metadata
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of facebook/detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0368
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.4991 | 0.3137 | 100 | 3.6244 |
| 3.1728 | 0.3451 | 110 | 3.4319 |
| 2.7857 | 0.3765 | 120 | 3.2574 |
| 3.0606 | 0.4078 | 130 | 3.1484 |
| 2.6704 | 0.4392 | 140 | 3.0390 |
| 2.7332 | 0.4706 | 150 | 2.9956 |
| 2.8436 | 0.5020 | 160 | 2.9110 |
| 2.8464 | 0.5333 | 170 | 2.8551 |
| 2.1192 | 0.5647 | 180 | 2.8163 |
| 2.6557 | 0.5961 | 190 | 2.8145 |
| 2.3224 | 0.6275 | 200 | 2.7858 |
| 2.6007 | 0.6588 | 210 | 2.7064 |
| 2.6117 | 0.6902 | 220 | 2.6602 |
| 2.4549 | 0.7216 | 230 | 2.6368 |
| 2.5487 | 0.7529 | 240 | 2.6029 |
| 2.6048 | 0.7843 | 250 | 2.5573 |
| 2.0348 | 0.8157 | 260 | 2.5203 |
| 2.4741 | 0.8471 | 270 | 2.4935 |
| 2.5855 | 0.8784 | 280 | 2.4731 |
| 2.1076 | 0.9098 | 290 | 2.4283 |
| 2.3073 | 0.9412 | 300 | 2.3896 |
| 2.214 | 0.9725 | 310 | 2.3919 |
| 2.2078 | 1.0039 | 320 | 2.3343 |
| 2.2391 | 1.0353 | 330 | 2.2970 |
| 2.3607 | 1.0667 | 340 | 2.2921 |
| 2.0244 | 1.0980 | 350 | 2.2751 |
| 2.251 | 1.1294 | 360 | 2.2713 |
| 2.1133 | 1.1608 | 370 | 2.2701 |
| 2.124 | 1.1922 | 380 | 2.2618 |
| 2.1989 | 1.2235 | 390 | 2.2429 |
| 2.2315 | 1.2549 | 400 | 2.2463 |
| 2.2398 | 1.2863 | 410 | 2.2386 |
| 2.261 | 1.3176 | 420 | 2.2360 |
| 2.2144 | 1.3490 | 430 | 2.2427 |
| 2.3344 | 1.3804 | 440 | 2.2452 |
| 2.0412 | 1.4118 | 450 | 2.2092 |
| 2.0854 | 1.4431 | 460 | 2.2197 |
| 2.1636 | 1.4745 | 470 | 2.1830 |
| 1.7776 | 1.5059 | 480 | 2.1904 |
| 2.1118 | 1.5373 | 490 | 2.2194 |
| 2.1203 | 1.5686 | 500 | 2.1978 |
| 2.2468 | 1.6 | 510 | 2.1968 |
| 2.2992 | 1.6314 | 520 | 2.1963 |
| 2.2596 | 1.6627 | 530 | 2.1816 |
| 2.1836 | 1.6941 | 540 | 2.1800 |
| 2.2672 | 1.7255 | 550 | 2.1679 |
| 2.0702 | 1.7569 | 560 | 2.1607 |
| 2.5606 | 1.7882 | 570 | 2.1568 |
| 2.1392 | 1.8196 | 580 | 2.1578 |
| 1.9255 | 1.8510 | 590 | 2.1799 |
| 2.0995 | 1.8824 | 600 | 2.1995 |
| 2.1153 | 1.9137 | 610 | 2.1741 |
| 2.2068 | 1.9451 | 620 | 2.1638 |
| 1.8698 | 1.9765 | 630 | 2.1819 |
| 1.8849 | 2.0078 | 640 | 2.1807 |
| 2.0291 | 2.0392 | 650 | 2.1636 |
| 2.2092 | 2.0706 | 660 | 2.1356 |
| 2.1117 | 2.1020 | 670 | 2.1682 |
| 1.8318 | 2.1333 | 680 | 2.1719 |
| 1.9884 | 2.1647 | 690 | 2.2114 |
| 2.1933 | 2.1961 | 700 | 2.1526 |
| 2.2953 | 2.2275 | 710 | 2.1525 |
| 2.2841 | 2.2588 | 720 | 2.1417 |
| 1.9865 | 2.2902 | 730 | 2.1399 |
| 1.9193 | 2.3216 | 740 | 2.1313 |
| 1.8882 | 2.3529 | 750 | 2.1362 |
| 1.8967 | 2.3843 | 760 | 2.1454 |
| 1.9424 | 2.4157 | 770 | 2.1356 |
| 1.8531 | 2.4471 | 780 | 2.1340 |
| 1.9435 | 2.4784 | 790 | 2.1413 |
| 2.0455 | 2.5098 | 800 | 2.1558 |
| 1.9384 | 2.5412 | 810 | 2.1519 |
| 2.0826 | 2.5725 | 820 | 2.1381 |
| 2.0008 | 2.6039 | 830 | 2.1136 |
| 1.922 | 2.6353 | 840 | 2.1160 |
| 1.9567 | 2.6667 | 850 | 2.0991 |
| 2.2798 | 2.6980 | 860 | 2.0998 |
| 2.4014 | 2.7294 | 870 | 2.0922 |
| 2.3427 | 2.7608 | 880 | 2.0976 |
| 2.2701 | 2.7922 | 890 | 2.0823 |
| 2.1405 | 2.8235 | 900 | 2.1009 |
| 1.9259 | 2.8549 | 910 | 2.1075 |
| 2.0055 | 2.8863 | 920 | 2.1041 |
| 1.9902 | 2.9176 | 930 | 2.0854 |
| 1.9821 | 2.9490 | 940 | 2.1107 |
| 2.0292 | 2.9804 | 950 | 2.0901 |
| 1.9811 | 3.0118 | 960 | 2.1227 |
| 2.2674 | 3.0431 | 970 | 2.0934 |
| 2.0632 | 3.0745 | 980 | 2.0935 |
| 2.1232 | 3.1059 | 990 | 2.0843 |
| 2.0056 | 3.1373 | 1000 | 2.0891 |
| 2.0188 | 3.1686 | 1010 | 2.0811 |
| 2.0898 | 3.2 | 1020 | 2.0848 |
| 2.1809 | 3.2314 | 1030 | 2.0883 |
| 2.1636 | 3.2627 | 1040 | 2.0931 |
| 1.9941 | 3.2941 | 1050 | 2.0894 |
| 1.9761 | 3.3255 | 1060 | 2.0957 |
| 1.9908 | 3.3569 | 1070 | 2.0715 |
| 2.0806 | 3.3882 | 1080 | 2.0774 |
| 1.9419 | 3.4196 | 1090 | 2.0713 |
| 1.8643 | 3.4510 | 1100 | 2.0654 |
| 1.969 | 3.4824 | 1110 | 2.0636 |
| 2.0104 | 3.5137 | 1120 | 2.0710 |
| 1.6745 | 3.5451 | 1130 | 2.0551 |
| 2.047 | 3.5765 | 1140 | 2.0598 |
| 2.1289 | 3.6078 | 1150 | 2.0426 |
| 2.1158 | 3.6392 | 1160 | 2.0525 |
| 1.8543 | 3.6706 | 1170 | 2.0515 |
| 2.0206 | 3.7020 | 1180 | 2.0508 |
| 2.1992 | 3.7333 | 1190 | 2.0485 |
| 1.6875 | 3.7647 | 1200 | 2.0558 |
| 1.8452 | 3.7961 | 1210 | 2.0543 |
| 2.2061 | 3.8275 | 1220 | 2.0594 |
| 2.0418 | 3.8588 | 1230 | 2.0652 |
| 2.0411 | 3.8902 | 1240 | 2.0679 |
| 2.0835 | 3.9216 | 1250 | 2.0731 |
| 1.9003 | 3.9529 | 1260 | 2.0574 |
| 1.7881 | 3.9843 | 1270 | 2.0777 |
| 2.1354 | 4.0157 | 1280 | 2.0630 |
| 1.8935 | 4.0471 | 1290 | 2.0607 |
| 2.1067 | 4.0784 | 1300 | 2.0576 |
| 1.8225 | 4.1098 | 1310 | 2.0767 |
| 1.8132 | 4.1412 | 1320 | 2.0507 |
| 1.985 | 4.1725 | 1330 | 2.0669 |
| 2.112 | 4.2039 | 1340 | 2.0836 |
| 1.7993 | 4.2353 | 1350 | 2.0718 |
| 1.9784 | 4.2667 | 1360 | 2.0676 |
| 2.1628 | 4.2980 | 1370 | 2.0525 |
| 1.876 | 4.3294 | 1380 | 2.0615 |
| 2.0081 | 4.3608 | 1390 | 2.0736 |
| 1.8642 | 4.3922 | 1400 | 2.0565 |
| 1.9308 | 4.4235 | 1410 | 2.0608 |
| 2.2296 | 4.4549 | 1420 | 2.0553 |
| 2.0166 | 4.4863 | 1430 | 2.0575 |
| 2.0422 | 4.5176 | 1440 | 2.0543 |
| 1.8729 | 4.5490 | 1450 | 2.0552 |
| 2.0323 | 4.5804 | 1460 | 2.0656 |
| 1.9935 | 4.6118 | 1470 | 2.0794 |
| 1.8534 | 4.6431 | 1480 | 2.0685 |
| 1.8363 | 4.6745 | 1490 | 2.0581 |
| 1.9679 | 4.7059 | 1500 | 2.0353 |
| 1.8585 | 4.7373 | 1510 | 2.0334 |
| 1.9772 | 4.7686 | 1520 | 2.0420 |
| 1.8753 | 4.8 | 1530 | 2.0427 |
| 1.8911 | 4.8314 | 1540 | 2.0499 |
| 2.0614 | 4.8627 | 1550 | 2.0481 |
| 2.1184 | 4.8941 | 1560 | 2.0481 |
| 1.9504 | 4.9255 | 1570 | 2.0541 |
| 2.1337 | 4.9569 | 1580 | 2.0480 |
| 2.4391 | 4.9882 | 1590 | 2.0416 |
| 1.72 | 5.0196 | 1600 | 2.0412 |
| 2.0808 | 5.0510 | 1610 | 2.0458 |
| 1.8639 | 5.0824 | 1620 | 2.0438 |
| 1.9462 | 5.1137 | 1630 | 2.0428 |
| 2.0055 | 5.1451 | 1640 | 2.0366 |
| 2.0345 | 5.1765 | 1650 | 2.0644 |
| 1.9321 | 5.2078 | 1660 | 2.0454 |
| 1.8705 | 5.2392 | 1670 | 2.0394 |
| 2.0345 | 5.2706 | 1680 | 2.0475 |
| 1.9992 | 5.3020 | 1690 | 2.0567 |
| 2.2208 | 5.3333 | 1700 | 2.0558 |
| 1.8253 | 5.3647 | 1710 | 2.0413 |
| 2.0765 | 5.3961 | 1720 | 2.0319 |
| 2.2315 | 5.4275 | 1730 | 2.0360 |
| 2.2432 | 5.4588 | 1740 | 2.0436 |
| 2.0666 | 5.4902 | 1750 | 2.0451 |
| 2.0603 | 5.5216 | 1760 | 2.0296 |
| 1.6625 | 5.5529 | 1770 | 2.0513 |
| 2.0946 | 5.5843 | 1780 | 2.0306 |
| 1.9464 | 5.6157 | 1790 | 2.0315 |
| 2.0183 | 5.6471 | 1800 | 2.0276 |
| 2.0794 | 5.6784 | 1810 | 2.0512 |
| 2.0289 | 5.7098 | 1820 | 2.0369 |
| 2.1014 | 5.7412 | 1830 | 2.0520 |
| 1.9159 | 5.7725 | 1840 | 2.0491 |
| 2.2446 | 5.8039 | 1850 | 2.0508 |
| 1.9383 | 5.8353 | 1860 | 2.0327 |
| 2.0132 | 5.8667 | 1870 | 2.0161 |
| 2.2234 | 5.8980 | 1880 | 2.0406 |
| 2.2556 | 5.9294 | 1890 | 2.0365 |
| 2.2061 | 5.9608 | 1900 | 2.0314 |
| 1.7465 | 5.9922 | 1910 | 2.0543 |
| 1.9388 | 6.0235 | 1920 | 2.0525 |
| 1.9223 | 6.0549 | 1930 | 2.0325 |
| 1.9386 | 6.0863 | 1940 | 2.0282 |
| 1.9171 | 6.1176 | 1950 | 2.0462 |
| 1.9319 | 6.1490 | 1960 | 2.0369 |
| 1.7689 | 6.1804 | 1970 | 2.0364 |
| 2.0063 | 6.2118 | 1980 | 2.0388 |
| 2.1053 | 6.2431 | 1990 | 2.0346 |
| 2.1074 | 6.2745 | 2000 | 2.0368 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1
- Datasets 2.19.2
- Tokenizers 0.19.1