| { | |
| "best_metric": 0.8085106382978723, | |
| "best_model_checkpoint": "videomae-base-finetuned-movienet-finetuned-movienet-more/checkpoint-372", | |
| "epoch": 7.120270270270271, | |
| "global_step": 1480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.3783783783783788e-06, | |
| "loss": 0.6452, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.7567567567567575e-06, | |
| "loss": 0.3741, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.0135135135135136e-05, | |
| "loss": 0.2853, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.3513513513513515e-05, | |
| "loss": 0.5599, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.6891891891891892e-05, | |
| "loss": 0.3713, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.0270270270270273e-05, | |
| "loss": 0.1326, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.364864864864865e-05, | |
| "loss": 0.1683, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 0.4612, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.0405405405405407e-05, | |
| "loss": 0.3596, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3783783783783784e-05, | |
| "loss": 0.2449, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.7162162162162165e-05, | |
| "loss": 0.1317, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.0540540540540545e-05, | |
| "loss": 0.53, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.391891891891892e-05, | |
| "loss": 0.1933, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.72972972972973e-05, | |
| "loss": 0.3087, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.9924924924924924e-05, | |
| "loss": 0.365, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.954954954954955e-05, | |
| "loss": 0.3458, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.9174174174174175e-05, | |
| "loss": 0.4004, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.87987987987988e-05, | |
| "loss": 0.4977, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.723404255319149, | |
| "eval_loss": 0.8209818601608276, | |
| "eval_runtime": 325.1637, | |
| "eval_samples_per_second": 0.578, | |
| "eval_steps_per_second": 0.074, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.8423423423423426e-05, | |
| "loss": 0.31, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.804804804804805e-05, | |
| "loss": 0.4281, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.767267267267268e-05, | |
| "loss": 0.5228, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.72972972972973e-05, | |
| "loss": 0.4479, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.692192192192192e-05, | |
| "loss": 0.4205, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.654654654654655e-05, | |
| "loss": 0.6442, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.617117117117117e-05, | |
| "loss": 0.5665, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.57957957957958e-05, | |
| "loss": 0.4637, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.5420420420420424e-05, | |
| "loss": 0.2689, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.5045045045045046e-05, | |
| "loss": 0.2813, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.4669669669669675e-05, | |
| "loss": 0.5086, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.42942942942943e-05, | |
| "loss": 0.2338, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.391891891891892e-05, | |
| "loss": 0.4156, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.354354354354355e-05, | |
| "loss": 0.4025, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.316816816816817e-05, | |
| "loss": 0.3151, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.27927927927928e-05, | |
| "loss": 0.4204, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.241741741741742e-05, | |
| "loss": 0.4158, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.204204204204204e-05, | |
| "loss": 0.3485, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.3974, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_accuracy": 0.8085106382978723, | |
| "eval_loss": 0.632224977016449, | |
| "eval_runtime": 167.3633, | |
| "eval_samples_per_second": 1.123, | |
| "eval_steps_per_second": 0.143, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.1291291291291294e-05, | |
| "loss": 0.2036, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.091591591591592e-05, | |
| "loss": 0.2391, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.0540540540540545e-05, | |
| "loss": 0.2951, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.016516516516517e-05, | |
| "loss": 0.3131, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.9789789789789796e-05, | |
| "loss": 0.3097, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 3.941441441441442e-05, | |
| "loss": 0.1422, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.903903903903904e-05, | |
| "loss": 0.0668, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.866366366366366e-05, | |
| "loss": 0.2289, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 3.8288288288288285e-05, | |
| "loss": 0.1771, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.7912912912912914e-05, | |
| "loss": 0.1779, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.7537537537537536e-05, | |
| "loss": 0.6673, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.7162162162162165e-05, | |
| "loss": 0.2319, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.678678678678679e-05, | |
| "loss": 0.157, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.641141141141141e-05, | |
| "loss": 0.2388, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.603603603603604e-05, | |
| "loss": 0.4595, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.566066066066066e-05, | |
| "loss": 0.2776, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.528528528528528e-05, | |
| "loss": 0.2687, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.490990990990991e-05, | |
| "loss": 0.1101, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 1.0521998405456543, | |
| "eval_runtime": 162.7827, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.147, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.453453453453453e-05, | |
| "loss": 0.1566, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.415915915915916e-05, | |
| "loss": 0.2506, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.3783783783783784e-05, | |
| "loss": 0.0709, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.3408408408408406e-05, | |
| "loss": 0.1136, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.3033033033033035e-05, | |
| "loss": 0.3604, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.265765765765766e-05, | |
| "loss": 0.0949, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.2282282282282286e-05, | |
| "loss": 0.038, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 3.190690690690691e-05, | |
| "loss": 0.0487, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 3.153153153153153e-05, | |
| "loss": 0.1361, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 3.115615615615616e-05, | |
| "loss": 0.2508, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.078078078078078e-05, | |
| "loss": 0.0955, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 3.0405405405405407e-05, | |
| "loss": 0.2185, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 3.0030030030030033e-05, | |
| "loss": 0.3311, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 2.9654654654654658e-05, | |
| "loss": 0.1093, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 2.927927927927928e-05, | |
| "loss": 0.0554, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 2.8903903903903906e-05, | |
| "loss": 0.084, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 2.852852852852853e-05, | |
| "loss": 0.1206, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2.8153153153153157e-05, | |
| "loss": 0.2526, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1618, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_accuracy": 0.7872340425531915, | |
| "eval_loss": 0.9184951782226562, | |
| "eval_runtime": 122.6151, | |
| "eval_samples_per_second": 1.533, | |
| "eval_steps_per_second": 0.196, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.7402402402402405e-05, | |
| "loss": 0.0652, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 0.027, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 2.6651651651651656e-05, | |
| "loss": 0.0875, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 2.6276276276276278e-05, | |
| "loss": 0.2058, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 2.5900900900900903e-05, | |
| "loss": 0.0566, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 2.552552552552553e-05, | |
| "loss": 0.082, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 2.5150150150150154e-05, | |
| "loss": 0.0835, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 2.4774774774774777e-05, | |
| "loss": 0.0831, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.43993993993994e-05, | |
| "loss": 0.0566, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.4024024024024024e-05, | |
| "loss": 0.053, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 2.364864864864865e-05, | |
| "loss": 0.0415, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 2.3273273273273275e-05, | |
| "loss": 0.072, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.28978978978979e-05, | |
| "loss": 0.1109, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.2522522522522523e-05, | |
| "loss": 0.1355, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 2.214714714714715e-05, | |
| "loss": 0.0971, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 2.1771771771771774e-05, | |
| "loss": 0.1569, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 2.13963963963964e-05, | |
| "loss": 0.0111, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 2.102102102102102e-05, | |
| "loss": 0.0249, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 2.0645645645645647e-05, | |
| "loss": 0.0052, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_accuracy": 0.8085106382978723, | |
| "eval_loss": 0.8585702776908875, | |
| "eval_runtime": 123.8694, | |
| "eval_samples_per_second": 1.518, | |
| "eval_steps_per_second": 0.194, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 2.0270270270270273e-05, | |
| "loss": 0.008, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 1.9894894894894898e-05, | |
| "loss": 0.0054, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 1.951951951951952e-05, | |
| "loss": 0.0067, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1.9144144144144142e-05, | |
| "loss": 0.0022, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1.8768768768768768e-05, | |
| "loss": 0.0504, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 1.8393393393393393e-05, | |
| "loss": 0.001, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 1.801801801801802e-05, | |
| "loss": 0.0017, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 1.764264264264264e-05, | |
| "loss": 0.0025, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 1.7267267267267267e-05, | |
| "loss": 0.1008, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.6891891891891892e-05, | |
| "loss": 0.0033, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.6516516516516518e-05, | |
| "loss": 0.0022, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 1.6141141141141143e-05, | |
| "loss": 0.0122, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 1.5765765765765765e-05, | |
| "loss": 0.0615, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 1.539039039039039e-05, | |
| "loss": 0.1198, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 1.5015015015015016e-05, | |
| "loss": 0.0386, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 1.463963963963964e-05, | |
| "loss": 0.0491, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 1.4264264264264266e-05, | |
| "loss": 0.0265, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.0013, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "eval_accuracy": 0.7925531914893617, | |
| "eval_loss": 1.0028539896011353, | |
| "eval_runtime": 127.0573, | |
| "eval_samples_per_second": 1.48, | |
| "eval_steps_per_second": 0.189, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.3513513513513515e-05, | |
| "loss": 0.0228, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 1.3138138138138139e-05, | |
| "loss": 0.0011, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 1.2762762762762764e-05, | |
| "loss": 0.0247, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 1.2387387387387388e-05, | |
| "loss": 0.0048, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 1.2012012012012012e-05, | |
| "loss": 0.0009, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.1636636636636638e-05, | |
| "loss": 0.0065, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.1261261261261261e-05, | |
| "loss": 0.0012, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.0885885885885887e-05, | |
| "loss": 0.0036, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 1.051051051051051e-05, | |
| "loss": 0.0009, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 1.0135135135135136e-05, | |
| "loss": 0.0115, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 9.75975975975976e-06, | |
| "loss": 0.011, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 9.384384384384384e-06, | |
| "loss": 0.0318, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 9.00900900900901e-06, | |
| "loss": 0.0025, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 8.633633633633633e-06, | |
| "loss": 0.0373, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 8.258258258258259e-06, | |
| "loss": 0.0651, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 7.882882882882883e-06, | |
| "loss": 0.0052, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 7.507507507507508e-06, | |
| "loss": 0.0008, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 7.132132132132133e-06, | |
| "loss": 0.0013, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 6.7567567567567575e-06, | |
| "loss": 0.0044, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_accuracy": 0.7872340425531915, | |
| "eval_loss": 1.0399647951126099, | |
| "eval_runtime": 160.3025, | |
| "eval_samples_per_second": 1.173, | |
| "eval_steps_per_second": 0.15, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 6.381381381381382e-06, | |
| "loss": 0.0009, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 6.006006006006006e-06, | |
| "loss": 0.0016, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 5.630630630630631e-06, | |
| "loss": 0.0008, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 5.255255255255255e-06, | |
| "loss": 0.0008, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 4.87987987987988e-06, | |
| "loss": 0.0009, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 4.504504504504505e-06, | |
| "loss": 0.0007, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 4.129129129129129e-06, | |
| "loss": 0.001, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 3.753753753753754e-06, | |
| "loss": 0.0008, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 3.3783783783783788e-06, | |
| "loss": 0.0007, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 3.003003003003003e-06, | |
| "loss": 0.001, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 2.6276276276276277e-06, | |
| "loss": 0.0007, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 2.2522522522522524e-06, | |
| "loss": 0.016, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 1.876876876876877e-06, | |
| "loss": 0.0008, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 1.5015015015015015e-06, | |
| "loss": 0.0023, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 1.1261261261261262e-06, | |
| "loss": 0.0007, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 7.507507507507508e-07, | |
| "loss": 0.0007, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 3.753753753753754e-07, | |
| "loss": 0.0007, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 0.0, | |
| "loss": 0.0008, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "eval_accuracy": 0.7978723404255319, | |
| "eval_loss": 1.0017523765563965, | |
| "eval_runtime": 123.2439, | |
| "eval_samples_per_second": 1.525, | |
| "eval_steps_per_second": 0.195, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "step": 1480, | |
| "total_flos": 1.4692740659720847e+19, | |
| "train_loss": 0.1616095771478187, | |
| "train_runtime": 12949.9285, | |
| "train_samples_per_second": 0.914, | |
| "train_steps_per_second": 0.114 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "eval_accuracy": 0.7916666666666666, | |
| "eval_loss": 0.6821911931037903, | |
| "eval_runtime": 285.028, | |
| "eval_samples_per_second": 0.674, | |
| "eval_steps_per_second": 0.084, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "eval_accuracy": 0.7916666666666666, | |
| "eval_loss": 0.6821911931037903, | |
| "eval_runtime": 126.6935, | |
| "eval_samples_per_second": 1.515, | |
| "eval_steps_per_second": 0.189, | |
| "step": 1480 | |
| } | |
| ], | |
| "max_steps": 1480, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.4692740659720847e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |