| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.980744544287548, | |
| "eval_steps": 500, | |
| "global_step": 485, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.6114, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.5742, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6e-06, | |
| "loss": 2.4717, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.3307, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-05, | |
| "loss": 2.5579, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.999892908320647e-06, | |
| "loss": 2.1376, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.999571637870035e-06, | |
| "loss": 2.5183, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.999036202410324e-06, | |
| "loss": 2.6324, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.998286624877786e-06, | |
| "loss": 2.6522, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.997322937381829e-06, | |
| "loss": 2.8157, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.996145181203616e-06, | |
| "loss": 2.2681, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.994753406794303e-06, | |
| "loss": 2.4257, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.993147673772869e-06, | |
| "loss": 2.9611, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.99132805092358e-06, | |
| "loss": 2.6448, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.989294616193018e-06, | |
| "loss": 2.1739, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.98704745668676e-06, | |
| "loss": 2.3803, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.984586668665641e-06, | |
| "loss": 3.0124, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.981912357541628e-06, | |
| "loss": 1.8866, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.979024637873309e-06, | |
| "loss": 2.8247, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.975923633360985e-06, | |
| "loss": 2.3442, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.972609476841368e-06, | |
| "loss": 2.2966, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.96908231028189e-06, | |
| "loss": 2.5517, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.965342284774633e-06, | |
| "loss": 1.9759, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.961389560529835e-06, | |
| "loss": 2.2761, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.957224306869053e-06, | |
| "loss": 2.3277, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.952846702217886e-06, | |
| "loss": 2.5624, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.948256934098353e-06, | |
| "loss": 2.379, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.943455199120836e-06, | |
| "loss": 2.3016, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.938441702975689e-06, | |
| "loss": 2.2362, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.933216660424396e-06, | |
| "loss": 2.0744, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.92778029529039e-06, | |
| "loss": 2.6486, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.922132840449459e-06, | |
| "loss": 2.2122, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.916274537819774e-06, | |
| "loss": 2.3736, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.91020563835152e-06, | |
| "loss": 2.0414, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.903926402016153e-06, | |
| "loss": 2.222, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.897437097795257e-06, | |
| "loss": 2.6075, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 2.3274, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.883829406604363e-06, | |
| "loss": 2.3744, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.876711602542564e-06, | |
| "loss": 2.7945, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.869384896386669e-06, | |
| "loss": 2.3775, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.861849601988384e-06, | |
| "loss": 1.9743, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.854106042134642e-06, | |
| "loss": 2.6625, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.846154548533773e-06, | |
| "loss": 2.3661, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.8379954618013e-06, | |
| "loss": 2.2979, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.829629131445342e-06, | |
| "loss": 2.3176, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.821055915851647e-06, | |
| "loss": 2.2117, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.812276182268236e-06, | |
| "loss": 1.9806, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.803290306789676e-06, | |
| "loss": 2.2496, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.794098674340966e-06, | |
| "loss": 2.3943, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.784701678661045e-06, | |
| "loss": 2.0787, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.775099722285934e-06, | |
| "loss": 2.1421, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.765293216531486e-06, | |
| "loss": 2.4088, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.755282581475769e-06, | |
| "loss": 2.1875, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.745068245941071e-06, | |
| "loss": 2.0356, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.73465064747553e-06, | |
| "loss": 2.0821, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.72403023233439e-06, | |
| "loss": 1.8047, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.713207455460893e-06, | |
| "loss": 2.3556, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.702182780466775e-06, | |
| "loss": 2.2028, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.690956679612422e-06, | |
| "loss": 2.5292, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.67952963378663e-06, | |
| "loss": 2.0529, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.667902132486009e-06, | |
| "loss": 2.3667, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.656074673794018e-06, | |
| "loss": 2.2068, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.644047764359623e-06, | |
| "loss": 2.3572, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.63182191937559e-06, | |
| "loss": 1.9575, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.619397662556434e-06, | |
| "loss": 2.1685, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.606775526115963e-06, | |
| "loss": 2.2896, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.593956050744493e-06, | |
| "loss": 2.3626, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.58093978558568e-06, | |
| "loss": 2.0103, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.567727288213005e-06, | |
| "loss": 2.1916, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.55431912460588e-06, | |
| "loss": 2.2239, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.540715869125407e-06, | |
| "loss": 1.8908, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.526918104489777e-06, | |
| "loss": 2.2892, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.512926421749305e-06, | |
| "loss": 1.9166, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.498741420261109e-06, | |
| "loss": 2.0043, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.484363707663443e-06, | |
| "loss": 2.3196, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.469793899849663e-06, | |
| "loss": 2.2653, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.45503262094184e-06, | |
| "loss": 2.034, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.440080503264038e-06, | |
| "loss": 2.1738, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.42493818731521e-06, | |
| "loss": 2.1786, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.409606321741776e-06, | |
| "loss": 1.896, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.394085563309827e-06, | |
| "loss": 2.1103, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.378376576876999e-06, | |
| "loss": 1.8544, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.362480035363987e-06, | |
| "loss": 1.9015, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.34639661972572e-06, | |
| "loss": 2.3878, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.330127018922195e-06, | |
| "loss": 1.9042, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.31367192988896e-06, | |
| "loss": 2.297, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.297032057507264e-06, | |
| "loss": 2.1189, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.280208114573859e-06, | |
| "loss": 2.156, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.263200821770462e-06, | |
| "loss": 2.0641, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.246010907632894e-06, | |
| "loss": 2.3262, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.228639108519867e-06, | |
| "loss": 2.0385, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.211086168581433e-06, | |
| "loss": 2.0262, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.193352839727122e-06, | |
| "loss": 2.4263, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.175439881593716e-06, | |
| "loss": 1.9041, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.157348061512728e-06, | |
| "loss": 2.1657, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.139078154477512e-06, | |
| "loss": 2.2347, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.120630943110078e-06, | |
| "loss": 2.1755, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.102007217627568e-06, | |
| "loss": 2.0328, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.083207775808395e-06, | |
| "loss": 2.149, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.064233422958078e-06, | |
| "loss": 2.1247, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 1.9357, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.025763242814291e-06, | |
| "loss": 1.8592, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.006269063455305e-06, | |
| "loss": 2.0261, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 8.986603268863536e-06, | |
| "loss": 1.9487, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 8.966766701456177e-06, | |
| "loss": 2.1715, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 8.94676021096575e-06, | |
| "loss": 2.1337, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 8.926584654403725e-06, | |
| "loss": 2.3317, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 8.906240896023794e-06, | |
| "loss": 2.0257, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 8.885729807284855e-06, | |
| "loss": 2.0842, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 8.865052266813686e-06, | |
| "loss": 2.2196, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 8.844209160367298e-06, | |
| "loss": 2.0957, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 8.823201380795003e-06, | |
| "loss": 2.1453, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.802029828000157e-06, | |
| "loss": 2.1887, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 8.780695408901613e-06, | |
| "loss": 2.032, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 8.759199037394888e-06, | |
| "loss": 2.2083, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 8.737541634312985e-06, | |
| "loss": 2.3168, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 8.715724127386971e-06, | |
| "loss": 1.9182, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 8.693747451206231e-06, | |
| "loss": 1.8499, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.671612547178428e-06, | |
| "loss": 2.1667, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 8.649320363489178e-06, | |
| "loss": 1.9357, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 8.626871855061438e-06, | |
| "loss": 2.0429, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 8.604267983514595e-06, | |
| "loss": 1.8081, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 8.581509717123272e-06, | |
| "loss": 1.6956, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 8.558598030775857e-06, | |
| "loss": 2.2946, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 8.535533905932739e-06, | |
| "loss": 2.1193, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 8.51231833058426e-06, | |
| "loss": 2.327, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 8.488952299208402e-06, | |
| "loss": 1.911, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 8.465436812728181e-06, | |
| "loss": 2.2266, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 8.44177287846877e-06, | |
| "loss": 2.1731, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 8.417961510114357e-06, | |
| "loss": 2.2541, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.39400372766471e-06, | |
| "loss": 2.0563, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 8.36990055739149e-06, | |
| "loss": 1.8764, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 8.345653031794292e-06, | |
| "loss": 2.3466, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 8.32126218955641e-06, | |
| "loss": 2.2691, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 8.296729075500345e-06, | |
| "loss": 2.1656, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 8.272054740543053e-06, | |
| "loss": 2.2326, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 8.247240241650918e-06, | |
| "loss": 1.8526, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.222286641794488e-06, | |
| "loss": 1.6012, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.197195009902924e-06, | |
| "loss": 1.947, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.171966420818227e-06, | |
| "loss": 1.8734, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.146601955249187e-06, | |
| "loss": 1.756, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.12110269972509e-06, | |
| "loss": 1.7878, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.095469746549172e-06, | |
| "loss": 2.0159, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.069704193751834e-06, | |
| "loss": 2.1754, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.043807145043604e-06, | |
| "loss": 2.0156, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 8.017779709767857e-06, | |
| "loss": 1.938, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.991623002853296e-06, | |
| "loss": 1.9589, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.965338144766186e-06, | |
| "loss": 2.0535, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.938926261462366e-06, | |
| "loss": 2.0857, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.912388484339012e-06, | |
| "loss": 2.2401, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.88572595018617e-06, | |
| "loss": 1.9925, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 7.858939801138061e-06, | |
| "loss": 2.2118, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.832031184624165e-06, | |
| "loss": 1.8856, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.80500125332005e-06, | |
| "loss": 1.8032, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 7.777851165098012e-06, | |
| "loss": 2.0556, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 7.750582082977468e-06, | |
| "loss": 2.1473, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 7.723195175075136e-06, | |
| "loss": 1.767, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 7.695691614555002e-06, | |
| "loss": 1.8623, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 7.66807257957806e-06, | |
| "loss": 1.9875, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 7.64033925325184e-06, | |
| "loss": 2.0664, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 7.612492823579744e-06, | |
| "loss": 1.9954, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 7.584534483410137e-06, | |
| "loss": 1.7128, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 7.55646543038526e-06, | |
| "loss": 2.4184, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 7.528286866889924e-06, | |
| "loss": 2.2349, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.9001, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 7.471606041430724e-06, | |
| "loss": 1.8973, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 7.443106207484776e-06, | |
| "loss": 2.0085, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 7.414501719000187e-06, | |
| "loss": 1.5986, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 7.3857938012980425e-06, | |
| "loss": 2.2827, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 7.3569836841299905e-06, | |
| "loss": 1.8377, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 7.328072601625558e-06, | |
| "loss": 1.9012, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 7.2990617922393e-06, | |
| "loss": 1.8906, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 7.269952498697734e-06, | |
| "loss": 2.0498, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 7.240745967946113e-06, | |
| "loss": 2.1313, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.211443451095007e-06, | |
| "loss": 1.8483, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.18204620336671e-06, | |
| "loss": 2.0565, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 7.1525554840414765e-06, | |
| "loss": 1.8597, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.1229725564035665e-06, | |
| "loss": 2.0648, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.093298687687141e-06, | |
| "loss": 2.0188, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.063535149021974e-06, | |
| "loss": 1.8016, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.033683215379002e-06, | |
| "loss": 2.2722, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.0037441655157045e-06, | |
| "loss": 2.044, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6.973719281921336e-06, | |
| "loss": 2.0889, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 6.943609850761979e-06, | |
| "loss": 1.9273, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 6.913417161825449e-06, | |
| "loss": 1.8093, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 6.883142508466054e-06, | |
| "loss": 1.8979, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.852787187549182e-06, | |
| "loss": 1.5268, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 6.822352499395751e-06, | |
| "loss": 2.2526, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 6.7918397477265e-06, | |
| "loss": 2.0474, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 6.7612502396061685e-06, | |
| "loss": 2.0026, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.730585285387465e-06, | |
| "loss": 2.0033, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.6998461986549715e-06, | |
| "loss": 1.719, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.669034296168855e-06, | |
| "loss": 1.829, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 6.638150897808469e-06, | |
| "loss": 2.0211, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.607197326515808e-06, | |
| "loss": 2.052, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 6.57617490823885e-06, | |
| "loss": 1.9236, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 1.989, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 6.513928849212874e-06, | |
| "loss": 1.7597, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.482707874877855e-06, | |
| "loss": 2.0161, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 6.451423386272312e-06, | |
| "loss": 2.167, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 6.420076723519615e-06, | |
| "loss": 2.1043, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 6.388669229406462e-06, | |
| "loss": 1.7945, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.3572022493253715e-06, | |
| "loss": 1.8759, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.325677131217041e-06, | |
| "loss": 1.9408, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 6.294095225512604e-06, | |
| "loss": 1.9382, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.26245788507579e-06, | |
| "loss": 1.953, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 6.230766465144966e-06, | |
| "loss": 1.9079, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 6.199022323275083e-06, | |
| "loss": 2.141, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 6.1672268192795285e-06, | |
| "loss": 1.7766, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 6.135381315171867e-06, | |
| "loss": 1.8225, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 6.103487175107508e-06, | |
| "loss": 1.9764, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 6.071545765325254e-06, | |
| "loss": 1.815, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 6.039558454088796e-06, | |
| "loss": 2.0872, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 6.0075266116280865e-06, | |
| "loss": 2.0516, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.975451610080643e-06, | |
| "loss": 1.9711, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 5.943334823432777e-06, | |
| "loss": 2.0024, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 5.911177627460739e-06, | |
| "loss": 2.0042, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.878981399671774e-06, | |
| "loss": 1.7748, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 5.846747519245123e-06, | |
| "loss": 2.0583, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 5.814477366972945e-06, | |
| "loss": 2.1047, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 5.782172325201155e-06, | |
| "loss": 1.9893, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 5.749833777770225e-06, | |
| "loss": 1.8167, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 5.717463109955896e-06, | |
| "loss": 1.8661, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 5.6850617084098416e-06, | |
| "loss": 2.0974, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 5.65263096110026e-06, | |
| "loss": 1.8873, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 5.620172257252427e-06, | |
| "loss": 1.7506, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 5.587686987289189e-06, | |
| "loss": 1.9003, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 5.555176542771389e-06, | |
| "loss": 1.906, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 1.935, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 5.490085701647805e-06, | |
| "loss": 1.7954, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 5.457508093317013e-06, | |
| "loss": 1.9815, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 5.4249108868622095e-06, | |
| "loss": 1.6584, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 5.392295478639226e-06, | |
| "loss": 1.8019, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 5.3596632657835975e-06, | |
| "loss": 2.1204, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.327015646150716e-06, | |
| "loss": 2.1109, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.294354018255945e-06, | |
| "loss": 1.9626, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.2616797812147205e-06, | |
| "loss": 1.8431, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.228994334682605e-06, | |
| "loss": 1.818, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.1962990787953436e-06, | |
| "loss": 1.8086, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.1635954141088815e-06, | |
| "loss": 1.8096, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.130884741539367e-06, | |
| "loss": 1.9406, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.098168462303141e-06, | |
| "loss": 2.0109, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.065447977856723e-06, | |
| "loss": 1.8903, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 5.0327246898367595e-06, | |
| "loss": 1.9648, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 5e-06, | |
| "loss": 1.9892, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.967275310163241e-06, | |
| "loss": 2.0007, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.934552022143279e-06, | |
| "loss": 1.7414, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.90183153769686e-06, | |
| "loss": 1.701, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.869115258460636e-06, | |
| "loss": 2.3587, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.83640458589112e-06, | |
| "loss": 1.8817, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.803700921204659e-06, | |
| "loss": 1.9942, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.771005665317398e-06, | |
| "loss": 2.2835, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.738320218785281e-06, | |
| "loss": 1.4821, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.705645981744055e-06, | |
| "loss": 1.8867, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.672984353849285e-06, | |
| "loss": 2.2334, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.640336734216403e-06, | |
| "loss": 1.8587, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 4.6077045213607765e-06, | |
| "loss": 1.8544, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 4.575089113137792e-06, | |
| "loss": 2.0754, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 4.542491906682988e-06, | |
| "loss": 2.0149, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 4.509914298352197e-06, | |
| "loss": 1.9791, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 4.477357683661734e-06, | |
| "loss": 1.6395, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 4.4448234572286126e-06, | |
| "loss": 2.11, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.4123130127108125e-06, | |
| "loss": 2.041, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.379827742747575e-06, | |
| "loss": 2.2184, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.347369038899744e-06, | |
| "loss": 1.7426, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.314938291590161e-06, | |
| "loss": 1.9714, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.282536890044105e-06, | |
| "loss": 2.0392, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.250166222229775e-06, | |
| "loss": 2.2633, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.217827674798845e-06, | |
| "loss": 2.0275, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.185522633027057e-06, | |
| "loss": 1.8916, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.1532524807548776e-06, | |
| "loss": 1.7847, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 4.1210186003282275e-06, | |
| "loss": 1.9785, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 4.088822372539263e-06, | |
| "loss": 1.858, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 4.056665176567225e-06, | |
| "loss": 2.0106, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 4.02454838991936e-06, | |
| "loss": 1.9469, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.992473388371914e-06, | |
| "loss": 2.327, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.960441545911205e-06, | |
| "loss": 1.9751, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.928454234674748e-06, | |
| "loss": 1.7995, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 3.8965128248924956e-06, | |
| "loss": 1.853, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.864618684828135e-06, | |
| "loss": 2.0151, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.832773180720475e-06, | |
| "loss": 2.1437, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.800977676724919e-06, | |
| "loss": 2.1601, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 3.769233534855035e-06, | |
| "loss": 1.9736, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 3.7375421149242102e-06, | |
| "loss": 1.7847, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 3.705904774487396e-06, | |
| "loss": 2.1208, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.6743228687829596e-06, | |
| "loss": 2.009, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.6427977506746293e-06, | |
| "loss": 1.6825, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.6113307705935398e-06, | |
| "loss": 1.6349, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.579923276480387e-06, | |
| "loss": 2.0538, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.5485766137276894e-06, | |
| "loss": 2.0987, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 3.517292125122146e-06, | |
| "loss": 1.9249, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.486071150787128e-06, | |
| "loss": 2.1965, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 1.8131, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.4238250917611533e-06, | |
| "loss": 1.7838, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.3928026734841935e-06, | |
| "loss": 1.7282, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.3618491021915334e-06, | |
| "loss": 1.9375, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 3.330965703831146e-06, | |
| "loss": 1.6664, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 3.3001538013450285e-06, | |
| "loss": 2.164, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.269414714612534e-06, | |
| "loss": 2.0269, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 3.2387497603938327e-06, | |
| "loss": 1.9625, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.2081602522734987e-06, | |
| "loss": 2.2313, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.177647500604252e-06, | |
| "loss": 2.1034, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.147212812450819e-06, | |
| "loss": 2.0628, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.1168574915339465e-06, | |
| "loss": 2.2198, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 3.0865828381745515e-06, | |
| "loss": 2.3057, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 3.056390149238022e-06, | |
| "loss": 1.8151, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 3.0262807180786647e-06, | |
| "loss": 2.0671, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 2.9962558344842963e-06, | |
| "loss": 2.1226, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 2.966316784621e-06, | |
| "loss": 2.0534, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 2.936464850978027e-06, | |
| "loss": 2.1771, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 2.906701312312861e-06, | |
| "loss": 2.1316, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2.8770274435964356e-06, | |
| "loss": 1.8236, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 2.8474445159585235e-06, | |
| "loss": 1.8514, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 2.817953796633289e-06, | |
| "loss": 2.1408, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 2.7885565489049948e-06, | |
| "loss": 1.7615, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 2.759254032053888e-06, | |
| "loss": 1.8991, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 2.7300475013022666e-06, | |
| "loss": 1.8208, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 2.700938207760701e-06, | |
| "loss": 1.6085, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 2.671927398374443e-06, | |
| "loss": 1.8248, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 2.6430163158700116e-06, | |
| "loss": 1.95, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 2.614206198701958e-06, | |
| "loss": 1.7459, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 2.5854982809998154e-06, | |
| "loss": 2.2413, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 2.5568937925152272e-06, | |
| "loss": 2.181, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 2.5283939585692787e-06, | |
| "loss": 1.6875, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 1.692, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 2.471713133110078e-06, | |
| "loss": 1.8894, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 2.4435345696147404e-06, | |
| "loss": 2.2015, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 2.4154655165898626e-06, | |
| "loss": 1.8859, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 2.387507176420256e-06, | |
| "loss": 2.0344, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 2.3596607467481602e-06, | |
| "loss": 1.8513, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 2.3319274204219427e-06, | |
| "loss": 1.9896, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 2.304308385444999e-06, | |
| "loss": 1.6932, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2.2768048249248648e-06, | |
| "loss": 2.0101, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 2.2494179170225333e-06, | |
| "loss": 1.793, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2.2221488349019903e-06, | |
| "loss": 1.8287, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2.1949987466799524e-06, | |
| "loss": 2.2081, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 2.1679688153758373e-06, | |
| "loss": 1.9535, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2.1410601988619394e-06, | |
| "loss": 1.9921, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2.1142740498138327e-06, | |
| "loss": 2.0291, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 2.08761151566099e-06, | |
| "loss": 2.063, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2.061073738537635e-06, | |
| "loss": 1.5788, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 2.034661855233815e-06, | |
| "loss": 2.2809, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 2.008376997146705e-06, | |
| "loss": 1.9602, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.982220290232143e-06, | |
| "loss": 1.507, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 1.956192854956397e-06, | |
| "loss": 1.5588, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1.9302958062481673e-06, | |
| "loss": 1.9348, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.9045302534508298e-06, | |
| "loss": 1.8372, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.8788973002749112e-06, | |
| "loss": 1.672, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.8533980447508138e-06, | |
| "loss": 1.8803, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 1.8280335791817733e-06, | |
| "loss": 2.133, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.8028049900970768e-06, | |
| "loss": 1.7064, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.777713358205514e-06, | |
| "loss": 1.8624, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.7527597583490825e-06, | |
| "loss": 1.7757, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.7279452594569484e-06, | |
| "loss": 1.9208, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.7032709244996559e-06, | |
| "loss": 1.9518, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.6787378104435931e-06, | |
| "loss": 1.6618, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 2.1538, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.6300994426085103e-06, | |
| "loss": 1.9981, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.6059962723352912e-06, | |
| "loss": 1.9644, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.5820384898856433e-06, | |
| "loss": 2.0848, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.5582271215312294e-06, | |
| "loss": 2.0623, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.5345631872718214e-06, | |
| "loss": 1.9082, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.5110477007916002e-06, | |
| "loss": 1.944, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1.487681669415742e-06, | |
| "loss": 1.7845, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.4644660940672628e-06, | |
| "loss": 2.0057, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.4414019692241437e-06, | |
| "loss": 2.2701, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.4184902828767288e-06, | |
| "loss": 1.8745, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 1.395732016485406e-06, | |
| "loss": 1.8174, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.373128144938563e-06, | |
| "loss": 1.9715, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.3506796365108232e-06, | |
| "loss": 1.8625, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.3283874528215735e-06, | |
| "loss": 2.1635, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.30625254879377e-06, | |
| "loss": 1.9431, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1.2842758726130283e-06, | |
| "loss": 1.7817, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 1.2624583656870153e-06, | |
| "loss": 2.1267, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 1.2408009626051137e-06, | |
| "loss": 2.2342, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 1.2193045910983864e-06, | |
| "loss": 1.8949, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 1.1979701719998454e-06, | |
| "loss": 1.8478, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.1767986192049986e-06, | |
| "loss": 1.927, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.1557908396327028e-06, | |
| "loss": 1.7817, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 1.134947733186315e-06, | |
| "loss": 2.1291, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.1142701927151456e-06, | |
| "loss": 2.0033, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 1.0937591039762086e-06, | |
| "loss": 1.8841, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 1.0734153455962765e-06, | |
| "loss": 1.4088, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.0532397890342506e-06, | |
| "loss": 1.9065, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 1.0332332985438248e-06, | |
| "loss": 1.9917, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1.013396731136465e-06, | |
| "loss": 1.7053, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 9.937309365446973e-07, | |
| "loss": 1.7789, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 9.742367571857092e-07, | |
| "loss": 1.9505, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 1.6999, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.357665770419244e-07, | |
| "loss": 1.8436, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.167922241916055e-07, | |
| "loss": 1.9749, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 8.979927823724321e-07, | |
| "loss": 2.0322, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 8.793690568899216e-07, | |
| "loss": 2.0703, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 8.609218455224893e-07, | |
| "loss": 1.9611, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 8.426519384872733e-07, | |
| "loss": 2.1701, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 8.245601184062851e-07, | |
| "loss": 2.0095, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 8.066471602728804e-07, | |
| "loss": 1.8908, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 7.88913831418568e-07, | |
| "loss": 2.1547, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 7.71360891480134e-07, | |
| "loss": 1.9623, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 7.539890923671061e-07, | |
| "loss": 1.8405, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 7.367991782295392e-07, | |
| "loss": 1.926, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 7.197918854261432e-07, | |
| "loss": 2.2612, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 7.029679424927366e-07, | |
| "loss": 2.0554, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 6.863280701110409e-07, | |
| "loss": 1.7727, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 6.698729810778065e-07, | |
| "loss": 1.8858, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 6.536033802742814e-07, | |
| "loss": 1.8505, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 6.375199646360142e-07, | |
| "loss": 2.0033, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.216234231230012e-07, | |
| "loss": 2.0853, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 6.059144366901737e-07, | |
| "loss": 1.684, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 5.903936782582253e-07, | |
| "loss": 2.0125, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 5.750618126847912e-07, | |
| "loss": 1.7071, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 5.599194967359639e-07, | |
| "loss": 2.0058, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 5.449673790581611e-07, | |
| "loss": 1.8514, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 5.302061001503395e-07, | |
| "loss": 1.7583, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 5.156362923365587e-07, | |
| "loss": 1.649, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 5.012585797388936e-07, | |
| "loss": 2.2002, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 4.87073578250698e-07, | |
| "loss": 2.2455, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 4.730818955102234e-07, | |
| "loss": 1.6698, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 4.5928413087459325e-07, | |
| "loss": 1.9811, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 4.456808753941205e-07, | |
| "loss": 1.9963, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 1.5793, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 4.1906021441432074e-07, | |
| "loss": 1.7237, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 4.0604394925550906e-07, | |
| "loss": 1.6936, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 3.9322447388403796e-07, | |
| "loss": 2.0876, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 3.8060233744356634e-07, | |
| "loss": 1.8514, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 3.6817808062440953e-07, | |
| "loss": 2.3487, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 3.5595223564037884e-07, | |
| "loss": 1.8364, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 3.439253262059822e-07, | |
| "loss": 1.9163, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 3.320978675139919e-07, | |
| "loss": 1.9985, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 3.204703662133724e-07, | |
| "loss": 1.9434, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 3.0904332038757977e-07, | |
| "loss": 1.9705, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 2.9781721953322627e-07, | |
| "loss": 2.2868, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 2.867925445391079e-07, | |
| "loss": 1.8121, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2.7596976766560977e-07, | |
| "loss": 1.6713, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 2.653493525244721e-07, | |
| "loss": 1.8284, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 2.5493175405893076e-07, | |
| "loss": 2.011, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 2.447174185242324e-07, | |
| "loss": 2.1148, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 2.3470678346851517e-07, | |
| "loss": 2.0046, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 2.2490027771406686e-07, | |
| "loss": 1.9366, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 2.152983213389559e-07, | |
| "loss": 2.1379, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 2.0590132565903475e-07, | |
| "loss": 1.9382, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 1.9670969321032407e-07, | |
| "loss": 1.8226, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 1.8772381773176417e-07, | |
| "loss": 2.2887, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 1.7894408414835362e-07, | |
| "loss": 1.7401, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 1.7037086855465902e-07, | |
| "loss": 1.713, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 1.6200453819870122e-07, | |
| "loss": 1.9873, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 1.5384545146622854e-07, | |
| "loss": 2.2339, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 1.4589395786535954e-07, | |
| "loss": 2.4256, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 1.3815039801161723e-07, | |
| "loss": 2.1304, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 1.3061510361333186e-07, | |
| "loss": 1.829, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 1.232883974574367e-07, | |
| "loss": 1.9966, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 1.1617059339563807e-07, | |
| "loss": 1.8668, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 1.0926199633097156e-07, | |
| "loss": 1.7622, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 1.0256290220474308e-07, | |
| "loss": 1.9253, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 9.607359798384785e-08, | |
| "loss": 1.8139, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 8.979436164848088e-08, | |
| "loss": 1.9552, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 8.372546218022747e-08, | |
| "loss": 1.5488, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 7.786715955054202e-08, | |
| "loss": 2.1687, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 7.221970470961125e-08, | |
| "loss": 1.7, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 6.678333957560513e-08, | |
| "loss": 2.0648, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 6.15582970243117e-08, | |
| "loss": 1.8835, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 5.654480087916303e-08, | |
| "loss": 1.8804, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 5.174306590164879e-08, | |
| "loss": 2.2831, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 4.715329778211375e-08, | |
| "loss": 1.9674, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 4.2775693130948094e-08, | |
| "loss": 2.0009, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 3.861043947016474e-08, | |
| "loss": 1.6058, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 3.465771522536854e-08, | |
| "loss": 1.7313, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 3.09176897181096e-08, | |
| "loss": 1.8912, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 2.7390523158633552e-08, | |
| "loss": 2.0388, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 2.4076366639015914e-08, | |
| "loss": 1.8365, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 2.097536212669171e-08, | |
| "loss": 1.9795, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 1.8087642458373135e-08, | |
| "loss": 1.9468, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 1.541333133436018e-08, | |
| "loss": 1.7218, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 1.2952543313240474e-08, | |
| "loss": 1.3056, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 1.0705383806982606e-08, | |
| "loss": 1.6465, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 8.671949076420883e-09, | |
| "loss": 1.6287, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 6.852326227130835e-09, | |
| "loss": 1.9142, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 5.246593205699424e-09, | |
| "loss": 2.4245, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 3.854818796385495e-09, | |
| "loss": 1.9302, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 2.6770626181715776e-09, | |
| "loss": 1.5904, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 1.7133751222137007e-09, | |
| "loss": 1.9541, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 9.637975896759077e-10, | |
| "loss": 1.7176, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.283621299649987e-10, | |
| "loss": 1.9053, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 1.0709167935385456e-10, | |
| "loss": 2.0116, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 0.0, | |
| "loss": 1.9722, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "step": 485, | |
| "total_flos": 4.3609614855438336e+17, | |
| "train_loss": 2.0201566543775735, | |
| "train_runtime": 8786.7992, | |
| "train_samples_per_second": 0.443, | |
| "train_steps_per_second": 0.055 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 485, | |
| "num_train_epochs": 5, | |
| "save_steps": 1000, | |
| "total_flos": 4.3609614855438336e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |