|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 13.722126929674099, |
|
"global_step": 2000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00995, |
|
"loss": 3.247, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0099, |
|
"loss": 2.397, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00985, |
|
"loss": 2.1303, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0098, |
|
"loss": 1.9873, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00975, |
|
"loss": 1.8902, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.0097, |
|
"loss": 1.7747, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.00965, |
|
"loss": 1.711, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.0096, |
|
"loss": 1.6649, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.00955, |
|
"loss": 1.6457, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.0095, |
|
"loss": 1.5889, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.00945, |
|
"loss": 1.602, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.0094, |
|
"loss": 1.5384, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.00935, |
|
"loss": 1.5033, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.009300000000000001, |
|
"loss": 1.5284, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.009250000000000001, |
|
"loss": 1.4809, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 0.0092, |
|
"loss": 1.4795, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.00915, |
|
"loss": 1.4555, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.0091, |
|
"loss": 1.4335, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.00905, |
|
"loss": 1.4275, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 0.009000000000000001, |
|
"loss": 1.4365, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.00895, |
|
"loss": 1.4345, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 0.0089, |
|
"loss": 1.4284, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 0.00885, |
|
"loss": 1.4069, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 0.0088, |
|
"loss": 1.4395, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.00875, |
|
"loss": 1.3858, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 0.0087, |
|
"loss": 1.3875, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 0.00865, |
|
"loss": 1.3721, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.0086, |
|
"loss": 1.374, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.00855, |
|
"loss": 1.348, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 0.0085, |
|
"loss": 1.358, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 0.00845, |
|
"loss": 1.3352, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 0.0084, |
|
"loss": 1.3385, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 0.00835, |
|
"loss": 1.3546, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 0.0083, |
|
"loss": 1.3472, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 0.00825, |
|
"loss": 1.3179, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.47, |
|
"learning_rate": 0.008199999999999999, |
|
"loss": 1.2895, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 0.00815, |
|
"loss": 1.303, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 0.008100000000000001, |
|
"loss": 1.3066, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 0.00805, |
|
"loss": 1.3264, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 2.74, |
|
"learning_rate": 0.008, |
|
"loss": 1.3202, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 0.00795, |
|
"loss": 1.2923, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 0.0079, |
|
"loss": 1.2711, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 0.007850000000000001, |
|
"loss": 1.313, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 0.0078000000000000005, |
|
"loss": 1.2948, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 0.007750000000000001, |
|
"loss": 1.2596, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 0.0077, |
|
"loss": 1.2505, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 3.22, |
|
"learning_rate": 0.0076500000000000005, |
|
"loss": 1.2581, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 3.29, |
|
"learning_rate": 0.0076, |
|
"loss": 1.2829, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 0.00755, |
|
"loss": 1.2487, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 3.43, |
|
"learning_rate": 0.0075, |
|
"loss": 1.2927, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 0.00745, |
|
"loss": 1.263, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 3.57, |
|
"learning_rate": 0.0074, |
|
"loss": 1.2565, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 0.00735, |
|
"loss": 1.2842, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 3.7, |
|
"learning_rate": 0.0073, |
|
"loss": 1.2506, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 3.77, |
|
"learning_rate": 0.0072499999999999995, |
|
"loss": 1.2436, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"learning_rate": 0.0072, |
|
"loss": 1.2752, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 0.00715, |
|
"loss": 1.2366, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 0.0070999999999999995, |
|
"loss": 1.2681, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 4.05, |
|
"learning_rate": 0.00705, |
|
"loss": 1.2076, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 4.12, |
|
"learning_rate": 0.006999999999999999, |
|
"loss": 1.2311, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 4.19, |
|
"learning_rate": 0.00695, |
|
"loss": 1.2203, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 4.25, |
|
"learning_rate": 0.0069, |
|
"loss": 1.2084, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"learning_rate": 0.006850000000000001, |
|
"loss": 1.2243, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 0.0068000000000000005, |
|
"loss": 1.2382, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 0.006750000000000001, |
|
"loss": 1.206, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 4.53, |
|
"learning_rate": 0.0067, |
|
"loss": 1.2301, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 0.0066500000000000005, |
|
"loss": 1.2079, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"learning_rate": 0.006600000000000001, |
|
"loss": 1.2072, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 4.73, |
|
"learning_rate": 0.00655, |
|
"loss": 1.169, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 0.006500000000000001, |
|
"loss": 1.2034, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 4.87, |
|
"learning_rate": 0.00645, |
|
"loss": 1.2168, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 4.94, |
|
"learning_rate": 0.0064, |
|
"loss": 1.2131, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 0.006350000000000001, |
|
"loss": 1.2044, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 5.08, |
|
"learning_rate": 0.0063, |
|
"loss": 1.1908, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 5.15, |
|
"learning_rate": 0.00625, |
|
"loss": 1.1594, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 5.21, |
|
"learning_rate": 0.0062, |
|
"loss": 1.1371, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 5.28, |
|
"learning_rate": 0.00615, |
|
"loss": 1.1905, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 5.35, |
|
"learning_rate": 0.0061, |
|
"loss": 1.1684, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 5.42, |
|
"learning_rate": 0.00605, |
|
"loss": 1.1942, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 5.49, |
|
"learning_rate": 0.006, |
|
"loss": 1.1848, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 5.56, |
|
"learning_rate": 0.0059499999999999996, |
|
"loss": 1.1786, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 5.63, |
|
"learning_rate": 0.0059, |
|
"loss": 1.1686, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 5.69, |
|
"learning_rate": 0.00585, |
|
"loss": 1.1852, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 5.76, |
|
"learning_rate": 0.0058, |
|
"loss": 1.198, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 5.83, |
|
"learning_rate": 0.00575, |
|
"loss": 1.1738, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 5.9, |
|
"learning_rate": 0.005699999999999999, |
|
"loss": 1.1808, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 5.97, |
|
"learning_rate": 0.00565, |
|
"loss": 1.1655, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 6.04, |
|
"learning_rate": 0.005600000000000001, |
|
"loss": 1.1467, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"learning_rate": 0.00555, |
|
"loss": 1.1559, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 6.17, |
|
"learning_rate": 0.0055000000000000005, |
|
"loss": 1.1497, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 6.24, |
|
"learning_rate": 0.005450000000000001, |
|
"loss": 1.1473, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 6.31, |
|
"learning_rate": 0.0054, |
|
"loss": 1.184, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 6.38, |
|
"learning_rate": 0.005350000000000001, |
|
"loss": 1.1053, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 6.45, |
|
"learning_rate": 0.0053, |
|
"loss": 1.1721, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 6.52, |
|
"learning_rate": 0.00525, |
|
"loss": 1.1418, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 6.59, |
|
"learning_rate": 0.005200000000000001, |
|
"loss": 1.1243, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 6.66, |
|
"learning_rate": 0.00515, |
|
"loss": 1.1386, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 6.72, |
|
"learning_rate": 0.0051, |
|
"loss": 1.1743, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 6.79, |
|
"learning_rate": 0.00505, |
|
"loss": 1.1201, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 6.86, |
|
"learning_rate": 0.005, |
|
"loss": 1.1224, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 6.93, |
|
"learning_rate": 0.00495, |
|
"loss": 1.1464, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 0.0049, |
|
"loss": 1.1547, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 7.07, |
|
"learning_rate": 0.00485, |
|
"loss": 1.145, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 7.14, |
|
"learning_rate": 0.0048, |
|
"loss": 1.1261, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 7.2, |
|
"learning_rate": 0.00475, |
|
"loss": 1.1422, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 7.27, |
|
"learning_rate": 0.0047, |
|
"loss": 1.1115, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 7.34, |
|
"learning_rate": 0.0046500000000000005, |
|
"loss": 1.0921, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 7.41, |
|
"learning_rate": 0.0046, |
|
"loss": 1.1041, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 7.48, |
|
"learning_rate": 0.00455, |
|
"loss": 1.1196, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 7.55, |
|
"learning_rate": 0.0045000000000000005, |
|
"loss": 1.133, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 7.62, |
|
"learning_rate": 0.00445, |
|
"loss": 1.1133, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 7.68, |
|
"learning_rate": 0.0044, |
|
"loss": 1.1034, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 7.75, |
|
"learning_rate": 0.00435, |
|
"loss": 1.118, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 7.82, |
|
"learning_rate": 0.0043, |
|
"loss": 1.128, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 7.89, |
|
"learning_rate": 0.00425, |
|
"loss": 1.1316, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 7.96, |
|
"learning_rate": 0.0042, |
|
"loss": 1.129, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 8.03, |
|
"learning_rate": 0.00415, |
|
"loss": 1.0815, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 8.1, |
|
"learning_rate": 0.0040999999999999995, |
|
"loss": 1.091, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 8.16, |
|
"learning_rate": 0.004050000000000001, |
|
"loss": 1.0751, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 8.23, |
|
"learning_rate": 0.004, |
|
"loss": 1.1042, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 8.3, |
|
"learning_rate": 0.00395, |
|
"loss": 1.0957, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 8.37, |
|
"learning_rate": 0.0039000000000000003, |
|
"loss": 1.1186, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 8.44, |
|
"learning_rate": 0.00385, |
|
"loss": 1.101, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 8.51, |
|
"learning_rate": 0.0038, |
|
"loss": 1.0889, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 8.58, |
|
"learning_rate": 0.00375, |
|
"loss": 1.1111, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 8.64, |
|
"learning_rate": 0.0037, |
|
"loss": 1.1158, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 8.71, |
|
"learning_rate": 0.00365, |
|
"loss": 1.0982, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 8.78, |
|
"learning_rate": 0.0036, |
|
"loss": 1.1002, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 8.85, |
|
"learning_rate": 0.0035499999999999998, |
|
"loss": 1.0892, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 8.92, |
|
"learning_rate": 0.0034999999999999996, |
|
"loss": 1.0698, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 8.99, |
|
"learning_rate": 0.00345, |
|
"loss": 1.0703, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 9.06, |
|
"learning_rate": 0.0034000000000000002, |
|
"loss": 1.0602, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 9.13, |
|
"learning_rate": 0.00335, |
|
"loss": 1.0611, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 9.19, |
|
"learning_rate": 0.0033000000000000004, |
|
"loss": 1.0886, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 9.26, |
|
"learning_rate": 0.0032500000000000003, |
|
"loss": 1.1028, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 9.33, |
|
"learning_rate": 0.0032, |
|
"loss": 1.0727, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 9.4, |
|
"learning_rate": 0.00315, |
|
"loss": 1.074, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 9.47, |
|
"learning_rate": 0.0031, |
|
"loss": 1.0605, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 9.54, |
|
"learning_rate": 0.00305, |
|
"loss": 1.0896, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 9.61, |
|
"learning_rate": 0.003, |
|
"loss": 1.0674, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 9.67, |
|
"learning_rate": 0.00295, |
|
"loss": 1.0894, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 9.74, |
|
"learning_rate": 0.0029, |
|
"loss": 1.0782, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 9.81, |
|
"learning_rate": 0.0028499999999999997, |
|
"loss": 1.0905, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 9.88, |
|
"learning_rate": 0.0028000000000000004, |
|
"loss": 1.0713, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 9.95, |
|
"learning_rate": 0.0027500000000000003, |
|
"loss": 1.0694, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 10.02, |
|
"learning_rate": 0.0027, |
|
"loss": 1.0734, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 10.09, |
|
"learning_rate": 0.00265, |
|
"loss": 1.0836, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 10.15, |
|
"learning_rate": 0.0026000000000000003, |
|
"loss": 1.033, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 10.22, |
|
"learning_rate": 0.00255, |
|
"loss": 1.0646, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 10.29, |
|
"learning_rate": 0.0025, |
|
"loss": 1.0718, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 10.36, |
|
"learning_rate": 0.00245, |
|
"loss": 1.0507, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 10.43, |
|
"learning_rate": 0.0024, |
|
"loss": 1.057, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 10.5, |
|
"learning_rate": 0.00235, |
|
"loss": 1.0603, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 10.57, |
|
"learning_rate": 0.0023, |
|
"loss": 1.0669, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 10.63, |
|
"learning_rate": 0.0022500000000000003, |
|
"loss": 1.0766, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 10.7, |
|
"learning_rate": 0.0022, |
|
"loss": 1.0346, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 10.77, |
|
"learning_rate": 0.00215, |
|
"loss": 1.0648, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 10.84, |
|
"learning_rate": 0.0021, |
|
"loss": 1.053, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 10.91, |
|
"learning_rate": 0.0020499999999999997, |
|
"loss": 1.0558, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 10.98, |
|
"learning_rate": 0.002, |
|
"loss": 1.0997, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 11.05, |
|
"learning_rate": 0.0019500000000000001, |
|
"loss": 1.0345, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 11.11, |
|
"learning_rate": 0.0019, |
|
"loss": 1.0371, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 11.18, |
|
"learning_rate": 0.00185, |
|
"loss": 1.0542, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 11.25, |
|
"learning_rate": 0.0018, |
|
"loss": 1.0702, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 11.32, |
|
"learning_rate": 0.0017499999999999998, |
|
"loss": 1.0396, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 11.39, |
|
"learning_rate": 0.0017000000000000001, |
|
"loss": 1.0159, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 11.46, |
|
"learning_rate": 0.0016500000000000002, |
|
"loss": 1.0364, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 11.53, |
|
"learning_rate": 0.0016, |
|
"loss": 1.054, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 11.6, |
|
"learning_rate": 0.00155, |
|
"loss": 1.0384, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 11.66, |
|
"learning_rate": 0.0015, |
|
"loss": 1.0737, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 11.73, |
|
"learning_rate": 0.00145, |
|
"loss": 1.0502, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 11.8, |
|
"learning_rate": 0.0014000000000000002, |
|
"loss": 1.0762, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 11.87, |
|
"learning_rate": 0.00135, |
|
"loss": 1.0386, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 11.94, |
|
"learning_rate": 0.0013000000000000002, |
|
"loss": 1.0463, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 0.00125, |
|
"loss": 1.0513, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 12.08, |
|
"learning_rate": 0.0012, |
|
"loss": 1.044, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 12.14, |
|
"learning_rate": 0.00115, |
|
"loss": 1.0252, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 12.21, |
|
"learning_rate": 0.0011, |
|
"loss": 1.0311, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 12.28, |
|
"learning_rate": 0.00105, |
|
"loss": 1.015, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 12.35, |
|
"learning_rate": 0.001, |
|
"loss": 1.0654, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 12.42, |
|
"learning_rate": 0.00095, |
|
"loss": 1.0541, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 12.49, |
|
"learning_rate": 0.0009, |
|
"loss": 1.0525, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 12.56, |
|
"learning_rate": 0.0008500000000000001, |
|
"loss": 1.0251, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 12.62, |
|
"learning_rate": 0.0008, |
|
"loss": 1.0657, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 12.69, |
|
"learning_rate": 0.00075, |
|
"loss": 1.041, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 12.76, |
|
"learning_rate": 0.0007000000000000001, |
|
"loss": 1.025, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 12.83, |
|
"learning_rate": 0.0006500000000000001, |
|
"loss": 1.0255, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 12.9, |
|
"learning_rate": 0.0006, |
|
"loss": 1.0641, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 12.97, |
|
"learning_rate": 0.00055, |
|
"loss": 1.0529, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 13.04, |
|
"learning_rate": 0.0005, |
|
"loss": 1.0367, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 13.1, |
|
"learning_rate": 0.00045, |
|
"loss": 1.0461, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 13.17, |
|
"learning_rate": 0.0004, |
|
"loss": 1.0197, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 13.24, |
|
"learning_rate": 0.00035000000000000005, |
|
"loss": 1.0339, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 13.31, |
|
"learning_rate": 0.0003, |
|
"loss": 1.0274, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 13.38, |
|
"learning_rate": 0.00025, |
|
"loss": 1.0222, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 13.45, |
|
"learning_rate": 0.0002, |
|
"loss": 1.0174, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 13.52, |
|
"learning_rate": 0.00015, |
|
"loss": 1.0295, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 13.58, |
|
"learning_rate": 0.0001, |
|
"loss": 1.0226, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 13.65, |
|
"learning_rate": 5e-05, |
|
"loss": 1.0655, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 13.72, |
|
"learning_rate": 0.0, |
|
"loss": 1.0367, |
|
"step": 2000 |
|
} |
|
], |
|
"max_steps": 2000, |
|
"num_train_epochs": 14, |
|
"total_flos": 3.447484134404915e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|