| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 20.0, |
| "eval_steps": 500, |
| "global_step": 620, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.0, |
| "loss": 1.5228, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 4.708178267332765e-05, |
| "loss": 1.2234, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 7.46228600043274e-05, |
| "loss": 1.2338, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 9.41635653466553e-05, |
| "loss": 1.1425, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00010932051394658049, |
| "loss": 1.0994, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00012170464267765504, |
| "loss": 1.0983, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.0001321752743272128, |
| "loss": 1.0435, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00014124534801998294, |
| "loss": 1.0501, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0001492457200086548, |
| "loss": 0.9684, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00015640229661990817, |
| "loss": 1.0087, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00016287620764191934, |
| "loss": 1.0092, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00016878642535098271, |
| "loss": 0.9322, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00017422329860526873, |
| "loss": 0.9101, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.00017925705700054043, |
| "loss": 0.8277, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.0001839433739509079, |
| "loss": 0.87, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0001883271306933106, |
| "loss": 0.8532, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00019244503717705084, |
| "loss": 0.8097, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00019632750268198243, |
| "loss": 0.74, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.0002, |
| "loss": 0.7398, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0002, |
| "loss": 0.6424, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.0002, |
| "loss": 0.7724, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.0002, |
| "loss": 0.6734, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.0002, |
| "loss": 0.6029, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0002, |
| "loss": 0.6885, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0002, |
| "loss": 0.5919, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.0002, |
| "loss": 0.5716, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.0002, |
| "loss": 0.5545, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.0002, |
| "loss": 0.4666, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.0002, |
| "loss": 0.4891, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.0002, |
| "loss": 0.4238, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0002, |
| "loss": 0.3811, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.2749203145503998, |
| "eval_runtime": 79.3043, |
| "eval_samples_per_second": 12.244, |
| "eval_steps_per_second": 0.391, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.0002, |
| "loss": 0.2765, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.0002, |
| "loss": 0.2996, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.0002, |
| "loss": 0.2371, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 0.0002, |
| "loss": 0.2181, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.0002, |
| "loss": 0.2288, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.0002, |
| "loss": 0.2497, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 0.0002, |
| "loss": 0.1946, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 0.0002, |
| "loss": 0.2178, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.0002, |
| "loss": 0.1129, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.0002, |
| "loss": 0.171, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.0002, |
| "loss": 0.1762, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.0002, |
| "loss": 0.1373, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.0002, |
| "loss": 0.1344, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.0002, |
| "loss": 0.1517, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.0002, |
| "loss": 0.1231, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.0002, |
| "loss": 0.1517, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.55, |
| "learning_rate": 0.0002, |
| "loss": 0.1475, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0609, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.0002, |
| "loss": 0.1443, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 0.0002, |
| "loss": 0.1158, |
| "step": 51 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 0.0002, |
| "loss": 0.1554, |
| "step": 52 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 0.0002, |
| "loss": 0.1112, |
| "step": 53 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0945, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 0.0002, |
| "loss": 0.1444, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0883, |
| "step": 56 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 0.0002, |
| "loss": 0.1058, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0993, |
| "step": 58 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0626, |
| "step": 59 |
| }, |
| { |
| "epoch": 1.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0951, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 0.0002, |
| "loss": 0.1157, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0443, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.04586551710963249, |
| "eval_runtime": 79.6358, |
| "eval_samples_per_second": 12.193, |
| "eval_steps_per_second": 0.389, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0536, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0456, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0362, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0369, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0318, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0311, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0274, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0361, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.29, |
| "learning_rate": 0.0002, |
| "loss": 0.031, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0311, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0511, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0267, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0381, |
| "step": 75 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0218, |
| "step": 76 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0188, |
| "step": 77 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0316, |
| "step": 78 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0161, |
| "step": 79 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 0.0002, |
| "loss": 0.025, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0349, |
| "step": 81 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0234, |
| "step": 82 |
| }, |
| { |
| "epoch": 2.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0247, |
| "step": 83 |
| }, |
| { |
| "epoch": 2.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0265, |
| "step": 84 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0228, |
| "step": 85 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0361, |
| "step": 86 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0331, |
| "step": 87 |
| }, |
| { |
| "epoch": 2.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0249, |
| "step": 88 |
| }, |
| { |
| "epoch": 2.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0123, |
| "step": 89 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0445, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0208, |
| "step": 91 |
| }, |
| { |
| "epoch": 2.97, |
| "learning_rate": 0.0002, |
| "loss": 0.023, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0107, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.011867301538586617, |
| "eval_runtime": 79.8194, |
| "eval_samples_per_second": 12.165, |
| "eval_steps_per_second": 0.388, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0106, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0121, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0119, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0177, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.16, |
| "learning_rate": 0.0002, |
| "loss": 0.013, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0108, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0099, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.26, |
| "learning_rate": 0.0002, |
| "loss": 0.009, |
| "step": 101 |
| }, |
| { |
| "epoch": 3.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0089, |
| "step": 102 |
| }, |
| { |
| "epoch": 3.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0122, |
| "step": 103 |
| }, |
| { |
| "epoch": 3.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0111, |
| "step": 104 |
| }, |
| { |
| "epoch": 3.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 105 |
| }, |
| { |
| "epoch": 3.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0154, |
| "step": 106 |
| }, |
| { |
| "epoch": 3.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0129, |
| "step": 107 |
| }, |
| { |
| "epoch": 3.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0081, |
| "step": 108 |
| }, |
| { |
| "epoch": 3.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0138, |
| "step": 109 |
| }, |
| { |
| "epoch": 3.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0099, |
| "step": 110 |
| }, |
| { |
| "epoch": 3.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0119, |
| "step": 111 |
| }, |
| { |
| "epoch": 3.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0163, |
| "step": 112 |
| }, |
| { |
| "epoch": 3.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0118, |
| "step": 113 |
| }, |
| { |
| "epoch": 3.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 114 |
| }, |
| { |
| "epoch": 3.71, |
| "learning_rate": 0.0002, |
| "loss": 0.009, |
| "step": 115 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 0.0002, |
| "loss": 0.008, |
| "step": 116 |
| }, |
| { |
| "epoch": 3.77, |
| "learning_rate": 0.0002, |
| "loss": 0.014, |
| "step": 117 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 118 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0128, |
| "step": 119 |
| }, |
| { |
| "epoch": 3.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 120 |
| }, |
| { |
| "epoch": 3.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0112, |
| "step": 121 |
| }, |
| { |
| "epoch": 3.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0075, |
| "step": 122 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0103, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.0058988723903894424, |
| "eval_runtime": 79.7449, |
| "eval_samples_per_second": 12.176, |
| "eval_steps_per_second": 0.389, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0039, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 126 |
| }, |
| { |
| "epoch": 4.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 127 |
| }, |
| { |
| "epoch": 4.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 128 |
| }, |
| { |
| "epoch": 4.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 129 |
| }, |
| { |
| "epoch": 4.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0067, |
| "step": 130 |
| }, |
| { |
| "epoch": 4.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0086, |
| "step": 131 |
| }, |
| { |
| "epoch": 4.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 132 |
| }, |
| { |
| "epoch": 4.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0095, |
| "step": 133 |
| }, |
| { |
| "epoch": 4.32, |
| "learning_rate": 0.0002, |
| "loss": 0.01, |
| "step": 134 |
| }, |
| { |
| "epoch": 4.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 135 |
| }, |
| { |
| "epoch": 4.39, |
| "learning_rate": 0.0002, |
| "loss": 0.011, |
| "step": 136 |
| }, |
| { |
| "epoch": 4.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0072, |
| "step": 137 |
| }, |
| { |
| "epoch": 4.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 138 |
| }, |
| { |
| "epoch": 4.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 139 |
| }, |
| { |
| "epoch": 4.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 140 |
| }, |
| { |
| "epoch": 4.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 141 |
| }, |
| { |
| "epoch": 4.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 142 |
| }, |
| { |
| "epoch": 4.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0078, |
| "step": 143 |
| }, |
| { |
| "epoch": 4.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 144 |
| }, |
| { |
| "epoch": 4.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 145 |
| }, |
| { |
| "epoch": 4.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0077, |
| "step": 146 |
| }, |
| { |
| "epoch": 4.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0077, |
| "step": 147 |
| }, |
| { |
| "epoch": 4.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0067, |
| "step": 148 |
| }, |
| { |
| "epoch": 4.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 149 |
| }, |
| { |
| "epoch": 4.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 150 |
| }, |
| { |
| "epoch": 4.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 151 |
| }, |
| { |
| "epoch": 4.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0064, |
| "step": 152 |
| }, |
| { |
| "epoch": 4.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 153 |
| }, |
| { |
| "epoch": 4.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 154 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0119, |
| "step": 155 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.003976665902882814, |
| "eval_runtime": 79.6005, |
| "eval_samples_per_second": 12.198, |
| "eval_steps_per_second": 0.389, |
| "step": 155 |
| }, |
| { |
| "epoch": 5.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 156 |
| }, |
| { |
| "epoch": 5.06, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 157 |
| }, |
| { |
| "epoch": 5.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 158 |
| }, |
| { |
| "epoch": 5.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0029, |
| "step": 159 |
| }, |
| { |
| "epoch": 5.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0037, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0055, |
| "step": 161 |
| }, |
| { |
| "epoch": 5.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 162 |
| }, |
| { |
| "epoch": 5.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0039, |
| "step": 163 |
| }, |
| { |
| "epoch": 5.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0052, |
| "step": 164 |
| }, |
| { |
| "epoch": 5.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0064, |
| "step": 165 |
| }, |
| { |
| "epoch": 5.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 166 |
| }, |
| { |
| "epoch": 5.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0046, |
| "step": 167 |
| }, |
| { |
| "epoch": 5.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 168 |
| }, |
| { |
| "epoch": 5.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 169 |
| }, |
| { |
| "epoch": 5.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0044, |
| "step": 170 |
| }, |
| { |
| "epoch": 5.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0064, |
| "step": 171 |
| }, |
| { |
| "epoch": 5.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 172 |
| }, |
| { |
| "epoch": 5.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 173 |
| }, |
| { |
| "epoch": 5.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0037, |
| "step": 174 |
| }, |
| { |
| "epoch": 5.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0057, |
| "step": 175 |
| }, |
| { |
| "epoch": 5.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 176 |
| }, |
| { |
| "epoch": 5.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0019, |
| "step": 177 |
| }, |
| { |
| "epoch": 5.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0044, |
| "step": 178 |
| }, |
| { |
| "epoch": 5.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 179 |
| }, |
| { |
| "epoch": 5.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 180 |
| }, |
| { |
| "epoch": 5.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0075, |
| "step": 181 |
| }, |
| { |
| "epoch": 5.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 182 |
| }, |
| { |
| "epoch": 5.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0041, |
| "step": 183 |
| }, |
| { |
| "epoch": 5.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0055, |
| "step": 184 |
| }, |
| { |
| "epoch": 5.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0052, |
| "step": 185 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 186 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.0033010360784828663, |
| "eval_runtime": 79.8425, |
| "eval_samples_per_second": 12.161, |
| "eval_steps_per_second": 0.388, |
| "step": 186 |
| }, |
| { |
| "epoch": 6.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 187 |
| }, |
| { |
| "epoch": 6.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 188 |
| }, |
| { |
| "epoch": 6.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 189 |
| }, |
| { |
| "epoch": 6.13, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 190 |
| }, |
| { |
| "epoch": 6.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 191 |
| }, |
| { |
| "epoch": 6.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0052, |
| "step": 192 |
| }, |
| { |
| "epoch": 6.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0044, |
| "step": 193 |
| }, |
| { |
| "epoch": 6.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 194 |
| }, |
| { |
| "epoch": 6.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 195 |
| }, |
| { |
| "epoch": 6.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0075, |
| "step": 196 |
| }, |
| { |
| "epoch": 6.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 197 |
| }, |
| { |
| "epoch": 6.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0066, |
| "step": 198 |
| }, |
| { |
| "epoch": 6.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 199 |
| }, |
| { |
| "epoch": 6.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 201 |
| }, |
| { |
| "epoch": 6.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 202 |
| }, |
| { |
| "epoch": 6.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0041, |
| "step": 203 |
| }, |
| { |
| "epoch": 6.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 204 |
| }, |
| { |
| "epoch": 6.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0141, |
| "step": 205 |
| }, |
| { |
| "epoch": 6.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 206 |
| }, |
| { |
| "epoch": 6.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0037, |
| "step": 207 |
| }, |
| { |
| "epoch": 6.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 208 |
| }, |
| { |
| "epoch": 6.74, |
| "learning_rate": 0.0002, |
| "loss": 0.006, |
| "step": 209 |
| }, |
| { |
| "epoch": 6.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 210 |
| }, |
| { |
| "epoch": 6.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 211 |
| }, |
| { |
| "epoch": 6.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 212 |
| }, |
| { |
| "epoch": 6.87, |
| "learning_rate": 0.0002, |
| "loss": 0.007, |
| "step": 213 |
| }, |
| { |
| "epoch": 6.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0042, |
| "step": 214 |
| }, |
| { |
| "epoch": 6.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 215 |
| }, |
| { |
| "epoch": 6.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0041, |
| "step": 216 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 217 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.0038308058865368366, |
| "eval_runtime": 79.7234, |
| "eval_samples_per_second": 12.18, |
| "eval_steps_per_second": 0.389, |
| "step": 217 |
| }, |
| { |
| "epoch": 7.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 218 |
| }, |
| { |
| "epoch": 7.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0107, |
| "step": 219 |
| }, |
| { |
| "epoch": 7.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 220 |
| }, |
| { |
| "epoch": 7.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 221 |
| }, |
| { |
| "epoch": 7.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0055, |
| "step": 222 |
| }, |
| { |
| "epoch": 7.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 223 |
| }, |
| { |
| "epoch": 7.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0041, |
| "step": 224 |
| }, |
| { |
| "epoch": 7.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 225 |
| }, |
| { |
| "epoch": 7.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 226 |
| }, |
| { |
| "epoch": 7.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 227 |
| }, |
| { |
| "epoch": 7.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 228 |
| }, |
| { |
| "epoch": 7.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 229 |
| }, |
| { |
| "epoch": 7.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 230 |
| }, |
| { |
| "epoch": 7.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 231 |
| }, |
| { |
| "epoch": 7.48, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 232 |
| }, |
| { |
| "epoch": 7.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 233 |
| }, |
| { |
| "epoch": 7.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 234 |
| }, |
| { |
| "epoch": 7.58, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 235 |
| }, |
| { |
| "epoch": 7.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 236 |
| }, |
| { |
| "epoch": 7.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 237 |
| }, |
| { |
| "epoch": 7.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 238 |
| }, |
| { |
| "epoch": 7.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 239 |
| }, |
| { |
| "epoch": 7.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 240 |
| }, |
| { |
| "epoch": 7.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0042, |
| "step": 241 |
| }, |
| { |
| "epoch": 7.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 242 |
| }, |
| { |
| "epoch": 7.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0042, |
| "step": 243 |
| }, |
| { |
| "epoch": 7.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 244 |
| }, |
| { |
| "epoch": 7.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 245 |
| }, |
| { |
| "epoch": 7.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 246 |
| }, |
| { |
| "epoch": 7.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 247 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 248 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.0018170507391914725, |
| "eval_runtime": 79.7215, |
| "eval_samples_per_second": 12.18, |
| "eval_steps_per_second": 0.389, |
| "step": 248 |
| }, |
| { |
| "epoch": 8.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 249 |
| }, |
| { |
| "epoch": 8.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 250 |
| }, |
| { |
| "epoch": 8.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 251 |
| }, |
| { |
| "epoch": 8.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 252 |
| }, |
| { |
| "epoch": 8.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 253 |
| }, |
| { |
| "epoch": 8.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 254 |
| }, |
| { |
| "epoch": 8.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 255 |
| }, |
| { |
| "epoch": 8.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 256 |
| }, |
| { |
| "epoch": 8.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 257 |
| }, |
| { |
| "epoch": 8.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 258 |
| }, |
| { |
| "epoch": 8.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 259 |
| }, |
| { |
| "epoch": 8.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 260 |
| }, |
| { |
| "epoch": 8.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 261 |
| }, |
| { |
| "epoch": 8.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 262 |
| }, |
| { |
| "epoch": 8.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 263 |
| }, |
| { |
| "epoch": 8.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 264 |
| }, |
| { |
| "epoch": 8.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 265 |
| }, |
| { |
| "epoch": 8.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 266 |
| }, |
| { |
| "epoch": 8.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0011, |
| "step": 267 |
| }, |
| { |
| "epoch": 8.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 268 |
| }, |
| { |
| "epoch": 8.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 269 |
| }, |
| { |
| "epoch": 8.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 270 |
| }, |
| { |
| "epoch": 8.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 271 |
| }, |
| { |
| "epoch": 8.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 272 |
| }, |
| { |
| "epoch": 8.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 273 |
| }, |
| { |
| "epoch": 8.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 274 |
| }, |
| { |
| "epoch": 8.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 275 |
| }, |
| { |
| "epoch": 8.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 276 |
| }, |
| { |
| "epoch": 8.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 277 |
| }, |
| { |
| "epoch": 8.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0008, |
| "step": 278 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 279 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.0018369569443166256, |
| "eval_runtime": 79.8171, |
| "eval_samples_per_second": 12.165, |
| "eval_steps_per_second": 0.388, |
| "step": 279 |
| }, |
| { |
| "epoch": 9.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0008, |
| "step": 280 |
| }, |
| { |
| "epoch": 9.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0003, |
| "step": 281 |
| }, |
| { |
| "epoch": 9.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 282 |
| }, |
| { |
| "epoch": 9.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 283 |
| }, |
| { |
| "epoch": 9.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 284 |
| }, |
| { |
| "epoch": 9.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 285 |
| }, |
| { |
| "epoch": 9.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 286 |
| }, |
| { |
| "epoch": 9.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 287 |
| }, |
| { |
| "epoch": 9.29, |
| "learning_rate": 0.0002, |
| "loss": 0.006, |
| "step": 288 |
| }, |
| { |
| "epoch": 9.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 289 |
| }, |
| { |
| "epoch": 9.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 290 |
| }, |
| { |
| "epoch": 9.39, |
| "learning_rate": 0.0002, |
| "loss": 0.003, |
| "step": 291 |
| }, |
| { |
| "epoch": 9.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0041, |
| "step": 292 |
| }, |
| { |
| "epoch": 9.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 293 |
| }, |
| { |
| "epoch": 9.48, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 294 |
| }, |
| { |
| "epoch": 9.52, |
| "learning_rate": 0.0002, |
| "loss": 0.005, |
| "step": 295 |
| }, |
| { |
| "epoch": 9.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 296 |
| }, |
| { |
| "epoch": 9.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 297 |
| }, |
| { |
| "epoch": 9.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 298 |
| }, |
| { |
| "epoch": 9.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 299 |
| }, |
| { |
| "epoch": 9.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 300 |
| }, |
| { |
| "epoch": 9.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 301 |
| }, |
| { |
| "epoch": 9.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 302 |
| }, |
| { |
| "epoch": 9.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 303 |
| }, |
| { |
| "epoch": 9.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 304 |
| }, |
| { |
| "epoch": 9.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 305 |
| }, |
| { |
| "epoch": 9.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 306 |
| }, |
| { |
| "epoch": 9.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 307 |
| }, |
| { |
| "epoch": 9.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0107, |
| "step": 308 |
| }, |
| { |
| "epoch": 9.97, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 309 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 310 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.0019491789862513542, |
| "eval_runtime": 79.6725, |
| "eval_samples_per_second": 12.187, |
| "eval_steps_per_second": 0.389, |
| "step": 310 |
| }, |
| { |
| "epoch": 10.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 311 |
| }, |
| { |
| "epoch": 10.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 312 |
| }, |
| { |
| "epoch": 10.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 313 |
| }, |
| { |
| "epoch": 10.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 314 |
| }, |
| { |
| "epoch": 10.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 315 |
| }, |
| { |
| "epoch": 10.19, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 316 |
| }, |
| { |
| "epoch": 10.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 317 |
| }, |
| { |
| "epoch": 10.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0008, |
| "step": 318 |
| }, |
| { |
| "epoch": 10.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 319 |
| }, |
| { |
| "epoch": 10.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 320 |
| }, |
| { |
| "epoch": 10.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0064, |
| "step": 321 |
| }, |
| { |
| "epoch": 10.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 322 |
| }, |
| { |
| "epoch": 10.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 323 |
| }, |
| { |
| "epoch": 10.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 324 |
| }, |
| { |
| "epoch": 10.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 325 |
| }, |
| { |
| "epoch": 10.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0011, |
| "step": 326 |
| }, |
| { |
| "epoch": 10.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0057, |
| "step": 327 |
| }, |
| { |
| "epoch": 10.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0051, |
| "step": 328 |
| }, |
| { |
| "epoch": 10.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 329 |
| }, |
| { |
| "epoch": 10.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 330 |
| }, |
| { |
| "epoch": 10.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 331 |
| }, |
| { |
| "epoch": 10.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 332 |
| }, |
| { |
| "epoch": 10.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 333 |
| }, |
| { |
| "epoch": 10.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 334 |
| }, |
| { |
| "epoch": 10.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 335 |
| }, |
| { |
| "epoch": 10.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0019, |
| "step": 336 |
| }, |
| { |
| "epoch": 10.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 337 |
| }, |
| { |
| "epoch": 10.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 338 |
| }, |
| { |
| "epoch": 10.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 339 |
| }, |
| { |
| "epoch": 10.97, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 340 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 341 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.0016952411970123649, |
| "eval_runtime": 79.8189, |
| "eval_samples_per_second": 12.165, |
| "eval_steps_per_second": 0.388, |
| "step": 341 |
| }, |
| { |
| "epoch": 11.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0008, |
| "step": 342 |
| }, |
| { |
| "epoch": 11.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 343 |
| }, |
| { |
| "epoch": 11.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 344 |
| }, |
| { |
| "epoch": 11.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 345 |
| }, |
| { |
| "epoch": 11.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 346 |
| }, |
| { |
| "epoch": 11.19, |
| "learning_rate": 0.0002, |
| "loss": 0.003, |
| "step": 347 |
| }, |
| { |
| "epoch": 11.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 348 |
| }, |
| { |
| "epoch": 11.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 349 |
| }, |
| { |
| "epoch": 11.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 350 |
| }, |
| { |
| "epoch": 11.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 351 |
| }, |
| { |
| "epoch": 11.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 352 |
| }, |
| { |
| "epoch": 11.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0025, |
| "step": 353 |
| }, |
| { |
| "epoch": 11.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 354 |
| }, |
| { |
| "epoch": 11.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 355 |
| }, |
| { |
| "epoch": 11.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0025, |
| "step": 356 |
| }, |
| { |
| "epoch": 11.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 357 |
| }, |
| { |
| "epoch": 11.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0008, |
| "step": 358 |
| }, |
| { |
| "epoch": 11.58, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 359 |
| }, |
| { |
| "epoch": 11.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 360 |
| }, |
| { |
| "epoch": 11.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 361 |
| }, |
| { |
| "epoch": 11.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0046, |
| "step": 362 |
| }, |
| { |
| "epoch": 11.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 363 |
| }, |
| { |
| "epoch": 11.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0042, |
| "step": 364 |
| }, |
| { |
| "epoch": 11.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 365 |
| }, |
| { |
| "epoch": 11.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 366 |
| }, |
| { |
| "epoch": 11.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 367 |
| }, |
| { |
| "epoch": 11.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 368 |
| }, |
| { |
| "epoch": 11.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 369 |
| }, |
| { |
| "epoch": 11.94, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 370 |
| }, |
| { |
| "epoch": 11.97, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 371 |
| }, |
| { |
| "epoch": 12.0, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 372 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.004638831131160259, |
| "eval_runtime": 79.6014, |
| "eval_samples_per_second": 12.198, |
| "eval_steps_per_second": 0.389, |
| "step": 372 |
| }, |
| { |
| "epoch": 12.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0029, |
| "step": 373 |
| }, |
| { |
| "epoch": 12.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 374 |
| }, |
| { |
| "epoch": 12.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 375 |
| }, |
| { |
| "epoch": 12.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 376 |
| }, |
| { |
| "epoch": 12.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0088, |
| "step": 377 |
| }, |
| { |
| "epoch": 12.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0011, |
| "step": 378 |
| }, |
| { |
| "epoch": 12.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 379 |
| }, |
| { |
| "epoch": 12.26, |
| "learning_rate": 0.0002, |
| "loss": 0.005, |
| "step": 380 |
| }, |
| { |
| "epoch": 12.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0055, |
| "step": 381 |
| }, |
| { |
| "epoch": 12.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 382 |
| }, |
| { |
| "epoch": 12.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 383 |
| }, |
| { |
| "epoch": 12.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 384 |
| }, |
| { |
| "epoch": 12.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0037, |
| "step": 385 |
| }, |
| { |
| "epoch": 12.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0044, |
| "step": 386 |
| }, |
| { |
| "epoch": 12.48, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 387 |
| }, |
| { |
| "epoch": 12.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 388 |
| }, |
| { |
| "epoch": 12.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0007, |
| "step": 389 |
| }, |
| { |
| "epoch": 12.58, |
| "learning_rate": 0.0002, |
| "loss": 0.009, |
| "step": 390 |
| }, |
| { |
| "epoch": 12.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0025, |
| "step": 391 |
| }, |
| { |
| "epoch": 12.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 392 |
| }, |
| { |
| "epoch": 12.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 393 |
| }, |
| { |
| "epoch": 12.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 394 |
| }, |
| { |
| "epoch": 12.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 395 |
| }, |
| { |
| "epoch": 12.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 396 |
| }, |
| { |
| "epoch": 12.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0116, |
| "step": 397 |
| }, |
| { |
| "epoch": 12.84, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 398 |
| }, |
| { |
| "epoch": 12.87, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 399 |
| }, |
| { |
| "epoch": 12.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 400 |
| }, |
| { |
| "epoch": 12.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 401 |
| }, |
| { |
| "epoch": 12.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 402 |
| }, |
| { |
| "epoch": 13.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 403 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 0.0034103540237993, |
| "eval_runtime": 79.8859, |
| "eval_samples_per_second": 12.155, |
| "eval_steps_per_second": 0.388, |
| "step": 403 |
| }, |
| { |
| "epoch": 13.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 404 |
| }, |
| { |
| "epoch": 13.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 405 |
| }, |
| { |
| "epoch": 13.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0041, |
| "step": 406 |
| }, |
| { |
| "epoch": 13.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 407 |
| }, |
| { |
| "epoch": 13.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0065, |
| "step": 408 |
| }, |
| { |
| "epoch": 13.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 409 |
| }, |
| { |
| "epoch": 13.23, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 410 |
| }, |
| { |
| "epoch": 13.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 411 |
| }, |
| { |
| "epoch": 13.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 412 |
| }, |
| { |
| "epoch": 13.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 413 |
| }, |
| { |
| "epoch": 13.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0104, |
| "step": 414 |
| }, |
| { |
| "epoch": 13.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0051, |
| "step": 415 |
| }, |
| { |
| "epoch": 13.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0055, |
| "step": 416 |
| }, |
| { |
| "epoch": 13.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0039, |
| "step": 417 |
| }, |
| { |
| "epoch": 13.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 418 |
| }, |
| { |
| "epoch": 13.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0042, |
| "step": 419 |
| }, |
| { |
| "epoch": 13.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 420 |
| }, |
| { |
| "epoch": 13.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0114, |
| "step": 421 |
| }, |
| { |
| "epoch": 13.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 422 |
| }, |
| { |
| "epoch": 13.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0042, |
| "step": 423 |
| }, |
| { |
| "epoch": 13.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 424 |
| }, |
| { |
| "epoch": 13.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 425 |
| }, |
| { |
| "epoch": 13.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 426 |
| }, |
| { |
| "epoch": 13.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 427 |
| }, |
| { |
| "epoch": 13.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0042, |
| "step": 428 |
| }, |
| { |
| "epoch": 13.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 429 |
| }, |
| { |
| "epoch": 13.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0134, |
| "step": 430 |
| }, |
| { |
| "epoch": 13.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0138, |
| "step": 431 |
| }, |
| { |
| "epoch": 13.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0083, |
| "step": 432 |
| }, |
| { |
| "epoch": 13.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 433 |
| }, |
| { |
| "epoch": 14.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0052, |
| "step": 434 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.0031798609998077154, |
| "eval_runtime": 79.8396, |
| "eval_samples_per_second": 12.162, |
| "eval_steps_per_second": 0.388, |
| "step": 434 |
| }, |
| { |
| "epoch": 14.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 435 |
| }, |
| { |
| "epoch": 14.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0051, |
| "step": 436 |
| }, |
| { |
| "epoch": 14.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0029, |
| "step": 437 |
| }, |
| { |
| "epoch": 14.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0057, |
| "step": 438 |
| }, |
| { |
| "epoch": 14.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 439 |
| }, |
| { |
| "epoch": 14.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 440 |
| }, |
| { |
| "epoch": 14.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0093, |
| "step": 441 |
| }, |
| { |
| "epoch": 14.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0025, |
| "step": 442 |
| }, |
| { |
| "epoch": 14.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 443 |
| }, |
| { |
| "epoch": 14.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 444 |
| }, |
| { |
| "epoch": 14.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 445 |
| }, |
| { |
| "epoch": 14.39, |
| "learning_rate": 0.0002, |
| "loss": 0.007, |
| "step": 446 |
| }, |
| { |
| "epoch": 14.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0076, |
| "step": 447 |
| }, |
| { |
| "epoch": 14.45, |
| "learning_rate": 0.0002, |
| "loss": 0.005, |
| "step": 448 |
| }, |
| { |
| "epoch": 14.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0078, |
| "step": 449 |
| }, |
| { |
| "epoch": 14.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0076, |
| "step": 450 |
| }, |
| { |
| "epoch": 14.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0077, |
| "step": 451 |
| }, |
| { |
| "epoch": 14.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0087, |
| "step": 452 |
| }, |
| { |
| "epoch": 14.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 453 |
| }, |
| { |
| "epoch": 14.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 454 |
| }, |
| { |
| "epoch": 14.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 455 |
| }, |
| { |
| "epoch": 14.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 456 |
| }, |
| { |
| "epoch": 14.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 457 |
| }, |
| { |
| "epoch": 14.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 458 |
| }, |
| { |
| "epoch": 14.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0075, |
| "step": 459 |
| }, |
| { |
| "epoch": 14.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 460 |
| }, |
| { |
| "epoch": 14.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0157, |
| "step": 461 |
| }, |
| { |
| "epoch": 14.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0072, |
| "step": 462 |
| }, |
| { |
| "epoch": 14.94, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 463 |
| }, |
| { |
| "epoch": 14.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0104, |
| "step": 464 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 465 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 0.0055189551785588264, |
| "eval_runtime": 79.7316, |
| "eval_samples_per_second": 12.178, |
| "eval_steps_per_second": 0.389, |
| "step": 465 |
| }, |
| { |
| "epoch": 15.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0067, |
| "step": 466 |
| }, |
| { |
| "epoch": 15.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 467 |
| }, |
| { |
| "epoch": 15.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0101, |
| "step": 468 |
| }, |
| { |
| "epoch": 15.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 469 |
| }, |
| { |
| "epoch": 15.16, |
| "learning_rate": 0.0002, |
| "loss": 0.007, |
| "step": 470 |
| }, |
| { |
| "epoch": 15.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0082, |
| "step": 471 |
| }, |
| { |
| "epoch": 15.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 472 |
| }, |
| { |
| "epoch": 15.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 473 |
| }, |
| { |
| "epoch": 15.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 474 |
| }, |
| { |
| "epoch": 15.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 475 |
| }, |
| { |
| "epoch": 15.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0064, |
| "step": 476 |
| }, |
| { |
| "epoch": 15.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0082, |
| "step": 477 |
| }, |
| { |
| "epoch": 15.42, |
| "learning_rate": 0.0002, |
| "loss": 0.007, |
| "step": 478 |
| }, |
| { |
| "epoch": 15.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0106, |
| "step": 479 |
| }, |
| { |
| "epoch": 15.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0077, |
| "step": 480 |
| }, |
| { |
| "epoch": 15.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 481 |
| }, |
| { |
| "epoch": 15.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0076, |
| "step": 482 |
| }, |
| { |
| "epoch": 15.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0191, |
| "step": 483 |
| }, |
| { |
| "epoch": 15.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0078, |
| "step": 484 |
| }, |
| { |
| "epoch": 15.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 485 |
| }, |
| { |
| "epoch": 15.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0093, |
| "step": 486 |
| }, |
| { |
| "epoch": 15.71, |
| "learning_rate": 0.0002, |
| "loss": 0.009, |
| "step": 487 |
| }, |
| { |
| "epoch": 15.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0084, |
| "step": 488 |
| }, |
| { |
| "epoch": 15.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0064, |
| "step": 489 |
| }, |
| { |
| "epoch": 15.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0151, |
| "step": 490 |
| }, |
| { |
| "epoch": 15.84, |
| "learning_rate": 0.0002, |
| "loss": 0.009, |
| "step": 491 |
| }, |
| { |
| "epoch": 15.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 492 |
| }, |
| { |
| "epoch": 15.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0085, |
| "step": 493 |
| }, |
| { |
| "epoch": 15.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 494 |
| }, |
| { |
| "epoch": 15.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0095, |
| "step": 495 |
| }, |
| { |
| "epoch": 16.0, |
| "learning_rate": 0.0002, |
| "loss": 0.008, |
| "step": 496 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.008225297555327415, |
| "eval_runtime": 79.8847, |
| "eval_samples_per_second": 12.155, |
| "eval_steps_per_second": 0.388, |
| "step": 496 |
| }, |
| { |
| "epoch": 16.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0081, |
| "step": 497 |
| }, |
| { |
| "epoch": 16.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0101, |
| "step": 498 |
| }, |
| { |
| "epoch": 16.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 499 |
| }, |
| { |
| "epoch": 16.13, |
| "learning_rate": 0.0002, |
| "loss": 0.011, |
| "step": 500 |
| }, |
| { |
| "epoch": 16.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 501 |
| }, |
| { |
| "epoch": 16.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0046, |
| "step": 502 |
| }, |
| { |
| "epoch": 16.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 503 |
| }, |
| { |
| "epoch": 16.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0062, |
| "step": 504 |
| }, |
| { |
| "epoch": 16.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 505 |
| }, |
| { |
| "epoch": 16.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0105, |
| "step": 506 |
| }, |
| { |
| "epoch": 16.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 507 |
| }, |
| { |
| "epoch": 16.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 508 |
| }, |
| { |
| "epoch": 16.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0057, |
| "step": 509 |
| }, |
| { |
| "epoch": 16.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 510 |
| }, |
| { |
| "epoch": 16.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0079, |
| "step": 511 |
| }, |
| { |
| "epoch": 16.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0093, |
| "step": 512 |
| }, |
| { |
| "epoch": 16.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 513 |
| }, |
| { |
| "epoch": 16.58, |
| "learning_rate": 0.0002, |
| "loss": 0.01, |
| "step": 514 |
| }, |
| { |
| "epoch": 16.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0111, |
| "step": 515 |
| }, |
| { |
| "epoch": 16.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0087, |
| "step": 516 |
| }, |
| { |
| "epoch": 16.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0091, |
| "step": 517 |
| }, |
| { |
| "epoch": 16.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0098, |
| "step": 518 |
| }, |
| { |
| "epoch": 16.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0088, |
| "step": 519 |
| }, |
| { |
| "epoch": 16.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0125, |
| "step": 520 |
| }, |
| { |
| "epoch": 16.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 521 |
| }, |
| { |
| "epoch": 16.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0083, |
| "step": 522 |
| }, |
| { |
| "epoch": 16.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0088, |
| "step": 523 |
| }, |
| { |
| "epoch": 16.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 524 |
| }, |
| { |
| "epoch": 16.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0171, |
| "step": 525 |
| }, |
| { |
| "epoch": 16.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0078, |
| "step": 526 |
| }, |
| { |
| "epoch": 17.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 527 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 0.005699164234101772, |
| "eval_runtime": 79.6831, |
| "eval_samples_per_second": 12.186, |
| "eval_steps_per_second": 0.389, |
| "step": 527 |
| }, |
| { |
| "epoch": 17.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 528 |
| }, |
| { |
| "epoch": 17.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0065, |
| "step": 529 |
| }, |
| { |
| "epoch": 17.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 530 |
| }, |
| { |
| "epoch": 17.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0108, |
| "step": 531 |
| }, |
| { |
| "epoch": 17.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0103, |
| "step": 532 |
| }, |
| { |
| "epoch": 17.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0101, |
| "step": 533 |
| }, |
| { |
| "epoch": 17.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0077, |
| "step": 534 |
| }, |
| { |
| "epoch": 17.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 535 |
| }, |
| { |
| "epoch": 17.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0076, |
| "step": 536 |
| }, |
| { |
| "epoch": 17.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 537 |
| }, |
| { |
| "epoch": 17.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 538 |
| }, |
| { |
| "epoch": 17.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 539 |
| }, |
| { |
| "epoch": 17.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 540 |
| }, |
| { |
| "epoch": 17.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 541 |
| }, |
| { |
| "epoch": 17.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0078, |
| "step": 542 |
| }, |
| { |
| "epoch": 17.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0067, |
| "step": 543 |
| }, |
| { |
| "epoch": 17.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0108, |
| "step": 544 |
| }, |
| { |
| "epoch": 17.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0077, |
| "step": 545 |
| }, |
| { |
| "epoch": 17.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0109, |
| "step": 546 |
| }, |
| { |
| "epoch": 17.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0119, |
| "step": 547 |
| }, |
| { |
| "epoch": 17.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0084, |
| "step": 548 |
| }, |
| { |
| "epoch": 17.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 549 |
| }, |
| { |
| "epoch": 17.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 550 |
| }, |
| { |
| "epoch": 17.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0099, |
| "step": 551 |
| }, |
| { |
| "epoch": 17.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0066, |
| "step": 552 |
| }, |
| { |
| "epoch": 17.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0082, |
| "step": 553 |
| }, |
| { |
| "epoch": 17.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 554 |
| }, |
| { |
| "epoch": 17.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 555 |
| }, |
| { |
| "epoch": 17.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 556 |
| }, |
| { |
| "epoch": 17.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 557 |
| }, |
| { |
| "epoch": 18.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0131, |
| "step": 558 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.005718123633414507, |
| "eval_runtime": 79.8345, |
| "eval_samples_per_second": 12.163, |
| "eval_steps_per_second": 0.388, |
| "step": 558 |
| }, |
| { |
| "epoch": 18.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0073, |
| "step": 559 |
| }, |
| { |
| "epoch": 18.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 560 |
| }, |
| { |
| "epoch": 18.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 561 |
| }, |
| { |
| "epoch": 18.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 562 |
| }, |
| { |
| "epoch": 18.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0135, |
| "step": 563 |
| }, |
| { |
| "epoch": 18.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0088, |
| "step": 564 |
| }, |
| { |
| "epoch": 18.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0052, |
| "step": 565 |
| }, |
| { |
| "epoch": 18.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0039, |
| "step": 566 |
| }, |
| { |
| "epoch": 18.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 567 |
| }, |
| { |
| "epoch": 18.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 568 |
| }, |
| { |
| "epoch": 18.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0078, |
| "step": 569 |
| }, |
| { |
| "epoch": 18.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0029, |
| "step": 570 |
| }, |
| { |
| "epoch": 18.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 571 |
| }, |
| { |
| "epoch": 18.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0115, |
| "step": 572 |
| }, |
| { |
| "epoch": 18.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0067, |
| "step": 573 |
| }, |
| { |
| "epoch": 18.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0085, |
| "step": 574 |
| }, |
| { |
| "epoch": 18.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 575 |
| }, |
| { |
| "epoch": 18.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 576 |
| }, |
| { |
| "epoch": 18.61, |
| "learning_rate": 0.0002, |
| "loss": 0.006, |
| "step": 577 |
| }, |
| { |
| "epoch": 18.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 578 |
| }, |
| { |
| "epoch": 18.68, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 579 |
| }, |
| { |
| "epoch": 18.71, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 580 |
| }, |
| { |
| "epoch": 18.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 581 |
| }, |
| { |
| "epoch": 18.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 582 |
| }, |
| { |
| "epoch": 18.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0083, |
| "step": 583 |
| }, |
| { |
| "epoch": 18.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0126, |
| "step": 584 |
| }, |
| { |
| "epoch": 18.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 585 |
| }, |
| { |
| "epoch": 18.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0064, |
| "step": 586 |
| }, |
| { |
| "epoch": 18.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 587 |
| }, |
| { |
| "epoch": 18.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0154, |
| "step": 588 |
| }, |
| { |
| "epoch": 19.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0079, |
| "step": 589 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 0.00487202825024724, |
| "eval_runtime": 79.8304, |
| "eval_samples_per_second": 12.163, |
| "eval_steps_per_second": 0.388, |
| "step": 589 |
| }, |
| { |
| "epoch": 19.03, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 590 |
| }, |
| { |
| "epoch": 19.06, |
| "learning_rate": 0.0002, |
| "loss": 0.0081, |
| "step": 591 |
| }, |
| { |
| "epoch": 19.1, |
| "learning_rate": 0.0002, |
| "loss": 0.0052, |
| "step": 592 |
| }, |
| { |
| "epoch": 19.13, |
| "learning_rate": 0.0002, |
| "loss": 0.0095, |
| "step": 593 |
| }, |
| { |
| "epoch": 19.16, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 594 |
| }, |
| { |
| "epoch": 19.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 595 |
| }, |
| { |
| "epoch": 19.23, |
| "learning_rate": 0.0002, |
| "loss": 0.0062, |
| "step": 596 |
| }, |
| { |
| "epoch": 19.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0041, |
| "step": 597 |
| }, |
| { |
| "epoch": 19.29, |
| "learning_rate": 0.0002, |
| "loss": 0.0065, |
| "step": 598 |
| }, |
| { |
| "epoch": 19.32, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 599 |
| }, |
| { |
| "epoch": 19.35, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 600 |
| }, |
| { |
| "epoch": 19.39, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 601 |
| }, |
| { |
| "epoch": 19.42, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 602 |
| }, |
| { |
| "epoch": 19.45, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 603 |
| }, |
| { |
| "epoch": 19.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0107, |
| "step": 604 |
| }, |
| { |
| "epoch": 19.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 605 |
| }, |
| { |
| "epoch": 19.55, |
| "learning_rate": 0.0002, |
| "loss": 0.0118, |
| "step": 606 |
| }, |
| { |
| "epoch": 19.58, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 607 |
| }, |
| { |
| "epoch": 19.61, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 608 |
| }, |
| { |
| "epoch": 19.65, |
| "learning_rate": 0.0002, |
| "loss": 0.0089, |
| "step": 609 |
| }, |
| { |
| "epoch": 19.68, |
| "learning_rate": 0.0002, |
| "loss": 0.003, |
| "step": 610 |
| }, |
| { |
| "epoch": 19.71, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 611 |
| }, |
| { |
| "epoch": 19.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 612 |
| }, |
| { |
| "epoch": 19.77, |
| "learning_rate": 0.0002, |
| "loss": 0.0121, |
| "step": 613 |
| }, |
| { |
| "epoch": 19.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0039, |
| "step": 614 |
| }, |
| { |
| "epoch": 19.84, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 615 |
| }, |
| { |
| "epoch": 19.87, |
| "learning_rate": 0.0002, |
| "loss": 0.0066, |
| "step": 616 |
| }, |
| { |
| "epoch": 19.9, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 617 |
| }, |
| { |
| "epoch": 19.94, |
| "learning_rate": 0.0002, |
| "loss": 0.0096, |
| "step": 618 |
| }, |
| { |
| "epoch": 19.97, |
| "learning_rate": 0.0002, |
| "loss": 0.0037, |
| "step": 619 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 620 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.0047739846631884575, |
| "eval_runtime": 79.8422, |
| "eval_samples_per_second": 12.161, |
| "eval_steps_per_second": 0.388, |
| "step": 620 |
| }, |
| { |
| "epoch": 20.0, |
| "step": 620, |
| "total_flos": 2.340547255766876e+18, |
| "train_loss": 0.055398393795692225, |
| "train_runtime": 10640.4455, |
| "train_samples_per_second": 1.825, |
| "train_steps_per_second": 0.058 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 620, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 50000, |
| "total_flos": 2.340547255766876e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
