| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9997400571874188, | |
| "eval_steps": 500, | |
| "global_step": 1923, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 1.3265, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.2154, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.4138, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.2762, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.2921, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3e-06, | |
| "loss": 1.4118, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.5000000000000004e-06, | |
| "loss": 1.4223, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.3753, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.5e-06, | |
| "loss": 1.1367, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3021, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 1.4498, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6e-06, | |
| "loss": 1.2938, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 1.1682, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 1.2197, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.5e-06, | |
| "loss": 1.6633, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.4189, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.500000000000002e-06, | |
| "loss": 1.3703, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9e-06, | |
| "loss": 1.4922, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.5e-06, | |
| "loss": 1.1706, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3173, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.05e-05, | |
| "loss": 1.2831, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 1.4416, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.1500000000000002e-05, | |
| "loss": 1.3837, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.3636, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.3739, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 1.2441, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 1.3829, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 1.3339, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.45e-05, | |
| "loss": 1.1033, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.9786, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.55e-05, | |
| "loss": 1.4697, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.3152, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.65e-05, | |
| "loss": 1.1868, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 1.2242, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.75e-05, | |
| "loss": 1.2609, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.3084, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.85e-05, | |
| "loss": 1.4121, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9e-05, | |
| "loss": 1.3678, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9500000000000003e-05, | |
| "loss": 1.215, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2735, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.05e-05, | |
| "loss": 1.3642, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.1e-05, | |
| "loss": 1.2973, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.15e-05, | |
| "loss": 1.3737, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 1.4091, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.25e-05, | |
| "loss": 1.1951, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 1.4724, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.35e-05, | |
| "loss": 1.4764, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.3698, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.45e-05, | |
| "loss": 1.3879, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.2186, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.5500000000000003e-05, | |
| "loss": 1.2671, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 1.1507, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.6500000000000004e-05, | |
| "loss": 1.3694, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 1.3214, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 1.3684, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 1.1656, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.8499999999999998e-05, | |
| "loss": 1.2861, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9e-05, | |
| "loss": 1.31, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.95e-05, | |
| "loss": 1.2966, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2768, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.05e-05, | |
| "loss": 1.3013, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.1e-05, | |
| "loss": 1.3436, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.15e-05, | |
| "loss": 1.4593, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.0969, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 1.3638, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.3e-05, | |
| "loss": 1.2177, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.35e-05, | |
| "loss": 1.3399, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 1.1634, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.45e-05, | |
| "loss": 1.1654, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.2155, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.55e-05, | |
| "loss": 1.1203, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.0554, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.65e-05, | |
| "loss": 1.5825, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.7e-05, | |
| "loss": 1.0265, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.2088, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.2954, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.85e-05, | |
| "loss": 1.6167, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 1.1433, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.9500000000000005e-05, | |
| "loss": 1.1323, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3639, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.05e-05, | |
| "loss": 1.2744, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.1e-05, | |
| "loss": 1.3432, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.15e-05, | |
| "loss": 1.2454, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.1253, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.25e-05, | |
| "loss": 1.0888, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.3e-05, | |
| "loss": 1.2655, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.35e-05, | |
| "loss": 1.1097, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.13, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.4500000000000004e-05, | |
| "loss": 1.4336, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.2444, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.55e-05, | |
| "loss": 1.5719, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.3214, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.6500000000000005e-05, | |
| "loss": 1.1302, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.3135, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.75e-05, | |
| "loss": 1.2013, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.2798, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.85e-05, | |
| "loss": 1.2612, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9e-05, | |
| "loss": 1.2751, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9500000000000004e-05, | |
| "loss": 1.4106, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3302, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.05e-05, | |
| "loss": 1.3724, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.1000000000000006e-05, | |
| "loss": 1.372, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.1500000000000005e-05, | |
| "loss": 1.3211, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.575, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.25e-05, | |
| "loss": 1.1218, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.300000000000001e-05, | |
| "loss": 1.2705, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.3500000000000006e-05, | |
| "loss": 1.2601, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 1.0858, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.45e-05, | |
| "loss": 1.093, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.174, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.550000000000001e-05, | |
| "loss": 1.1384, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.1938, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.65e-05, | |
| "loss": 1.3795, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 1.1647, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.7499999999999995e-05, | |
| "loss": 1.2393, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.8e-05, | |
| "loss": 1.3243, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.85e-05, | |
| "loss": 1.2405, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.9e-05, | |
| "loss": 1.2137, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.95e-05, | |
| "loss": 1.3568, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1655, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.05e-05, | |
| "loss": 1.2738, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.1e-05, | |
| "loss": 1.2492, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.15e-05, | |
| "loss": 1.2742, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.2e-05, | |
| "loss": 1.2629, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.25e-05, | |
| "loss": 1.2166, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.3e-05, | |
| "loss": 1.4565, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.35e-05, | |
| "loss": 1.307, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 1.3814, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.450000000000001e-05, | |
| "loss": 1.0619, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.1153, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.55e-05, | |
| "loss": 1.0533, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.6e-05, | |
| "loss": 1.3519, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.65e-05, | |
| "loss": 1.2274, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.7e-05, | |
| "loss": 1.2153, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.750000000000001e-05, | |
| "loss": 1.3973, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 1.2013, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.850000000000001e-05, | |
| "loss": 1.1725, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.9e-05, | |
| "loss": 1.3099, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.95e-05, | |
| "loss": 1.0581, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7e-05, | |
| "loss": 1.307, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.05e-05, | |
| "loss": 1.2178, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.1e-05, | |
| "loss": 1.1576, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.15e-05, | |
| "loss": 1.2082, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.2e-05, | |
| "loss": 1.2107, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.25e-05, | |
| "loss": 1.3164, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.3e-05, | |
| "loss": 1.1493, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.35e-05, | |
| "loss": 1.2999, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.4e-05, | |
| "loss": 1.2204, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.450000000000001e-05, | |
| "loss": 1.3198, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.2885, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.55e-05, | |
| "loss": 1.1629, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.6e-05, | |
| "loss": 1.3117, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.65e-05, | |
| "loss": 1.2879, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.7e-05, | |
| "loss": 1.3134, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.4065, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 1.2643, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.850000000000001e-05, | |
| "loss": 1.3002, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.900000000000001e-05, | |
| "loss": 1.0212, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.950000000000001e-05, | |
| "loss": 1.3631, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1889, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.05e-05, | |
| "loss": 1.2936, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.1e-05, | |
| "loss": 1.2504, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.15e-05, | |
| "loss": 1.0772, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.2e-05, | |
| "loss": 1.2375, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.25e-05, | |
| "loss": 1.4532, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.3e-05, | |
| "loss": 1.2731, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.35e-05, | |
| "loss": 1.5938, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.4e-05, | |
| "loss": 1.333, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.450000000000001e-05, | |
| "loss": 1.0296, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.1217, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.55e-05, | |
| "loss": 1.3373, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.6e-05, | |
| "loss": 1.2632, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.65e-05, | |
| "loss": 1.2222, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.7e-05, | |
| "loss": 1.4764, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.75e-05, | |
| "loss": 1.1269, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 1.0338, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.850000000000001e-05, | |
| "loss": 1.4067, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.900000000000001e-05, | |
| "loss": 1.0529, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.950000000000001e-05, | |
| "loss": 1.2269, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2431, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.05e-05, | |
| "loss": 1.3188, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.1e-05, | |
| "loss": 1.1709, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.15e-05, | |
| "loss": 1.1214, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 1.189, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.250000000000001e-05, | |
| "loss": 1.2679, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.300000000000001e-05, | |
| "loss": 1.2885, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.350000000000001e-05, | |
| "loss": 1.3915, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.4e-05, | |
| "loss": 1.0889, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.449999999999999e-05, | |
| "loss": 1.3092, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.9545, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.55e-05, | |
| "loss": 1.1133, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.6e-05, | |
| "loss": 1.2836, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.65e-05, | |
| "loss": 1.2318, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.7e-05, | |
| "loss": 1.1629, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.75e-05, | |
| "loss": 1.2815, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.8e-05, | |
| "loss": 1.0077, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.850000000000001e-05, | |
| "loss": 1.2258, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 1.1527, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.95e-05, | |
| "loss": 1.2455, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1776, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.9999916886977e-05, | |
| "loss": 1.1374, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.999966754818431e-05, | |
| "loss": 1.0304, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.999925198445083e-05, | |
| "loss": 1.315, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.999867019715816e-05, | |
| "loss": 1.0497, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.999792218824043e-05, | |
| "loss": 1.235, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.99970079601844e-05, | |
| "loss": 1.1516, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.999592751602948e-05, | |
| "loss": 1.3269, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.999468085936763e-05, | |
| "loss": 1.2229, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.999326799434334e-05, | |
| "loss": 1.247, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.999168892565375e-05, | |
| "loss": 1.1759, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.998994365854849e-05, | |
| "loss": 1.2796, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.998803219882972e-05, | |
| "loss": 1.2271, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.998595455285217e-05, | |
| "loss": 1.2924, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.9983710727523e-05, | |
| "loss": 1.1457, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.998130073030183e-05, | |
| "loss": 1.2093, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.997872456920076e-05, | |
| "loss": 1.293, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.997598225278432e-05, | |
| "loss": 1.0672, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.997307379016935e-05, | |
| "loss": 1.0995, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.996999919102514e-05, | |
| "loss": 1.2144, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.996675846557324e-05, | |
| "loss": 1.2003, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.99633516245875e-05, | |
| "loss": 1.0402, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.995977867939406e-05, | |
| "loss": 1.1233, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.995603964187121e-05, | |
| "loss": 1.3863, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.995213452444949e-05, | |
| "loss": 1.4199, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.994806334011153e-05, | |
| "loss": 1.2665, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.994382610239209e-05, | |
| "loss": 1.2067, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.993942282537793e-05, | |
| "loss": 1.2441, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.993485352370786e-05, | |
| "loss": 1.2809, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.993011821257258e-05, | |
| "loss": 1.1514, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.992521690771477e-05, | |
| "loss": 1.3324, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.992014962542891e-05, | |
| "loss": 1.2969, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.991491638256128e-05, | |
| "loss": 1.0613, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.990951719650991e-05, | |
| "loss": 1.3351, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.990395208522451e-05, | |
| "loss": 1.2896, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.98982210672064e-05, | |
| "loss": 1.544, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.989232416150847e-05, | |
| "loss": 1.2168, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.988626138773512e-05, | |
| "loss": 1.2035, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.988003276604214e-05, | |
| "loss": 1.4066, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.987363831713675e-05, | |
| "loss": 1.1118, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.98670780622774e-05, | |
| "loss": 1.1596, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.98603520232738e-05, | |
| "loss": 1.2041, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.985346022248682e-05, | |
| "loss": 1.3492, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.984640268282839e-05, | |
| "loss": 1.3059, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.983917942776143e-05, | |
| "loss": 1.1398, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.983179048129984e-05, | |
| "loss": 1.1331, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.982423586800828e-05, | |
| "loss": 1.2026, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.981651561300227e-05, | |
| "loss": 1.1979, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.980862974194794e-05, | |
| "loss": 1.3297, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.9800578281062e-05, | |
| "loss": 1.3714, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.979236125711176e-05, | |
| "loss": 1.3026, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.978397869741483e-05, | |
| "loss": 1.3155, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.977543062983925e-05, | |
| "loss": 1.4042, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.976671708280323e-05, | |
| "loss": 1.2624, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.975783808527513e-05, | |
| "loss": 1.1971, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.974879366677338e-05, | |
| "loss": 1.0979, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.973958385736632e-05, | |
| "loss": 1.2437, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.973020868767219e-05, | |
| "loss": 1.4261, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.97206681888589e-05, | |
| "loss": 1.0455, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.971096239264406e-05, | |
| "loss": 1.2655, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.970109133129477e-05, | |
| "loss": 1.3763, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.96910550376276e-05, | |
| "loss": 1.4274, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.968085354500843e-05, | |
| "loss": 1.23, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.96704868873523e-05, | |
| "loss": 1.1988, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.96599550991234e-05, | |
| "loss": 1.0926, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.964925821533488e-05, | |
| "loss": 1.1961, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.963839627154875e-05, | |
| "loss": 1.4652, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.962736930387577e-05, | |
| "loss": 1.1523, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.961617734897534e-05, | |
| "loss": 1.4453, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.960482044405532e-05, | |
| "loss": 1.1945, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.959329862687202e-05, | |
| "loss": 1.3258, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.95816119357299e-05, | |
| "loss": 1.32, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.956976040948166e-05, | |
| "loss": 1.3227, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.955774408752794e-05, | |
| "loss": 1.155, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.954556300981723e-05, | |
| "loss": 1.1726, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.95332172168458e-05, | |
| "loss": 1.0085, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.952070674965749e-05, | |
| "loss": 1.3393, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.950803164984362e-05, | |
| "loss": 1.2202, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.949519195954279e-05, | |
| "loss": 1.2616, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.948218772144087e-05, | |
| "loss": 1.1509, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.946901897877068e-05, | |
| "loss": 1.3472, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.945568577531199e-05, | |
| "loss": 1.2072, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.944218815539132e-05, | |
| "loss": 1.1268, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.94285261638818e-05, | |
| "loss": 1.2487, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.9414699846203e-05, | |
| "loss": 1.1807, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.940070924832079e-05, | |
| "loss": 1.1669, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.93865544167472e-05, | |
| "loss": 1.1645, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.93722353985403e-05, | |
| "loss": 1.2843, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.935775224130392e-05, | |
| "loss": 1.2936, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.934310499318766e-05, | |
| "loss": 0.9255, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.932829370288658e-05, | |
| "loss": 1.3423, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.931331841964113e-05, | |
| "loss": 1.3437, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.929817919323695e-05, | |
| "loss": 1.2699, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.92828760740047e-05, | |
| "loss": 0.9829, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.926740911281995e-05, | |
| "loss": 1.3234, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.925177836110294e-05, | |
| "loss": 1.326, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.923598387081839e-05, | |
| "loss": 1.2118, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.922002569447545e-05, | |
| "loss": 1.2041, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.92039038851274e-05, | |
| "loss": 1.0476, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.918761849637152e-05, | |
| "loss": 1.2216, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.917116958234894e-05, | |
| "loss": 1.304, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.91545571977444e-05, | |
| "loss": 1.1485, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.913778139778615e-05, | |
| "loss": 1.2469, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.912084223824567e-05, | |
| "loss": 1.2226, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.910373977543757e-05, | |
| "loss": 1.3169, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.90864740662193e-05, | |
| "loss": 1.3588, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.906904516799112e-05, | |
| "loss": 1.3137, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.905145313869574e-05, | |
| "loss": 1.0384, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.903369803681823e-05, | |
| "loss": 1.1589, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.901577992138582e-05, | |
| "loss": 1.1683, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.899769885196763e-05, | |
| "loss": 1.3877, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.897945488867457e-05, | |
| "loss": 1.2704, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.896104809215907e-05, | |
| "loss": 0.9693, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.894247852361494e-05, | |
| "loss": 1.2223, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.892374624477705e-05, | |
| "loss": 1.1193, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.890485131792127e-05, | |
| "loss": 0.9616, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.888579380586421e-05, | |
| "loss": 1.1675, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.886657377196292e-05, | |
| "loss": 1.4157, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.884719128011483e-05, | |
| "loss": 1.0697, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.882764639475746e-05, | |
| "loss": 1.2046, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.880793918086816e-05, | |
| "loss": 1.4468, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.878806970396397e-05, | |
| "loss": 1.0372, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.876803803010142e-05, | |
| "loss": 1.3172, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.874784422587617e-05, | |
| "loss": 1.1049, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.8727488358423e-05, | |
| "loss": 1.3502, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.87069704954154e-05, | |
| "loss": 1.2951, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.868629070506543e-05, | |
| "loss": 1.0411, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.866544905612347e-05, | |
| "loss": 1.1961, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.864444561787805e-05, | |
| "loss": 1.2872, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.862328046015551e-05, | |
| "loss": 1.0193, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.860195365331989e-05, | |
| "loss": 1.256, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.858046526827258e-05, | |
| "loss": 1.1076, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.855881537645218e-05, | |
| "loss": 1.195, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.85370040498342e-05, | |
| "loss": 1.1291, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.851503136093085e-05, | |
| "loss": 1.1176, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.849289738279079e-05, | |
| "loss": 1.2578, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.847060218899891e-05, | |
| "loss": 1.1173, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.844814585367605e-05, | |
| "loss": 1.3805, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.842552845147874e-05, | |
| "loss": 1.1338, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.840275005759905e-05, | |
| "loss": 1.1474, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.837981074776417e-05, | |
| "loss": 1.1238, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.835671059823637e-05, | |
| "loss": 1.2331, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.833344968581253e-05, | |
| "loss": 1.1747, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.831002808782408e-05, | |
| "loss": 1.2161, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.82864458821366e-05, | |
| "loss": 1.1954, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.826270314714962e-05, | |
| "loss": 1.176, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.823879996179638e-05, | |
| "loss": 1.0719, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.821473640554348e-05, | |
| "loss": 1.374, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.819051255839076e-05, | |
| "loss": 1.1604, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.816612850087088e-05, | |
| "loss": 1.2255, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.814158431404915e-05, | |
| "loss": 1.2576, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.811688007952325e-05, | |
| "loss": 1.2603, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.80920158794229e-05, | |
| "loss": 1.1246, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.806699179640968e-05, | |
| "loss": 1.2878, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.804180791367665e-05, | |
| "loss": 1.3484, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.801646431494818e-05, | |
| "loss": 1.2683, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.799096108447955e-05, | |
| "loss": 1.3375, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.796529830705686e-05, | |
| "loss": 1.2114, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.793947606799649e-05, | |
| "loss": 1.1716, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.791349445314504e-05, | |
| "loss": 1.2046, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.78873535488789e-05, | |
| "loss": 1.1576, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.78610534421041e-05, | |
| "loss": 1.0715, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.783459422025584e-05, | |
| "loss": 1.1537, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.780797597129841e-05, | |
| "loss": 1.2881, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.778119878372471e-05, | |
| "loss": 1.0485, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.775426274655607e-05, | |
| "loss": 1.2284, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.772716794934189e-05, | |
| "loss": 1.109, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.769991448215942e-05, | |
| "loss": 1.1225, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.767250243561335e-05, | |
| "loss": 1.2791, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.764493190083561e-05, | |
| "loss": 1.0072, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.761720296948505e-05, | |
| "loss": 1.0999, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.758931573374704e-05, | |
| "loss": 1.4052, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.75612702863333e-05, | |
| "loss": 1.387, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.75330667204815e-05, | |
| "loss": 1.3822, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.7504705129955e-05, | |
| "loss": 1.175, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.747618560904249e-05, | |
| "loss": 1.4638, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.744750825255768e-05, | |
| "loss": 1.2045, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.741867315583912e-05, | |
| "loss": 1.3583, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.738968041474963e-05, | |
| "loss": 1.2506, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.736053012567619e-05, | |
| "loss": 1.2797, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.733122238552957e-05, | |
| "loss": 1.0465, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.730175729174396e-05, | |
| "loss": 1.3715, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.727213494227665e-05, | |
| "loss": 1.1819, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.72423554356078e-05, | |
| "loss": 1.1403, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.721241887073999e-05, | |
| "loss": 1.1891, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.718232534719793e-05, | |
| "loss": 1.3049, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.715207496502821e-05, | |
| "loss": 1.156, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.712166782479885e-05, | |
| "loss": 1.3982, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.7091104027599e-05, | |
| "loss": 1.0459, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.706038367503866e-05, | |
| "loss": 1.1016, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.702950686924828e-05, | |
| "loss": 1.0758, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.699847371287845e-05, | |
| "loss": 1.0696, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.696728430909953e-05, | |
| "loss": 1.1031, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.693593876160139e-05, | |
| "loss": 1.0106, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.690443717459292e-05, | |
| "loss": 1.3341, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.687277965280181e-05, | |
| "loss": 1.0979, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.684096630147415e-05, | |
| "loss": 1.1858, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.680899722637411e-05, | |
| "loss": 1.163, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.677687253378353e-05, | |
| "loss": 1.1796, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.674459233050166e-05, | |
| "loss": 1.2926, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.671215672384465e-05, | |
| "loss": 1.0633, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.667956582164541e-05, | |
| "loss": 1.3512, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.664681973225305e-05, | |
| "loss": 1.4255, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.661391856453262e-05, | |
| "loss": 1.362, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.658086242786475e-05, | |
| "loss": 1.2563, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.654765143214526e-05, | |
| "loss": 1.0424, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.65142856877848e-05, | |
| "loss": 1.2177, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.648076530570849e-05, | |
| "loss": 1.2181, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.644709039735553e-05, | |
| "loss": 1.1583, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.641326107467887e-05, | |
| "loss": 0.9852, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.63792774501448e-05, | |
| "loss": 1.2722, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.634513963673257e-05, | |
| "loss": 1.2874, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.631084774793409e-05, | |
| "loss": 1.4289, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.627640189775342e-05, | |
| "loss": 1.1595, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.624180220070655e-05, | |
| "loss": 1.5097, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.620704877182087e-05, | |
| "loss": 1.27, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.617214172663489e-05, | |
| "loss": 1.2607, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.61370811811978e-05, | |
| "loss": 1.163, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.610186725206914e-05, | |
| "loss": 1.195, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.606650005631835e-05, | |
| "loss": 0.8829, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.603097971152439e-05, | |
| "loss": 1.2487, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.599530633577541e-05, | |
| "loss": 1.0727, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.595948004766828e-05, | |
| "loss": 1.148, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.592350096630825e-05, | |
| "loss": 1.2615, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.588736921130854e-05, | |
| "loss": 1.3796, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.585108490278992e-05, | |
| "loss": 1.245, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.581464816138032e-05, | |
| "loss": 0.9468, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.577805910821447e-05, | |
| "loss": 1.2144, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.574131786493341e-05, | |
| "loss": 1.1647, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.57044245536842e-05, | |
| "loss": 1.1677, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.566737929711942e-05, | |
| "loss": 1.0524, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.563018221839682e-05, | |
| "loss": 1.0839, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.559283344117881e-05, | |
| "loss": 1.3635, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.555533308963223e-05, | |
| "loss": 1.259, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.551768128842776e-05, | |
| "loss": 1.3303, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.547987816273963e-05, | |
| "loss": 0.8336, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.544192383824509e-05, | |
| "loss": 1.2629, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.54038184411241e-05, | |
| "loss": 1.018, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.536556209805882e-05, | |
| "loss": 1.1639, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.532715493623332e-05, | |
| "loss": 1.2744, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.528859708333297e-05, | |
| "loss": 1.185, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.524988866754418e-05, | |
| "loss": 1.1974, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.521102981755388e-05, | |
| "loss": 1.3143, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.517202066254913e-05, | |
| "loss": 1.1848, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.513286133221669e-05, | |
| "loss": 1.2064, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.509355195674255e-05, | |
| "loss": 1.1289, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.505409266681158e-05, | |
| "loss": 1.3492, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.501448359360698e-05, | |
| "loss": 1.0746, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.497472486880998e-05, | |
| "loss": 1.471, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.493481662459926e-05, | |
| "loss": 1.3751, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.489475899365065e-05, | |
| "loss": 1.2825, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.485455210913654e-05, | |
| "loss": 1.2538, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.481419610472559e-05, | |
| "loss": 1.2412, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.477369111458216e-05, | |
| "loss": 1.4307, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.473303727336596e-05, | |
| "loss": 1.1483, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.469223471623151e-05, | |
| "loss": 1.3021, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.465128357882778e-05, | |
| "loss": 1.256, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.461018399729768e-05, | |
| "loss": 1.0797, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.456893610827764e-05, | |
| "loss": 0.9405, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.45275400488971e-05, | |
| "loss": 1.2256, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.448599595677816e-05, | |
| "loss": 1.2766, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.444430397003501e-05, | |
| "loss": 1.0803, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.44024642272735e-05, | |
| "loss": 1.2599, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.43604768675908e-05, | |
| "loss": 1.2711, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.431834203057471e-05, | |
| "loss": 1.2072, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.427605985630339e-05, | |
| "loss": 1.2504, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.423363048534482e-05, | |
| "loss": 1.366, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.419105405875631e-05, | |
| "loss": 1.335, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.414833071808411e-05, | |
| "loss": 0.9171, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.410546060536285e-05, | |
| "loss": 0.9289, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.406244386311511e-05, | |
| "loss": 1.2373, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.401928063435096e-05, | |
| "loss": 1.231, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.397597106256744e-05, | |
| "loss": 1.1774, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.393251529174815e-05, | |
| "loss": 1.1562, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.388891346636268e-05, | |
| "loss": 1.2252, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.384516573136626e-05, | |
| "loss": 1.151, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.380127223219908e-05, | |
| "loss": 1.0452, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.375723311478606e-05, | |
| "loss": 1.3582, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.371304852553614e-05, | |
| "loss": 1.2245, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.36687186113419e-05, | |
| "loss": 1.1152, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.362424351957909e-05, | |
| "loss": 1.5204, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.357962339810608e-05, | |
| "loss": 1.2947, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.353485839526337e-05, | |
| "loss": 1.1592, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.348994865987319e-05, | |
| "loss": 1.2963, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.344489434123887e-05, | |
| "loss": 1.2709, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.339969558914443e-05, | |
| "loss": 1.2915, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.335435255385407e-05, | |
| "loss": 1.0188, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.330886538611168e-05, | |
| "loss": 1.2702, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.326323423714027e-05, | |
| "loss": 0.9531, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.321745925864157e-05, | |
| "loss": 1.1594, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.317154060279545e-05, | |
| "loss": 1.112, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.312547842225945e-05, | |
| "loss": 1.3651, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.307927287016823e-05, | |
| "loss": 1.2503, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.303292410013314e-05, | |
| "loss": 1.1272, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.298643226624162e-05, | |
| "loss": 1.105, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.293979752305674e-05, | |
| "loss": 1.191, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.28930200256167e-05, | |
| "loss": 1.4381, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.284609992943423e-05, | |
| "loss": 1.2571, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.279903739049622e-05, | |
| "loss": 0.9782, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.275183256526304e-05, | |
| "loss": 1.0205, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.270448561066812e-05, | |
| "loss": 1.2248, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.26569966841174e-05, | |
| "loss": 1.3196, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.260936594348882e-05, | |
| "loss": 1.1606, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.256159354713177e-05, | |
| "loss": 1.3015, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.251367965386657e-05, | |
| "loss": 1.1851, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.246562442298396e-05, | |
| "loss": 1.2675, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.241742801424458e-05, | |
| "loss": 1.2338, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.236909058787837e-05, | |
| "loss": 1.0725, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.232061230458415e-05, | |
| "loss": 1.1511, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.227199332552897e-05, | |
| "loss": 1.169, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.222323381234763e-05, | |
| "loss": 1.1732, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.217433392714217e-05, | |
| "loss": 1.3209, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.212529383248127e-05, | |
| "loss": 1.2429, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.207611369139976e-05, | |
| "loss": 1.1698, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.202679366739805e-05, | |
| "loss": 1.147, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.197733392444158e-05, | |
| "loss": 1.3747, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.192773462696031e-05, | |
| "loss": 1.3735, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.187799593984814e-05, | |
| "loss": 1.1444, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.182811802846236e-05, | |
| "loss": 1.4551, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.177810105862317e-05, | |
| "loss": 1.1338, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.172794519661298e-05, | |
| "loss": 0.9286, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.167765060917604e-05, | |
| "loss": 1.13, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.162721746351774e-05, | |
| "loss": 1.244, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.157664592730415e-05, | |
| "loss": 1.1904, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.152593616866137e-05, | |
| "loss": 1.1416, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.147508835617507e-05, | |
| "loss": 1.034, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.142410265888986e-05, | |
| "loss": 1.1931, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.137297924630876e-05, | |
| "loss": 1.4585, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.132171828839265e-05, | |
| "loss": 1.3864, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.127031995555962e-05, | |
| "loss": 1.2767, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.12187844186845e-05, | |
| "loss": 1.2892, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.116711184909829e-05, | |
| "loss": 1.3043, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.111530241858752e-05, | |
| "loss": 1.4871, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.106335629939372e-05, | |
| "loss": 1.3069, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.101127366421285e-05, | |
| "loss": 1.374, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.095905468619472e-05, | |
| "loss": 1.4679, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.090669953894242e-05, | |
| "loss": 1.3099, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.085420839651171e-05, | |
| "loss": 0.9329, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.080158143341052e-05, | |
| "loss": 1.2446, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.074881882459829e-05, | |
| "loss": 1.2754, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.069592074548539e-05, | |
| "loss": 1.3945, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.064288737193261e-05, | |
| "loss": 0.94, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.058971888025052e-05, | |
| "loss": 1.4074, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.053641544719885e-05, | |
| "loss": 1.2893, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.0482977249986e-05, | |
| "loss": 1.5227, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.042940446626838e-05, | |
| "loss": 1.1112, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.037569727414982e-05, | |
| "loss": 1.159, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.0321855852181e-05, | |
| "loss": 1.2672, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.026788037935887e-05, | |
| "loss": 1.3641, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.021377103512602e-05, | |
| "loss": 1.2538, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.015952799937006e-05, | |
| "loss": 1.1996, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.010515145242313e-05, | |
| "loss": 1.1443, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.00506415750612e-05, | |
| "loss": 1.0743, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.999599854850348e-05, | |
| "loss": 1.2867, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.994122255441187e-05, | |
| "loss": 1.1508, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.988631377489029e-05, | |
| "loss": 0.9629, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.983127239248414e-05, | |
| "loss": 0.9616, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.977609859017964e-05, | |
| "loss": 1.1318, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.972079255140326e-05, | |
| "loss": 1.2026, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.966535446002108e-05, | |
| "loss": 1.3242, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.96097845003382e-05, | |
| "loss": 1.3938, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.95540828570981e-05, | |
| "loss": 1.1968, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.949824971548206e-05, | |
| "loss": 1.2053, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.944228526110853e-05, | |
| "loss": 1.1864, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.938618968003252e-05, | |
| "loss": 1.1069, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.932996315874494e-05, | |
| "loss": 1.1645, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.927360588417207e-05, | |
| "loss": 1.2939, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.921711804367481e-05, | |
| "loss": 1.2385, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.916049982504818e-05, | |
| "loss": 1.0396, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.910375141652064e-05, | |
| "loss": 1.2254, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.904687300675348e-05, | |
| "loss": 1.0961, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.898986478484013e-05, | |
| "loss": 1.2456, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.893272694030562e-05, | |
| "loss": 1.1735, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.887545966310594e-05, | |
| "loss": 1.4055, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.88180631436273e-05, | |
| "loss": 0.8493, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.876053757268568e-05, | |
| "loss": 1.3657, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.870288314152602e-05, | |
| "loss": 1.3016, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.864510004182167e-05, | |
| "loss": 1.3746, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.858718846567378e-05, | |
| "loss": 1.0269, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.852914860561058e-05, | |
| "loss": 1.3918, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.847098065458683e-05, | |
| "loss": 1.1872, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.841268480598306e-05, | |
| "loss": 1.1086, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.835426125360504e-05, | |
| "loss": 1.3269, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.829571019168313e-05, | |
| "loss": 1.1969, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.823703181487151e-05, | |
| "loss": 1.3008, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.817822631824771e-05, | |
| "loss": 1.0524, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.811929389731182e-05, | |
| "loss": 1.0839, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.806023474798591e-05, | |
| "loss": 1.2481, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.800104906661333e-05, | |
| "loss": 1.2175, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.794173704995817e-05, | |
| "loss": 1.2142, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.788229889520443e-05, | |
| "loss": 1.2194, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.782273479995551e-05, | |
| "loss": 1.0141, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.776304496223349e-05, | |
| "loss": 1.2398, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.770322958047847e-05, | |
| "loss": 1.0739, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.764328885354796e-05, | |
| "loss": 1.2605, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.758322298071617e-05, | |
| "loss": 1.2878, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.752303216167333e-05, | |
| "loss": 1.2351, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.746271659652506e-05, | |
| "loss": 1.1342, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.740227648579175e-05, | |
| "loss": 0.9648, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.73417120304078e-05, | |
| "loss": 1.2837, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.728102343172102e-05, | |
| "loss": 1.4112, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.72202108914919e-05, | |
| "loss": 1.308, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.715927461189304e-05, | |
| "loss": 1.276, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.709821479550832e-05, | |
| "loss": 0.9097, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.703703164533246e-05, | |
| "loss": 1.3017, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.697572536477004e-05, | |
| "loss": 1.1793, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.69142961576351e-05, | |
| "loss": 1.0274, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.685274422815035e-05, | |
| "loss": 0.9989, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.679106978094646e-05, | |
| "loss": 1.2198, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.672927302106138e-05, | |
| "loss": 1.3074, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.666735415393978e-05, | |
| "loss": 1.3617, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.66053133854322e-05, | |
| "loss": 1.3652, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.654315092179449e-05, | |
| "loss": 1.1059, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.648086696968705e-05, | |
| "loss": 1.2449, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.641846173617416e-05, | |
| "loss": 1.3829, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.635593542872338e-05, | |
| "loss": 1.3094, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.629328825520467e-05, | |
| "loss": 1.4383, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.62305204238899e-05, | |
| "loss": 1.158, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.616763214345205e-05, | |
| "loss": 1.1641, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.61046236229645e-05, | |
| "loss": 1.3722, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.604149507190038e-05, | |
| "loss": 1.1437, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.597824670013193e-05, | |
| "loss": 1.4047, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.591487871792963e-05, | |
| "loss": 1.149, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.58513913359617e-05, | |
| "loss": 1.0646, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.578778476529326e-05, | |
| "loss": 1.1806, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.572405921738567e-05, | |
| "loss": 1.1038, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.566021490409586e-05, | |
| "loss": 1.2863, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.559625203767559e-05, | |
| "loss": 1.3052, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.553217083077075e-05, | |
| "loss": 1.1362, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.546797149642062e-05, | |
| "loss": 1.4099, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.540365424805727e-05, | |
| "loss": 1.1942, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.533921929950472e-05, | |
| "loss": 1.174, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.527466686497831e-05, | |
| "loss": 1.137, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.520999715908396e-05, | |
| "loss": 1.2968, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.514521039681744e-05, | |
| "loss": 1.475, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.508030679356373e-05, | |
| "loss": 1.3125, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.501528656509618e-05, | |
| "loss": 1.3202, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.495014992757595e-05, | |
| "loss": 1.3215, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.48848970975511e-05, | |
| "loss": 1.1636, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.481952829195605e-05, | |
| "loss": 1.3107, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.475404372811078e-05, | |
| "loss": 1.0467, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.468844362372006e-05, | |
| "loss": 0.9995, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.462272819687283e-05, | |
| "loss": 0.9843, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.455689766604139e-05, | |
| "loss": 1.0997, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.449095225008072e-05, | |
| "loss": 1.3293, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.442489216822777e-05, | |
| "loss": 1.2984, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.435871764010059e-05, | |
| "loss": 1.2803, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.429242888569786e-05, | |
| "loss": 1.0006, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.422602612539788e-05, | |
| "loss": 1.2775, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.415950957995803e-05, | |
| "loss": 1.2761, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.409287947051397e-05, | |
| "loss": 1.0964, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.402613601857887e-05, | |
| "loss": 1.3977, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.395927944604276e-05, | |
| "loss": 1.137, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.389230997517167e-05, | |
| "loss": 1.2955, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.382522782860707e-05, | |
| "loss": 1.2196, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.37580332293649e-05, | |
| "loss": 1.0837, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.369072640083504e-05, | |
| "loss": 1.0474, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.362330756678046e-05, | |
| "loss": 1.2218, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.355577695133645e-05, | |
| "loss": 1.3201, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.348813477900999e-05, | |
| "loss": 1.4093, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.342038127467886e-05, | |
| "loss": 1.2219, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.335251666359106e-05, | |
| "loss": 1.0485, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.328454117136382e-05, | |
| "loss": 1.1785, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.321645502398317e-05, | |
| "loss": 1.3, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.31482584478029e-05, | |
| "loss": 1.1686, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.307995166954395e-05, | |
| "loss": 1.1267, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.301153491629363e-05, | |
| "loss": 1.063, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.294300841550486e-05, | |
| "loss": 1.1755, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.287437239499548e-05, | |
| "loss": 1.0905, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.28056270829473e-05, | |
| "loss": 1.369, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.27367727079056e-05, | |
| "loss": 1.3327, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.266780949877818e-05, | |
| "loss": 1.085, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.259873768483464e-05, | |
| "loss": 1.3786, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.252955749570572e-05, | |
| "loss": 1.2915, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.246026916138237e-05, | |
| "loss": 1.1354, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.239087291221513e-05, | |
| "loss": 1.1055, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.232136897891327e-05, | |
| "loss": 1.3266, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.225175759254406e-05, | |
| "loss": 1.1572, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.218203898453203e-05, | |
| "loss": 1.2385, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.211221338665813e-05, | |
| "loss": 1.2913, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.204228103105906e-05, | |
| "loss": 1.1688, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.197224215022634e-05, | |
| "loss": 1.1315, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.190209697700575e-05, | |
| "loss": 1.4308, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.183184574459635e-05, | |
| "loss": 1.1688, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.176148868654986e-05, | |
| "loss": 1.184, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.169102603676977e-05, | |
| "loss": 1.2145, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.162045802951064e-05, | |
| "loss": 1.2645, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.154978489937728e-05, | |
| "loss": 1.2871, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.1479006881324e-05, | |
| "loss": 1.3045, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.14081242106538e-05, | |
| "loss": 1.3655, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.13371371230176e-05, | |
| "loss": 1.3607, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.126604585441344e-05, | |
| "loss": 1.1406, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.119485064118577e-05, | |
| "loss": 1.2151, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.112355172002453e-05, | |
| "loss": 1.09, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.105214932796447e-05, | |
| "loss": 1.2609, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.098064370238438e-05, | |
| "loss": 1.466, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.090903508100618e-05, | |
| "loss": 1.1498, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.083732370189421e-05, | |
| "loss": 1.2825, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.07655098034545e-05, | |
| "loss": 1.3832, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.069359362443381e-05, | |
| "loss": 1.0951, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.0621575403919e-05, | |
| "loss": 1.2812, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.054945538133616e-05, | |
| "loss": 1.0743, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.04772337964498e-05, | |
| "loss": 1.1008, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 8.040491088936208e-05, | |
| "loss": 1.2507, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 8.033248690051206e-05, | |
| "loss": 1.2828, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 8.025996207067477e-05, | |
| "loss": 1.2943, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 8.018733664096053e-05, | |
| "loss": 1.3268, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 8.01146108528141e-05, | |
| "loss": 1.1281, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 8.004178494801388e-05, | |
| "loss": 1.0686, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.996885916867115e-05, | |
| "loss": 1.0461, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.989583375722913e-05, | |
| "loss": 1.4064, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.98227089564624e-05, | |
| "loss": 1.1746, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.974948500947582e-05, | |
| "loss": 1.2857, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.967616215970395e-05, | |
| "loss": 1.1761, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.960274065091015e-05, | |
| "loss": 1.3091, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.952922072718579e-05, | |
| "loss": 1.2446, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.945560263294935e-05, | |
| "loss": 1.4189, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.938188661294574e-05, | |
| "loss": 0.8042, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.930807291224541e-05, | |
| "loss": 1.2675, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.923416177624356e-05, | |
| "loss": 1.4177, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.91601534506593e-05, | |
| "loss": 1.1725, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.908604818153486e-05, | |
| "loss": 1.2327, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.901184621523475e-05, | |
| "loss": 1.3717, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.893754779844497e-05, | |
| "loss": 1.5799, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.886315317817214e-05, | |
| "loss": 1.3008, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.886315317817214e-05, | |
| "loss": 1.333, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.878866260174278e-05, | |
| "loss": 1.2296, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.871407631680232e-05, | |
| "loss": 1.2223, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.863939457131443e-05, | |
| "loss": 1.1686, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.856461761356015e-05, | |
| "loss": 1.2449, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.848974569213705e-05, | |
| "loss": 1.2279, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.841477905595839e-05, | |
| "loss": 1.2712, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.833971795425231e-05, | |
| "loss": 1.0918, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.8264562636561e-05, | |
| "loss": 1.2084, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.818931335273993e-05, | |
| "loss": 1.3312, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.811397035295688e-05, | |
| "loss": 1.2071, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.803853388769127e-05, | |
| "loss": 1.3825, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.796300420773315e-05, | |
| "loss": 1.0597, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.788738156418256e-05, | |
| "loss": 1.1342, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.781166620844855e-05, | |
| "loss": 1.1296, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.773585839224841e-05, | |
| "loss": 1.1714, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.765995836760681e-05, | |
| "loss": 1.1898, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.758396638685496e-05, | |
| "loss": 1.3164, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.75078827026298e-05, | |
| "loss": 1.1351, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.743170756787312e-05, | |
| "loss": 1.1505, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.735544123583076e-05, | |
| "loss": 1.3683, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.727908396005172e-05, | |
| "loss": 1.2137, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.720263599438737e-05, | |
| "loss": 1.4369, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.71260975929906e-05, | |
| "loss": 1.2565, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.704946901031488e-05, | |
| "loss": 1.3778, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.697275050111356e-05, | |
| "loss": 1.1218, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.689594232043893e-05, | |
| "loss": 0.9591, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.681904472364136e-05, | |
| "loss": 1.1062, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.674205796636858e-05, | |
| "loss": 1.1178, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.666498230456463e-05, | |
| "loss": 1.2184, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.658781799446919e-05, | |
| "loss": 1.2851, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.65105652926166e-05, | |
| "loss": 1.4507, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.643322445583507e-05, | |
| "loss": 1.1688, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.635579574124586e-05, | |
| "loss": 1.1526, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.627827940626233e-05, | |
| "loss": 1.3492, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.62006757085892e-05, | |
| "loss": 1.1999, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.612298490622154e-05, | |
| "loss": 1.1812, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.604520725744404e-05, | |
| "loss": 1.2115, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.596734302083016e-05, | |
| "loss": 0.8849, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.588939245524119e-05, | |
| "loss": 1.0837, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.581135581982534e-05, | |
| "loss": 1.1529, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.573323337401712e-05, | |
| "loss": 1.1747, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.565502537753622e-05, | |
| "loss": 1.219, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.557673209038672e-05, | |
| "loss": 1.1351, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.549835377285632e-05, | |
| "loss": 1.1187, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.541989068551538e-05, | |
| "loss": 1.3856, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.534134308921606e-05, | |
| "loss": 1.2495, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.52627112450915e-05, | |
| "loss": 1.2021, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.51839954145549e-05, | |
| "loss": 1.2281, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.510519585929869e-05, | |
| "loss": 1.2627, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.502631284129365e-05, | |
| "loss": 1.2729, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.494734662278803e-05, | |
| "loss": 1.3051, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.486829746630663e-05, | |
| "loss": 0.999, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.478916563465007e-05, | |
| "loss": 1.294, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.470995139089377e-05, | |
| "loss": 1.2407, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.463065499838711e-05, | |
| "loss": 1.1426, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.455127672075266e-05, | |
| "loss": 1.407, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.447181682188511e-05, | |
| "loss": 1.2811, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.43922755659506e-05, | |
| "loss": 0.9844, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.431265321738566e-05, | |
| "loss": 1.168, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.42329500408965e-05, | |
| "loss": 1.2511, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.415316630145796e-05, | |
| "loss": 1.2908, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.407330226431276e-05, | |
| "loss": 1.0027, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.399335819497057e-05, | |
| "loss": 1.1104, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.39133343592071e-05, | |
| "loss": 1.1626, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.38332310230633e-05, | |
| "loss": 1.1255, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.375304845284438e-05, | |
| "loss": 1.1745, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.367278691511895e-05, | |
| "loss": 1.0799, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.359244667671818e-05, | |
| "loss": 1.2972, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.351202800473487e-05, | |
| "loss": 1.2253, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.343153116652257e-05, | |
| "loss": 1.115, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.335095642969474e-05, | |
| "loss": 1.2523, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.327030406212374e-05, | |
| "loss": 1.2458, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.318957433194009e-05, | |
| "loss": 1.312, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.310876750753141e-05, | |
| "loss": 1.2535, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.302788385754174e-05, | |
| "loss": 1.1227, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.294692365087042e-05, | |
| "loss": 1.1932, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.286588715667137e-05, | |
| "loss": 1.1414, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.278477464435212e-05, | |
| "loss": 1.3467, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.270358638357291e-05, | |
| "loss": 1.1323, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.262232264424579e-05, | |
| "loss": 1.3177, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.254098369653377e-05, | |
| "loss": 1.1928, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.245956981084992e-05, | |
| "loss": 1.0264, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.237808125785635e-05, | |
| "loss": 1.1941, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.22965183084635e-05, | |
| "loss": 1.0098, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.221488123382907e-05, | |
| "loss": 0.9925, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.213317030535724e-05, | |
| "loss": 1.238, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.205138579469772e-05, | |
| "loss": 1.4423, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.19695279737448e-05, | |
| "loss": 1.1988, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.188759711463653e-05, | |
| "loss": 1.3415, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.180559348975376e-05, | |
| "loss": 1.2357, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.172351737171923e-05, | |
| "loss": 1.2059, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.164136903339675e-05, | |
| "loss": 1.1749, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.15591487478902e-05, | |
| "loss": 1.1634, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.14768567885426e-05, | |
| "loss": 1.3124, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.139449342893531e-05, | |
| "loss": 1.2205, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.131205894288704e-05, | |
| "loss": 1.1267, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.122955360445296e-05, | |
| "loss": 1.3008, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.114697768792378e-05, | |
| "loss": 1.3424, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.106433146782492e-05, | |
| "loss": 1.299, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.09816152189154e-05, | |
| "loss": 1.2755, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.089882921618714e-05, | |
| "loss": 1.2192, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.081597373486395e-05, | |
| "loss": 1.123, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.073304905040061e-05, | |
| "loss": 1.2551, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.065005543848197e-05, | |
| "loss": 1.4018, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.0566993175022e-05, | |
| "loss": 1.0449, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.048386253616297e-05, | |
| "loss": 1.1892, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.040066379827441e-05, | |
| "loss": 1.2919, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.031739723795227e-05, | |
| "loss": 1.0878, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.023406313201797e-05, | |
| "loss": 1.5978, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.01506617575175e-05, | |
| "loss": 1.0435, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.006719339172044e-05, | |
| "loss": 1.2939, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.998365831211913e-05, | |
| "loss": 1.3341, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.990005679642773e-05, | |
| "loss": 1.2776, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.981638912258119e-05, | |
| "loss": 1.1926, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.973265556873445e-05, | |
| "loss": 1.1579, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.964885641326146e-05, | |
| "loss": 1.2139, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.956499193475425e-05, | |
| "loss": 1.22, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.948106241202206e-05, | |
| "loss": 1.1147, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.939706812409035e-05, | |
| "loss": 1.0886, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.931300935019986e-05, | |
| "loss": 0.9858, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.922888636980575e-05, | |
| "loss": 1.1773, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.914469946257663e-05, | |
| "loss": 1.0702, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.906044890839365e-05, | |
| "loss": 1.0421, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.897613498734952e-05, | |
| "loss": 1.076, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.889175797974764e-05, | |
| "loss": 1.3004, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.880731816610112e-05, | |
| "loss": 1.3847, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.872281582713195e-05, | |
| "loss": 1.0796, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.863825124376984e-05, | |
| "loss": 0.9651, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.855362469715157e-05, | |
| "loss": 1.1469, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.846893646861985e-05, | |
| "loss": 1.2286, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.838418683972245e-05, | |
| "loss": 1.1228, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.829937609221133e-05, | |
| "loss": 1.1105, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.821450450804154e-05, | |
| "loss": 1.082, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.812957236937047e-05, | |
| "loss": 1.1787, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.804457995855679e-05, | |
| "loss": 1.0335, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.795952755815953e-05, | |
| "loss": 1.418, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.787441545093721e-05, | |
| "loss": 1.3354, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.778924391984676e-05, | |
| "loss": 1.3398, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.770401324804276e-05, | |
| "loss": 1.2421, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.761872371887635e-05, | |
| "loss": 1.1488, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.753337561589435e-05, | |
| "loss": 1.0732, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.744796922283832e-05, | |
| "loss": 1.3388, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.736250482364356e-05, | |
| "loss": 1.2863, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.727698270243831e-05, | |
| "loss": 1.1406, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.719140314354262e-05, | |
| "loss": 1.2804, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.710576643146757e-05, | |
| "loss": 1.1616, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.702007285091412e-05, | |
| "loss": 1.3191, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.693432268677244e-05, | |
| "loss": 1.0719, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.68485162241207e-05, | |
| "loss": 1.2268, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.67626537482243e-05, | |
| "loss": 1.073, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.667673554453485e-05, | |
| "loss": 1.3546, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.65907618986892e-05, | |
| "loss": 1.3935, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.650473309650855e-05, | |
| "loss": 1.2897, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.641864942399741e-05, | |
| "loss": 1.107, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.633251116734278e-05, | |
| "loss": 1.1136, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.62463186129131e-05, | |
| "loss": 1.2193, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.616007204725734e-05, | |
| "loss": 1.0417, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.607377175710396e-05, | |
| "loss": 1.4403, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.598741802936013e-05, | |
| "loss": 1.2471, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.590101115111058e-05, | |
| "loss": 1.273, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.581455140961682e-05, | |
| "loss": 1.2479, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.572803909231605e-05, | |
| "loss": 1.3102, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.564147448682028e-05, | |
| "loss": 1.2035, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.555485788091537e-05, | |
| "loss": 1.236, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.546818956256002e-05, | |
| "loss": 1.183, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.538146981988486e-05, | |
| "loss": 1.258, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.529469894119152e-05, | |
| "loss": 1.0608, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.520787721495157e-05, | |
| "loss": 1.3015, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.512100492980567e-05, | |
| "loss": 1.4924, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.503408237456255e-05, | |
| "loss": 1.2852, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.494710983819805e-05, | |
| "loss": 1.2941, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.486008760985423e-05, | |
| "loss": 1.0439, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.477301597883823e-05, | |
| "loss": 0.905, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.468589523462159e-05, | |
| "loss": 1.1491, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.4598725666839e-05, | |
| "loss": 1.1544, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.45115075652875e-05, | |
| "loss": 1.113, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.442424121992555e-05, | |
| "loss": 1.3204, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.433692692087189e-05, | |
| "loss": 1.3703, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.424956495840477e-05, | |
| "loss": 1.219, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.416215562296082e-05, | |
| "loss": 1.1624, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.407469920513423e-05, | |
| "loss": 1.2366, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.398719599567569e-05, | |
| "loss": 1.1827, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.389964628549144e-05, | |
| "loss": 0.9569, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.381205036564235e-05, | |
| "loss": 1.2483, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.372440852734286e-05, | |
| "loss": 1.0956, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.36367210619601e-05, | |
| "loss": 1.3902, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.354898826101288e-05, | |
| "loss": 1.3328, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.346121041617076e-05, | |
| "loss": 1.0272, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.3373387819253e-05, | |
| "loss": 1.1318, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.328552076222764e-05, | |
| "loss": 1.2359, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.31976095372106e-05, | |
| "loss": 1.1629, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.310965443646453e-05, | |
| "loss": 1.4244, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.302165575239804e-05, | |
| "loss": 1.4141, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.293361377756458e-05, | |
| "loss": 1.3342, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.284552880466154e-05, | |
| "loss": 1.2453, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.275740112652929e-05, | |
| "loss": 1.0781, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.266923103615008e-05, | |
| "loss": 1.1899, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.258101882664725e-05, | |
| "loss": 1.2435, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.249276479128415e-05, | |
| "loss": 1.2253, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.240446922346312e-05, | |
| "loss": 1.3321, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.231613241672468e-05, | |
| "loss": 1.28, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.222775466474636e-05, | |
| "loss": 1.3513, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.213933626134185e-05, | |
| "loss": 1.104, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.205087750045997e-05, | |
| "loss": 1.1304, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.196237867618375e-05, | |
| "loss": 1.356, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.187384008272936e-05, | |
| "loss": 1.245, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.178526201444521e-05, | |
| "loss": 1.3331, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.169664476581095e-05, | |
| "loss": 1.227, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.160798863143646e-05, | |
| "loss": 1.3408, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.151929390606094e-05, | |
| "loss": 1.474, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.143056088455183e-05, | |
| "loss": 1.4309, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.134178986190394e-05, | |
| "loss": 1.1121, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.125298113323836e-05, | |
| "loss": 1.4073, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.11641349938016e-05, | |
| "loss": 0.9651, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.10752517389645e-05, | |
| "loss": 1.0073, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.098633166422131e-05, | |
| "loss": 1.3508, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.089737506518867e-05, | |
| "loss": 1.1648, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.080838223760462e-05, | |
| "loss": 1.2285, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.0719353477327736e-05, | |
| "loss": 1.1274, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.063028908033594e-05, | |
| "loss": 0.9918, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.0541189342725725e-05, | |
| "loss": 1.1932, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.045205456071102e-05, | |
| "loss": 1.3955, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.036288503062227e-05, | |
| "loss": 1.0882, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.027368104890544e-05, | |
| "loss": 1.1175, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.018444291212103e-05, | |
| "loss": 1.2404, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.00951709169431e-05, | |
| "loss": 0.9958, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.000586536015827e-05, | |
| "loss": 1.1738, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.991652653866472e-05, | |
| "loss": 1.2169, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.9827154749471235e-05, | |
| "loss": 1.2691, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.9737750289696204e-05, | |
| "loss": 1.3551, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.964831345656663e-05, | |
| "loss": 1.4156, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.9558844547417116e-05, | |
| "loss": 1.2732, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.946934385968892e-05, | |
| "loss": 1.2012, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.937981169092896e-05, | |
| "loss": 0.8553, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.929024833878882e-05, | |
| "loss": 1.315, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.9200654101023734e-05, | |
| "loss": 1.2734, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.91110292754916e-05, | |
| "loss": 1.0681, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.902137416015204e-05, | |
| "loss": 1.3215, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.8931689053065354e-05, | |
| "loss": 1.3002, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.884197425239154e-05, | |
| "loss": 1.0457, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.875223005638937e-05, | |
| "loss": 1.2968, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.8662456763415273e-05, | |
| "loss": 1.1312, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.8572654671922455e-05, | |
| "loss": 1.1457, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.848282408045983e-05, | |
| "loss": 1.2871, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.839296528767108e-05, | |
| "loss": 1.1148, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.830307859229366e-05, | |
| "loss": 1.056, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.821316429315775e-05, | |
| "loss": 1.2034, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.812322268918534e-05, | |
| "loss": 1.3442, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.803325407938915e-05, | |
| "loss": 1.1675, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.794325876287172e-05, | |
| "loss": 1.3523, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.785323703882435e-05, | |
| "loss": 1.1103, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.776318920652616e-05, | |
| "loss": 1.1762, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.767311556534305e-05, | |
| "loss": 1.0724, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.758301641472672e-05, | |
| "loss": 1.1906, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.749289205421368e-05, | |
| "loss": 1.1472, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.7402742783424236e-05, | |
| "loss": 1.2873, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.731256890206157e-05, | |
| "loss": 1.1637, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.7222370709910586e-05, | |
| "loss": 1.0984, | |
| "step": 983 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.7132148506837105e-05, | |
| "loss": 0.9113, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.70419025927867e-05, | |
| "loss": 1.1948, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.695163326778379e-05, | |
| "loss": 1.2219, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.6861340831930675e-05, | |
| "loss": 1.5302, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.677102558540641e-05, | |
| "loss": 1.2566, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.6680687828465936e-05, | |
| "loss": 1.3525, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.659032786143903e-05, | |
| "loss": 1.094, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.6499945984729267e-05, | |
| "loss": 1.2439, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.640954249881309e-05, | |
| "loss": 1.3596, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.63191177042388e-05, | |
| "loss": 1.2205, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.622867190162551e-05, | |
| "loss": 1.2724, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.613820539166216e-05, | |
| "loss": 1.2892, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.604771847510658e-05, | |
| "loss": 1.2164, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.5957211452784407e-05, | |
| "loss": 1.0882, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.586668462558814e-05, | |
| "loss": 1.2512, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.5776138294476114e-05, | |
| "loss": 1.3113, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.568557276047147e-05, | |
| "loss": 1.229, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.559498832466124e-05, | |
| "loss": 1.2745, | |
| "step": 1001 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.550438528819529e-05, | |
| "loss": 1.1249, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.541376395228529e-05, | |
| "loss": 1.4018, | |
| "step": 1003 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.532312461820378e-05, | |
| "loss": 1.1, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.523246758728311e-05, | |
| "loss": 1.0846, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.5141793160914503e-05, | |
| "loss": 1.2021, | |
| "step": 1006 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.505110164054692e-05, | |
| "loss": 1.1134, | |
| "step": 1007 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.49603933276863e-05, | |
| "loss": 1.1655, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.486966852389428e-05, | |
| "loss": 1.1094, | |
| "step": 1009 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.4778927530787374e-05, | |
| "loss": 1.3497, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.468817065003593e-05, | |
| "loss": 1.3793, | |
| "step": 1011 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.459739818336307e-05, | |
| "loss": 1.2663, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.450661043254377e-05, | |
| "loss": 0.9848, | |
| "step": 1013 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.4415807699403806e-05, | |
| "loss": 0.9374, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.432499028581878e-05, | |
| "loss": 1.2192, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.4234158493713064e-05, | |
| "loss": 1.1517, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.414331262505885e-05, | |
| "loss": 0.9754, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.405245298187514e-05, | |
| "loss": 1.2599, | |
| "step": 1018 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.3961579866226705e-05, | |
| "loss": 1.342, | |
| "step": 1019 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.387069358022314e-05, | |
| "loss": 1.0915, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.3779794426017796e-05, | |
| "loss": 1.0447, | |
| "step": 1021 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.368888270580679e-05, | |
| "loss": 1.1727, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.359795872182807e-05, | |
| "loss": 1.4081, | |
| "step": 1023 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.3507022776360294e-05, | |
| "loss": 1.2752, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.341607517172196e-05, | |
| "loss": 1.4003, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.332511621027023e-05, | |
| "loss": 1.5025, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.3234146194400104e-05, | |
| "loss": 1.0317, | |
| "step": 1027 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.314316542654328e-05, | |
| "loss": 1.2976, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.305217420916726e-05, | |
| "loss": 1.0828, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.296117284477423e-05, | |
| "loss": 1.1612, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.287016163590012e-05, | |
| "loss": 1.1667, | |
| "step": 1031 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.277914088511362e-05, | |
| "loss": 1.3622, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.2688110895015096e-05, | |
| "loss": 1.2583, | |
| "step": 1033 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.259707196823564e-05, | |
| "loss": 1.077, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.250602440743614e-05, | |
| "loss": 1.0585, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.241496851530605e-05, | |
| "loss": 1.2527, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.232390459456262e-05, | |
| "loss": 1.2744, | |
| "step": 1037 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.223283294794974e-05, | |
| "loss": 1.2888, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.214175387823701e-05, | |
| "loss": 1.2656, | |
| "step": 1039 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.205066768821871e-05, | |
| "loss": 1.4323, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.1959574680712775e-05, | |
| "loss": 1.3173, | |
| "step": 1041 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.1868475158559836e-05, | |
| "loss": 0.9765, | |
| "step": 1042 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.1777369424622135e-05, | |
| "loss": 1.2085, | |
| "step": 1043 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.168625778178259e-05, | |
| "loss": 1.1058, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.159514053294378e-05, | |
| "loss": 1.1363, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.15040179810269e-05, | |
| "loss": 1.3826, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.141289042897077e-05, | |
| "loss": 0.9896, | |
| "step": 1047 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.132175817973086e-05, | |
| "loss": 1.3667, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.1230621536278224e-05, | |
| "loss": 1.2513, | |
| "step": 1049 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.113948080159854e-05, | |
| "loss": 1.2384, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.104833627869111e-05, | |
| "loss": 1.3229, | |
| "step": 1051 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.0957188270567776e-05, | |
| "loss": 0.9799, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.086603708025201e-05, | |
| "loss": 1.141, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.077488301077787e-05, | |
| "loss": 1.4041, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.068372636518893e-05, | |
| "loss": 1.0402, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.059256744653741e-05, | |
| "loss": 1.2024, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.050140655788299e-05, | |
| "loss": 1.2475, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.0410244002292004e-05, | |
| "loss": 1.2159, | |
| "step": 1058 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.0319080082836234e-05, | |
| "loss": 1.1485, | |
| "step": 1059 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.022791510259206e-05, | |
| "loss": 1.0548, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.013674936463935e-05, | |
| "loss": 1.2628, | |
| "step": 1061 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.0045583172060514e-05, | |
| "loss": 1.2038, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.995441682793949e-05, | |
| "loss": 1.3627, | |
| "step": 1063 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.986325063536067e-05, | |
| "loss": 1.2064, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.9772084897407955e-05, | |
| "loss": 1.2028, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.968091991716378e-05, | |
| "loss": 1.3858, | |
| "step": 1066 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.9589755997708014e-05, | |
| "loss": 1.1065, | |
| "step": 1067 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.9498593442117e-05, | |
| "loss": 1.0755, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.940743255346261e-05, | |
| "loss": 1.3851, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.931627363481108e-05, | |
| "loss": 1.2311, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.922511698922215e-05, | |
| "loss": 1.2331, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.9133962919747985e-05, | |
| "loss": 1.1331, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.904281172943223e-05, | |
| "loss": 1.203, | |
| "step": 1073 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.895166372130891e-05, | |
| "loss": 1.2504, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.886051919840146e-05, | |
| "loss": 1.2005, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.876937846372179e-05, | |
| "loss": 0.8887, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.8678241820269155e-05, | |
| "loss": 1.067, | |
| "step": 1077 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.8587109571029246e-05, | |
| "loss": 1.1751, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.8495982018973106e-05, | |
| "loss": 1.0429, | |
| "step": 1079 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.840485946705623e-05, | |
| "loss": 1.2141, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.8313742218217425e-05, | |
| "loss": 1.0819, | |
| "step": 1081 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.822263057537787e-05, | |
| "loss": 1.211, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.8131524841440176e-05, | |
| "loss": 0.9122, | |
| "step": 1083 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.804042531928723e-05, | |
| "loss": 1.1623, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.7949332311781294e-05, | |
| "loss": 1.2037, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.7858246121763e-05, | |
| "loss": 1.3522, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.776716705205027e-05, | |
| "loss": 1.2074, | |
| "step": 1087 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.76760954054374e-05, | |
| "loss": 1.126, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.758503148469395e-05, | |
| "loss": 1.1957, | |
| "step": 1089 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.7493975592563875e-05, | |
| "loss": 1.2672, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.740292803176436e-05, | |
| "loss": 1.1742, | |
| "step": 1091 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.7311889104984916e-05, | |
| "loss": 1.0278, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.7220859114886394e-05, | |
| "loss": 1.2994, | |
| "step": 1093 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.712983836409989e-05, | |
| "loss": 1.2597, | |
| "step": 1094 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.7038827155225796e-05, | |
| "loss": 1.2351, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.6947825790832745e-05, | |
| "loss": 1.1062, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.685683457345672e-05, | |
| "loss": 1.0231, | |
| "step": 1097 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.6765853805599914e-05, | |
| "loss": 1.3052, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.6674883789729775e-05, | |
| "loss": 1.284, | |
| "step": 1099 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.658392482827806e-05, | |
| "loss": 1.241, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.649297722363971e-05, | |
| "loss": 1.4075, | |
| "step": 1101 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.640204127817195e-05, | |
| "loss": 1.0153, | |
| "step": 1102 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.6311117294193216e-05, | |
| "loss": 1.311, | |
| "step": 1103 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.622020557398222e-05, | |
| "loss": 1.2149, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.612930641977688e-05, | |
| "loss": 1.2351, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.60384201337733e-05, | |
| "loss": 1.2453, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.5947547018124874e-05, | |
| "loss": 1.099, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.585668737494116e-05, | |
| "loss": 1.3147, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.576584150628696e-05, | |
| "loss": 1.3119, | |
| "step": 1109 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.567500971418123e-05, | |
| "loss": 1.2774, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.55841923005962e-05, | |
| "loss": 1.0127, | |
| "step": 1111 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.549338956745625e-05, | |
| "loss": 1.3091, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.540260181663694e-05, | |
| "loss": 1.1621, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.531182934996408e-05, | |
| "loss": 1.1383, | |
| "step": 1114 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.522107246921263e-05, | |
| "loss": 1.2495, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.513033147610574e-05, | |
| "loss": 1.0042, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.5039606672313704e-05, | |
| "loss": 1.2262, | |
| "step": 1117 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.494889835945308e-05, | |
| "loss": 1.1954, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.485820683908553e-05, | |
| "loss": 1.3371, | |
| "step": 1119 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.476753241271689e-05, | |
| "loss": 1.2371, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.467687538179623e-05, | |
| "loss": 1.1821, | |
| "step": 1121 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.458623604771472e-05, | |
| "loss": 1.1586, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.449561471180472e-05, | |
| "loss": 1.0946, | |
| "step": 1123 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.440501167533876e-05, | |
| "loss": 1.2704, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.431442723952854e-05, | |
| "loss": 1.3291, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.422386170552392e-05, | |
| "loss": 1.3034, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.413331537441186e-05, | |
| "loss": 1.2161, | |
| "step": 1127 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.4042788547215605e-05, | |
| "loss": 1.1876, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.3952281524893426e-05, | |
| "loss": 1.3105, | |
| "step": 1129 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.3861794608337854e-05, | |
| "loss": 1.0672, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.377132809837451e-05, | |
| "loss": 1.1523, | |
| "step": 1131 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.368088229576122e-05, | |
| "loss": 0.9571, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.359045750118693e-05, | |
| "loss": 1.0446, | |
| "step": 1133 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.3500054015270745e-05, | |
| "loss": 1.2725, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.340967213856098e-05, | |
| "loss": 1.4426, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.3319312171534075e-05, | |
| "loss": 1.2784, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.3228974414593596e-05, | |
| "loss": 1.375, | |
| "step": 1137 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.3138659168069337e-05, | |
| "loss": 0.9357, | |
| "step": 1138 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.304836673221622e-05, | |
| "loss": 1.2066, | |
| "step": 1139 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.295809740721332e-05, | |
| "loss": 1.4191, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.28678514931629e-05, | |
| "loss": 1.1511, | |
| "step": 1141 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.277762929008942e-05, | |
| "loss": 1.1777, | |
| "step": 1142 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.2687431097938454e-05, | |
| "loss": 1.0865, | |
| "step": 1143 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.2597257216575756e-05, | |
| "loss": 1.0529, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.250710794578634e-05, | |
| "loss": 0.9454, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.2416983585273296e-05, | |
| "loss": 1.2136, | |
| "step": 1146 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.232688443465697e-05, | |
| "loss": 1.149, | |
| "step": 1147 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.2236810793473844e-05, | |
| "loss": 1.2721, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.214676296117566e-05, | |
| "loss": 1.3382, | |
| "step": 1149 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.2056741237128295e-05, | |
| "loss": 1.2635, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.196674592061086e-05, | |
| "loss": 1.1043, | |
| "step": 1151 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.187677731081468e-05, | |
| "loss": 1.0379, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.178683570684226e-05, | |
| "loss": 1.2013, | |
| "step": 1153 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.169692140770636e-05, | |
| "loss": 1.0428, | |
| "step": 1154 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.160703471232893e-05, | |
| "loss": 1.2311, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.151717591954019e-05, | |
| "loss": 1.2851, | |
| "step": 1156 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.1427345328077564e-05, | |
| "loss": 0.9672, | |
| "step": 1157 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.1337543236584725e-05, | |
| "loss": 1.3405, | |
| "step": 1158 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.124776994361064e-05, | |
| "loss": 1.2669, | |
| "step": 1159 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.115802574760847e-05, | |
| "loss": 1.2971, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.106831094693467e-05, | |
| "loss": 1.2095, | |
| "step": 1161 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.097862583984797e-05, | |
| "loss": 1.282, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.088897072450841e-05, | |
| "loss": 1.0068, | |
| "step": 1163 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.0799345898976285e-05, | |
| "loss": 1.2247, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.070975166121117e-05, | |
| "loss": 1.368, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.062018830907104e-05, | |
| "loss": 1.1987, | |
| "step": 1166 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.053065614031109e-05, | |
| "loss": 1.2158, | |
| "step": 1167 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.0441155452582916e-05, | |
| "loss": 1.4295, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.0351686543433385e-05, | |
| "loss": 1.1489, | |
| "step": 1169 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.026224971030381e-05, | |
| "loss": 1.4325, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.017284525052877e-05, | |
| "loss": 1.3098, | |
| "step": 1171 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.008347346133529e-05, | |
| "loss": 1.2097, | |
| "step": 1172 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.999413463984174e-05, | |
| "loss": 1.2226, | |
| "step": 1173 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.990482908305692e-05, | |
| "loss": 1.0856, | |
| "step": 1174 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.981555708787897e-05, | |
| "loss": 1.0226, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.972631895109458e-05, | |
| "loss": 1.1042, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.963711496937774e-05, | |
| "loss": 1.0424, | |
| "step": 1177 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.954794543928899e-05, | |
| "loss": 1.242, | |
| "step": 1178 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.945881065727427e-05, | |
| "loss": 0.8678, | |
| "step": 1179 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.936971091966406e-05, | |
| "loss": 0.9766, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.9280646522672296e-05, | |
| "loss": 0.9824, | |
| "step": 1181 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.919161776239538e-05, | |
| "loss": 0.8786, | |
| "step": 1182 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.910262493481135e-05, | |
| "loss": 1.3209, | |
| "step": 1183 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.90136683357787e-05, | |
| "loss": 1.1778, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.892474826103551e-05, | |
| "loss": 1.1158, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.8835865006198394e-05, | |
| "loss": 1.2111, | |
| "step": 1186 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.8747018866761655e-05, | |
| "loss": 1.2069, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.865821013809609e-05, | |
| "loss": 1.2878, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.8569439115448175e-05, | |
| "loss": 1.2627, | |
| "step": 1189 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.848070609393907e-05, | |
| "loss": 1.2609, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.839201136856355e-05, | |
| "loss": 1.1303, | |
| "step": 1191 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.8303355234189065e-05, | |
| "loss": 1.1948, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.82147379855548e-05, | |
| "loss": 1.4789, | |
| "step": 1193 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.812615991727065e-05, | |
| "loss": 1.1536, | |
| "step": 1194 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.8037621323816265e-05, | |
| "loss": 1.1729, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.7949122499540024e-05, | |
| "loss": 0.988, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.7860663738658165e-05, | |
| "loss": 1.3364, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.777224533525365e-05, | |
| "loss": 1.2749, | |
| "step": 1198 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.7683867583275334e-05, | |
| "loss": 1.2638, | |
| "step": 1199 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.759553077653687e-05, | |
| "loss": 1.1076, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.750723520871587e-05, | |
| "loss": 1.071, | |
| "step": 1201 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.741898117335277e-05, | |
| "loss": 1.3803, | |
| "step": 1202 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.733076896384993e-05, | |
| "loss": 1.2528, | |
| "step": 1203 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.7242598873470725e-05, | |
| "loss": 1.278, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.715447119533846e-05, | |
| "loss": 1.0355, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.7066386222435436e-05, | |
| "loss": 1.1408, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.697834424760197e-05, | |
| "loss": 1.2431, | |
| "step": 1207 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.689034556353549e-05, | |
| "loss": 1.0098, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.6802390462789425e-05, | |
| "loss": 1.1916, | |
| "step": 1209 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.671447923777236e-05, | |
| "loss": 1.1652, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.662661218074702e-05, | |
| "loss": 1.2237, | |
| "step": 1211 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.6538789583829256e-05, | |
| "loss": 1.1594, | |
| "step": 1212 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.645101173898712e-05, | |
| "loss": 1.2234, | |
| "step": 1213 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.636327893803991e-05, | |
| "loss": 1.1729, | |
| "step": 1214 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.6275591472657155e-05, | |
| "loss": 1.1862, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.618794963435767e-05, | |
| "loss": 1.3494, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.610035371450855e-05, | |
| "loss": 1.3393, | |
| "step": 1217 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.6012804004324326e-05, | |
| "loss": 1.1165, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.592530079486578e-05, | |
| "loss": 1.139, | |
| "step": 1219 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.58378443770392e-05, | |
| "loss": 1.1465, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.5750435041595245e-05, | |
| "loss": 1.0544, | |
| "step": 1221 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.566307307912812e-05, | |
| "loss": 1.0745, | |
| "step": 1222 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.5575758780074475e-05, | |
| "loss": 1.2333, | |
| "step": 1223 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.5488492434712496e-05, | |
| "loss": 1.2437, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.5401274333161014e-05, | |
| "loss": 1.2495, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.531410476537843e-05, | |
| "loss": 0.8417, | |
| "step": 1226 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.522698402116176e-05, | |
| "loss": 1.0684, | |
| "step": 1227 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.513991239014579e-05, | |
| "loss": 1.4122, | |
| "step": 1228 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.505289016180195e-05, | |
| "loss": 1.2178, | |
| "step": 1229 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.496591762543746e-05, | |
| "loss": 1.3021, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.487899507019433e-05, | |
| "loss": 1.1669, | |
| "step": 1231 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.4792122785048433e-05, | |
| "loss": 1.3314, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.47053010588085e-05, | |
| "loss": 1.3982, | |
| "step": 1233 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.4618530180115135e-05, | |
| "loss": 1.1775, | |
| "step": 1234 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.4531810437439995e-05, | |
| "loss": 1.1471, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.444514211908464e-05, | |
| "loss": 1.0212, | |
| "step": 1236 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.435852551317973e-05, | |
| "loss": 1.2904, | |
| "step": 1237 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.427196090768395e-05, | |
| "loss": 1.2251, | |
| "step": 1238 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.4185448590383195e-05, | |
| "loss": 1.1489, | |
| "step": 1239 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.409898884888943e-05, | |
| "loss": 1.3208, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.4012581970639884e-05, | |
| "loss": 1.0485, | |
| "step": 1241 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.392622824289604e-05, | |
| "loss": 1.0749, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.383992795274268e-05, | |
| "loss": 1.2257, | |
| "step": 1243 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.375368138708691e-05, | |
| "loss": 1.3465, | |
| "step": 1244 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.366748883265722e-05, | |
| "loss": 1.264, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.3581350576002604e-05, | |
| "loss": 1.2529, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.3495266903491486e-05, | |
| "loss": 1.015, | |
| "step": 1247 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.34092381013108e-05, | |
| "loss": 1.4367, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.3323264455465155e-05, | |
| "loss": 1.1671, | |
| "step": 1249 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.3237346251775706e-05, | |
| "loss": 0.9378, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.315148377587931e-05, | |
| "loss": 1.2775, | |
| "step": 1251 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.3065677313227574e-05, | |
| "loss": 0.9664, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.297992714908589e-05, | |
| "loss": 1.2685, | |
| "step": 1253 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.289423356853246e-05, | |
| "loss": 0.9817, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.2808596856457366e-05, | |
| "loss": 1.451, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.27230172975617e-05, | |
| "loss": 0.9221, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.263749517635644e-05, | |
| "loss": 1.2592, | |
| "step": 1257 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.255203077716169e-05, | |
| "loss": 1.0317, | |
| "step": 1258 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.246662438410566e-05, | |
| "loss": 1.2019, | |
| "step": 1259 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.2381276281123664e-05, | |
| "loss": 1.2084, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.229598675195725e-05, | |
| "loss": 1.2217, | |
| "step": 1261 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.221075608015324e-05, | |
| "loss": 1.2973, | |
| "step": 1262 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.21255845490628e-05, | |
| "loss": 1.0845, | |
| "step": 1263 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.2040472441840476e-05, | |
| "loss": 1.0169, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.195542004144321e-05, | |
| "loss": 1.2404, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.187042763062954e-05, | |
| "loss": 1.133, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.1785495491958466e-05, | |
| "loss": 1.2377, | |
| "step": 1267 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.17006239077887e-05, | |
| "loss": 1.1758, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.1615813160277545e-05, | |
| "loss": 1.3162, | |
| "step": 1269 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.153106353138017e-05, | |
| "loss": 1.3858, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.1446375302848454e-05, | |
| "loss": 1.0595, | |
| "step": 1271 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.136174875623016e-05, | |
| "loss": 1.235, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.127718417286806e-05, | |
| "loss": 1.2516, | |
| "step": 1273 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.119268183389887e-05, | |
| "loss": 1.1253, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.110824202025238e-05, | |
| "loss": 0.873, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.102386501265049e-05, | |
| "loss": 1.2489, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.0939551091606366e-05, | |
| "loss": 1.3002, | |
| "step": 1277 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.085530053742337e-05, | |
| "loss": 1.1461, | |
| "step": 1278 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.077111363019425e-05, | |
| "loss": 1.1955, | |
| "step": 1279 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.068699064980015e-05, | |
| "loss": 1.5328, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.0602931875909665e-05, | |
| "loss": 1.1265, | |
| "step": 1281 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.051893758797796e-05, | |
| "loss": 1.2197, | |
| "step": 1282 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.0435008065245756e-05, | |
| "loss": 1.2036, | |
| "step": 1283 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.0351143586738563e-05, | |
| "loss": 1.1365, | |
| "step": 1284 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.0267344431265576e-05, | |
| "loss": 1.1958, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.0183610877418815e-05, | |
| "loss": 1.0393, | |
| "step": 1286 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.0099943203572277e-05, | |
| "loss": 1.0549, | |
| "step": 1287 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.001634168788088e-05, | |
| "loss": 1.1079, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.9932806608279583e-05, | |
| "loss": 1.1098, | |
| "step": 1289 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.9849338242482517e-05, | |
| "loss": 1.2439, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.9765936867982035e-05, | |
| "loss": 1.3083, | |
| "step": 1291 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.9682602762047745e-05, | |
| "loss": 1.1166, | |
| "step": 1292 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.959933620172559e-05, | |
| "loss": 0.9772, | |
| "step": 1293 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.951613746383704e-05, | |
| "loss": 1.2004, | |
| "step": 1294 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.9433006824978006e-05, | |
| "loss": 1.4374, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.9349944561518055e-05, | |
| "loss": 0.9909, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.9266950949599394e-05, | |
| "loss": 1.0746, | |
| "step": 1297 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.9184026265136056e-05, | |
| "loss": 1.4001, | |
| "step": 1298 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.910117078381288e-05, | |
| "loss": 1.1129, | |
| "step": 1299 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.9018384781084618e-05, | |
| "loss": 1.2081, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.8935668532175108e-05, | |
| "loss": 1.0179, | |
| "step": 1301 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.8853022312076204e-05, | |
| "loss": 1.0857, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.8770446395547036e-05, | |
| "loss": 1.4195, | |
| "step": 1303 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.8687941057112967e-05, | |
| "loss": 1.3654, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.86055065710647e-05, | |
| "loss": 1.2281, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.8523143211457414e-05, | |
| "loss": 1.2947, | |
| "step": 1306 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.8440851252109806e-05, | |
| "loss": 1.0888, | |
| "step": 1307 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.835863096660325e-05, | |
| "loss": 0.9354, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.8276482628280787e-05, | |
| "loss": 1.2106, | |
| "step": 1309 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.8194406510246263e-05, | |
| "loss": 1.2892, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.8112402885363493e-05, | |
| "loss": 1.2886, | |
| "step": 1311 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.803047202625522e-05, | |
| "loss": 1.3912, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.7948614205302288e-05, | |
| "loss": 1.1805, | |
| "step": 1313 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.7866829694642743e-05, | |
| "loss": 1.1429, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.7785118766170932e-05, | |
| "loss": 1.1025, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.7703481691536514e-05, | |
| "loss": 1.1885, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.7621918742143648e-05, | |
| "loss": 1.1314, | |
| "step": 1317 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.7540430189150098e-05, | |
| "loss": 1.1463, | |
| "step": 1318 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.7459016303466233e-05, | |
| "loss": 1.3265, | |
| "step": 1319 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.737767735575424e-05, | |
| "loss": 1.3577, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.7296413616427107e-05, | |
| "loss": 1.5955, | |
| "step": 1321 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.7215225355647893e-05, | |
| "loss": 1.0874, | |
| "step": 1322 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.713411284332863e-05, | |
| "loss": 1.2897, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.705307634912959e-05, | |
| "loss": 1.3041, | |
| "step": 1324 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.697211614245827e-05, | |
| "loss": 1.1114, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.68912324924686e-05, | |
| "loss": 1.1106, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.6810425668059942e-05, | |
| "loss": 1.1093, | |
| "step": 1327 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.672969593787626e-05, | |
| "loss": 1.1339, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.6649043570305277e-05, | |
| "loss": 1.2661, | |
| "step": 1329 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.6568468833477446e-05, | |
| "loss": 1.1655, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.6487971995265148e-05, | |
| "loss": 1.2499, | |
| "step": 1331 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.6407553323281846e-05, | |
| "loss": 1.2827, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.6327213084881087e-05, | |
| "loss": 1.2469, | |
| "step": 1333 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.624695154715564e-05, | |
| "loss": 1.0619, | |
| "step": 1334 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.616676897693669e-05, | |
| "loss": 1.3993, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.6086665640792896e-05, | |
| "loss": 1.1368, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.6006641805029442e-05, | |
| "loss": 1.2083, | |
| "step": 1337 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.592669773568724e-05, | |
| "loss": 1.083, | |
| "step": 1338 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.584683369854205e-05, | |
| "loss": 1.3993, | |
| "step": 1339 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.5767049959103517e-05, | |
| "loss": 1.3574, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.5687346782614353e-05, | |
| "loss": 1.2423, | |
| "step": 1341 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.5607724434049418e-05, | |
| "loss": 1.4365, | |
| "step": 1342 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.5528183178114906e-05, | |
| "loss": 1.3273, | |
| "step": 1343 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.5448723279247354e-05, | |
| "loss": 1.1423, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.5369345001612897e-05, | |
| "loss": 1.269, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.5290048609106242e-05, | |
| "loss": 1.3031, | |
| "step": 1346 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.5210834365349944e-05, | |
| "loss": 0.9519, | |
| "step": 1347 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.513170253369337e-05, | |
| "loss": 0.9234, | |
| "step": 1348 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.5052653377211987e-05, | |
| "loss": 1.0248, | |
| "step": 1349 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.4973687158706353e-05, | |
| "loss": 1.1734, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.4894804140701316e-05, | |
| "loss": 1.1355, | |
| "step": 1351 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.4816004585445102e-05, | |
| "loss": 1.1891, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.4737288754908517e-05, | |
| "loss": 1.0418, | |
| "step": 1353 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.465865691078396e-05, | |
| "loss": 1.3651, | |
| "step": 1354 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.4580109314484634e-05, | |
| "loss": 1.327, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.4501646227143677e-05, | |
| "loss": 1.4478, | |
| "step": 1356 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.442326790961329e-05, | |
| "loss": 0.8422, | |
| "step": 1357 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.4344974622463805e-05, | |
| "loss": 1.3061, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.4266766625982874e-05, | |
| "loss": 1.057, | |
| "step": 1359 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.4188644180174656e-05, | |
| "loss": 1.0059, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.4110607544758847e-05, | |
| "loss": 1.0519, | |
| "step": 1361 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.4032656979169837e-05, | |
| "loss": 1.1574, | |
| "step": 1362 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.3954792742555964e-05, | |
| "loss": 1.2772, | |
| "step": 1363 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.3877015093778487e-05, | |
| "loss": 1.3723, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.3799324291410813e-05, | |
| "loss": 1.1069, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.3721720593737666e-05, | |
| "loss": 1.1158, | |
| "step": 1366 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.364420425875414e-05, | |
| "loss": 1.139, | |
| "step": 1367 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.3566775544164937e-05, | |
| "loss": 1.0133, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.3489434707383407e-05, | |
| "loss": 0.9206, | |
| "step": 1369 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.341218200553082e-05, | |
| "loss": 1.0263, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.3335017695435367e-05, | |
| "loss": 1.0982, | |
| "step": 1371 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.325794203363143e-05, | |
| "loss": 1.2994, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.3180955276358628e-05, | |
| "loss": 1.3514, | |
| "step": 1373 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.3104057679561093e-05, | |
| "loss": 0.9839, | |
| "step": 1374 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.302724949888646e-05, | |
| "loss": 1.1459, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.2950530989685132e-05, | |
| "loss": 1.1129, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.28739024070094e-05, | |
| "loss": 1.279, | |
| "step": 1377 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.2797364005612624e-05, | |
| "loss": 1.3932, | |
| "step": 1378 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.272091603994829e-05, | |
| "loss": 1.2359, | |
| "step": 1379 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.264455876416925e-05, | |
| "loss": 1.3105, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.2568292432126892e-05, | |
| "loss": 1.2369, | |
| "step": 1381 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.2492117297370226e-05, | |
| "loss": 1.0573, | |
| "step": 1382 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.241603361314505e-05, | |
| "loss": 1.4352, | |
| "step": 1383 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.2340041632393204e-05, | |
| "loss": 1.1255, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.226414160775161e-05, | |
| "loss": 0.7906, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.218833379155145e-05, | |
| "loss": 1.1251, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.2112618435817457e-05, | |
| "loss": 1.4728, | |
| "step": 1387 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.2036995792266852e-05, | |
| "loss": 1.3291, | |
| "step": 1388 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.196146611230875e-05, | |
| "loss": 1.3443, | |
| "step": 1389 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.188602964704311e-05, | |
| "loss": 1.1733, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.1810686647260077e-05, | |
| "loss": 1.2824, | |
| "step": 1391 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.1735437363439005e-05, | |
| "loss": 1.1908, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.1660282045747698e-05, | |
| "loss": 1.1784, | |
| "step": 1393 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.1585220944041624e-05, | |
| "loss": 1.1599, | |
| "step": 1394 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.1510254307862965e-05, | |
| "loss": 1.3805, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.143538238643987e-05, | |
| "loss": 1.5486, | |
| "step": 1396 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.136060542868558e-05, | |
| "loss": 1.4098, | |
| "step": 1397 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.128592368319769e-05, | |
| "loss": 1.3092, | |
| "step": 1398 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.1211337398257235e-05, | |
| "loss": 1.1389, | |
| "step": 1399 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.1136846821827845e-05, | |
| "loss": 1.0426, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.106245220155504e-05, | |
| "loss": 1.2593, | |
| "step": 1401 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.0988153784765263e-05, | |
| "loss": 1.1895, | |
| "step": 1402 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.091395181846516e-05, | |
| "loss": 1.3372, | |
| "step": 1403 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.0839846549340706e-05, | |
| "loss": 1.2243, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.0765838223756456e-05, | |
| "loss": 1.0844, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.069192708775461e-05, | |
| "loss": 1.0819, | |
| "step": 1406 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.061811338705427e-05, | |
| "loss": 1.2997, | |
| "step": 1407 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.0544397367050673e-05, | |
| "loss": 1.2678, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.047077927281422e-05, | |
| "loss": 1.0304, | |
| "step": 1409 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.0397259349089853e-05, | |
| "loss": 1.1767, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.0323837840296052e-05, | |
| "loss": 1.1169, | |
| "step": 1411 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.0250514990524198e-05, | |
| "loss": 1.1612, | |
| "step": 1412 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.017729104353763e-05, | |
| "loss": 1.3474, | |
| "step": 1413 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.010416624277086e-05, | |
| "loss": 0.8136, | |
| "step": 1414 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.003114083132886e-05, | |
| "loss": 1.112, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.9958215051986124e-05, | |
| "loss": 1.2453, | |
| "step": 1416 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.9885389147185918e-05, | |
| "loss": 1.0449, | |
| "step": 1417 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.9812663359039485e-05, | |
| "loss": 1.0873, | |
| "step": 1418 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.9740037929325232e-05, | |
| "loss": 1.2039, | |
| "step": 1419 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.966751309948795e-05, | |
| "loss": 1.304, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.9595089110637903e-05, | |
| "loss": 1.1506, | |
| "step": 1421 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.952276620355021e-05, | |
| "loss": 1.4212, | |
| "step": 1422 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.945054461866386e-05, | |
| "loss": 1.2858, | |
| "step": 1423 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.937842459608102e-05, | |
| "loss": 1.2276, | |
| "step": 1424 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.9306406375566205e-05, | |
| "loss": 1.1212, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.9234490196545525e-05, | |
| "loss": 1.0541, | |
| "step": 1426 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.916267629810581e-05, | |
| "loss": 1.3656, | |
| "step": 1427 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.9090964918993836e-05, | |
| "loss": 1.3855, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.9019356297615637e-05, | |
| "loss": 1.2408, | |
| "step": 1429 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.894785067203553e-05, | |
| "loss": 1.1285, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.8876448279975474e-05, | |
| "loss": 1.2005, | |
| "step": 1431 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.880514935881424e-05, | |
| "loss": 1.2734, | |
| "step": 1432 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.8733954145586564e-05, | |
| "loss": 1.2516, | |
| "step": 1433 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8662862876982423e-05, | |
| "loss": 1.171, | |
| "step": 1434 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8591875789346208e-05, | |
| "loss": 1.2292, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.852099311867601e-05, | |
| "loss": 1.1973, | |
| "step": 1436 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8450215100622736e-05, | |
| "loss": 1.3026, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8379541970489366e-05, | |
| "loss": 1.3474, | |
| "step": 1438 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.830897396323024e-05, | |
| "loss": 1.2925, | |
| "step": 1439 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.823851131345014e-05, | |
| "loss": 1.3473, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8168154255403646e-05, | |
| "loss": 0.9422, | |
| "step": 1441 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8097903022994244e-05, | |
| "loss": 1.1527, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8027757849773657e-05, | |
| "loss": 1.139, | |
| "step": 1443 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7957718968940956e-05, | |
| "loss": 1.3206, | |
| "step": 1444 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7887786613341863e-05, | |
| "loss": 1.2061, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.781796101546798e-05, | |
| "loss": 1.2261, | |
| "step": 1446 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7748242407455955e-05, | |
| "loss": 1.2742, | |
| "step": 1447 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7678631021086755e-05, | |
| "loss": 1.3468, | |
| "step": 1448 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7609127087784883e-05, | |
| "loss": 1.2675, | |
| "step": 1449 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.753973083861764e-05, | |
| "loss": 1.2128, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.747044250429429e-05, | |
| "loss": 1.3977, | |
| "step": 1451 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7401262315165345e-05, | |
| "loss": 1.3158, | |
| "step": 1452 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.733219050122183e-05, | |
| "loss": 1.4221, | |
| "step": 1453 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.7263227292094407e-05, | |
| "loss": 1.2207, | |
| "step": 1454 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.7194372917052715e-05, | |
| "loss": 1.4739, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.7125627605004536e-05, | |
| "loss": 1.2519, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.705699158449514e-05, | |
| "loss": 1.3087, | |
| "step": 1457 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.698846508370639e-05, | |
| "loss": 1.2113, | |
| "step": 1458 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.692004833045607e-05, | |
| "loss": 1.0787, | |
| "step": 1459 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.685174155219712e-05, | |
| "loss": 1.2434, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.678354497601683e-05, | |
| "loss": 1.1818, | |
| "step": 1461 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6715458828636182e-05, | |
| "loss": 1.2087, | |
| "step": 1462 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.664748333640896e-05, | |
| "loss": 1.2178, | |
| "step": 1463 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.657961872532114e-05, | |
| "loss": 0.8577, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6511865220990026e-05, | |
| "loss": 1.1468, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6444223048663548e-05, | |
| "loss": 1.2385, | |
| "step": 1466 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6376692433219548e-05, | |
| "loss": 1.2496, | |
| "step": 1467 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6309273599164963e-05, | |
| "loss": 1.3128, | |
| "step": 1468 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6241966770635114e-05, | |
| "loss": 1.1155, | |
| "step": 1469 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6174772171392942e-05, | |
| "loss": 1.1619, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.6107690024828332e-05, | |
| "loss": 1.1044, | |
| "step": 1471 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.604072055395725e-05, | |
| "loss": 1.2591, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5973863981421123e-05, | |
| "loss": 1.1969, | |
| "step": 1473 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5907120529486035e-05, | |
| "loss": 1.3183, | |
| "step": 1474 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5840490420041976e-05, | |
| "loss": 1.065, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5773973874602123e-05, | |
| "loss": 1.35, | |
| "step": 1476 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.570757111430215e-05, | |
| "loss": 1.2008, | |
| "step": 1477 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5641282359899413e-05, | |
| "loss": 1.28, | |
| "step": 1478 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5575107831772258e-05, | |
| "loss": 1.3216, | |
| "step": 1479 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5509047749919277e-05, | |
| "loss": 1.2521, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.544310233395862e-05, | |
| "loss": 1.1923, | |
| "step": 1481 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.537727180312719e-05, | |
| "loss": 1.2108, | |
| "step": 1482 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5311556376279957e-05, | |
| "loss": 1.3311, | |
| "step": 1483 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5245956271889228e-05, | |
| "loss": 1.2425, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5180471708043953e-05, | |
| "loss": 1.2847, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5115102902448913e-05, | |
| "loss": 1.4778, | |
| "step": 1486 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.504985007242406e-05, | |
| "loss": 1.2304, | |
| "step": 1487 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.4984713434903813e-05, | |
| "loss": 1.2299, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.4919693206436281e-05, | |
| "loss": 1.306, | |
| "step": 1489 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.4854789603182557e-05, | |
| "loss": 1.3552, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4790002840916051e-05, | |
| "loss": 0.9951, | |
| "step": 1491 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4725333135021702e-05, | |
| "loss": 1.2237, | |
| "step": 1492 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.466078070049528e-05, | |
| "loss": 1.1483, | |
| "step": 1493 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4596345751942719e-05, | |
| "loss": 1.205, | |
| "step": 1494 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4532028503579375e-05, | |
| "loss": 1.0997, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4467829169229268e-05, | |
| "loss": 1.123, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.440374796232441e-05, | |
| "loss": 1.1807, | |
| "step": 1497 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.433978509590414e-05, | |
| "loss": 1.1934, | |
| "step": 1498 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4275940782614344e-05, | |
| "loss": 1.3633, | |
| "step": 1499 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4212215234706767e-05, | |
| "loss": 1.0159, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.414860866403831e-05, | |
| "loss": 1.2446, | |
| "step": 1501 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4085121282070385e-05, | |
| "loss": 1.1826, | |
| "step": 1502 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4021753299868101e-05, | |
| "loss": 1.3877, | |
| "step": 1503 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.3958504928099624e-05, | |
| "loss": 1.0565, | |
| "step": 1504 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.3895376377035512e-05, | |
| "loss": 1.2594, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.3832367856547963e-05, | |
| "loss": 1.2363, | |
| "step": 1506 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.3769479576110106e-05, | |
| "loss": 1.3128, | |
| "step": 1507 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.370671174479533e-05, | |
| "loss": 1.3741, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.3644064571276638e-05, | |
| "loss": 1.1882, | |
| "step": 1509 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.358153826382585e-05, | |
| "loss": 1.2914, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3519133030312969e-05, | |
| "loss": 1.3082, | |
| "step": 1511 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3456849078205531e-05, | |
| "loss": 1.0512, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3394686614567813e-05, | |
| "loss": 1.3328, | |
| "step": 1513 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3332645846060226e-05, | |
| "loss": 1.2559, | |
| "step": 1514 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3270726978938624e-05, | |
| "loss": 1.2557, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.320893021905355e-05, | |
| "loss": 1.2131, | |
| "step": 1516 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3147255771849648e-05, | |
| "loss": 1.1012, | |
| "step": 1517 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3085703842364888e-05, | |
| "loss": 1.3519, | |
| "step": 1518 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3024274635229966e-05, | |
| "loss": 1.1433, | |
| "step": 1519 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.2962968354667566e-05, | |
| "loss": 1.1603, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.2901785204491668e-05, | |
| "loss": 1.0539, | |
| "step": 1521 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.2840725388106978e-05, | |
| "loss": 1.2916, | |
| "step": 1522 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.2779789108508111e-05, | |
| "loss": 1.199, | |
| "step": 1523 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.2718976568279006e-05, | |
| "loss": 0.9716, | |
| "step": 1524 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.265828796959221e-05, | |
| "loss": 1.3246, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.2597723514208253e-05, | |
| "loss": 1.1401, | |
| "step": 1526 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.2537283403474947e-05, | |
| "loss": 1.0621, | |
| "step": 1527 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.2476967838326681e-05, | |
| "loss": 1.2135, | |
| "step": 1528 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.2416777019283837e-05, | |
| "loss": 1.2582, | |
| "step": 1529 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2356711146452044e-05, | |
| "loss": 1.2656, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2296770419521541e-05, | |
| "loss": 1.1185, | |
| "step": 1531 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2236955037766523e-05, | |
| "loss": 1.1502, | |
| "step": 1532 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2177265200044507e-05, | |
| "loss": 1.2342, | |
| "step": 1533 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2117701104795592e-05, | |
| "loss": 1.0936, | |
| "step": 1534 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2058262950041842e-05, | |
| "loss": 1.0644, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1998950933386677e-05, | |
| "loss": 0.825, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1939765252014108e-05, | |
| "loss": 1.1516, | |
| "step": 1537 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1880706102688199e-05, | |
| "loss": 1.0482, | |
| "step": 1538 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1821773681752296e-05, | |
| "loss": 1.3054, | |
| "step": 1539 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1762968185128498e-05, | |
| "loss": 1.1447, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1704289808316898e-05, | |
| "loss": 1.2114, | |
| "step": 1541 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1645738746394964e-05, | |
| "loss": 1.2715, | |
| "step": 1542 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1587315194016957e-05, | |
| "loss": 1.1241, | |
| "step": 1543 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.152901934541319e-05, | |
| "loss": 1.3107, | |
| "step": 1544 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1470851394389426e-05, | |
| "loss": 1.1323, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1412811534326229e-05, | |
| "loss": 1.3046, | |
| "step": 1546 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1354899958178328e-05, | |
| "loss": 1.3713, | |
| "step": 1547 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1297116858474e-05, | |
| "loss": 1.1967, | |
| "step": 1548 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1239462427314323e-05, | |
| "loss": 1.2154, | |
| "step": 1549 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1181936856372704e-05, | |
| "loss": 1.0635, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1124540336894085e-05, | |
| "loss": 1.0571, | |
| "step": 1551 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1067273059694394e-05, | |
| "loss": 1.4461, | |
| "step": 1552 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1010135215159883e-05, | |
| "loss": 1.4232, | |
| "step": 1553 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0953126993246538e-05, | |
| "loss": 1.1822, | |
| "step": 1554 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0896248583479368e-05, | |
| "loss": 1.3299, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0839500174951828e-05, | |
| "loss": 1.0899, | |
| "step": 1556 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0782881956325213e-05, | |
| "loss": 1.2371, | |
| "step": 1557 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0726394115827949e-05, | |
| "loss": 0.9279, | |
| "step": 1558 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.067003684125506e-05, | |
| "loss": 1.2444, | |
| "step": 1559 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0613810319967488e-05, | |
| "loss": 1.3963, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0557714738891477e-05, | |
| "loss": 1.2298, | |
| "step": 1561 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0501750284517953e-05, | |
| "loss": 1.2426, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0445917142901906e-05, | |
| "loss": 1.1094, | |
| "step": 1563 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.039021549966181e-05, | |
| "loss": 1.0657, | |
| "step": 1564 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0334645539978927e-05, | |
| "loss": 1.2189, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0279207448596739e-05, | |
| "loss": 1.0071, | |
| "step": 1566 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0223901409820364e-05, | |
| "loss": 1.1207, | |
| "step": 1567 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.016872760751586e-05, | |
| "loss": 1.1286, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.011368622510972e-05, | |
| "loss": 0.843, | |
| "step": 1569 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.0058777445588136e-05, | |
| "loss": 1.3613, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.0004001451496525e-05, | |
| "loss": 0.9225, | |
| "step": 1571 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.94935842493881e-06, | |
| "loss": 1.2983, | |
| "step": 1572 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.894848547576868e-06, | |
| "loss": 1.3591, | |
| "step": 1573 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.840472000629947e-06, | |
| "loss": 1.368, | |
| "step": 1574 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.786228964874e-06, | |
| "loss": 1.2772, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.732119620641139e-06, | |
| "loss": 1.2762, | |
| "step": 1576 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.678144147818996e-06, | |
| "loss": 1.2335, | |
| "step": 1577 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.624302725850187e-06, | |
| "loss": 1.2516, | |
| "step": 1578 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.570595533731624e-06, | |
| "loss": 1.3189, | |
| "step": 1579 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.517022750013992e-06, | |
| "loss": 1.1988, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.463584552801152e-06, | |
| "loss": 1.2294, | |
| "step": 1581 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.410281119749498e-06, | |
| "loss": 1.1056, | |
| "step": 1582 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.357112628067399e-06, | |
| "loss": 1.2084, | |
| "step": 1583 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.304079254514614e-06, | |
| "loss": 1.1507, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.25118117540173e-06, | |
| "loss": 1.0806, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.198418566589496e-06, | |
| "loss": 1.3011, | |
| "step": 1586 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.145791603488297e-06, | |
| "loss": 1.3109, | |
| "step": 1587 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.093300461057602e-06, | |
| "loss": 0.977, | |
| "step": 1588 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.040945313805288e-06, | |
| "loss": 1.1077, | |
| "step": 1589 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.988726335787162e-06, | |
| "loss": 1.1945, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.936643700606278e-06, | |
| "loss": 1.0885, | |
| "step": 1591 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.884697581412482e-06, | |
| "loss": 0.9791, | |
| "step": 1592 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.832888150901713e-06, | |
| "loss": 1.2781, | |
| "step": 1593 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.781215581315494e-06, | |
| "loss": 1.1729, | |
| "step": 1594 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.72968004444039e-06, | |
| "loss": 1.1235, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.678281711607367e-06, | |
| "loss": 1.1015, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.627020753691245e-06, | |
| "loss": 1.1341, | |
| "step": 1597 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.575897341110145e-06, | |
| "loss": 1.1307, | |
| "step": 1598 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.524911643824946e-06, | |
| "loss": 1.392, | |
| "step": 1599 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.474063831338641e-06, | |
| "loss": 1.0998, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.423354072695854e-06, | |
| "loss": 1.2868, | |
| "step": 1601 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.37278253648226e-06, | |
| "loss": 1.2419, | |
| "step": 1602 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.322349390823969e-06, | |
| "loss": 1.3416, | |
| "step": 1603 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.272054803387019e-06, | |
| "loss": 1.3764, | |
| "step": 1604 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.221898941376844e-06, | |
| "loss": 1.0162, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.171881971537638e-06, | |
| "loss": 1.361, | |
| "step": 1606 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.122004060151872e-06, | |
| "loss": 1.2593, | |
| "step": 1607 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.07226537303969e-06, | |
| "loss": 1.2895, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.022666075558421e-06, | |
| "loss": 1.1029, | |
| "step": 1609 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.973206332601945e-06, | |
| "loss": 1.2487, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.923886308600238e-06, | |
| "loss": 1.5164, | |
| "step": 1611 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.874706167518725e-06, | |
| "loss": 1.1289, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.825666072857834e-06, | |
| "loss": 0.7554, | |
| "step": 1613 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.776766187652379e-06, | |
| "loss": 1.4283, | |
| "step": 1614 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.728006674471039e-06, | |
| "loss": 0.9559, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.679387695415856e-06, | |
| "loss": 1.2598, | |
| "step": 1616 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.630909412121639e-06, | |
| "loss": 1.0026, | |
| "step": 1617 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.582571985755433e-06, | |
| "loss": 1.2828, | |
| "step": 1618 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.5343755770160505e-06, | |
| "loss": 1.2615, | |
| "step": 1619 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.486320346133452e-06, | |
| "loss": 1.1935, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.438406452868246e-06, | |
| "loss": 0.9452, | |
| "step": 1621 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.390634056511181e-06, | |
| "loss": 1.2256, | |
| "step": 1622 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.3430033158825966e-06, | |
| "loss": 1.368, | |
| "step": 1623 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.2955143893318864e-06, | |
| "loss": 1.1477, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.248167434736957e-06, | |
| "loss": 1.4463, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.200962609503781e-06, | |
| "loss": 1.2813, | |
| "step": 1626 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.153900070565772e-06, | |
| "loss": 1.2198, | |
| "step": 1627 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.106979974383327e-06, | |
| "loss": 1.2491, | |
| "step": 1628 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.060202476943268e-06, | |
| "loss": 1.2309, | |
| "step": 1629 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.0135677337583975e-06, | |
| "loss": 1.2671, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.967075899866871e-06, | |
| "loss": 1.2979, | |
| "step": 1631 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.920727129831778e-06, | |
| "loss": 1.2447, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.874521577740556e-06, | |
| "loss": 0.997, | |
| "step": 1633 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.828459397204551e-06, | |
| "loss": 1.3152, | |
| "step": 1634 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.78254074135844e-06, | |
| "loss": 1.1278, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.736765762859731e-06, | |
| "loss": 1.5342, | |
| "step": 1636 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.691134613888334e-06, | |
| "loss": 1.5108, | |
| "step": 1637 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.645647446145942e-06, | |
| "loss": 1.1687, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.6003044108555844e-06, | |
| "loss": 1.2524, | |
| "step": 1639 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.5551056587611516e-06, | |
| "loss": 1.4549, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.510051340126827e-06, | |
| "loss": 1.205, | |
| "step": 1641 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.46514160473663e-06, | |
| "loss": 1.1393, | |
| "step": 1642 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.4203766018939235e-06, | |
| "loss": 1.2351, | |
| "step": 1643 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.375756480420913e-06, | |
| "loss": 1.1488, | |
| "step": 1644 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.331281388658105e-06, | |
| "loss": 1.3727, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.286951474463865e-06, | |
| "loss": 1.2617, | |
| "step": 1646 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.242766885213947e-06, | |
| "loss": 1.3704, | |
| "step": 1647 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.198727767800921e-06, | |
| "loss": 1.2386, | |
| "step": 1648 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.154834268633753e-06, | |
| "loss": 1.2488, | |
| "step": 1649 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.111086533637317e-06, | |
| "loss": 1.4943, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.0674847082518635e-06, | |
| "loss": 1.2883, | |
| "step": 1651 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.024028937432563e-06, | |
| "loss": 1.0691, | |
| "step": 1652 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.980719365649051e-06, | |
| "loss": 1.2204, | |
| "step": 1653 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.937556136884892e-06, | |
| "loss": 1.1225, | |
| "step": 1654 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.894539394637161e-06, | |
| "loss": 1.1153, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.851669281915889e-06, | |
| "loss": 1.2628, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.808945941243693e-06, | |
| "loss": 1.3027, | |
| "step": 1657 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.766369514655201e-06, | |
| "loss": 1.2969, | |
| "step": 1658 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.723940143696632e-06, | |
| "loss": 1.1445, | |
| "step": 1659 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.6816579694253025e-06, | |
| "loss": 1.168, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.639523132409213e-06, | |
| "loss": 1.0854, | |
| "step": 1661 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.5975357727265035e-06, | |
| "loss": 1.3945, | |
| "step": 1662 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.555696029965008e-06, | |
| "loss": 1.1004, | |
| "step": 1663 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.5140040432218434e-06, | |
| "loss": 1.313, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.472459951102898e-06, | |
| "loss": 1.1305, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.431063891722377e-06, | |
| "loss": 1.1284, | |
| "step": 1666 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.389816002702319e-06, | |
| "loss": 1.1026, | |
| "step": 1667 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.348716421172228e-06, | |
| "loss": 1.27, | |
| "step": 1668 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.307765283768501e-06, | |
| "loss": 1.4698, | |
| "step": 1669 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.26696272663405e-06, | |
| "loss": 1.042, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.226308885417847e-06, | |
| "loss": 1.181, | |
| "step": 1671 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.185803895274427e-06, | |
| "loss": 1.1094, | |
| "step": 1672 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.145447890863475e-06, | |
| "loss": 1.1533, | |
| "step": 1673 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.105241006349365e-06, | |
| "loss": 1.363, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.0651833754007395e-06, | |
| "loss": 1.2546, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.025275131190032e-06, | |
| "loss": 1.2988, | |
| "step": 1676 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.98551640639302e-06, | |
| "loss": 1.3231, | |
| "step": 1677 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.945907333188432e-06, | |
| "loss": 1.2732, | |
| "step": 1678 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.906448043257456e-06, | |
| "loss": 1.2485, | |
| "step": 1679 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.867138667783322e-06, | |
| "loss": 1.2093, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.827979337450866e-06, | |
| "loss": 1.4399, | |
| "step": 1681 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.788970182446123e-06, | |
| "loss": 1.1892, | |
| "step": 1682 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.750111332455825e-06, | |
| "loss": 1.2882, | |
| "step": 1683 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.7114029166670294e-06, | |
| "loss": 1.2116, | |
| "step": 1684 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.672845063766678e-06, | |
| "loss": 1.1849, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.634437901941174e-06, | |
| "loss": 1.1107, | |
| "step": 1686 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.596181558875923e-06, | |
| "loss": 1.3546, | |
| "step": 1687 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.5580761617549205e-06, | |
| "loss": 1.2241, | |
| "step": 1688 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.520121837260383e-06, | |
| "loss": 1.0992, | |
| "step": 1689 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.482318711572248e-06, | |
| "loss": 1.285, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.444666910367779e-06, | |
| "loss": 1.3888, | |
| "step": 1691 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.407166558821202e-06, | |
| "loss": 1.4195, | |
| "step": 1692 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.369817781603208e-06, | |
| "loss": 1.2618, | |
| "step": 1693 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.33262070288058e-06, | |
| "loss": 1.2616, | |
| "step": 1694 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.295575446315803e-06, | |
| "loss": 1.0012, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.258682135066594e-06, | |
| "loss": 1.1821, | |
| "step": 1696 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.221940891785547e-06, | |
| "loss": 1.0638, | |
| "step": 1697 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.185351838619683e-06, | |
| "loss": 1.0286, | |
| "step": 1698 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.148915097210087e-06, | |
| "loss": 1.1041, | |
| "step": 1699 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.112630788691463e-06, | |
| "loss": 1.3143, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.07649903369175e-06, | |
| "loss": 1.0934, | |
| "step": 1701 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.040519952331729e-06, | |
| "loss": 1.2883, | |
| "step": 1702 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.004693664224607e-06, | |
| "loss": 1.413, | |
| "step": 1703 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.969020288475628e-06, | |
| "loss": 1.4394, | |
| "step": 1704 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.9334999436816676e-06, | |
| "loss": 1.2069, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.898132747930861e-06, | |
| "loss": 1.1115, | |
| "step": 1706 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.862918818802202e-06, | |
| "loss": 1.2998, | |
| "step": 1707 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.827858273365114e-06, | |
| "loss": 1.045, | |
| "step": 1708 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.792951228179137e-06, | |
| "loss": 1.2848, | |
| "step": 1709 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.7581977992934614e-06, | |
| "loss": 1.187, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.723598102246584e-06, | |
| "loss": 1.4277, | |
| "step": 1711 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.6891522520659193e-06, | |
| "loss": 1.1144, | |
| "step": 1712 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.654860363267432e-06, | |
| "loss": 1.1549, | |
| "step": 1713 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.62072254985521e-06, | |
| "loss": 0.947, | |
| "step": 1714 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.5867389253211313e-06, | |
| "loss": 1.3587, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.552909602644472e-06, | |
| "loss": 1.1771, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.5192346942915123e-06, | |
| "loss": 1.1695, | |
| "step": 1717 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.4857143122152046e-06, | |
| "loss": 1.1407, | |
| "step": 1718 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.4523485678547406e-06, | |
| "loss": 0.9661, | |
| "step": 1719 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.419137572135256e-06, | |
| "loss": 0.9738, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.3860814354673976e-06, | |
| "loss": 0.9138, | |
| "step": 1721 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.3531802677469637e-06, | |
| "loss": 1.2507, | |
| "step": 1722 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.3204341783545977e-06, | |
| "loss": 1.4461, | |
| "step": 1723 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.28784327615535e-06, | |
| "loss": 1.1542, | |
| "step": 1724 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.255407669498356e-06, | |
| "loss": 1.0647, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.2231274662164635e-06, | |
| "loss": 1.0255, | |
| "step": 1726 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.1910027736258953e-06, | |
| "loss": 1.1207, | |
| "step": 1727 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.159033698525854e-06, | |
| "loss": 1.2126, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.1272203471981952e-06, | |
| "loss": 1.0872, | |
| "step": 1729 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.095562825407089e-06, | |
| "loss": 1.2591, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.064061238398619e-06, | |
| "loss": 1.1745, | |
| "step": 1731 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.032715690900462e-06, | |
| "loss": 1.1854, | |
| "step": 1732 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.0015262871215587e-06, | |
| "loss": 1.0139, | |
| "step": 1733 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.9704931307517337e-06, | |
| "loss": 1.3936, | |
| "step": 1734 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.939616324961353e-06, | |
| "loss": 1.3471, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.90889597240101e-06, | |
| "loss": 1.3437, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.8783321752011648e-06, | |
| "loss": 1.0694, | |
| "step": 1737 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.847925034971788e-06, | |
| "loss": 1.4547, | |
| "step": 1738 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.8176746528020603e-06, | |
| "loss": 1.0212, | |
| "step": 1739 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.7875811292600195e-06, | |
| "loss": 1.0489, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.757644564392209e-06, | |
| "loss": 1.241, | |
| "step": 1741 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.7278650577233555e-06, | |
| "loss": 1.0673, | |
| "step": 1742 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.6982427082560544e-06, | |
| "loss": 1.3088, | |
| "step": 1743 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.6687776144704413e-06, | |
| "loss": 1.208, | |
| "step": 1744 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.6394698743238187e-06, | |
| "loss": 1.2631, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.6103195852503813e-06, | |
| "loss": 1.1418, | |
| "step": 1746 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.5813268441608974e-06, | |
| "loss": 1.1425, | |
| "step": 1747 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.5524917474423205e-06, | |
| "loss": 1.3816, | |
| "step": 1748 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.5238143909575294e-06, | |
| "loss": 1.1894, | |
| "step": 1749 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.495294870045006e-06, | |
| "loss": 1.0318, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.4669332795185016e-06, | |
| "loss": 1.2237, | |
| "step": 1751 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.43872971366671e-06, | |
| "loss": 0.8134, | |
| "step": 1752 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.410684266252966e-06, | |
| "loss": 1.2216, | |
| "step": 1753 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.382797030514966e-06, | |
| "loss": 1.3003, | |
| "step": 1754 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.3550680991643927e-06, | |
| "loss": 1.2226, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.3274975643866657e-06, | |
| "loss": 1.0127, | |
| "step": 1756 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.300085517840589e-06, | |
| "loss": 1.201, | |
| "step": 1757 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.2728320506581138e-06, | |
| "loss": 1.2562, | |
| "step": 1758 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.2457372534439358e-06, | |
| "loss": 1.1304, | |
| "step": 1759 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.2188012162752904e-06, | |
| "loss": 1.1761, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.1920240287015837e-06, | |
| "loss": 1.2002, | |
| "step": 1761 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.165405779744156e-06, | |
| "loss": 1.2275, | |
| "step": 1762 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.1389465578959154e-06, | |
| "loss": 1.2094, | |
| "step": 1763 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.112646451121103e-06, | |
| "loss": 1.355, | |
| "step": 1764 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.0865055468549775e-06, | |
| "loss": 1.0163, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.060523932003522e-06, | |
| "loss": 1.1066, | |
| "step": 1766 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.0347016929431474e-06, | |
| "loss": 1.0126, | |
| "step": 1767 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.009038915520439e-06, | |
| "loss": 1.2624, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.9835356850518404e-06, | |
| "loss": 1.1024, | |
| "step": 1769 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.958192086323357e-06, | |
| "loss": 1.0249, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.933008203590331e-06, | |
| "loss": 1.152, | |
| "step": 1771 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.9079841205771053e-06, | |
| "loss": 1.0416, | |
| "step": 1772 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.8831199204767612e-06, | |
| "loss": 1.2809, | |
| "step": 1773 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.8584156859508484e-06, | |
| "loss": 1.186, | |
| "step": 1774 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.833871499129125e-06, | |
| "loss": 1.4144, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.8094874416092478e-06, | |
| "loss": 1.0609, | |
| "step": 1776 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.7852635944565156e-06, | |
| "loss": 1.3819, | |
| "step": 1777 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.7612000382036308e-06, | |
| "loss": 1.15, | |
| "step": 1778 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.7372968528503786e-06, | |
| "loss": 1.1709, | |
| "step": 1779 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.713554117863403e-06, | |
| "loss": 1.1053, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.6899719121759195e-06, | |
| "loss": 1.1431, | |
| "step": 1781 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.6665503141874704e-06, | |
| "loss": 1.2098, | |
| "step": 1782 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.643289401763648e-06, | |
| "loss": 1.0764, | |
| "step": 1783 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.620189252235832e-06, | |
| "loss": 1.5289, | |
| "step": 1784 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5972499424009634e-06, | |
| "loss": 1.1616, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5744715485212614e-06, | |
| "loss": 0.997, | |
| "step": 1786 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5518541463239611e-06, | |
| "loss": 0.8163, | |
| "step": 1787 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5293978110010932e-06, | |
| "loss": 1.2457, | |
| "step": 1788 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5071026172092163e-06, | |
| "loss": 1.0526, | |
| "step": 1789 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.4849686390691675e-06, | |
| "loss": 1.3221, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.4629959501658185e-06, | |
| "loss": 1.1639, | |
| "step": 1791 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.441184623547831e-06, | |
| "loss": 1.1474, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.4195347317274287e-06, | |
| "loss": 1.1721, | |
| "step": 1793 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.3980463466801209e-06, | |
| "loss": 1.1457, | |
| "step": 1794 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.3767195398444899e-06, | |
| "loss": 1.2726, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.3555543821219597e-06, | |
| "loss": 1.1688, | |
| "step": 1796 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.3345509438765335e-06, | |
| "loss": 1.4171, | |
| "step": 1797 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.3137092949345785e-06, | |
| "loss": 1.3101, | |
| "step": 1798 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.2930295045846031e-06, | |
| "loss": 1.2313, | |
| "step": 1799 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.272511641577001e-06, | |
| "loss": 1.3029, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.2521557741238256e-06, | |
| "loss": 1.147, | |
| "step": 1801 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.2319619698985984e-06, | |
| "loss": 1.114, | |
| "step": 1802 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.211930296036029e-06, | |
| "loss": 1.2693, | |
| "step": 1803 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.1920608191318515e-06, | |
| "loss": 0.9843, | |
| "step": 1804 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.1723536052425432e-06, | |
| "loss": 1.2129, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.1528087198851623e-06, | |
| "loss": 1.2133, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.1334262280370878e-06, | |
| "loss": 1.4306, | |
| "step": 1807 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.1142061941358085e-06, | |
| "loss": 1.1638, | |
| "step": 1808 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.0951486820787337e-06, | |
| "loss": 1.1973, | |
| "step": 1809 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.0762537552229668e-06, | |
| "loss": 1.1617, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.0575214763850815e-06, | |
| "loss": 1.2347, | |
| "step": 1811 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.0389519078409293e-06, | |
| "loss": 0.9908, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.0205451113254327e-06, | |
| "loss": 1.1283, | |
| "step": 1813 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.0023011480323751e-06, | |
| "loss": 0.9934, | |
| "step": 1814 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.842200786141898e-07, | |
| "loss": 1.1358, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.663019631817705e-07, | |
| "loss": 1.0588, | |
| "step": 1816 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.48546861304267e-07, | |
| "loss": 1.2026, | |
| "step": 1817 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.309548320088902e-07, | |
| "loss": 1.0423, | |
| "step": 1818 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.135259337807011e-07, | |
| "loss": 1.5038, | |
| "step": 1819 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.962602245624451e-07, | |
| "loss": 1.3513, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.791577617543345e-07, | |
| "loss": 1.0861, | |
| "step": 1821 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.622186022138489e-07, | |
| "loss": 1.3154, | |
| "step": 1822 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.454428022556027e-07, | |
| "loss": 1.0979, | |
| "step": 1823 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.288304176510719e-07, | |
| "loss": 1.0523, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.123815036284955e-07, | |
| "loss": 1.2029, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.960961148726131e-07, | |
| "loss": 0.9439, | |
| "step": 1826 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.799743055245557e-07, | |
| "loss": 1.2333, | |
| "step": 1827 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.640161291816161e-07, | |
| "loss": 0.9478, | |
| "step": 1828 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.482216388970675e-07, | |
| "loss": 1.3768, | |
| "step": 1829 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.325908871800458e-07, | |
| "loss": 1.3599, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.171239259953e-07, | |
| "loss": 1.4516, | |
| "step": 1831 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.01820806763065e-07, | |
| "loss": 1.2499, | |
| "step": 1832 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 6.866815803588833e-07, | |
| "loss": 0.8766, | |
| "step": 1833 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 6.71706297113428e-07, | |
| "loss": 1.518, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 6.56895006812347e-07, | |
| "loss": 1.2825, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 6.422477586960796e-07, | |
| "loss": 1.2727, | |
| "step": 1836 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 6.277646014597127e-07, | |
| "loss": 1.3522, | |
| "step": 1837 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 6.13445583252803e-07, | |
| "loss": 1.0688, | |
| "step": 1838 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.992907516792268e-07, | |
| "loss": 1.2109, | |
| "step": 1839 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.853001537970137e-07, | |
| "loss": 1.2496, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.714738361182026e-07, | |
| "loss": 0.9845, | |
| "step": 1841 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.5781184460868e-07, | |
| "loss": 1.3632, | |
| "step": 1842 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.44314224688014e-07, | |
| "loss": 1.2382, | |
| "step": 1843 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.309810212293376e-07, | |
| "loss": 1.1642, | |
| "step": 1844 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.178122785591433e-07, | |
| "loss": 0.7902, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.048080404572109e-07, | |
| "loss": 1.2465, | |
| "step": 1846 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.919683501563966e-07, | |
| "loss": 1.2211, | |
| "step": 1847 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.792932503425163e-07, | |
| "loss": 1.43, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.667827831542071e-07, | |
| "loss": 1.3409, | |
| "step": 1849 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.544369901827772e-07, | |
| "loss": 1.1314, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.422559124720727e-07, | |
| "loss": 1.3475, | |
| "step": 1851 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.3023959051834426e-07, | |
| "loss": 1.1728, | |
| "step": 1852 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.183880642701088e-07, | |
| "loss": 1.1887, | |
| "step": 1853 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.067013731279989e-07, | |
| "loss": 1.248, | |
| "step": 1854 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.951795559446803e-07, | |
| "loss": 1.0142, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.8382265102466786e-07, | |
| "loss": 1.3268, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.7263069612423205e-07, | |
| "loss": 1.2656, | |
| "step": 1857 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.6160372845125414e-07, | |
| "loss": 1.1623, | |
| "step": 1858 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.5074178466513176e-07, | |
| "loss": 1.0747, | |
| "step": 1859 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.4004490087661267e-07, | |
| "loss": 0.911, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.2951311264771133e-07, | |
| "loss": 1.269, | |
| "step": 1861 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.191464549915868e-07, | |
| "loss": 1.2852, | |
| "step": 1862 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.0894496237240387e-07, | |
| "loss": 1.2144, | |
| "step": 1863 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.989086687052334e-07, | |
| "loss": 1.2294, | |
| "step": 1864 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.89037607355952e-07, | |
| "loss": 1.2296, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.793318111411036e-07, | |
| "loss": 1.1884, | |
| "step": 1866 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.697913123278162e-07, | |
| "loss": 1.2567, | |
| "step": 1867 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.6041614263367375e-07, | |
| "loss": 1.137, | |
| "step": 1868 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.512063332266279e-07, | |
| "loss": 1.3245, | |
| "step": 1869 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.421619147248755e-07, | |
| "loss": 1.0415, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.3328291719678098e-07, | |
| "loss": 1.2194, | |
| "step": 1871 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.245693701607543e-07, | |
| "loss": 1.1821, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.160213025851676e-07, | |
| "loss": 1.136, | |
| "step": 1873 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.076387428882498e-07, | |
| "loss": 1.2666, | |
| "step": 1874 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.9942171893799765e-07, | |
| "loss": 1.1209, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.9137025805207043e-07, | |
| "loss": 1.3464, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.8348438699772874e-07, | |
| "loss": 1.1171, | |
| "step": 1877 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.7576413199171248e-07, | |
| "loss": 1.3537, | |
| "step": 1878 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.6820951870016865e-07, | |
| "loss": 1.2962, | |
| "step": 1879 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.608205722385736e-07, | |
| "loss": 1.0434, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.5359731717162206e-07, | |
| "loss": 1.0271, | |
| "step": 1881 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.4653977751318825e-07, | |
| "loss": 1.0585, | |
| "step": 1882 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.3964797672620934e-07, | |
| "loss": 1.1897, | |
| "step": 1883 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.329219377226132e-07, | |
| "loss": 1.2887, | |
| "step": 1884 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.2636168286326299e-07, | |
| "loss": 1.1153, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.199672339578628e-07, | |
| "loss": 1.27, | |
| "step": 1886 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.1373861226489091e-07, | |
| "loss": 1.3765, | |
| "step": 1887 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.0767583849153328e-07, | |
| "loss": 1.2347, | |
| "step": 1888 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.0177893279360585e-07, | |
| "loss": 1.1657, | |
| "step": 1889 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.604791477549336e-08, | |
| "loss": 1.0167, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.048280349008842e-08, | |
| "loss": 1.2204, | |
| "step": 1891 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.508361743871928e-08, | |
| "loss": 1.3354, | |
| "step": 1892 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.985037457108879e-08, | |
| "loss": 1.2595, | |
| "step": 1893 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.47830922852244e-08, | |
| "loss": 1.3354, | |
| "step": 1894 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6.988178742741714e-08, | |
| "loss": 1.2313, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6.514647629214943e-08, | |
| "loss": 1.2937, | |
| "step": 1896 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6.05771746220729e-08, | |
| "loss": 1.1192, | |
| "step": 1897 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5.6173897607914025e-08, | |
| "loss": 1.2165, | |
| "step": 1898 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5.193665988846852e-08, | |
| "loss": 1.0047, | |
| "step": 1899 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.7865475550512575e-08, | |
| "loss": 1.2049, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.396035812879729e-08, | |
| "loss": 1.2192, | |
| "step": 1901 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.022132060595429e-08, | |
| "loss": 0.9467, | |
| "step": 1902 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.664837541250132e-08, | |
| "loss": 1.1139, | |
| "step": 1903 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.324153442676448e-08, | |
| "loss": 1.0515, | |
| "step": 1904 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.000080897485602e-08, | |
| "loss": 1.1698, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.6926209830641092e-08, | |
| "loss": 1.2773, | |
| "step": 1906 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.4017747215687724e-08, | |
| "loss": 0.9871, | |
| "step": 1907 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.1275430799239105e-08, | |
| "loss": 1.2191, | |
| "step": 1908 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.8699269698180255e-08, | |
| "loss": 1.3552, | |
| "step": 1909 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.6289272477015837e-08, | |
| "loss": 1.0154, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.4045447147836844e-08, | |
| "loss": 1.1927, | |
| "step": 1911 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.1967801170276182e-08, | |
| "loss": 0.9973, | |
| "step": 1912 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.0056341451525342e-08, | |
| "loss": 1.2536, | |
| "step": 1913 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 8.311074346256664e-09, | |
| "loss": 1.1, | |
| "step": 1914 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 6.73200565666221e-09, | |
| "loss": 1.2848, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.319140632381592e-09, | |
| "loss": 1.1745, | |
| "step": 1916 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.0724839705130746e-09, | |
| "loss": 1.1493, | |
| "step": 1917 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.9920398155913742e-09, | |
| "loss": 1.13, | |
| "step": 1918 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.0778117595821045e-09, | |
| "loss": 1.2359, | |
| "step": 1919 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3298028418484709e-09, | |
| "loss": 1.2037, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.480155491679241e-10, | |
| "loss": 1.242, | |
| "step": 1921 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.324518157044043e-10, | |
| "loss": 1.0958, | |
| "step": 1922 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 8.311302300278989e-11, | |
| "loss": 1.0877, | |
| "step": 1923 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 1923, | |
| "total_flos": 1.299811752898619e+19, | |
| "train_loss": 1.2127362723407558, | |
| "train_runtime": 58007.7542, | |
| "train_samples_per_second": 0.133, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 1923, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1.299811752898619e+19, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |