| { | |
| "best_metric": 0.4120555818080902, | |
| "best_model_checkpoint": "bart_lora_outputs\\checkpoint-6000", | |
| "epoch": 9.787928221859707, | |
| "eval_steps": 100, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9281, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8201, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6e-05, | |
| "loss": 2.579, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4427, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1681, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7104, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00014000000000000001, | |
| "loss": 1.4177, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2515, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.1238, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0489, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.8469381928443909, | |
| "eval_runtime": 5.9601, | |
| "eval_samples_per_second": 196.474, | |
| "eval_steps_per_second": 24.664, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00022, | |
| "loss": 1.0079, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00024, | |
| "loss": 1.0077, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00026000000000000003, | |
| "loss": 0.9416, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00028000000000000003, | |
| "loss": 0.8882, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8595, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00032, | |
| "loss": 0.8853, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00034, | |
| "loss": 0.7678, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00035999999999999997, | |
| "loss": 0.8595, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00038, | |
| "loss": 0.8514, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0004, | |
| "loss": 0.8128, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.6850531697273254, | |
| "eval_runtime": 6.0279, | |
| "eval_samples_per_second": 194.264, | |
| "eval_steps_per_second": 24.387, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00042, | |
| "loss": 0.7782, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00044, | |
| "loss": 0.8064, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00046, | |
| "loss": 0.7627, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00048, | |
| "loss": 0.7447, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0005, | |
| "loss": 0.7652, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0005200000000000001, | |
| "loss": 0.7568, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00054, | |
| "loss": 0.7291, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0005600000000000001, | |
| "loss": 0.7118, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00058, | |
| "loss": 0.7462, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0006, | |
| "loss": 0.6866, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.629724383354187, | |
| "eval_runtime": 6.0378, | |
| "eval_samples_per_second": 193.943, | |
| "eval_steps_per_second": 24.346, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00062, | |
| "loss": 0.6995, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00064, | |
| "loss": 0.724, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00066, | |
| "loss": 0.6698, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00068, | |
| "loss": 0.6516, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0007, | |
| "loss": 0.6657, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0007199999999999999, | |
| "loss": 0.6765, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00074, | |
| "loss": 0.6596, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00076, | |
| "loss": 0.6884, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0007800000000000001, | |
| "loss": 0.647, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0008, | |
| "loss": 0.713, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.5541791319847107, | |
| "eval_runtime": 6.0716, | |
| "eval_samples_per_second": 192.864, | |
| "eval_steps_per_second": 24.211, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00082, | |
| "loss": 0.6593, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00084, | |
| "loss": 0.62, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00086, | |
| "loss": 0.6912, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00088, | |
| "loss": 0.6407, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0009000000000000001, | |
| "loss": 0.6444, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00092, | |
| "loss": 0.6591, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00094, | |
| "loss": 0.6329, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00096, | |
| "loss": 0.6097, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00098, | |
| "loss": 0.6444, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.001, | |
| "loss": 0.6106, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.5469470024108887, | |
| "eval_runtime": 6.1353, | |
| "eval_samples_per_second": 190.861, | |
| "eval_steps_per_second": 23.96, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0009982238010657195, | |
| "loss": 0.6725, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0009964476021314388, | |
| "loss": 0.6612, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.000994671403197158, | |
| "loss": 0.6202, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0009928952042628776, | |
| "loss": 0.6085, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0009911190053285969, | |
| "loss": 0.6023, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0009893428063943162, | |
| "loss": 0.6209, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0009875666074600357, | |
| "loss": 0.6128, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.000985790408525755, | |
| "loss": 0.5971, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0009840142095914742, | |
| "loss": 0.6028, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0009822380106571937, | |
| "loss": 0.6105, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.527148425579071, | |
| "eval_runtime": 6.0982, | |
| "eval_samples_per_second": 192.024, | |
| "eval_steps_per_second": 24.105, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.000980461811722913, | |
| "loss": 0.6101, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0009786856127886323, | |
| "loss": 0.5349, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0009769094138543518, | |
| "loss": 0.5903, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0009751332149200711, | |
| "loss": 0.6033, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0009733570159857904, | |
| "loss": 0.544, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0009715808170515098, | |
| "loss": 0.5582, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0009698046181172292, | |
| "loss": 0.5488, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0009680284191829485, | |
| "loss": 0.5799, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0009662522202486678, | |
| "loss": 0.5857, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0009644760213143872, | |
| "loss": 0.5857, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 0.5239382982254028, | |
| "eval_runtime": 6.2471, | |
| "eval_samples_per_second": 187.448, | |
| "eval_steps_per_second": 23.531, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0009626998223801065, | |
| "loss": 0.5289, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0009609236234458259, | |
| "loss": 0.6082, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0009591474245115453, | |
| "loss": 0.5837, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0009573712255772646, | |
| "loss": 0.5571, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.000955595026642984, | |
| "loss": 0.5948, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0009538188277087034, | |
| "loss": 0.5455, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0009520426287744227, | |
| "loss": 0.5858, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0009502664298401421, | |
| "loss": 0.5289, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0009484902309058615, | |
| "loss": 0.6011, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0009467140319715807, | |
| "loss": 0.5841, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.5005862712860107, | |
| "eval_runtime": 5.9494, | |
| "eval_samples_per_second": 196.827, | |
| "eval_steps_per_second": 24.708, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0009449378330373001, | |
| "loss": 0.5403, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0009431616341030196, | |
| "loss": 0.558, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0009413854351687389, | |
| "loss": 0.5435, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0009396092362344583, | |
| "loss": 0.5341, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0009378330373001777, | |
| "loss": 0.5398, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.000936056838365897, | |
| "loss": 0.5548, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0009342806394316164, | |
| "loss": 0.5438, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0009325044404973358, | |
| "loss": 0.5845, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0009307282415630552, | |
| "loss": 0.5146, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0009289520426287745, | |
| "loss": 0.5274, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.49163827300071716, | |
| "eval_runtime": 6.0349, | |
| "eval_samples_per_second": 194.04, | |
| "eval_steps_per_second": 24.359, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0009271758436944939, | |
| "loss": 0.5999, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0009253996447602132, | |
| "loss": 0.5798, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0009236234458259325, | |
| "loss": 0.5465, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0009218472468916519, | |
| "loss": 0.5752, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0009200710479573713, | |
| "loss": 0.5544, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0009182948490230906, | |
| "loss": 0.5576, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00091651865008881, | |
| "loss": 0.5351, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0009147424511545294, | |
| "loss": 0.5584, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0009129662522202487, | |
| "loss": 0.5191, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0009111900532859681, | |
| "loss": 0.5304, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 0.48665139079093933, | |
| "eval_runtime": 5.92, | |
| "eval_samples_per_second": 197.803, | |
| "eval_steps_per_second": 24.831, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0009094138543516875, | |
| "loss": 0.5042, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0009076376554174067, | |
| "loss": 0.5495, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0009058614564831261, | |
| "loss": 0.5309, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0009040852575488455, | |
| "loss": 0.5207, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0009023090586145648, | |
| "loss": 0.5209, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0009005328596802842, | |
| "loss": 0.5172, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0008987566607460036, | |
| "loss": 0.5284, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0008969804618117229, | |
| "loss": 0.532, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0008952042628774423, | |
| "loss": 0.534, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0008934280639431617, | |
| "loss": 0.5299, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.47891008853912354, | |
| "eval_runtime": 5.951, | |
| "eval_samples_per_second": 196.772, | |
| "eval_steps_per_second": 24.702, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.000891651865008881, | |
| "loss": 0.5213, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0008898756660746004, | |
| "loss": 0.5443, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0008880994671403197, | |
| "loss": 0.5367, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0008863232682060391, | |
| "loss": 0.5393, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0008845470692717584, | |
| "loss": 0.5286, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0008827708703374778, | |
| "loss": 0.5363, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0008809946714031972, | |
| "loss": 0.4707, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0008792184724689165, | |
| "loss": 0.5414, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0008774422735346359, | |
| "loss": 0.508, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0008756660746003553, | |
| "loss": 0.5238, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.47723039984703064, | |
| "eval_runtime": 11.5341, | |
| "eval_samples_per_second": 101.525, | |
| "eval_steps_per_second": 12.745, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0008738898756660746, | |
| "loss": 0.527, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.000872113676731794, | |
| "loss": 0.537, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0008703374777975134, | |
| "loss": 0.5252, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0008685612788632326, | |
| "loss": 0.5252, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.000866785079928952, | |
| "loss": 0.501, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0008650088809946714, | |
| "loss": 0.4979, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0008632326820603907, | |
| "loss": 0.5041, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0008614564831261101, | |
| "loss": 0.4837, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0008596802841918295, | |
| "loss": 0.5124, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0008579040852575488, | |
| "loss": 0.4876, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.4801134765148163, | |
| "eval_runtime": 5.9243, | |
| "eval_samples_per_second": 197.662, | |
| "eval_steps_per_second": 24.813, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0008561278863232682, | |
| "loss": 0.4937, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0008543516873889876, | |
| "loss": 0.4969, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0008525754884547069, | |
| "loss": 0.4921, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0008507992895204263, | |
| "loss": 0.5073, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0008490230905861456, | |
| "loss": 0.4758, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.000847246891651865, | |
| "loss": 0.5329, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0008454706927175843, | |
| "loss": 0.4786, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0008436944937833037, | |
| "loss": 0.4819, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0008419182948490231, | |
| "loss": 0.5125, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0008401420959147424, | |
| "loss": 0.5048, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.46734750270843506, | |
| "eval_runtime": 13.0931, | |
| "eval_samples_per_second": 89.436, | |
| "eval_steps_per_second": 11.227, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.0008383658969804618, | |
| "loss": 0.5128, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.0008365896980461812, | |
| "loss": 0.5022, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0008348134991119005, | |
| "loss": 0.4767, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.00083303730017762, | |
| "loss": 0.4959, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0008312611012433394, | |
| "loss": 0.5147, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.0008294849023090586, | |
| "loss": 0.4922, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.000827708703374778, | |
| "loss": 0.4936, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0008259325044404974, | |
| "loss": 0.5041, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0008241563055062167, | |
| "loss": 0.491, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.0008223801065719361, | |
| "loss": 0.5096, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 0.45563551783561707, | |
| "eval_runtime": 13.1221, | |
| "eval_samples_per_second": 89.239, | |
| "eval_steps_per_second": 11.202, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0008206039076376555, | |
| "loss": 0.4859, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0008188277087033748, | |
| "loss": 0.5359, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0008170515097690942, | |
| "loss": 0.4693, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0008152753108348136, | |
| "loss": 0.4506, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0008134991119005329, | |
| "loss": 0.4449, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.0008117229129662523, | |
| "loss": 0.4976, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0008099467140319717, | |
| "loss": 0.4781, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0008081705150976909, | |
| "loss": 0.4755, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.0008063943161634103, | |
| "loss": 0.5088, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.0008046181172291297, | |
| "loss": 0.4777, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 0.46053746342658997, | |
| "eval_runtime": 13.1201, | |
| "eval_samples_per_second": 89.252, | |
| "eval_steps_per_second": 11.204, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0008028419182948491, | |
| "loss": 0.4648, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0008010657193605684, | |
| "loss": 0.5066, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.0007992895204262878, | |
| "loss": 0.5127, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.0007975133214920072, | |
| "loss": 0.5136, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0007957371225577265, | |
| "loss": 0.4911, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.0007939609236234459, | |
| "loss": 0.4537, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.0007921847246891653, | |
| "loss": 0.4958, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0007904085257548845, | |
| "loss": 0.4997, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.0007886323268206039, | |
| "loss": 0.5192, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.0007868561278863233, | |
| "loss": 0.4977, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 0.4585750102996826, | |
| "eval_runtime": 13.1101, | |
| "eval_samples_per_second": 89.32, | |
| "eval_steps_per_second": 11.213, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0007850799289520426, | |
| "loss": 0.5044, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.000783303730017762, | |
| "loss": 0.4839, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0007815275310834814, | |
| "loss": 0.5234, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0007797513321492007, | |
| "loss": 0.4835, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0007779751332149201, | |
| "loss": 0.4939, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.0007761989342806395, | |
| "loss": 0.554, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0007744227353463588, | |
| "loss": 0.4643, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0007726465364120782, | |
| "loss": 0.4909, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.0007708703374777975, | |
| "loss": 0.5042, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0007690941385435168, | |
| "loss": 0.4772, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 0.44169098138809204, | |
| "eval_runtime": 13.0107, | |
| "eval_samples_per_second": 90.003, | |
| "eval_steps_per_second": 11.298, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.0007673179396092362, | |
| "loss": 0.4529, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.0007655417406749556, | |
| "loss": 0.5058, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0007637655417406749, | |
| "loss": 0.4794, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0007619893428063943, | |
| "loss": 0.477, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0007602131438721137, | |
| "loss": 0.4663, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.0007584369449378331, | |
| "loss": 0.4634, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.0007566607460035524, | |
| "loss": 0.5159, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0007548845470692718, | |
| "loss": 0.4818, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0007531083481349912, | |
| "loss": 0.4747, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.0007513321492007104, | |
| "loss": 0.4605, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_loss": 0.4483106732368469, | |
| "eval_runtime": 13.1231, | |
| "eval_samples_per_second": 89.232, | |
| "eval_steps_per_second": 11.202, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0007495559502664298, | |
| "loss": 0.474, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.0007477797513321492, | |
| "loss": 0.4639, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 0.0007460035523978685, | |
| "loss": 0.4485, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.0007442273534635879, | |
| "loss": 0.4835, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.0007424511545293073, | |
| "loss": 0.4805, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.0007406749555950266, | |
| "loss": 0.4818, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.000738898756660746, | |
| "loss": 0.4921, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0007371225577264654, | |
| "loss": 0.4601, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.0007353463587921847, | |
| "loss": 0.4771, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.000733570159857904, | |
| "loss": 0.4487, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_loss": 0.46053341031074524, | |
| "eval_runtime": 12.936, | |
| "eval_samples_per_second": 90.523, | |
| "eval_steps_per_second": 11.364, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.0007317939609236234, | |
| "loss": 0.4824, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.0007300177619893427, | |
| "loss": 0.4741, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.0007282415630550621, | |
| "loss": 0.4649, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0007264653641207815, | |
| "loss": 0.471, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.0007246891651865008, | |
| "loss": 0.4411, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.0007229129662522202, | |
| "loss": 0.4435, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.0007211367673179397, | |
| "loss": 0.4464, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.000719360568383659, | |
| "loss": 0.4268, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 0.0007175843694493784, | |
| "loss": 0.4648, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 0.0007158081705150978, | |
| "loss": 0.4746, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "eval_loss": 0.44933727383613586, | |
| "eval_runtime": 12.9431, | |
| "eval_samples_per_second": 90.473, | |
| "eval_steps_per_second": 11.357, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.0007140319715808172, | |
| "loss": 0.4758, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.0007122557726465364, | |
| "loss": 0.4585, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 0.0007104795737122558, | |
| "loss": 0.4386, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.0007087033747779752, | |
| "loss": 0.4575, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.0007069271758436945, | |
| "loss": 0.46, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.0007051509769094139, | |
| "loss": 0.4529, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.0007033747779751333, | |
| "loss": 0.4723, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.0007015985790408526, | |
| "loss": 0.47, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 0.000699822380106572, | |
| "loss": 0.4952, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 0.0006980461811722914, | |
| "loss": 0.4488, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "eval_loss": 0.43646687269210815, | |
| "eval_runtime": 13.2627, | |
| "eval_samples_per_second": 88.293, | |
| "eval_steps_per_second": 11.084, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 0.0006962699822380107, | |
| "loss": 0.4558, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 0.0006944937833037301, | |
| "loss": 0.4657, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.0006927175843694495, | |
| "loss": 0.4671, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 0.0006909413854351687, | |
| "loss": 0.5003, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.0006891651865008881, | |
| "loss": 0.4523, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.0006873889875666075, | |
| "loss": 0.4466, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 0.0006856127886323268, | |
| "loss": 0.4448, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 0.0006838365896980462, | |
| "loss": 0.4491, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 0.0006820603907637656, | |
| "loss": 0.4719, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.0006802841918294849, | |
| "loss": 0.4742, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 0.43938902020454407, | |
| "eval_runtime": 13.1019, | |
| "eval_samples_per_second": 89.376, | |
| "eval_steps_per_second": 11.22, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.0006785079928952043, | |
| "loss": 0.4709, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.0006767317939609237, | |
| "loss": 0.4575, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 0.000674955595026643, | |
| "loss": 0.4688, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0006731793960923623, | |
| "loss": 0.4552, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.0006714031971580817, | |
| "loss": 0.4515, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.0006696269982238011, | |
| "loss": 0.455, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.0006678507992895204, | |
| "loss": 0.4465, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 0.0006660746003552398, | |
| "loss": 0.479, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.0006642984014209592, | |
| "loss": 0.4492, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.0006625222024866785, | |
| "loss": 0.4465, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 0.4411802589893341, | |
| "eval_runtime": 12.9494, | |
| "eval_samples_per_second": 90.429, | |
| "eval_steps_per_second": 11.352, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.0006607460035523979, | |
| "loss": 0.4851, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.0006589698046181173, | |
| "loss": 0.4414, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 0.0006571936056838366, | |
| "loss": 0.4333, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.000655417406749556, | |
| "loss": 0.4733, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0006536412078152753, | |
| "loss": 0.4667, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 0.0006518650088809946, | |
| "loss": 0.4381, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.000650088809946714, | |
| "loss": 0.4267, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.0006483126110124334, | |
| "loss": 0.4361, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 0.0006465364120781527, | |
| "loss": 0.4636, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.0006447602131438721, | |
| "loss": 0.4578, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_loss": 0.4399421811103821, | |
| "eval_runtime": 13.1521, | |
| "eval_samples_per_second": 89.035, | |
| "eval_steps_per_second": 11.177, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0006429840142095915, | |
| "loss": 0.4375, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.0006412078152753108, | |
| "loss": 0.4485, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 0.0006394316163410302, | |
| "loss": 0.4633, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.0006376554174067496, | |
| "loss": 0.4457, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 0.0006358792184724689, | |
| "loss": 0.4504, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 0.0006341030195381882, | |
| "loss": 0.4719, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.0006323268206039076, | |
| "loss": 0.4223, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.0006305506216696269, | |
| "loss": 0.4481, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.0006287744227353463, | |
| "loss": 0.4371, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 0.0006269982238010657, | |
| "loss": 0.4284, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "eval_loss": 0.44260162115097046, | |
| "eval_runtime": 13.1231, | |
| "eval_samples_per_second": 89.232, | |
| "eval_steps_per_second": 11.202, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 0.0006252220248667851, | |
| "loss": 0.4474, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 0.0006234458259325044, | |
| "loss": 0.4725, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.0006216696269982238, | |
| "loss": 0.4319, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.0006198934280639432, | |
| "loss": 0.4502, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 0.0006181172291296625, | |
| "loss": 0.4378, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 0.0006163410301953819, | |
| "loss": 0.4333, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.0006145648312611012, | |
| "loss": 0.4206, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 0.0006127886323268205, | |
| "loss": 0.4314, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 0.00061101243339254, | |
| "loss": 0.4083, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 0.0006092362344582594, | |
| "loss": 0.4416, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_loss": 0.4252881109714508, | |
| "eval_runtime": 13.1357, | |
| "eval_samples_per_second": 89.146, | |
| "eval_steps_per_second": 11.191, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 0.0006074600355239787, | |
| "loss": 0.452, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.0006056838365896981, | |
| "loss": 0.4075, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.0006039076376554175, | |
| "loss": 0.466, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.0006021314387211368, | |
| "loss": 0.4219, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.0006003552397868562, | |
| "loss": 0.4391, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 0.0005985790408525756, | |
| "loss": 0.4952, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.0005968028419182949, | |
| "loss": 0.4594, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 0.0005950266429840142, | |
| "loss": 0.4501, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 0.0005932504440497336, | |
| "loss": 0.4474, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.0005914742451154529, | |
| "loss": 0.4335, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_loss": 0.43218302726745605, | |
| "eval_runtime": 12.9197, | |
| "eval_samples_per_second": 90.637, | |
| "eval_steps_per_second": 11.378, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 0.0005896980461811723, | |
| "loss": 0.4498, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 0.0005879218472468917, | |
| "loss": 0.4228, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.0005861456483126111, | |
| "loss": 0.4399, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.0005843694493783304, | |
| "loss": 0.4561, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 0.0005825932504440498, | |
| "loss": 0.4394, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 0.0005808170515097692, | |
| "loss": 0.4641, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.0005790408525754885, | |
| "loss": 0.4162, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.0005772646536412079, | |
| "loss": 0.4456, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 0.0005754884547069273, | |
| "loss": 0.4588, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.0005737122557726465, | |
| "loss": 0.4316, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "eval_loss": 0.428786039352417, | |
| "eval_runtime": 12.9621, | |
| "eval_samples_per_second": 90.341, | |
| "eval_steps_per_second": 11.341, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 0.0005719360568383659, | |
| "loss": 0.4255, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 0.0005701598579040853, | |
| "loss": 0.4353, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.0005683836589698046, | |
| "loss": 0.4517, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.000566607460035524, | |
| "loss": 0.4747, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0005648312611012434, | |
| "loss": 0.4213, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 0.0005630550621669627, | |
| "loss": 0.437, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 0.0005612788632326821, | |
| "loss": 0.4278, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.0005595026642984015, | |
| "loss": 0.428, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 0.0005577264653641208, | |
| "loss": 0.4256, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.0005559502664298401, | |
| "loss": 0.4509, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "eval_loss": 0.4271390736103058, | |
| "eval_runtime": 12.8651, | |
| "eval_samples_per_second": 91.022, | |
| "eval_steps_per_second": 11.426, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 0.0005541740674955595, | |
| "loss": 0.4681, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 0.0005523978685612788, | |
| "loss": 0.4466, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 0.0005506216696269982, | |
| "loss": 0.4146, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 0.0005488454706927176, | |
| "loss": 0.4909, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 0.0005470692717584369, | |
| "loss": 0.4382, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 0.0005452930728241563, | |
| "loss": 0.4615, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.0005435168738898757, | |
| "loss": 0.4114, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.0005417406749555951, | |
| "loss": 0.4365, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.0005399644760213144, | |
| "loss": 0.4459, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 0.0005381882770870338, | |
| "loss": 0.4326, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "eval_loss": 0.42266643047332764, | |
| "eval_runtime": 12.9188, | |
| "eval_samples_per_second": 90.643, | |
| "eval_steps_per_second": 11.379, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.0005364120781527531, | |
| "loss": 0.4261, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.0005346358792184724, | |
| "loss": 0.4112, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0005328596802841918, | |
| "loss": 0.4144, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.0005310834813499112, | |
| "loss": 0.4119, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 0.0005293072824156305, | |
| "loss": 0.3985, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 0.0005275310834813499, | |
| "loss": 0.4249, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 0.0005257548845470693, | |
| "loss": 0.4289, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 0.0005239786856127886, | |
| "loss": 0.446, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 0.000522202486678508, | |
| "loss": 0.4505, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.0005204262877442274, | |
| "loss": 0.4613, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_loss": 0.4256543815135956, | |
| "eval_runtime": 12.7792, | |
| "eval_samples_per_second": 91.634, | |
| "eval_steps_per_second": 11.503, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 0.0005186500888099467, | |
| "loss": 0.4168, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 0.000516873889875666, | |
| "loss": 0.4754, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.0005150976909413854, | |
| "loss": 0.4053, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 0.0005133214920071047, | |
| "loss": 0.4463, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 0.0005115452930728241, | |
| "loss": 0.4651, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.0005097690941385435, | |
| "loss": 0.4347, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.0005079928952042628, | |
| "loss": 0.4227, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 0.0005062166962699822, | |
| "loss": 0.4292, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 0.0005044404973357016, | |
| "loss": 0.4408, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.0005026642984014209, | |
| "loss": 0.446, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "eval_loss": 0.4269155263900757, | |
| "eval_runtime": 12.9043, | |
| "eval_samples_per_second": 90.745, | |
| "eval_steps_per_second": 11.392, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 0.0005008880994671403, | |
| "loss": 0.4059, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 0.0004991119005328598, | |
| "loss": 0.4111, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.000497335701598579, | |
| "loss": 0.3952, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 0.0004955595026642984, | |
| "loss": 0.4449, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 0.0004937833037300178, | |
| "loss": 0.4312, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.0004920071047957371, | |
| "loss": 0.428, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 0.0004902309058614565, | |
| "loss": 0.4202, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 0.0004884547069271759, | |
| "loss": 0.4164, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 0.0004866785079928952, | |
| "loss": 0.407, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 0.0004849023090586146, | |
| "loss": 0.4, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "eval_loss": 0.4314885437488556, | |
| "eval_runtime": 13.0675, | |
| "eval_samples_per_second": 89.612, | |
| "eval_steps_per_second": 11.249, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 0.0004831261101243339, | |
| "loss": 0.4138, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 0.00048134991119005326, | |
| "loss": 0.4223, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.00047957371225577266, | |
| "loss": 0.4108, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 0.000477797513321492, | |
| "loss": 0.4065, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 0.00047602131438721133, | |
| "loss": 0.4481, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 0.00047424511545293073, | |
| "loss": 0.4273, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 0.00047246891651865007, | |
| "loss": 0.4267, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 0.00047069271758436946, | |
| "loss": 0.4626, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 0.00046891651865008885, | |
| "loss": 0.4441, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.0004671403197158082, | |
| "loss": 0.4086, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "eval_loss": 0.4278687536716461, | |
| "eval_runtime": 12.9778, | |
| "eval_samples_per_second": 90.231, | |
| "eval_steps_per_second": 11.327, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 0.0004653641207815276, | |
| "loss": 0.4377, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 0.0004635879218472469, | |
| "loss": 0.4315, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 0.00046181172291296627, | |
| "loss": 0.4392, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 0.00046003552397868566, | |
| "loss": 0.4151, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 0.000458259325044405, | |
| "loss": 0.3884, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.00045648312611012434, | |
| "loss": 0.4362, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 0.00045470692717584373, | |
| "loss": 0.4401, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 0.00045293072824156307, | |
| "loss": 0.4199, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.0004511545293072824, | |
| "loss": 0.4, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 0.0004493783303730018, | |
| "loss": 0.4056, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "eval_loss": 0.42200714349746704, | |
| "eval_runtime": 13.1531, | |
| "eval_samples_per_second": 89.029, | |
| "eval_steps_per_second": 11.176, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 0.00044760213143872114, | |
| "loss": 0.4444, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 0.0004458259325044405, | |
| "loss": 0.4229, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 0.0004440497335701599, | |
| "loss": 0.4206, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 0.0004422735346358792, | |
| "loss": 0.4243, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 0.0004404973357015986, | |
| "loss": 0.4117, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.00043872113676731795, | |
| "loss": 0.4375, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 0.0004369449378330373, | |
| "loss": 0.4372, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.0004351687388987567, | |
| "loss": 0.4045, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.000433392539964476, | |
| "loss": 0.3872, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 0.00043161634103019536, | |
| "loss": 0.4049, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "eval_loss": 0.4243859648704529, | |
| "eval_runtime": 12.9291, | |
| "eval_samples_per_second": 90.571, | |
| "eval_steps_per_second": 11.37, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 0.00042984014209591475, | |
| "loss": 0.4333, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.0004280639431616341, | |
| "loss": 0.4061, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 0.00042628774422735343, | |
| "loss": 0.3993, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 0.0004245115452930728, | |
| "loss": 0.3988, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 0.00042273534635879216, | |
| "loss": 0.3962, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.00042095914742451156, | |
| "loss": 0.3863, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.0004191829484902309, | |
| "loss": 0.4184, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 0.00041740674955595023, | |
| "loss": 0.4171, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.0004156305506216697, | |
| "loss": 0.416, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 0.000413854351687389, | |
| "loss": 0.4311, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "eval_loss": 0.42171674966812134, | |
| "eval_runtime": 13.1531, | |
| "eval_samples_per_second": 89.029, | |
| "eval_steps_per_second": 11.176, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 0.00041207815275310836, | |
| "loss": 0.4266, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 0.00041030195381882775, | |
| "loss": 0.3933, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 0.0004085257548845471, | |
| "loss": 0.4154, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.00040674955595026643, | |
| "loss": 0.4321, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 0.0004049733570159858, | |
| "loss": 0.4338, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.00040319715808170517, | |
| "loss": 0.4204, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 0.00040142095914742456, | |
| "loss": 0.4274, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 0.0003996447602131439, | |
| "loss": 0.3985, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 0.00039786856127886324, | |
| "loss": 0.4232, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 0.00039609236234458263, | |
| "loss": 0.3799, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "eval_loss": 0.4199593961238861, | |
| "eval_runtime": 12.9106, | |
| "eval_samples_per_second": 90.7, | |
| "eval_steps_per_second": 11.386, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 0.00039431616341030197, | |
| "loss": 0.4061, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 0.0003925399644760213, | |
| "loss": 0.398, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.0003907637655417407, | |
| "loss": 0.3987, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 0.00038898756660746004, | |
| "loss": 0.3811, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 0.0003872113676731794, | |
| "loss": 0.4133, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 0.0003854351687388988, | |
| "loss": 0.4053, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 0.0003836589698046181, | |
| "loss": 0.4046, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 0.00038188277087033745, | |
| "loss": 0.3875, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.00038010657193605685, | |
| "loss": 0.4017, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.0003783303730017762, | |
| "loss": 0.4281, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "eval_loss": 0.42139747738838196, | |
| "eval_runtime": 13.202, | |
| "eval_samples_per_second": 88.699, | |
| "eval_steps_per_second": 11.135, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 0.0003765541740674956, | |
| "loss": 0.4198, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.0003747779751332149, | |
| "loss": 0.3908, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 0.00037300177619893426, | |
| "loss": 0.4296, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 0.00037122557726465365, | |
| "loss": 0.4183, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 0.000369449378330373, | |
| "loss": 0.4371, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 0.00036767317939609233, | |
| "loss": 0.3934, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 0.0003658969804618117, | |
| "loss": 0.4581, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 0.00036412078152753106, | |
| "loss": 0.3908, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.0003623445825932504, | |
| "loss": 0.4237, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 0.00036056838365896985, | |
| "loss": 0.3975, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "eval_loss": 0.4162620007991791, | |
| "eval_runtime": 12.9992, | |
| "eval_samples_per_second": 90.082, | |
| "eval_steps_per_second": 11.308, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 0.0003587921847246892, | |
| "loss": 0.4152, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.0003570159857904086, | |
| "loss": 0.4353, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 0.0003552397868561279, | |
| "loss": 0.3991, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 0.00035346358792184726, | |
| "loss": 0.4094, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 0.00035168738898756665, | |
| "loss": 0.4099, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 0.000349911190053286, | |
| "loss": 0.4107, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 0.00034813499111900533, | |
| "loss": 0.433, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 0.0003463587921847247, | |
| "loss": 0.4267, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 0.00034458259325044407, | |
| "loss": 0.4373, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 0.0003428063943161634, | |
| "loss": 0.4053, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "eval_loss": 0.4194377064704895, | |
| "eval_runtime": 13.0635, | |
| "eval_samples_per_second": 89.639, | |
| "eval_steps_per_second": 11.253, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 0.0003410301953818828, | |
| "loss": 0.4298, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.00033925399644760214, | |
| "loss": 0.4074, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 0.0003374777975133215, | |
| "loss": 0.423, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 0.00033570159857904087, | |
| "loss": 0.4292, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 0.0003339253996447602, | |
| "loss": 0.4068, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 0.0003321492007104796, | |
| "loss": 0.41, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 0.00033037300177619894, | |
| "loss": 0.4429, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 0.0003285968028419183, | |
| "loss": 0.4352, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.0003268206039076377, | |
| "loss": 0.4314, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 0.000325044404973357, | |
| "loss": 0.3817, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_loss": 0.42648157477378845, | |
| "eval_runtime": 12.8627, | |
| "eval_samples_per_second": 91.039, | |
| "eval_steps_per_second": 11.428, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 0.00032326820603907635, | |
| "loss": 0.4002, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 0.00032149200710479575, | |
| "loss": 0.397, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 0.0003197158081705151, | |
| "loss": 0.4064, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 0.0003179396092362344, | |
| "loss": 0.4314, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.0003161634103019538, | |
| "loss": 0.4149, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.00031438721136767316, | |
| "loss": 0.3956, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 0.00031261101243339255, | |
| "loss": 0.4218, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.0003108348134991119, | |
| "loss": 0.3959, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 0.00030905861456483123, | |
| "loss": 0.4071, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 0.0003072824156305506, | |
| "loss": 0.3927, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "eval_loss": 0.41820862889289856, | |
| "eval_runtime": 12.8919, | |
| "eval_samples_per_second": 90.832, | |
| "eval_steps_per_second": 11.403, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 0.00030550621669627, | |
| "loss": 0.4069, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 0.00030373001776198936, | |
| "loss": 0.403, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 0.00030195381882770875, | |
| "loss": 0.402, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 0.0003001776198934281, | |
| "loss": 0.4277, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.00029840142095914743, | |
| "loss": 0.4067, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 0.0002966252220248668, | |
| "loss": 0.3873, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 0.00029484902309058616, | |
| "loss": 0.3955, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 0.00029307282415630555, | |
| "loss": 0.3845, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 0.0002912966252220249, | |
| "loss": 0.4149, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 0.00028952042628774423, | |
| "loss": 0.3996, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "eval_loss": 0.41941431164741516, | |
| "eval_runtime": 12.818, | |
| "eval_samples_per_second": 91.356, | |
| "eval_steps_per_second": 11.468, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 0.0002877442273534636, | |
| "loss": 0.4006, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.00028596802841918297, | |
| "loss": 0.4024, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 0.0002841918294849023, | |
| "loss": 0.3959, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 0.0002824156305506217, | |
| "loss": 0.3917, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.00028063943161634104, | |
| "loss": 0.3994, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 0.0002788632326820604, | |
| "loss": 0.4246, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 0.00027708703374777977, | |
| "loss": 0.3905, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.0002753108348134991, | |
| "loss": 0.4076, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 0.00027353463587921845, | |
| "loss": 0.3924, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 0.00027175843694493784, | |
| "loss": 0.3863, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "eval_loss": 0.4166851341724396, | |
| "eval_runtime": 12.731, | |
| "eval_samples_per_second": 91.98, | |
| "eval_steps_per_second": 11.547, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 0.0002699822380106572, | |
| "loss": 0.3949, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 0.0002682060390763766, | |
| "loss": 0.3966, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 0.0002664298401420959, | |
| "loss": 0.3899, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 0.00026465364120781525, | |
| "loss": 0.41, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 0.00026287744227353465, | |
| "loss": 0.3993, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 0.000261101243339254, | |
| "loss": 0.4216, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 0.0002593250444049733, | |
| "loss": 0.4144, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.0002575488454706927, | |
| "loss": 0.4117, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 0.00025577264653641206, | |
| "loss": 0.4288, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 0.0002539964476021314, | |
| "loss": 0.3837, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "eval_loss": 0.4177791476249695, | |
| "eval_runtime": 12.7781, | |
| "eval_samples_per_second": 91.642, | |
| "eval_steps_per_second": 11.504, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 0.0002522202486678508, | |
| "loss": 0.3894, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 0.00025044404973357013, | |
| "loss": 0.4109, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 0.0002486678507992895, | |
| "loss": 0.4211, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 0.0002468916518650089, | |
| "loss": 0.3984, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 0.00024511545293072826, | |
| "loss": 0.3988, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 0.0002433392539964476, | |
| "loss": 0.4185, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 0.00024156305506216696, | |
| "loss": 0.3986, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.00023978685612788633, | |
| "loss": 0.4035, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 0.00023801065719360567, | |
| "loss": 0.4028, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 0.00023623445825932503, | |
| "loss": 0.3998, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "eval_loss": 0.42066851258277893, | |
| "eval_runtime": 12.801, | |
| "eval_samples_per_second": 91.477, | |
| "eval_steps_per_second": 11.483, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 0.00023445825932504443, | |
| "loss": 0.4137, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 0.0002326820603907638, | |
| "loss": 0.3972, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 0.00023090586145648313, | |
| "loss": 0.4158, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 0.0002291296625222025, | |
| "loss": 0.3972, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 0.00022735346358792187, | |
| "loss": 0.4246, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 0.0002255772646536412, | |
| "loss": 0.3866, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 0.00022380106571936057, | |
| "loss": 0.4359, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.00022202486678507994, | |
| "loss": 0.386, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 0.0002202486678507993, | |
| "loss": 0.38, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 0.00021847246891651864, | |
| "loss": 0.3936, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_loss": 0.41456684470176697, | |
| "eval_runtime": 12.7936, | |
| "eval_samples_per_second": 91.53, | |
| "eval_steps_per_second": 11.49, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.000216696269982238, | |
| "loss": 0.3634, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 0.00021492007104795738, | |
| "loss": 0.3883, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 0.00021314387211367671, | |
| "loss": 0.3864, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 0.00021136767317939608, | |
| "loss": 0.3848, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 0.00020959147424511545, | |
| "loss": 0.4164, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 0.00020781527531083484, | |
| "loss": 0.3963, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 0.00020603907637655418, | |
| "loss": 0.3873, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 0.00020426287744227355, | |
| "loss": 0.4306, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 0.0002024866785079929, | |
| "loss": 0.3966, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 0.00020071047957371228, | |
| "loss": 0.3672, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "eval_loss": 0.4176868200302124, | |
| "eval_runtime": 12.7243, | |
| "eval_samples_per_second": 92.029, | |
| "eval_steps_per_second": 11.553, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 0.00019893428063943162, | |
| "loss": 0.3893, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 0.00019715808170515098, | |
| "loss": 0.3948, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 0.00019538188277087035, | |
| "loss": 0.3831, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 0.0001936056838365897, | |
| "loss": 0.3828, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 0.00019182948490230906, | |
| "loss": 0.3986, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 0.00019005328596802842, | |
| "loss": 0.3826, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 0.0001882770870337478, | |
| "loss": 0.4053, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 0.00018650088809946713, | |
| "loss": 0.399, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 0.0001847246891651865, | |
| "loss": 0.4096, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 0.00018294849023090586, | |
| "loss": 0.3931, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "eval_loss": 0.4182140529155731, | |
| "eval_runtime": 12.7337, | |
| "eval_samples_per_second": 91.961, | |
| "eval_steps_per_second": 11.544, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 0.0001811722912966252, | |
| "loss": 0.4117, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 0.0001793960923623446, | |
| "loss": 0.3754, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 0.00017761989342806396, | |
| "loss": 0.3688, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 0.00017584369449378333, | |
| "loss": 0.4199, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 0.00017406749555950267, | |
| "loss": 0.4011, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 0.00017229129662522203, | |
| "loss": 0.4013, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 0.0001705150976909414, | |
| "loss": 0.414, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 0.00016873889875666074, | |
| "loss": 0.3682, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 0.0001669626998223801, | |
| "loss": 0.377, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 0.00016518650088809947, | |
| "loss": 0.3904, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "eval_loss": 0.41562286019325256, | |
| "eval_runtime": 12.9077, | |
| "eval_samples_per_second": 90.721, | |
| "eval_steps_per_second": 11.389, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 0.00016341030195381884, | |
| "loss": 0.3955, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 0.00016163410301953818, | |
| "loss": 0.386, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 0.00015985790408525754, | |
| "loss": 0.3862, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.0001580817051509769, | |
| "loss": 0.3979, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 0.00015630550621669628, | |
| "loss": 0.381, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 0.00015452930728241561, | |
| "loss": 0.4016, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 0.000152753108348135, | |
| "loss": 0.4191, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 0.00015097690941385437, | |
| "loss": 0.3832, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 0.00014920071047957371, | |
| "loss": 0.3934, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 0.00014742451154529308, | |
| "loss": 0.3968, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "eval_loss": 0.41458660364151, | |
| "eval_runtime": 12.7995, | |
| "eval_samples_per_second": 91.488, | |
| "eval_steps_per_second": 11.485, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.00014564831261101245, | |
| "loss": 0.409, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 0.0001438721136767318, | |
| "loss": 0.3797, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 0.00014209591474245115, | |
| "loss": 0.3895, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.00014031971580817052, | |
| "loss": 0.3722, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 0.00013854351687388988, | |
| "loss": 0.4083, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 0.00013676731793960922, | |
| "loss": 0.4032, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 0.0001349911190053286, | |
| "loss": 0.3985, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 0.00013321492007104796, | |
| "loss": 0.3894, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 0.00013143872113676732, | |
| "loss": 0.3924, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 0.00012966252220248666, | |
| "loss": 0.3677, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "eval_loss": 0.41405031085014343, | |
| "eval_runtime": 12.6828, | |
| "eval_samples_per_second": 92.33, | |
| "eval_steps_per_second": 11.591, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 0.00012788632326820603, | |
| "loss": 0.3836, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 0.0001261101243339254, | |
| "loss": 0.4018, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 0.00012433392539964476, | |
| "loss": 0.4, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 0.00012255772646536413, | |
| "loss": 0.3869, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 0.00012078152753108348, | |
| "loss": 0.4168, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 0.00011900532859680283, | |
| "loss": 0.3929, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 0.00011722912966252221, | |
| "loss": 0.4153, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 0.00011545293072824157, | |
| "loss": 0.4017, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 0.00011367673179396093, | |
| "loss": 0.3844, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 0.00011190053285968029, | |
| "loss": 0.3823, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "eval_loss": 0.417066365480423, | |
| "eval_runtime": 12.7641, | |
| "eval_samples_per_second": 91.742, | |
| "eval_steps_per_second": 11.517, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 0.00011012433392539965, | |
| "loss": 0.4155, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.000108348134991119, | |
| "loss": 0.3614, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 0.00010657193605683836, | |
| "loss": 0.3688, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 0.00010479573712255772, | |
| "loss": 0.3798, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 0.00010301953818827709, | |
| "loss": 0.3968, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 0.00010124333925399646, | |
| "loss": 0.3894, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 9.946714031971581e-05, | |
| "loss": 0.3858, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 9.769094138543518e-05, | |
| "loss": 0.3638, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 9.591474245115453e-05, | |
| "loss": 0.3674, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 9.41385435168739e-05, | |
| "loss": 0.3568, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "eval_loss": 0.41371241211891174, | |
| "eval_runtime": 13.0451, | |
| "eval_samples_per_second": 89.766, | |
| "eval_steps_per_second": 11.269, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 9.236234458259325e-05, | |
| "loss": 0.3748, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 9.05861456483126e-05, | |
| "loss": 0.3901, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 8.880994671403198e-05, | |
| "loss": 0.3737, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 8.703374777975133e-05, | |
| "loss": 0.3973, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 8.52575488454707e-05, | |
| "loss": 0.3985, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 8.348134991119005e-05, | |
| "loss": 0.37, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 8.170515097690942e-05, | |
| "loss": 0.4537, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 7.992895204262877e-05, | |
| "loss": 0.3747, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 7.815275310834814e-05, | |
| "loss": 0.4095, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 7.63765541740675e-05, | |
| "loss": 0.3971, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "eval_loss": 0.4128452241420746, | |
| "eval_runtime": 13.0551, | |
| "eval_samples_per_second": 89.697, | |
| "eval_steps_per_second": 11.26, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 7.460035523978686e-05, | |
| "loss": 0.3814, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 7.282415630550622e-05, | |
| "loss": 0.3894, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 7.104795737122558e-05, | |
| "loss": 0.3985, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 6.927175843694494e-05, | |
| "loss": 0.3593, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 6.74955595026643e-05, | |
| "loss": 0.3783, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 6.571936056838366e-05, | |
| "loss": 0.387, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 6.394316163410301e-05, | |
| "loss": 0.3839, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 6.216696269982238e-05, | |
| "loss": 0.3701, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 6.039076376554174e-05, | |
| "loss": 0.3752, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 5.861456483126111e-05, | |
| "loss": 0.3907, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "eval_loss": 0.41585057973861694, | |
| "eval_runtime": 13.094, | |
| "eval_samples_per_second": 89.43, | |
| "eval_steps_per_second": 11.227, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 5.6838365896980466e-05, | |
| "loss": 0.3675, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 5.5062166962699826e-05, | |
| "loss": 0.3804, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 5.328596802841918e-05, | |
| "loss": 0.3968, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 5.1509769094138545e-05, | |
| "loss": 0.3831, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 4.9733570159857905e-05, | |
| "loss": 0.3973, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 4.7957371225577264e-05, | |
| "loss": 0.3962, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 4.6181172291296624e-05, | |
| "loss": 0.3819, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 4.440497335701599e-05, | |
| "loss": 0.4078, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 4.262877442273535e-05, | |
| "loss": 0.4032, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 4.085257548845471e-05, | |
| "loss": 0.4149, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "eval_loss": 0.4138317406177521, | |
| "eval_runtime": 13.0042, | |
| "eval_samples_per_second": 90.048, | |
| "eval_steps_per_second": 11.304, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 3.907637655417407e-05, | |
| "loss": 0.385, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 3.730017761989343e-05, | |
| "loss": 0.3657, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 3.552397868561279e-05, | |
| "loss": 0.3999, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "learning_rate": 3.374777975133215e-05, | |
| "loss": 0.3896, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 3.197158081705151e-05, | |
| "loss": 0.4021, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 3.019538188277087e-05, | |
| "loss": 0.3781, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 2.8419182948490233e-05, | |
| "loss": 0.4082, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 2.664298401420959e-05, | |
| "loss": 0.3819, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 2.4866785079928952e-05, | |
| "loss": 0.3874, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 2.3090586145648312e-05, | |
| "loss": 0.3801, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "eval_loss": 0.4120555818080902, | |
| "eval_runtime": 13.0061, | |
| "eval_samples_per_second": 90.035, | |
| "eval_steps_per_second": 11.302, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 6130, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1.1329492947664896e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |