| { | |
| "best_metric": 0.4731843173503876, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-250", | |
| "epoch": 1.5268161434977578, | |
| "eval_steps": 25, | |
| "global_step": 266, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005739910313901345, | |
| "grad_norm": 0.2956002354621887, | |
| "learning_rate": 2e-05, | |
| "loss": 1.12, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005739910313901345, | |
| "eval_loss": 1.7397924661636353, | |
| "eval_runtime": 0.9426, | |
| "eval_samples_per_second": 53.046, | |
| "eval_steps_per_second": 13.792, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01147982062780269, | |
| "grad_norm": 0.43654918670654297, | |
| "learning_rate": 4e-05, | |
| "loss": 1.598, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017219730941704037, | |
| "grad_norm": 0.5595598220825195, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5995, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02295964125560538, | |
| "grad_norm": 0.5066915154457092, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5276, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.028699551569506727, | |
| "grad_norm": 0.6286351084709167, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5622, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03443946188340807, | |
| "grad_norm": 0.6938809156417847, | |
| "learning_rate": 0.00012, | |
| "loss": 1.538, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04017937219730942, | |
| "grad_norm": 0.7844440340995789, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5416, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04591928251121076, | |
| "grad_norm": 0.7578993439674377, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5058, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05165919282511211, | |
| "grad_norm": 0.7300332188606262, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5009, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05739910313901345, | |
| "grad_norm": 0.7704319953918457, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4593, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0631390134529148, | |
| "grad_norm": 1.1217689514160156, | |
| "learning_rate": 0.00019999322316552302, | |
| "loss": 1.4246, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06887892376681615, | |
| "grad_norm": 1.324763536453247, | |
| "learning_rate": 0.0001999728936826584, | |
| "loss": 1.4849, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07461883408071748, | |
| "grad_norm": 0.5333749055862427, | |
| "learning_rate": 0.00019993901461295147, | |
| "loss": 0.6922, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08035874439461883, | |
| "grad_norm": 1.0703330039978027, | |
| "learning_rate": 0.00019989159105846555, | |
| "loss": 1.0634, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08609865470852018, | |
| "grad_norm": 0.8238877654075623, | |
| "learning_rate": 0.00019983063016101342, | |
| "loss": 1.0134, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09183856502242152, | |
| "grad_norm": 0.5358161330223083, | |
| "learning_rate": 0.00019975614110108212, | |
| "loss": 0.9468, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09757847533632287, | |
| "grad_norm": 0.4043968617916107, | |
| "learning_rate": 0.00019966813509645002, | |
| "loss": 0.9086, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10331838565022422, | |
| "grad_norm": 0.4523843228816986, | |
| "learning_rate": 0.00019956662540049773, | |
| "loss": 0.9095, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10905829596412556, | |
| "grad_norm": 0.4627666771411896, | |
| "learning_rate": 0.00019945162730021209, | |
| "loss": 0.894, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1147982062780269, | |
| "grad_norm": 0.4633651673793793, | |
| "learning_rate": 0.0001993231581138839, | |
| "loss": 0.8746, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12053811659192826, | |
| "grad_norm": 0.4129200279712677, | |
| "learning_rate": 0.0001991812371885002, | |
| "loss": 0.8828, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1262780269058296, | |
| "grad_norm": 0.394033282995224, | |
| "learning_rate": 0.0001990258858968303, | |
| "loss": 0.8767, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13201793721973093, | |
| "grad_norm": 0.39186373353004456, | |
| "learning_rate": 0.00019885712763420728, | |
| "loss": 0.8641, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1377578475336323, | |
| "grad_norm": 0.4424944221973419, | |
| "learning_rate": 0.0001986749878150047, | |
| "loss": 0.8931, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14349775784753363, | |
| "grad_norm": 0.6562401652336121, | |
| "learning_rate": 0.00019847949386880948, | |
| "loss": 0.926, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14349775784753363, | |
| "eval_loss": 0.7843173742294312, | |
| "eval_runtime": 0.9216, | |
| "eval_samples_per_second": 54.254, | |
| "eval_steps_per_second": 14.106, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14923766816143497, | |
| "grad_norm": 0.375760942697525, | |
| "learning_rate": 0.00019827067523629075, | |
| "loss": 0.5227, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.15497757847533633, | |
| "grad_norm": 0.6195258498191833, | |
| "learning_rate": 0.0001980485633647665, | |
| "loss": 0.8541, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16071748878923767, | |
| "grad_norm": 0.5944555401802063, | |
| "learning_rate": 0.00019781319170346758, | |
| "loss": 0.8391, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.166457399103139, | |
| "grad_norm": 0.49085184931755066, | |
| "learning_rate": 0.00019756459569850044, | |
| "loss": 0.7846, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.17219730941704037, | |
| "grad_norm": 0.4676542580127716, | |
| "learning_rate": 0.00019730281278750898, | |
| "loss": 0.7784, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1779372197309417, | |
| "grad_norm": 0.41902828216552734, | |
| "learning_rate": 0.0001970278823940367, | |
| "loss": 0.746, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.18367713004484304, | |
| "grad_norm": 0.35981717705726624, | |
| "learning_rate": 0.0001967398459215896, | |
| "loss": 0.7416, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1894170403587444, | |
| "grad_norm": 0.36896347999572754, | |
| "learning_rate": 0.00019643874674740093, | |
| "loss": 0.7621, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19515695067264574, | |
| "grad_norm": 0.4268818497657776, | |
| "learning_rate": 0.0001961246302158988, | |
| "loss": 0.7631, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.20089686098654708, | |
| "grad_norm": 0.4003854990005493, | |
| "learning_rate": 0.00019579754363187747, | |
| "loss": 0.7616, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.20663677130044844, | |
| "grad_norm": 0.3968479037284851, | |
| "learning_rate": 0.0001954575362533733, | |
| "loss": 0.7288, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.21237668161434978, | |
| "grad_norm": 0.4149373471736908, | |
| "learning_rate": 0.0001951046592842469, | |
| "loss": 0.7176, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2181165919282511, | |
| "grad_norm": 0.1808343082666397, | |
| "learning_rate": 0.00019473896586647186, | |
| "loss": 0.3811, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.22385650224215248, | |
| "grad_norm": 0.36954265832901, | |
| "learning_rate": 0.00019436051107213175, | |
| "loss": 0.7165, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2295964125560538, | |
| "grad_norm": 0.4004439115524292, | |
| "learning_rate": 0.0001939693518951265, | |
| "loss": 0.7231, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23533632286995515, | |
| "grad_norm": 0.4269639849662781, | |
| "learning_rate": 0.0001935655472425894, | |
| "loss": 0.7353, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.24107623318385651, | |
| "grad_norm": 0.37840205430984497, | |
| "learning_rate": 0.00019314915792601581, | |
| "loss": 0.719, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.24681614349775785, | |
| "grad_norm": 0.37707093358039856, | |
| "learning_rate": 0.00019272024665210522, | |
| "loss": 0.7005, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2525560538116592, | |
| "grad_norm": 0.3464455008506775, | |
| "learning_rate": 0.00019227887801331778, | |
| "loss": 0.7053, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.25829596412556055, | |
| "grad_norm": 0.38833266496658325, | |
| "learning_rate": 0.000191825118478147, | |
| "loss": 0.6921, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.26403587443946186, | |
| "grad_norm": 0.34195584058761597, | |
| "learning_rate": 0.00019135903638110993, | |
| "loss": 0.6617, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2697757847533632, | |
| "grad_norm": 0.38158613443374634, | |
| "learning_rate": 0.00019088070191245585, | |
| "loss": 0.6968, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2755156950672646, | |
| "grad_norm": 0.32683825492858887, | |
| "learning_rate": 0.00019039018710759637, | |
| "loss": 0.7062, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2812556053811659, | |
| "grad_norm": 0.31679072976112366, | |
| "learning_rate": 0.00018988756583625686, | |
| "loss": 0.6335, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.28699551569506726, | |
| "grad_norm": 0.43332555890083313, | |
| "learning_rate": 0.00018937291379135196, | |
| "loss": 0.6828, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.28699551569506726, | |
| "eval_loss": 0.6181142330169678, | |
| "eval_runtime": 0.9223, | |
| "eval_samples_per_second": 54.214, | |
| "eval_steps_per_second": 14.096, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2927354260089686, | |
| "grad_norm": 0.20470459759235382, | |
| "learning_rate": 0.0001888463084775866, | |
| "loss": 0.4231, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.29847533632286993, | |
| "grad_norm": 0.3457722067832947, | |
| "learning_rate": 0.00018830782919978406, | |
| "loss": 0.6588, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3042152466367713, | |
| "grad_norm": 0.3492876887321472, | |
| "learning_rate": 0.00018775755705094282, | |
| "loss": 0.6704, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.30995515695067266, | |
| "grad_norm": 0.3490440547466278, | |
| "learning_rate": 0.0001871955749000245, | |
| "loss": 0.6571, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.31569506726457397, | |
| "grad_norm": 0.33820873498916626, | |
| "learning_rate": 0.00018662196737947388, | |
| "loss": 0.6841, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.32143497757847533, | |
| "grad_norm": 0.2790636718273163, | |
| "learning_rate": 0.00018603682087247364, | |
| "loss": 0.6353, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3271748878923767, | |
| "grad_norm": 0.27815526723861694, | |
| "learning_rate": 0.00018544022349993542, | |
| "loss": 0.6104, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.332914798206278, | |
| "grad_norm": 0.280226469039917, | |
| "learning_rate": 0.0001848322651072291, | |
| "loss": 0.6385, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.33865470852017937, | |
| "grad_norm": 0.3228759765625, | |
| "learning_rate": 0.0001842130372506523, | |
| "loss": 0.6372, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.34439461883408073, | |
| "grad_norm": 0.39957645535469055, | |
| "learning_rate": 0.00018358263318364254, | |
| "loss": 0.6381, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.35013452914798204, | |
| "grad_norm": 0.38383835554122925, | |
| "learning_rate": 0.00018294114784273352, | |
| "loss": 0.6543, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3558744394618834, | |
| "grad_norm": 0.3201979398727417, | |
| "learning_rate": 0.00018228867783325804, | |
| "loss": 0.5848, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.36161434977578477, | |
| "grad_norm": 0.25422611832618713, | |
| "learning_rate": 0.00018162532141479954, | |
| "loss": 0.4634, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3673542600896861, | |
| "grad_norm": 0.33904367685317993, | |
| "learning_rate": 0.00018095117848639458, | |
| "loss": 0.6119, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.37309417040358744, | |
| "grad_norm": 0.32347720861434937, | |
| "learning_rate": 0.0001802663505714885, | |
| "loss": 0.6417, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3788340807174888, | |
| "grad_norm": 0.32679322361946106, | |
| "learning_rate": 0.00017957094080264634, | |
| "loss": 0.6631, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3845739910313901, | |
| "grad_norm": 0.3418073058128357, | |
| "learning_rate": 0.00017886505390602133, | |
| "loss": 0.6605, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.3903139013452915, | |
| "grad_norm": 0.3066117763519287, | |
| "learning_rate": 0.00017814879618558362, | |
| "loss": 0.6393, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.39605381165919284, | |
| "grad_norm": 0.3158493638038635, | |
| "learning_rate": 0.00017742227550711134, | |
| "loss": 0.6483, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.40179372197309415, | |
| "grad_norm": 0.2925642430782318, | |
| "learning_rate": 0.00017668560128194635, | |
| "loss": 0.6248, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4075336322869955, | |
| "grad_norm": 0.3093167245388031, | |
| "learning_rate": 0.00017593888445051716, | |
| "loss": 0.6187, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4132735426008969, | |
| "grad_norm": 0.31884729862213135, | |
| "learning_rate": 0.00017518223746563206, | |
| "loss": 0.6008, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4190134529147982, | |
| "grad_norm": 0.33142465353012085, | |
| "learning_rate": 0.00017441577427554367, | |
| "loss": 0.6345, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.42475336322869955, | |
| "grad_norm": 0.33919477462768555, | |
| "learning_rate": 0.00017363961030678927, | |
| "loss": 0.5662, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.4304932735426009, | |
| "grad_norm": 0.42973288893699646, | |
| "learning_rate": 0.00017285386244680757, | |
| "loss": 0.5928, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4304932735426009, | |
| "eval_loss": 0.5645103454589844, | |
| "eval_runtime": 0.9223, | |
| "eval_samples_per_second": 54.214, | |
| "eval_steps_per_second": 14.096, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4362331838565022, | |
| "grad_norm": 0.23932668566703796, | |
| "learning_rate": 0.00017205864902633604, | |
| "loss": 0.418, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.4419730941704036, | |
| "grad_norm": 0.37948039174079895, | |
| "learning_rate": 0.0001712540898015908, | |
| "loss": 0.6106, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.44771300448430495, | |
| "grad_norm": 0.38140037655830383, | |
| "learning_rate": 0.00017044030593623167, | |
| "loss": 0.6314, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.45345291479820626, | |
| "grad_norm": 0.35335981845855713, | |
| "learning_rate": 0.00016961741998311548, | |
| "loss": 0.6099, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.4591928251121076, | |
| "grad_norm": 0.3372631371021271, | |
| "learning_rate": 0.0001687855558658399, | |
| "loss": 0.6299, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.464932735426009, | |
| "grad_norm": 0.3550214469432831, | |
| "learning_rate": 0.00016794483886008123, | |
| "loss": 0.6016, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.4706726457399103, | |
| "grad_norm": 0.3631860613822937, | |
| "learning_rate": 0.0001670953955747281, | |
| "loss": 0.5989, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.47641255605381166, | |
| "grad_norm": 0.3243929445743561, | |
| "learning_rate": 0.0001662373539328148, | |
| "loss": 0.5598, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.48215246636771303, | |
| "grad_norm": 0.332532674074173, | |
| "learning_rate": 0.00016537084315225643, | |
| "loss": 0.6061, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.48789237668161434, | |
| "grad_norm": 0.3495044708251953, | |
| "learning_rate": 0.0001644959937263893, | |
| "loss": 0.5622, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4936322869955157, | |
| "grad_norm": 0.3646451532840729, | |
| "learning_rate": 0.00016361293740431904, | |
| "loss": 0.5949, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.49937219730941707, | |
| "grad_norm": 0.3812481462955475, | |
| "learning_rate": 0.0001627218071710795, | |
| "loss": 0.5562, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5051121076233184, | |
| "grad_norm": 0.26016414165496826, | |
| "learning_rate": 0.0001618227372276061, | |
| "loss": 0.431, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5108520179372197, | |
| "grad_norm": 0.37813055515289307, | |
| "learning_rate": 0.0001609158629705252, | |
| "loss": 0.5677, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.5165919282511211, | |
| "grad_norm": 0.33156195282936096, | |
| "learning_rate": 0.00016000132097176422, | |
| "loss": 0.5934, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5223318385650224, | |
| "grad_norm": 0.3131614923477173, | |
| "learning_rate": 0.00015907924895798418, | |
| "loss": 0.6103, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.5280717488789237, | |
| "grad_norm": 0.33647915720939636, | |
| "learning_rate": 0.00015814978578983878, | |
| "loss": 0.6084, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.5338116591928251, | |
| "grad_norm": 0.3749343156814575, | |
| "learning_rate": 0.0001572130714410622, | |
| "loss": 0.5954, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.5395515695067264, | |
| "grad_norm": 0.38268035650253296, | |
| "learning_rate": 0.00015626924697738993, | |
| "loss": 0.5957, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.5452914798206278, | |
| "grad_norm": 0.3427310585975647, | |
| "learning_rate": 0.0001553184545353146, | |
| "loss": 0.5759, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5510313901345292, | |
| "grad_norm": 0.3409261703491211, | |
| "learning_rate": 0.0001543608373006806, | |
| "loss": 0.5682, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.5567713004484305, | |
| "grad_norm": 0.3772481381893158, | |
| "learning_rate": 0.00015339653948712108, | |
| "loss": 0.5436, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.5625112107623318, | |
| "grad_norm": 0.392767071723938, | |
| "learning_rate": 0.0001524257063143398, | |
| "loss": 0.5582, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.5682511210762332, | |
| "grad_norm": 0.3690810203552246, | |
| "learning_rate": 0.00015144848398624162, | |
| "loss": 0.5056, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5739910313901345, | |
| "grad_norm": 0.5016475915908813, | |
| "learning_rate": 0.00015046501966891463, | |
| "loss": 0.593, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5739910313901345, | |
| "eval_loss": 0.5337885022163391, | |
| "eval_runtime": 0.9218, | |
| "eval_samples_per_second": 54.242, | |
| "eval_steps_per_second": 14.103, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5797309417040358, | |
| "grad_norm": 0.2608706057071686, | |
| "learning_rate": 0.00014947546146846748, | |
| "loss": 0.3916, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.5854708520179372, | |
| "grad_norm": 0.379069447517395, | |
| "learning_rate": 0.0001484799584087254, | |
| "loss": 0.566, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.5912107623318386, | |
| "grad_norm": 0.3914828598499298, | |
| "learning_rate": 0.00014747866040878738, | |
| "loss": 0.6203, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.5969506726457399, | |
| "grad_norm": 0.4011947512626648, | |
| "learning_rate": 0.00014647171826044907, | |
| "loss": 0.5886, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.6026905829596413, | |
| "grad_norm": 0.38338544964790344, | |
| "learning_rate": 0.00014545928360549436, | |
| "loss": 0.5889, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6084304932735426, | |
| "grad_norm": 0.40191414952278137, | |
| "learning_rate": 0.00014444150891285807, | |
| "loss": 0.5612, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.6141704035874439, | |
| "grad_norm": 0.3976474404335022, | |
| "learning_rate": 0.00014341854745566538, | |
| "loss": 0.5905, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.6199103139013453, | |
| "grad_norm": 0.3555368185043335, | |
| "learning_rate": 0.00014239055328814894, | |
| "loss": 0.5735, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6256502242152466, | |
| "grad_norm": 0.3123275935649872, | |
| "learning_rate": 0.0001413576812224491, | |
| "loss": 0.5211, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.6313901345291479, | |
| "grad_norm": 0.35772255063056946, | |
| "learning_rate": 0.0001403200868052998, | |
| "loss": 0.5413, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6371300448430494, | |
| "grad_norm": 0.34592434763908386, | |
| "learning_rate": 0.00013927792629460367, | |
| "loss": 0.5764, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.6428699551569507, | |
| "grad_norm": 0.33390721678733826, | |
| "learning_rate": 0.00013823135663590025, | |
| "loss": 0.5225, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.648609865470852, | |
| "grad_norm": 0.21307708323001862, | |
| "learning_rate": 0.00013718053543873056, | |
| "loss": 0.3379, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.6543497757847534, | |
| "grad_norm": 0.41324618458747864, | |
| "learning_rate": 0.0001361256209529016, | |
| "loss": 0.538, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.6600896860986547, | |
| "grad_norm": 0.4129272997379303, | |
| "learning_rate": 0.00013506677204465475, | |
| "loss": 0.5736, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.665829596412556, | |
| "grad_norm": 0.39694082736968994, | |
| "learning_rate": 0.00013400414817274088, | |
| "loss": 0.5951, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.6715695067264574, | |
| "grad_norm": 0.4103195369243622, | |
| "learning_rate": 0.00013293790936440633, | |
| "loss": 0.5936, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.6773094170403587, | |
| "grad_norm": 0.3834230303764343, | |
| "learning_rate": 0.00013186821619129378, | |
| "loss": 0.5769, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.68304932735426, | |
| "grad_norm": 0.40706706047058105, | |
| "learning_rate": 0.00013079522974526042, | |
| "loss": 0.5666, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.6887892376681615, | |
| "grad_norm": 0.3616923689842224, | |
| "learning_rate": 0.00012971911161411827, | |
| "loss": 0.5568, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6945291479820628, | |
| "grad_norm": 0.32444703578948975, | |
| "learning_rate": 0.00012864002385729967, | |
| "loss": 0.5424, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.7002690582959641, | |
| "grad_norm": 0.34600815176963806, | |
| "learning_rate": 0.00012755812898145155, | |
| "loss": 0.5415, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.7060089686098655, | |
| "grad_norm": 0.41751474142074585, | |
| "learning_rate": 0.0001264735899159627, | |
| "loss": 0.5645, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.7117488789237668, | |
| "grad_norm": 0.3468458950519562, | |
| "learning_rate": 0.00012538656998842713, | |
| "loss": 0.4588, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.7174887892376681, | |
| "grad_norm": 0.4765909016132355, | |
| "learning_rate": 0.00012429723290004752, | |
| "loss": 0.5565, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7174887892376681, | |
| "eval_loss": 0.5193074941635132, | |
| "eval_runtime": 0.9221, | |
| "eval_samples_per_second": 54.225, | |
| "eval_steps_per_second": 14.098, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7232286995515695, | |
| "grad_norm": 0.27293744683265686, | |
| "learning_rate": 0.00012320574270098254, | |
| "loss": 0.3958, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.7289686098654709, | |
| "grad_norm": 0.37524548172950745, | |
| "learning_rate": 0.00012211226376564137, | |
| "loss": 0.5386, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.7347085201793722, | |
| "grad_norm": 0.3265777826309204, | |
| "learning_rate": 0.00012101696076792946, | |
| "loss": 0.5729, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.7404484304932736, | |
| "grad_norm": 0.3645853102207184, | |
| "learning_rate": 0.00011991999865644949, | |
| "loss": 0.6049, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.7461883408071749, | |
| "grad_norm": 0.39641687273979187, | |
| "learning_rate": 0.0001188215426296605, | |
| "loss": 0.5868, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7519282511210762, | |
| "grad_norm": 0.3878898620605469, | |
| "learning_rate": 0.00011772175811099962, | |
| "loss": 0.5686, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.7576681614349776, | |
| "grad_norm": 0.38877856731414795, | |
| "learning_rate": 0.00011662081072397009, | |
| "loss": 0.5596, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.7634080717488789, | |
| "grad_norm": 0.3513187766075134, | |
| "learning_rate": 0.00011551886626719879, | |
| "loss": 0.5512, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.7691479820627802, | |
| "grad_norm": 0.33318498730659485, | |
| "learning_rate": 0.00011441609068946764, | |
| "loss": 0.5654, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.7748878923766817, | |
| "grad_norm": 0.38084232807159424, | |
| "learning_rate": 0.00011331265006472231, | |
| "loss": 0.5368, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.780627802690583, | |
| "grad_norm": 0.40014737844467163, | |
| "learning_rate": 0.00011220871056706212, | |
| "loss": 0.5569, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.7863677130044843, | |
| "grad_norm": 0.40615227818489075, | |
| "learning_rate": 0.0001111044384457148, | |
| "loss": 0.5602, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.7921076233183857, | |
| "grad_norm": 0.20240327715873718, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 0.2802, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.797847533632287, | |
| "grad_norm": 0.4555722177028656, | |
| "learning_rate": 0.00010889556155428522, | |
| "loss": 0.5397, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.8035874439461883, | |
| "grad_norm": 0.3639007806777954, | |
| "learning_rate": 0.0001077912894329379, | |
| "loss": 0.5589, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8093273542600897, | |
| "grad_norm": 0.3477562665939331, | |
| "learning_rate": 0.00010668734993527771, | |
| "loss": 0.5665, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.815067264573991, | |
| "grad_norm": 0.32893893122673035, | |
| "learning_rate": 0.0001055839093105324, | |
| "loss": 0.6049, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.8208071748878923, | |
| "grad_norm": 0.3630063533782959, | |
| "learning_rate": 0.00010448113373280125, | |
| "loss": 0.566, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.8265470852017938, | |
| "grad_norm": 0.4404502213001251, | |
| "learning_rate": 0.00010337918927602994, | |
| "loss": 0.5496, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.8322869955156951, | |
| "grad_norm": 0.4184599816799164, | |
| "learning_rate": 0.00010227824188900043, | |
| "loss": 0.5382, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8380269058295964, | |
| "grad_norm": 0.3810145854949951, | |
| "learning_rate": 0.00010117845737033956, | |
| "loss": 0.5412, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.8437668161434978, | |
| "grad_norm": 0.37553566694259644, | |
| "learning_rate": 0.00010008000134355053, | |
| "loss": 0.5264, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.8495067264573991, | |
| "grad_norm": 0.35165223479270935, | |
| "learning_rate": 9.898303923207055e-05, | |
| "loss": 0.5131, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.8552466367713004, | |
| "grad_norm": 0.41181644797325134, | |
| "learning_rate": 9.788773623435865e-05, | |
| "loss": 0.5279, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.8609865470852018, | |
| "grad_norm": 0.47862258553504944, | |
| "learning_rate": 9.679425729901746e-05, | |
| "loss": 0.5313, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8609865470852018, | |
| "eval_loss": 0.5081304907798767, | |
| "eval_runtime": 0.9227, | |
| "eval_samples_per_second": 54.191, | |
| "eval_steps_per_second": 14.09, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8667264573991031, | |
| "grad_norm": 0.28677311539649963, | |
| "learning_rate": 9.57027670999525e-05, | |
| "loss": 0.3418, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.8724663677130045, | |
| "grad_norm": 0.48761609196662903, | |
| "learning_rate": 9.46134300115729e-05, | |
| "loss": 0.5671, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.8782062780269059, | |
| "grad_norm": 0.48662909865379333, | |
| "learning_rate": 9.352641008403732e-05, | |
| "loss": 0.5802, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.8839461883408072, | |
| "grad_norm": 0.39658379554748535, | |
| "learning_rate": 9.244187101854847e-05, | |
| "loss": 0.5988, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.8896860986547085, | |
| "grad_norm": 0.3358779847621918, | |
| "learning_rate": 9.135997614270035e-05, | |
| "loss": 0.5709, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.8954260089686099, | |
| "grad_norm": 0.36029863357543945, | |
| "learning_rate": 9.028088838588173e-05, | |
| "loss": 0.5361, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.9011659192825112, | |
| "grad_norm": 0.37783312797546387, | |
| "learning_rate": 8.920477025473961e-05, | |
| "loss": 0.5498, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.9069058295964125, | |
| "grad_norm": 0.41614797711372375, | |
| "learning_rate": 8.813178380870625e-05, | |
| "loss": 0.5639, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.912645739910314, | |
| "grad_norm": 0.4205968976020813, | |
| "learning_rate": 8.706209063559369e-05, | |
| "loss": 0.5375, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.9183856502242153, | |
| "grad_norm": 0.4054337739944458, | |
| "learning_rate": 8.599585182725915e-05, | |
| "loss": 0.513, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9241255605381166, | |
| "grad_norm": 0.4122784435749054, | |
| "learning_rate": 8.493322795534524e-05, | |
| "loss": 0.5391, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.929865470852018, | |
| "grad_norm": 0.3715398907661438, | |
| "learning_rate": 8.38743790470984e-05, | |
| "loss": 0.5019, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.9356053811659193, | |
| "grad_norm": 0.2431960552930832, | |
| "learning_rate": 8.281946456126948e-05, | |
| "loss": 0.3709, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.9413452914798206, | |
| "grad_norm": 0.3482334613800049, | |
| "learning_rate": 8.176864336409977e-05, | |
| "loss": 0.5183, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.947085201793722, | |
| "grad_norm": 0.3396470844745636, | |
| "learning_rate": 8.072207370539635e-05, | |
| "loss": 0.5506, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9528251121076233, | |
| "grad_norm": 0.3452121317386627, | |
| "learning_rate": 7.96799131947002e-05, | |
| "loss": 0.5623, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.9585650224215246, | |
| "grad_norm": 0.3748196065425873, | |
| "learning_rate": 7.86423187775509e-05, | |
| "loss": 0.5504, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.9643049327354261, | |
| "grad_norm": 0.3832938075065613, | |
| "learning_rate": 7.760944671185106e-05, | |
| "loss": 0.5523, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.9700448430493274, | |
| "grad_norm": 0.3845353126525879, | |
| "learning_rate": 7.658145254433464e-05, | |
| "loss": 0.5536, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.9757847533632287, | |
| "grad_norm": 0.3579016923904419, | |
| "learning_rate": 7.555849108714192e-05, | |
| "loss": 0.5452, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9815246636771301, | |
| "grad_norm": 0.35198974609375, | |
| "learning_rate": 7.454071639450568e-05, | |
| "loss": 0.5256, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.9872645739910314, | |
| "grad_norm": 0.3465883433818817, | |
| "learning_rate": 7.352828173955092e-05, | |
| "loss": 0.5216, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.9930044843049327, | |
| "grad_norm": 0.3699122965335846, | |
| "learning_rate": 7.252133959121267e-05, | |
| "loss": 0.5106, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.9987443946188341, | |
| "grad_norm": 0.3901955783367157, | |
| "learning_rate": 7.152004159127463e-05, | |
| "loss": 0.4872, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.0044843049327354, | |
| "grad_norm": 1.1412564516067505, | |
| "learning_rate": 7.052453853153254e-05, | |
| "loss": 0.7525, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.0044843049327354, | |
| "eval_loss": 0.49331748485565186, | |
| "eval_runtime": 0.9236, | |
| "eval_samples_per_second": 54.138, | |
| "eval_steps_per_second": 14.076, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.0102242152466367, | |
| "grad_norm": 0.4304850995540619, | |
| "learning_rate": 6.953498033108541e-05, | |
| "loss": 0.4813, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.015964125560538, | |
| "grad_norm": 0.353695809841156, | |
| "learning_rate": 6.85515160137584e-05, | |
| "loss": 0.5574, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.0217040358744394, | |
| "grad_norm": 0.314039409160614, | |
| "learning_rate": 6.757429368566022e-05, | |
| "loss": 0.5421, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.027443946188341, | |
| "grad_norm": 0.3056468367576599, | |
| "learning_rate": 6.660346051287897e-05, | |
| "loss": 0.5369, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.0331838565022422, | |
| "grad_norm": 0.33235135674476624, | |
| "learning_rate": 6.563916269931944e-05, | |
| "loss": 0.5317, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0389237668161435, | |
| "grad_norm": 0.3649938106536865, | |
| "learning_rate": 6.468154546468544e-05, | |
| "loss": 0.5445, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.0446636771300448, | |
| "grad_norm": 0.38012173771858215, | |
| "learning_rate": 6.373075302261006e-05, | |
| "loss": 0.5236, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.0504035874439461, | |
| "grad_norm": 0.39040887355804443, | |
| "learning_rate": 6.278692855893782e-05, | |
| "loss": 0.4868, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.0561434977578474, | |
| "grad_norm": 0.4336410462856293, | |
| "learning_rate": 6.185021421016127e-05, | |
| "loss": 0.4899, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.061883408071749, | |
| "grad_norm": 0.35759079456329346, | |
| "learning_rate": 6.092075104201584e-05, | |
| "loss": 0.5052, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.0676233183856503, | |
| "grad_norm": 0.36424076557159424, | |
| "learning_rate": 5.9998679028235824e-05, | |
| "loss": 0.4613, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.0733632286995516, | |
| "grad_norm": 0.2789258360862732, | |
| "learning_rate": 5.9084137029474816e-05, | |
| "loss": 0.3913, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.079103139013453, | |
| "grad_norm": 0.43460971117019653, | |
| "learning_rate": 5.817726277239393e-05, | |
| "loss": 0.5143, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.0848430493273542, | |
| "grad_norm": 0.42008864879608154, | |
| "learning_rate": 5.7278192828920504e-05, | |
| "loss": 0.525, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.0905829596412555, | |
| "grad_norm": 0.3849257230758667, | |
| "learning_rate": 5.6387062595681006e-05, | |
| "loss": 0.5529, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.096322869955157, | |
| "grad_norm": 0.36319607496261597, | |
| "learning_rate": 5.550400627361072e-05, | |
| "loss": 0.522, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.1020627802690584, | |
| "grad_norm": 0.3183014392852783, | |
| "learning_rate": 5.46291568477436e-05, | |
| "loss": 0.5057, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.1078026905829597, | |
| "grad_norm": 0.3118283748626709, | |
| "learning_rate": 5.376264606718524e-05, | |
| "loss": 0.5227, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.113542600896861, | |
| "grad_norm": 0.2829921245574951, | |
| "learning_rate": 5.290460442527192e-05, | |
| "loss": 0.5009, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.1192825112107623, | |
| "grad_norm": 0.3522259294986725, | |
| "learning_rate": 5.2055161139918793e-05, | |
| "loss": 0.501, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.1250224215246636, | |
| "grad_norm": 0.3565344214439392, | |
| "learning_rate": 5.121444413416012e-05, | |
| "loss": 0.4798, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.1307623318385651, | |
| "grad_norm": 0.3734815716743469, | |
| "learning_rate": 5.038258001688454e-05, | |
| "loss": 0.4725, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.1365022421524664, | |
| "grad_norm": 0.3412702977657318, | |
| "learning_rate": 4.955969406376835e-05, | |
| "loss": 0.4802, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.1422421524663677, | |
| "grad_norm": 0.43615493178367615, | |
| "learning_rate": 4.874591019840923e-05, | |
| "loss": 0.46, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.147982062780269, | |
| "grad_norm": 0.2464035153388977, | |
| "learning_rate": 4.794135097366398e-05, | |
| "loss": 0.3742, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.147982062780269, | |
| "eval_loss": 0.48591822385787964, | |
| "eval_runtime": 0.9221, | |
| "eval_samples_per_second": 54.226, | |
| "eval_steps_per_second": 14.099, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1537219730941703, | |
| "grad_norm": 0.3372306823730469, | |
| "learning_rate": 4.7146137553192454e-05, | |
| "loss": 0.4717, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.1594618834080717, | |
| "grad_norm": 0.33223405480384827, | |
| "learning_rate": 4.6360389693210735e-05, | |
| "loss": 0.5198, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.1652017937219732, | |
| "grad_norm": 0.3706080913543701, | |
| "learning_rate": 4.5584225724456334e-05, | |
| "loss": 0.5424, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.1709417040358745, | |
| "grad_norm": 0.3313405513763428, | |
| "learning_rate": 4.481776253436799e-05, | |
| "loss": 0.542, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.1766816143497758, | |
| "grad_norm": 0.32144275307655334, | |
| "learning_rate": 4.4061115549482855e-05, | |
| "loss": 0.5204, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.1824215246636771, | |
| "grad_norm": 0.32734695076942444, | |
| "learning_rate": 4.33143987180537e-05, | |
| "loss": 0.5126, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.1881614349775784, | |
| "grad_norm": 0.33365294337272644, | |
| "learning_rate": 4.2577724492888685e-05, | |
| "loss": 0.5009, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.1939013452914797, | |
| "grad_norm": 0.3367886245250702, | |
| "learning_rate": 4.18512038144164e-05, | |
| "loss": 0.4769, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.1996412556053813, | |
| "grad_norm": 0.38147518038749695, | |
| "learning_rate": 4.1134946093978696e-05, | |
| "loss": 0.4995, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.2053811659192826, | |
| "grad_norm": 0.4221321940422058, | |
| "learning_rate": 4.042905919735367e-05, | |
| "loss": 0.493, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.2111210762331839, | |
| "grad_norm": 0.39333173632621765, | |
| "learning_rate": 3.97336494285115e-05, | |
| "loss": 0.4496, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.2168609865470852, | |
| "grad_norm": 0.24255159497261047, | |
| "learning_rate": 3.904882151360544e-05, | |
| "loss": 0.3046, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.2226008968609865, | |
| "grad_norm": 0.3250392973423004, | |
| "learning_rate": 3.83746785852005e-05, | |
| "loss": 0.471, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.2283408071748878, | |
| "grad_norm": 0.34921231865882874, | |
| "learning_rate": 3.771132216674197e-05, | |
| "loss": 0.5089, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.2340807174887893, | |
| "grad_norm": 0.33424094319343567, | |
| "learning_rate": 3.705885215726649e-05, | |
| "loss": 0.5478, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.2398206278026906, | |
| "grad_norm": 0.3389650583267212, | |
| "learning_rate": 3.641736681635748e-05, | |
| "loss": 0.5351, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.245560538116592, | |
| "grad_norm": 0.31873995065689087, | |
| "learning_rate": 3.5786962749347745e-05, | |
| "loss": 0.5341, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.2513004484304933, | |
| "grad_norm": 0.3182890713214874, | |
| "learning_rate": 3.516773489277092e-05, | |
| "loss": 0.5261, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.2570403587443946, | |
| "grad_norm": 0.3134552538394928, | |
| "learning_rate": 3.455977650006458e-05, | |
| "loss": 0.484, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.2627802690582959, | |
| "grad_norm": 0.3109564483165741, | |
| "learning_rate": 3.396317912752636e-05, | |
| "loss": 0.5056, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2685201793721972, | |
| "grad_norm": 0.3221109211444855, | |
| "learning_rate": 3.337803262052613e-05, | |
| "loss": 0.4935, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 1.2742600896860987, | |
| "grad_norm": 0.3416219651699066, | |
| "learning_rate": 3.2804425099975525e-05, | |
| "loss": 0.4988, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.35584232211112976, | |
| "learning_rate": 3.22424429490572e-05, | |
| "loss": 0.4709, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.2857399103139013, | |
| "grad_norm": 0.379276841878891, | |
| "learning_rate": 3.169217080021598e-05, | |
| "loss": 0.4671, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.2914798206278026, | |
| "grad_norm": 0.3112328350543976, | |
| "learning_rate": 3.115369152241342e-05, | |
| "loss": 0.3621, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.2914798206278026, | |
| "eval_loss": 0.47635313868522644, | |
| "eval_runtime": 0.9223, | |
| "eval_samples_per_second": 54.214, | |
| "eval_steps_per_second": 14.096, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.2972197309417042, | |
| "grad_norm": 0.29332128167152405, | |
| "learning_rate": 3.062708620864806e-05, | |
| "loss": 0.4526, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 1.3029596412556055, | |
| "grad_norm": 0.31223607063293457, | |
| "learning_rate": 3.0112434163743157e-05, | |
| "loss": 0.5191, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.3086995515695068, | |
| "grad_norm": 0.3201247751712799, | |
| "learning_rate": 2.9609812892403632e-05, | |
| "loss": 0.5294, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.314439461883408, | |
| "grad_norm": 0.29841506481170654, | |
| "learning_rate": 2.911929808754415e-05, | |
| "loss": 0.5239, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 1.3201793721973094, | |
| "grad_norm": 0.28671491146087646, | |
| "learning_rate": 2.8640963618890103e-05, | |
| "loss": 0.5297, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.3259192825112107, | |
| "grad_norm": 0.32272037863731384, | |
| "learning_rate": 2.8174881521852992e-05, | |
| "loss": 0.4861, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.331659192825112, | |
| "grad_norm": 0.30266034603118896, | |
| "learning_rate": 2.772112198668224e-05, | |
| "loss": 0.4576, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.3373991031390133, | |
| "grad_norm": 0.34197890758514404, | |
| "learning_rate": 2.7279753347894803e-05, | |
| "loss": 0.4886, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 1.3431390134529149, | |
| "grad_norm": 0.3624284267425537, | |
| "learning_rate": 2.6850842073984196e-05, | |
| "loss": 0.4499, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.3488789237668162, | |
| "grad_norm": 0.35989314317703247, | |
| "learning_rate": 2.643445275741061e-05, | |
| "loss": 0.5159, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.3546188340807175, | |
| "grad_norm": 0.39581242203712463, | |
| "learning_rate": 2.6030648104873506e-05, | |
| "loss": 0.437, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 1.3603587443946188, | |
| "grad_norm": 0.2373550683259964, | |
| "learning_rate": 2.5639488927868267e-05, | |
| "loss": 0.3402, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 1.36609865470852, | |
| "grad_norm": 0.29506540298461914, | |
| "learning_rate": 2.5261034133528138e-05, | |
| "loss": 0.4671, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.3718385650224216, | |
| "grad_norm": 0.3008054792881012, | |
| "learning_rate": 2.4895340715753094e-05, | |
| "loss": 0.5108, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 1.377578475336323, | |
| "grad_norm": 0.3018406331539154, | |
| "learning_rate": 2.45424637466267e-05, | |
| "loss": 0.5314, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3833183856502242, | |
| "grad_norm": 0.31109651923179626, | |
| "learning_rate": 2.4202456368122556e-05, | |
| "loss": 0.5201, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 1.3890582959641256, | |
| "grad_norm": 0.2933644950389862, | |
| "learning_rate": 2.387536978410121e-05, | |
| "loss": 0.5317, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.3947982062780269, | |
| "grad_norm": 0.30081358551979065, | |
| "learning_rate": 2.356125325259908e-05, | |
| "loss": 0.5154, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.4005381165919282, | |
| "grad_norm": 0.3170672059059143, | |
| "learning_rate": 2.3260154078410418e-05, | |
| "loss": 0.4799, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.4062780269058295, | |
| "grad_norm": 0.3238869905471802, | |
| "learning_rate": 2.2972117605963318e-05, | |
| "loss": 0.4746, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.412017937219731, | |
| "grad_norm": 0.3185063898563385, | |
| "learning_rate": 2.2697187212491044e-05, | |
| "loss": 0.4872, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.4177578475336323, | |
| "grad_norm": 0.3538781404495239, | |
| "learning_rate": 2.2435404301499595e-05, | |
| "loss": 0.4898, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.4234977578475336, | |
| "grad_norm": 0.3690301179885864, | |
| "learning_rate": 2.218680829653244e-05, | |
| "loss": 0.4509, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 1.429237668161435, | |
| "grad_norm": 0.427407830953598, | |
| "learning_rate": 2.1951436635233524e-05, | |
| "loss": 0.5208, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 1.4349775784753362, | |
| "grad_norm": 0.2645489275455475, | |
| "learning_rate": 2.1729324763709264e-05, | |
| "loss": 0.3754, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.4349775784753362, | |
| "eval_loss": 0.4731843173503876, | |
| "eval_runtime": 0.9238, | |
| "eval_samples_per_second": 54.124, | |
| "eval_steps_per_second": 14.072, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.4407174887892378, | |
| "grad_norm": 0.26860833168029785, | |
| "learning_rate": 2.1520506131190538e-05, | |
| "loss": 0.4482, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.446457399103139, | |
| "grad_norm": 0.2933943271636963, | |
| "learning_rate": 2.1325012184995292e-05, | |
| "loss": 0.5343, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.4521973094170404, | |
| "grad_norm": 0.3026564419269562, | |
| "learning_rate": 2.1142872365792744e-05, | |
| "loss": 0.5285, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 1.4579372197309417, | |
| "grad_norm": 0.2953205406665802, | |
| "learning_rate": 2.0974114103169712e-05, | |
| "loss": 0.4991, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.463677130044843, | |
| "grad_norm": 0.31326618790626526, | |
| "learning_rate": 2.08187628114998e-05, | |
| "loss": 0.519, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.4694170403587443, | |
| "grad_norm": 0.32098764181137085, | |
| "learning_rate": 2.0676841886116105e-05, | |
| "loss": 0.5006, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.4751569506726456, | |
| "grad_norm": 0.33045464754104614, | |
| "learning_rate": 2.0548372699787956e-05, | |
| "loss": 0.5063, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 1.4808968609865472, | |
| "grad_norm": 0.34082722663879395, | |
| "learning_rate": 2.043337459950229e-05, | |
| "loss": 0.51, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 1.4866367713004485, | |
| "grad_norm": 0.33419910073280334, | |
| "learning_rate": 2.0331864903549983e-05, | |
| "loss": 0.48, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.4923766816143498, | |
| "grad_norm": 0.349400132894516, | |
| "learning_rate": 2.0243858898917882e-05, | |
| "loss": 0.4653, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.498116591928251, | |
| "grad_norm": 0.348258912563324, | |
| "learning_rate": 2.0169369838986577e-05, | |
| "loss": 0.4778, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.5038565022421526, | |
| "grad_norm": 0.22999514639377594, | |
| "learning_rate": 2.0108408941534486e-05, | |
| "loss": 0.2897, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 1.509596412556054, | |
| "grad_norm": 0.2894325852394104, | |
| "learning_rate": 2.0060985387048543e-05, | |
| "loss": 0.457, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 1.5153363228699552, | |
| "grad_norm": 0.29187583923339844, | |
| "learning_rate": 2.0027106317341622e-05, | |
| "loss": 0.4962, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.5210762331838565, | |
| "grad_norm": 0.2911413311958313, | |
| "learning_rate": 2.0006776834477e-05, | |
| "loss": 0.5401, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.5268161434977578, | |
| "grad_norm": 0.30475127696990967, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5332, | |
| "step": 266 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 266, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 60, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3695631230791844e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |