| { | |
| "best_metric": 1.0848859548568726, | |
| "best_model_checkpoint": "output/Baichuan-13B-Chat_lora_wqs/checkpoint-1900", | |
| "epoch": 1.998465865507543, | |
| "global_step": 1954, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9996768893414955e-05, | |
| "loss": 1.5804, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.998707640886381e-05, | |
| "loss": 1.36, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.99709250517426e-05, | |
| "loss": 1.2505, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.994831899699185e-05, | |
| "loss": 1.2495, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9919264088017345e-05, | |
| "loss": 1.2084, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.98837678351797e-05, | |
| "loss": 1.1923, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.984183941385301e-05, | |
| "loss": 1.1929, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.979348966205315e-05, | |
| "loss": 1.1736, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9738731077636225e-05, | |
| "loss": 1.1626, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.9677577815068056e-05, | |
| "loss": 1.1779, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.1614866256713867, | |
| "eval_runtime": 26.6319, | |
| "eval_samples_per_second": 23.768, | |
| "eval_steps_per_second": 3.004, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.9610045681765385e-05, | |
| "loss": 1.1527, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.953615213400987e-05, | |
| "loss": 1.1638, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.945591627243581e-05, | |
| "loss": 1.155, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.9369358837092853e-05, | |
| "loss": 1.1672, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.927650220208495e-05, | |
| "loss": 1.1674, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.917737036978689e-05, | |
| "loss": 1.1511, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.907198896463996e-05, | |
| "loss": 1.1497, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.8960385226528335e-05, | |
| "loss": 1.1271, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.8842588003737854e-05, | |
| "loss": 1.1888, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.87186277454991e-05, | |
| "loss": 1.1494, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.1362522840499878, | |
| "eval_runtime": 23.9991, | |
| "eval_samples_per_second": 26.376, | |
| "eval_steps_per_second": 3.333, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.858853649411662e-05, | |
| "loss": 1.1425, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.845234787668632e-05, | |
| "loss": 1.1591, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.831009709640329e-05, | |
| "loss": 1.118, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.8161820923462165e-05, | |
| "loss": 1.1469, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.800755768555244e-05, | |
| "loss": 1.1128, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.784734725795123e-05, | |
| "loss": 1.152, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.768123105321596e-05, | |
| "loss": 1.125, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.7509252010479645e-05, | |
| "loss": 1.123, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.7331454584351686e-05, | |
| "loss": 1.1294, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.714788473342685e-05, | |
| "loss": 1.1299, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.1234092712402344, | |
| "eval_runtime": 23.8841, | |
| "eval_samples_per_second": 26.503, | |
| "eval_steps_per_second": 3.35, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.695858990840544e-05, | |
| "loss": 1.1195, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.6763619039827936e-05, | |
| "loss": 1.1233, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.6563022525426905e-05, | |
| "loss": 1.1281, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.6356852217099856e-05, | |
| "loss": 1.0921, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.614516140750604e-05, | |
| "loss": 1.1106, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.592800481629097e-05, | |
| "loss": 1.1103, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.570543857594201e-05, | |
| "loss": 1.1162, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.547752021727873e-05, | |
| "loss": 1.1341, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.52443086545819e-05, | |
| "loss": 1.1098, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.5005864170364784e-05, | |
| "loss": 1.1109, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.115441083908081, | |
| "eval_runtime": 23.9395, | |
| "eval_samples_per_second": 26.442, | |
| "eval_steps_per_second": 3.342, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.476224839979084e-05, | |
| "loss": 1.1114, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.4513524314741714e-05, | |
| "loss": 1.132, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.425975620753973e-05, | |
| "loss": 1.1282, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.4001009674329054e-05, | |
| "loss": 1.1135, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.373735159811988e-05, | |
| "loss": 1.1366, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.3468850131499917e-05, | |
| "loss": 1.1052, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.31955746790177e-05, | |
| "loss": 1.1148, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.291759587924237e-05, | |
| "loss": 1.1329, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.263498558650434e-05, | |
| "loss": 1.1064, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.234781685232187e-05, | |
| "loss": 1.12, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.108825922012329, | |
| "eval_runtime": 23.967, | |
| "eval_samples_per_second": 26.411, | |
| "eval_steps_per_second": 3.338, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.205616390651796e-05, | |
| "loss": 1.0966, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.1760102138032956e-05, | |
| "loss": 1.1145, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.145970807543721e-05, | |
| "loss": 1.1018, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.115505936714943e-05, | |
| "loss": 1.1063, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.084623476136541e-05, | |
| "loss": 1.1037, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.053331408570254e-05, | |
| "loss": 1.0981, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.021637822656529e-05, | |
| "loss": 1.1018, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.9895509108236956e-05, | |
| "loss": 1.1154, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.957078967170325e-05, | |
| "loss": 1.1498, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.9242303853212944e-05, | |
| "loss": 1.1071, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.103700041770935, | |
| "eval_runtime": 23.9888, | |
| "eval_samples_per_second": 26.387, | |
| "eval_steps_per_second": 3.335, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.891013656258133e-05, | |
| "loss": 1.1107, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.857437366124202e-05, | |
| "loss": 1.0919, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.823510194005273e-05, | |
| "loss": 1.1019, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.789240909686087e-05, | |
| "loss": 1.1217, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.754638371383461e-05, | |
| "loss": 1.1171, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.719711523456545e-05, | |
| "loss": 1.0918, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.684469394094805e-05, | |
| "loss": 1.1195, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.648921092984342e-05, | |
| "loss": 1.1083, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.6130758089531404e-05, | |
| "loss": 1.0735, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.576942807595861e-05, | |
| "loss": 1.1161, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.1002016067504883, | |
| "eval_runtime": 24.0418, | |
| "eval_samples_per_second": 26.329, | |
| "eval_steps_per_second": 3.328, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.540531428878795e-05, | |
| "loss": 1.0867, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.5038510847255846e-05, | |
| "loss": 1.105, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.466911256584355e-05, | |
| "loss": 1.1156, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.42972149297686e-05, | |
| "loss": 1.099, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.3922914070303076e-05, | |
| "loss": 1.0994, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.354630673992473e-05, | |
| "loss": 1.1177, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.316749028730757e-05, | |
| "loss": 1.1095, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.278656263215836e-05, | |
| "loss": 1.1083, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.24036222399055e-05, | |
| "loss": 1.0836, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.2018768096246834e-05, | |
| "loss": 1.0982, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.0972065925598145, | |
| "eval_runtime": 24.0261, | |
| "eval_samples_per_second": 26.346, | |
| "eval_steps_per_second": 3.33, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.1632099681562996e-05, | |
| "loss": 1.1041, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.1243716945202864e-05, | |
| "loss": 1.0974, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.085372027964777e-05, | |
| "loss": 1.0945, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.0462210494561283e-05, | |
| "loss": 1.1045, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.0069288790730966e-05, | |
| "loss": 1.0842, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.9675056733909196e-05, | |
| "loss": 1.097, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.9279616228559542e-05, | |
| "loss": 1.1034, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.8883069491515696e-05, | |
| "loss": 1.1033, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.8485519025559503e-05, | |
| "loss": 1.0894, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.8087067592925252e-05, | |
| "loss": 1.1062, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.0946753025054932, | |
| "eval_runtime": 23.9793, | |
| "eval_samples_per_second": 26.398, | |
| "eval_steps_per_second": 3.336, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.7687818188736757e-05, | |
| "loss": 1.1243, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.7287874014384346e-05, | |
| "loss": 1.0975, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.6887338450848448e-05, | |
| "loss": 1.0885, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.64863150319768e-05, | |
| "loss": 1.0938, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.6084907417722176e-05, | |
| "loss": 1.1014, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.5683219367347432e-05, | |
| "loss": 1.105, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.528135471260493e-05, | |
| "loss": 1.0993, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.4879417330897267e-05, | |
| "loss": 1.0867, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.4477511118426093e-05, | |
| "loss": 1.059, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2.4075739963336182e-05, | |
| "loss": 1.0744, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 1.0925548076629639, | |
| "eval_runtime": 23.9765, | |
| "eval_samples_per_second": 26.401, | |
| "eval_steps_per_second": 3.337, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.367420771886154e-05, | |
| "loss": 1.096, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 2.3273018176480492e-05, | |
| "loss": 1.0873, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2.2872275039086823e-05, | |
| "loss": 1.097, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.2472081894183744e-05, | |
| "loss": 1.0801, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.207254218710772e-05, | |
| "loss": 1.1006, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2.1673759194289033e-05, | |
| "loss": 1.0811, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2.1275835996556e-05, | |
| "loss": 1.0969, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.08788754524898e-05, | |
| "loss": 1.0888, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.0482980171836648e-05, | |
| "loss": 1.09, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.008825248898443e-05, | |
| "loss": 1.0867, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 1.0904080867767334, | |
| "eval_runtime": 23.9806, | |
| "eval_samples_per_second": 26.396, | |
| "eval_steps_per_second": 3.336, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.969479443651036e-05, | |
| "loss": 1.0925, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.930270771880679e-05, | |
| "loss": 1.0827, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.8912093685791748e-05, | |
| "loss": 1.0976, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.8523053306711203e-05, | |
| "loss": 1.0746, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.813568714403957e-05, | |
| "loss": 1.0922, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.7750095327485605e-05, | |
| "loss": 1.121, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.7366377528109895e-05, | |
| "loss": 1.0915, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.6984632932561124e-05, | |
| "loss": 1.0866, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.6604960217437398e-05, | |
| "loss": 1.0822, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.6227457523779532e-05, | |
| "loss": 1.0809, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 1.088823914527893, | |
| "eval_runtime": 23.9277, | |
| "eval_samples_per_second": 26.455, | |
| "eval_steps_per_second": 3.343, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.5852222431702658e-05, | |
| "loss": 1.0903, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.547935193517295e-05, | |
| "loss": 1.088, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.510894241693573e-05, | |
| "loss": 1.0988, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.4741089623601678e-05, | |
| "loss": 1.0935, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.4375888640897438e-05, | |
| "loss": 1.0812, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.4013433869087006e-05, | |
| "loss": 1.1036, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.3653818998570378e-05, | |
| "loss": 1.0917, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.329713698566567e-05, | |
| "loss": 1.0697, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.2943480028580917e-05, | |
| "loss": 1.092, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.2592939543581947e-05, | |
| "loss": 1.0994, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.0873268842697144, | |
| "eval_runtime": 23.9478, | |
| "eval_samples_per_second": 26.433, | |
| "eval_steps_per_second": 3.341, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.2245606141362318e-05, | |
| "loss": 1.0737, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.1901569603621487e-05, | |
| "loss": 1.0718, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.1560918859857247e-05, | |
| "loss": 1.0992, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.1223741964378518e-05, | |
| "loss": 1.0757, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.0890126073544276e-05, | |
| "loss": 1.0916, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.0560157423234681e-05, | |
| "loss": 1.1017, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.0233921306560029e-05, | |
| "loss": 1.0897, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.911502051813499e-06, | |
| "loss": 1.1047, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.592983000673272e-06, | |
| "loss": 1.0877, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 9.278446486659642e-06, | |
| "loss": 1.0622, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 1.0861936807632446, | |
| "eval_runtime": 23.9135, | |
| "eval_samples_per_second": 26.47, | |
| "eval_steps_per_second": 3.345, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.967973813852743e-06, | |
| "loss": 1.0791, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.66164523587637e-06, | |
| "loss": 1.0952, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.359539935153368e-06, | |
| "loss": 1.0998, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.061736002437862e-06, | |
| "loss": 1.0714, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 7.768310416629703e-06, | |
| "loss": 1.0934, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.479339024876283e-06, | |
| "loss": 1.1074, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.1948965229669425e-06, | |
| "loss": 1.0993, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 6.915056436024964e-06, | |
| "loss": 1.0962, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 6.63989109950216e-06, | |
| "loss": 1.077, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 6.3694716404810065e-06, | |
| "loss": 1.1079, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 1.0856590270996094, | |
| "eval_runtime": 23.9592, | |
| "eval_samples_per_second": 26.42, | |
| "eval_steps_per_second": 3.339, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 6.10386795928907e-06, | |
| "loss": 1.0622, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 5.843148711430621e-06, | |
| "loss": 1.1085, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 5.5873812898399546e-06, | |
| "loss": 1.0871, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 5.336631807461076e-06, | |
| "loss": 1.1106, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 5.090965080158278e-06, | |
| "loss": 1.0841, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.850444609961988e-06, | |
| "loss": 1.1075, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.615132568654215e-06, | |
| "loss": 1.0983, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.385089781697863e-06, | |
| "loss": 1.0859, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.160375712514019e-06, | |
| "loss": 1.0759, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 3.941048447111387e-06, | |
| "loss": 1.0612, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 1.085319995880127, | |
| "eval_runtime": 23.9411, | |
| "eval_samples_per_second": 26.44, | |
| "eval_steps_per_second": 3.342, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3.727164679071696e-06, | |
| "loss": 1.0806, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.5187796948950384e-06, | |
| "loss": 1.0861, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.315947359708993e-06, | |
| "loss": 1.0712, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.118720103345063e-06, | |
| "loss": 1.086, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.9271489067861953e-06, | |
| "loss": 1.1087, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.7412832889887664e-06, | |
| "loss": 1.1036, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.5611712940825065e-06, | |
| "loss": 1.0712, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.3868594789516336e-06, | |
| "loss": 1.0695, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.2183929012004527e-06, | |
| "loss": 1.0858, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.055815107506451e-06, | |
| "loss": 1.0839, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 1.0849649906158447, | |
| "eval_runtime": 23.9223, | |
| "eval_samples_per_second": 26.461, | |
| "eval_steps_per_second": 3.344, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.899168122364023e-06, | |
| "loss": 1.0925, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.7484924372215744e-06, | |
| "loss": 1.0888, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.6038270000149903e-06, | |
| "loss": 1.0667, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.4652092051000155e-06, | |
| "loss": 1.0893, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.3326748835862463e-06, | |
| "loss": 1.061, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.2062582940751965e-06, | |
| "loss": 1.1043, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.085992113804854e-06, | |
| "loss": 1.0908, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 9.719074302029813e-07, | |
| "loss": 1.1128, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.640337328513743e-07, | |
| "loss": 1.082, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.623989058631459e-07, | |
| "loss": 1.0702, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 1.0849045515060425, | |
| "eval_runtime": 23.9602, | |
| "eval_samples_per_second": 26.419, | |
| "eval_steps_per_second": 3.339, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 6.67029220674989e-07, | |
| "loss": 1.1089, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 5.779493292563304e-07, | |
| "loss": 1.0929, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 4.951822577370785e-07, | |
| "loss": 1.0648, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.1874940045561194e-07, | |
| "loss": 1.0654, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.4867051442860896e-07, | |
| "loss": 1.0822, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.8496371424407975e-07, | |
| "loss": 1.0873, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.2764546737895076e-07, | |
| "loss": 1.0725, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.7673058994241432e-07, | |
| "loss": 1.0772, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.3223224284613366e-07, | |
| "loss": 1.07, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 9.416192840228932e-08, | |
| "loss": 1.0886, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 1.0848859548568726, | |
| "eval_runtime": 23.9384, | |
| "eval_samples_per_second": 26.443, | |
| "eval_steps_per_second": 3.342, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 6.252948735037678e-08, | |
| "loss": 1.0917, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 3.734309631348854e-08, | |
| "loss": 1.1042, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.8609265684738086e-08, | |
| "loss": 1.0908, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.332837944400538e-09, | |
| "loss": 1.0769, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 5.16986408199971e-10, | |
| "loss": 1.078, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 1954, | |
| "total_flos": 4.405931905703215e+18, | |
| "train_loss": 1.1088850573849165, | |
| "train_runtime": 12573.3474, | |
| "train_samples_per_second": 9.954, | |
| "train_steps_per_second": 0.155 | |
| } | |
| ], | |
| "max_steps": 1954, | |
| "num_train_epochs": 2, | |
| "total_flos": 4.405931905703215e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |