| { | |
| "best_metric": 0.2909798324108124, | |
| "best_model_checkpoint": "DrishtiSharma/finetuned-SwinT-Indian-Food-Classification-v3/checkpoint-3300", | |
| "epoch": 10.0, | |
| "global_step": 3330, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019951951951951952, | |
| "loss": 2.6877, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019891891891891895, | |
| "loss": 1.414, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019831831831831833, | |
| "loss": 0.9319, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019771771771771773, | |
| "loss": 0.7099, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019711711711711713, | |
| "loss": 0.9566, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019651651651651653, | |
| "loss": 0.8187, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000195975975975976, | |
| "loss": 0.8349, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001953753753753754, | |
| "loss": 0.7547, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0001947747747747748, | |
| "loss": 0.7049, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001941741741741742, | |
| "loss": 0.9511, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.8172157279489904, | |
| "eval_loss": 0.6092320680618286, | |
| "eval_runtime": 41.8655, | |
| "eval_samples_per_second": 22.477, | |
| "eval_steps_per_second": 2.819, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00019357357357357356, | |
| "loss": 0.93, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.000192972972972973, | |
| "loss": 0.7919, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019237237237237236, | |
| "loss": 0.7467, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0001917717717717718, | |
| "loss": 0.6385, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001911711711711712, | |
| "loss": 0.6259, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00019057057057057057, | |
| "loss": 0.6855, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00018996996996997, | |
| "loss": 0.7514, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00018936936936936937, | |
| "loss": 0.799, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001887687687687688, | |
| "loss": 0.7728, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00018816816816816817, | |
| "loss": 0.6214, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.8671625929861849, | |
| "eval_loss": 0.4405747056007385, | |
| "eval_runtime": 42.025, | |
| "eval_samples_per_second": 22.391, | |
| "eval_steps_per_second": 2.808, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00018756756756756757, | |
| "loss": 0.696, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00018696696696696697, | |
| "loss": 0.8194, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00018636636636636637, | |
| "loss": 0.6639, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00018576576576576577, | |
| "loss": 0.6229, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00018516516516516517, | |
| "loss": 0.598, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00018456456456456458, | |
| "loss": 0.724, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00018396396396396398, | |
| "loss": 0.6808, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00018336336336336338, | |
| "loss": 0.9956, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00018276276276276275, | |
| "loss": 0.661, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00018216216216216218, | |
| "loss": 0.7355, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.8926673751328374, | |
| "eval_loss": 0.3664906620979309, | |
| "eval_runtime": 41.8476, | |
| "eval_samples_per_second": 22.486, | |
| "eval_steps_per_second": 2.82, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00018156156156156155, | |
| "loss": 0.7618, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00018102102102102104, | |
| "loss": 0.583, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0001804204204204204, | |
| "loss": 0.4483, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00017981981981981984, | |
| "loss": 0.553, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0001792192192192192, | |
| "loss": 0.6715, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00017861861861861861, | |
| "loss": 0.4049, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00017801801801801804, | |
| "loss": 0.2682, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00017741741741741742, | |
| "loss": 0.6865, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00017681681681681684, | |
| "loss": 0.6398, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00017621621621621622, | |
| "loss": 0.6078, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.9064824654622742, | |
| "eval_loss": 0.3284536898136139, | |
| "eval_runtime": 42.3721, | |
| "eval_samples_per_second": 22.208, | |
| "eval_steps_per_second": 2.785, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00017561561561561562, | |
| "loss": 0.4809, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00017501501501501502, | |
| "loss": 0.4514, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00017441441441441442, | |
| "loss": 0.4345, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00017381381381381382, | |
| "loss": 0.6553, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00017321321321321322, | |
| "loss": 0.509, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00017261261261261262, | |
| "loss": 0.7415, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00017201201201201202, | |
| "loss": 0.4097, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00017141141141141142, | |
| "loss": 0.5408, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00017081081081081083, | |
| "loss": 0.6177, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00017021021021021023, | |
| "loss": 0.439, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.8916046758767269, | |
| "eval_loss": 0.3854953944683075, | |
| "eval_runtime": 42.0098, | |
| "eval_samples_per_second": 22.4, | |
| "eval_steps_per_second": 2.809, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001696096096096096, | |
| "loss": 0.5833, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00016900900900900903, | |
| "loss": 0.5769, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0001684084084084084, | |
| "loss": 0.6425, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00016780780780780783, | |
| "loss": 0.5285, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00016720720720720723, | |
| "loss": 0.3756, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0001666066066066066, | |
| "loss": 0.5905, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00016600600600600603, | |
| "loss": 0.5225, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001654054054054054, | |
| "loss": 0.3937, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0001648048048048048, | |
| "loss": 0.6641, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0001642042042042042, | |
| "loss": 0.3644, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_accuracy": 0.8969181721572795, | |
| "eval_loss": 0.40817153453826904, | |
| "eval_runtime": 42.2201, | |
| "eval_samples_per_second": 22.288, | |
| "eval_steps_per_second": 2.795, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0001636036036036036, | |
| "loss": 0.3914, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.000163003003003003, | |
| "loss": 0.5051, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0001624024024024024, | |
| "loss": 0.5306, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0001618018018018018, | |
| "loss": 0.492, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0001612012012012012, | |
| "loss": 0.4476, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0001606006006006006, | |
| "loss": 0.5976, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.00016, | |
| "loss": 0.5336, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00015939939939939941, | |
| "loss": 0.5416, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0001587987987987988, | |
| "loss": 0.3908, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00015819819819819822, | |
| "loss": 0.4748, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.9022316684378321, | |
| "eval_loss": 0.3496166467666626, | |
| "eval_runtime": 42.0671, | |
| "eval_samples_per_second": 22.369, | |
| "eval_steps_per_second": 2.805, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0001575975975975976, | |
| "loss": 0.2206, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.00015699699699699702, | |
| "loss": 0.3733, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00015639639639639642, | |
| "loss": 0.3506, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0001557957957957958, | |
| "loss": 0.2672, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00015519519519519522, | |
| "loss": 0.3588, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0001545945945945946, | |
| "loss": 0.3908, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00015399399399399402, | |
| "loss": 0.5611, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0001533933933933934, | |
| "loss": 0.4638, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0001527927927927928, | |
| "loss": 0.5441, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0001521921921921922, | |
| "loss": 0.3966, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.8905419766206164, | |
| "eval_loss": 0.36262860894203186, | |
| "eval_runtime": 40.9458, | |
| "eval_samples_per_second": 22.982, | |
| "eval_steps_per_second": 2.882, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0001515915915915916, | |
| "loss": 0.2038, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.000150990990990991, | |
| "loss": 0.3805, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.0001503903903903904, | |
| "loss": 0.395, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.0001497897897897898, | |
| "loss": 0.4266, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0001491891891891892, | |
| "loss": 0.3128, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0001485885885885886, | |
| "loss": 0.3916, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.00014798798798798798, | |
| "loss": 0.3253, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0001473873873873874, | |
| "loss": 0.6879, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00014678678678678678, | |
| "loss": 0.326, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0001461861861861862, | |
| "loss": 0.5799, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_accuracy": 0.8767268862911796, | |
| "eval_loss": 0.4832826554775238, | |
| "eval_runtime": 42.1482, | |
| "eval_samples_per_second": 22.326, | |
| "eval_steps_per_second": 2.8, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.0001455855855855856, | |
| "loss": 0.4715, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00014498498498498498, | |
| "loss": 0.4166, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0001443843843843844, | |
| "loss": 0.6237, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.00014378378378378378, | |
| "loss": 0.5164, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0001431831831831832, | |
| "loss": 0.3581, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.00014258258258258258, | |
| "loss": 0.3834, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.00014198198198198198, | |
| "loss": 0.2722, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00014138138138138138, | |
| "loss": 0.6858, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.00014078078078078079, | |
| "loss": 0.4076, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0001401801801801802, | |
| "loss": 0.2995, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9043570669500531, | |
| "eval_loss": 0.33867305517196655, | |
| "eval_runtime": 42.1556, | |
| "eval_samples_per_second": 22.322, | |
| "eval_steps_per_second": 2.799, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.0001395795795795796, | |
| "loss": 0.2855, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.000138978978978979, | |
| "loss": 0.4162, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.0001383783783783784, | |
| "loss": 0.1903, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0001377777777777778, | |
| "loss": 0.3357, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 0.00013717717717717716, | |
| "loss": 0.444, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.0001365765765765766, | |
| "loss": 0.2977, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.00013597597597597597, | |
| "loss": 0.2442, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.0001353753753753754, | |
| "loss": 0.369, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.0001347747747747748, | |
| "loss": 0.377, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.00013417417417417417, | |
| "loss": 0.3152, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.9096705632306057, | |
| "eval_loss": 0.37393638491630554, | |
| "eval_runtime": 43.1022, | |
| "eval_samples_per_second": 21.832, | |
| "eval_steps_per_second": 2.738, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0001335735735735736, | |
| "loss": 0.4133, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.00013297297297297297, | |
| "loss": 0.2448, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.0001323723723723724, | |
| "loss": 0.4011, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.00013177177177177177, | |
| "loss": 0.3495, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 0.00013117117117117117, | |
| "loss": 0.3656, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 0.00013057057057057057, | |
| "loss": 0.3285, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.00012996996996996997, | |
| "loss": 0.1904, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.00012936936936936937, | |
| "loss": 0.3852, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 0.00012876876876876878, | |
| "loss": 0.2966, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.00012816816816816818, | |
| "loss": 0.3284, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_accuracy": 0.8916046758767269, | |
| "eval_loss": 0.4216819107532501, | |
| "eval_runtime": 43.8685, | |
| "eval_samples_per_second": 21.45, | |
| "eval_steps_per_second": 2.69, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.00012756756756756758, | |
| "loss": 0.3911, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.00012696696696696698, | |
| "loss": 0.2183, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.00012636636636636635, | |
| "loss": 0.4146, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 0.00012576576576576578, | |
| "loss": 0.4245, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.00012516516516516515, | |
| "loss": 0.2051, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.00012456456456456458, | |
| "loss": 0.2955, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.00012396396396396398, | |
| "loss": 0.3594, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 0.00012336336336336336, | |
| "loss": 0.4109, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.00012276276276276278, | |
| "loss": 0.2371, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.00012216216216216216, | |
| "loss": 0.3631, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "eval_accuracy": 0.9043570669500531, | |
| "eval_loss": 0.41184473037719727, | |
| "eval_runtime": 41.3527, | |
| "eval_samples_per_second": 22.755, | |
| "eval_steps_per_second": 2.854, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.00012156156156156157, | |
| "loss": 0.4564, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 0.00012096096096096097, | |
| "loss": 0.4595, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.00012036036036036036, | |
| "loss": 0.3554, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.00011975975975975977, | |
| "loss": 0.4029, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.00011915915915915916, | |
| "loss": 0.2339, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.00011855855855855858, | |
| "loss": 0.2711, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.00011795795795795796, | |
| "loss": 0.2034, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00011735735735735735, | |
| "loss": 0.4796, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 0.00011675675675675676, | |
| "loss": 0.2313, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.00011615615615615617, | |
| "loss": 0.219, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.9139213602550478, | |
| "eval_loss": 0.37211018800735474, | |
| "eval_runtime": 42.0279, | |
| "eval_samples_per_second": 22.39, | |
| "eval_steps_per_second": 2.808, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.00011555555555555555, | |
| "loss": 0.224, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 0.00011495495495495497, | |
| "loss": 0.2262, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00011435435435435435, | |
| "loss": 0.2165, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 0.00011375375375375377, | |
| "loss": 0.2617, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.00011315315315315316, | |
| "loss": 0.1725, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 0.00011255255255255254, | |
| "loss": 0.2667, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.00011195195195195196, | |
| "loss": 0.506, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.00011135135135135135, | |
| "loss": 0.4481, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.00011075075075075076, | |
| "loss": 0.3483, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 0.00011015015015015016, | |
| "loss": 0.2874, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_accuracy": 0.9287991498405951, | |
| "eval_loss": 0.30303552746772766, | |
| "eval_runtime": 41.8473, | |
| "eval_samples_per_second": 22.487, | |
| "eval_steps_per_second": 2.82, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 0.00010954954954954955, | |
| "loss": 0.3234, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 0.00010894894894894896, | |
| "loss": 0.3609, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 0.00010834834834834835, | |
| "loss": 0.2809, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.00010774774774774776, | |
| "loss": 0.2844, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 0.00010714714714714715, | |
| "loss": 0.2682, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.00010654654654654654, | |
| "loss": 0.257, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 0.00010594594594594595, | |
| "loss": 0.1629, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 0.00010534534534534535, | |
| "loss": 0.3236, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 0.00010474474474474475, | |
| "loss": 0.1371, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.00010414414414414416, | |
| "loss": 0.2819, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_accuracy": 0.9149840595111584, | |
| "eval_loss": 0.40561917424201965, | |
| "eval_runtime": 42.3715, | |
| "eval_samples_per_second": 22.208, | |
| "eval_steps_per_second": 2.785, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 0.00010354354354354354, | |
| "loss": 0.3263, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.00010294294294294296, | |
| "loss": 0.1687, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.00010234234234234234, | |
| "loss": 0.2958, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 0.00010174174174174173, | |
| "loss": 0.4361, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.00010114114114114115, | |
| "loss": 0.3248, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 0.00010054054054054053, | |
| "loss": 0.3016, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 9.993993993993995e-05, | |
| "loss": 0.1838, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 9.933933933933935e-05, | |
| "loss": 0.2782, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 9.873873873873875e-05, | |
| "loss": 0.148, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 9.813813813813815e-05, | |
| "loss": 0.1755, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "eval_accuracy": 0.9096705632306057, | |
| "eval_loss": 0.40392687916755676, | |
| "eval_runtime": 41.1675, | |
| "eval_samples_per_second": 22.858, | |
| "eval_steps_per_second": 2.866, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 9.753753753753754e-05, | |
| "loss": 0.1787, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 9.693693693693694e-05, | |
| "loss": 0.161, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 9.633633633633634e-05, | |
| "loss": 0.3622, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 9.573573573573574e-05, | |
| "loss": 0.2815, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 9.513513513513514e-05, | |
| "loss": 0.206, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 9.453453453453454e-05, | |
| "loss": 0.277, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 9.393393393393394e-05, | |
| "loss": 0.2796, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.2123, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 9.273273273273274e-05, | |
| "loss": 0.2877, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 9.213213213213213e-05, | |
| "loss": 0.2462, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_accuracy": 0.9117959617428267, | |
| "eval_loss": 0.35504746437072754, | |
| "eval_runtime": 42.4152, | |
| "eval_samples_per_second": 22.185, | |
| "eval_steps_per_second": 2.782, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 9.153153153153153e-05, | |
| "loss": 0.2847, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 9.093093093093093e-05, | |
| "loss": 0.1655, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 9.033033033033033e-05, | |
| "loss": 0.168, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 8.972972972972973e-05, | |
| "loss": 0.2172, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 8.912912912912914e-05, | |
| "loss": 0.1425, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 8.852852852852854e-05, | |
| "loss": 0.2147, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 8.792792792792794e-05, | |
| "loss": 0.2172, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 8.732732732732734e-05, | |
| "loss": 0.1565, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 8.672672672672673e-05, | |
| "loss": 0.2442, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 8.612612612612613e-05, | |
| "loss": 0.1737, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "eval_accuracy": 0.9149840595111584, | |
| "eval_loss": 0.34443262219429016, | |
| "eval_runtime": 42.7483, | |
| "eval_samples_per_second": 22.013, | |
| "eval_steps_per_second": 2.76, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 8.552552552552553e-05, | |
| "loss": 0.1837, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 8.492492492492493e-05, | |
| "loss": 0.1993, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 8.432432432432433e-05, | |
| "loss": 0.1556, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 8.372372372372373e-05, | |
| "loss": 0.188, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 8.312312312312313e-05, | |
| "loss": 0.299, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 8.252252252252253e-05, | |
| "loss": 0.1826, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 8.192192192192193e-05, | |
| "loss": 0.2584, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 8.132132132132132e-05, | |
| "loss": 0.1874, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 8.072072072072072e-05, | |
| "loss": 0.2002, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 8.012012012012012e-05, | |
| "loss": 0.174, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "eval_accuracy": 0.9160467587672688, | |
| "eval_loss": 0.3666709363460541, | |
| "eval_runtime": 42.6208, | |
| "eval_samples_per_second": 22.078, | |
| "eval_steps_per_second": 2.769, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 7.951951951951952e-05, | |
| "loss": 0.1239, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 7.891891891891892e-05, | |
| "loss": 0.2739, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 7.831831831831832e-05, | |
| "loss": 0.1614, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 7.771771771771772e-05, | |
| "loss": 0.2269, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 7.711711711711713e-05, | |
| "loss": 0.1065, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 7.651651651651653e-05, | |
| "loss": 0.1147, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 7.591591591591593e-05, | |
| "loss": 0.203, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 7.531531531531531e-05, | |
| "loss": 0.1332, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 7.471471471471471e-05, | |
| "loss": 0.1617, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 7.411411411411412e-05, | |
| "loss": 0.1536, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "eval_accuracy": 0.9287991498405951, | |
| "eval_loss": 0.33007681369781494, | |
| "eval_runtime": 42.7421, | |
| "eval_samples_per_second": 22.016, | |
| "eval_steps_per_second": 2.761, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 7.351351351351352e-05, | |
| "loss": 0.1875, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 7.291291291291292e-05, | |
| "loss": 0.1985, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 7.231231231231232e-05, | |
| "loss": 0.1353, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 7.171171171171172e-05, | |
| "loss": 0.3048, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 7.111111111111112e-05, | |
| "loss": 0.1192, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 7.051051051051052e-05, | |
| "loss": 0.1597, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 6.990990990990991e-05, | |
| "loss": 0.1847, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 6.930930930930931e-05, | |
| "loss": 0.1219, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 6.870870870870871e-05, | |
| "loss": 0.1896, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 6.810810810810811e-05, | |
| "loss": 0.0911, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "eval_accuracy": 0.9298618490967057, | |
| "eval_loss": 0.3390131890773773, | |
| "eval_runtime": 41.5116, | |
| "eval_samples_per_second": 22.668, | |
| "eval_steps_per_second": 2.843, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 6.750750750750751e-05, | |
| "loss": 0.139, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 6.690690690690691e-05, | |
| "loss": 0.1199, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 6.630630630630631e-05, | |
| "loss": 0.2636, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 6.570570570570571e-05, | |
| "loss": 0.2218, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 6.510510510510511e-05, | |
| "loss": 0.22, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 6.45045045045045e-05, | |
| "loss": 0.2532, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 6.39039039039039e-05, | |
| "loss": 0.1398, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 6.33033033033033e-05, | |
| "loss": 0.2485, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 6.27027027027027e-05, | |
| "loss": 0.3601, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 6.21021021021021e-05, | |
| "loss": 0.0907, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "eval_accuracy": 0.9287991498405951, | |
| "eval_loss": 0.29225409030914307, | |
| "eval_runtime": 41.9047, | |
| "eval_samples_per_second": 22.456, | |
| "eval_steps_per_second": 2.816, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 6.15015015015015e-05, | |
| "loss": 0.233, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 6.09009009009009e-05, | |
| "loss": 0.1495, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 6.030030030030031e-05, | |
| "loss": 0.1787, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 5.969969969969971e-05, | |
| "loss": 0.1085, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 5.9099099099099096e-05, | |
| "loss": 0.0735, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 5.84984984984985e-05, | |
| "loss": 0.1993, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 5.7897897897897904e-05, | |
| "loss": 0.1596, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 5.7297297297297305e-05, | |
| "loss": 0.2082, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 5.669669669669669e-05, | |
| "loss": 0.0653, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 5.6096096096096093e-05, | |
| "loss": 0.0921, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_accuracy": 0.9256110520722636, | |
| "eval_loss": 0.3502277135848999, | |
| "eval_runtime": 42.8984, | |
| "eval_samples_per_second": 21.936, | |
| "eval_steps_per_second": 2.751, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 5.5495495495495494e-05, | |
| "loss": 0.1173, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 5.48948948948949e-05, | |
| "loss": 0.2822, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 5.42942942942943e-05, | |
| "loss": 0.1641, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 5.369369369369369e-05, | |
| "loss": 0.0522, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 5.309309309309309e-05, | |
| "loss": 0.0885, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 5.24924924924925e-05, | |
| "loss": 0.2203, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 5.18918918918919e-05, | |
| "loss": 0.2119, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 5.12912912912913e-05, | |
| "loss": 0.1296, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 5.075075075075075e-05, | |
| "loss": 0.1648, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 5.015015015015015e-05, | |
| "loss": 0.1662, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "eval_accuracy": 0.9341126461211477, | |
| "eval_loss": 0.31974515318870544, | |
| "eval_runtime": 42.4132, | |
| "eval_samples_per_second": 22.187, | |
| "eval_steps_per_second": 2.782, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 4.954954954954955e-05, | |
| "loss": 0.3236, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 4.8948948948948954e-05, | |
| "loss": 0.1613, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 4.834834834834835e-05, | |
| "loss": 0.127, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 4.774774774774775e-05, | |
| "loss": 0.19, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 4.714714714714715e-05, | |
| "loss": 0.2622, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 4.654654654654655e-05, | |
| "loss": 0.1676, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 4.594594594594595e-05, | |
| "loss": 0.0607, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 4.5345345345345345e-05, | |
| "loss": 0.0951, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 4.4744744744744746e-05, | |
| "loss": 0.0619, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 4.414414414414415e-05, | |
| "loss": 0.0607, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_accuracy": 0.9362380446333688, | |
| "eval_loss": 0.3092383146286011, | |
| "eval_runtime": 42.8615, | |
| "eval_samples_per_second": 21.954, | |
| "eval_steps_per_second": 2.753, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 4.354354354354355e-05, | |
| "loss": 0.1651, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 4.294294294294294e-05, | |
| "loss": 0.1729, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 4.234234234234234e-05, | |
| "loss": 0.0926, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 4.1741741741741744e-05, | |
| "loss": 0.1416, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 4.1141141141141144e-05, | |
| "loss": 0.1423, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 4.0540540540540545e-05, | |
| "loss": 0.2282, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 3.993993993993994e-05, | |
| "loss": 0.1875, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 3.933933933933934e-05, | |
| "loss": 0.082, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 3.873873873873874e-05, | |
| "loss": 0.0841, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 3.813813813813814e-05, | |
| "loss": 0.111, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "eval_accuracy": 0.9394261424017003, | |
| "eval_loss": 0.3145782947540283, | |
| "eval_runtime": 41.6631, | |
| "eval_samples_per_second": 22.586, | |
| "eval_steps_per_second": 2.832, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 3.7537537537537536e-05, | |
| "loss": 0.1134, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 3.693693693693694e-05, | |
| "loss": 0.2025, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 3.633633633633634e-05, | |
| "loss": 0.0839, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 3.573573573573574e-05, | |
| "loss": 0.1108, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 3.513513513513514e-05, | |
| "loss": 0.1802, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 3.453453453453453e-05, | |
| "loss": 0.0608, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 3.3933933933933934e-05, | |
| "loss": 0.139, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1329, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 3.2732732732732736e-05, | |
| "loss": 0.1711, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 3.213213213213213e-05, | |
| "loss": 0.0588, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "eval_accuracy": 0.9341126461211477, | |
| "eval_loss": 0.3069179654121399, | |
| "eval_runtime": 44.1439, | |
| "eval_samples_per_second": 21.317, | |
| "eval_steps_per_second": 2.673, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 3.153153153153153e-05, | |
| "loss": 0.1412, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 3.093093093093093e-05, | |
| "loss": 0.1177, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 3.0330330330330332e-05, | |
| "loss": 0.0592, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 2.9729729729729733e-05, | |
| "loss": 0.0826, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 2.912912912912913e-05, | |
| "loss": 0.0291, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 2.852852852852853e-05, | |
| "loss": 0.1077, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 2.7927927927927926e-05, | |
| "loss": 0.1541, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 2.732732732732733e-05, | |
| "loss": 0.0972, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 2.672672672672673e-05, | |
| "loss": 0.0879, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 2.6126126126126128e-05, | |
| "loss": 0.131, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "eval_accuracy": 0.9404888416578109, | |
| "eval_loss": 0.29712456464767456, | |
| "eval_runtime": 44.6124, | |
| "eval_samples_per_second": 21.093, | |
| "eval_steps_per_second": 2.645, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 2.552552552552553e-05, | |
| "loss": 0.1452, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 2.4924924924924926e-05, | |
| "loss": 0.1011, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 2.4324324324324327e-05, | |
| "loss": 0.0698, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 2.3723723723723725e-05, | |
| "loss": 0.0426, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 2.3123123123123125e-05, | |
| "loss": 0.155, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 2.2522522522522523e-05, | |
| "loss": 0.118, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 2.1921921921921924e-05, | |
| "loss": 0.1174, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 2.132132132132132e-05, | |
| "loss": 0.1205, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 2.0720720720720722e-05, | |
| "loss": 0.0585, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 2.012012012012012e-05, | |
| "loss": 0.1903, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "eval_accuracy": 0.9383634431455898, | |
| "eval_loss": 0.3077952265739441, | |
| "eval_runtime": 43.3819, | |
| "eval_samples_per_second": 21.691, | |
| "eval_steps_per_second": 2.72, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 1.951951951951952e-05, | |
| "loss": 0.0579, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 1.891891891891892e-05, | |
| "loss": 0.1152, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 1.831831831831832e-05, | |
| "loss": 0.0329, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 1.771771771771772e-05, | |
| "loss": 0.1108, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 1.7117117117117117e-05, | |
| "loss": 0.1499, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 1.6516516516516518e-05, | |
| "loss": 0.0679, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 1.5915915915915915e-05, | |
| "loss": 0.0834, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 1.5315315315315316e-05, | |
| "loss": 0.1488, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 1.4714714714714713e-05, | |
| "loss": 0.0965, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 1.4114114114114116e-05, | |
| "loss": 0.2116, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "eval_accuracy": 0.9341126461211477, | |
| "eval_loss": 0.31116607785224915, | |
| "eval_runtime": 42.4775, | |
| "eval_samples_per_second": 22.153, | |
| "eval_steps_per_second": 2.778, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 1.3513513513513515e-05, | |
| "loss": 0.0979, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 1.2912912912912914e-05, | |
| "loss": 0.1489, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 1.2312312312312313e-05, | |
| "loss": 0.0512, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 1.1711711711711713e-05, | |
| "loss": 0.0908, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0914, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 1.051051051051051e-05, | |
| "loss": 0.0726, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 9.90990990990991e-06, | |
| "loss": 0.0876, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 9.309309309309309e-06, | |
| "loss": 0.153, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 8.708708708708708e-06, | |
| "loss": 0.1306, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 8.108108108108109e-06, | |
| "loss": 0.1415, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "eval_accuracy": 0.9404888416578109, | |
| "eval_loss": 0.29556912183761597, | |
| "eval_runtime": 43.4001, | |
| "eval_samples_per_second": 21.682, | |
| "eval_steps_per_second": 2.719, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 7.507507507507508e-06, | |
| "loss": 0.0865, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 6.906906906906907e-06, | |
| "loss": 0.0654, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 6.306306306306306e-06, | |
| "loss": 0.1104, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 5.705705705705706e-06, | |
| "loss": 0.0943, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 5.105105105105106e-06, | |
| "loss": 0.1215, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 4.504504504504505e-06, | |
| "loss": 0.1062, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 3.903903903903904e-06, | |
| "loss": 0.122, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 3.3033033033033035e-06, | |
| "loss": 0.0634, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 2.702702702702703e-06, | |
| "loss": 0.1094, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 2.102102102102102e-06, | |
| "loss": 0.1106, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "eval_accuracy": 0.9436769394261424, | |
| "eval_loss": 0.2909798324108124, | |
| "eval_runtime": 42.5282, | |
| "eval_samples_per_second": 22.126, | |
| "eval_steps_per_second": 2.775, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 1.5015015015015015e-06, | |
| "loss": 0.026, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 9.00900900900901e-07, | |
| "loss": 0.0736, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.003003003003003e-07, | |
| "loss": 0.0909, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 3330, | |
| "total_flos": 4.175139032456233e+18, | |
| "train_loss": 0.31485966012642547, | |
| "train_runtime": 4358.8867, | |
| "train_samples_per_second": 12.223, | |
| "train_steps_per_second": 0.764 | |
| } | |
| ], | |
| "max_steps": 3330, | |
| "num_train_epochs": 10, | |
| "total_flos": 4.175139032456233e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |