| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.943820224719101, | |
| "eval_steps": 500, | |
| "global_step": 385, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.5e-06, | |
| "loss": 2.3199, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5e-06, | |
| "loss": 2.6164, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 2.7792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6204, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.999830024102874e-06, | |
| "loss": 2.3813, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.99932010796822e-06, | |
| "loss": 2.5856, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.998470286265415e-06, | |
| "loss": 2.3747, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.997280616774147e-06, | |
| "loss": 2.5818, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.995751180380468e-06, | |
| "loss": 2.5867, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.993882081071307e-06, | |
| "loss": 2.2268, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.991673445927399e-06, | |
| "loss": 2.6059, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.989125425114639e-06, | |
| "loss": 2.0894, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.986238191873874e-06, | |
| "loss": 2.2201, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.983011942509131e-06, | |
| "loss": 2.316, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.979446896374264e-06, | |
| "loss": 2.6564, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.975543295858035e-06, | |
| "loss": 2.465, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.971301406367644e-06, | |
| "loss": 2.4582, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.966721516310683e-06, | |
| "loss": 2.2573, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.961803937075516e-06, | |
| "loss": 2.3717, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.956549003010122e-06, | |
| "loss": 2.6225, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.950957071399357e-06, | |
| "loss": 2.0773, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.945028522440654e-06, | |
| "loss": 2.2186, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.938763759218186e-06, | |
| "loss": 2.7806, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.93216320767545e-06, | |
| "loss": 2.5508, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.925227316586316e-06, | |
| "loss": 2.2016, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.917956557524511e-06, | |
| "loss": 2.2435, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.910351424831545e-06, | |
| "loss": 2.5108, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.902412435583127e-06, | |
| "loss": 2.2933, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.89414012955398e-06, | |
| "loss": 2.1846, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.885535069181163e-06, | |
| "loss": 2.9822, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.876597839525814e-06, | |
| "loss": 2.231, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.867329048233387e-06, | |
| "loss": 2.2585, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.857729325492329e-06, | |
| "loss": 2.3573, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.847799323991234e-06, | |
| "loss": 2.2582, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.837539718874466e-06, | |
| "loss": 2.2804, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.826951207696258e-06, | |
| "loss": 2.864, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.816034510373287e-06, | |
| "loss": 2.1242, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.804790369135719e-06, | |
| "loss": 2.2738, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.793219548476754e-06, | |
| "loss": 2.6035, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.781322835100639e-06, | |
| "loss": 2.1281, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.769101037869187e-06, | |
| "loss": 2.392, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.756554987746777e-06, | |
| "loss": 2.2579, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.743685537743856e-06, | |
| "loss": 2.1741, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.730493562858954e-06, | |
| "loss": 2.2772, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.716979960019173e-06, | |
| "loss": 2.2809, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.70314564801922e-06, | |
| "loss": 2.3821, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.688991567458934e-06, | |
| "loss": 2.5027, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.67451868067933e-06, | |
| "loss": 2.3994, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.659727971697173e-06, | |
| "loss": 2.3403, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.644620446138078e-06, | |
| "loss": 2.2843, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.629197131168125e-06, | |
| "loss": 1.9102, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.613459075424033e-06, | |
| "loss": 2.0563, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.597407348941865e-06, | |
| "loss": 2.5812, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.58104304308426e-06, | |
| "loss": 2.0869, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.564367270466247e-06, | |
| "loss": 1.9037, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.54738116487959e-06, | |
| "loss": 2.3678, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.530085881215705e-06, | |
| "loss": 2.2848, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.512482595387131e-06, | |
| "loss": 2.0607, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.494572504247593e-06, | |
| "loss": 1.956, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.476356825510613e-06, | |
| "loss": 2.2119, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.457836797666722e-06, | |
| "loss": 2.2242, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.439013679899263e-06, | |
| "loss": 2.259, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.419888751998768e-06, | |
| "loss": 2.2482, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.400463314275942e-06, | |
| "loss": 2.0579, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.380738687473274e-06, | |
| "loss": 1.9384, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.360716212675213e-06, | |
| "loss": 2.1505, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.340397251217009e-06, | |
| "loss": 2.0986, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.319783184592142e-06, | |
| "loss": 2.3174, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.298875414358399e-06, | |
| "loss": 2.1534, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.27767536204258e-06, | |
| "loss": 2.1114, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.256184469043852e-06, | |
| "loss": 1.9863, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.23440419653574e-06, | |
| "loss": 2.137, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.212336025366789e-06, | |
| "loss": 2.225, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.189981455959873e-06, | |
| "loss": 2.0334, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.167342008210191e-06, | |
| "loss": 1.9056, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.144419221381919e-06, | |
| "loss": 2.144, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.121214654003561e-06, | |
| "loss": 1.8992, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.097729883761977e-06, | |
| "loss": 1.8587, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.073966507395123e-06, | |
| "loss": 2.5454, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.049926140583487e-06, | |
| "loss": 2.0381, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.025610417840238e-06, | |
| "loss": 2.0646, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.001020992400086e-06, | |
| "loss": 1.6412, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 8.976159536106895e-06, | |
| "loss": 1.9907, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 8.951027739299996e-06, | |
| "loss": 1.8317, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 8.925627310699275e-06, | |
| "loss": 2.1631, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 8.899959977288988e-06, | |
| "loss": 2.2149, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 8.874027484200342e-06, | |
| "loss": 2.2374, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 8.847831594592851e-06, | |
| "loss": 2.124, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 8.821374089534446e-06, | |
| "loss": 2.0088, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.794656767880394e-06, | |
| "loss": 2.1843, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 8.767681446150977e-06, | |
| "loss": 2.552, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 8.740449958408006e-06, | |
| "loss": 1.7471, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 8.7129641561301e-06, | |
| "loss": 1.9054, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 8.68522590808682e-06, | |
| "loss": 2.1348, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.657237100211604e-06, | |
| "loss": 2.0139, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 8.628999635473547e-06, | |
| "loss": 1.9181, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 8.600515433748003e-06, | |
| "loss": 2.2683, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 8.571786431686074e-06, | |
| "loss": 1.7892, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 8.542814582582917e-06, | |
| "loss": 1.9259, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 8.513601856244951e-06, | |
| "loss": 1.9594, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 8.484150238855921e-06, | |
| "loss": 2.1425, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 8.454461732841864e-06, | |
| "loss": 2.1687, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 8.424538356734957e-06, | |
| "loss": 2.128, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 8.394382145036277e-06, | |
| "loss": 2.3052, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.363995148077481e-06, | |
| "loss": 2.1029, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 8.333379431881398e-06, | |
| "loss": 1.9932, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 8.302537078021555e-06, | |
| "loss": 1.9616, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 8.271470183480664e-06, | |
| "loss": 2.0529, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 8.240180860508027e-06, | |
| "loss": 1.8921, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 8.208671236475945e-06, | |
| "loss": 1.7787, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.176943453735062e-06, | |
| "loss": 2.0703, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.144999669468714e-06, | |
| "loss": 1.9988, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.112842055546254e-06, | |
| "loss": 1.8816, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.080472798375392e-06, | |
| "loss": 1.953, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.04789409875354e-06, | |
| "loss": 2.0868, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.015108171718177e-06, | |
| "loss": 2.2089, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.982117246396246e-06, | |
| "loss": 1.9521, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.948923565852597e-06, | |
| "loss": 2.2335, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.915529386937486e-06, | |
| "loss": 2.2536, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.881936980133118e-06, | |
| "loss": 1.6541, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.848148629399287e-06, | |
| "loss": 1.9498, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.814166632018083e-06, | |
| "loss": 2.3166, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.779993298437704e-06, | |
| "loss": 2.1169, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 7.745630952115365e-06, | |
| "loss": 2.1505, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 7.711081929359316e-06, | |
| "loss": 1.9007, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 7.67634857917002e-06, | |
| "loss": 2.1772, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 7.641433263080418e-06, | |
| "loss": 2.4341, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 7.606338354995381e-06, | |
| "loss": 1.7081, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 7.571066241030302e-06, | |
| "loss": 2.0402, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 7.5356193193488655e-06, | |
| "loss": 2.0681, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.5562, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 7.464210704754009e-06, | |
| "loss": 1.7387, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 7.4282538669379186e-06, | |
| "loss": 2.1956, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 7.3921319312700365e-06, | |
| "loss": 2.0449, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 7.355847353693729e-06, | |
| "loss": 1.8579, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 7.319402601210448e-06, | |
| "loss": 2.0661, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 7.282800151711991e-06, | |
| "loss": 2.1408, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 7.246042493812036e-06, | |
| "loss": 1.729, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 7.209132126676934e-06, | |
| "loss": 2.3547, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.172071559855792e-06, | |
| "loss": 2.2959, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.134863313109847e-06, | |
| "loss": 2.3131, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 7.097509916241145e-06, | |
| "loss": 1.7705, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.060013908920549e-06, | |
| "loss": 1.6909, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.022377840515047e-06, | |
| "loss": 1.84, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 6.984604269914437e-06, | |
| "loss": 1.977, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 6.94669576535734e-06, | |
| "loss": 2.177, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 6.908654904256584e-06, | |
| "loss": 1.9606, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 6.870484273023967e-06, | |
| "loss": 2.0072, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 6.832186466894402e-06, | |
| "loss": 1.7583, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 6.793764089749473e-06, | |
| "loss": 1.8085, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 6.755219753940389e-06, | |
| "loss": 1.7839, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 6.716556080110374e-06, | |
| "loss": 1.9219, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.677775697016484e-06, | |
| "loss": 2.1836, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.638881241350884e-06, | |
| "loss": 1.964, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 6.599875357561572e-06, | |
| "loss": 1.8509, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.560760697672583e-06, | |
| "loss": 2.2632, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 6.5215399211036815e-06, | |
| "loss": 1.9777, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 6.4822156944895375e-06, | |
| "loss": 1.9851, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.442790691498433e-06, | |
| "loss": 2.204, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 6.403267592650466e-06, | |
| "loss": 1.7941, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 6.363649085135311e-06, | |
| "loss": 1.8559, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.323937862629513e-06, | |
| "loss": 1.9673, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.2841366251133405e-06, | |
| "loss": 1.883, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 6.244248078687213e-06, | |
| "loss": 1.9343, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.204274935387716e-06, | |
| "loss": 1.8082, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 6.164219913003208e-06, | |
| "loss": 1.9898, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 6.124085734889034e-06, | |
| "loss": 1.6458, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 6.083875129782366e-06, | |
| "loss": 2.0815, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 6.043590831616677e-06, | |
| "loss": 2.1997, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 6.003235579335851e-06, | |
| "loss": 2.1733, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.962812116707977e-06, | |
| "loss": 1.8058, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.92232319213878e-06, | |
| "loss": 2.1662, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 5.8817715584847744e-06, | |
| "loss": 1.8951, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 5.841159972866085e-06, | |
| "loss": 1.9074, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 5.800491196478989e-06, | |
| "loss": 1.9271, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 5.759767994408188e-06, | |
| "loss": 1.9044, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 5.718993135438803e-06, | |
| "loss": 1.9798, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 5.678169391868128e-06, | |
| "loss": 1.9495, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 5.637299539317141e-06, | |
| "loss": 2.1539, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 5.596386356541779e-06, | |
| "loss": 2.0293, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 5.555432625244024e-06, | |
| "loss": 1.8224, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 5.51444112988276e-06, | |
| "loss": 1.6832, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 5.473414657484468e-06, | |
| "loss": 2.0847, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 5.432355997453729e-06, | |
| "loss": 2.0309, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 5.391267941383572e-06, | |
| "loss": 2.0406, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 5.350153282865674e-06, | |
| "loss": 1.7257, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 5.309014817300422e-06, | |
| "loss": 1.8888, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.26785534170685e-06, | |
| "loss": 1.8149, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.226677654532476e-06, | |
| "loss": 2.0397, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.185484555463026e-06, | |
| "loss": 2.1468, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.1442788452320915e-06, | |
| "loss": 2.1732, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.1030633254306935e-06, | |
| "loss": 2.2631, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.061840798316815e-06, | |
| "loss": 1.9009, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.020614066624868e-06, | |
| "loss": 2.2187, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.979385933375133e-06, | |
| "loss": 1.6122, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.9381592016831856e-06, | |
| "loss": 1.5505, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.896936674569309e-06, | |
| "loss": 1.843, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.85572115476791e-06, | |
| "loss": 1.7565, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.814515444536975e-06, | |
| "loss": 1.8699, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.773322345467525e-06, | |
| "loss": 1.9872, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.732144658293151e-06, | |
| "loss": 1.9223, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.690985182699581e-06, | |
| "loss": 1.9225, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.649846717134327e-06, | |
| "loss": 1.8284, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.6087320586164296e-06, | |
| "loss": 1.8652, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.567644002546273e-06, | |
| "loss": 1.735, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 4.526585342515533e-06, | |
| "loss": 2.0562, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 4.485558870117241e-06, | |
| "loss": 2.0004, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 4.444567374755978e-06, | |
| "loss": 2.2094, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 4.403613643458222e-06, | |
| "loss": 1.9606, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.362700460682861e-06, | |
| "loss": 1.984, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.321830608131872e-06, | |
| "loss": 1.7363, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.281006864561199e-06, | |
| "loss": 1.9783, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.240232005591816e-06, | |
| "loss": 1.6583, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.1995088035210126e-06, | |
| "loss": 2.3748, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.158840027133917e-06, | |
| "loss": 2.0012, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.1182284415152255e-06, | |
| "loss": 1.6849, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 4.077676807861221e-06, | |
| "loss": 1.729, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 4.037187883292027e-06, | |
| "loss": 2.2028, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.996764420664149e-06, | |
| "loss": 1.9073, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.956409168383325e-06, | |
| "loss": 1.6662, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.916124870217635e-06, | |
| "loss": 1.9193, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.875914265110967e-06, | |
| "loss": 1.8654, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 3.835780086996794e-06, | |
| "loss": 1.9015, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.7957250646122843e-06, | |
| "loss": 1.9406, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.755751921312788e-06, | |
| "loss": 1.8809, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.715863374886661e-06, | |
| "loss": 1.8371, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 3.6760621373704867e-06, | |
| "loss": 2.0746, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 3.636350914864689e-06, | |
| "loss": 1.822, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.5967324073495363e-06, | |
| "loss": 1.7246, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.5572093085015683e-06, | |
| "loss": 1.6679, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.5177843055104633e-06, | |
| "loss": 1.8069, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.4784600788963197e-06, | |
| "loss": 1.9182, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 3.4392393023274173e-06, | |
| "loss": 1.6175, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.4001246424384294e-06, | |
| "loss": 1.8909, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.361118758649116e-06, | |
| "loss": 2.0512, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.322224302983517e-06, | |
| "loss": 1.8031, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.2834439198896285e-06, | |
| "loss": 1.8325, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 3.2447802460596124e-06, | |
| "loss": 1.9987, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.206235910250529e-06, | |
| "loss": 1.694, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 3.167813533105598e-06, | |
| "loss": 2.1121, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.1295157269760347e-06, | |
| "loss": 2.1676, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.0913450957434177e-06, | |
| "loss": 1.9139, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.0533042346426612e-06, | |
| "loss": 1.8614, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 3.015395730085565e-06, | |
| "loss": 1.9445, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 2.9776221594849565e-06, | |
| "loss": 2.1084, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 2.9399860910794532e-06, | |
| "loss": 1.9299, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 2.902490083758856e-06, | |
| "loss": 1.7569, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 2.8651366868901543e-06, | |
| "loss": 1.5915, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2.8279284401442085e-06, | |
| "loss": 1.4711, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 2.790867873323067e-06, | |
| "loss": 1.7658, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 2.753957506187964e-06, | |
| "loss": 2.2383, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 2.7171998482880093e-06, | |
| "loss": 2.1103, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 2.680597398789554e-06, | |
| "loss": 1.9208, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 2.6441526463062727e-06, | |
| "loss": 1.9773, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 2.607868068729966e-06, | |
| "loss": 2.0155, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 2.571746133062082e-06, | |
| "loss": 1.8626, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 2.5357892952459917e-06, | |
| "loss": 1.764, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 2.0152, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 2.4643806806511344e-06, | |
| "loss": 1.8742, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 2.4289337589697e-06, | |
| "loss": 2.0988, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 2.3936616450046207e-06, | |
| "loss": 1.9274, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 2.3585667369195815e-06, | |
| "loss": 1.5094, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 2.32365142082998e-06, | |
| "loss": 2.0823, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 2.288918070640684e-06, | |
| "loss": 1.6446, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 2.254369047884639e-06, | |
| "loss": 1.9535, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2.2200067015622986e-06, | |
| "loss": 1.5839, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 2.185833367981918e-06, | |
| "loss": 1.7815, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2.1518513706007154e-06, | |
| "loss": 1.4904, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2.118063019866884e-06, | |
| "loss": 2.2307, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2.0844706130625146e-06, | |
| "loss": 1.947, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2.0510764341474032e-06, | |
| "loss": 2.2949, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 2.0178827536037547e-06, | |
| "loss": 1.7868, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.9848918282818242e-06, | |
| "loss": 1.663, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.952105901246461e-06, | |
| "loss": 1.7499, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.9195272016246105e-06, | |
| "loss": 1.938, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 1.887157944453749e-06, | |
| "loss": 2.0385, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.855000330531289e-06, | |
| "loss": 2.0374, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.823056546264939e-06, | |
| "loss": 1.7599, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.7913287635240573e-06, | |
| "loss": 2.1512, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.7598191394919738e-06, | |
| "loss": 1.8319, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.7285298165193388e-06, | |
| "loss": 1.7238, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.697462921978446e-06, | |
| "loss": 1.8568, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.6666205681186032e-06, | |
| "loss": 2.1115, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.6360048519225197e-06, | |
| "loss": 1.8881, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.6056178549637248e-06, | |
| "loss": 1.8789, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.5754616432650443e-06, | |
| "loss": 2.168, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.5455382671581365e-06, | |
| "loss": 1.9499, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.5158497611440792e-06, | |
| "loss": 2.0706, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.48639814375505e-06, | |
| "loss": 1.9817, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.4571854174170847e-06, | |
| "loss": 1.8163, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1.428213568313927e-06, | |
| "loss": 1.785, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.3994845662519985e-06, | |
| "loss": 2.0604, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.3710003645264559e-06, | |
| "loss": 1.7002, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 1.3427628997883957e-06, | |
| "loss": 1.788, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.3147740919131814e-06, | |
| "loss": 1.5869, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.2870358438699005e-06, | |
| "loss": 1.6432, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.2595500415919948e-06, | |
| "loss": 1.9052, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1.232318553849023e-06, | |
| "loss": 1.8955, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 1.2053432321196085e-06, | |
| "loss": 1.904, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 1.1786259104655562e-06, | |
| "loss": 2.0135, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 1.1521684054071524e-06, | |
| "loss": 1.8603, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.1259725157996593e-06, | |
| "loss": 1.7627, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.1000400227110142e-06, | |
| "loss": 1.6693, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 1.0743726893007257e-06, | |
| "loss": 1.779, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 1.0489722607000052e-06, | |
| "loss": 2.0575, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 1.0238404638931077e-06, | |
| "loss": 1.9037, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 9.989790075999145e-07, | |
| "loss": 1.9991, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 9.743895821597638e-07, | |
| "loss": 2.0821, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 9.500738594165132e-07, | |
| "loss": 1.9613, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 9.260334926048787e-07, | |
| "loss": 1.939, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 9.022701162380259e-07, | |
| "loss": 1.7692, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 8.787853459964407e-07, | |
| "loss": 2.0053, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 8.555807786180814e-07, | |
| "loss": 1.8909, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 8.326579917898098e-07, | |
| "loss": 1.8692, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 8.100185440401276e-07, | |
| "loss": 2.1948, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 7.876639746332132e-07, | |
| "loss": 2.2319, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 7.655958034642619e-07, | |
| "loss": 1.8725, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 7.43815530956149e-07, | |
| "loss": 1.5717, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 7.223246379574206e-07, | |
| "loss": 1.7549, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 7.011245856416016e-07, | |
| "loss": 2.0717, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 6.802168154078586e-07, | |
| "loss": 1.9039, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 6.596027487829915e-07, | |
| "loss": 2.0704, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 6.392837873247876e-07, | |
| "loss": 1.8727, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 6.192613125267283e-07, | |
| "loss": 1.8494, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 5.995366857240592e-07, | |
| "loss": 1.9835, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 5.801112480012344e-07, | |
| "loss": 2.0905, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 5.609863201007382e-07, | |
| "loss": 1.8491, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 5.421632023332779e-07, | |
| "loss": 1.6643, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 5.236431744893883e-07, | |
| "loss": 1.5409, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 5.054274957524075e-07, | |
| "loss": 1.6956, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 4.875174046128684e-07, | |
| "loss": 1.9333, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 4.6991411878429593e-07, | |
| "loss": 1.7577, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 4.526188351204103e-07, | |
| "loss": 2.0727, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 4.3563272953375426e-07, | |
| "loss": 1.8069, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 4.1895695691574146e-07, | |
| "loss": 2.0435, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 4.025926510581357e-07, | |
| "loss": 2.0467, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 3.8654092457596714e-07, | |
| "loss": 1.6247, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 3.7080286883187713e-07, | |
| "loss": 1.9954, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 3.553795538619237e-07, | |
| "loss": 2.255, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 3.402720283028277e-07, | |
| "loss": 1.9724, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 3.2548131932067184e-07, | |
| "loss": 1.9318, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 3.110084325410667e-07, | |
| "loss": 1.7369, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 2.9685435198078095e-07, | |
| "loss": 1.7993, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 2.830200399808286e-07, | |
| "loss": 1.9586, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.6950643714104774e-07, | |
| "loss": 1.6359, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 2.563144622561453e-07, | |
| "loss": 1.8904, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2.4344501225322557e-07, | |
| "loss": 1.7661, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 2.3089896213081553e-07, | |
| "loss": 1.8997, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 2.1867716489936297e-07, | |
| "loss": 1.759, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 2.0678045152324798e-07, | |
| "loss": 1.7521, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 1.9520963086428258e-07, | |
| "loss": 1.5358, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 1.8396548962671456e-07, | |
| "loss": 2.0727, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 1.7304879230374328e-07, | |
| "loss": 2.0473, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 1.6246028112553603e-07, | |
| "loss": 1.9068, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 1.5220067600876686e-07, | |
| "loss": 2.1523, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 1.422706745076713e-07, | |
| "loss": 1.9869, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 1.3267095176661304e-07, | |
| "loss": 2.0737, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 1.2340216047418697e-07, | |
| "loss": 1.9659, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 1.1446493081883891e-07, | |
| "loss": 1.4132, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 1.0585987044602009e-07, | |
| "loss": 1.7613, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 9.758756441687333e-08, | |
| "loss": 2.0321, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 8.964857516845449e-08, | |
| "loss": 2.1659, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 8.204344247549067e-08, | |
| "loss": 1.7783, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 7.47726834136836e-08, | |
| "loss": 1.8563, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 6.783679232455043e-08, | |
| "loss": 1.986, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 6.123624078181512e-08, | |
| "loss": 1.8735, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 5.4971477559346286e-08, | |
| "loss": 1.5537, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 4.90429286006433e-08, | |
| "loss": 1.857, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 4.34509969898772e-08, | |
| "loss": 1.673, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 3.819606292448541e-08, | |
| "loss": 1.9837, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 3.327848368931907e-08, | |
| "loss": 1.6531, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 2.8698593632357496e-08, | |
| "loss": 1.9188, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 2.4456704141967437e-08, | |
| "loss": 1.9565, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.0553103625737813e-08, | |
| "loss": 1.6245, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 1.6988057490868736e-08, | |
| "loss": 1.7511, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 1.3761808126126486e-08, | |
| "loss": 1.8122, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 1.0874574885362809e-08, | |
| "loss": 1.6269, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 8.32655407260241e-09, | |
| "loss": 2.0738, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 6.117918928693623e-09, | |
| "loss": 2.0557, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 4.248819619533384e-09, | |
| "loss": 1.8619, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 2.7193832258537447e-09, | |
| "loss": 2.2485, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.5297137345843261e-09, | |
| "loss": 1.9175, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 6.798920317807601e-10, | |
| "loss": 2.099, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 1.6997589712575145e-10, | |
| "loss": 2.1961, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 0.0, | |
| "loss": 2.2319, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "step": 385, | |
| "total_flos": 3.4617941689368576e+17, | |
| "train_loss": 2.0085288332654283, | |
| "train_runtime": 6983.5696, | |
| "train_samples_per_second": 0.446, | |
| "train_steps_per_second": 0.055 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 385, | |
| "num_train_epochs": 5, | |
| "save_steps": 1000, | |
| "total_flos": 3.4617941689368576e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |