metadata
license: other
base_model: nvidia/mit-b0
tags:
- vision
- image-segmentation
- generated_from_trainer
model-index:
- name: segformer-b0-finetuned-segments-sidewalk-2
results: []
segformer-b0-finetuned-segments-sidewalk-2
This model is a fine-tuned version of nvidia/mit-b0 on the eleninaneversmiles/wheels dataset. It achieves the following results on the evaluation set:
- Loss: 0.1170
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: 6e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 300
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9481 | 4.0 | 20 | 3.5435 |
| 2.6731 | 8.0 | 40 | 3.0067 |
| 2.6124 | 12.0 | 60 | 2.4952 |
| 2.0959 | 16.0 | 80 | 2.0672 |
| 2.0621 | 20.0 | 100 | 1.8896 |
| 1.8677 | 24.0 | 120 | 1.6907 |
| 1.7867 | 28.0 | 140 | 1.5101 |
| 1.3991 | 32.0 | 160 | 1.3829 |
| 1.1594 | 36.0 | 180 | 1.2332 |
| 1.0339 | 40.0 | 200 | 1.0889 |
| 0.8877 | 44.0 | 220 | 0.9699 |
| 0.9484 | 48.0 | 240 | 0.8998 |
| 0.8533 | 52.0 | 260 | 0.7505 |
| 0.5803 | 56.0 | 280 | 0.6548 |
| 0.5161 | 60.0 | 300 | 0.5719 |
| 0.4307 | 64.0 | 320 | 0.5128 |
| 0.3615 | 68.0 | 340 | 0.4228 |
| 0.3185 | 72.0 | 360 | 0.3733 |
| 0.2852 | 76.0 | 380 | 0.3421 |
| 0.299 | 80.0 | 400 | 0.3033 |
| 0.2014 | 84.0 | 420 | 0.2814 |
| 0.2139 | 88.0 | 440 | 0.2346 |
| 0.147 | 92.0 | 460 | 0.2176 |
| 0.1386 | 96.0 | 480 | 0.2030 |
| 0.1189 | 100.0 | 500 | 0.1950 |
| 0.1527 | 104.0 | 520 | 0.1804 |
| 0.093 | 108.0 | 540 | 0.1708 |
| 0.0934 | 112.0 | 560 | 0.1712 |
| 0.0878 | 116.0 | 580 | 0.1582 |
| 0.1096 | 120.0 | 600 | 0.1553 |
| 0.0743 | 124.0 | 620 | 0.1460 |
| 0.0677 | 128.0 | 640 | 0.1413 |
| 0.0661 | 132.0 | 660 | 0.1399 |
| 0.0619 | 136.0 | 680 | 0.1359 |
| 0.0617 | 140.0 | 700 | 0.1318 |
| 0.064 | 144.0 | 720 | 0.1316 |
| 0.0542 | 148.0 | 740 | 0.1309 |
| 0.0584 | 152.0 | 760 | 0.1286 |
| 0.0525 | 156.0 | 780 | 0.1298 |
| 0.069 | 160.0 | 800 | 0.1283 |
| 0.05 | 164.0 | 820 | 0.1270 |
| 0.0497 | 168.0 | 840 | 0.1240 |
| 0.0478 | 172.0 | 860 | 0.1231 |
| 0.0472 | 176.0 | 880 | 0.1190 |
| 0.0457 | 180.0 | 900 | 0.1207 |
| 0.0435 | 184.0 | 920 | 0.1221 |
| 0.0427 | 188.0 | 940 | 0.1212 |
| 0.0425 | 192.0 | 960 | 0.1197 |
| 0.0481 | 196.0 | 980 | 0.1199 |
| 0.0484 | 200.0 | 1000 | 0.1210 |
| 0.0553 | 204.0 | 1020 | 0.1197 |
| 0.0389 | 208.0 | 1040 | 0.1177 |
| 0.0391 | 212.0 | 1060 | 0.1181 |
| 0.0491 | 216.0 | 1080 | 0.1226 |
| 0.038 | 220.0 | 1100 | 0.1189 |
| 0.0443 | 224.0 | 1120 | 0.1177 |
| 0.038 | 228.0 | 1140 | 0.1178 |
| 0.0365 | 232.0 | 1160 | 0.1186 |
| 0.044 | 236.0 | 1180 | 0.1174 |
| 0.0608 | 240.0 | 1200 | 0.1205 |
| 0.0356 | 244.0 | 1220 | 0.1200 |
| 0.0431 | 248.0 | 1240 | 0.1195 |
| 0.0414 | 252.0 | 1260 | 0.1183 |
| 0.0374 | 256.0 | 1280 | 0.1173 |
| 0.0389 | 260.0 | 1300 | 0.1185 |
| 0.0335 | 264.0 | 1320 | 0.1181 |
| 0.0363 | 268.0 | 1340 | 0.1182 |
| 0.0408 | 272.0 | 1360 | 0.1191 |
| 0.0411 | 276.0 | 1380 | 0.1186 |
| 0.037 | 280.0 | 1400 | 0.1176 |
| 0.0424 | 284.0 | 1420 | 0.1185 |
| 0.04 | 288.0 | 1440 | 0.1200 |
| 0.0399 | 292.0 | 1460 | 0.1187 |
| 0.0415 | 296.0 | 1480 | 0.1186 |
| 0.038 | 300.0 | 1500 | 0.1170 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cpu
- Datasets 2.19.2
- Tokenizers 0.19.1