| { | |
| "best_metric": 0.9507407407407408, | |
| "best_model_checkpoint": "mobilevit-xx-small-finetuned-eurosat/checkpoint-1520", | |
| "epoch": 10.0, | |
| "global_step": 1900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.631578947368421e-06, | |
| "loss": 2.3276, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 2.3289, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.894736842105263e-06, | |
| "loss": 2.3152, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 2.3021, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 2.2939, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.5789473684210526e-05, | |
| "loss": 2.2682, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.8421052631578947e-05, | |
| "loss": 2.2401, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.105263157894737e-05, | |
| "loss": 2.2106, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.368421052631579e-05, | |
| "loss": 2.1706, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 2.1411, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.8947368421052634e-05, | |
| "loss": 2.0986, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.157894736842105e-05, | |
| "loss": 2.0471, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.421052631578947e-05, | |
| "loss": 2.0002, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.6842105263157895e-05, | |
| "loss": 1.9392, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 1.8584, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.210526315789474e-05, | |
| "loss": 1.7827, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.473684210526316e-05, | |
| "loss": 1.6963, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.736842105263158e-05, | |
| "loss": 1.5962, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5074, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7077777777777777, | |
| "eval_loss": 1.3433218002319336, | |
| "eval_runtime": 6.7484, | |
| "eval_samples_per_second": 400.097, | |
| "eval_steps_per_second": 12.596, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 1.4517, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.941520467836258e-05, | |
| "loss": 1.4136, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.912280701754386e-05, | |
| "loss": 1.3514, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.883040935672515e-05, | |
| "loss": 1.3052, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 4.853801169590643e-05, | |
| "loss": 1.2468, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.824561403508772e-05, | |
| "loss": 1.2389, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.7953216374269006e-05, | |
| "loss": 1.1687, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 4.7660818713450294e-05, | |
| "loss": 1.1483, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 4.736842105263158e-05, | |
| "loss": 1.1665, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.707602339181287e-05, | |
| "loss": 1.0939, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 1.0914, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.649122807017544e-05, | |
| "loss": 1.0623, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.619883040935672e-05, | |
| "loss": 1.0393, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.590643274853802e-05, | |
| "loss": 1.0274, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 4.56140350877193e-05, | |
| "loss": 0.9957, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 4.5321637426900585e-05, | |
| "loss": 1.0176, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 4.502923976608187e-05, | |
| "loss": 0.9963, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.473684210526316e-05, | |
| "loss": 0.9611, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.9398, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.85, | |
| "eval_loss": 0.717716634273529, | |
| "eval_runtime": 6.6482, | |
| "eval_samples_per_second": 406.123, | |
| "eval_steps_per_second": 12.785, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.4152046783625734e-05, | |
| "loss": 0.9262, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.8718, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 4.356725146198831e-05, | |
| "loss": 0.8925, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 4.327485380116959e-05, | |
| "loss": 0.852, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.298245614035088e-05, | |
| "loss": 0.8706, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 4.269005847953216e-05, | |
| "loss": 0.8152, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 4.239766081871345e-05, | |
| "loss": 0.823, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 4.210526315789474e-05, | |
| "loss": 0.8239, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 4.1812865497076025e-05, | |
| "loss": 0.7756, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.152046783625731e-05, | |
| "loss": 0.8068, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.12280701754386e-05, | |
| "loss": 0.7516, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.7439, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 4.0643274853801174e-05, | |
| "loss": 0.7157, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.0350877192982455e-05, | |
| "loss": 0.7353, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 4.005847953216375e-05, | |
| "loss": 0.6941, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.976608187134503e-05, | |
| "loss": 0.6756, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 0.6934, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.9181286549707604e-05, | |
| "loss": 0.6508, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.7035, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9070370370370371, | |
| "eval_loss": 0.4251876175403595, | |
| "eval_runtime": 6.5087, | |
| "eval_samples_per_second": 414.829, | |
| "eval_steps_per_second": 13.059, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 3.859649122807018e-05, | |
| "loss": 0.6747, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.8304093567251465e-05, | |
| "loss": 0.6437, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.6677, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.771929824561404e-05, | |
| "loss": 0.6333, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 3.742690058479532e-05, | |
| "loss": 0.5999, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.713450292397661e-05, | |
| "loss": 0.6074, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.6842105263157895e-05, | |
| "loss": 0.6006, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 3.654970760233918e-05, | |
| "loss": 0.5783, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 3.625730994152047e-05, | |
| "loss": 0.6052, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 3.5964912280701756e-05, | |
| "loss": 0.5428, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 3.5672514619883044e-05, | |
| "loss": 0.6207, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 3.538011695906433e-05, | |
| "loss": 0.5259, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.5637, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 3.4795321637426905e-05, | |
| "loss": 0.5595, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 3.4502923976608186e-05, | |
| "loss": 0.5284, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 3.421052631578947e-05, | |
| "loss": 0.5708, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 3.391812865497076e-05, | |
| "loss": 0.568, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 3.362573099415205e-05, | |
| "loss": 0.5766, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.5435, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9281481481481482, | |
| "eval_loss": 0.3079540431499481, | |
| "eval_runtime": 6.531, | |
| "eval_samples_per_second": 413.415, | |
| "eval_steps_per_second": 13.015, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 3.304093567251462e-05, | |
| "loss": 0.5273, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 3.274853801169591e-05, | |
| "loss": 0.5117, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 3.24561403508772e-05, | |
| "loss": 0.52, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.5671, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 3.187134502923977e-05, | |
| "loss": 0.4939, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 3.157894736842105e-05, | |
| "loss": 0.5159, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 3.128654970760234e-05, | |
| "loss": 0.5199, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 3.0994152046783626e-05, | |
| "loss": 0.5391, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 3.0701754385964913e-05, | |
| "loss": 0.5256, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 3.0409356725146197e-05, | |
| "loss": 0.5168, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 3.0116959064327488e-05, | |
| "loss": 0.4874, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 2.9824561403508772e-05, | |
| "loss": 0.4711, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 2.9532163742690062e-05, | |
| "loss": 0.4856, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.4733, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 2.8947368421052634e-05, | |
| "loss": 0.4822, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 2.8654970760233917e-05, | |
| "loss": 0.4633, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 2.8362573099415208e-05, | |
| "loss": 0.4827, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 2.8070175438596492e-05, | |
| "loss": 0.477, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5007, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9388888888888889, | |
| "eval_loss": 0.24653582274913788, | |
| "eval_runtime": 7.0867, | |
| "eval_samples_per_second": 380.997, | |
| "eval_steps_per_second": 11.994, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 2.7485380116959063e-05, | |
| "loss": 0.4798, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 2.7192982456140354e-05, | |
| "loss": 0.4548, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 2.6900584795321637e-05, | |
| "loss": 0.4981, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 2.6608187134502928e-05, | |
| "loss": 0.4549, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.4804, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 2.60233918128655e-05, | |
| "loss": 0.475, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 2.5730994152046783e-05, | |
| "loss": 0.4739, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 2.5438596491228074e-05, | |
| "loss": 0.4497, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 2.5146198830409358e-05, | |
| "loss": 0.5059, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 2.485380116959064e-05, | |
| "loss": 0.4863, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 2.456140350877193e-05, | |
| "loss": 0.5016, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 2.4269005847953216e-05, | |
| "loss": 0.4152, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 2.3976608187134503e-05, | |
| "loss": 0.4425, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 2.368421052631579e-05, | |
| "loss": 0.5285, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.4645, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 2.309941520467836e-05, | |
| "loss": 0.424, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 2.280701754385965e-05, | |
| "loss": 0.4313, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 2.2514619883040936e-05, | |
| "loss": 0.4525, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.4533, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9444444444444444, | |
| "eval_loss": 0.22906289994716644, | |
| "eval_runtime": 6.6825, | |
| "eval_samples_per_second": 404.042, | |
| "eval_steps_per_second": 12.72, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 2.1929824561403507e-05, | |
| "loss": 0.4753, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 2.1637426900584794e-05, | |
| "loss": 0.4641, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 2.134502923976608e-05, | |
| "loss": 0.4654, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 2.105263157894737e-05, | |
| "loss": 0.4861, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 2.0760233918128656e-05, | |
| "loss": 0.4639, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.4197, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 2.0175438596491227e-05, | |
| "loss": 0.4251, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 1.9883040935672515e-05, | |
| "loss": 0.4716, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 1.9590643274853802e-05, | |
| "loss": 0.4679, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 1.929824561403509e-05, | |
| "loss": 0.3977, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 1.9005847953216373e-05, | |
| "loss": 0.4449, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 1.871345029239766e-05, | |
| "loss": 0.4409, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 1.8421052631578947e-05, | |
| "loss": 0.4587, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.8128654970760235e-05, | |
| "loss": 0.412, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 1.7836257309941522e-05, | |
| "loss": 0.4097, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.4342, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 1.7251461988304093e-05, | |
| "loss": 0.471, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 1.695906432748538e-05, | |
| "loss": 0.4607, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.3961, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9496296296296296, | |
| "eval_loss": 0.19912981986999512, | |
| "eval_runtime": 6.7692, | |
| "eval_samples_per_second": 398.866, | |
| "eval_steps_per_second": 12.557, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 1.6374269005847955e-05, | |
| "loss": 0.4264, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 1.608187134502924e-05, | |
| "loss": 0.387, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 1.5789473684210526e-05, | |
| "loss": 0.4116, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 1.5497076023391813e-05, | |
| "loss": 0.4089, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 1.5204678362573099e-05, | |
| "loss": 0.4028, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 1.4912280701754386e-05, | |
| "loss": 0.4375, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.4481, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 1.4327485380116959e-05, | |
| "loss": 0.403, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 1.4035087719298246e-05, | |
| "loss": 0.4124, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 1.3742690058479531e-05, | |
| "loss": 0.4091, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 1.3450292397660819e-05, | |
| "loss": 0.4497, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 0.4252, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 1.2865497076023392e-05, | |
| "loss": 0.4626, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 1.2573099415204679e-05, | |
| "loss": 0.4044, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 1.2280701754385964e-05, | |
| "loss": 0.4299, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1.1988304093567252e-05, | |
| "loss": 0.43, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.4418, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 1.1403508771929824e-05, | |
| "loss": 0.4073, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3949, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9507407407407408, | |
| "eval_loss": 0.1926022469997406, | |
| "eval_runtime": 6.688, | |
| "eval_samples_per_second": 403.706, | |
| "eval_steps_per_second": 12.709, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 1.0818713450292397e-05, | |
| "loss": 0.4227, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 0.4243, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 1.023391812865497e-05, | |
| "loss": 0.4481, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 9.941520467836257e-06, | |
| "loss": 0.465, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 9.649122807017545e-06, | |
| "loss": 0.4156, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 9.35672514619883e-06, | |
| "loss": 0.397, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 9.064327485380117e-06, | |
| "loss": 0.4107, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.4445, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 8.47953216374269e-06, | |
| "loss": 0.3787, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 8.187134502923977e-06, | |
| "loss": 0.4289, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 7.894736842105263e-06, | |
| "loss": 0.398, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 7.602339181286549e-06, | |
| "loss": 0.4389, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 7.3099415204678366e-06, | |
| "loss": 0.3948, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 7.017543859649123e-06, | |
| "loss": 0.4032, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 6.725146198830409e-06, | |
| "loss": 0.4187, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 6.432748538011696e-06, | |
| "loss": 0.4195, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 6.140350877192982e-06, | |
| "loss": 0.3972, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.3934, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.4302, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.95, | |
| "eval_loss": 0.19283165037631989, | |
| "eval_runtime": 6.6653, | |
| "eval_samples_per_second": 405.082, | |
| "eval_steps_per_second": 12.753, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 0.4043, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 4.970760233918129e-06, | |
| "loss": 0.4216, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 4.678362573099415e-06, | |
| "loss": 0.3846, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 4.3859649122807014e-06, | |
| "loss": 0.4307, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 4.093567251461989e-06, | |
| "loss": 0.3826, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.8011695906432747e-06, | |
| "loss": 0.4006, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 3.5087719298245615e-06, | |
| "loss": 0.4459, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 3.216374269005848e-06, | |
| "loss": 0.4038, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.4069, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 2.631578947368421e-06, | |
| "loss": 0.3911, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 2.3391812865497075e-06, | |
| "loss": 0.4002, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 2.0467836257309943e-06, | |
| "loss": 0.3768, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 1.7543859649122807e-06, | |
| "loss": 0.4195, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 1.4619883040935671e-06, | |
| "loss": 0.4108, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 1.1695906432748538e-06, | |
| "loss": 0.3811, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 8.771929824561404e-07, | |
| "loss": 0.4, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 5.847953216374269e-07, | |
| "loss": 0.3771, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 2.9239766081871344e-07, | |
| "loss": 0.4072, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.4061, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9462962962962963, | |
| "eval_loss": 0.1930549293756485, | |
| "eval_runtime": 6.7634, | |
| "eval_samples_per_second": 399.209, | |
| "eval_steps_per_second": 12.568, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1900, | |
| "total_flos": 3.46193285935104e+17, | |
| "train_loss": 0.7228629551435771, | |
| "train_runtime": 1251.8481, | |
| "train_samples_per_second": 194.113, | |
| "train_steps_per_second": 1.518 | |
| } | |
| ], | |
| "max_steps": 1900, | |
| "num_train_epochs": 10, | |
| "total_flos": 3.46193285935104e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |