{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.9990726429675425, | |
"eval_steps": 500, | |
"global_step": 404, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.0, | |
"learning_rate": 0.0003, | |
"loss": 1.7184, | |
"step": 1 | |
}, | |
{ | |
"epoch": 0.0, | |
"learning_rate": 0.0003, | |
"loss": 1.6242, | |
"step": 2 | |
}, | |
{ | |
"epoch": 0.01, | |
"learning_rate": 0.0003, | |
"loss": 1.7006, | |
"step": 3 | |
}, | |
{ | |
"epoch": 0.01, | |
"learning_rate": 0.0003, | |
"loss": 1.7697, | |
"step": 4 | |
}, | |
{ | |
"epoch": 0.01, | |
"learning_rate": 0.0003, | |
"loss": 1.6528, | |
"step": 5 | |
}, | |
{ | |
"epoch": 0.01, | |
"learning_rate": 0.0003, | |
"loss": 1.6636, | |
"step": 6 | |
}, | |
{ | |
"epoch": 0.02, | |
"learning_rate": 0.0003, | |
"loss": 1.6225, | |
"step": 7 | |
}, | |
{ | |
"epoch": 0.02, | |
"learning_rate": 0.0003, | |
"loss": 1.6799, | |
"step": 8 | |
}, | |
{ | |
"epoch": 0.02, | |
"learning_rate": 0.0003, | |
"loss": 1.6725, | |
"step": 9 | |
}, | |
{ | |
"epoch": 0.02, | |
"learning_rate": 0.0003, | |
"loss": 1.552, | |
"step": 10 | |
}, | |
{ | |
"epoch": 0.03, | |
"learning_rate": 0.0003, | |
"loss": 1.5227, | |
"step": 11 | |
}, | |
{ | |
"epoch": 0.03, | |
"learning_rate": 0.0003, | |
"loss": 1.4236, | |
"step": 12 | |
}, | |
{ | |
"epoch": 0.03, | |
"learning_rate": 0.0003, | |
"loss": 1.3809, | |
"step": 13 | |
}, | |
{ | |
"epoch": 0.03, | |
"learning_rate": 0.0003, | |
"loss": 1.3746, | |
"step": 14 | |
}, | |
{ | |
"epoch": 0.04, | |
"learning_rate": 0.0003, | |
"loss": 1.3449, | |
"step": 15 | |
}, | |
{ | |
"epoch": 0.04, | |
"learning_rate": 0.0003, | |
"loss": 1.2441, | |
"step": 16 | |
}, | |
{ | |
"epoch": 0.04, | |
"learning_rate": 0.0003, | |
"loss": 1.1681, | |
"step": 17 | |
}, | |
{ | |
"epoch": 0.04, | |
"learning_rate": 0.0003, | |
"loss": 1.2103, | |
"step": 18 | |
}, | |
{ | |
"epoch": 0.05, | |
"learning_rate": 0.0003, | |
"loss": 1.2124, | |
"step": 19 | |
}, | |
{ | |
"epoch": 0.05, | |
"learning_rate": 0.0003, | |
"loss": 1.1958, | |
"step": 20 | |
}, | |
{ | |
"epoch": 0.05, | |
"learning_rate": 0.0003, | |
"loss": 1.1211, | |
"step": 21 | |
}, | |
{ | |
"epoch": 0.05, | |
"learning_rate": 0.0003, | |
"loss": 1.1484, | |
"step": 22 | |
}, | |
{ | |
"epoch": 0.06, | |
"learning_rate": 0.0003, | |
"loss": 1.1299, | |
"step": 23 | |
}, | |
{ | |
"epoch": 0.06, | |
"learning_rate": 0.0003, | |
"loss": 1.0587, | |
"step": 24 | |
}, | |
{ | |
"epoch": 0.06, | |
"learning_rate": 0.0003, | |
"loss": 1.0198, | |
"step": 25 | |
}, | |
{ | |
"epoch": 0.06, | |
"learning_rate": 0.0003, | |
"loss": 1.007, | |
"step": 26 | |
}, | |
{ | |
"epoch": 0.07, | |
"learning_rate": 0.0003, | |
"loss": 1.0815, | |
"step": 27 | |
}, | |
{ | |
"epoch": 0.07, | |
"learning_rate": 0.0003, | |
"loss": 1.0145, | |
"step": 28 | |
}, | |
{ | |
"epoch": 0.07, | |
"learning_rate": 0.0003, | |
"loss": 1.0089, | |
"step": 29 | |
}, | |
{ | |
"epoch": 0.07, | |
"learning_rate": 0.0003, | |
"loss": 0.9865, | |
"step": 30 | |
}, | |
{ | |
"epoch": 0.08, | |
"learning_rate": 0.0003, | |
"loss": 0.9924, | |
"step": 31 | |
}, | |
{ | |
"epoch": 0.08, | |
"learning_rate": 0.0003, | |
"loss": 1.0034, | |
"step": 32 | |
}, | |
{ | |
"epoch": 0.08, | |
"learning_rate": 0.0003, | |
"loss": 0.9772, | |
"step": 33 | |
}, | |
{ | |
"epoch": 0.08, | |
"learning_rate": 0.0003, | |
"loss": 1.0055, | |
"step": 34 | |
}, | |
{ | |
"epoch": 0.09, | |
"learning_rate": 0.0003, | |
"loss": 0.9489, | |
"step": 35 | |
}, | |
{ | |
"epoch": 0.09, | |
"learning_rate": 0.0003, | |
"loss": 0.9731, | |
"step": 36 | |
}, | |
{ | |
"epoch": 0.09, | |
"learning_rate": 0.0003, | |
"loss": 0.9487, | |
"step": 37 | |
}, | |
{ | |
"epoch": 0.09, | |
"learning_rate": 0.0003, | |
"loss": 0.9429, | |
"step": 38 | |
}, | |
{ | |
"epoch": 0.1, | |
"learning_rate": 0.0003, | |
"loss": 0.9552, | |
"step": 39 | |
}, | |
{ | |
"epoch": 0.1, | |
"learning_rate": 0.0003, | |
"loss": 0.9253, | |
"step": 40 | |
}, | |
{ | |
"epoch": 0.1, | |
"learning_rate": 0.0003, | |
"loss": 0.9705, | |
"step": 41 | |
}, | |
{ | |
"epoch": 0.1, | |
"learning_rate": 0.0003, | |
"loss": 0.9383, | |
"step": 42 | |
}, | |
{ | |
"epoch": 0.11, | |
"learning_rate": 0.0003, | |
"loss": 0.9394, | |
"step": 43 | |
}, | |
{ | |
"epoch": 0.11, | |
"learning_rate": 0.0003, | |
"loss": 0.9348, | |
"step": 44 | |
}, | |
{ | |
"epoch": 0.11, | |
"learning_rate": 0.0003, | |
"loss": 0.9268, | |
"step": 45 | |
}, | |
{ | |
"epoch": 0.11, | |
"learning_rate": 0.0003, | |
"loss": 0.9618, | |
"step": 46 | |
}, | |
{ | |
"epoch": 0.12, | |
"learning_rate": 0.0003, | |
"loss": 0.9302, | |
"step": 47 | |
}, | |
{ | |
"epoch": 0.12, | |
"learning_rate": 0.0003, | |
"loss": 0.936, | |
"step": 48 | |
}, | |
{ | |
"epoch": 0.12, | |
"learning_rate": 0.0003, | |
"loss": 0.9258, | |
"step": 49 | |
}, | |
{ | |
"epoch": 0.12, | |
"learning_rate": 0.0003, | |
"loss": 0.9676, | |
"step": 50 | |
}, | |
{ | |
"epoch": 0.13, | |
"learning_rate": 0.0003, | |
"loss": 0.9002, | |
"step": 51 | |
}, | |
{ | |
"epoch": 0.13, | |
"learning_rate": 0.0003, | |
"loss": 0.9183, | |
"step": 52 | |
}, | |
{ | |
"epoch": 0.13, | |
"learning_rate": 0.0003, | |
"loss": 0.9177, | |
"step": 53 | |
}, | |
{ | |
"epoch": 0.13, | |
"learning_rate": 0.0003, | |
"loss": 0.9172, | |
"step": 54 | |
}, | |
{ | |
"epoch": 0.14, | |
"learning_rate": 0.0003, | |
"loss": 0.93, | |
"step": 55 | |
}, | |
{ | |
"epoch": 0.14, | |
"learning_rate": 0.0003, | |
"loss": 0.9294, | |
"step": 56 | |
}, | |
{ | |
"epoch": 0.14, | |
"learning_rate": 0.0003, | |
"loss": 0.9779, | |
"step": 57 | |
}, | |
{ | |
"epoch": 0.14, | |
"learning_rate": 0.0003, | |
"loss": 0.9128, | |
"step": 58 | |
}, | |
{ | |
"epoch": 0.15, | |
"learning_rate": 0.0003, | |
"loss": 0.9028, | |
"step": 59 | |
}, | |
{ | |
"epoch": 0.15, | |
"learning_rate": 0.0003, | |
"loss": 0.9244, | |
"step": 60 | |
}, | |
{ | |
"epoch": 0.15, | |
"learning_rate": 0.0003, | |
"loss": 0.9246, | |
"step": 61 | |
}, | |
{ | |
"epoch": 0.15, | |
"learning_rate": 0.0003, | |
"loss": 0.9252, | |
"step": 62 | |
}, | |
{ | |
"epoch": 0.16, | |
"learning_rate": 0.0003, | |
"loss": 0.9146, | |
"step": 63 | |
}, | |
{ | |
"epoch": 0.16, | |
"learning_rate": 0.0003, | |
"loss": 0.921, | |
"step": 64 | |
}, | |
{ | |
"epoch": 0.16, | |
"learning_rate": 0.0003, | |
"loss": 0.9297, | |
"step": 65 | |
}, | |
{ | |
"epoch": 0.16, | |
"learning_rate": 0.0003, | |
"loss": 0.9131, | |
"step": 66 | |
}, | |
{ | |
"epoch": 0.17, | |
"learning_rate": 0.0003, | |
"loss": 0.9308, | |
"step": 67 | |
}, | |
{ | |
"epoch": 0.17, | |
"learning_rate": 0.0003, | |
"loss": 0.9748, | |
"step": 68 | |
}, | |
{ | |
"epoch": 0.17, | |
"learning_rate": 0.0003, | |
"loss": 0.9015, | |
"step": 69 | |
}, | |
{ | |
"epoch": 0.17, | |
"learning_rate": 0.0003, | |
"loss": 0.9371, | |
"step": 70 | |
}, | |
{ | |
"epoch": 0.18, | |
"learning_rate": 0.0003, | |
"loss": 0.9315, | |
"step": 71 | |
}, | |
{ | |
"epoch": 0.18, | |
"learning_rate": 0.0003, | |
"loss": 0.8673, | |
"step": 72 | |
}, | |
{ | |
"epoch": 0.18, | |
"learning_rate": 0.0003, | |
"loss": 0.9251, | |
"step": 73 | |
}, | |
{ | |
"epoch": 0.18, | |
"learning_rate": 0.0003, | |
"loss": 0.9253, | |
"step": 74 | |
}, | |
{ | |
"epoch": 0.19, | |
"learning_rate": 0.0003, | |
"loss": 0.932, | |
"step": 75 | |
}, | |
{ | |
"epoch": 0.19, | |
"learning_rate": 0.0003, | |
"loss": 0.9164, | |
"step": 76 | |
}, | |
{ | |
"epoch": 0.19, | |
"learning_rate": 0.0003, | |
"loss": 0.9252, | |
"step": 77 | |
}, | |
{ | |
"epoch": 0.19, | |
"learning_rate": 0.0003, | |
"loss": 0.9238, | |
"step": 78 | |
}, | |
{ | |
"epoch": 0.2, | |
"learning_rate": 0.0003, | |
"loss": 0.905, | |
"step": 79 | |
}, | |
{ | |
"epoch": 0.2, | |
"learning_rate": 0.0003, | |
"loss": 0.9107, | |
"step": 80 | |
}, | |
{ | |
"epoch": 0.2, | |
"learning_rate": 0.0003, | |
"loss": 0.873, | |
"step": 81 | |
}, | |
{ | |
"epoch": 0.2, | |
"learning_rate": 0.0003, | |
"loss": 0.9245, | |
"step": 82 | |
}, | |
{ | |
"epoch": 0.21, | |
"learning_rate": 0.0003, | |
"loss": 0.9165, | |
"step": 83 | |
}, | |
{ | |
"epoch": 0.21, | |
"learning_rate": 0.0003, | |
"loss": 0.9109, | |
"step": 84 | |
}, | |
{ | |
"epoch": 0.21, | |
"learning_rate": 0.0003, | |
"loss": 0.9053, | |
"step": 85 | |
}, | |
{ | |
"epoch": 0.21, | |
"learning_rate": 0.0003, | |
"loss": 0.9254, | |
"step": 86 | |
}, | |
{ | |
"epoch": 0.22, | |
"learning_rate": 0.0003, | |
"loss": 0.9015, | |
"step": 87 | |
}, | |
{ | |
"epoch": 0.22, | |
"learning_rate": 0.0003, | |
"loss": 0.9319, | |
"step": 88 | |
}, | |
{ | |
"epoch": 0.22, | |
"learning_rate": 0.0003, | |
"loss": 0.9205, | |
"step": 89 | |
}, | |
{ | |
"epoch": 0.22, | |
"learning_rate": 0.0003, | |
"loss": 0.919, | |
"step": 90 | |
}, | |
{ | |
"epoch": 0.23, | |
"learning_rate": 0.0003, | |
"loss": 0.8942, | |
"step": 91 | |
}, | |
{ | |
"epoch": 0.23, | |
"learning_rate": 0.0003, | |
"loss": 0.92, | |
"step": 92 | |
}, | |
{ | |
"epoch": 0.23, | |
"learning_rate": 0.0003, | |
"loss": 0.9456, | |
"step": 93 | |
}, | |
{ | |
"epoch": 0.23, | |
"learning_rate": 0.0003, | |
"loss": 0.9066, | |
"step": 94 | |
}, | |
{ | |
"epoch": 0.23, | |
"learning_rate": 0.0003, | |
"loss": 0.9041, | |
"step": 95 | |
}, | |
{ | |
"epoch": 0.24, | |
"learning_rate": 0.0003, | |
"loss": 0.9121, | |
"step": 96 | |
}, | |
{ | |
"epoch": 0.24, | |
"learning_rate": 0.0003, | |
"loss": 0.9156, | |
"step": 97 | |
}, | |
{ | |
"epoch": 0.24, | |
"learning_rate": 0.0003, | |
"loss": 0.899, | |
"step": 98 | |
}, | |
{ | |
"epoch": 0.24, | |
"learning_rate": 0.0003, | |
"loss": 0.9414, | |
"step": 99 | |
}, | |
{ | |
"epoch": 0.25, | |
"learning_rate": 0.0003, | |
"loss": 0.92, | |
"step": 100 | |
}, | |
{ | |
"epoch": 0.25, | |
"learning_rate": 0.0003, | |
"loss": 0.9251, | |
"step": 101 | |
}, | |
{ | |
"epoch": 0.25, | |
"learning_rate": 0.0003, | |
"loss": 0.8706, | |
"step": 102 | |
}, | |
{ | |
"epoch": 0.25, | |
"learning_rate": 0.0003, | |
"loss": 0.8911, | |
"step": 103 | |
}, | |
{ | |
"epoch": 0.26, | |
"learning_rate": 0.0003, | |
"loss": 0.9159, | |
"step": 104 | |
}, | |
{ | |
"epoch": 0.26, | |
"learning_rate": 0.0003, | |
"loss": 0.9095, | |
"step": 105 | |
}, | |
{ | |
"epoch": 0.26, | |
"learning_rate": 0.0003, | |
"loss": 0.9275, | |
"step": 106 | |
}, | |
{ | |
"epoch": 0.26, | |
"learning_rate": 0.0003, | |
"loss": 0.9225, | |
"step": 107 | |
}, | |
{ | |
"epoch": 0.27, | |
"learning_rate": 0.0003, | |
"loss": 0.9248, | |
"step": 108 | |
}, | |
{ | |
"epoch": 0.27, | |
"learning_rate": 0.0003, | |
"loss": 0.8902, | |
"step": 109 | |
}, | |
{ | |
"epoch": 0.27, | |
"learning_rate": 0.0003, | |
"loss": 0.8971, | |
"step": 110 | |
}, | |
{ | |
"epoch": 0.27, | |
"learning_rate": 0.0003, | |
"loss": 0.9236, | |
"step": 111 | |
}, | |
{ | |
"epoch": 0.28, | |
"learning_rate": 0.0003, | |
"loss": 0.9325, | |
"step": 112 | |
}, | |
{ | |
"epoch": 0.28, | |
"learning_rate": 0.0003, | |
"loss": 0.9097, | |
"step": 113 | |
}, | |
{ | |
"epoch": 0.28, | |
"learning_rate": 0.0003, | |
"loss": 0.8829, | |
"step": 114 | |
}, | |
{ | |
"epoch": 0.28, | |
"learning_rate": 0.0003, | |
"loss": 0.8532, | |
"step": 115 | |
}, | |
{ | |
"epoch": 0.29, | |
"learning_rate": 0.0003, | |
"loss": 0.9136, | |
"step": 116 | |
}, | |
{ | |
"epoch": 0.29, | |
"learning_rate": 0.0003, | |
"loss": 0.8688, | |
"step": 117 | |
}, | |
{ | |
"epoch": 0.29, | |
"learning_rate": 0.0003, | |
"loss": 0.9104, | |
"step": 118 | |
}, | |
{ | |
"epoch": 0.29, | |
"learning_rate": 0.0003, | |
"loss": 0.9034, | |
"step": 119 | |
}, | |
{ | |
"epoch": 0.3, | |
"learning_rate": 0.0003, | |
"loss": 0.9262, | |
"step": 120 | |
}, | |
{ | |
"epoch": 0.3, | |
"learning_rate": 0.0003, | |
"loss": 0.903, | |
"step": 121 | |
}, | |
{ | |
"epoch": 0.3, | |
"learning_rate": 0.0003, | |
"loss": 0.8986, | |
"step": 122 | |
}, | |
{ | |
"epoch": 0.3, | |
"learning_rate": 0.0003, | |
"loss": 0.9269, | |
"step": 123 | |
}, | |
{ | |
"epoch": 0.31, | |
"learning_rate": 0.0003, | |
"loss": 0.8902, | |
"step": 124 | |
}, | |
{ | |
"epoch": 0.31, | |
"learning_rate": 0.0003, | |
"loss": 0.9177, | |
"step": 125 | |
}, | |
{ | |
"epoch": 0.31, | |
"learning_rate": 0.0003, | |
"loss": 0.9291, | |
"step": 126 | |
}, | |
{ | |
"epoch": 0.31, | |
"learning_rate": 0.0003, | |
"loss": 0.8834, | |
"step": 127 | |
}, | |
{ | |
"epoch": 0.32, | |
"learning_rate": 0.0003, | |
"loss": 0.893, | |
"step": 128 | |
}, | |
{ | |
"epoch": 0.32, | |
"learning_rate": 0.0003, | |
"loss": 0.8991, | |
"step": 129 | |
}, | |
{ | |
"epoch": 0.32, | |
"learning_rate": 0.0003, | |
"loss": 0.8875, | |
"step": 130 | |
}, | |
{ | |
"epoch": 0.32, | |
"learning_rate": 0.0003, | |
"loss": 0.9592, | |
"step": 131 | |
}, | |
{ | |
"epoch": 0.33, | |
"learning_rate": 0.0003, | |
"loss": 0.936, | |
"step": 132 | |
}, | |
{ | |
"epoch": 0.33, | |
"learning_rate": 0.0003, | |
"loss": 0.8701, | |
"step": 133 | |
}, | |
{ | |
"epoch": 0.33, | |
"learning_rate": 0.0003, | |
"loss": 0.8815, | |
"step": 134 | |
}, | |
{ | |
"epoch": 0.33, | |
"learning_rate": 0.0003, | |
"loss": 0.9151, | |
"step": 135 | |
}, | |
{ | |
"epoch": 0.34, | |
"learning_rate": 0.0003, | |
"loss": 0.9016, | |
"step": 136 | |
}, | |
{ | |
"epoch": 0.34, | |
"learning_rate": 0.0003, | |
"loss": 0.8793, | |
"step": 137 | |
}, | |
{ | |
"epoch": 0.34, | |
"learning_rate": 0.0003, | |
"loss": 0.9387, | |
"step": 138 | |
}, | |
{ | |
"epoch": 0.34, | |
"learning_rate": 0.0003, | |
"loss": 0.9042, | |
"step": 139 | |
}, | |
{ | |
"epoch": 0.35, | |
"learning_rate": 0.0003, | |
"loss": 0.9093, | |
"step": 140 | |
}, | |
{ | |
"epoch": 0.35, | |
"learning_rate": 0.0003, | |
"loss": 0.9126, | |
"step": 141 | |
}, | |
{ | |
"epoch": 0.35, | |
"learning_rate": 0.0003, | |
"loss": 0.9271, | |
"step": 142 | |
}, | |
{ | |
"epoch": 0.35, | |
"learning_rate": 0.0003, | |
"loss": 0.8805, | |
"step": 143 | |
}, | |
{ | |
"epoch": 0.36, | |
"learning_rate": 0.0003, | |
"loss": 0.8738, | |
"step": 144 | |
}, | |
{ | |
"epoch": 0.36, | |
"learning_rate": 0.0003, | |
"loss": 0.9027, | |
"step": 145 | |
}, | |
{ | |
"epoch": 0.36, | |
"learning_rate": 0.0003, | |
"loss": 0.929, | |
"step": 146 | |
}, | |
{ | |
"epoch": 0.36, | |
"learning_rate": 0.0003, | |
"loss": 0.8835, | |
"step": 147 | |
}, | |
{ | |
"epoch": 0.37, | |
"learning_rate": 0.0003, | |
"loss": 0.9399, | |
"step": 148 | |
}, | |
{ | |
"epoch": 0.37, | |
"learning_rate": 0.0003, | |
"loss": 0.8788, | |
"step": 149 | |
}, | |
{ | |
"epoch": 0.37, | |
"learning_rate": 0.0003, | |
"loss": 0.8981, | |
"step": 150 | |
}, | |
{ | |
"epoch": 0.37, | |
"learning_rate": 0.0003, | |
"loss": 0.8797, | |
"step": 151 | |
}, | |
{ | |
"epoch": 0.38, | |
"learning_rate": 0.0003, | |
"loss": 0.9192, | |
"step": 152 | |
}, | |
{ | |
"epoch": 0.38, | |
"learning_rate": 0.0003, | |
"loss": 0.8938, | |
"step": 153 | |
}, | |
{ | |
"epoch": 0.38, | |
"learning_rate": 0.0003, | |
"loss": 0.9308, | |
"step": 154 | |
}, | |
{ | |
"epoch": 0.38, | |
"learning_rate": 0.0003, | |
"loss": 0.8916, | |
"step": 155 | |
}, | |
{ | |
"epoch": 0.39, | |
"learning_rate": 0.0003, | |
"loss": 0.9001, | |
"step": 156 | |
}, | |
{ | |
"epoch": 0.39, | |
"learning_rate": 0.0003, | |
"loss": 0.8612, | |
"step": 157 | |
}, | |
{ | |
"epoch": 0.39, | |
"learning_rate": 0.0003, | |
"loss": 0.8839, | |
"step": 158 | |
}, | |
{ | |
"epoch": 0.39, | |
"learning_rate": 0.0003, | |
"loss": 0.9049, | |
"step": 159 | |
}, | |
{ | |
"epoch": 0.4, | |
"learning_rate": 0.0003, | |
"loss": 0.8817, | |
"step": 160 | |
}, | |
{ | |
"epoch": 0.4, | |
"learning_rate": 0.0003, | |
"loss": 0.902, | |
"step": 161 | |
}, | |
{ | |
"epoch": 0.4, | |
"learning_rate": 0.0003, | |
"loss": 0.9477, | |
"step": 162 | |
}, | |
{ | |
"epoch": 0.4, | |
"learning_rate": 0.0003, | |
"loss": 0.885, | |
"step": 163 | |
}, | |
{ | |
"epoch": 0.41, | |
"learning_rate": 0.0003, | |
"loss": 0.8849, | |
"step": 164 | |
}, | |
{ | |
"epoch": 0.41, | |
"learning_rate": 0.0003, | |
"loss": 0.8765, | |
"step": 165 | |
}, | |
{ | |
"epoch": 0.41, | |
"learning_rate": 0.0003, | |
"loss": 0.9031, | |
"step": 166 | |
}, | |
{ | |
"epoch": 0.41, | |
"learning_rate": 0.0003, | |
"loss": 0.9301, | |
"step": 167 | |
}, | |
{ | |
"epoch": 0.42, | |
"learning_rate": 0.0003, | |
"loss": 0.9257, | |
"step": 168 | |
}, | |
{ | |
"epoch": 0.42, | |
"learning_rate": 0.0003, | |
"loss": 0.9197, | |
"step": 169 | |
}, | |
{ | |
"epoch": 0.42, | |
"learning_rate": 0.0003, | |
"loss": 0.8922, | |
"step": 170 | |
}, | |
{ | |
"epoch": 0.42, | |
"learning_rate": 0.0003, | |
"loss": 0.9155, | |
"step": 171 | |
}, | |
{ | |
"epoch": 0.43, | |
"learning_rate": 0.0003, | |
"loss": 0.8692, | |
"step": 172 | |
}, | |
{ | |
"epoch": 0.43, | |
"learning_rate": 0.0003, | |
"loss": 0.9124, | |
"step": 173 | |
}, | |
{ | |
"epoch": 0.43, | |
"learning_rate": 0.0003, | |
"loss": 0.9049, | |
"step": 174 | |
}, | |
{ | |
"epoch": 0.43, | |
"learning_rate": 0.0003, | |
"loss": 0.8939, | |
"step": 175 | |
}, | |
{ | |
"epoch": 0.44, | |
"learning_rate": 0.0003, | |
"loss": 0.9001, | |
"step": 176 | |
}, | |
{ | |
"epoch": 0.44, | |
"learning_rate": 0.0003, | |
"loss": 0.9266, | |
"step": 177 | |
}, | |
{ | |
"epoch": 0.44, | |
"learning_rate": 0.0003, | |
"loss": 0.9199, | |
"step": 178 | |
}, | |
{ | |
"epoch": 0.44, | |
"learning_rate": 0.0003, | |
"loss": 0.892, | |
"step": 179 | |
}, | |
{ | |
"epoch": 0.45, | |
"learning_rate": 0.0003, | |
"loss": 0.9048, | |
"step": 180 | |
}, | |
{ | |
"epoch": 0.45, | |
"learning_rate": 0.0003, | |
"loss": 0.8519, | |
"step": 181 | |
}, | |
{ | |
"epoch": 0.45, | |
"learning_rate": 0.0003, | |
"loss": 0.8902, | |
"step": 182 | |
}, | |
{ | |
"epoch": 0.45, | |
"learning_rate": 0.0003, | |
"loss": 0.9216, | |
"step": 183 | |
}, | |
{ | |
"epoch": 0.46, | |
"learning_rate": 0.0003, | |
"loss": 0.9349, | |
"step": 184 | |
}, | |
{ | |
"epoch": 0.46, | |
"learning_rate": 0.0003, | |
"loss": 0.9328, | |
"step": 185 | |
}, | |
{ | |
"epoch": 0.46, | |
"learning_rate": 0.0003, | |
"loss": 0.906, | |
"step": 186 | |
}, | |
{ | |
"epoch": 0.46, | |
"learning_rate": 0.0003, | |
"loss": 0.9005, | |
"step": 187 | |
}, | |
{ | |
"epoch": 0.46, | |
"learning_rate": 0.0003, | |
"loss": 0.9005, | |
"step": 188 | |
}, | |
{ | |
"epoch": 0.47, | |
"learning_rate": 0.0003, | |
"loss": 0.9253, | |
"step": 189 | |
}, | |
{ | |
"epoch": 0.47, | |
"learning_rate": 0.0003, | |
"loss": 0.9224, | |
"step": 190 | |
}, | |
{ | |
"epoch": 0.47, | |
"learning_rate": 0.0003, | |
"loss": 0.8771, | |
"step": 191 | |
}, | |
{ | |
"epoch": 0.47, | |
"learning_rate": 0.0003, | |
"loss": 0.9028, | |
"step": 192 | |
}, | |
{ | |
"epoch": 0.48, | |
"learning_rate": 0.0003, | |
"loss": 0.9182, | |
"step": 193 | |
}, | |
{ | |
"epoch": 0.48, | |
"learning_rate": 0.0003, | |
"loss": 0.9215, | |
"step": 194 | |
}, | |
{ | |
"epoch": 0.48, | |
"learning_rate": 0.0003, | |
"loss": 0.907, | |
"step": 195 | |
}, | |
{ | |
"epoch": 0.48, | |
"learning_rate": 0.0003, | |
"loss": 0.8934, | |
"step": 196 | |
}, | |
{ | |
"epoch": 0.49, | |
"learning_rate": 0.0003, | |
"loss": 0.9169, | |
"step": 197 | |
}, | |
{ | |
"epoch": 0.49, | |
"learning_rate": 0.0003, | |
"loss": 0.859, | |
"step": 198 | |
}, | |
{ | |
"epoch": 0.49, | |
"learning_rate": 0.0003, | |
"loss": 0.8991, | |
"step": 199 | |
}, | |
{ | |
"epoch": 0.49, | |
"learning_rate": 0.0003, | |
"loss": 0.8618, | |
"step": 200 | |
}, | |
{ | |
"epoch": 0.5, | |
"learning_rate": 0.0003, | |
"loss": 0.8924, | |
"step": 201 | |
}, | |
{ | |
"epoch": 0.5, | |
"learning_rate": 0.0003, | |
"loss": 0.875, | |
"step": 202 | |
}, | |
{ | |
"epoch": 0.5, | |
"learning_rate": 0.0003, | |
"loss": 0.8961, | |
"step": 203 | |
}, | |
{ | |
"epoch": 0.5, | |
"learning_rate": 0.0003, | |
"loss": 0.9209, | |
"step": 204 | |
}, | |
{ | |
"epoch": 0.51, | |
"learning_rate": 0.0003, | |
"loss": 0.9302, | |
"step": 205 | |
}, | |
{ | |
"epoch": 0.51, | |
"learning_rate": 0.0003, | |
"loss": 0.8938, | |
"step": 206 | |
}, | |
{ | |
"epoch": 0.51, | |
"learning_rate": 0.0003, | |
"loss": 0.9276, | |
"step": 207 | |
}, | |
{ | |
"epoch": 0.51, | |
"learning_rate": 0.0003, | |
"loss": 0.8967, | |
"step": 208 | |
}, | |
{ | |
"epoch": 0.52, | |
"learning_rate": 0.0003, | |
"loss": 0.8779, | |
"step": 209 | |
}, | |
{ | |
"epoch": 0.52, | |
"learning_rate": 0.0003, | |
"loss": 0.8924, | |
"step": 210 | |
}, | |
{ | |
"epoch": 0.52, | |
"learning_rate": 0.0003, | |
"loss": 0.8539, | |
"step": 211 | |
}, | |
{ | |
"epoch": 0.52, | |
"learning_rate": 0.0003, | |
"loss": 0.9068, | |
"step": 212 | |
}, | |
{ | |
"epoch": 0.53, | |
"learning_rate": 0.0003, | |
"loss": 0.8866, | |
"step": 213 | |
}, | |
{ | |
"epoch": 0.53, | |
"learning_rate": 0.0003, | |
"loss": 0.9564, | |
"step": 214 | |
}, | |
{ | |
"epoch": 0.53, | |
"learning_rate": 0.0003, | |
"loss": 0.8917, | |
"step": 215 | |
}, | |
{ | |
"epoch": 0.53, | |
"learning_rate": 0.0003, | |
"loss": 0.9049, | |
"step": 216 | |
}, | |
{ | |
"epoch": 0.54, | |
"learning_rate": 0.0003, | |
"loss": 0.8903, | |
"step": 217 | |
}, | |
{ | |
"epoch": 0.54, | |
"learning_rate": 0.0003, | |
"loss": 0.893, | |
"step": 218 | |
}, | |
{ | |
"epoch": 0.54, | |
"learning_rate": 0.0003, | |
"loss": 0.863, | |
"step": 219 | |
}, | |
{ | |
"epoch": 0.54, | |
"learning_rate": 0.0003, | |
"loss": 0.8816, | |
"step": 220 | |
}, | |
{ | |
"epoch": 0.55, | |
"learning_rate": 0.0003, | |
"loss": 0.9226, | |
"step": 221 | |
}, | |
{ | |
"epoch": 0.55, | |
"learning_rate": 0.0003, | |
"loss": 0.8985, | |
"step": 222 | |
}, | |
{ | |
"epoch": 0.55, | |
"learning_rate": 0.0003, | |
"loss": 0.9396, | |
"step": 223 | |
}, | |
{ | |
"epoch": 0.55, | |
"learning_rate": 0.0003, | |
"loss": 0.8862, | |
"step": 224 | |
}, | |
{ | |
"epoch": 0.56, | |
"learning_rate": 0.0003, | |
"loss": 0.8995, | |
"step": 225 | |
}, | |
{ | |
"epoch": 0.56, | |
"learning_rate": 0.0003, | |
"loss": 0.898, | |
"step": 226 | |
}, | |
{ | |
"epoch": 0.56, | |
"learning_rate": 0.0003, | |
"loss": 0.9014, | |
"step": 227 | |
}, | |
{ | |
"epoch": 0.56, | |
"learning_rate": 0.0003, | |
"loss": 0.8822, | |
"step": 228 | |
}, | |
{ | |
"epoch": 0.57, | |
"learning_rate": 0.0003, | |
"loss": 0.9084, | |
"step": 229 | |
}, | |
{ | |
"epoch": 0.57, | |
"learning_rate": 0.0003, | |
"loss": 0.8888, | |
"step": 230 | |
}, | |
{ | |
"epoch": 0.57, | |
"learning_rate": 0.0003, | |
"loss": 0.9185, | |
"step": 231 | |
}, | |
{ | |
"epoch": 0.57, | |
"learning_rate": 0.0003, | |
"loss": 0.9116, | |
"step": 232 | |
}, | |
{ | |
"epoch": 0.58, | |
"learning_rate": 0.0003, | |
"loss": 0.8842, | |
"step": 233 | |
}, | |
{ | |
"epoch": 0.58, | |
"learning_rate": 0.0003, | |
"loss": 0.8918, | |
"step": 234 | |
}, | |
{ | |
"epoch": 0.58, | |
"learning_rate": 0.0003, | |
"loss": 0.8647, | |
"step": 235 | |
}, | |
{ | |
"epoch": 0.58, | |
"learning_rate": 0.0003, | |
"loss": 0.8821, | |
"step": 236 | |
}, | |
{ | |
"epoch": 0.59, | |
"learning_rate": 0.0003, | |
"loss": 0.904, | |
"step": 237 | |
}, | |
{ | |
"epoch": 0.59, | |
"learning_rate": 0.0003, | |
"loss": 0.9179, | |
"step": 238 | |
}, | |
{ | |
"epoch": 0.59, | |
"learning_rate": 0.0003, | |
"loss": 0.8994, | |
"step": 239 | |
}, | |
{ | |
"epoch": 0.59, | |
"learning_rate": 0.0003, | |
"loss": 0.9438, | |
"step": 240 | |
}, | |
{ | |
"epoch": 0.6, | |
"learning_rate": 0.0003, | |
"loss": 0.8809, | |
"step": 241 | |
}, | |
{ | |
"epoch": 0.6, | |
"learning_rate": 0.0003, | |
"loss": 0.8913, | |
"step": 242 | |
}, | |
{ | |
"epoch": 0.6, | |
"learning_rate": 0.0003, | |
"loss": 0.8929, | |
"step": 243 | |
}, | |
{ | |
"epoch": 0.6, | |
"learning_rate": 0.0003, | |
"loss": 0.8877, | |
"step": 244 | |
}, | |
{ | |
"epoch": 0.61, | |
"learning_rate": 0.0003, | |
"loss": 0.9005, | |
"step": 245 | |
}, | |
{ | |
"epoch": 0.61, | |
"learning_rate": 0.0003, | |
"loss": 0.9035, | |
"step": 246 | |
}, | |
{ | |
"epoch": 0.61, | |
"learning_rate": 0.0003, | |
"loss": 0.9202, | |
"step": 247 | |
}, | |
{ | |
"epoch": 0.61, | |
"learning_rate": 0.0003, | |
"loss": 0.8931, | |
"step": 248 | |
}, | |
{ | |
"epoch": 0.62, | |
"learning_rate": 0.0003, | |
"loss": 0.8916, | |
"step": 249 | |
}, | |
{ | |
"epoch": 0.62, | |
"learning_rate": 0.0003, | |
"loss": 0.8337, | |
"step": 250 | |
}, | |
{ | |
"epoch": 0.62, | |
"learning_rate": 0.0003, | |
"loss": 0.8981, | |
"step": 251 | |
}, | |
{ | |
"epoch": 0.62, | |
"learning_rate": 0.0003, | |
"loss": 0.9022, | |
"step": 252 | |
}, | |
{ | |
"epoch": 0.63, | |
"learning_rate": 0.0003, | |
"loss": 0.9063, | |
"step": 253 | |
}, | |
{ | |
"epoch": 0.63, | |
"learning_rate": 0.0003, | |
"loss": 0.8907, | |
"step": 254 | |
}, | |
{ | |
"epoch": 0.63, | |
"learning_rate": 0.0003, | |
"loss": 0.8918, | |
"step": 255 | |
}, | |
{ | |
"epoch": 0.63, | |
"learning_rate": 0.0003, | |
"loss": 0.9085, | |
"step": 256 | |
}, | |
{ | |
"epoch": 0.64, | |
"learning_rate": 0.0003, | |
"loss": 0.8681, | |
"step": 257 | |
}, | |
{ | |
"epoch": 0.64, | |
"learning_rate": 0.0003, | |
"loss": 0.8807, | |
"step": 258 | |
}, | |
{ | |
"epoch": 0.64, | |
"learning_rate": 0.0003, | |
"loss": 0.8989, | |
"step": 259 | |
}, | |
{ | |
"epoch": 0.64, | |
"learning_rate": 0.0003, | |
"loss": 0.8523, | |
"step": 260 | |
}, | |
{ | |
"epoch": 0.65, | |
"learning_rate": 0.0003, | |
"loss": 0.873, | |
"step": 261 | |
}, | |
{ | |
"epoch": 0.65, | |
"learning_rate": 0.0003, | |
"loss": 0.9374, | |
"step": 262 | |
}, | |
{ | |
"epoch": 0.65, | |
"learning_rate": 0.0003, | |
"loss": 0.886, | |
"step": 263 | |
}, | |
{ | |
"epoch": 0.65, | |
"learning_rate": 0.0003, | |
"loss": 0.9104, | |
"step": 264 | |
}, | |
{ | |
"epoch": 0.66, | |
"learning_rate": 0.0003, | |
"loss": 0.8521, | |
"step": 265 | |
}, | |
{ | |
"epoch": 0.66, | |
"learning_rate": 0.0003, | |
"loss": 0.8816, | |
"step": 266 | |
}, | |
{ | |
"epoch": 0.66, | |
"learning_rate": 0.0003, | |
"loss": 0.848, | |
"step": 267 | |
}, | |
{ | |
"epoch": 0.66, | |
"learning_rate": 0.0003, | |
"loss": 0.8816, | |
"step": 268 | |
}, | |
{ | |
"epoch": 0.67, | |
"learning_rate": 0.0003, | |
"loss": 0.8989, | |
"step": 269 | |
}, | |
{ | |
"epoch": 0.67, | |
"learning_rate": 0.0003, | |
"loss": 0.9293, | |
"step": 270 | |
}, | |
{ | |
"epoch": 0.67, | |
"learning_rate": 0.0003, | |
"loss": 0.8613, | |
"step": 271 | |
}, | |
{ | |
"epoch": 0.67, | |
"learning_rate": 0.0003, | |
"loss": 0.8611, | |
"step": 272 | |
}, | |
{ | |
"epoch": 0.68, | |
"learning_rate": 0.0003, | |
"loss": 0.8602, | |
"step": 273 | |
}, | |
{ | |
"epoch": 0.68, | |
"learning_rate": 0.0003, | |
"loss": 0.8994, | |
"step": 274 | |
}, | |
{ | |
"epoch": 0.68, | |
"learning_rate": 0.0003, | |
"loss": 0.8984, | |
"step": 275 | |
}, | |
{ | |
"epoch": 0.68, | |
"learning_rate": 0.0003, | |
"loss": 0.8879, | |
"step": 276 | |
}, | |
{ | |
"epoch": 0.69, | |
"learning_rate": 0.0003, | |
"loss": 0.8605, | |
"step": 277 | |
}, | |
{ | |
"epoch": 0.69, | |
"learning_rate": 0.0003, | |
"loss": 0.9027, | |
"step": 278 | |
}, | |
{ | |
"epoch": 0.69, | |
"learning_rate": 0.0003, | |
"loss": 0.9147, | |
"step": 279 | |
}, | |
{ | |
"epoch": 0.69, | |
"learning_rate": 0.0003, | |
"loss": 0.8787, | |
"step": 280 | |
}, | |
{ | |
"epoch": 0.69, | |
"learning_rate": 0.0003, | |
"loss": 0.8815, | |
"step": 281 | |
}, | |
{ | |
"epoch": 0.7, | |
"learning_rate": 0.0003, | |
"loss": 0.8915, | |
"step": 282 | |
}, | |
{ | |
"epoch": 0.7, | |
"learning_rate": 0.0003, | |
"loss": 0.8788, | |
"step": 283 | |
}, | |
{ | |
"epoch": 0.7, | |
"learning_rate": 0.0003, | |
"loss": 0.8641, | |
"step": 284 | |
}, | |
{ | |
"epoch": 0.7, | |
"learning_rate": 0.0003, | |
"loss": 0.8845, | |
"step": 285 | |
}, | |
{ | |
"epoch": 0.71, | |
"learning_rate": 0.0003, | |
"loss": 0.8866, | |
"step": 286 | |
}, | |
{ | |
"epoch": 0.71, | |
"learning_rate": 0.0003, | |
"loss": 0.8927, | |
"step": 287 | |
}, | |
{ | |
"epoch": 0.71, | |
"learning_rate": 0.0003, | |
"loss": 0.9105, | |
"step": 288 | |
}, | |
{ | |
"epoch": 0.71, | |
"learning_rate": 0.0003, | |
"loss": 0.869, | |
"step": 289 | |
}, | |
{ | |
"epoch": 0.72, | |
"learning_rate": 0.0003, | |
"loss": 0.8809, | |
"step": 290 | |
}, | |
{ | |
"epoch": 0.72, | |
"learning_rate": 0.0003, | |
"loss": 0.8306, | |
"step": 291 | |
}, | |
{ | |
"epoch": 0.72, | |
"learning_rate": 0.0003, | |
"loss": 0.8725, | |
"step": 292 | |
}, | |
{ | |
"epoch": 0.72, | |
"learning_rate": 0.0003, | |
"loss": 0.8808, | |
"step": 293 | |
}, | |
{ | |
"epoch": 0.73, | |
"learning_rate": 0.0003, | |
"loss": 0.8682, | |
"step": 294 | |
}, | |
{ | |
"epoch": 0.73, | |
"learning_rate": 0.0003, | |
"loss": 0.893, | |
"step": 295 | |
}, | |
{ | |
"epoch": 0.73, | |
"learning_rate": 0.0003, | |
"loss": 0.8647, | |
"step": 296 | |
}, | |
{ | |
"epoch": 0.73, | |
"learning_rate": 0.0003, | |
"loss": 0.9019, | |
"step": 297 | |
}, | |
{ | |
"epoch": 0.74, | |
"learning_rate": 0.0003, | |
"loss": 0.8794, | |
"step": 298 | |
}, | |
{ | |
"epoch": 0.74, | |
"learning_rate": 0.0003, | |
"loss": 0.9074, | |
"step": 299 | |
}, | |
{ | |
"epoch": 0.74, | |
"learning_rate": 0.0003, | |
"loss": 0.9037, | |
"step": 300 | |
}, | |
{ | |
"epoch": 0.74, | |
"learning_rate": 0.0003, | |
"loss": 0.8777, | |
"step": 301 | |
}, | |
{ | |
"epoch": 0.75, | |
"learning_rate": 0.0003, | |
"loss": 0.8645, | |
"step": 302 | |
}, | |
{ | |
"epoch": 0.75, | |
"learning_rate": 0.0003, | |
"loss": 0.8971, | |
"step": 303 | |
}, | |
{ | |
"epoch": 0.75, | |
"learning_rate": 0.0003, | |
"loss": 0.8714, | |
"step": 304 | |
}, | |
{ | |
"epoch": 0.75, | |
"learning_rate": 0.0003, | |
"loss": 0.878, | |
"step": 305 | |
}, | |
{ | |
"epoch": 0.76, | |
"learning_rate": 0.0003, | |
"loss": 0.9052, | |
"step": 306 | |
}, | |
{ | |
"epoch": 0.76, | |
"learning_rate": 0.0003, | |
"loss": 0.8836, | |
"step": 307 | |
}, | |
{ | |
"epoch": 0.76, | |
"learning_rate": 0.0003, | |
"loss": 0.9095, | |
"step": 308 | |
}, | |
{ | |
"epoch": 0.76, | |
"learning_rate": 0.0003, | |
"loss": 0.9076, | |
"step": 309 | |
}, | |
{ | |
"epoch": 0.77, | |
"learning_rate": 0.0003, | |
"loss": 0.8988, | |
"step": 310 | |
}, | |
{ | |
"epoch": 0.77, | |
"learning_rate": 0.0003, | |
"loss": 0.8855, | |
"step": 311 | |
}, | |
{ | |
"epoch": 0.77, | |
"learning_rate": 0.0003, | |
"loss": 0.8558, | |
"step": 312 | |
}, | |
{ | |
"epoch": 0.77, | |
"learning_rate": 0.0003, | |
"loss": 0.887, | |
"step": 313 | |
}, | |
{ | |
"epoch": 0.78, | |
"learning_rate": 0.0003, | |
"loss": 0.9039, | |
"step": 314 | |
}, | |
{ | |
"epoch": 0.78, | |
"learning_rate": 0.0003, | |
"loss": 0.8897, | |
"step": 315 | |
}, | |
{ | |
"epoch": 0.78, | |
"learning_rate": 0.0003, | |
"loss": 0.8936, | |
"step": 316 | |
}, | |
{ | |
"epoch": 0.78, | |
"learning_rate": 0.0003, | |
"loss": 0.9265, | |
"step": 317 | |
}, | |
{ | |
"epoch": 0.79, | |
"learning_rate": 0.0003, | |
"loss": 0.8856, | |
"step": 318 | |
}, | |
{ | |
"epoch": 0.79, | |
"learning_rate": 0.0003, | |
"loss": 0.8473, | |
"step": 319 | |
}, | |
{ | |
"epoch": 0.79, | |
"learning_rate": 0.0003, | |
"loss": 0.8493, | |
"step": 320 | |
}, | |
{ | |
"epoch": 0.79, | |
"learning_rate": 0.0003, | |
"loss": 0.9019, | |
"step": 321 | |
}, | |
{ | |
"epoch": 0.8, | |
"learning_rate": 0.0003, | |
"loss": 0.9075, | |
"step": 322 | |
}, | |
{ | |
"epoch": 0.8, | |
"learning_rate": 0.0003, | |
"loss": 0.9216, | |
"step": 323 | |
}, | |
{ | |
"epoch": 0.8, | |
"learning_rate": 0.0003, | |
"loss": 0.8735, | |
"step": 324 | |
}, | |
{ | |
"epoch": 0.8, | |
"learning_rate": 0.0003, | |
"loss": 0.8935, | |
"step": 325 | |
}, | |
{ | |
"epoch": 0.81, | |
"learning_rate": 0.0003, | |
"loss": 0.8832, | |
"step": 326 | |
}, | |
{ | |
"epoch": 0.81, | |
"learning_rate": 0.0003, | |
"loss": 0.8999, | |
"step": 327 | |
}, | |
{ | |
"epoch": 0.81, | |
"learning_rate": 0.0003, | |
"loss": 0.8748, | |
"step": 328 | |
}, | |
{ | |
"epoch": 0.81, | |
"learning_rate": 0.0003, | |
"loss": 0.8612, | |
"step": 329 | |
}, | |
{ | |
"epoch": 0.82, | |
"learning_rate": 0.0003, | |
"loss": 0.8726, | |
"step": 330 | |
}, | |
{ | |
"epoch": 0.82, | |
"learning_rate": 0.0003, | |
"loss": 0.8716, | |
"step": 331 | |
}, | |
{ | |
"epoch": 0.82, | |
"learning_rate": 0.0003, | |
"loss": 0.9239, | |
"step": 332 | |
}, | |
{ | |
"epoch": 0.82, | |
"learning_rate": 0.0003, | |
"loss": 0.8707, | |
"step": 333 | |
}, | |
{ | |
"epoch": 0.83, | |
"learning_rate": 0.0003, | |
"loss": 0.8939, | |
"step": 334 | |
}, | |
{ | |
"epoch": 0.83, | |
"learning_rate": 0.0003, | |
"loss": 0.8633, | |
"step": 335 | |
}, | |
{ | |
"epoch": 0.83, | |
"learning_rate": 0.0003, | |
"loss": 0.9025, | |
"step": 336 | |
}, | |
{ | |
"epoch": 0.83, | |
"learning_rate": 0.0003, | |
"loss": 0.8577, | |
"step": 337 | |
}, | |
{ | |
"epoch": 0.84, | |
"learning_rate": 0.0003, | |
"loss": 0.8932, | |
"step": 338 | |
}, | |
{ | |
"epoch": 0.84, | |
"learning_rate": 0.0003, | |
"loss": 0.8895, | |
"step": 339 | |
}, | |
{ | |
"epoch": 0.84, | |
"learning_rate": 0.0003, | |
"loss": 0.8985, | |
"step": 340 | |
}, | |
{ | |
"epoch": 0.84, | |
"learning_rate": 0.0003, | |
"loss": 0.8744, | |
"step": 341 | |
}, | |
{ | |
"epoch": 0.85, | |
"learning_rate": 0.0003, | |
"loss": 0.8889, | |
"step": 342 | |
}, | |
{ | |
"epoch": 0.85, | |
"learning_rate": 0.0003, | |
"loss": 0.8939, | |
"step": 343 | |
}, | |
{ | |
"epoch": 0.85, | |
"learning_rate": 0.0003, | |
"loss": 0.9041, | |
"step": 344 | |
}, | |
{ | |
"epoch": 0.85, | |
"learning_rate": 0.0003, | |
"loss": 0.8922, | |
"step": 345 | |
}, | |
{ | |
"epoch": 0.86, | |
"learning_rate": 0.0003, | |
"loss": 0.9089, | |
"step": 346 | |
}, | |
{ | |
"epoch": 0.86, | |
"learning_rate": 0.0003, | |
"loss": 0.8842, | |
"step": 347 | |
}, | |
{ | |
"epoch": 0.86, | |
"learning_rate": 0.0003, | |
"loss": 0.8911, | |
"step": 348 | |
}, | |
{ | |
"epoch": 0.86, | |
"learning_rate": 0.0003, | |
"loss": 0.8839, | |
"step": 349 | |
}, | |
{ | |
"epoch": 0.87, | |
"learning_rate": 0.0003, | |
"loss": 0.8809, | |
"step": 350 | |
}, | |
{ | |
"epoch": 0.87, | |
"learning_rate": 0.0003, | |
"loss": 0.877, | |
"step": 351 | |
}, | |
{ | |
"epoch": 0.87, | |
"learning_rate": 0.0003, | |
"loss": 0.8688, | |
"step": 352 | |
}, | |
{ | |
"epoch": 0.87, | |
"learning_rate": 0.0003, | |
"loss": 0.8821, | |
"step": 353 | |
}, | |
{ | |
"epoch": 0.88, | |
"learning_rate": 0.0003, | |
"loss": 0.8915, | |
"step": 354 | |
}, | |
{ | |
"epoch": 0.88, | |
"learning_rate": 0.0003, | |
"loss": 0.898, | |
"step": 355 | |
}, | |
{ | |
"epoch": 0.88, | |
"learning_rate": 0.0003, | |
"loss": 0.891, | |
"step": 356 | |
}, | |
{ | |
"epoch": 0.88, | |
"learning_rate": 0.0003, | |
"loss": 0.9312, | |
"step": 357 | |
}, | |
{ | |
"epoch": 0.89, | |
"learning_rate": 0.0003, | |
"loss": 0.8735, | |
"step": 358 | |
}, | |
{ | |
"epoch": 0.89, | |
"learning_rate": 0.0003, | |
"loss": 0.8689, | |
"step": 359 | |
}, | |
{ | |
"epoch": 0.89, | |
"learning_rate": 0.0003, | |
"loss": 0.8601, | |
"step": 360 | |
}, | |
{ | |
"epoch": 0.89, | |
"learning_rate": 0.0003, | |
"loss": 0.9331, | |
"step": 361 | |
}, | |
{ | |
"epoch": 0.9, | |
"learning_rate": 0.0003, | |
"loss": 0.8806, | |
"step": 362 | |
}, | |
{ | |
"epoch": 0.9, | |
"learning_rate": 0.0003, | |
"loss": 0.8544, | |
"step": 363 | |
}, | |
{ | |
"epoch": 0.9, | |
"learning_rate": 0.0003, | |
"loss": 0.8771, | |
"step": 364 | |
}, | |
{ | |
"epoch": 0.9, | |
"learning_rate": 0.0003, | |
"loss": 0.891, | |
"step": 365 | |
}, | |
{ | |
"epoch": 0.91, | |
"learning_rate": 0.0003, | |
"loss": 0.8807, | |
"step": 366 | |
}, | |
{ | |
"epoch": 0.91, | |
"learning_rate": 0.0003, | |
"loss": 0.8782, | |
"step": 367 | |
}, | |
{ | |
"epoch": 0.91, | |
"learning_rate": 0.0003, | |
"loss": 0.9059, | |
"step": 368 | |
}, | |
{ | |
"epoch": 0.91, | |
"learning_rate": 0.0003, | |
"loss": 0.9165, | |
"step": 369 | |
}, | |
{ | |
"epoch": 0.91, | |
"learning_rate": 0.0003, | |
"loss": 0.8859, | |
"step": 370 | |
}, | |
{ | |
"epoch": 0.92, | |
"learning_rate": 0.0003, | |
"loss": 0.8848, | |
"step": 371 | |
}, | |
{ | |
"epoch": 0.92, | |
"learning_rate": 0.0003, | |
"loss": 0.8517, | |
"step": 372 | |
}, | |
{ | |
"epoch": 0.92, | |
"learning_rate": 0.0003, | |
"loss": 0.8688, | |
"step": 373 | |
}, | |
{ | |
"epoch": 0.92, | |
"learning_rate": 0.0003, | |
"loss": 0.8794, | |
"step": 374 | |
}, | |
{ | |
"epoch": 0.93, | |
"learning_rate": 0.0003, | |
"loss": 0.8675, | |
"step": 375 | |
}, | |
{ | |
"epoch": 0.93, | |
"learning_rate": 0.0003, | |
"loss": 0.877, | |
"step": 376 | |
}, | |
{ | |
"epoch": 0.93, | |
"learning_rate": 0.0003, | |
"loss": 0.9139, | |
"step": 377 | |
}, | |
{ | |
"epoch": 0.93, | |
"learning_rate": 0.0003, | |
"loss": 0.8533, | |
"step": 378 | |
}, | |
{ | |
"epoch": 0.94, | |
"learning_rate": 0.0003, | |
"loss": 0.8762, | |
"step": 379 | |
}, | |
{ | |
"epoch": 0.94, | |
"learning_rate": 0.0003, | |
"loss": 0.8953, | |
"step": 380 | |
}, | |
{ | |
"epoch": 0.94, | |
"learning_rate": 0.0003, | |
"loss": 0.8971, | |
"step": 381 | |
}, | |
{ | |
"epoch": 0.94, | |
"learning_rate": 0.0003, | |
"loss": 0.8966, | |
"step": 382 | |
}, | |
{ | |
"epoch": 0.95, | |
"learning_rate": 0.0003, | |
"loss": 0.8959, | |
"step": 383 | |
}, | |
{ | |
"epoch": 0.95, | |
"learning_rate": 0.0003, | |
"loss": 0.8883, | |
"step": 384 | |
}, | |
{ | |
"epoch": 0.95, | |
"learning_rate": 0.0003, | |
"loss": 0.8837, | |
"step": 385 | |
}, | |
{ | |
"epoch": 0.95, | |
"learning_rate": 0.0003, | |
"loss": 0.8944, | |
"step": 386 | |
}, | |
{ | |
"epoch": 0.96, | |
"learning_rate": 0.0003, | |
"loss": 0.8617, | |
"step": 387 | |
}, | |
{ | |
"epoch": 0.96, | |
"learning_rate": 0.0003, | |
"loss": 0.8482, | |
"step": 388 | |
}, | |
{ | |
"epoch": 0.96, | |
"learning_rate": 0.0003, | |
"loss": 0.8621, | |
"step": 389 | |
}, | |
{ | |
"epoch": 0.96, | |
"learning_rate": 0.0003, | |
"loss": 0.928, | |
"step": 390 | |
}, | |
{ | |
"epoch": 0.97, | |
"learning_rate": 0.0003, | |
"loss": 0.8794, | |
"step": 391 | |
}, | |
{ | |
"epoch": 0.97, | |
"learning_rate": 0.0003, | |
"loss": 0.9038, | |
"step": 392 | |
}, | |
{ | |
"epoch": 0.97, | |
"learning_rate": 0.0003, | |
"loss": 0.8731, | |
"step": 393 | |
}, | |
{ | |
"epoch": 0.97, | |
"learning_rate": 0.0003, | |
"loss": 0.8977, | |
"step": 394 | |
}, | |
{ | |
"epoch": 0.98, | |
"learning_rate": 0.0003, | |
"loss": 0.8541, | |
"step": 395 | |
}, | |
{ | |
"epoch": 0.98, | |
"learning_rate": 0.0003, | |
"loss": 0.8964, | |
"step": 396 | |
}, | |
{ | |
"epoch": 0.98, | |
"learning_rate": 0.0003, | |
"loss": 0.8922, | |
"step": 397 | |
}, | |
{ | |
"epoch": 0.98, | |
"learning_rate": 0.0003, | |
"loss": 0.893, | |
"step": 398 | |
}, | |
{ | |
"epoch": 0.99, | |
"learning_rate": 0.0003, | |
"loss": 0.8912, | |
"step": 399 | |
}, | |
{ | |
"epoch": 0.99, | |
"learning_rate": 0.0003, | |
"loss": 0.8605, | |
"step": 400 | |
}, | |
{ | |
"epoch": 0.99, | |
"learning_rate": 0.0003, | |
"loss": 0.8736, | |
"step": 401 | |
}, | |
{ | |
"epoch": 0.99, | |
"learning_rate": 0.0003, | |
"loss": 0.8684, | |
"step": 402 | |
}, | |
{ | |
"epoch": 1.0, | |
"learning_rate": 0.0003, | |
"loss": 0.8944, | |
"step": 403 | |
}, | |
{ | |
"epoch": 1.0, | |
"learning_rate": 0.0003, | |
"loss": 0.874, | |
"step": 404 | |
}, | |
{ | |
"epoch": 1.0, | |
"step": 404, | |
"total_flos": 4.542094418965709e+17, | |
"train_loss": 0.933016965589901, | |
"train_runtime": 5794.0332, | |
"train_samples_per_second": 8.933, | |
"train_steps_per_second": 0.07 | |
} | |
], | |
"logging_steps": 1, | |
"max_steps": 404, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 1, | |
"save_steps": 25, | |
"total_flos": 4.542094418965709e+17, | |
"train_batch_size": 1, | |
"trial_name": null, | |
"trial_params": null | |
} | |