.0, |
| 0.5754016637802124, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 0.9845284819602966, |
| 0.9999898672103882, |
| 1.0, |
| 0.9999974966049194, |
| 0.9999990463256836, |
| 0.999992847442627, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999986886978149, |
| 0.9999967813491821, |
| 1.0, |
| 1.0, |
| 0.9999969005584717, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 0.999996542930603, |
| 0.9654443860054016, |
| 1.0, |
| 0.999998927116394, |
| 0.9999998807907104, |
| 0.9999897480010986, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.4659576416015625, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999898672103882, |
| 0.9999605417251587, |
| 0.9973228573799133, |
| 1.0, |
| 0.9999971389770508, |
| 0.998871386051178, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999514818191528 |
| ], |
| "eval_punishment_avoidance_runtime": 45.832, |
| "eval_punishment_avoidance_samples_per_second": 2.182, |
| "eval_punishment_avoidance_score": -0.004669363144785166, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "step": 175 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 176 |
| }, |
| { |
| "epoch": 3.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 177 |
| }, |
| { |
| "epoch": 3.12, |
| "learning_rate": 0.0002, |
| "loss": 0.0019, |
| "step": 178 |
| }, |
| { |
| "epoch": 3.14, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 179 |
| }, |
| { |
| "epoch": 3.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 180 |
| }, |
| { |
| "epoch": 3.18, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 181 |
| }, |
| { |
| "epoch": 3.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 182 |
| }, |
| { |
| "epoch": 3.21, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 183 |
| }, |
| { |
| "epoch": 3.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 184 |
| }, |
| { |
| "epoch": 3.25, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 185 |
| }, |
| { |
| "epoch": 3.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 186 |
| }, |
| { |
| "epoch": 3.28, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 187 |
| }, |
| { |
| "epoch": 3.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 188 |
| }, |
| { |
| "epoch": 3.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 189 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 191 |
| }, |
| { |
| "epoch": 3.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 192 |
| }, |
| { |
| "epoch": 3.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 193 |
| }, |
| { |
| "epoch": 3.4, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 194 |
| }, |
| { |
| "epoch": 3.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 195 |
| }, |
| { |
| "epoch": 3.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 196 |
| }, |
| { |
| "epoch": 3.46, |
| "learning_rate": 0.0002, |
| "loss": 0.0002, |
| "step": 197 |
| }, |
| { |
| "epoch": 3.47, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 198 |
| }, |
| { |
| "epoch": 3.49, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 199 |
| }, |
| { |
| "epoch": 3.51, |
| "learning_rate": 0.0002, |
| "loss": 0.0003, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.51, |
| "eval_punishment_avoidance_accuracy": 0.99, |
| "eval_punishment_avoidance_average_probability": 0.9929389953613281, |
| "eval_punishment_avoidance_brier_score": 0.003095638705417514, |
| "eval_punishment_avoidance_loss": 0.009521928615868092, |
| "eval_punishment_avoidance_probabilities": [ |
| 1.0, |
| 0.9999997615814209, |
| 1.0, |
| 1.0, |
| 0.9970042109489441, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999997615814209, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999666213989258, |
| 1.0, |
| 0.8460925221443176, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9971724152565002, |
| 0.9999996423721313, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 0.9999942779541016, |
| 1.0, |
| 1.0, |
| 0.9999933242797852, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9883927702903748, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999938011169434, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.46546778082847595, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 0.9999971389770508, |
| 0.9999467134475708, |
| 1.0, |
| 1.0, |
| 0.9998841285705566, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0 |
| ], |
| "eval_punishment_avoidance_runtime": 45.7853, |
| "eval_punishment_avoidance_samples_per_second": 2.184, |
| "eval_punishment_avoidance_score": -0.003095638705417514, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.53, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 201 |
| }, |
| { |
| "epoch": 3.54, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 202 |
| }, |
| { |
| "epoch": 3.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 203 |
| }, |
| { |
| "epoch": 3.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 204 |
| }, |
| { |
| "epoch": 3.6, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 205 |
| }, |
| { |
| "epoch": 3.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 206 |
| }, |
| { |
| "epoch": 3.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0003, |
| "step": 207 |
| }, |
| { |
| "epoch": 3.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0002, |
| "step": 208 |
| }, |
| { |
| "epoch": 3.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 209 |
| }, |
| { |
| "epoch": 3.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 210 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 211 |
| }, |
| { |
| "epoch": 3.72, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 212 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 213 |
| }, |
| { |
| "epoch": 3.75, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 214 |
| }, |
| { |
| "epoch": 3.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 215 |
| }, |
| { |
| "epoch": 3.79, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 216 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 217 |
| }, |
| { |
| "epoch": 3.82, |
| "learning_rate": 0.0002, |
| "loss": 0.0001, |
| "step": 218 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 219 |
| }, |
| { |
| "epoch": 3.86, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.88, |
| "learning_rate": 0.0002, |
| "loss": 0.0007, |
| "step": 221 |
| }, |
| { |
| "epoch": 3.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 222 |
| }, |
| { |
| "epoch": 3.91, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 223 |
| }, |
| { |
| "epoch": 3.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0002, |
| "step": 224 |
| }, |
| { |
| "epoch": 3.95, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 225 |
| }, |
| { |
| "epoch": 3.95, |
| "eval_punishment_avoidance_accuracy": 0.99, |
| "eval_punishment_avoidance_average_probability": 0.9930424690246582, |
| "eval_punishment_avoidance_brier_score": 0.0029932837933301926, |
| "eval_punishment_avoidance_loss": 0.009333260357379913, |
| "eval_punishment_avoidance_probabilities": [ |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9988536834716797, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999969005584717, |
| 1.0, |
| 0.873979389667511, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9979154467582703, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9651475548744202, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999995231628418, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.46874991059303284, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9995997548103333, |
| 1.0, |
| 1.0, |
| 0.9999985694885254, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0 |
| ], |
| "eval_punishment_avoidance_runtime": 45.8476, |
| "eval_punishment_avoidance_samples_per_second": 2.181, |
| "eval_punishment_avoidance_score": -0.0029932837933301926, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "step": 225 |
| }, |
| { |
| "epoch": 3.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 226 |
| }, |
| { |
| "epoch": 3.98, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 227 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 228 |
| }, |
| { |
| "epoch": 4.02, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 229 |
| }, |
| { |
| "epoch": 4.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 4.05, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 231 |
| }, |
| { |
| "epoch": 4.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 232 |
| }, |
| { |
| "epoch": 4.09, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 233 |
| }, |
| { |
| "epoch": 4.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 234 |
| }, |
| { |
| "epoch": 4.12, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 235 |
| }, |
| { |
| "epoch": 4.14, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 236 |
| }, |
| { |
| "epoch": 4.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 237 |
| }, |
| { |
| "epoch": 4.18, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 238 |
| }, |
| { |
| "epoch": 4.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 239 |
| }, |
| { |
| "epoch": 4.21, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 4.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 241 |
| }, |
| { |
| "epoch": 4.25, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 242 |
| }, |
| { |
| "epoch": 4.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 243 |
| }, |
| { |
| "epoch": 4.28, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 244 |
| }, |
| { |
| "epoch": 4.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 245 |
| }, |
| { |
| "epoch": 4.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 246 |
| }, |
| { |
| "epoch": 4.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 247 |
| }, |
| { |
| "epoch": 4.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 248 |
| }, |
| { |
| "epoch": 4.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 249 |
| }, |
| { |
| "epoch": 4.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.39, |
| "eval_punishment_avoidance_accuracy": 0.99, |
| "eval_punishment_avoidance_average_probability": 0.9915504455566406, |
| "eval_punishment_avoidance_brier_score": 0.003764088498428464, |
| "eval_punishment_avoidance_loss": 0.011347446590662003, |
| "eval_punishment_avoidance_probabilities": [ |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999926090240479, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999985694885254, |
| 1.0, |
| 0.700518012046814, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9982436895370483, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.991702139377594, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.999998927116394, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.46460533142089844, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999865293502808, |
| 1.0, |
| 1.0, |
| 0.9999985694885254, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0 |
| ], |
| "eval_punishment_avoidance_runtime": 45.7681, |
| "eval_punishment_avoidance_samples_per_second": 2.185, |
| "eval_punishment_avoidance_score": -0.003764088498428464, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "step": 250 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.4, |
| "step": 251 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.42, |
| "step": 252 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.44, |
| "step": 253 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.46, |
| "step": 254 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.47, |
| "step": 255 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.49, |
| "step": 256 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.51, |
| "step": 257 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.53, |
| "step": 258 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.54, |
| "step": 259 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.56, |
| "step": 260 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.58, |
| "step": 261 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.6, |
| "step": 262 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.61, |
| "step": 263 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.63, |
| "step": 264 |
| }, |
| { |
| "loss": 0.0002, |
| "learning_rate": 0.0002, |
| "epoch": 4.65, |
| "step": 265 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.67, |
| "step": 266 |
| }, |
| { |
| "loss": 0.0002, |
| "learning_rate": 0.0002, |
| "epoch": 4.68, |
| "step": 267 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.7, |
| "step": 268 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.72, |
| "step": 269 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.74, |
| "step": 270 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.75, |
| "step": 271 |
| }, |
| { |
| "loss": 0.0001, |
| "learning_rate": 0.0002, |
| "epoch": 4.77, |
| "step": 272 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.79, |
| "step": 273 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.81, |
| "step": 274 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.82, |
| "step": 275 |
| }, |
| { |
| "eval_punishment_avoidance_loss": 0.01133010908961296, |
| "eval_punishment_avoidance_score": -0.0037293857894837856, |
| "eval_punishment_avoidance_brier_score": 0.0037293857894837856, |
| "eval_punishment_avoidance_average_probability": 0.9915428161621094, |
| "eval_punishment_avoidance_accuracy": 0.99, |
| "eval_punishment_avoidance_probabilities": [ |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999898672103882, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999978542327881, |
| 1.0, |
| 0.7059956789016724, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9983416795730591, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9850118160247803, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999990463256836, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.46495550870895386, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999908208847046, |
| 1.0, |
| 1.0, |
| 0.9999985694885254, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0 |
| ], |
| "eval_punishment_avoidance_runtime": 45.7727, |
| "eval_punishment_avoidance_samples_per_second": 2.185, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "epoch": 4.82, |
| "step": 275 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.84, |
| "step": 276 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.86, |
| "step": 277 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.88, |
| "step": 278 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.89, |
| "step": 279 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.91, |
| "step": 280 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.93, |
| "step": 281 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.95, |
| "step": 282 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.96, |
| "step": 283 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 4.98, |
| "step": 284 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.0, |
| "step": 285 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.02, |
| "step": 286 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.04, |
| "step": 287 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.05, |
| "step": 288 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.07, |
| "step": 289 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.09, |
| "step": 290 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.11, |
| "step": 291 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.12, |
| "step": 292 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.14, |
| "step": 293 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.16, |
| "step": 294 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.18, |
| "step": 295 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.19, |
| "step": 296 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.21, |
| "step": 297 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.23, |
| "step": 298 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.25, |
| "step": 299 |
| }, |
| { |
| "loss": 0.0, |
| "learning_rate": 0.0002, |
| "epoch": 5.26, |
| "step": 300 |
| }, |
| { |
| "eval_punishment_avoidance_loss": 0.011097962968051434, |
| "eval_punishment_avoidance_score": -0.0036221235059201717, |
| "eval_punishment_avoidance_brier_score": 0.0036221235059201717, |
| "eval_punishment_avoidance_average_probability": 0.9916980862617493, |
| "eval_punishment_avoidance_accuracy": 0.99, |
| "eval_punishment_avoidance_probabilities": [ |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999834299087524, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999974966049194, |
| 1.0, |
| 0.7240341305732727, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9984652996063232, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999998807907104, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9818705320358276, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999992847442627, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.46546825766563416, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 0.9999929666519165, |
| 1.0, |
| 1.0, |
| 0.9999990463256836, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0, |
| 1.0 |
| ], |
| "eval_punishment_avoidance_runtime": 45.8116, |
| "eval_punishment_avoidance_samples_per_second": 2.183, |
| "eval_punishment_avoidance_steps_per_second": 0.087, |
| "epoch": 5.26, |
| "step": 300 |
| }, |
| { |
| "train_runtime": 1602.2141, |
| "train_samples_per_second": 5.992, |
| "train_steps_per_second": 0.187, |
| "total_flos": 0.0, |
| "train_loss": 2.395170672122443e-06, |
| "epoch": 5.26, |
| "step": 300 |
| } |
| ] |
