| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 10.0, | |
| "global_step": 1310, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0004999281136632892, | |
| "loss": 0.3104, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0004997124959943201, | |
| "loss": 0.148, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0004993532709928075, | |
| "loss": 0.1311, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0004988506452457066, | |
| "loss": 0.1266, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0004982049078084071, | |
| "loss": 0.1169, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0004974164300384998, | |
| "loss": 0.1142, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0004964856653822122, | |
| "loss": 0.1128, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0004954131491136361, | |
| "loss": 0.1103, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0004941994980268967, | |
| "loss": 0.1188, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.000492845410081439, | |
| "loss": 0.1028, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0004913516640006391, | |
| "loss": 0.1076, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0004897191188239667, | |
| "loss": 0.1114, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00048794871341296, | |
| "loss": 0.1084, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00048604146591129483, | |
| "loss": 0.1107, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00048399847315926, | |
| "loss": 0.1062, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00048182091006297446, | |
| "loss": 0.1021, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00047951002891870987, | |
| "loss": 0.102, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00047706715869270635, | |
| "loss": 0.098, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000474493704256897, | |
| "loss": 0.103, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0004717911455809782, | |
| "loss": 0.1111, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0004689610368812938, | |
| "loss": 0.1033, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0004660050057270191, | |
| "loss": 0.1018, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0004629247521041611, | |
| "loss": 0.1108, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0004597220474379125, | |
| "loss": 0.1084, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0004563987335739216, | |
| "loss": 0.1084, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00045295672171906365, | |
| "loss": 0.1156, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00044939799134232397, | |
| "loss": 0.1076, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0004457245890364235, | |
| "loss": 0.1077, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0004419386273408428, | |
| "loss": 0.1034, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0004380422835269193, | |
| "loss": 0.1045, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00043403779834572, | |
| "loss": 0.1017, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00042992747473940553, | |
| "loss": 0.1092, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00042571367651682995, | |
| "loss": 0.1042, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00042139882699413617, | |
| "loss": 0.0961, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00041698540760112926, | |
| "loss": 0.1003, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00041247595645422955, | |
| "loss": 0.1027, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0004078730668968252, | |
| "loss": 0.0969, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00040317938600786487, | |
| "loss": 0.1028, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00039839761307954675, | |
| "loss": 0.1093, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0003935304980649813, | |
| "loss": 0.1115, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0003885808399967186, | |
| "loss": 0.0995, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0003835514853770505, | |
| "loss": 0.0961, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00037844532654101405, | |
| "loss": 0.0966, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0003732652999930364, | |
| "loss": 0.0992, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00036801438471817827, | |
| "loss": 0.1008, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00036269560046894763, | |
| "loss": 0.1018, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0003573120060286679, | |
| "loss": 0.0995, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00035186669745240024, | |
| "loss": 0.1009, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0003463628062864312, | |
| "loss": 0.0998, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00034080349776734924, | |
| "loss": 0.1043, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00033519196900174726, | |
| "loss": 0.1006, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0003295314471275954, | |
| "loss": 0.0975, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00032382518745834515, | |
| "loss": 0.0987, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00031807647161082795, | |
| "loss": 0.0996, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0003122886056180284, | |
| "loss": 0.1042, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00030646491802781517, | |
| "loss": 0.1044, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00030060875798872436, | |
| "loss": 0.1033, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00029472349332389523, | |
| "loss": 0.0983, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002888125085942664, | |
| "loss": 0.1014, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00028287920315214646, | |
| "loss": 0.0949, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002769269891862778, | |
| "loss": 0.1037, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002709592897595191, | |
| "loss": 0.0971, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002649795368402735, | |
| "loss": 0.0943, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00025899116932879537, | |
| "loss": 0.102, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002529976310795108, | |
| "loss": 0.0926, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002470023689204893, | |
| "loss": 0.0945, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00024100883067120475, | |
| "loss": 0.0964, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00023502046315972656, | |
| "loss": 0.0889, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0002290407102404809, | |
| "loss": 0.0916, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00022307301081372224, | |
| "loss": 0.0928, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00021712079684785363, | |
| "loss": 0.0937, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002111874914057336, | |
| "loss": 0.0893, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00020527650667610475, | |
| "loss": 0.0923, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001993912420112756, | |
| "loss": 0.092, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00019353508197218492, | |
| "loss": 0.0949, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00018771139438197168, | |
| "loss": 0.0909, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018192352838917208, | |
| "loss": 0.0912, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0001761748125416549, | |
| "loss": 0.0915, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00017046855287240463, | |
| "loss": 0.0947, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00016480803099825278, | |
| "loss": 0.0891, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0001591965022326507, | |
| "loss": 0.0979, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00015363719371356882, | |
| "loss": 0.0881, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00014813330254759985, | |
| "loss": 0.0895, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001426879939713322, | |
| "loss": 0.0931, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00013730439953105243, | |
| "loss": 0.0928, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00013198561528182182, | |
| "loss": 0.0978, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00012673470000696365, | |
| "loss": 0.0916, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00012155467345898602, | |
| "loss": 0.0885, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00011644851462294955, | |
| "loss": 0.0959, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00011141916000328151, | |
| "loss": 0.0929, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0001064695019350187, | |
| "loss": 0.0924, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00010160238692045331, | |
| "loss": 0.0926, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.682061399213524e-05, | |
| "loss": 0.0976, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.21269331031748e-05, | |
| "loss": 0.0958, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.752404354577052e-05, | |
| "loss": 0.0921, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.301459239887074e-05, | |
| "loss": 0.0973, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 7.860117300586384e-05, | |
| "loss": 0.0957, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.428632348317005e-05, | |
| "loss": 0.099, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.007252526059446e-05, | |
| "loss": 0.0934, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 6.596220165428002e-05, | |
| "loss": 0.0925, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 6.195771647308074e-05, | |
| "loss": 0.0937, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 5.8061372659157316e-05, | |
| "loss": 0.0979, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 5.427541096357647e-05, | |
| "loss": 0.099, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 5.060200865767606e-05, | |
| "loss": 0.0915, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.704327828093641e-05, | |
| "loss": 0.0931, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.360126642607842e-05, | |
| "loss": 0.095, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.027795256208749e-05, | |
| "loss": 0.095, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3.707524789583891e-05, | |
| "loss": 0.095, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.3994994272980944e-05, | |
| "loss": 0.0898, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.1038963118706244e-05, | |
| "loss": 0.0901, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.8208854419021823e-05, | |
| "loss": 0.0902, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.5506295743103092e-05, | |
| "loss": 0.0945, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.2932841307293644e-05, | |
| "loss": 0.0904, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.0489971081290192e-05, | |
| "loss": 0.0895, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.817908993702555e-05, | |
| "loss": 0.0936, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.600152684074005e-05, | |
| "loss": 0.0927, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.3958534088705205e-05, | |
| "loss": 0.0947, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.205128658704005e-05, | |
| "loss": 0.0993, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.028088117603332e-05, | |
| "loss": 0.0894, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.648335999360934e-06, | |
| "loss": 0.0909, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.154589918561022e-06, | |
| "loss": 0.0886, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 5.800501973103362e-06, | |
| "loss": 0.0949, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.586850886363874e-06, | |
| "loss": 0.0958, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.5143346177878568e-06, | |
| "loss": 0.0939, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.583569961500276e-06, | |
| "loss": 0.0932, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.7950921915928787e-06, | |
| "loss": 0.0972, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.149354754293397e-06, | |
| "loss": 0.088, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 6.467290071925646e-07, | |
| "loss": 0.0955, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.8750400567992274e-07, | |
| "loss": 0.0879, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 7.188633671079136e-08, | |
| "loss": 0.0985, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.091, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 1310, | |
| "total_flos": 3.149409890779267e+18, | |
| "train_loss": 0.10076319215861895, | |
| "train_runtime": 21644.7687, | |
| "train_samples_per_second": 3.873, | |
| "train_steps_per_second": 0.061 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1310, | |
| "num_train_epochs": 2, | |
| "save_steps": 150, | |
| "total_flos": 3.149409890779267e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |