{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 908, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002203325644644886, "learning_rate": 0.0, "loss": 0.4959, "step": 1 }, { "epoch": 0.004406651289289772, "learning_rate": 3.3333333333333333e-06, "loss": 0.4258, "step": 2 }, { "epoch": 0.006609976933934658, "learning_rate": 6.666666666666667e-06, "loss": 0.4444, "step": 3 }, { "epoch": 0.008813302578579544, "learning_rate": 1e-05, "loss": 0.471, "step": 4 }, { "epoch": 0.011016628223224429, "learning_rate": 1.3333333333333333e-05, "loss": 0.4367, "step": 5 }, { "epoch": 0.013219953867869316, "learning_rate": 1.6666666666666667e-05, "loss": 0.4054, "step": 6 }, { "epoch": 0.015423279512514201, "learning_rate": 2e-05, "loss": 0.3863, "step": 7 }, { "epoch": 0.017626605157159088, "learning_rate": 2.3333333333333336e-05, "loss": 0.3937, "step": 8 }, { "epoch": 0.019829930801803973, "learning_rate": 2.6666666666666667e-05, "loss": 0.3868, "step": 9 }, { "epoch": 0.022033256446448858, "learning_rate": 3e-05, "loss": 0.3927, "step": 10 }, { "epoch": 0.024236582091093743, "learning_rate": 3.3333333333333335e-05, "loss": 0.3845, "step": 11 }, { "epoch": 0.026439907735738632, "learning_rate": 3.6666666666666666e-05, "loss": 0.3613, "step": 12 }, { "epoch": 0.028643233380383517, "learning_rate": 4e-05, "loss": 0.3332, "step": 13 }, { "epoch": 0.030846559025028402, "learning_rate": 4.3333333333333334e-05, "loss": 0.3663, "step": 14 }, { "epoch": 0.03304988466967329, "learning_rate": 4.666666666666667e-05, "loss": 0.3129, "step": 15 }, { "epoch": 0.035253210314318176, "learning_rate": 5e-05, "loss": 0.3753, "step": 16 }, { "epoch": 0.03745653595896306, "learning_rate": 4.994400895856663e-05, "loss": 0.373, "step": 17 }, { "epoch": 0.039659861603607946, "learning_rate": 4.988801791713326e-05, "loss": 0.3474, "step": 18 }, { "epoch": 0.04186318724825283, "learning_rate": 4.983202687569989e-05, "loss": 0.3783, "step": 19 }, { "epoch": 0.044066512892897716, "learning_rate": 4.977603583426652e-05, "loss": 0.373, "step": 20 }, { "epoch": 0.0462698385375426, "learning_rate": 4.972004479283315e-05, "loss": 0.3482, "step": 21 }, { "epoch": 0.048473164182187486, "learning_rate": 4.966405375139978e-05, "loss": 0.3564, "step": 22 }, { "epoch": 0.05067648982683238, "learning_rate": 4.960806270996641e-05, "loss": 0.3085, "step": 23 }, { "epoch": 0.052879815471477264, "learning_rate": 4.9552071668533036e-05, "loss": 0.2783, "step": 24 }, { "epoch": 0.05508314111612215, "learning_rate": 4.9496080627099664e-05, "loss": 0.3635, "step": 25 }, { "epoch": 0.057286466760767034, "learning_rate": 4.944008958566629e-05, "loss": 0.3594, "step": 26 }, { "epoch": 0.05948979240541192, "learning_rate": 4.938409854423293e-05, "loss": 0.366, "step": 27 }, { "epoch": 0.061693118050056804, "learning_rate": 4.9328107502799556e-05, "loss": 0.3868, "step": 28 }, { "epoch": 0.0638964436947017, "learning_rate": 4.9272116461366184e-05, "loss": 0.355, "step": 29 }, { "epoch": 0.06609976933934658, "learning_rate": 4.921612541993281e-05, "loss": 0.3484, "step": 30 }, { "epoch": 0.06830309498399147, "learning_rate": 4.916013437849945e-05, "loss": 0.3848, "step": 31 }, { "epoch": 0.07050642062863635, "learning_rate": 4.910414333706607e-05, "loss": 0.3442, "step": 32 }, { "epoch": 0.07270974627328124, "learning_rate": 4.90481522956327e-05, "loss": 0.3459, "step": 33 }, { "epoch": 0.07491307191792612, "learning_rate": 4.899216125419933e-05, "loss": 0.3971, "step": 34 }, { "epoch": 0.077116397562571, "learning_rate": 4.893617021276596e-05, "loss": 0.4116, "step": 35 }, { "epoch": 0.07931972320721589, "learning_rate": 4.888017917133259e-05, "loss": 0.3585, "step": 36 }, { "epoch": 0.08152304885186078, "learning_rate": 4.882418812989922e-05, "loss": 0.3788, "step": 37 }, { "epoch": 0.08372637449650566, "learning_rate": 4.876819708846585e-05, "loss": 0.4267, "step": 38 }, { "epoch": 0.08592970014115055, "learning_rate": 4.8712206047032474e-05, "loss": 0.328, "step": 39 }, { "epoch": 0.08813302578579543, "learning_rate": 4.86562150055991e-05, "loss": 0.3519, "step": 40 }, { "epoch": 0.09033635143044032, "learning_rate": 4.860022396416574e-05, "loss": 0.3659, "step": 41 }, { "epoch": 0.0925396770750852, "learning_rate": 4.8544232922732366e-05, "loss": 0.4017, "step": 42 }, { "epoch": 0.09474300271973009, "learning_rate": 4.8488241881298994e-05, "loss": 0.3212, "step": 43 }, { "epoch": 0.09694632836437497, "learning_rate": 4.843225083986562e-05, "loss": 0.3381, "step": 44 }, { "epoch": 0.09914965400901986, "learning_rate": 4.837625979843226e-05, "loss": 0.404, "step": 45 }, { "epoch": 0.10135297965366476, "learning_rate": 4.832026875699888e-05, "loss": 0.3611, "step": 46 }, { "epoch": 0.10355630529830964, "learning_rate": 4.8264277715565514e-05, "loss": 0.335, "step": 47 }, { "epoch": 0.10575963094295453, "learning_rate": 4.820828667413214e-05, "loss": 0.3233, "step": 48 }, { "epoch": 0.10796295658759941, "learning_rate": 4.815229563269877e-05, "loss": 0.3177, "step": 49 }, { "epoch": 0.1101662822322443, "learning_rate": 4.80963045912654e-05, "loss": 0.3595, "step": 50 }, { "epoch": 0.11236960787688918, "learning_rate": 4.804031354983203e-05, "loss": 0.3953, "step": 51 }, { "epoch": 0.11457293352153407, "learning_rate": 4.798432250839866e-05, "loss": 0.3744, "step": 52 }, { "epoch": 0.11677625916617895, "learning_rate": 4.7928331466965284e-05, "loss": 0.347, "step": 53 }, { "epoch": 0.11897958481082384, "learning_rate": 4.787234042553192e-05, "loss": 0.3549, "step": 54 }, { "epoch": 0.12118291045546872, "learning_rate": 4.781634938409855e-05, "loss": 0.3974, "step": 55 }, { "epoch": 0.12338623610011361, "learning_rate": 4.7760358342665176e-05, "loss": 0.3458, "step": 56 }, { "epoch": 0.1255895617447585, "learning_rate": 4.7704367301231804e-05, "loss": 0.3478, "step": 57 }, { "epoch": 0.1277928873894034, "learning_rate": 4.764837625979843e-05, "loss": 0.32, "step": 58 }, { "epoch": 0.12999621303404826, "learning_rate": 4.759238521836507e-05, "loss": 0.3217, "step": 59 }, { "epoch": 0.13219953867869316, "learning_rate": 4.753639417693169e-05, "loss": 0.3226, "step": 60 }, { "epoch": 0.13440286432333803, "learning_rate": 4.7480403135498324e-05, "loss": 0.3535, "step": 61 }, { "epoch": 0.13660618996798293, "learning_rate": 4.742441209406495e-05, "loss": 0.3876, "step": 62 }, { "epoch": 0.1388095156126278, "learning_rate": 4.736842105263158e-05, "loss": 0.3447, "step": 63 }, { "epoch": 0.1410128412572727, "learning_rate": 4.731243001119821e-05, "loss": 0.3108, "step": 64 }, { "epoch": 0.14321616690191757, "learning_rate": 4.725643896976484e-05, "loss": 0.3199, "step": 65 }, { "epoch": 0.14541949254656247, "learning_rate": 4.720044792833147e-05, "loss": 0.329, "step": 66 }, { "epoch": 0.14762281819120734, "learning_rate": 4.7144456886898094e-05, "loss": 0.3156, "step": 67 }, { "epoch": 0.14982614383585224, "learning_rate": 4.708846584546473e-05, "loss": 0.3657, "step": 68 }, { "epoch": 0.15202946948049711, "learning_rate": 4.703247480403136e-05, "loss": 0.3094, "step": 69 }, { "epoch": 0.154232795125142, "learning_rate": 4.6976483762597986e-05, "loss": 0.3314, "step": 70 }, { "epoch": 0.15643612076978688, "learning_rate": 4.6920492721164614e-05, "loss": 0.3504, "step": 71 }, { "epoch": 0.15863944641443178, "learning_rate": 4.686450167973124e-05, "loss": 0.3949, "step": 72 }, { "epoch": 0.16084277205907666, "learning_rate": 4.680851063829788e-05, "loss": 0.3925, "step": 73 }, { "epoch": 0.16304609770372155, "learning_rate": 4.67525195968645e-05, "loss": 0.3272, "step": 74 }, { "epoch": 0.16524942334836645, "learning_rate": 4.6696528555431134e-05, "loss": 0.3718, "step": 75 }, { "epoch": 0.16745274899301132, "learning_rate": 4.664053751399776e-05, "loss": 0.3937, "step": 76 }, { "epoch": 0.16965607463765622, "learning_rate": 4.65845464725644e-05, "loss": 0.3246, "step": 77 }, { "epoch": 0.1718594002823011, "learning_rate": 4.652855543113102e-05, "loss": 0.3679, "step": 78 }, { "epoch": 0.174062725926946, "learning_rate": 4.647256438969765e-05, "loss": 0.3595, "step": 79 }, { "epoch": 0.17626605157159086, "learning_rate": 4.641657334826428e-05, "loss": 0.3398, "step": 80 }, { "epoch": 0.17846937721623576, "learning_rate": 4.6360582306830904e-05, "loss": 0.3083, "step": 81 }, { "epoch": 0.18067270286088064, "learning_rate": 4.630459126539754e-05, "loss": 0.3463, "step": 82 }, { "epoch": 0.18287602850552553, "learning_rate": 4.624860022396417e-05, "loss": 0.316, "step": 83 }, { "epoch": 0.1850793541501704, "learning_rate": 4.61926091825308e-05, "loss": 0.3296, "step": 84 }, { "epoch": 0.1872826797948153, "learning_rate": 4.6136618141097424e-05, "loss": 0.35, "step": 85 }, { "epoch": 0.18948600543946018, "learning_rate": 4.608062709966405e-05, "loss": 0.3388, "step": 86 }, { "epoch": 0.19168933108410507, "learning_rate": 4.602463605823069e-05, "loss": 0.3729, "step": 87 }, { "epoch": 0.19389265672874995, "learning_rate": 4.5968645016797316e-05, "loss": 0.305, "step": 88 }, { "epoch": 0.19609598237339484, "learning_rate": 4.5912653975363944e-05, "loss": 0.3037, "step": 89 }, { "epoch": 0.19829930801803972, "learning_rate": 4.585666293393057e-05, "loss": 0.407, "step": 90 }, { "epoch": 0.20050263366268462, "learning_rate": 4.580067189249721e-05, "loss": 0.3349, "step": 91 }, { "epoch": 0.20270595930732951, "learning_rate": 4.574468085106383e-05, "loss": 0.3807, "step": 92 }, { "epoch": 0.20490928495197439, "learning_rate": 4.5688689809630464e-05, "loss": 0.3134, "step": 93 }, { "epoch": 0.20711261059661928, "learning_rate": 4.563269876819709e-05, "loss": 0.3666, "step": 94 }, { "epoch": 0.20931593624126416, "learning_rate": 4.557670772676372e-05, "loss": 0.3559, "step": 95 }, { "epoch": 0.21151926188590905, "learning_rate": 4.552071668533035e-05, "loss": 0.3828, "step": 96 }, { "epoch": 0.21372258753055393, "learning_rate": 4.546472564389698e-05, "loss": 0.3693, "step": 97 }, { "epoch": 0.21592591317519882, "learning_rate": 4.540873460246361e-05, "loss": 0.3306, "step": 98 }, { "epoch": 0.2181292388198437, "learning_rate": 4.5352743561030234e-05, "loss": 0.3975, "step": 99 }, { "epoch": 0.2203325644644886, "learning_rate": 4.529675251959687e-05, "loss": 0.356, "step": 100 }, { "epoch": 0.22253589010913347, "learning_rate": 4.52407614781635e-05, "loss": 0.3303, "step": 101 }, { "epoch": 0.22473921575377837, "learning_rate": 4.5184770436730126e-05, "loss": 0.3826, "step": 102 }, { "epoch": 0.22694254139842324, "learning_rate": 4.5128779395296754e-05, "loss": 0.3657, "step": 103 }, { "epoch": 0.22914586704306814, "learning_rate": 4.507278835386338e-05, "loss": 0.362, "step": 104 }, { "epoch": 0.231349192687713, "learning_rate": 4.501679731243002e-05, "loss": 0.3379, "step": 105 }, { "epoch": 0.2335525183323579, "learning_rate": 4.496080627099664e-05, "loss": 0.3597, "step": 106 }, { "epoch": 0.23575584397700278, "learning_rate": 4.4904815229563274e-05, "loss": 0.3514, "step": 107 }, { "epoch": 0.23795916962164768, "learning_rate": 4.48488241881299e-05, "loss": 0.3194, "step": 108 }, { "epoch": 0.24016249526629255, "learning_rate": 4.479283314669653e-05, "loss": 0.3519, "step": 109 }, { "epoch": 0.24236582091093745, "learning_rate": 4.473684210526316e-05, "loss": 0.3155, "step": 110 }, { "epoch": 0.24456914655558235, "learning_rate": 4.468085106382979e-05, "loss": 0.3547, "step": 111 }, { "epoch": 0.24677247220022722, "learning_rate": 4.462486002239642e-05, "loss": 0.3453, "step": 112 }, { "epoch": 0.24897579784487212, "learning_rate": 4.4568868980963044e-05, "loss": 0.3884, "step": 113 }, { "epoch": 0.251179123489517, "learning_rate": 4.451287793952968e-05, "loss": 0.3504, "step": 114 }, { "epoch": 0.25338244913416186, "learning_rate": 4.445688689809631e-05, "loss": 0.3374, "step": 115 }, { "epoch": 0.2555857747788068, "learning_rate": 4.4400895856662936e-05, "loss": 0.3613, "step": 116 }, { "epoch": 0.25778910042345166, "learning_rate": 4.4344904815229564e-05, "loss": 0.3118, "step": 117 }, { "epoch": 0.2599924260680965, "learning_rate": 4.428891377379619e-05, "loss": 0.3152, "step": 118 }, { "epoch": 0.2621957517127414, "learning_rate": 4.423292273236283e-05, "loss": 0.2972, "step": 119 }, { "epoch": 0.2643990773573863, "learning_rate": 4.417693169092945e-05, "loss": 0.3496, "step": 120 }, { "epoch": 0.2666024030020312, "learning_rate": 4.4120940649496084e-05, "loss": 0.3518, "step": 121 }, { "epoch": 0.26880572864667607, "learning_rate": 4.406494960806271e-05, "loss": 0.3261, "step": 122 }, { "epoch": 0.27100905429132094, "learning_rate": 4.400895856662934e-05, "loss": 0.3358, "step": 123 }, { "epoch": 0.27321237993596587, "learning_rate": 4.395296752519597e-05, "loss": 0.2997, "step": 124 }, { "epoch": 0.27541570558061074, "learning_rate": 4.38969764837626e-05, "loss": 0.308, "step": 125 }, { "epoch": 0.2776190312252556, "learning_rate": 4.384098544232923e-05, "loss": 0.3644, "step": 126 }, { "epoch": 0.2798223568699005, "learning_rate": 4.3784994400895854e-05, "loss": 0.3128, "step": 127 }, { "epoch": 0.2820256825145454, "learning_rate": 4.372900335946249e-05, "loss": 0.3235, "step": 128 }, { "epoch": 0.2842290081591903, "learning_rate": 4.367301231802912e-05, "loss": 0.3441, "step": 129 }, { "epoch": 0.28643233380383515, "learning_rate": 4.3617021276595746e-05, "loss": 0.3565, "step": 130 }, { "epoch": 0.2886356594484801, "learning_rate": 4.3561030235162374e-05, "loss": 0.3663, "step": 131 }, { "epoch": 0.29083898509312495, "learning_rate": 4.350503919372901e-05, "loss": 0.3912, "step": 132 }, { "epoch": 0.2930423107377698, "learning_rate": 4.344904815229564e-05, "loss": 0.3473, "step": 133 }, { "epoch": 0.2952456363824147, "learning_rate": 4.339305711086226e-05, "loss": 0.3971, "step": 134 }, { "epoch": 0.2974489620270596, "learning_rate": 4.3337066069428894e-05, "loss": 0.3203, "step": 135 }, { "epoch": 0.2996522876717045, "learning_rate": 4.328107502799552e-05, "loss": 0.3691, "step": 136 }, { "epoch": 0.30185561331634936, "learning_rate": 4.322508398656215e-05, "loss": 0.3743, "step": 137 }, { "epoch": 0.30405893896099423, "learning_rate": 4.316909294512878e-05, "loss": 0.351, "step": 138 }, { "epoch": 0.30626226460563916, "learning_rate": 4.3113101903695414e-05, "loss": 0.3515, "step": 139 }, { "epoch": 0.308465590250284, "learning_rate": 4.305711086226204e-05, "loss": 0.304, "step": 140 }, { "epoch": 0.3106689158949289, "learning_rate": 4.3001119820828664e-05, "loss": 0.344, "step": 141 }, { "epoch": 0.31287224153957377, "learning_rate": 4.29451287793953e-05, "loss": 0.3147, "step": 142 }, { "epoch": 0.3150755671842187, "learning_rate": 4.288913773796193e-05, "loss": 0.3861, "step": 143 }, { "epoch": 0.31727889282886357, "learning_rate": 4.2833146696528556e-05, "loss": 0.3295, "step": 144 }, { "epoch": 0.31948221847350844, "learning_rate": 4.2777155655095184e-05, "loss": 0.3541, "step": 145 }, { "epoch": 0.3216855441181533, "learning_rate": 4.272116461366182e-05, "loss": 0.3278, "step": 146 }, { "epoch": 0.32388886976279824, "learning_rate": 4.266517357222845e-05, "loss": 0.3607, "step": 147 }, { "epoch": 0.3260921954074431, "learning_rate": 4.2609182530795076e-05, "loss": 0.3033, "step": 148 }, { "epoch": 0.328295521052088, "learning_rate": 4.2553191489361704e-05, "loss": 0.3541, "step": 149 }, { "epoch": 0.3304988466967329, "learning_rate": 4.249720044792833e-05, "loss": 0.3553, "step": 150 }, { "epoch": 0.3327021723413778, "learning_rate": 4.244120940649496e-05, "loss": 0.3697, "step": 151 }, { "epoch": 0.33490549798602265, "learning_rate": 4.238521836506159e-05, "loss": 0.341, "step": 152 }, { "epoch": 0.3371088236306675, "learning_rate": 4.2329227323628225e-05, "loss": 0.3221, "step": 153 }, { "epoch": 0.33931214927531245, "learning_rate": 4.227323628219485e-05, "loss": 0.3142, "step": 154 }, { "epoch": 0.3415154749199573, "learning_rate": 4.221724524076148e-05, "loss": 0.3497, "step": 155 }, { "epoch": 0.3437188005646022, "learning_rate": 4.216125419932811e-05, "loss": 0.3192, "step": 156 }, { "epoch": 0.34592212620924706, "learning_rate": 4.210526315789474e-05, "loss": 0.3391, "step": 157 }, { "epoch": 0.348125451853892, "learning_rate": 4.2049272116461366e-05, "loss": 0.3203, "step": 158 }, { "epoch": 0.35032877749853686, "learning_rate": 4.1993281075027994e-05, "loss": 0.3407, "step": 159 }, { "epoch": 0.35253210314318173, "learning_rate": 4.193729003359463e-05, "loss": 0.3379, "step": 160 }, { "epoch": 0.3547354287878266, "learning_rate": 4.188129899216126e-05, "loss": 0.359, "step": 161 }, { "epoch": 0.35693875443247153, "learning_rate": 4.1825307950727886e-05, "loss": 0.3315, "step": 162 }, { "epoch": 0.3591420800771164, "learning_rate": 4.1769316909294514e-05, "loss": 0.3456, "step": 163 }, { "epoch": 0.36134540572176127, "learning_rate": 4.171332586786114e-05, "loss": 0.3836, "step": 164 }, { "epoch": 0.3635487313664062, "learning_rate": 4.165733482642777e-05, "loss": 0.3276, "step": 165 }, { "epoch": 0.36575205701105107, "learning_rate": 4.16013437849944e-05, "loss": 0.3468, "step": 166 }, { "epoch": 0.36795538265569594, "learning_rate": 4.1545352743561035e-05, "loss": 0.3648, "step": 167 }, { "epoch": 0.3701587083003408, "learning_rate": 4.148936170212766e-05, "loss": 0.3457, "step": 168 }, { "epoch": 0.37236203394498574, "learning_rate": 4.143337066069429e-05, "loss": 0.2898, "step": 169 }, { "epoch": 0.3745653595896306, "learning_rate": 4.137737961926092e-05, "loss": 0.3647, "step": 170 }, { "epoch": 0.3767686852342755, "learning_rate": 4.1321388577827555e-05, "loss": 0.3321, "step": 171 }, { "epoch": 0.37897201087892035, "learning_rate": 4.1265397536394176e-05, "loss": 0.3411, "step": 172 }, { "epoch": 0.3811753365235653, "learning_rate": 4.1209406494960804e-05, "loss": 0.3252, "step": 173 }, { "epoch": 0.38337866216821015, "learning_rate": 4.115341545352744e-05, "loss": 0.3251, "step": 174 }, { "epoch": 0.385581987812855, "learning_rate": 4.109742441209407e-05, "loss": 0.335, "step": 175 }, { "epoch": 0.3877853134574999, "learning_rate": 4.1041433370660696e-05, "loss": 0.364, "step": 176 }, { "epoch": 0.3899886391021448, "learning_rate": 4.0985442329227325e-05, "loss": 0.3241, "step": 177 }, { "epoch": 0.3921919647467897, "learning_rate": 4.092945128779396e-05, "loss": 0.3339, "step": 178 }, { "epoch": 0.39439529039143456, "learning_rate": 4.087346024636058e-05, "loss": 0.3395, "step": 179 }, { "epoch": 0.39659861603607943, "learning_rate": 4.081746920492721e-05, "loss": 0.317, "step": 180 }, { "epoch": 0.39880194168072436, "learning_rate": 4.0761478163493845e-05, "loss": 0.3359, "step": 181 }, { "epoch": 0.40100526732536923, "learning_rate": 4.070548712206047e-05, "loss": 0.3086, "step": 182 }, { "epoch": 0.4032085929700141, "learning_rate": 4.06494960806271e-05, "loss": 0.3568, "step": 183 }, { "epoch": 0.40541191861465903, "learning_rate": 4.059350503919373e-05, "loss": 0.3415, "step": 184 }, { "epoch": 0.4076152442593039, "learning_rate": 4.0537513997760365e-05, "loss": 0.3099, "step": 185 }, { "epoch": 0.40981856990394877, "learning_rate": 4.0481522956326986e-05, "loss": 0.3563, "step": 186 }, { "epoch": 0.41202189554859364, "learning_rate": 4.0425531914893614e-05, "loss": 0.3492, "step": 187 }, { "epoch": 0.41422522119323857, "learning_rate": 4.036954087346025e-05, "loss": 0.3649, "step": 188 }, { "epoch": 0.41642854683788344, "learning_rate": 4.031354983202688e-05, "loss": 0.376, "step": 189 }, { "epoch": 0.4186318724825283, "learning_rate": 4.0257558790593506e-05, "loss": 0.3637, "step": 190 }, { "epoch": 0.4208351981271732, "learning_rate": 4.0201567749160135e-05, "loss": 0.3301, "step": 191 }, { "epoch": 0.4230385237718181, "learning_rate": 4.014557670772677e-05, "loss": 0.3638, "step": 192 }, { "epoch": 0.425241849416463, "learning_rate": 4.008958566629339e-05, "loss": 0.337, "step": 193 }, { "epoch": 0.42744517506110785, "learning_rate": 4.0033594624860026e-05, "loss": 0.3583, "step": 194 }, { "epoch": 0.4296485007057527, "learning_rate": 3.9977603583426655e-05, "loss": 0.3652, "step": 195 }, { "epoch": 0.43185182635039765, "learning_rate": 3.992161254199328e-05, "loss": 0.3277, "step": 196 }, { "epoch": 0.4340551519950425, "learning_rate": 3.986562150055991e-05, "loss": 0.3107, "step": 197 }, { "epoch": 0.4362584776396874, "learning_rate": 3.980963045912654e-05, "loss": 0.3634, "step": 198 }, { "epoch": 0.43846180328433226, "learning_rate": 3.9753639417693175e-05, "loss": 0.3296, "step": 199 }, { "epoch": 0.4406651289289772, "learning_rate": 3.9697648376259796e-05, "loss": 0.3087, "step": 200 }, { "epoch": 0.44286845457362206, "learning_rate": 3.964165733482643e-05, "loss": 0.3818, "step": 201 }, { "epoch": 0.44507178021826693, "learning_rate": 3.958566629339306e-05, "loss": 0.3395, "step": 202 }, { "epoch": 0.44727510586291186, "learning_rate": 3.952967525195969e-05, "loss": 0.3131, "step": 203 }, { "epoch": 0.44947843150755673, "learning_rate": 3.9473684210526316e-05, "loss": 0.3294, "step": 204 }, { "epoch": 0.4516817571522016, "learning_rate": 3.9417693169092945e-05, "loss": 0.3553, "step": 205 }, { "epoch": 0.4538850827968465, "learning_rate": 3.936170212765958e-05, "loss": 0.3129, "step": 206 }, { "epoch": 0.4560884084414914, "learning_rate": 3.93057110862262e-05, "loss": 0.3634, "step": 207 }, { "epoch": 0.45829173408613627, "learning_rate": 3.9249720044792836e-05, "loss": 0.3127, "step": 208 }, { "epoch": 0.46049505973078114, "learning_rate": 3.9193729003359465e-05, "loss": 0.3603, "step": 209 }, { "epoch": 0.462698385375426, "learning_rate": 3.91377379619261e-05, "loss": 0.3289, "step": 210 }, { "epoch": 0.46490171102007094, "learning_rate": 3.908174692049272e-05, "loss": 0.3154, "step": 211 }, { "epoch": 0.4671050366647158, "learning_rate": 3.902575587905935e-05, "loss": 0.2939, "step": 212 }, { "epoch": 0.4693083623093607, "learning_rate": 3.8969764837625985e-05, "loss": 0.2989, "step": 213 }, { "epoch": 0.47151168795400555, "learning_rate": 3.891377379619261e-05, "loss": 0.3398, "step": 214 }, { "epoch": 0.4737150135986505, "learning_rate": 3.885778275475924e-05, "loss": 0.3259, "step": 215 }, { "epoch": 0.47591833924329535, "learning_rate": 3.880179171332587e-05, "loss": 0.359, "step": 216 }, { "epoch": 0.4781216648879402, "learning_rate": 3.8745800671892505e-05, "loss": 0.3197, "step": 217 }, { "epoch": 0.4803249905325851, "learning_rate": 3.8689809630459126e-05, "loss": 0.3224, "step": 218 }, { "epoch": 0.48252831617723, "learning_rate": 3.8633818589025755e-05, "loss": 0.2804, "step": 219 }, { "epoch": 0.4847316418218749, "learning_rate": 3.857782754759239e-05, "loss": 0.2935, "step": 220 }, { "epoch": 0.48693496746651976, "learning_rate": 3.852183650615902e-05, "loss": 0.3372, "step": 221 }, { "epoch": 0.4891382931111647, "learning_rate": 3.8465845464725646e-05, "loss": 0.3031, "step": 222 }, { "epoch": 0.49134161875580956, "learning_rate": 3.8409854423292275e-05, "loss": 0.3388, "step": 223 }, { "epoch": 0.49354494440045443, "learning_rate": 3.835386338185891e-05, "loss": 0.3445, "step": 224 }, { "epoch": 0.4957482700450993, "learning_rate": 3.829787234042553e-05, "loss": 0.3138, "step": 225 }, { "epoch": 0.49795159568974423, "learning_rate": 3.824188129899216e-05, "loss": 0.3185, "step": 226 }, { "epoch": 0.5001549213343891, "learning_rate": 3.8185890257558795e-05, "loss": 0.305, "step": 227 }, { "epoch": 0.502358246979034, "learning_rate": 3.812989921612542e-05, "loss": 0.3322, "step": 228 }, { "epoch": 0.5045615726236788, "learning_rate": 3.807390817469205e-05, "loss": 0.3629, "step": 229 }, { "epoch": 0.5067648982683237, "learning_rate": 3.801791713325868e-05, "loss": 0.3774, "step": 230 }, { "epoch": 0.5089682239129686, "learning_rate": 3.7961926091825315e-05, "loss": 0.3287, "step": 231 }, { "epoch": 0.5111715495576136, "learning_rate": 3.7905935050391936e-05, "loss": 0.3311, "step": 232 }, { "epoch": 0.5133748752022584, "learning_rate": 3.784994400895857e-05, "loss": 0.3536, "step": 233 }, { "epoch": 0.5155782008469033, "learning_rate": 3.77939529675252e-05, "loss": 0.3713, "step": 234 }, { "epoch": 0.5177815264915482, "learning_rate": 3.773796192609183e-05, "loss": 0.3302, "step": 235 }, { "epoch": 0.519984852136193, "learning_rate": 3.7681970884658456e-05, "loss": 0.2943, "step": 236 }, { "epoch": 0.5221881777808379, "learning_rate": 3.7625979843225085e-05, "loss": 0.3253, "step": 237 }, { "epoch": 0.5243915034254828, "learning_rate": 3.756998880179172e-05, "loss": 0.3145, "step": 238 }, { "epoch": 0.5265948290701278, "learning_rate": 3.751399776035834e-05, "loss": 0.3417, "step": 239 }, { "epoch": 0.5287981547147727, "learning_rate": 3.7458006718924976e-05, "loss": 0.3146, "step": 240 }, { "epoch": 0.5310014803594175, "learning_rate": 3.7402015677491605e-05, "loss": 0.3522, "step": 241 }, { "epoch": 0.5332048060040624, "learning_rate": 3.734602463605823e-05, "loss": 0.3418, "step": 242 }, { "epoch": 0.5354081316487073, "learning_rate": 3.729003359462486e-05, "loss": 0.3286, "step": 243 }, { "epoch": 0.5376114572933521, "learning_rate": 3.723404255319149e-05, "loss": 0.3516, "step": 244 }, { "epoch": 0.539814782937997, "learning_rate": 3.7178051511758125e-05, "loss": 0.3359, "step": 245 }, { "epoch": 0.5420181085826419, "learning_rate": 3.7122060470324746e-05, "loss": 0.3684, "step": 246 }, { "epoch": 0.5442214342272869, "learning_rate": 3.706606942889138e-05, "loss": 0.3171, "step": 247 }, { "epoch": 0.5464247598719317, "learning_rate": 3.701007838745801e-05, "loss": 0.3842, "step": 248 }, { "epoch": 0.5486280855165766, "learning_rate": 3.695408734602464e-05, "loss": 0.3396, "step": 249 }, { "epoch": 0.5508314111612215, "learning_rate": 3.6898096304591266e-05, "loss": 0.3645, "step": 250 }, { "epoch": 0.5530347368058663, "learning_rate": 3.6842105263157895e-05, "loss": 0.3014, "step": 251 }, { "epoch": 0.5552380624505112, "learning_rate": 3.678611422172453e-05, "loss": 0.336, "step": 252 }, { "epoch": 0.5574413880951561, "learning_rate": 3.673012318029115e-05, "loss": 0.422, "step": 253 }, { "epoch": 0.559644713739801, "learning_rate": 3.6674132138857786e-05, "loss": 0.3374, "step": 254 }, { "epoch": 0.5618480393844459, "learning_rate": 3.6618141097424415e-05, "loss": 0.3345, "step": 255 }, { "epoch": 0.5640513650290908, "learning_rate": 3.656215005599104e-05, "loss": 0.3256, "step": 256 }, { "epoch": 0.5662546906737357, "learning_rate": 3.650615901455767e-05, "loss": 0.357, "step": 257 }, { "epoch": 0.5684580163183806, "learning_rate": 3.64501679731243e-05, "loss": 0.3226, "step": 258 }, { "epoch": 0.5706613419630254, "learning_rate": 3.6394176931690935e-05, "loss": 0.3935, "step": 259 }, { "epoch": 0.5728646676076703, "learning_rate": 3.6338185890257556e-05, "loss": 0.3606, "step": 260 }, { "epoch": 0.5750679932523152, "learning_rate": 3.628219484882419e-05, "loss": 0.3711, "step": 261 }, { "epoch": 0.5772713188969602, "learning_rate": 3.622620380739082e-05, "loss": 0.3201, "step": 262 }, { "epoch": 0.579474644541605, "learning_rate": 3.617021276595745e-05, "loss": 0.3218, "step": 263 }, { "epoch": 0.5816779701862499, "learning_rate": 3.6114221724524076e-05, "loss": 0.3124, "step": 264 }, { "epoch": 0.5838812958308948, "learning_rate": 3.6058230683090705e-05, "loss": 0.3106, "step": 265 }, { "epoch": 0.5860846214755396, "learning_rate": 3.600223964165734e-05, "loss": 0.3999, "step": 266 }, { "epoch": 0.5882879471201845, "learning_rate": 3.594624860022396e-05, "loss": 0.3769, "step": 267 }, { "epoch": 0.5904912727648294, "learning_rate": 3.5890257558790596e-05, "loss": 0.3273, "step": 268 }, { "epoch": 0.5926945984094742, "learning_rate": 3.5834266517357225e-05, "loss": 0.2974, "step": 269 }, { "epoch": 0.5948979240541192, "learning_rate": 3.577827547592385e-05, "loss": 0.2956, "step": 270 }, { "epoch": 0.5971012496987641, "learning_rate": 3.572228443449048e-05, "loss": 0.3313, "step": 271 }, { "epoch": 0.599304575343409, "learning_rate": 3.5666293393057117e-05, "loss": 0.3375, "step": 272 }, { "epoch": 0.6015079009880538, "learning_rate": 3.5610302351623745e-05, "loss": 0.3106, "step": 273 }, { "epoch": 0.6037112266326987, "learning_rate": 3.5554311310190366e-05, "loss": 0.3853, "step": 274 }, { "epoch": 0.6059145522773436, "learning_rate": 3.5498320268757e-05, "loss": 0.3104, "step": 275 }, { "epoch": 0.6081178779219885, "learning_rate": 3.544232922732363e-05, "loss": 0.2796, "step": 276 }, { "epoch": 0.6103212035666334, "learning_rate": 3.538633818589026e-05, "loss": 0.3284, "step": 277 }, { "epoch": 0.6125245292112783, "learning_rate": 3.5330347144456886e-05, "loss": 0.3359, "step": 278 }, { "epoch": 0.6147278548559232, "learning_rate": 3.527435610302352e-05, "loss": 0.3284, "step": 279 }, { "epoch": 0.616931180500568, "learning_rate": 3.521836506159015e-05, "loss": 0.3275, "step": 280 }, { "epoch": 0.6191345061452129, "learning_rate": 3.516237402015677e-05, "loss": 0.3061, "step": 281 }, { "epoch": 0.6213378317898578, "learning_rate": 3.5106382978723407e-05, "loss": 0.321, "step": 282 }, { "epoch": 0.6235411574345027, "learning_rate": 3.5050391937290035e-05, "loss": 0.2993, "step": 283 }, { "epoch": 0.6257444830791475, "learning_rate": 3.499440089585666e-05, "loss": 0.3777, "step": 284 }, { "epoch": 0.6279478087237925, "learning_rate": 3.493840985442329e-05, "loss": 0.3784, "step": 285 }, { "epoch": 0.6301511343684374, "learning_rate": 3.4882418812989927e-05, "loss": 0.3349, "step": 286 }, { "epoch": 0.6323544600130823, "learning_rate": 3.4826427771556555e-05, "loss": 0.3691, "step": 287 }, { "epoch": 0.6345577856577271, "learning_rate": 3.4770436730123176e-05, "loss": 0.3236, "step": 288 }, { "epoch": 0.636761111302372, "learning_rate": 3.471444568868981e-05, "loss": 0.3304, "step": 289 }, { "epoch": 0.6389644369470169, "learning_rate": 3.465845464725644e-05, "loss": 0.3148, "step": 290 }, { "epoch": 0.6411677625916617, "learning_rate": 3.460246360582307e-05, "loss": 0.3332, "step": 291 }, { "epoch": 0.6433710882363066, "learning_rate": 3.4546472564389696e-05, "loss": 0.3055, "step": 292 }, { "epoch": 0.6455744138809516, "learning_rate": 3.449048152295633e-05, "loss": 0.385, "step": 293 }, { "epoch": 0.6477777395255965, "learning_rate": 3.443449048152296e-05, "loss": 0.365, "step": 294 }, { "epoch": 0.6499810651702413, "learning_rate": 3.437849944008959e-05, "loss": 0.3344, "step": 295 }, { "epoch": 0.6521843908148862, "learning_rate": 3.4322508398656217e-05, "loss": 0.3491, "step": 296 }, { "epoch": 0.6543877164595311, "learning_rate": 3.4266517357222845e-05, "loss": 0.3169, "step": 297 }, { "epoch": 0.656591042104176, "learning_rate": 3.421052631578947e-05, "loss": 0.3788, "step": 298 }, { "epoch": 0.6587943677488208, "learning_rate": 3.41545352743561e-05, "loss": 0.3661, "step": 299 }, { "epoch": 0.6609976933934658, "learning_rate": 3.4098544232922737e-05, "loss": 0.3436, "step": 300 }, { "epoch": 0.6632010190381107, "learning_rate": 3.4042553191489365e-05, "loss": 0.2968, "step": 301 }, { "epoch": 0.6654043446827556, "learning_rate": 3.398656215005599e-05, "loss": 0.3656, "step": 302 }, { "epoch": 0.6676076703274004, "learning_rate": 3.393057110862262e-05, "loss": 0.3357, "step": 303 }, { "epoch": 0.6698109959720453, "learning_rate": 3.387458006718925e-05, "loss": 0.338, "step": 304 }, { "epoch": 0.6720143216166902, "learning_rate": 3.381858902575588e-05, "loss": 0.3072, "step": 305 }, { "epoch": 0.674217647261335, "learning_rate": 3.3762597984322507e-05, "loss": 0.2788, "step": 306 }, { "epoch": 0.6764209729059799, "learning_rate": 3.370660694288914e-05, "loss": 0.3424, "step": 307 }, { "epoch": 0.6786242985506249, "learning_rate": 3.365061590145577e-05, "loss": 0.3282, "step": 308 }, { "epoch": 0.6808276241952698, "learning_rate": 3.35946248600224e-05, "loss": 0.3339, "step": 309 }, { "epoch": 0.6830309498399146, "learning_rate": 3.3538633818589027e-05, "loss": 0.3097, "step": 310 }, { "epoch": 0.6852342754845595, "learning_rate": 3.348264277715566e-05, "loss": 0.2883, "step": 311 }, { "epoch": 0.6874376011292044, "learning_rate": 3.342665173572228e-05, "loss": 0.3558, "step": 312 }, { "epoch": 0.6896409267738492, "learning_rate": 3.337066069428891e-05, "loss": 0.3503, "step": 313 }, { "epoch": 0.6918442524184941, "learning_rate": 3.331466965285555e-05, "loss": 0.358, "step": 314 }, { "epoch": 0.6940475780631391, "learning_rate": 3.3258678611422175e-05, "loss": 0.3028, "step": 315 }, { "epoch": 0.696250903707784, "learning_rate": 3.32026875699888e-05, "loss": 0.3826, "step": 316 }, { "epoch": 0.6984542293524288, "learning_rate": 3.314669652855543e-05, "loss": 0.3777, "step": 317 }, { "epoch": 0.7006575549970737, "learning_rate": 3.309070548712207e-05, "loss": 0.3116, "step": 318 }, { "epoch": 0.7028608806417186, "learning_rate": 3.303471444568869e-05, "loss": 0.3619, "step": 319 }, { "epoch": 0.7050642062863635, "learning_rate": 3.2978723404255317e-05, "loss": 0.3582, "step": 320 }, { "epoch": 0.7072675319310083, "learning_rate": 3.292273236282195e-05, "loss": 0.3705, "step": 321 }, { "epoch": 0.7094708575756532, "learning_rate": 3.286674132138858e-05, "loss": 0.278, "step": 322 }, { "epoch": 0.7116741832202982, "learning_rate": 3.281075027995521e-05, "loss": 0.3196, "step": 323 }, { "epoch": 0.7138775088649431, "learning_rate": 3.2754759238521837e-05, "loss": 0.304, "step": 324 }, { "epoch": 0.7160808345095879, "learning_rate": 3.269876819708847e-05, "loss": 0.368, "step": 325 }, { "epoch": 0.7182841601542328, "learning_rate": 3.264277715565509e-05, "loss": 0.3445, "step": 326 }, { "epoch": 0.7204874857988777, "learning_rate": 3.258678611422172e-05, "loss": 0.3255, "step": 327 }, { "epoch": 0.7226908114435225, "learning_rate": 3.253079507278836e-05, "loss": 0.3204, "step": 328 }, { "epoch": 0.7248941370881674, "learning_rate": 3.2474804031354985e-05, "loss": 0.3205, "step": 329 }, { "epoch": 0.7270974627328124, "learning_rate": 3.241881298992161e-05, "loss": 0.3234, "step": 330 }, { "epoch": 0.7293007883774573, "learning_rate": 3.236282194848824e-05, "loss": 0.3406, "step": 331 }, { "epoch": 0.7315041140221021, "learning_rate": 3.230683090705488e-05, "loss": 0.3474, "step": 332 }, { "epoch": 0.733707439666747, "learning_rate": 3.22508398656215e-05, "loss": 0.3028, "step": 333 }, { "epoch": 0.7359107653113919, "learning_rate": 3.219484882418813e-05, "loss": 0.3224, "step": 334 }, { "epoch": 0.7381140909560368, "learning_rate": 3.213885778275476e-05, "loss": 0.3049, "step": 335 }, { "epoch": 0.7403174166006816, "learning_rate": 3.208286674132139e-05, "loss": 0.2644, "step": 336 }, { "epoch": 0.7425207422453265, "learning_rate": 3.202687569988802e-05, "loss": 0.3707, "step": 337 }, { "epoch": 0.7447240678899715, "learning_rate": 3.197088465845465e-05, "loss": 0.3538, "step": 338 }, { "epoch": 0.7469273935346163, "learning_rate": 3.191489361702128e-05, "loss": 0.3591, "step": 339 }, { "epoch": 0.7491307191792612, "learning_rate": 3.185890257558791e-05, "loss": 0.3472, "step": 340 }, { "epoch": 0.7513340448239061, "learning_rate": 3.180291153415454e-05, "loss": 0.2976, "step": 341 }, { "epoch": 0.753537370468551, "learning_rate": 3.174692049272117e-05, "loss": 0.3356, "step": 342 }, { "epoch": 0.7557406961131958, "learning_rate": 3.1690929451287795e-05, "loss": 0.3689, "step": 343 }, { "epoch": 0.7579440217578407, "learning_rate": 3.163493840985442e-05, "loss": 0.3326, "step": 344 }, { "epoch": 0.7601473474024856, "learning_rate": 3.157894736842105e-05, "loss": 0.3358, "step": 345 }, { "epoch": 0.7623506730471306, "learning_rate": 3.152295632698769e-05, "loss": 0.3108, "step": 346 }, { "epoch": 0.7645539986917754, "learning_rate": 3.1466965285554315e-05, "loss": 0.3508, "step": 347 }, { "epoch": 0.7667573243364203, "learning_rate": 3.141097424412094e-05, "loss": 0.3215, "step": 348 }, { "epoch": 0.7689606499810652, "learning_rate": 3.135498320268757e-05, "loss": 0.3429, "step": 349 }, { "epoch": 0.77116397562571, "learning_rate": 3.12989921612542e-05, "loss": 0.3579, "step": 350 }, { "epoch": 0.7733673012703549, "learning_rate": 3.124300111982083e-05, "loss": 0.3391, "step": 351 }, { "epoch": 0.7755706269149998, "learning_rate": 3.118701007838746e-05, "loss": 0.2998, "step": 352 }, { "epoch": 0.7777739525596448, "learning_rate": 3.113101903695409e-05, "loss": 0.3108, "step": 353 }, { "epoch": 0.7799772782042896, "learning_rate": 3.107502799552072e-05, "loss": 0.3102, "step": 354 }, { "epoch": 0.7821806038489345, "learning_rate": 3.101903695408735e-05, "loss": 0.3365, "step": 355 }, { "epoch": 0.7843839294935794, "learning_rate": 3.096304591265398e-05, "loss": 0.3501, "step": 356 }, { "epoch": 0.7865872551382243, "learning_rate": 3.090705487122061e-05, "loss": 0.2936, "step": 357 }, { "epoch": 0.7887905807828691, "learning_rate": 3.085106382978723e-05, "loss": 0.3757, "step": 358 }, { "epoch": 0.790993906427514, "learning_rate": 3.079507278835386e-05, "loss": 0.3199, "step": 359 }, { "epoch": 0.7931972320721589, "learning_rate": 3.07390817469205e-05, "loss": 0.2927, "step": 360 }, { "epoch": 0.7954005577168038, "learning_rate": 3.0683090705487125e-05, "loss": 0.326, "step": 361 }, { "epoch": 0.7976038833614487, "learning_rate": 3.0627099664053753e-05, "loss": 0.3247, "step": 362 }, { "epoch": 0.7998072090060936, "learning_rate": 3.057110862262038e-05, "loss": 0.2971, "step": 363 }, { "epoch": 0.8020105346507385, "learning_rate": 3.0515117581187013e-05, "loss": 0.2974, "step": 364 }, { "epoch": 0.8042138602953833, "learning_rate": 3.0459126539753642e-05, "loss": 0.3774, "step": 365 }, { "epoch": 0.8064171859400282, "learning_rate": 3.0403135498320267e-05, "loss": 0.3513, "step": 366 }, { "epoch": 0.8086205115846731, "learning_rate": 3.0347144456886902e-05, "loss": 0.2809, "step": 367 }, { "epoch": 0.8108238372293181, "learning_rate": 3.0291153415453527e-05, "loss": 0.3702, "step": 368 }, { "epoch": 0.8130271628739629, "learning_rate": 3.023516237402016e-05, "loss": 0.3797, "step": 369 }, { "epoch": 0.8152304885186078, "learning_rate": 3.0179171332586787e-05, "loss": 0.3238, "step": 370 }, { "epoch": 0.8174338141632527, "learning_rate": 3.012318029115342e-05, "loss": 0.3393, "step": 371 }, { "epoch": 0.8196371398078975, "learning_rate": 3.0067189249720047e-05, "loss": 0.2938, "step": 372 }, { "epoch": 0.8218404654525424, "learning_rate": 3.001119820828668e-05, "loss": 0.3467, "step": 373 }, { "epoch": 0.8240437910971873, "learning_rate": 2.9955207166853307e-05, "loss": 0.3892, "step": 374 }, { "epoch": 0.8262471167418322, "learning_rate": 2.9899216125419932e-05, "loss": 0.3416, "step": 375 }, { "epoch": 0.8284504423864771, "learning_rate": 2.9843225083986563e-05, "loss": 0.2999, "step": 376 }, { "epoch": 0.830653768031122, "learning_rate": 2.9787234042553192e-05, "loss": 0.3173, "step": 377 }, { "epoch": 0.8328570936757669, "learning_rate": 2.9731243001119823e-05, "loss": 0.3937, "step": 378 }, { "epoch": 0.8350604193204118, "learning_rate": 2.9675251959686452e-05, "loss": 0.2966, "step": 379 }, { "epoch": 0.8372637449650566, "learning_rate": 2.9619260918253083e-05, "loss": 0.2968, "step": 380 }, { "epoch": 0.8394670706097015, "learning_rate": 2.9563269876819712e-05, "loss": 0.2777, "step": 381 }, { "epoch": 0.8416703962543464, "learning_rate": 2.9507278835386337e-05, "loss": 0.317, "step": 382 }, { "epoch": 0.8438737218989912, "learning_rate": 2.945128779395297e-05, "loss": 0.33, "step": 383 }, { "epoch": 0.8460770475436362, "learning_rate": 2.9395296752519597e-05, "loss": 0.3249, "step": 384 }, { "epoch": 0.8482803731882811, "learning_rate": 2.933930571108623e-05, "loss": 0.337, "step": 385 }, { "epoch": 0.850483698832926, "learning_rate": 2.9283314669652857e-05, "loss": 0.3125, "step": 386 }, { "epoch": 0.8526870244775708, "learning_rate": 2.922732362821949e-05, "loss": 0.3142, "step": 387 }, { "epoch": 0.8548903501222157, "learning_rate": 2.9171332586786117e-05, "loss": 0.3555, "step": 388 }, { "epoch": 0.8570936757668606, "learning_rate": 2.9115341545352742e-05, "loss": 0.3818, "step": 389 }, { "epoch": 0.8592970014115054, "learning_rate": 2.9059350503919373e-05, "loss": 0.3974, "step": 390 }, { "epoch": 0.8615003270561504, "learning_rate": 2.9003359462486002e-05, "loss": 0.3287, "step": 391 }, { "epoch": 0.8637036527007953, "learning_rate": 2.8947368421052634e-05, "loss": 0.299, "step": 392 }, { "epoch": 0.8659069783454402, "learning_rate": 2.8891377379619262e-05, "loss": 0.2839, "step": 393 }, { "epoch": 0.868110303990085, "learning_rate": 2.8835386338185894e-05, "loss": 0.338, "step": 394 }, { "epoch": 0.8703136296347299, "learning_rate": 2.8779395296752522e-05, "loss": 0.3429, "step": 395 }, { "epoch": 0.8725169552793748, "learning_rate": 2.8723404255319154e-05, "loss": 0.3391, "step": 396 }, { "epoch": 0.8747202809240197, "learning_rate": 2.866741321388578e-05, "loss": 0.3061, "step": 397 }, { "epoch": 0.8769236065686645, "learning_rate": 2.8611422172452407e-05, "loss": 0.2952, "step": 398 }, { "epoch": 0.8791269322133095, "learning_rate": 2.855543113101904e-05, "loss": 0.3196, "step": 399 }, { "epoch": 0.8813302578579544, "learning_rate": 2.8499440089585667e-05, "loss": 0.3185, "step": 400 }, { "epoch": 0.8835335835025993, "learning_rate": 2.84434490481523e-05, "loss": 0.3758, "step": 401 }, { "epoch": 0.8857369091472441, "learning_rate": 2.8387458006718927e-05, "loss": 0.2846, "step": 402 }, { "epoch": 0.887940234791889, "learning_rate": 2.833146696528556e-05, "loss": 0.3723, "step": 403 }, { "epoch": 0.8901435604365339, "learning_rate": 2.8275475923852184e-05, "loss": 0.324, "step": 404 }, { "epoch": 0.8923468860811787, "learning_rate": 2.8219484882418812e-05, "loss": 0.3004, "step": 405 }, { "epoch": 0.8945502117258237, "learning_rate": 2.8163493840985444e-05, "loss": 0.2913, "step": 406 }, { "epoch": 0.8967535373704686, "learning_rate": 2.8107502799552072e-05, "loss": 0.3424, "step": 407 }, { "epoch": 0.8989568630151135, "learning_rate": 2.8051511758118704e-05, "loss": 0.3461, "step": 408 }, { "epoch": 0.9011601886597583, "learning_rate": 2.7995520716685332e-05, "loss": 0.3837, "step": 409 }, { "epoch": 0.9033635143044032, "learning_rate": 2.7939529675251964e-05, "loss": 0.3184, "step": 410 }, { "epoch": 0.9055668399490481, "learning_rate": 2.788353863381859e-05, "loss": 0.3427, "step": 411 }, { "epoch": 0.907770165593693, "learning_rate": 2.7827547592385224e-05, "loss": 0.3291, "step": 412 }, { "epoch": 0.9099734912383378, "learning_rate": 2.777155655095185e-05, "loss": 0.3242, "step": 413 }, { "epoch": 0.9121768168829828, "learning_rate": 2.7715565509518477e-05, "loss": 0.3571, "step": 414 }, { "epoch": 0.9143801425276277, "learning_rate": 2.765957446808511e-05, "loss": 0.3477, "step": 415 }, { "epoch": 0.9165834681722725, "learning_rate": 2.7603583426651737e-05, "loss": 0.3772, "step": 416 }, { "epoch": 0.9187867938169174, "learning_rate": 2.754759238521837e-05, "loss": 0.3352, "step": 417 }, { "epoch": 0.9209901194615623, "learning_rate": 2.7491601343784994e-05, "loss": 0.3078, "step": 418 }, { "epoch": 0.9231934451062072, "learning_rate": 2.743561030235163e-05, "loss": 0.319, "step": 419 }, { "epoch": 0.925396770750852, "learning_rate": 2.7379619260918254e-05, "loss": 0.3372, "step": 420 }, { "epoch": 0.9276000963954969, "learning_rate": 2.7323628219484882e-05, "loss": 0.3696, "step": 421 }, { "epoch": 0.9298034220401419, "learning_rate": 2.7267637178051514e-05, "loss": 0.3187, "step": 422 }, { "epoch": 0.9320067476847868, "learning_rate": 2.7211646136618142e-05, "loss": 0.3651, "step": 423 }, { "epoch": 0.9342100733294316, "learning_rate": 2.7155655095184774e-05, "loss": 0.3204, "step": 424 }, { "epoch": 0.9364133989740765, "learning_rate": 2.70996640537514e-05, "loss": 0.328, "step": 425 }, { "epoch": 0.9386167246187214, "learning_rate": 2.7043673012318034e-05, "loss": 0.357, "step": 426 }, { "epoch": 0.9408200502633662, "learning_rate": 2.698768197088466e-05, "loss": 0.3399, "step": 427 }, { "epoch": 0.9430233759080111, "learning_rate": 2.6931690929451287e-05, "loss": 0.3349, "step": 428 }, { "epoch": 0.9452267015526561, "learning_rate": 2.687569988801792e-05, "loss": 0.3497, "step": 429 }, { "epoch": 0.947430027197301, "learning_rate": 2.6819708846584547e-05, "loss": 0.3402, "step": 430 }, { "epoch": 0.9496333528419458, "learning_rate": 2.676371780515118e-05, "loss": 0.286, "step": 431 }, { "epoch": 0.9518366784865907, "learning_rate": 2.6707726763717804e-05, "loss": 0.3552, "step": 432 }, { "epoch": 0.9540400041312356, "learning_rate": 2.665173572228444e-05, "loss": 0.3187, "step": 433 }, { "epoch": 0.9562433297758804, "learning_rate": 2.6595744680851064e-05, "loss": 0.3167, "step": 434 }, { "epoch": 0.9584466554205253, "learning_rate": 2.65397536394177e-05, "loss": 0.295, "step": 435 }, { "epoch": 0.9606499810651702, "learning_rate": 2.6483762597984324e-05, "loss": 0.3386, "step": 436 }, { "epoch": 0.9628533067098152, "learning_rate": 2.6427771556550952e-05, "loss": 0.3044, "step": 437 }, { "epoch": 0.96505663235446, "learning_rate": 2.6371780515117584e-05, "loss": 0.3118, "step": 438 }, { "epoch": 0.9672599579991049, "learning_rate": 2.6315789473684212e-05, "loss": 0.3264, "step": 439 }, { "epoch": 0.9694632836437498, "learning_rate": 2.6259798432250844e-05, "loss": 0.3217, "step": 440 }, { "epoch": 0.9716666092883947, "learning_rate": 2.620380739081747e-05, "loss": 0.3236, "step": 441 }, { "epoch": 0.9738699349330395, "learning_rate": 2.6147816349384104e-05, "loss": 0.3259, "step": 442 }, { "epoch": 0.9760732605776844, "learning_rate": 2.609182530795073e-05, "loss": 0.2746, "step": 443 }, { "epoch": 0.9782765862223294, "learning_rate": 2.6035834266517357e-05, "loss": 0.3595, "step": 444 }, { "epoch": 0.9804799118669743, "learning_rate": 2.597984322508399e-05, "loss": 0.3179, "step": 445 }, { "epoch": 0.9826832375116191, "learning_rate": 2.5923852183650617e-05, "loss": 0.3041, "step": 446 }, { "epoch": 0.984886563156264, "learning_rate": 2.586786114221725e-05, "loss": 0.305, "step": 447 }, { "epoch": 0.9870898888009089, "learning_rate": 2.5811870100783874e-05, "loss": 0.3142, "step": 448 }, { "epoch": 0.9892932144455537, "learning_rate": 2.575587905935051e-05, "loss": 0.3178, "step": 449 }, { "epoch": 0.9914965400901986, "learning_rate": 2.5699888017917134e-05, "loss": 0.3319, "step": 450 }, { "epoch": 0.9936998657348435, "learning_rate": 2.5643896976483762e-05, "loss": 0.3442, "step": 451 }, { "epoch": 0.9959031913794885, "learning_rate": 2.5587905935050394e-05, "loss": 0.3583, "step": 452 }, { "epoch": 0.9981065170241333, "learning_rate": 2.5531914893617022e-05, "loss": 0.3336, "step": 453 }, { "epoch": 1.0, "learning_rate": 2.5475923852183654e-05, "loss": 0.2352, "step": 454 }, { "epoch": 1.002203325644645, "learning_rate": 2.541993281075028e-05, "loss": 0.2155, "step": 455 }, { "epoch": 1.0044066512892897, "learning_rate": 2.5363941769316914e-05, "loss": 0.1435, "step": 456 }, { "epoch": 1.0066099769339347, "learning_rate": 2.530795072788354e-05, "loss": 0.1776, "step": 457 }, { "epoch": 1.0088133025785795, "learning_rate": 2.525195968645017e-05, "loss": 0.1639, "step": 458 }, { "epoch": 1.0110166282232245, "learning_rate": 2.51959686450168e-05, "loss": 0.1692, "step": 459 }, { "epoch": 1.0132199538678692, "learning_rate": 2.5139977603583427e-05, "loss": 0.1273, "step": 460 }, { "epoch": 1.0154232795125142, "learning_rate": 2.508398656215006e-05, "loss": 0.1805, "step": 461 }, { "epoch": 1.0176266051571592, "learning_rate": 2.5027995520716684e-05, "loss": 0.1431, "step": 462 }, { "epoch": 1.019829930801804, "learning_rate": 2.4972004479283315e-05, "loss": 0.1499, "step": 463 }, { "epoch": 1.022033256446449, "learning_rate": 2.4916013437849944e-05, "loss": 0.1761, "step": 464 }, { "epoch": 1.0242365820910937, "learning_rate": 2.4860022396416575e-05, "loss": 0.148, "step": 465 }, { "epoch": 1.0264399077357387, "learning_rate": 2.4804031354983204e-05, "loss": 0.1764, "step": 466 }, { "epoch": 1.0286432333803834, "learning_rate": 2.4748040313549832e-05, "loss": 0.1755, "step": 467 }, { "epoch": 1.0308465590250284, "learning_rate": 2.4692049272116464e-05, "loss": 0.1783, "step": 468 }, { "epoch": 1.0330498846696732, "learning_rate": 2.4636058230683092e-05, "loss": 0.1458, "step": 469 }, { "epoch": 1.0352532103143182, "learning_rate": 2.4580067189249724e-05, "loss": 0.1596, "step": 470 }, { "epoch": 1.0374565359589631, "learning_rate": 2.452407614781635e-05, "loss": 0.1674, "step": 471 }, { "epoch": 1.039659861603608, "learning_rate": 2.446808510638298e-05, "loss": 0.1731, "step": 472 }, { "epoch": 1.0418631872482529, "learning_rate": 2.441209406494961e-05, "loss": 0.1791, "step": 473 }, { "epoch": 1.0440665128928976, "learning_rate": 2.4356103023516237e-05, "loss": 0.1501, "step": 474 }, { "epoch": 1.0462698385375426, "learning_rate": 2.430011198208287e-05, "loss": 0.1504, "step": 475 }, { "epoch": 1.0484731641821874, "learning_rate": 2.4244120940649497e-05, "loss": 0.1624, "step": 476 }, { "epoch": 1.0506764898268324, "learning_rate": 2.418812989921613e-05, "loss": 0.1651, "step": 477 }, { "epoch": 1.0528798154714774, "learning_rate": 2.4132138857782757e-05, "loss": 0.1799, "step": 478 }, { "epoch": 1.0550831411161221, "learning_rate": 2.4076147816349385e-05, "loss": 0.1629, "step": 479 }, { "epoch": 1.057286466760767, "learning_rate": 2.4020156774916014e-05, "loss": 0.1679, "step": 480 }, { "epoch": 1.0594897924054119, "learning_rate": 2.3964165733482642e-05, "loss": 0.1656, "step": 481 }, { "epoch": 1.0616931180500568, "learning_rate": 2.3908174692049274e-05, "loss": 0.1485, "step": 482 }, { "epoch": 1.0638964436947016, "learning_rate": 2.3852183650615902e-05, "loss": 0.157, "step": 483 }, { "epoch": 1.0660997693393466, "learning_rate": 2.3796192609182534e-05, "loss": 0.1261, "step": 484 }, { "epoch": 1.0683030949839916, "learning_rate": 2.3740201567749162e-05, "loss": 0.1614, "step": 485 }, { "epoch": 1.0705064206286363, "learning_rate": 2.368421052631579e-05, "loss": 0.1355, "step": 486 }, { "epoch": 1.0727097462732813, "learning_rate": 2.362821948488242e-05, "loss": 0.1688, "step": 487 }, { "epoch": 1.074913071917926, "learning_rate": 2.3572228443449047e-05, "loss": 0.1676, "step": 488 }, { "epoch": 1.077116397562571, "learning_rate": 2.351623740201568e-05, "loss": 0.1654, "step": 489 }, { "epoch": 1.0793197232072158, "learning_rate": 2.3460246360582307e-05, "loss": 0.1579, "step": 490 }, { "epoch": 1.0815230488518608, "learning_rate": 2.340425531914894e-05, "loss": 0.1363, "step": 491 }, { "epoch": 1.0837263744965058, "learning_rate": 2.3348264277715567e-05, "loss": 0.1447, "step": 492 }, { "epoch": 1.0859297001411505, "learning_rate": 2.32922732362822e-05, "loss": 0.1751, "step": 493 }, { "epoch": 1.0881330257857955, "learning_rate": 2.3236282194848824e-05, "loss": 0.1386, "step": 494 }, { "epoch": 1.0903363514304403, "learning_rate": 2.3180291153415452e-05, "loss": 0.1681, "step": 495 }, { "epoch": 1.0925396770750853, "learning_rate": 2.3124300111982084e-05, "loss": 0.181, "step": 496 }, { "epoch": 1.09474300271973, "learning_rate": 2.3068309070548712e-05, "loss": 0.1442, "step": 497 }, { "epoch": 1.096946328364375, "learning_rate": 2.3012318029115344e-05, "loss": 0.1598, "step": 498 }, { "epoch": 1.0991496540090198, "learning_rate": 2.2956326987681972e-05, "loss": 0.1936, "step": 499 }, { "epoch": 1.1013529796536647, "learning_rate": 2.2900335946248604e-05, "loss": 0.1497, "step": 500 }, { "epoch": 1.1035563052983097, "learning_rate": 2.2844344904815232e-05, "loss": 0.137, "step": 501 }, { "epoch": 1.1057596309429545, "learning_rate": 2.278835386338186e-05, "loss": 0.1915, "step": 502 }, { "epoch": 1.1079629565875995, "learning_rate": 2.273236282194849e-05, "loss": 0.1547, "step": 503 }, { "epoch": 1.1101662822322442, "learning_rate": 2.2676371780515117e-05, "loss": 0.1555, "step": 504 }, { "epoch": 1.1123696078768892, "learning_rate": 2.262038073908175e-05, "loss": 0.1486, "step": 505 }, { "epoch": 1.114572933521534, "learning_rate": 2.2564389697648377e-05, "loss": 0.1408, "step": 506 }, { "epoch": 1.116776259166179, "learning_rate": 2.250839865621501e-05, "loss": 0.1494, "step": 507 }, { "epoch": 1.118979584810824, "learning_rate": 2.2452407614781637e-05, "loss": 0.1478, "step": 508 }, { "epoch": 1.1211829104554687, "learning_rate": 2.2396416573348266e-05, "loss": 0.1446, "step": 509 }, { "epoch": 1.1233862361001137, "learning_rate": 2.2340425531914894e-05, "loss": 0.1436, "step": 510 }, { "epoch": 1.1255895617447584, "learning_rate": 2.2284434490481522e-05, "loss": 0.158, "step": 511 }, { "epoch": 1.1277928873894034, "learning_rate": 2.2228443449048154e-05, "loss": 0.1629, "step": 512 }, { "epoch": 1.1299962130340482, "learning_rate": 2.2172452407614782e-05, "loss": 0.1688, "step": 513 }, { "epoch": 1.1321995386786932, "learning_rate": 2.2116461366181414e-05, "loss": 0.1485, "step": 514 }, { "epoch": 1.134402864323338, "learning_rate": 2.2060470324748042e-05, "loss": 0.1654, "step": 515 }, { "epoch": 1.136606189967983, "learning_rate": 2.200447928331467e-05, "loss": 0.1434, "step": 516 }, { "epoch": 1.1388095156126279, "learning_rate": 2.19484882418813e-05, "loss": 0.195, "step": 517 }, { "epoch": 1.1410128412572726, "learning_rate": 2.1892497200447927e-05, "loss": 0.1558, "step": 518 }, { "epoch": 1.1432161669019176, "learning_rate": 2.183650615901456e-05, "loss": 0.173, "step": 519 }, { "epoch": 1.1454194925465624, "learning_rate": 2.1780515117581187e-05, "loss": 0.1576, "step": 520 }, { "epoch": 1.1476228181912074, "learning_rate": 2.172452407614782e-05, "loss": 0.165, "step": 521 }, { "epoch": 1.1498261438358521, "learning_rate": 2.1668533034714447e-05, "loss": 0.1402, "step": 522 }, { "epoch": 1.1520294694804971, "learning_rate": 2.1612541993281076e-05, "loss": 0.151, "step": 523 }, { "epoch": 1.154232795125142, "learning_rate": 2.1556550951847707e-05, "loss": 0.1819, "step": 524 }, { "epoch": 1.1564361207697869, "learning_rate": 2.1500559910414332e-05, "loss": 0.1436, "step": 525 }, { "epoch": 1.1586394464144318, "learning_rate": 2.1444568868980964e-05, "loss": 0.1517, "step": 526 }, { "epoch": 1.1608427720590766, "learning_rate": 2.1388577827547592e-05, "loss": 0.1502, "step": 527 }, { "epoch": 1.1630460977037216, "learning_rate": 2.1332586786114224e-05, "loss": 0.1844, "step": 528 }, { "epoch": 1.1652494233483663, "learning_rate": 2.1276595744680852e-05, "loss": 0.1477, "step": 529 }, { "epoch": 1.1674527489930113, "learning_rate": 2.122060470324748e-05, "loss": 0.1412, "step": 530 }, { "epoch": 1.1696560746376563, "learning_rate": 2.1164613661814112e-05, "loss": 0.1376, "step": 531 }, { "epoch": 1.171859400282301, "learning_rate": 2.110862262038074e-05, "loss": 0.1242, "step": 532 }, { "epoch": 1.174062725926946, "learning_rate": 2.105263157894737e-05, "loss": 0.151, "step": 533 }, { "epoch": 1.1762660515715908, "learning_rate": 2.0996640537513997e-05, "loss": 0.1252, "step": 534 }, { "epoch": 1.1784693772162358, "learning_rate": 2.094064949608063e-05, "loss": 0.1583, "step": 535 }, { "epoch": 1.1806727028608806, "learning_rate": 2.0884658454647257e-05, "loss": 0.1531, "step": 536 }, { "epoch": 1.1828760285055255, "learning_rate": 2.0828667413213886e-05, "loss": 0.1201, "step": 537 }, { "epoch": 1.1850793541501705, "learning_rate": 2.0772676371780517e-05, "loss": 0.1543, "step": 538 }, { "epoch": 1.1872826797948153, "learning_rate": 2.0716685330347146e-05, "loss": 0.173, "step": 539 }, { "epoch": 1.1894860054394603, "learning_rate": 2.0660694288913777e-05, "loss": 0.149, "step": 540 }, { "epoch": 1.191689331084105, "learning_rate": 2.0604703247480402e-05, "loss": 0.14, "step": 541 }, { "epoch": 1.19389265672875, "learning_rate": 2.0548712206047034e-05, "loss": 0.1325, "step": 542 }, { "epoch": 1.1960959823733948, "learning_rate": 2.0492721164613662e-05, "loss": 0.139, "step": 543 }, { "epoch": 1.1982993080180397, "learning_rate": 2.043673012318029e-05, "loss": 0.1217, "step": 544 }, { "epoch": 1.2005026336626847, "learning_rate": 2.0380739081746922e-05, "loss": 0.1491, "step": 545 }, { "epoch": 1.2027059593073295, "learning_rate": 2.032474804031355e-05, "loss": 0.1685, "step": 546 }, { "epoch": 1.2049092849519745, "learning_rate": 2.0268756998880182e-05, "loss": 0.1261, "step": 547 }, { "epoch": 1.2071126105966192, "learning_rate": 2.0212765957446807e-05, "loss": 0.1694, "step": 548 }, { "epoch": 1.2093159362412642, "learning_rate": 2.015677491601344e-05, "loss": 0.1697, "step": 549 }, { "epoch": 1.211519261885909, "learning_rate": 2.0100783874580067e-05, "loss": 0.1338, "step": 550 }, { "epoch": 1.213722587530554, "learning_rate": 2.0044792833146696e-05, "loss": 0.1748, "step": 551 }, { "epoch": 1.215925913175199, "learning_rate": 1.9988801791713327e-05, "loss": 0.1329, "step": 552 }, { "epoch": 1.2181292388198437, "learning_rate": 1.9932810750279956e-05, "loss": 0.1702, "step": 553 }, { "epoch": 1.2203325644644887, "learning_rate": 1.9876819708846587e-05, "loss": 0.1756, "step": 554 }, { "epoch": 1.2225358901091334, "learning_rate": 1.9820828667413216e-05, "loss": 0.1623, "step": 555 }, { "epoch": 1.2247392157537784, "learning_rate": 1.9764837625979844e-05, "loss": 0.1378, "step": 556 }, { "epoch": 1.2269425413984232, "learning_rate": 1.9708846584546472e-05, "loss": 0.1422, "step": 557 }, { "epoch": 1.2291458670430682, "learning_rate": 1.96528555431131e-05, "loss": 0.1311, "step": 558 }, { "epoch": 1.231349192687713, "learning_rate": 1.9596864501679732e-05, "loss": 0.1731, "step": 559 }, { "epoch": 1.233552518332358, "learning_rate": 1.954087346024636e-05, "loss": 0.1509, "step": 560 }, { "epoch": 1.2357558439770027, "learning_rate": 1.9484882418812992e-05, "loss": 0.1625, "step": 561 }, { "epoch": 1.2379591696216476, "learning_rate": 1.942889137737962e-05, "loss": 0.1635, "step": 562 }, { "epoch": 1.2401624952662926, "learning_rate": 1.9372900335946252e-05, "loss": 0.1627, "step": 563 }, { "epoch": 1.2423658209109374, "learning_rate": 1.9316909294512877e-05, "loss": 0.1763, "step": 564 }, { "epoch": 1.2445691465555824, "learning_rate": 1.926091825307951e-05, "loss": 0.1394, "step": 565 }, { "epoch": 1.2467724722002271, "learning_rate": 1.9204927211646137e-05, "loss": 0.1823, "step": 566 }, { "epoch": 1.2489757978448721, "learning_rate": 1.9148936170212766e-05, "loss": 0.1881, "step": 567 }, { "epoch": 1.2511791234895169, "learning_rate": 1.9092945128779397e-05, "loss": 0.1528, "step": 568 }, { "epoch": 1.2533824491341619, "learning_rate": 1.9036954087346026e-05, "loss": 0.1485, "step": 569 }, { "epoch": 1.2555857747788068, "learning_rate": 1.8980963045912657e-05, "loss": 0.1725, "step": 570 }, { "epoch": 1.2577891004234516, "learning_rate": 1.8924972004479286e-05, "loss": 0.152, "step": 571 }, { "epoch": 1.2599924260680966, "learning_rate": 1.8868980963045914e-05, "loss": 0.1581, "step": 572 }, { "epoch": 1.2621957517127413, "learning_rate": 1.8812989921612542e-05, "loss": 0.1714, "step": 573 }, { "epoch": 1.2643990773573863, "learning_rate": 1.875699888017917e-05, "loss": 0.1494, "step": 574 }, { "epoch": 1.266602403002031, "learning_rate": 1.8701007838745802e-05, "loss": 0.1479, "step": 575 }, { "epoch": 1.268805728646676, "learning_rate": 1.864501679731243e-05, "loss": 0.1594, "step": 576 }, { "epoch": 1.271009054291321, "learning_rate": 1.8589025755879062e-05, "loss": 0.1415, "step": 577 }, { "epoch": 1.2732123799359658, "learning_rate": 1.853303471444569e-05, "loss": 0.1663, "step": 578 }, { "epoch": 1.2754157055806108, "learning_rate": 1.847704367301232e-05, "loss": 0.1872, "step": 579 }, { "epoch": 1.2776190312252556, "learning_rate": 1.8421052631578947e-05, "loss": 0.1595, "step": 580 }, { "epoch": 1.2798223568699005, "learning_rate": 1.8365061590145576e-05, "loss": 0.1582, "step": 581 }, { "epoch": 1.2820256825145453, "learning_rate": 1.8309070548712207e-05, "loss": 0.1558, "step": 582 }, { "epoch": 1.2842290081591903, "learning_rate": 1.8253079507278836e-05, "loss": 0.1691, "step": 583 }, { "epoch": 1.2864323338038353, "learning_rate": 1.8197088465845467e-05, "loss": 0.192, "step": 584 }, { "epoch": 1.28863565944848, "learning_rate": 1.8141097424412096e-05, "loss": 0.1589, "step": 585 }, { "epoch": 1.290838985093125, "learning_rate": 1.8085106382978724e-05, "loss": 0.144, "step": 586 }, { "epoch": 1.2930423107377698, "learning_rate": 1.8029115341545352e-05, "loss": 0.1723, "step": 587 }, { "epoch": 1.2952456363824147, "learning_rate": 1.797312430011198e-05, "loss": 0.1461, "step": 588 }, { "epoch": 1.2974489620270595, "learning_rate": 1.7917133258678612e-05, "loss": 0.1772, "step": 589 }, { "epoch": 1.2996522876717045, "learning_rate": 1.786114221724524e-05, "loss": 0.1461, "step": 590 }, { "epoch": 1.3018556133163495, "learning_rate": 1.7805151175811872e-05, "loss": 0.1667, "step": 591 }, { "epoch": 1.3040589389609942, "learning_rate": 1.77491601343785e-05, "loss": 0.1597, "step": 592 }, { "epoch": 1.3062622646056392, "learning_rate": 1.769316909294513e-05, "loss": 0.1739, "step": 593 }, { "epoch": 1.308465590250284, "learning_rate": 1.763717805151176e-05, "loss": 0.1692, "step": 594 }, { "epoch": 1.310668915894929, "learning_rate": 1.7581187010078386e-05, "loss": 0.1736, "step": 595 }, { "epoch": 1.3128722415395737, "learning_rate": 1.7525195968645017e-05, "loss": 0.1569, "step": 596 }, { "epoch": 1.3150755671842187, "learning_rate": 1.7469204927211646e-05, "loss": 0.1669, "step": 597 }, { "epoch": 1.3172788928288637, "learning_rate": 1.7413213885778277e-05, "loss": 0.1607, "step": 598 }, { "epoch": 1.3194822184735084, "learning_rate": 1.7357222844344906e-05, "loss": 0.1715, "step": 599 }, { "epoch": 1.3216855441181532, "learning_rate": 1.7301231802911534e-05, "loss": 0.1448, "step": 600 }, { "epoch": 1.3238888697627982, "learning_rate": 1.7245240761478166e-05, "loss": 0.1532, "step": 601 }, { "epoch": 1.3260921954074432, "learning_rate": 1.7189249720044794e-05, "loss": 0.1549, "step": 602 }, { "epoch": 1.328295521052088, "learning_rate": 1.7133258678611422e-05, "loss": 0.1837, "step": 603 }, { "epoch": 1.330498846696733, "learning_rate": 1.707726763717805e-05, "loss": 0.2056, "step": 604 }, { "epoch": 1.3327021723413779, "learning_rate": 1.7021276595744682e-05, "loss": 0.1931, "step": 605 }, { "epoch": 1.3349054979860226, "learning_rate": 1.696528555431131e-05, "loss": 0.1442, "step": 606 }, { "epoch": 1.3371088236306674, "learning_rate": 1.690929451287794e-05, "loss": 0.1504, "step": 607 }, { "epoch": 1.3393121492753124, "learning_rate": 1.685330347144457e-05, "loss": 0.102, "step": 608 }, { "epoch": 1.3415154749199574, "learning_rate": 1.67973124300112e-05, "loss": 0.1206, "step": 609 }, { "epoch": 1.3437188005646021, "learning_rate": 1.674132138857783e-05, "loss": 0.1779, "step": 610 }, { "epoch": 1.3459221262092471, "learning_rate": 1.6685330347144456e-05, "loss": 0.1392, "step": 611 }, { "epoch": 1.348125451853892, "learning_rate": 1.6629339305711087e-05, "loss": 0.1629, "step": 612 }, { "epoch": 1.3503287774985369, "learning_rate": 1.6573348264277716e-05, "loss": 0.1245, "step": 613 }, { "epoch": 1.3525321031431816, "learning_rate": 1.6517357222844344e-05, "loss": 0.1486, "step": 614 }, { "epoch": 1.3547354287878266, "learning_rate": 1.6461366181410976e-05, "loss": 0.1401, "step": 615 }, { "epoch": 1.3569387544324716, "learning_rate": 1.6405375139977604e-05, "loss": 0.1713, "step": 616 }, { "epoch": 1.3591420800771163, "learning_rate": 1.6349384098544236e-05, "loss": 0.1471, "step": 617 }, { "epoch": 1.3613454057217613, "learning_rate": 1.629339305711086e-05, "loss": 0.1618, "step": 618 }, { "epoch": 1.3635487313664063, "learning_rate": 1.6237402015677492e-05, "loss": 0.1504, "step": 619 }, { "epoch": 1.365752057011051, "learning_rate": 1.618141097424412e-05, "loss": 0.1692, "step": 620 }, { "epoch": 1.3679553826556958, "learning_rate": 1.612541993281075e-05, "loss": 0.1423, "step": 621 }, { "epoch": 1.3701587083003408, "learning_rate": 1.606942889137738e-05, "loss": 0.1747, "step": 622 }, { "epoch": 1.3723620339449858, "learning_rate": 1.601343784994401e-05, "loss": 0.1451, "step": 623 }, { "epoch": 1.3745653595896306, "learning_rate": 1.595744680851064e-05, "loss": 0.1761, "step": 624 }, { "epoch": 1.3767686852342755, "learning_rate": 1.590145576707727e-05, "loss": 0.1508, "step": 625 }, { "epoch": 1.3789720108789203, "learning_rate": 1.5845464725643898e-05, "loss": 0.1502, "step": 626 }, { "epoch": 1.3811753365235653, "learning_rate": 1.5789473684210526e-05, "loss": 0.1649, "step": 627 }, { "epoch": 1.38337866216821, "learning_rate": 1.5733482642777158e-05, "loss": 0.1522, "step": 628 }, { "epoch": 1.385581987812855, "learning_rate": 1.5677491601343786e-05, "loss": 0.1536, "step": 629 }, { "epoch": 1.3877853134575, "learning_rate": 1.5621500559910414e-05, "loss": 0.1391, "step": 630 }, { "epoch": 1.3899886391021448, "learning_rate": 1.5565509518477046e-05, "loss": 0.1617, "step": 631 }, { "epoch": 1.3921919647467897, "learning_rate": 1.5509518477043674e-05, "loss": 0.1378, "step": 632 }, { "epoch": 1.3943952903914345, "learning_rate": 1.5453527435610306e-05, "loss": 0.1907, "step": 633 }, { "epoch": 1.3965986160360795, "learning_rate": 1.539753639417693e-05, "loss": 0.1921, "step": 634 }, { "epoch": 1.3988019416807242, "learning_rate": 1.5341545352743563e-05, "loss": 0.165, "step": 635 }, { "epoch": 1.4010052673253692, "learning_rate": 1.528555431131019e-05, "loss": 0.184, "step": 636 }, { "epoch": 1.4032085929700142, "learning_rate": 1.5229563269876821e-05, "loss": 0.1839, "step": 637 }, { "epoch": 1.405411918614659, "learning_rate": 1.5173572228443451e-05, "loss": 0.1412, "step": 638 }, { "epoch": 1.407615244259304, "learning_rate": 1.511758118701008e-05, "loss": 0.1473, "step": 639 }, { "epoch": 1.4098185699039487, "learning_rate": 1.506159014557671e-05, "loss": 0.1398, "step": 640 }, { "epoch": 1.4120218955485937, "learning_rate": 1.500559910414334e-05, "loss": 0.1508, "step": 641 }, { "epoch": 1.4142252211932385, "learning_rate": 1.4949608062709966e-05, "loss": 0.1546, "step": 642 }, { "epoch": 1.4164285468378834, "learning_rate": 1.4893617021276596e-05, "loss": 0.1397, "step": 643 }, { "epoch": 1.4186318724825284, "learning_rate": 1.4837625979843226e-05, "loss": 0.1576, "step": 644 }, { "epoch": 1.4208351981271732, "learning_rate": 1.4781634938409856e-05, "loss": 0.1683, "step": 645 }, { "epoch": 1.4230385237718182, "learning_rate": 1.4725643896976484e-05, "loss": 0.1664, "step": 646 }, { "epoch": 1.425241849416463, "learning_rate": 1.4669652855543114e-05, "loss": 0.1217, "step": 647 }, { "epoch": 1.427445175061108, "learning_rate": 1.4613661814109744e-05, "loss": 0.1678, "step": 648 }, { "epoch": 1.4296485007057527, "learning_rate": 1.4557670772676371e-05, "loss": 0.1778, "step": 649 }, { "epoch": 1.4318518263503976, "learning_rate": 1.4501679731243001e-05, "loss": 0.1628, "step": 650 }, { "epoch": 1.4340551519950426, "learning_rate": 1.4445688689809631e-05, "loss": 0.187, "step": 651 }, { "epoch": 1.4362584776396874, "learning_rate": 1.4389697648376261e-05, "loss": 0.1548, "step": 652 }, { "epoch": 1.4384618032843322, "learning_rate": 1.433370660694289e-05, "loss": 0.1428, "step": 653 }, { "epoch": 1.4406651289289771, "learning_rate": 1.427771556550952e-05, "loss": 0.1576, "step": 654 }, { "epoch": 1.4428684545736221, "learning_rate": 1.422172452407615e-05, "loss": 0.1381, "step": 655 }, { "epoch": 1.4450717802182669, "learning_rate": 1.416573348264278e-05, "loss": 0.1201, "step": 656 }, { "epoch": 1.4472751058629119, "learning_rate": 1.4109742441209406e-05, "loss": 0.1564, "step": 657 }, { "epoch": 1.4494784315075568, "learning_rate": 1.4053751399776036e-05, "loss": 0.1669, "step": 658 }, { "epoch": 1.4516817571522016, "learning_rate": 1.3997760358342666e-05, "loss": 0.139, "step": 659 }, { "epoch": 1.4538850827968464, "learning_rate": 1.3941769316909294e-05, "loss": 0.1439, "step": 660 }, { "epoch": 1.4560884084414913, "learning_rate": 1.3885778275475924e-05, "loss": 0.149, "step": 661 }, { "epoch": 1.4582917340861363, "learning_rate": 1.3829787234042554e-05, "loss": 0.1531, "step": 662 }, { "epoch": 1.460495059730781, "learning_rate": 1.3773796192609184e-05, "loss": 0.1595, "step": 663 }, { "epoch": 1.462698385375426, "learning_rate": 1.3717805151175814e-05, "loss": 0.1731, "step": 664 }, { "epoch": 1.464901711020071, "learning_rate": 1.3661814109742441e-05, "loss": 0.1779, "step": 665 }, { "epoch": 1.4671050366647158, "learning_rate": 1.3605823068309071e-05, "loss": 0.1547, "step": 666 }, { "epoch": 1.4693083623093606, "learning_rate": 1.35498320268757e-05, "loss": 0.1568, "step": 667 }, { "epoch": 1.4715116879540056, "learning_rate": 1.349384098544233e-05, "loss": 0.1615, "step": 668 }, { "epoch": 1.4737150135986505, "learning_rate": 1.343784994400896e-05, "loss": 0.1629, "step": 669 }, { "epoch": 1.4759183392432953, "learning_rate": 1.338185890257559e-05, "loss": 0.1734, "step": 670 }, { "epoch": 1.4781216648879403, "learning_rate": 1.332586786114222e-05, "loss": 0.1406, "step": 671 }, { "epoch": 1.480324990532585, "learning_rate": 1.326987681970885e-05, "loss": 0.1684, "step": 672 }, { "epoch": 1.48252831617723, "learning_rate": 1.3213885778275476e-05, "loss": 0.1479, "step": 673 }, { "epoch": 1.4847316418218748, "learning_rate": 1.3157894736842106e-05, "loss": 0.1928, "step": 674 }, { "epoch": 1.4869349674665198, "learning_rate": 1.3101903695408734e-05, "loss": 0.1383, "step": 675 }, { "epoch": 1.4891382931111647, "learning_rate": 1.3045912653975364e-05, "loss": 0.1602, "step": 676 }, { "epoch": 1.4913416187558095, "learning_rate": 1.2989921612541994e-05, "loss": 0.1793, "step": 677 }, { "epoch": 1.4935449444004545, "learning_rate": 1.2933930571108624e-05, "loss": 0.1668, "step": 678 }, { "epoch": 1.4957482700450992, "learning_rate": 1.2877939529675254e-05, "loss": 0.1457, "step": 679 }, { "epoch": 1.4979515956897442, "learning_rate": 1.2821948488241881e-05, "loss": 0.1395, "step": 680 }, { "epoch": 1.500154921334389, "learning_rate": 1.2765957446808511e-05, "loss": 0.1524, "step": 681 }, { "epoch": 1.502358246979034, "learning_rate": 1.270996640537514e-05, "loss": 0.1574, "step": 682 }, { "epoch": 1.504561572623679, "learning_rate": 1.265397536394177e-05, "loss": 0.144, "step": 683 }, { "epoch": 1.5067648982683237, "learning_rate": 1.25979843225084e-05, "loss": 0.1537, "step": 684 }, { "epoch": 1.5089682239129685, "learning_rate": 1.254199328107503e-05, "loss": 0.1208, "step": 685 }, { "epoch": 1.5111715495576137, "learning_rate": 1.2486002239641658e-05, "loss": 0.1447, "step": 686 }, { "epoch": 1.5133748752022584, "learning_rate": 1.2430011198208288e-05, "loss": 0.1616, "step": 687 }, { "epoch": 1.5155782008469032, "learning_rate": 1.2374020156774916e-05, "loss": 0.1429, "step": 688 }, { "epoch": 1.5177815264915482, "learning_rate": 1.2318029115341546e-05, "loss": 0.1783, "step": 689 }, { "epoch": 1.5199848521361932, "learning_rate": 1.2262038073908174e-05, "loss": 0.1417, "step": 690 }, { "epoch": 1.522188177780838, "learning_rate": 1.2206047032474804e-05, "loss": 0.1836, "step": 691 }, { "epoch": 1.5243915034254827, "learning_rate": 1.2150055991041434e-05, "loss": 0.1371, "step": 692 }, { "epoch": 1.526594829070128, "learning_rate": 1.2094064949608064e-05, "loss": 0.1251, "step": 693 }, { "epoch": 1.5287981547147727, "learning_rate": 1.2038073908174693e-05, "loss": 0.1232, "step": 694 }, { "epoch": 1.5310014803594174, "learning_rate": 1.1982082866741321e-05, "loss": 0.1608, "step": 695 }, { "epoch": 1.5332048060040624, "learning_rate": 1.1926091825307951e-05, "loss": 0.1937, "step": 696 }, { "epoch": 1.5354081316487074, "learning_rate": 1.1870100783874581e-05, "loss": 0.1465, "step": 697 }, { "epoch": 1.5376114572933521, "learning_rate": 1.181410974244121e-05, "loss": 0.1284, "step": 698 }, { "epoch": 1.539814782937997, "learning_rate": 1.175811870100784e-05, "loss": 0.1468, "step": 699 }, { "epoch": 1.5420181085826419, "learning_rate": 1.170212765957447e-05, "loss": 0.1178, "step": 700 }, { "epoch": 1.5442214342272869, "learning_rate": 1.16461366181411e-05, "loss": 0.1378, "step": 701 }, { "epoch": 1.5464247598719316, "learning_rate": 1.1590145576707726e-05, "loss": 0.1669, "step": 702 }, { "epoch": 1.5486280855165766, "learning_rate": 1.1534154535274356e-05, "loss": 0.1759, "step": 703 }, { "epoch": 1.5508314111612216, "learning_rate": 1.1478163493840986e-05, "loss": 0.1747, "step": 704 }, { "epoch": 1.5530347368058663, "learning_rate": 1.1422172452407616e-05, "loss": 0.1603, "step": 705 }, { "epoch": 1.555238062450511, "learning_rate": 1.1366181410974244e-05, "loss": 0.1554, "step": 706 }, { "epoch": 1.557441388095156, "learning_rate": 1.1310190369540874e-05, "loss": 0.1413, "step": 707 }, { "epoch": 1.559644713739801, "learning_rate": 1.1254199328107504e-05, "loss": 0.14, "step": 708 }, { "epoch": 1.5618480393844458, "learning_rate": 1.1198208286674133e-05, "loss": 0.1605, "step": 709 }, { "epoch": 1.5640513650290908, "learning_rate": 1.1142217245240761e-05, "loss": 0.1522, "step": 710 }, { "epoch": 1.5662546906737358, "learning_rate": 1.1086226203807391e-05, "loss": 0.1249, "step": 711 }, { "epoch": 1.5684580163183806, "learning_rate": 1.1030235162374021e-05, "loss": 0.1767, "step": 712 }, { "epoch": 1.5706613419630253, "learning_rate": 1.097424412094065e-05, "loss": 0.1527, "step": 713 }, { "epoch": 1.5728646676076703, "learning_rate": 1.091825307950728e-05, "loss": 0.1656, "step": 714 }, { "epoch": 1.5750679932523153, "learning_rate": 1.086226203807391e-05, "loss": 0.1749, "step": 715 }, { "epoch": 1.57727131889696, "learning_rate": 1.0806270996640538e-05, "loss": 0.1443, "step": 716 }, { "epoch": 1.579474644541605, "learning_rate": 1.0750279955207166e-05, "loss": 0.1882, "step": 717 }, { "epoch": 1.58167797018625, "learning_rate": 1.0694288913773796e-05, "loss": 0.163, "step": 718 }, { "epoch": 1.5838812958308948, "learning_rate": 1.0638297872340426e-05, "loss": 0.1549, "step": 719 }, { "epoch": 1.5860846214755395, "learning_rate": 1.0582306830907056e-05, "loss": 0.148, "step": 720 }, { "epoch": 1.5882879471201845, "learning_rate": 1.0526315789473684e-05, "loss": 0.1753, "step": 721 }, { "epoch": 1.5904912727648295, "learning_rate": 1.0470324748040314e-05, "loss": 0.1721, "step": 722 }, { "epoch": 1.5926945984094742, "learning_rate": 1.0414333706606943e-05, "loss": 0.1549, "step": 723 }, { "epoch": 1.5948979240541192, "learning_rate": 1.0358342665173573e-05, "loss": 0.1753, "step": 724 }, { "epoch": 1.5971012496987642, "learning_rate": 1.0302351623740201e-05, "loss": 0.2103, "step": 725 }, { "epoch": 1.599304575343409, "learning_rate": 1.0246360582306831e-05, "loss": 0.1398, "step": 726 }, { "epoch": 1.6015079009880537, "learning_rate": 1.0190369540873461e-05, "loss": 0.1578, "step": 727 }, { "epoch": 1.6037112266326987, "learning_rate": 1.0134378499440091e-05, "loss": 0.1657, "step": 728 }, { "epoch": 1.6059145522773437, "learning_rate": 1.007838745800672e-05, "loss": 0.1471, "step": 729 }, { "epoch": 1.6081178779219885, "learning_rate": 1.0022396416573348e-05, "loss": 0.1381, "step": 730 }, { "epoch": 1.6103212035666334, "learning_rate": 9.966405375139978e-06, "loss": 0.1514, "step": 731 }, { "epoch": 1.6125245292112784, "learning_rate": 9.910414333706608e-06, "loss": 0.1662, "step": 732 }, { "epoch": 1.6147278548559232, "learning_rate": 9.854423292273236e-06, "loss": 0.1425, "step": 733 }, { "epoch": 1.616931180500568, "learning_rate": 9.798432250839866e-06, "loss": 0.1511, "step": 734 }, { "epoch": 1.619134506145213, "learning_rate": 9.742441209406496e-06, "loss": 0.1382, "step": 735 }, { "epoch": 1.621337831789858, "learning_rate": 9.686450167973126e-06, "loss": 0.1859, "step": 736 }, { "epoch": 1.6235411574345027, "learning_rate": 9.630459126539755e-06, "loss": 0.193, "step": 737 }, { "epoch": 1.6257444830791474, "learning_rate": 9.574468085106383e-06, "loss": 0.1659, "step": 738 }, { "epoch": 1.6279478087237926, "learning_rate": 9.518477043673013e-06, "loss": 0.1655, "step": 739 }, { "epoch": 1.6301511343684374, "learning_rate": 9.462486002239643e-06, "loss": 0.1152, "step": 740 }, { "epoch": 1.6323544600130822, "learning_rate": 9.406494960806271e-06, "loss": 0.1579, "step": 741 }, { "epoch": 1.6345577856577271, "learning_rate": 9.350503919372901e-06, "loss": 0.1425, "step": 742 }, { "epoch": 1.6367611113023721, "learning_rate": 9.294512877939531e-06, "loss": 0.1623, "step": 743 }, { "epoch": 1.6389644369470169, "learning_rate": 9.23852183650616e-06, "loss": 0.1442, "step": 744 }, { "epoch": 1.6411677625916616, "learning_rate": 9.182530795072788e-06, "loss": 0.1541, "step": 745 }, { "epoch": 1.6433710882363066, "learning_rate": 9.126539753639418e-06, "loss": 0.1549, "step": 746 }, { "epoch": 1.6455744138809516, "learning_rate": 9.070548712206048e-06, "loss": 0.1381, "step": 747 }, { "epoch": 1.6477777395255964, "learning_rate": 9.014557670772676e-06, "loss": 0.1436, "step": 748 }, { "epoch": 1.6499810651702413, "learning_rate": 8.958566629339306e-06, "loss": 0.1491, "step": 749 }, { "epoch": 1.6521843908148863, "learning_rate": 8.902575587905936e-06, "loss": 0.1615, "step": 750 }, { "epoch": 1.654387716459531, "learning_rate": 8.846584546472565e-06, "loss": 0.1307, "step": 751 }, { "epoch": 1.6565910421041758, "learning_rate": 8.790593505039193e-06, "loss": 0.1559, "step": 752 }, { "epoch": 1.6587943677488208, "learning_rate": 8.734602463605823e-06, "loss": 0.1595, "step": 753 }, { "epoch": 1.6609976933934658, "learning_rate": 8.678611422172453e-06, "loss": 0.1483, "step": 754 }, { "epoch": 1.6632010190381106, "learning_rate": 8.622620380739083e-06, "loss": 0.1142, "step": 755 }, { "epoch": 1.6654043446827556, "learning_rate": 8.566629339305711e-06, "loss": 0.1607, "step": 756 }, { "epoch": 1.6676076703274005, "learning_rate": 8.510638297872341e-06, "loss": 0.1296, "step": 757 }, { "epoch": 1.6698109959720453, "learning_rate": 8.45464725643897e-06, "loss": 0.1477, "step": 758 }, { "epoch": 1.67201432161669, "learning_rate": 8.3986562150056e-06, "loss": 0.1639, "step": 759 }, { "epoch": 1.674217647261335, "learning_rate": 8.342665173572228e-06, "loss": 0.1636, "step": 760 }, { "epoch": 1.67642097290598, "learning_rate": 8.286674132138858e-06, "loss": 0.1518, "step": 761 }, { "epoch": 1.6786242985506248, "learning_rate": 8.230683090705488e-06, "loss": 0.1543, "step": 762 }, { "epoch": 1.6808276241952698, "learning_rate": 8.174692049272118e-06, "loss": 0.1391, "step": 763 }, { "epoch": 1.6830309498399147, "learning_rate": 8.118701007838746e-06, "loss": 0.1405, "step": 764 }, { "epoch": 1.6852342754845595, "learning_rate": 8.062709966405375e-06, "loss": 0.137, "step": 765 }, { "epoch": 1.6874376011292043, "learning_rate": 8.006718924972005e-06, "loss": 0.1625, "step": 766 }, { "epoch": 1.6896409267738492, "learning_rate": 7.950727883538635e-06, "loss": 0.15, "step": 767 }, { "epoch": 1.6918442524184942, "learning_rate": 7.894736842105263e-06, "loss": 0.1154, "step": 768 }, { "epoch": 1.694047578063139, "learning_rate": 7.838745800671893e-06, "loss": 0.1677, "step": 769 }, { "epoch": 1.696250903707784, "learning_rate": 7.782754759238523e-06, "loss": 0.1448, "step": 770 }, { "epoch": 1.698454229352429, "learning_rate": 7.726763717805153e-06, "loss": 0.1536, "step": 771 }, { "epoch": 1.7006575549970737, "learning_rate": 7.670772676371781e-06, "loss": 0.1545, "step": 772 }, { "epoch": 1.7028608806417185, "learning_rate": 7.6147816349384104e-06, "loss": 0.1898, "step": 773 }, { "epoch": 1.7050642062863635, "learning_rate": 7.55879059350504e-06, "loss": 0.1567, "step": 774 }, { "epoch": 1.7072675319310084, "learning_rate": 7.50279955207167e-06, "loss": 0.1743, "step": 775 }, { "epoch": 1.7094708575756532, "learning_rate": 7.446808510638298e-06, "loss": 0.1503, "step": 776 }, { "epoch": 1.7116741832202982, "learning_rate": 7.390817469204928e-06, "loss": 0.1176, "step": 777 }, { "epoch": 1.7138775088649432, "learning_rate": 7.334826427771557e-06, "loss": 0.1418, "step": 778 }, { "epoch": 1.716080834509588, "learning_rate": 7.2788353863381854e-06, "loss": 0.1522, "step": 779 }, { "epoch": 1.7182841601542327, "learning_rate": 7.2228443449048155e-06, "loss": 0.1448, "step": 780 }, { "epoch": 1.7204874857988777, "learning_rate": 7.166853303471445e-06, "loss": 0.1306, "step": 781 }, { "epoch": 1.7226908114435227, "learning_rate": 7.110862262038075e-06, "loss": 0.1417, "step": 782 }, { "epoch": 1.7248941370881674, "learning_rate": 7.054871220604703e-06, "loss": 0.1509, "step": 783 }, { "epoch": 1.7270974627328124, "learning_rate": 6.998880179171333e-06, "loss": 0.1758, "step": 784 }, { "epoch": 1.7293007883774574, "learning_rate": 6.942889137737962e-06, "loss": 0.1518, "step": 785 }, { "epoch": 1.7315041140221021, "learning_rate": 6.886898096304592e-06, "loss": 0.1153, "step": 786 }, { "epoch": 1.733707439666747, "learning_rate": 6.8309070548712205e-06, "loss": 0.1459, "step": 787 }, { "epoch": 1.7359107653113919, "learning_rate": 6.77491601343785e-06, "loss": 0.1719, "step": 788 }, { "epoch": 1.7381140909560369, "learning_rate": 6.71892497200448e-06, "loss": 0.141, "step": 789 }, { "epoch": 1.7403174166006816, "learning_rate": 6.66293393057111e-06, "loss": 0.1622, "step": 790 }, { "epoch": 1.7425207422453264, "learning_rate": 6.606942889137738e-06, "loss": 0.162, "step": 791 }, { "epoch": 1.7447240678899716, "learning_rate": 6.550951847704367e-06, "loss": 0.1712, "step": 792 }, { "epoch": 1.7469273935346163, "learning_rate": 6.494960806270997e-06, "loss": 0.1435, "step": 793 }, { "epoch": 1.749130719179261, "learning_rate": 6.438969764837627e-06, "loss": 0.1759, "step": 794 }, { "epoch": 1.751334044823906, "learning_rate": 6.3829787234042555e-06, "loss": 0.1485, "step": 795 }, { "epoch": 1.753537370468551, "learning_rate": 6.326987681970885e-06, "loss": 0.1434, "step": 796 }, { "epoch": 1.7557406961131958, "learning_rate": 6.270996640537515e-06, "loss": 0.1452, "step": 797 }, { "epoch": 1.7579440217578406, "learning_rate": 6.215005599104144e-06, "loss": 0.1195, "step": 798 }, { "epoch": 1.7601473474024856, "learning_rate": 6.159014557670773e-06, "loss": 0.1254, "step": 799 }, { "epoch": 1.7623506730471306, "learning_rate": 6.103023516237402e-06, "loss": 0.1631, "step": 800 }, { "epoch": 1.7645539986917753, "learning_rate": 6.047032474804032e-06, "loss": 0.1429, "step": 801 }, { "epoch": 1.7667573243364203, "learning_rate": 5.9910414333706605e-06, "loss": 0.125, "step": 802 }, { "epoch": 1.7689606499810653, "learning_rate": 5.9350503919372905e-06, "loss": 0.1612, "step": 803 }, { "epoch": 1.77116397562571, "learning_rate": 5.87905935050392e-06, "loss": 0.1565, "step": 804 }, { "epoch": 1.7733673012703548, "learning_rate": 5.82306830907055e-06, "loss": 0.142, "step": 805 }, { "epoch": 1.7755706269149998, "learning_rate": 5.767077267637178e-06, "loss": 0.1464, "step": 806 }, { "epoch": 1.7777739525596448, "learning_rate": 5.711086226203808e-06, "loss": 0.183, "step": 807 }, { "epoch": 1.7799772782042895, "learning_rate": 5.655095184770437e-06, "loss": 0.1608, "step": 808 }, { "epoch": 1.7821806038489345, "learning_rate": 5.599104143337066e-06, "loss": 0.1479, "step": 809 }, { "epoch": 1.7843839294935795, "learning_rate": 5.5431131019036955e-06, "loss": 0.1436, "step": 810 }, { "epoch": 1.7865872551382243, "learning_rate": 5.487122060470325e-06, "loss": 0.1642, "step": 811 }, { "epoch": 1.788790580782869, "learning_rate": 5.431131019036955e-06, "loss": 0.1371, "step": 812 }, { "epoch": 1.790993906427514, "learning_rate": 5.375139977603583e-06, "loss": 0.138, "step": 813 }, { "epoch": 1.793197232072159, "learning_rate": 5.319148936170213e-06, "loss": 0.1726, "step": 814 }, { "epoch": 1.7954005577168037, "learning_rate": 5.263157894736842e-06, "loss": 0.1085, "step": 815 }, { "epoch": 1.7976038833614487, "learning_rate": 5.207166853303471e-06, "loss": 0.1268, "step": 816 }, { "epoch": 1.7998072090060937, "learning_rate": 5.1511758118701006e-06, "loss": 0.1436, "step": 817 }, { "epoch": 1.8020105346507385, "learning_rate": 5.0951847704367306e-06, "loss": 0.1544, "step": 818 }, { "epoch": 1.8042138602953832, "learning_rate": 5.03919372900336e-06, "loss": 0.1392, "step": 819 }, { "epoch": 1.8064171859400282, "learning_rate": 4.983202687569989e-06, "loss": 0.1491, "step": 820 }, { "epoch": 1.8086205115846732, "learning_rate": 4.927211646136618e-06, "loss": 0.16, "step": 821 }, { "epoch": 1.810823837229318, "learning_rate": 4.871220604703248e-06, "loss": 0.1653, "step": 822 }, { "epoch": 1.813027162873963, "learning_rate": 4.815229563269877e-06, "loss": 0.1716, "step": 823 }, { "epoch": 1.815230488518608, "learning_rate": 4.759238521836506e-06, "loss": 0.1468, "step": 824 }, { "epoch": 1.8174338141632527, "learning_rate": 4.703247480403136e-06, "loss": 0.157, "step": 825 }, { "epoch": 1.8196371398078974, "learning_rate": 4.647256438969766e-06, "loss": 0.1551, "step": 826 }, { "epoch": 1.8218404654525424, "learning_rate": 4.591265397536394e-06, "loss": 0.1574, "step": 827 }, { "epoch": 1.8240437910971874, "learning_rate": 4.535274356103024e-06, "loss": 0.1623, "step": 828 }, { "epoch": 1.8262471167418322, "learning_rate": 4.479283314669653e-06, "loss": 0.1361, "step": 829 }, { "epoch": 1.8284504423864771, "learning_rate": 4.423292273236282e-06, "loss": 0.1584, "step": 830 }, { "epoch": 1.8306537680311221, "learning_rate": 4.3673012318029114e-06, "loss": 0.1582, "step": 831 }, { "epoch": 1.8328570936757669, "learning_rate": 4.3113101903695414e-06, "loss": 0.1599, "step": 832 }, { "epoch": 1.8350604193204116, "learning_rate": 4.255319148936171e-06, "loss": 0.1394, "step": 833 }, { "epoch": 1.8372637449650566, "learning_rate": 4.1993281075028e-06, "loss": 0.1491, "step": 834 }, { "epoch": 1.8394670706097016, "learning_rate": 4.143337066069429e-06, "loss": 0.1698, "step": 835 }, { "epoch": 1.8416703962543464, "learning_rate": 4.087346024636059e-06, "loss": 0.1836, "step": 836 }, { "epoch": 1.8438737218989911, "learning_rate": 4.031354983202687e-06, "loss": 0.153, "step": 837 }, { "epoch": 1.8460770475436363, "learning_rate": 3.975363941769317e-06, "loss": 0.1449, "step": 838 }, { "epoch": 1.848280373188281, "learning_rate": 3.9193729003359465e-06, "loss": 0.1364, "step": 839 }, { "epoch": 1.8504836988329258, "learning_rate": 3.8633818589025765e-06, "loss": 0.1297, "step": 840 }, { "epoch": 1.8526870244775708, "learning_rate": 3.8073908174692052e-06, "loss": 0.1278, "step": 841 }, { "epoch": 1.8548903501222158, "learning_rate": 3.751399776035835e-06, "loss": 0.1523, "step": 842 }, { "epoch": 1.8570936757668606, "learning_rate": 3.695408734602464e-06, "loss": 0.1549, "step": 843 }, { "epoch": 1.8592970014115053, "learning_rate": 3.6394176931690927e-06, "loss": 0.1703, "step": 844 }, { "epoch": 1.8615003270561505, "learning_rate": 3.5834266517357223e-06, "loss": 0.1704, "step": 845 }, { "epoch": 1.8637036527007953, "learning_rate": 3.5274356103023515e-06, "loss": 0.1753, "step": 846 }, { "epoch": 1.86590697834544, "learning_rate": 3.471444568868981e-06, "loss": 0.1572, "step": 847 }, { "epoch": 1.868110303990085, "learning_rate": 3.4154535274356102e-06, "loss": 0.1519, "step": 848 }, { "epoch": 1.87031362963473, "learning_rate": 3.35946248600224e-06, "loss": 0.1405, "step": 849 }, { "epoch": 1.8725169552793748, "learning_rate": 3.303471444568869e-06, "loss": 0.1866, "step": 850 }, { "epoch": 1.8747202809240195, "learning_rate": 3.2474804031354986e-06, "loss": 0.1356, "step": 851 }, { "epoch": 1.8769236065686645, "learning_rate": 3.1914893617021277e-06, "loss": 0.1554, "step": 852 }, { "epoch": 1.8791269322133095, "learning_rate": 3.1354983202687573e-06, "loss": 0.1508, "step": 853 }, { "epoch": 1.8813302578579543, "learning_rate": 3.0795072788353865e-06, "loss": 0.171, "step": 854 }, { "epoch": 1.8835335835025993, "learning_rate": 3.023516237402016e-06, "loss": 0.1408, "step": 855 }, { "epoch": 1.8857369091472442, "learning_rate": 2.9675251959686453e-06, "loss": 0.1445, "step": 856 }, { "epoch": 1.887940234791889, "learning_rate": 2.911534154535275e-06, "loss": 0.1866, "step": 857 }, { "epoch": 1.8901435604365338, "learning_rate": 2.855543113101904e-06, "loss": 0.1156, "step": 858 }, { "epoch": 1.8923468860811787, "learning_rate": 2.799552071668533e-06, "loss": 0.1349, "step": 859 }, { "epoch": 1.8945502117258237, "learning_rate": 2.7435610302351624e-06, "loss": 0.16, "step": 860 }, { "epoch": 1.8967535373704685, "learning_rate": 2.6875699888017915e-06, "loss": 0.1621, "step": 861 }, { "epoch": 1.8989568630151135, "learning_rate": 2.631578947368421e-06, "loss": 0.1346, "step": 862 }, { "epoch": 1.9011601886597584, "learning_rate": 2.5755879059350503e-06, "loss": 0.1525, "step": 863 }, { "epoch": 1.9033635143044032, "learning_rate": 2.51959686450168e-06, "loss": 0.1448, "step": 864 }, { "epoch": 1.905566839949048, "learning_rate": 2.463605823068309e-06, "loss": 0.1629, "step": 865 }, { "epoch": 1.907770165593693, "learning_rate": 2.4076147816349386e-06, "loss": 0.1587, "step": 866 }, { "epoch": 1.909973491238338, "learning_rate": 2.351623740201568e-06, "loss": 0.1594, "step": 867 }, { "epoch": 1.9121768168829827, "learning_rate": 2.295632698768197e-06, "loss": 0.1252, "step": 868 }, { "epoch": 1.9143801425276277, "learning_rate": 2.2396416573348266e-06, "loss": 0.1459, "step": 869 }, { "epoch": 1.9165834681722727, "learning_rate": 2.1836506159014557e-06, "loss": 0.1766, "step": 870 }, { "epoch": 1.9187867938169174, "learning_rate": 2.1276595744680853e-06, "loss": 0.1544, "step": 871 }, { "epoch": 1.9209901194615622, "learning_rate": 2.0716685330347145e-06, "loss": 0.1602, "step": 872 }, { "epoch": 1.9231934451062072, "learning_rate": 2.0156774916013436e-06, "loss": 0.1646, "step": 873 }, { "epoch": 1.9253967707508521, "learning_rate": 1.9596864501679732e-06, "loss": 0.1431, "step": 874 }, { "epoch": 1.927600096395497, "learning_rate": 1.9036954087346026e-06, "loss": 0.1385, "step": 875 }, { "epoch": 1.9298034220401419, "learning_rate": 1.847704367301232e-06, "loss": 0.165, "step": 876 }, { "epoch": 1.9320067476847869, "learning_rate": 1.7917133258678612e-06, "loss": 0.1602, "step": 877 }, { "epoch": 1.9342100733294316, "learning_rate": 1.7357222844344905e-06, "loss": 0.1555, "step": 878 }, { "epoch": 1.9364133989740764, "learning_rate": 1.67973124300112e-06, "loss": 0.1528, "step": 879 }, { "epoch": 1.9386167246187214, "learning_rate": 1.6237402015677493e-06, "loss": 0.1432, "step": 880 }, { "epoch": 1.9408200502633663, "learning_rate": 1.5677491601343787e-06, "loss": 0.1579, "step": 881 }, { "epoch": 1.943023375908011, "learning_rate": 1.511758118701008e-06, "loss": 0.1885, "step": 882 }, { "epoch": 1.945226701552656, "learning_rate": 1.4557670772676374e-06, "loss": 0.1559, "step": 883 }, { "epoch": 1.947430027197301, "learning_rate": 1.3997760358342666e-06, "loss": 0.1818, "step": 884 }, { "epoch": 1.9496333528419458, "learning_rate": 1.3437849944008958e-06, "loss": 0.1342, "step": 885 }, { "epoch": 1.9518366784865906, "learning_rate": 1.2877939529675251e-06, "loss": 0.1709, "step": 886 }, { "epoch": 1.9540400041312356, "learning_rate": 1.2318029115341545e-06, "loss": 0.1961, "step": 887 }, { "epoch": 1.9562433297758806, "learning_rate": 1.175811870100784e-06, "loss": 0.1542, "step": 888 }, { "epoch": 1.9584466554205253, "learning_rate": 1.1198208286674133e-06, "loss": 0.125, "step": 889 }, { "epoch": 1.96064998106517, "learning_rate": 1.0638297872340427e-06, "loss": 0.1569, "step": 890 }, { "epoch": 1.9628533067098153, "learning_rate": 1.0078387458006718e-06, "loss": 0.1714, "step": 891 }, { "epoch": 1.96505663235446, "learning_rate": 9.518477043673013e-07, "loss": 0.1163, "step": 892 }, { "epoch": 1.9672599579991048, "learning_rate": 8.958566629339306e-07, "loss": 0.138, "step": 893 }, { "epoch": 1.9694632836437498, "learning_rate": 8.3986562150056e-07, "loss": 0.1248, "step": 894 }, { "epoch": 1.9716666092883948, "learning_rate": 7.838745800671893e-07, "loss": 0.1659, "step": 895 }, { "epoch": 1.9738699349330395, "learning_rate": 7.278835386338187e-07, "loss": 0.181, "step": 896 }, { "epoch": 1.9760732605776843, "learning_rate": 6.718924972004479e-07, "loss": 0.1504, "step": 897 }, { "epoch": 1.9782765862223295, "learning_rate": 6.159014557670773e-07, "loss": 0.1832, "step": 898 }, { "epoch": 1.9804799118669743, "learning_rate": 5.599104143337066e-07, "loss": 0.1611, "step": 899 }, { "epoch": 1.982683237511619, "learning_rate": 5.039193729003359e-07, "loss": 0.164, "step": 900 }, { "epoch": 1.984886563156264, "learning_rate": 4.479283314669653e-07, "loss": 0.1252, "step": 901 }, { "epoch": 1.987089888800909, "learning_rate": 3.9193729003359467e-07, "loss": 0.1722, "step": 902 }, { "epoch": 1.9892932144455537, "learning_rate": 3.3594624860022394e-07, "loss": 0.1581, "step": 903 }, { "epoch": 1.9914965400901985, "learning_rate": 2.799552071668533e-07, "loss": 0.1474, "step": 904 }, { "epoch": 1.9936998657348435, "learning_rate": 2.2396416573348264e-07, "loss": 0.1623, "step": 905 }, { "epoch": 1.9959031913794885, "learning_rate": 1.6797312430011197e-07, "loss": 0.1588, "step": 906 }, { "epoch": 1.9981065170241332, "learning_rate": 1.1198208286674132e-07, "loss": 0.1542, "step": 907 }, { "epoch": 2.0, "learning_rate": 5.599104143337066e-08, "loss": 0.1542, "step": 908 }, { "epoch": 2.0, "step": 908, "total_flos": 2.742806676631683e+18, "train_loss": 0.2480007687723059, "train_runtime": 40148.8243, "train_samples_per_second": 5.788, "train_steps_per_second": 0.023 } ], "logging_steps": 1.0, "max_steps": 908, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.742806676631683e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }