| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.915300209591912, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5.555555555555555e-05, | |
| "loss": 13.7427, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001111111111111111, | |
| "loss": 8.8821, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00016666666666666666, | |
| "loss": 2.5857, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002222222222222222, | |
| "loss": 1.3518, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002777777777777778, | |
| "loss": 1.0054, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0003333333333333333, | |
| "loss": 0.864, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0003888888888888889, | |
| "loss": 0.8669, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0004444444444444444, | |
| "loss": 0.9395, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0005, | |
| "loss": 1.0424, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0004985515643105447, | |
| "loss": 0.6298, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.61441171169281, | |
| "eval_rouge1": 0.07727272727272727, | |
| "eval_rouge2": 0.061111111111111116, | |
| "eval_rougeL": 0.06893939393939394, | |
| "eval_rougeLsum": 0.08333333333333333, | |
| "eval_runtime": 91.9317, | |
| "eval_samples_per_second": 0.218, | |
| "eval_steps_per_second": 0.218, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0004971031286210893, | |
| "loss": 0.5699, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0004956546929316338, | |
| "loss": 0.6074, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0004942062572421785, | |
| "loss": 0.6291, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0004927578215527231, | |
| "loss": 0.5098, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0004913093858632677, | |
| "loss": 0.4448, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0004898609501738123, | |
| "loss": 0.4508, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0004884125144843569, | |
| "loss": 0.4255, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00048696407879490153, | |
| "loss": 0.3705, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0004855156431054461, | |
| "loss": 0.4009, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00048406720741599077, | |
| "loss": 0.4317, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.176011323928833, | |
| "eval_rouge1": 0.16153846153846152, | |
| "eval_rouge2": 0.06988636363636364, | |
| "eval_rougeL": 0.15999999999999998, | |
| "eval_rougeLsum": 0.15999999999999998, | |
| "eval_runtime": 88.2692, | |
| "eval_samples_per_second": 0.227, | |
| "eval_steps_per_second": 0.227, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00048261877172653536, | |
| "loss": 0.3679, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00048117033603707995, | |
| "loss": 0.3252, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0004797219003476246, | |
| "loss": 0.3707, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0004782734646581692, | |
| "loss": 0.3543, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0004768250289687138, | |
| "loss": 0.3434, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0004753765932792584, | |
| "loss": 0.4007, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.000473928157589803, | |
| "loss": 0.3552, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00047247972190034765, | |
| "loss": 0.388, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00047103128621089224, | |
| "loss": 0.307, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0004695828505214368, | |
| "loss": 0.2588, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.0633952617645264, | |
| "eval_rouge1": 0.08, | |
| "eval_rouge2": 0.05555555555555556, | |
| "eval_rougeL": 0.08414141414141416, | |
| "eval_rougeLsum": 0.08383838383838385, | |
| "eval_runtime": 88.5138, | |
| "eval_samples_per_second": 0.226, | |
| "eval_steps_per_second": 0.226, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00046813441483198147, | |
| "loss": 0.2965, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00046668597914252606, | |
| "loss": 0.3096, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0004652375434530707, | |
| "loss": 0.301, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00046378910776361535, | |
| "loss": 0.3153, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00046234067207415994, | |
| "loss": 0.3549, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0004608922363847045, | |
| "loss": 0.356, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00045944380069524917, | |
| "loss": 0.3278, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00045799536500579376, | |
| "loss": 0.2985, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00045654692931633835, | |
| "loss": 0.3152, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.000455098493626883, | |
| "loss": 0.2665, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.044259786605835, | |
| "eval_rouge1": 0.06307692307692307, | |
| "eval_rouge2": 0.021590909090909088, | |
| "eval_rougeL": 0.06307692307692307, | |
| "eval_rougeLsum": 0.06307692307692307, | |
| "eval_runtime": 80.5878, | |
| "eval_samples_per_second": 0.248, | |
| "eval_steps_per_second": 0.248, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0004536500579374276, | |
| "loss": 0.2323, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00045220162224797217, | |
| "loss": 0.2222, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0004507531865585168, | |
| "loss": 0.2516, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0004493047508690614, | |
| "loss": 0.2851, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.000447856315179606, | |
| "loss": 0.2677, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00044640787949015064, | |
| "loss": 0.2447, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00044495944380069523, | |
| "loss": 0.3186, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0004435110081112398, | |
| "loss": 0.3035, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0004420625724217845, | |
| "loss": 0.3036, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0004406141367323291, | |
| "loss": 0.1972, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.0465357303619385, | |
| "eval_rouge1": 0.1908791208791209, | |
| "eval_rouge2": 0.10681818181818181, | |
| "eval_rougeL": 0.17934065934065935, | |
| "eval_rougeLsum": 0.19159340659340657, | |
| "eval_runtime": 84.3482, | |
| "eval_samples_per_second": 0.237, | |
| "eval_steps_per_second": 0.237, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00043916570104287375, | |
| "loss": 0.279, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00043771726535341834, | |
| "loss": 0.272, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00043626882966396293, | |
| "loss": 0.2272, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0004348203939745076, | |
| "loss": 0.2495, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00043337195828505216, | |
| "loss": 0.1965, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00043192352259559675, | |
| "loss": 0.2364, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0004304750869061414, | |
| "loss": 0.2478, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.000429026651216686, | |
| "loss": 0.2046, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0004275782155272306, | |
| "loss": 0.2661, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0004261297798377752, | |
| "loss": 0.2041, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.9551488757133484, | |
| "eval_rouge1": 0.09038461538461538, | |
| "eval_rouge2": 0.05051948051948052, | |
| "eval_rougeL": 0.09679487179487178, | |
| "eval_rougeLsum": 0.09871794871794871, | |
| "eval_runtime": 89.0139, | |
| "eval_samples_per_second": 0.225, | |
| "eval_steps_per_second": 0.225, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0004246813441483198, | |
| "loss": 0.2816, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0004232329084588644, | |
| "loss": 0.1904, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00042178447276940904, | |
| "loss": 0.21, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0004203360370799537, | |
| "loss": 0.1662, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0004188876013904983, | |
| "loss": 0.3052, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0004174391657010429, | |
| "loss": 0.1744, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0004159907300115875, | |
| "loss": 0.288, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0004145422943221321, | |
| "loss": 0.2303, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00041309385863267674, | |
| "loss": 0.2866, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00041164542294322133, | |
| "loss": 0.238, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.9423090219497681, | |
| "eval_rouge1": 0.1, | |
| "eval_rouge2": 0.07291666666666667, | |
| "eval_rougeL": 0.1, | |
| "eval_rougeLsum": 0.10333333333333335, | |
| "eval_runtime": 88.0456, | |
| "eval_samples_per_second": 0.227, | |
| "eval_steps_per_second": 0.227, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0004101969872537659, | |
| "loss": 0.2342, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00040874855156431057, | |
| "loss": 0.2716, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00040730011587485516, | |
| "loss": 0.2453, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00040585168018539974, | |
| "loss": 0.2313, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0004044032444959444, | |
| "loss": 0.2306, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.000402954808806489, | |
| "loss": 0.1773, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00040150637311703357, | |
| "loss": 0.1957, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0004000579374275782, | |
| "loss": 0.2758, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0003986095017381228, | |
| "loss": 0.2649, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0003971610660486675, | |
| "loss": 0.275, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.9273136258125305, | |
| "eval_rouge1": 0.14666666666666667, | |
| "eval_rouge2": 0.10977272727272727, | |
| "eval_rougeL": 0.15038461538461537, | |
| "eval_rougeLsum": 0.15153846153846154, | |
| "eval_runtime": 87.8017, | |
| "eval_samples_per_second": 0.228, | |
| "eval_steps_per_second": 0.228, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0003957126303592121, | |
| "loss": 0.2102, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0003942641946697567, | |
| "loss": 0.2146, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0003928157589803013, | |
| "loss": 0.1918, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0003913673232908459, | |
| "loss": 0.2512, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0003899188876013905, | |
| "loss": 0.2499, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00038847045191193515, | |
| "loss": 0.228, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00038702201622247974, | |
| "loss": 0.2507, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0003855735805330243, | |
| "loss": 0.1735, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00038412514484356897, | |
| "loss": 0.2752, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00038267670915411356, | |
| "loss": 0.2379, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 0.9023244976997375, | |
| "eval_rouge1": 0.1, | |
| "eval_rouge2": 0.08333333333333333, | |
| "eval_rougeL": 0.1, | |
| "eval_rougeLsum": 0.1, | |
| "eval_runtime": 80.7798, | |
| "eval_samples_per_second": 0.248, | |
| "eval_steps_per_second": 0.248, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00038122827346465815, | |
| "loss": 0.1993, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0003797798377752028, | |
| "loss": 0.2058, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0003783314020857474, | |
| "loss": 0.2675, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00037688296639629197, | |
| "loss": 0.1928, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0003754345307068366, | |
| "loss": 0.1903, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00037398609501738126, | |
| "loss": 0.1967, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00037253765932792585, | |
| "loss": 0.2044, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0003710892236384705, | |
| "loss": 0.2027, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0003696407879490151, | |
| "loss": 0.25, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00036819235225955967, | |
| "loss": 0.2896, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.9184179306030273, | |
| "eval_rouge1": 0.19, | |
| "eval_rouge2": 0.1, | |
| "eval_rougeL": 0.18893939393939393, | |
| "eval_rougeLsum": 0.19848484848484846, | |
| "eval_runtime": 81.9559, | |
| "eval_samples_per_second": 0.244, | |
| "eval_steps_per_second": 0.244, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0003667439165701043, | |
| "loss": 0.1462, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0003652954808806489, | |
| "loss": 0.1944, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0003638470451911935, | |
| "loss": 0.2296, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00036239860950173814, | |
| "loss": 0.2446, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.00036095017381228273, | |
| "loss": 0.1448, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0003595017381228273, | |
| "loss": 0.1507, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00035805330243337196, | |
| "loss": 0.1636, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.00035660486674391655, | |
| "loss": 0.1909, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0003551564310544612, | |
| "loss": 0.1895, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0003537079953650058, | |
| "loss": 0.2663, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.9002671241760254, | |
| "eval_rouge1": 0.07948717948717948, | |
| "eval_rouge2": 0.06779220779220778, | |
| "eval_rougeL": 0.08782051282051281, | |
| "eval_rougeLsum": 0.08333333333333333, | |
| "eval_runtime": 84.9078, | |
| "eval_samples_per_second": 0.236, | |
| "eval_steps_per_second": 0.236, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0003522595596755504, | |
| "loss": 0.1672, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.00035081112398609507, | |
| "loss": 0.1909, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.00034936268829663966, | |
| "loss": 0.1675, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00034791425260718425, | |
| "loss": 0.2636, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0003464658169177289, | |
| "loss": 0.2119, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0003450173812282735, | |
| "loss": 0.2114, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0003435689455388181, | |
| "loss": 0.1456, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0003421205098493627, | |
| "loss": 0.1993, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0003406720741599073, | |
| "loss": 0.1467, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0003392236384704519, | |
| "loss": 0.237, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.9139176607131958, | |
| "eval_rouge1": 0.19904761904761903, | |
| "eval_rouge2": 0.10285714285714284, | |
| "eval_rougeL": 0.19511904761904764, | |
| "eval_rougeLsum": 0.20619047619047615, | |
| "eval_runtime": 85.9903, | |
| "eval_samples_per_second": 0.233, | |
| "eval_steps_per_second": 0.233, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.00033777520278099654, | |
| "loss": 0.1996, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00033632676709154113, | |
| "loss": 0.1725, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0003348783314020857, | |
| "loss": 0.2089, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.00033342989571263036, | |
| "loss": 0.183, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.00033198146002317495, | |
| "loss": 0.1631, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00033053302433371954, | |
| "loss": 0.1889, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.00032908458864426424, | |
| "loss": 0.172, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.00032763615295480883, | |
| "loss": 0.1236, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0003261877172653534, | |
| "loss": 0.1682, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00032473928157589806, | |
| "loss": 0.2019, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 0.920964241027832, | |
| "eval_rouge1": 0.11282051282051282, | |
| "eval_rouge2": 0.03636363636363636, | |
| "eval_rougeL": 0.1128205128205128, | |
| "eval_rougeLsum": 0.11607142857142858, | |
| "eval_runtime": 82.9262, | |
| "eval_samples_per_second": 0.241, | |
| "eval_steps_per_second": 0.241, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.00032329084588644265, | |
| "loss": 0.1681, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.00032184241019698724, | |
| "loss": 0.2372, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0003203939745075319, | |
| "loss": 0.1343, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.0003189455388180765, | |
| "loss": 0.2125, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0003174971031286211, | |
| "loss": 0.2217, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0003160486674391657, | |
| "loss": 0.1542, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.0003146002317497103, | |
| "loss": 0.171, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.00031315179606025494, | |
| "loss": 0.1808, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.00031170336037079953, | |
| "loss": 0.1423, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.0003102549246813441, | |
| "loss": 0.1794, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 0.9037507772445679, | |
| "eval_rouge1": 0.11666666666666667, | |
| "eval_rouge2": 0.08636363636363635, | |
| "eval_rougeL": 0.11833333333333333, | |
| "eval_rougeLsum": 0.12064102564102563, | |
| "eval_runtime": 84.5851, | |
| "eval_samples_per_second": 0.236, | |
| "eval_steps_per_second": 0.236, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.00030880648899188877, | |
| "loss": 0.2313, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.00030735805330243336, | |
| "loss": 0.1548, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.000305909617612978, | |
| "loss": 0.2318, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00030446118192352264, | |
| "loss": 0.1959, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00030301274623406723, | |
| "loss": 0.1438, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0003015643105446118, | |
| "loss": 0.1953, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.00030011587485515647, | |
| "loss": 0.1542, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.00029866743916570106, | |
| "loss": 0.1693, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00029721900347624565, | |
| "loss": 0.1836, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0002957705677867903, | |
| "loss": 0.1847, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.8892697095870972, | |
| "eval_rouge1": 0.14335664335664336, | |
| "eval_rouge2": 0.13131313131313133, | |
| "eval_rougeL": 0.14375624375624377, | |
| "eval_rougeLsum": 0.14725274725274726, | |
| "eval_runtime": 86.985, | |
| "eval_samples_per_second": 0.23, | |
| "eval_steps_per_second": 0.23, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002943221320973349, | |
| "loss": 0.1245, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00029287369640787947, | |
| "loss": 0.1917, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0002914252607184241, | |
| "loss": 0.205, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.0002899768250289687, | |
| "loss": 0.1493, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0002885283893395133, | |
| "loss": 0.1596, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.00028707995365005794, | |
| "loss": 0.1689, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.0002856315179606025, | |
| "loss": 0.1371, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0002841830822711471, | |
| "loss": 0.1676, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.0002827346465816918, | |
| "loss": 0.1441, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.0002812862108922364, | |
| "loss": 0.1436, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "eval_loss": 0.8872199058532715, | |
| "eval_rouge1": 0.16825396825396824, | |
| "eval_rouge2": 0.05833333333333333, | |
| "eval_rougeL": 0.1650793650793651, | |
| "eval_rougeLsum": 0.17285714285714288, | |
| "eval_runtime": 83.5131, | |
| "eval_samples_per_second": 0.239, | |
| "eval_steps_per_second": 0.239, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.000279837775202781, | |
| "loss": 0.2173, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.00027838933951332564, | |
| "loss": 0.1457, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.0002769409038238702, | |
| "loss": 0.1503, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.00027549246813441487, | |
| "loss": 0.1371, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.00027404403244495946, | |
| "loss": 0.1331, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.00027259559675550405, | |
| "loss": 0.2068, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.0002711471610660487, | |
| "loss": 0.2001, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 0.0002696987253765933, | |
| "loss": 0.177, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.00026825028968713787, | |
| "loss": 0.1772, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.0002668018539976825, | |
| "loss": 0.138, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_loss": 0.8929020762443542, | |
| "eval_rouge1": 0.22999999999999998, | |
| "eval_rouge2": 0.12491883116883117, | |
| "eval_rougeL": 0.22615384615384615, | |
| "eval_rougeLsum": 0.23115384615384618, | |
| "eval_runtime": 86.6494, | |
| "eval_samples_per_second": 0.231, | |
| "eval_steps_per_second": 0.231, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.0002653534183082271, | |
| "loss": 0.164, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 0.0002639049826187717, | |
| "loss": 0.1249, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.00026245654692931634, | |
| "loss": 0.1356, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.000261008111239861, | |
| "loss": 0.1374, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.00025955967555040557, | |
| "loss": 0.2013, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 0.0002581112398609502, | |
| "loss": 0.1337, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 0.0002566628041714948, | |
| "loss": 0.1226, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.0002552143684820394, | |
| "loss": 0.1166, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.00025376593279258404, | |
| "loss": 0.2308, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.00025231749710312863, | |
| "loss": 0.1265, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_loss": 0.9203845858573914, | |
| "eval_rouge1": 0.17454545454545453, | |
| "eval_rouge2": 0.07291666666666667, | |
| "eval_rougeL": 0.16999999999999998, | |
| "eval_rougeLsum": 0.17727272727272728, | |
| "eval_runtime": 87.9704, | |
| "eval_samples_per_second": 0.227, | |
| "eval_steps_per_second": 0.227, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.0002508690614136732, | |
| "loss": 0.1526, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.00024942062572421786, | |
| "loss": 0.2201, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 0.00024797219003476245, | |
| "loss": 0.1271, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.0002465237543453071, | |
| "loss": 0.1749, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 0.0002450753186558517, | |
| "loss": 0.133, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.0002436268829663963, | |
| "loss": 0.2259, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.00024217844727694092, | |
| "loss": 0.1549, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.00024073001158748554, | |
| "loss": 0.1173, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 0.00023928157589803013, | |
| "loss": 0.1337, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.00023783314020857474, | |
| "loss": 0.1828, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 0.9094276428222656, | |
| "eval_rouge1": 0.18, | |
| "eval_rouge2": 0.14886363636363636, | |
| "eval_rougeL": 0.18, | |
| "eval_rougeLsum": 0.18615384615384614, | |
| "eval_runtime": 84.5106, | |
| "eval_samples_per_second": 0.237, | |
| "eval_steps_per_second": 0.237, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.00023638470451911936, | |
| "loss": 0.1821, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 0.00023493626882966395, | |
| "loss": 0.1257, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.00023348783314020857, | |
| "loss": 0.172, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.0002320393974507532, | |
| "loss": 0.1833, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.0002305909617612978, | |
| "loss": 0.1334, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.00022914252607184242, | |
| "loss": 0.1736, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 0.00022769409038238703, | |
| "loss": 0.1163, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 0.00022624565469293165, | |
| "loss": 0.1844, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.00022479721900347624, | |
| "loss": 0.1358, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.00022334878331402086, | |
| "loss": 0.1447, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_loss": 0.89415442943573, | |
| "eval_rouge1": 0.19, | |
| "eval_rouge2": 0.09886363636363635, | |
| "eval_rougeL": 0.18615384615384617, | |
| "eval_rougeLsum": 0.19615384615384615, | |
| "eval_runtime": 84.0506, | |
| "eval_samples_per_second": 0.238, | |
| "eval_steps_per_second": 0.238, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 0.00022190034762456547, | |
| "loss": 0.1566, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.0002204519119351101, | |
| "loss": 0.1132, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 0.0002190034762456547, | |
| "loss": 0.1013, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.00021755504055619932, | |
| "loss": 0.1554, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.0002161066048667439, | |
| "loss": 0.1405, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.00021465816917728853, | |
| "loss": 0.152, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.00021320973348783315, | |
| "loss": 0.1591, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.00021176129779837773, | |
| "loss": 0.152, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 0.00021031286210892235, | |
| "loss": 0.1059, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 0.000208864426419467, | |
| "loss": 0.099, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_loss": 0.9297454953193665, | |
| "eval_rouge1": 0.23864468864468863, | |
| "eval_rouge2": 0.15, | |
| "eval_rougeL": 0.23516483516483513, | |
| "eval_rougeLsum": 0.24514652014652014, | |
| "eval_runtime": 85.7086, | |
| "eval_samples_per_second": 0.233, | |
| "eval_steps_per_second": 0.233, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 0.0002074159907300116, | |
| "loss": 0.0916, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.0002059675550405562, | |
| "loss": 0.2006, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.00020451911935110082, | |
| "loss": 0.144, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.00020307068366164544, | |
| "loss": 0.1893, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.00020162224797219002, | |
| "loss": 0.1697, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 0.00020017381228273464, | |
| "loss": 0.1101, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00019872537659327929, | |
| "loss": 0.1539, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.00019727694090382387, | |
| "loss": 0.1038, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.0001958285052143685, | |
| "loss": 0.1466, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.0001943800695249131, | |
| "loss": 0.1366, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "eval_loss": 0.9124263525009155, | |
| "eval_rouge1": 0.12, | |
| "eval_rouge2": 0.07291666666666667, | |
| "eval_rougeL": 0.12, | |
| "eval_rougeLsum": 0.12454545454545454, | |
| "eval_runtime": 91.5173, | |
| "eval_samples_per_second": 0.219, | |
| "eval_steps_per_second": 0.219, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 0.0001929316338354577, | |
| "loss": 0.1298, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 0.00019148319814600231, | |
| "loss": 0.1886, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.00019003476245654693, | |
| "loss": 0.1579, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 0.00018858632676709152, | |
| "loss": 0.1078, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.00018713789107763616, | |
| "loss": 0.1509, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.00018568945538818078, | |
| "loss": 0.108, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.0001842410196987254, | |
| "loss": 0.1305, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 0.00018279258400927, | |
| "loss": 0.1257, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.0001813441483198146, | |
| "loss": 0.117, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 0.00017989571263035922, | |
| "loss": 0.1519, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "eval_loss": 0.9040172696113586, | |
| "eval_rouge1": 0.18727272727272726, | |
| "eval_rouge2": 0.09861111111111112, | |
| "eval_rougeL": 0.18333333333333332, | |
| "eval_rougeLsum": 0.1906060606060606, | |
| "eval_runtime": 82.9032, | |
| "eval_samples_per_second": 0.241, | |
| "eval_steps_per_second": 0.241, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 0.0001784472769409038, | |
| "loss": 0.1536, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 0.00017699884125144843, | |
| "loss": 0.1159, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 0.00017555040556199307, | |
| "loss": 0.1257, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.00017410196987253766, | |
| "loss": 0.1698, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 0.00017265353418308228, | |
| "loss": 0.1369, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 0.0001712050984936269, | |
| "loss": 0.0809, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.00016975666280417148, | |
| "loss": 0.1003, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.0001683082271147161, | |
| "loss": 0.1066, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 0.00016685979142526072, | |
| "loss": 0.1621, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 0.00016541135573580533, | |
| "loss": 0.119, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_loss": 0.9120545387268066, | |
| "eval_rouge1": 0.12, | |
| "eval_rouge2": 0.04583333333333333, | |
| "eval_rougeL": 0.11285714285714285, | |
| "eval_rougeLsum": 0.12285714285714286, | |
| "eval_runtime": 84.1673, | |
| "eval_samples_per_second": 0.238, | |
| "eval_steps_per_second": 0.238, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 0.00016396292004634995, | |
| "loss": 0.1185, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.00016251448435689457, | |
| "loss": 0.1657, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.00016106604866743918, | |
| "loss": 0.1233, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 0.00015961761297798377, | |
| "loss": 0.1611, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.0001581691772885284, | |
| "loss": 0.1613, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.000156720741599073, | |
| "loss": 0.1107, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 0.0001552723059096176, | |
| "loss": 0.1436, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 0.00015382387022016221, | |
| "loss": 0.129, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 0.00015237543453070686, | |
| "loss": 0.1586, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 0.00015092699884125145, | |
| "loss": 0.1364, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_loss": 0.9120429754257202, | |
| "eval_rouge1": 0.20904761904761907, | |
| "eval_rouge2": 0.12583333333333332, | |
| "eval_rougeL": 0.20666666666666664, | |
| "eval_rougeLsum": 0.21904761904761902, | |
| "eval_runtime": 82.9463, | |
| "eval_samples_per_second": 0.241, | |
| "eval_steps_per_second": 0.241, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 0.00014947856315179606, | |
| "loss": 0.1688, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 0.00014803012746234068, | |
| "loss": 0.1385, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0001465816917728853, | |
| "loss": 0.1592, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.0001451332560834299, | |
| "loss": 0.1014, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.0001436848203939745, | |
| "loss": 0.0796, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 0.00014223638470451912, | |
| "loss": 0.0981, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 0.00014078794901506374, | |
| "loss": 0.093, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 0.00013933951332560835, | |
| "loss": 0.1599, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.00013789107763615297, | |
| "loss": 0.1223, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 0.00013644264194669756, | |
| "loss": 0.1, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "eval_loss": 0.9408878087997437, | |
| "eval_rouge1": 0.12507936507936507, | |
| "eval_rouge2": 0.08333333333333333, | |
| "eval_rougeL": 0.12396825396825398, | |
| "eval_rougeLsum": 0.13111111111111112, | |
| "eval_runtime": 96.2103, | |
| "eval_samples_per_second": 0.208, | |
| "eval_steps_per_second": 0.208, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.00013499420625724218, | |
| "loss": 0.1284, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 0.0001335457705677868, | |
| "loss": 0.1523, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 0.00013209733487833138, | |
| "loss": 0.1051, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.00013064889918887603, | |
| "loss": 0.1216, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 0.00012920046349942064, | |
| "loss": 0.1219, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 0.00012775202780996523, | |
| "loss": 0.1482, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 0.00012630359212050985, | |
| "loss": 0.1076, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 0.00012485515643105447, | |
| "loss": 0.121, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.00012340672074159908, | |
| "loss": 0.1448, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 0.0001219582850521437, | |
| "loss": 0.1683, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "eval_loss": 0.9422550201416016, | |
| "eval_rouge1": 0.13818181818181818, | |
| "eval_rouge2": 0.0951010101010101, | |
| "eval_rougeL": 0.13713286713286715, | |
| "eval_rougeLsum": 0.14174825174825176, | |
| "eval_runtime": 96.365, | |
| "eval_samples_per_second": 0.208, | |
| "eval_steps_per_second": 0.208, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 0.0001205098493626883, | |
| "loss": 0.103, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 0.0001190614136732329, | |
| "loss": 0.1434, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 0.00011761297798377752, | |
| "loss": 0.1419, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 0.00011616454229432214, | |
| "loss": 0.1145, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00011471610660486674, | |
| "loss": 0.1302, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 0.00011326767091541136, | |
| "loss": 0.0718, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 0.00011181923522595596, | |
| "loss": 0.1166, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 0.0001103707995365006, | |
| "loss": 0.1265, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 0.0001089223638470452, | |
| "loss": 0.0972, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 0.0001074739281575898, | |
| "loss": 0.1395, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "eval_loss": 0.9336325526237488, | |
| "eval_rouge1": 0.16115384615384615, | |
| "eval_rouge2": 0.12329545454545454, | |
| "eval_rougeL": 0.15999999999999998, | |
| "eval_rougeLsum": 0.16307692307692306, | |
| "eval_runtime": 93.5346, | |
| "eval_samples_per_second": 0.214, | |
| "eval_steps_per_second": 0.214, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 0.00010602549246813442, | |
| "loss": 0.0808, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 0.00010457705677867903, | |
| "loss": 0.1205, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.00010312862108922364, | |
| "loss": 0.119, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 0.00010168018539976825, | |
| "loss": 0.1357, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 0.00010023174971031286, | |
| "loss": 0.1144, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 9.878331402085749e-05, | |
| "loss": 0.138, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 9.733487833140209e-05, | |
| "loss": 0.0998, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 9.588644264194669e-05, | |
| "loss": 0.1437, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 9.443800695249131e-05, | |
| "loss": 0.1053, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 9.298957126303593e-05, | |
| "loss": 0.1067, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_loss": 0.9290033578872681, | |
| "eval_rouge1": 0.2234265734265734, | |
| "eval_rouge2": 0.13156565656565655, | |
| "eval_rougeL": 0.21744755244755246, | |
| "eval_rougeLsum": 0.2169230769230769, | |
| "eval_runtime": 91.8958, | |
| "eval_samples_per_second": 0.218, | |
| "eval_steps_per_second": 0.218, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 9.154113557358054e-05, | |
| "loss": 0.1225, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 9.009269988412515e-05, | |
| "loss": 0.0867, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 8.864426419466975e-05, | |
| "loss": 0.1325, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 8.719582850521438e-05, | |
| "loss": 0.118, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 8.574739281575898e-05, | |
| "loss": 0.112, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 8.429895712630359e-05, | |
| "loss": 0.1326, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 8.28505214368482e-05, | |
| "loss": 0.1506, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 8.140208574739282e-05, | |
| "loss": 0.1499, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 7.995365005793744e-05, | |
| "loss": 0.1092, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 7.850521436848204e-05, | |
| "loss": 0.1104, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_loss": 0.9244877696037292, | |
| "eval_rouge1": 0.2, | |
| "eval_rouge2": 0.1, | |
| "eval_rougeL": 0.19153846153846155, | |
| "eval_rougeLsum": 0.19153846153846155, | |
| "eval_runtime": 93.7022, | |
| "eval_samples_per_second": 0.213, | |
| "eval_steps_per_second": 0.213, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 7.705677867902664e-05, | |
| "loss": 0.0824, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 7.560834298957127e-05, | |
| "loss": 0.1048, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 7.415990730011588e-05, | |
| "loss": 0.1295, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 7.271147161066048e-05, | |
| "loss": 0.1296, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 7.12630359212051e-05, | |
| "loss": 0.1146, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 6.981460023174971e-05, | |
| "loss": 0.1158, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 6.836616454229433e-05, | |
| "loss": 0.094, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 6.691772885283893e-05, | |
| "loss": 0.1141, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 6.546929316338354e-05, | |
| "loss": 0.1025, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 6.402085747392817e-05, | |
| "loss": 0.1474, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 0.9422538876533508, | |
| "eval_rouge1": 0.20069541569541566, | |
| "eval_rouge2": 0.10303030303030303, | |
| "eval_rougeL": 0.19625097125097124, | |
| "eval_rougeLsum": 0.19848096348096347, | |
| "eval_runtime": 94.7246, | |
| "eval_samples_per_second": 0.211, | |
| "eval_steps_per_second": 0.211, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 6.257242178447277e-05, | |
| "loss": 0.09, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 6.112398609501739e-05, | |
| "loss": 0.1235, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 5.9675550405561996e-05, | |
| "loss": 0.0733, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 5.822711471610661e-05, | |
| "loss": 0.1035, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 5.6778679026651216e-05, | |
| "loss": 0.1027, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 5.533024333719583e-05, | |
| "loss": 0.0863, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 5.388180764774044e-05, | |
| "loss": 0.095, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 5.243337195828506e-05, | |
| "loss": 0.1103, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 5.098493626882966e-05, | |
| "loss": 0.1325, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 4.953650057937428e-05, | |
| "loss": 0.1052, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "eval_loss": 0.9328528642654419, | |
| "eval_rouge1": 0.2023076923076923, | |
| "eval_rouge2": 0.1102272727272727, | |
| "eval_rougeL": 0.19999999999999998, | |
| "eval_rougeLsum": 0.2, | |
| "eval_runtime": 92.8302, | |
| "eval_samples_per_second": 0.215, | |
| "eval_steps_per_second": 0.215, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 4.808806488991889e-05, | |
| "loss": 0.1293, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 4.6639629200463506e-05, | |
| "loss": 0.1301, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 4.519119351100811e-05, | |
| "loss": 0.0873, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.3742757821552725e-05, | |
| "loss": 0.1017, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 4.2294322132097335e-05, | |
| "loss": 0.0846, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 4.084588644264195e-05, | |
| "loss": 0.0898, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 3.9397450753186555e-05, | |
| "loss": 0.1494, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 3.794901506373117e-05, | |
| "loss": 0.0742, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 3.650057937427578e-05, | |
| "loss": 0.0793, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 3.50521436848204e-05, | |
| "loss": 0.1203, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "eval_loss": 0.9380243420600891, | |
| "eval_rouge1": 0.2023076923076923, | |
| "eval_rouge2": 0.1102272727272727, | |
| "eval_rougeL": 0.19999999999999998, | |
| "eval_rougeLsum": 0.2, | |
| "eval_runtime": 94.5066, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.212, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 3.360370799536501e-05, | |
| "loss": 0.1257, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 3.215527230590962e-05, | |
| "loss": 0.1177, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 3.070683661645423e-05, | |
| "loss": 0.1359, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 2.9258400926998842e-05, | |
| "loss": 0.1303, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 2.7809965237543452e-05, | |
| "loss": 0.0968, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 2.6361529548088065e-05, | |
| "loss": 0.1061, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 2.4913093858632675e-05, | |
| "loss": 0.1307, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 2.346465816917729e-05, | |
| "loss": 0.0981, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 2.20162224797219e-05, | |
| "loss": 0.0901, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 2.0567786790266515e-05, | |
| "loss": 0.1125, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "eval_loss": 0.9421626925468445, | |
| "eval_rouge1": 0.18958041958041955, | |
| "eval_rouge2": 0.0977272727272727, | |
| "eval_rougeL": 0.18615384615384614, | |
| "eval_rougeLsum": 0.19, | |
| "eval_runtime": 96.4239, | |
| "eval_samples_per_second": 0.207, | |
| "eval_steps_per_second": 0.207, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.9119351100811125e-05, | |
| "loss": 0.0823, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 1.767091541135574e-05, | |
| "loss": 0.1016, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 1.6222479721900348e-05, | |
| "loss": 0.1172, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 1.477404403244496e-05, | |
| "loss": 0.0959, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 1.3325608342989572e-05, | |
| "loss": 0.1534, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 1.1877172653534183e-05, | |
| "loss": 0.125, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 1.0428736964078795e-05, | |
| "loss": 0.1221, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 8.980301274623406e-06, | |
| "loss": 0.1391, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 7.531865585168019e-06, | |
| "loss": 0.0986, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 6.083429895712631e-06, | |
| "loss": 0.1323, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_loss": 0.9433181881904602, | |
| "eval_rouge1": 0.19, | |
| "eval_rouge2": 0.0977272727272727, | |
| "eval_rougeL": 0.18615384615384617, | |
| "eval_rougeLsum": 0.19, | |
| "eval_runtime": 94.6833, | |
| "eval_samples_per_second": 0.211, | |
| "eval_steps_per_second": 0.211, | |
| "step": 3500 | |
| } | |
| ], | |
| "max_steps": 3542, | |
| "num_train_epochs": 7, | |
| "total_flos": 8.516307584906035e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |