| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 20.0, |
| "eval_steps": 500, |
| "global_step": 540, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.0, |
| "loss": 1.5857, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 4.8930108423645205e-05, |
| "loss": 1.1134, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 7.755238700769803e-05, |
| "loss": 1.0305, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 9.786021684729041e-05, |
| "loss": 1.0862, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00011361219343474658, |
| "loss": 1.1588, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00012648249543134322, |
| "loss": 0.9897, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0001373641807199326, |
| "loss": 1.0786, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00014679032527093562, |
| "loss": 0.9976, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00015510477401539606, |
| "loss": 0.9506, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.0001625423018583918, |
| "loss": 0.8853, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0001692703641841094, |
| "loss": 0.8753, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.00017541260385498843, |
| "loss": 0.777, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00018106291662380673, |
| "loss": 0.8107, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0001862942891435778, |
| "loss": 0.7394, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0001911645804424446, |
| "loss": 0.6992, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.00019572043369458082, |
| "loss": 0.7101, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.0002, |
| "loss": 0.5249, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0002, |
| "loss": 0.5232, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.0002, |
| "loss": 0.6104, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.0002, |
| "loss": 0.4919, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.0002, |
| "loss": 0.3575, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0002, |
| "loss": 0.528, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.0002, |
| "loss": 0.3896, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.0002, |
| "loss": 0.2822, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.0002, |
| "loss": 0.3985, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.0002, |
| "loss": 0.2425, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0002, |
| "loss": 0.2679, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.18373605608940125, |
| "eval_runtime": 47.8216, |
| "eval_samples_per_second": 8.887, |
| "eval_steps_per_second": 0.565, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.0002, |
| "loss": 0.1042, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0874, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.0002, |
| "loss": 0.1573, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.0002, |
| "loss": 0.1906, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.0002, |
| "loss": 0.1532, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.0002, |
| "loss": 0.1201, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 0.0002, |
| "loss": 0.1575, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 0.0002, |
| "loss": 0.1519, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0897, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0967, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 0.0002, |
| "loss": 0.1094, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.0002, |
| "loss": 0.1451, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.0002, |
| "loss": 0.1914, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.0002, |
| "loss": 0.1286, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.0002, |
| "loss": 0.07, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.0002, |
| "loss": 0.1391, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0355, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.0002, |
| "loss": 0.1301, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0502, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.0002, |
| "loss": 0.035, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 0.0002, |
| "loss": 0.1198, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0349, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0407, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0461, |
| "step": 51 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 0.0002, |
| "loss": 0.1048, |
| "step": 52 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0841, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0749, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.03986518457531929, |
| "eval_runtime": 48.089, |
| "eval_samples_per_second": 8.838, |
| "eval_steps_per_second": 0.561, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0225, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0393, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0339, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0242, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0314, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0156, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0283, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0306, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0239, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0325, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0081, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0095, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0253, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0402, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0278, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0114, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0319, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0101, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0136, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0137, |
| "step": 75 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0259, |
| "step": 76 |
| }, |
| { |
| "epoch": 2.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0259, |
| "step": 77 |
| }, |
| { |
| "epoch": 2.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0206, |
| "step": 78 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 79 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0136, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0096, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.010682879947125912, |
| "eval_runtime": 48.1877, |
| "eval_samples_per_second": 8.82, |
| "eval_steps_per_second": 0.56, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0076, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0104, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.11, |
| "learning_rate": 0.0002, |
| "loss": 0.01, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0041, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0073, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0066, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.37, |
| "learning_rate": 0.0002, |
| "loss": 0.006, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.41, |
| "learning_rate": 0.0002, |
| "loss": 0.019, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0134, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0199, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.52, |
| "learning_rate": 0.0002, |
| "loss": 0.011, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0057, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0106, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0019, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0075, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 101 |
| }, |
| { |
| "epoch": 3.78, |
| "learning_rate": 0.0002, |
| "loss": 0.012, |
| "step": 102 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0097, |
| "step": 103 |
| }, |
| { |
| "epoch": 3.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0105, |
| "step": 104 |
| }, |
| { |
| "epoch": 3.89, |
| "learning_rate": 0.0002, |
| "loss": 0.01, |
| "step": 105 |
| }, |
| { |
| "epoch": 3.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 106 |
| }, |
| { |
| "epoch": 3.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0062, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0114, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.009599113836884499, |
| "eval_runtime": 48.2015, |
| "eval_samples_per_second": 8.817, |
| "eval_steps_per_second": 0.56, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0078, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.07, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0078, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0153, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0029, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0289, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 126 |
| }, |
| { |
| "epoch": 4.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 127 |
| }, |
| { |
| "epoch": 4.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0144, |
| "step": 128 |
| }, |
| { |
| "epoch": 4.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 129 |
| }, |
| { |
| "epoch": 4.81, |
| "learning_rate": 0.0002, |
| "loss": 0.011, |
| "step": 130 |
| }, |
| { |
| "epoch": 4.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 131 |
| }, |
| { |
| "epoch": 4.89, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 132 |
| }, |
| { |
| "epoch": 4.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 133 |
| }, |
| { |
| "epoch": 4.96, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 134 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 135 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.004502412863075733, |
| "eval_runtime": 48.1685, |
| "eval_samples_per_second": 8.823, |
| "eval_steps_per_second": 0.561, |
| "step": 135 |
| }, |
| { |
| "epoch": 5.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 136 |
| }, |
| { |
| "epoch": 5.07, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 137 |
| }, |
| { |
| "epoch": 5.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 138 |
| }, |
| { |
| "epoch": 5.15, |
| "learning_rate": 0.0002, |
| "loss": 0.008, |
| "step": 139 |
| }, |
| { |
| "epoch": 5.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0145, |
| "step": 140 |
| }, |
| { |
| "epoch": 5.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 141 |
| }, |
| { |
| "epoch": 5.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0047, |
| "step": 142 |
| }, |
| { |
| "epoch": 5.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 143 |
| }, |
| { |
| "epoch": 5.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 144 |
| }, |
| { |
| "epoch": 5.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 145 |
| }, |
| { |
| "epoch": 5.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 146 |
| }, |
| { |
| "epoch": 5.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 147 |
| }, |
| { |
| "epoch": 5.48, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 148 |
| }, |
| { |
| "epoch": 5.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 149 |
| }, |
| { |
| "epoch": 5.56, |
| "learning_rate": 0.0002, |
| "loss": 0.003, |
| "step": 150 |
| }, |
| { |
| "epoch": 5.59, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 151 |
| }, |
| { |
| "epoch": 5.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 152 |
| }, |
| { |
| "epoch": 5.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 153 |
| }, |
| { |
| "epoch": 5.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 154 |
| }, |
| { |
| "epoch": 5.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 155 |
| }, |
| { |
| "epoch": 5.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0025, |
| "step": 156 |
| }, |
| { |
| "epoch": 5.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 157 |
| }, |
| { |
| "epoch": 5.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0164, |
| "step": 158 |
| }, |
| { |
| "epoch": 5.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0093, |
| "step": 159 |
| }, |
| { |
| "epoch": 5.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 161 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 162 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.003009921871125698, |
| "eval_runtime": 48.0407, |
| "eval_samples_per_second": 8.847, |
| "eval_steps_per_second": 0.562, |
| "step": 162 |
| }, |
| { |
| "epoch": 6.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 163 |
| }, |
| { |
| "epoch": 6.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 164 |
| }, |
| { |
| "epoch": 6.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 165 |
| }, |
| { |
| "epoch": 6.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 166 |
| }, |
| { |
| "epoch": 6.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 167 |
| }, |
| { |
| "epoch": 6.22, |
| "learning_rate": 0.0002, |
| "loss": 0.003, |
| "step": 168 |
| }, |
| { |
| "epoch": 6.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0008, |
| "step": 169 |
| }, |
| { |
| "epoch": 6.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 170 |
| }, |
| { |
| "epoch": 6.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 171 |
| }, |
| { |
| "epoch": 6.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 172 |
| }, |
| { |
| "epoch": 6.41, |
| "learning_rate": 0.0002, |
| "loss": 0.005, |
| "step": 173 |
| }, |
| { |
| "epoch": 6.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 174 |
| }, |
| { |
| "epoch": 6.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 175 |
| }, |
| { |
| "epoch": 6.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0076, |
| "step": 176 |
| }, |
| { |
| "epoch": 6.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 177 |
| }, |
| { |
| "epoch": 6.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 178 |
| }, |
| { |
| "epoch": 6.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 179 |
| }, |
| { |
| "epoch": 6.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 180 |
| }, |
| { |
| "epoch": 6.7, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 181 |
| }, |
| { |
| "epoch": 6.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0025, |
| "step": 182 |
| }, |
| { |
| "epoch": 6.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 183 |
| }, |
| { |
| "epoch": 6.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 184 |
| }, |
| { |
| "epoch": 6.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 185 |
| }, |
| { |
| "epoch": 6.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 186 |
| }, |
| { |
| "epoch": 6.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 187 |
| }, |
| { |
| "epoch": 6.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0085, |
| "step": 188 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 189 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.000877623853739351, |
| "eval_runtime": 48.1303, |
| "eval_samples_per_second": 8.83, |
| "eval_steps_per_second": 0.561, |
| "step": 189 |
| }, |
| { |
| "epoch": 7.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 190 |
| }, |
| { |
| "epoch": 7.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 191 |
| }, |
| { |
| "epoch": 7.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0065, |
| "step": 192 |
| }, |
| { |
| "epoch": 7.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 193 |
| }, |
| { |
| "epoch": 7.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 194 |
| }, |
| { |
| "epoch": 7.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0025, |
| "step": 195 |
| }, |
| { |
| "epoch": 7.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0007, |
| "step": 196 |
| }, |
| { |
| "epoch": 7.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 197 |
| }, |
| { |
| "epoch": 7.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 198 |
| }, |
| { |
| "epoch": 7.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 199 |
| }, |
| { |
| "epoch": 7.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 200 |
| }, |
| { |
| "epoch": 7.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 201 |
| }, |
| { |
| "epoch": 7.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 202 |
| }, |
| { |
| "epoch": 7.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 203 |
| }, |
| { |
| "epoch": 7.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0011, |
| "step": 204 |
| }, |
| { |
| "epoch": 7.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 205 |
| }, |
| { |
| "epoch": 7.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 206 |
| }, |
| { |
| "epoch": 7.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0003, |
| "step": 207 |
| }, |
| { |
| "epoch": 7.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0029, |
| "step": 208 |
| }, |
| { |
| "epoch": 7.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 209 |
| }, |
| { |
| "epoch": 7.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 210 |
| }, |
| { |
| "epoch": 7.81, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 211 |
| }, |
| { |
| "epoch": 7.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 212 |
| }, |
| { |
| "epoch": 7.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 213 |
| }, |
| { |
| "epoch": 7.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 214 |
| }, |
| { |
| "epoch": 7.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 215 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0041, |
| "step": 216 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.0037567296531051397, |
| "eval_runtime": 48.0606, |
| "eval_samples_per_second": 8.843, |
| "eval_steps_per_second": 0.562, |
| "step": 216 |
| }, |
| { |
| "epoch": 8.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 217 |
| }, |
| { |
| "epoch": 8.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 218 |
| }, |
| { |
| "epoch": 8.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0052, |
| "step": 219 |
| }, |
| { |
| "epoch": 8.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0064, |
| "step": 220 |
| }, |
| { |
| "epoch": 8.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 221 |
| }, |
| { |
| "epoch": 8.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0065, |
| "step": 222 |
| }, |
| { |
| "epoch": 8.26, |
| "learning_rate": 0.0002, |
| "loss": 0.013, |
| "step": 223 |
| }, |
| { |
| "epoch": 8.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 224 |
| }, |
| { |
| "epoch": 8.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0008, |
| "step": 225 |
| }, |
| { |
| "epoch": 8.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0029, |
| "step": 226 |
| }, |
| { |
| "epoch": 8.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 227 |
| }, |
| { |
| "epoch": 8.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0008, |
| "step": 228 |
| }, |
| { |
| "epoch": 8.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 229 |
| }, |
| { |
| "epoch": 8.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 230 |
| }, |
| { |
| "epoch": 8.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 231 |
| }, |
| { |
| "epoch": 8.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 232 |
| }, |
| { |
| "epoch": 8.63, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 233 |
| }, |
| { |
| "epoch": 8.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0011, |
| "step": 234 |
| }, |
| { |
| "epoch": 8.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 235 |
| }, |
| { |
| "epoch": 8.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 236 |
| }, |
| { |
| "epoch": 8.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0011, |
| "step": 237 |
| }, |
| { |
| "epoch": 8.81, |
| "learning_rate": 0.0002, |
| "loss": 0.003, |
| "step": 238 |
| }, |
| { |
| "epoch": 8.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 239 |
| }, |
| { |
| "epoch": 8.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 240 |
| }, |
| { |
| "epoch": 8.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0121, |
| "step": 241 |
| }, |
| { |
| "epoch": 8.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 242 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0009, |
| "step": 243 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.0028407848440110683, |
| "eval_runtime": 48.0769, |
| "eval_samples_per_second": 8.84, |
| "eval_steps_per_second": 0.562, |
| "step": 243 |
| }, |
| { |
| "epoch": 9.04, |
| "learning_rate": 0.0002, |
| "loss": 0.009, |
| "step": 244 |
| }, |
| { |
| "epoch": 9.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0003, |
| "step": 245 |
| }, |
| { |
| "epoch": 9.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0006, |
| "step": 246 |
| }, |
| { |
| "epoch": 9.15, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 247 |
| }, |
| { |
| "epoch": 9.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 248 |
| }, |
| { |
| "epoch": 9.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 249 |
| }, |
| { |
| "epoch": 9.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 250 |
| }, |
| { |
| "epoch": 9.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 251 |
| }, |
| { |
| "epoch": 9.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 252 |
| }, |
| { |
| "epoch": 9.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 253 |
| }, |
| { |
| "epoch": 9.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 254 |
| }, |
| { |
| "epoch": 9.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 255 |
| }, |
| { |
| "epoch": 9.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 256 |
| }, |
| { |
| "epoch": 9.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0028, |
| "step": 257 |
| }, |
| { |
| "epoch": 9.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 258 |
| }, |
| { |
| "epoch": 9.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 259 |
| }, |
| { |
| "epoch": 9.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0035, |
| "step": 260 |
| }, |
| { |
| "epoch": 9.67, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 261 |
| }, |
| { |
| "epoch": 9.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 262 |
| }, |
| { |
| "epoch": 9.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 263 |
| }, |
| { |
| "epoch": 9.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0012, |
| "step": 264 |
| }, |
| { |
| "epoch": 9.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 265 |
| }, |
| { |
| "epoch": 9.85, |
| "learning_rate": 0.0002, |
| "loss": 0.005, |
| "step": 266 |
| }, |
| { |
| "epoch": 9.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0073, |
| "step": 267 |
| }, |
| { |
| "epoch": 9.93, |
| "learning_rate": 0.0002, |
| "loss": 0.001, |
| "step": 268 |
| }, |
| { |
| "epoch": 9.96, |
| "learning_rate": 0.0002, |
| "loss": 0.003, |
| "step": 269 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0029, |
| "step": 270 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.0032664372120052576, |
| "eval_runtime": 48.0025, |
| "eval_samples_per_second": 8.854, |
| "eval_steps_per_second": 0.562, |
| "step": 270 |
| }, |
| { |
| "epoch": 10.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 271 |
| }, |
| { |
| "epoch": 10.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0127, |
| "step": 272 |
| }, |
| { |
| "epoch": 10.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 273 |
| }, |
| { |
| "epoch": 10.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 274 |
| }, |
| { |
| "epoch": 10.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 275 |
| }, |
| { |
| "epoch": 10.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0007, |
| "step": 276 |
| }, |
| { |
| "epoch": 10.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0093, |
| "step": 277 |
| }, |
| { |
| "epoch": 10.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0025, |
| "step": 278 |
| }, |
| { |
| "epoch": 10.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0008, |
| "step": 279 |
| }, |
| { |
| "epoch": 10.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 280 |
| }, |
| { |
| "epoch": 10.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 281 |
| }, |
| { |
| "epoch": 10.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 282 |
| }, |
| { |
| "epoch": 10.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 283 |
| }, |
| { |
| "epoch": 10.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 284 |
| }, |
| { |
| "epoch": 10.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 285 |
| }, |
| { |
| "epoch": 10.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 286 |
| }, |
| { |
| "epoch": 10.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0051, |
| "step": 287 |
| }, |
| { |
| "epoch": 10.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 288 |
| }, |
| { |
| "epoch": 10.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 289 |
| }, |
| { |
| "epoch": 10.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 290 |
| }, |
| { |
| "epoch": 10.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0019, |
| "step": 291 |
| }, |
| { |
| "epoch": 10.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0083, |
| "step": 292 |
| }, |
| { |
| "epoch": 10.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0003, |
| "step": 293 |
| }, |
| { |
| "epoch": 10.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0019, |
| "step": 294 |
| }, |
| { |
| "epoch": 10.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 295 |
| }, |
| { |
| "epoch": 10.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 296 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 297 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.00336476624943316, |
| "eval_runtime": 48.2832, |
| "eval_samples_per_second": 8.802, |
| "eval_steps_per_second": 0.559, |
| "step": 297 |
| }, |
| { |
| "epoch": 11.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0066, |
| "step": 298 |
| }, |
| { |
| "epoch": 11.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 299 |
| }, |
| { |
| "epoch": 11.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0023, |
| "step": 300 |
| }, |
| { |
| "epoch": 11.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0044, |
| "step": 301 |
| }, |
| { |
| "epoch": 11.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0014, |
| "step": 302 |
| }, |
| { |
| "epoch": 11.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 303 |
| }, |
| { |
| "epoch": 11.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 304 |
| }, |
| { |
| "epoch": 11.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 305 |
| }, |
| { |
| "epoch": 11.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 306 |
| }, |
| { |
| "epoch": 11.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0004, |
| "step": 307 |
| }, |
| { |
| "epoch": 11.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 308 |
| }, |
| { |
| "epoch": 11.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 309 |
| }, |
| { |
| "epoch": 11.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 310 |
| }, |
| { |
| "epoch": 11.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0029, |
| "step": 311 |
| }, |
| { |
| "epoch": 11.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0046, |
| "step": 312 |
| }, |
| { |
| "epoch": 11.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 313 |
| }, |
| { |
| "epoch": 11.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0089, |
| "step": 314 |
| }, |
| { |
| "epoch": 11.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 315 |
| }, |
| { |
| "epoch": 11.7, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 316 |
| }, |
| { |
| "epoch": 11.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0011, |
| "step": 317 |
| }, |
| { |
| "epoch": 11.78, |
| "learning_rate": 0.0002, |
| "loss": 0.005, |
| "step": 318 |
| }, |
| { |
| "epoch": 11.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 319 |
| }, |
| { |
| "epoch": 11.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 320 |
| }, |
| { |
| "epoch": 11.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 321 |
| }, |
| { |
| "epoch": 11.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 322 |
| }, |
| { |
| "epoch": 11.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 323 |
| }, |
| { |
| "epoch": 12.0, |
| "learning_rate": 0.0002, |
| "loss": 0.007, |
| "step": 324 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.004381947685033083, |
| "eval_runtime": 48.0671, |
| "eval_samples_per_second": 8.842, |
| "eval_steps_per_second": 0.562, |
| "step": 324 |
| }, |
| { |
| "epoch": 12.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 325 |
| }, |
| { |
| "epoch": 12.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0055, |
| "step": 326 |
| }, |
| { |
| "epoch": 12.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0005, |
| "step": 327 |
| }, |
| { |
| "epoch": 12.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 328 |
| }, |
| { |
| "epoch": 12.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0066, |
| "step": 329 |
| }, |
| { |
| "epoch": 12.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0162, |
| "step": 330 |
| }, |
| { |
| "epoch": 12.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 331 |
| }, |
| { |
| "epoch": 12.3, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 332 |
| }, |
| { |
| "epoch": 12.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 333 |
| }, |
| { |
| "epoch": 12.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 334 |
| }, |
| { |
| "epoch": 12.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0032, |
| "step": 335 |
| }, |
| { |
| "epoch": 12.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0065, |
| "step": 336 |
| }, |
| { |
| "epoch": 12.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 337 |
| }, |
| { |
| "epoch": 12.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0015, |
| "step": 338 |
| }, |
| { |
| "epoch": 12.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 339 |
| }, |
| { |
| "epoch": 12.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0042, |
| "step": 340 |
| }, |
| { |
| "epoch": 12.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0148, |
| "step": 341 |
| }, |
| { |
| "epoch": 12.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 342 |
| }, |
| { |
| "epoch": 12.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0017, |
| "step": 343 |
| }, |
| { |
| "epoch": 12.74, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 344 |
| }, |
| { |
| "epoch": 12.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0055, |
| "step": 345 |
| }, |
| { |
| "epoch": 12.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0019, |
| "step": 346 |
| }, |
| { |
| "epoch": 12.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0033, |
| "step": 347 |
| }, |
| { |
| "epoch": 12.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0127, |
| "step": 348 |
| }, |
| { |
| "epoch": 12.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0103, |
| "step": 349 |
| }, |
| { |
| "epoch": 12.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 350 |
| }, |
| { |
| "epoch": 13.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0111, |
| "step": 351 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 0.007907378487288952, |
| "eval_runtime": 48.1829, |
| "eval_samples_per_second": 8.821, |
| "eval_steps_per_second": 0.56, |
| "step": 351 |
| }, |
| { |
| "epoch": 13.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0073, |
| "step": 352 |
| }, |
| { |
| "epoch": 13.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0106, |
| "step": 353 |
| }, |
| { |
| "epoch": 13.11, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 354 |
| }, |
| { |
| "epoch": 13.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0064, |
| "step": 355 |
| }, |
| { |
| "epoch": 13.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0138, |
| "step": 356 |
| }, |
| { |
| "epoch": 13.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0133, |
| "step": 357 |
| }, |
| { |
| "epoch": 13.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0236, |
| "step": 358 |
| }, |
| { |
| "epoch": 13.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0108, |
| "step": 359 |
| }, |
| { |
| "epoch": 13.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0093, |
| "step": 360 |
| }, |
| { |
| "epoch": 13.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0107, |
| "step": 361 |
| }, |
| { |
| "epoch": 13.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 362 |
| }, |
| { |
| "epoch": 13.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0143, |
| "step": 363 |
| }, |
| { |
| "epoch": 13.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 364 |
| }, |
| { |
| "epoch": 13.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0051, |
| "step": 365 |
| }, |
| { |
| "epoch": 13.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0124, |
| "step": 366 |
| }, |
| { |
| "epoch": 13.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0075, |
| "step": 367 |
| }, |
| { |
| "epoch": 13.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 368 |
| }, |
| { |
| "epoch": 13.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0051, |
| "step": 369 |
| }, |
| { |
| "epoch": 13.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0111, |
| "step": 370 |
| }, |
| { |
| "epoch": 13.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0107, |
| "step": 371 |
| }, |
| { |
| "epoch": 13.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 372 |
| }, |
| { |
| "epoch": 13.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0079, |
| "step": 373 |
| }, |
| { |
| "epoch": 13.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0115, |
| "step": 374 |
| }, |
| { |
| "epoch": 13.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 375 |
| }, |
| { |
| "epoch": 13.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 376 |
| }, |
| { |
| "epoch": 13.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0044, |
| "step": 377 |
| }, |
| { |
| "epoch": 14.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0097, |
| "step": 378 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.00604825746268034, |
| "eval_runtime": 48.0832, |
| "eval_samples_per_second": 8.839, |
| "eval_steps_per_second": 0.562, |
| "step": 378 |
| }, |
| { |
| "epoch": 14.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0084, |
| "step": 379 |
| }, |
| { |
| "epoch": 14.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0086, |
| "step": 380 |
| }, |
| { |
| "epoch": 14.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0022, |
| "step": 381 |
| }, |
| { |
| "epoch": 14.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 382 |
| }, |
| { |
| "epoch": 14.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 383 |
| }, |
| { |
| "epoch": 14.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0139, |
| "step": 384 |
| }, |
| { |
| "epoch": 14.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 385 |
| }, |
| { |
| "epoch": 14.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0084, |
| "step": 386 |
| }, |
| { |
| "epoch": 14.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0062, |
| "step": 387 |
| }, |
| { |
| "epoch": 14.37, |
| "learning_rate": 0.0002, |
| "loss": 0.008, |
| "step": 388 |
| }, |
| { |
| "epoch": 14.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 389 |
| }, |
| { |
| "epoch": 14.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0096, |
| "step": 390 |
| }, |
| { |
| "epoch": 14.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 391 |
| }, |
| { |
| "epoch": 14.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0031, |
| "step": 392 |
| }, |
| { |
| "epoch": 14.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 393 |
| }, |
| { |
| "epoch": 14.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0041, |
| "step": 394 |
| }, |
| { |
| "epoch": 14.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 395 |
| }, |
| { |
| "epoch": 14.67, |
| "learning_rate": 0.0002, |
| "loss": 0.016, |
| "step": 396 |
| }, |
| { |
| "epoch": 14.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0018, |
| "step": 397 |
| }, |
| { |
| "epoch": 14.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0176, |
| "step": 398 |
| }, |
| { |
| "epoch": 14.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0144, |
| "step": 399 |
| }, |
| { |
| "epoch": 14.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0118, |
| "step": 400 |
| }, |
| { |
| "epoch": 14.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0163, |
| "step": 401 |
| }, |
| { |
| "epoch": 14.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0111, |
| "step": 402 |
| }, |
| { |
| "epoch": 14.93, |
| "learning_rate": 0.0002, |
| "loss": 0.008, |
| "step": 403 |
| }, |
| { |
| "epoch": 14.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0204, |
| "step": 404 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0332, |
| "step": 405 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 0.011913908645510674, |
| "eval_runtime": 48.0366, |
| "eval_samples_per_second": 8.847, |
| "eval_steps_per_second": 0.562, |
| "step": 405 |
| }, |
| { |
| "epoch": 15.04, |
| "learning_rate": 0.0002, |
| "loss": 0.007, |
| "step": 406 |
| }, |
| { |
| "epoch": 15.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0103, |
| "step": 407 |
| }, |
| { |
| "epoch": 15.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0086, |
| "step": 408 |
| }, |
| { |
| "epoch": 15.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0121, |
| "step": 409 |
| }, |
| { |
| "epoch": 15.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0143, |
| "step": 410 |
| }, |
| { |
| "epoch": 15.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0104, |
| "step": 411 |
| }, |
| { |
| "epoch": 15.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0118, |
| "step": 412 |
| }, |
| { |
| "epoch": 15.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0096, |
| "step": 413 |
| }, |
| { |
| "epoch": 15.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0113, |
| "step": 414 |
| }, |
| { |
| "epoch": 15.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0095, |
| "step": 415 |
| }, |
| { |
| "epoch": 15.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0105, |
| "step": 416 |
| }, |
| { |
| "epoch": 15.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0151, |
| "step": 417 |
| }, |
| { |
| "epoch": 15.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0112, |
| "step": 418 |
| }, |
| { |
| "epoch": 15.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0113, |
| "step": 419 |
| }, |
| { |
| "epoch": 15.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0201, |
| "step": 420 |
| }, |
| { |
| "epoch": 15.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0101, |
| "step": 421 |
| }, |
| { |
| "epoch": 15.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0116, |
| "step": 422 |
| }, |
| { |
| "epoch": 15.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0231, |
| "step": 423 |
| }, |
| { |
| "epoch": 15.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0138, |
| "step": 424 |
| }, |
| { |
| "epoch": 15.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0043, |
| "step": 425 |
| }, |
| { |
| "epoch": 15.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0105, |
| "step": 426 |
| }, |
| { |
| "epoch": 15.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0082, |
| "step": 427 |
| }, |
| { |
| "epoch": 15.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0105, |
| "step": 428 |
| }, |
| { |
| "epoch": 15.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0218, |
| "step": 429 |
| }, |
| { |
| "epoch": 15.93, |
| "learning_rate": 0.0002, |
| "loss": 0.012, |
| "step": 430 |
| }, |
| { |
| "epoch": 15.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 431 |
| }, |
| { |
| "epoch": 16.0, |
| "learning_rate": 0.0002, |
| "loss": 0.012, |
| "step": 432 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.0072858938947319984, |
| "eval_runtime": 48.0428, |
| "eval_samples_per_second": 8.846, |
| "eval_steps_per_second": 0.562, |
| "step": 432 |
| }, |
| { |
| "epoch": 16.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0098, |
| "step": 433 |
| }, |
| { |
| "epoch": 16.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 434 |
| }, |
| { |
| "epoch": 16.11, |
| "learning_rate": 0.0002, |
| "loss": 0.008, |
| "step": 435 |
| }, |
| { |
| "epoch": 16.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 436 |
| }, |
| { |
| "epoch": 16.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0229, |
| "step": 437 |
| }, |
| { |
| "epoch": 16.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 438 |
| }, |
| { |
| "epoch": 16.26, |
| "learning_rate": 0.0002, |
| "loss": 0.003, |
| "step": 439 |
| }, |
| { |
| "epoch": 16.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0169, |
| "step": 440 |
| }, |
| { |
| "epoch": 16.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 441 |
| }, |
| { |
| "epoch": 16.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 442 |
| }, |
| { |
| "epoch": 16.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0176, |
| "step": 443 |
| }, |
| { |
| "epoch": 16.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 444 |
| }, |
| { |
| "epoch": 16.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0116, |
| "step": 445 |
| }, |
| { |
| "epoch": 16.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 446 |
| }, |
| { |
| "epoch": 16.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0186, |
| "step": 447 |
| }, |
| { |
| "epoch": 16.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 448 |
| }, |
| { |
| "epoch": 16.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0125, |
| "step": 449 |
| }, |
| { |
| "epoch": 16.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0075, |
| "step": 450 |
| }, |
| { |
| "epoch": 16.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 451 |
| }, |
| { |
| "epoch": 16.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0084, |
| "step": 452 |
| }, |
| { |
| "epoch": 16.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0122, |
| "step": 453 |
| }, |
| { |
| "epoch": 16.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0076, |
| "step": 454 |
| }, |
| { |
| "epoch": 16.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0163, |
| "step": 455 |
| }, |
| { |
| "epoch": 16.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0155, |
| "step": 456 |
| }, |
| { |
| "epoch": 16.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0016, |
| "step": 457 |
| }, |
| { |
| "epoch": 16.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0163, |
| "step": 458 |
| }, |
| { |
| "epoch": 17.0, |
| "learning_rate": 0.0002, |
| "loss": 0.003, |
| "step": 459 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 0.006067308597266674, |
| "eval_runtime": 48.1545, |
| "eval_samples_per_second": 8.826, |
| "eval_steps_per_second": 0.561, |
| "step": 459 |
| }, |
| { |
| "epoch": 17.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0013, |
| "step": 460 |
| }, |
| { |
| "epoch": 17.07, |
| "learning_rate": 0.0002, |
| "loss": 0.022, |
| "step": 461 |
| }, |
| { |
| "epoch": 17.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0101, |
| "step": 462 |
| }, |
| { |
| "epoch": 17.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0052, |
| "step": 463 |
| }, |
| { |
| "epoch": 17.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0367, |
| "step": 464 |
| }, |
| { |
| "epoch": 17.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 465 |
| }, |
| { |
| "epoch": 17.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0082, |
| "step": 466 |
| }, |
| { |
| "epoch": 17.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0037, |
| "step": 467 |
| }, |
| { |
| "epoch": 17.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 468 |
| }, |
| { |
| "epoch": 17.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 469 |
| }, |
| { |
| "epoch": 17.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 470 |
| }, |
| { |
| "epoch": 17.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0042, |
| "step": 471 |
| }, |
| { |
| "epoch": 17.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0181, |
| "step": 472 |
| }, |
| { |
| "epoch": 17.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0065, |
| "step": 473 |
| }, |
| { |
| "epoch": 17.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 474 |
| }, |
| { |
| "epoch": 17.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0057, |
| "step": 475 |
| }, |
| { |
| "epoch": 17.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0055, |
| "step": 476 |
| }, |
| { |
| "epoch": 17.67, |
| "learning_rate": 0.0002, |
| "loss": 0.008, |
| "step": 477 |
| }, |
| { |
| "epoch": 17.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0123, |
| "step": 478 |
| }, |
| { |
| "epoch": 17.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 479 |
| }, |
| { |
| "epoch": 17.78, |
| "learning_rate": 0.0002, |
| "loss": 0.019, |
| "step": 480 |
| }, |
| { |
| "epoch": 17.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0143, |
| "step": 481 |
| }, |
| { |
| "epoch": 17.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0227, |
| "step": 482 |
| }, |
| { |
| "epoch": 17.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0141, |
| "step": 483 |
| }, |
| { |
| "epoch": 17.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0121, |
| "step": 484 |
| }, |
| { |
| "epoch": 17.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0151, |
| "step": 485 |
| }, |
| { |
| "epoch": 18.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 486 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.01013600081205368, |
| "eval_runtime": 48.1592, |
| "eval_samples_per_second": 8.825, |
| "eval_steps_per_second": 0.561, |
| "step": 486 |
| }, |
| { |
| "epoch": 18.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0084, |
| "step": 487 |
| }, |
| { |
| "epoch": 18.07, |
| "learning_rate": 0.0002, |
| "loss": 0.0107, |
| "step": 488 |
| }, |
| { |
| "epoch": 18.11, |
| "learning_rate": 0.0002, |
| "loss": 0.0296, |
| "step": 489 |
| }, |
| { |
| "epoch": 18.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 490 |
| }, |
| { |
| "epoch": 18.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0111, |
| "step": 491 |
| }, |
| { |
| "epoch": 18.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 492 |
| }, |
| { |
| "epoch": 18.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0053, |
| "step": 493 |
| }, |
| { |
| "epoch": 18.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0082, |
| "step": 494 |
| }, |
| { |
| "epoch": 18.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0134, |
| "step": 495 |
| }, |
| { |
| "epoch": 18.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 496 |
| }, |
| { |
| "epoch": 18.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0213, |
| "step": 497 |
| }, |
| { |
| "epoch": 18.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0091, |
| "step": 498 |
| }, |
| { |
| "epoch": 18.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0046, |
| "step": 499 |
| }, |
| { |
| "epoch": 18.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0186, |
| "step": 500 |
| }, |
| { |
| "epoch": 18.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0156, |
| "step": 501 |
| }, |
| { |
| "epoch": 18.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0115, |
| "step": 502 |
| }, |
| { |
| "epoch": 18.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0091, |
| "step": 503 |
| }, |
| { |
| "epoch": 18.67, |
| "learning_rate": 0.0002, |
| "loss": 0.0088, |
| "step": 504 |
| }, |
| { |
| "epoch": 18.7, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 505 |
| }, |
| { |
| "epoch": 18.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0171, |
| "step": 506 |
| }, |
| { |
| "epoch": 18.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 507 |
| }, |
| { |
| "epoch": 18.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0172, |
| "step": 508 |
| }, |
| { |
| "epoch": 18.85, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 509 |
| }, |
| { |
| "epoch": 18.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0067, |
| "step": 510 |
| }, |
| { |
| "epoch": 18.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0192, |
| "step": 511 |
| }, |
| { |
| "epoch": 18.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0118, |
| "step": 512 |
| }, |
| { |
| "epoch": 19.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0092, |
| "step": 513 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 0.00668308325111866, |
| "eval_runtime": 48.0025, |
| "eval_samples_per_second": 8.854, |
| "eval_steps_per_second": 0.562, |
| "step": 513 |
| }, |
| { |
| "epoch": 19.04, |
| "learning_rate": 0.0002, |
| "loss": 0.0055, |
| "step": 514 |
| }, |
| { |
| "epoch": 19.07, |
| "learning_rate": 0.0002, |
| "loss": 0.006, |
| "step": 515 |
| }, |
| { |
| "epoch": 19.11, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 516 |
| }, |
| { |
| "epoch": 19.15, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 517 |
| }, |
| { |
| "epoch": 19.19, |
| "learning_rate": 0.0002, |
| "loss": 0.0036, |
| "step": 518 |
| }, |
| { |
| "epoch": 19.22, |
| "learning_rate": 0.0002, |
| "loss": 0.0119, |
| "step": 519 |
| }, |
| { |
| "epoch": 19.26, |
| "learning_rate": 0.0002, |
| "loss": 0.0084, |
| "step": 520 |
| }, |
| { |
| "epoch": 19.3, |
| "learning_rate": 0.0002, |
| "loss": 0.0057, |
| "step": 521 |
| }, |
| { |
| "epoch": 19.33, |
| "learning_rate": 0.0002, |
| "loss": 0.0181, |
| "step": 522 |
| }, |
| { |
| "epoch": 19.37, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 523 |
| }, |
| { |
| "epoch": 19.41, |
| "learning_rate": 0.0002, |
| "loss": 0.0024, |
| "step": 524 |
| }, |
| { |
| "epoch": 19.44, |
| "learning_rate": 0.0002, |
| "loss": 0.0157, |
| "step": 525 |
| }, |
| { |
| "epoch": 19.48, |
| "learning_rate": 0.0002, |
| "loss": 0.0095, |
| "step": 526 |
| }, |
| { |
| "epoch": 19.52, |
| "learning_rate": 0.0002, |
| "loss": 0.0217, |
| "step": 527 |
| }, |
| { |
| "epoch": 19.56, |
| "learning_rate": 0.0002, |
| "loss": 0.0142, |
| "step": 528 |
| }, |
| { |
| "epoch": 19.59, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 529 |
| }, |
| { |
| "epoch": 19.63, |
| "learning_rate": 0.0002, |
| "loss": 0.0099, |
| "step": 530 |
| }, |
| { |
| "epoch": 19.67, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 531 |
| }, |
| { |
| "epoch": 19.7, |
| "learning_rate": 0.0002, |
| "loss": 0.008, |
| "step": 532 |
| }, |
| { |
| "epoch": 19.74, |
| "learning_rate": 0.0002, |
| "loss": 0.0027, |
| "step": 533 |
| }, |
| { |
| "epoch": 19.78, |
| "learning_rate": 0.0002, |
| "loss": 0.0141, |
| "step": 534 |
| }, |
| { |
| "epoch": 19.81, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 535 |
| }, |
| { |
| "epoch": 19.85, |
| "learning_rate": 0.0002, |
| "loss": 0.005, |
| "step": 536 |
| }, |
| { |
| "epoch": 19.89, |
| "learning_rate": 0.0002, |
| "loss": 0.0112, |
| "step": 537 |
| }, |
| { |
| "epoch": 19.93, |
| "learning_rate": 0.0002, |
| "loss": 0.0039, |
| "step": 538 |
| }, |
| { |
| "epoch": 19.96, |
| "learning_rate": 0.0002, |
| "loss": 0.0176, |
| "step": 539 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 0.0002, |
| "loss": 0.0026, |
| "step": 540 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.007353875320404768, |
| "eval_runtime": 48.0165, |
| "eval_samples_per_second": 8.851, |
| "eval_steps_per_second": 0.562, |
| "step": 540 |
| }, |
| { |
| "epoch": 20.0, |
| "step": 540, |
| "total_flos": 8.164299192349491e+17, |
| "train_loss": 0.04922065762948478, |
| "train_runtime": 6513.5085, |
| "train_samples_per_second": 1.305, |
| "train_steps_per_second": 0.083 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 540, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 50000, |
| "total_flos": 8.164299192349491e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
