End of training
Browse files
README.md
CHANGED
@@ -15,17 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [nvidia/mit-b4](https://huggingface.co/nvidia/mit-b4) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
-
|
19 |
-
-
|
20 |
-
-
|
21 |
-
-
|
22 |
-
-
|
23 |
-
-
|
24 |
-
- eval_runtime: 733.0358
|
25 |
-
- eval_samples_per_second: 1.247
|
26 |
-
- eval_steps_per_second: 0.312
|
27 |
-
- epoch: 3.0
|
28 |
-
- step: 1371
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -52,6 +47,22 @@ The following hyperparameters were used during training:
|
|
52 |
- lr_scheduler_type: linear
|
53 |
- num_epochs: 10
|
54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
### Framework versions
|
56 |
|
57 |
- Transformers 4.33.1
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [nvidia/mit-b4](https://huggingface.co/nvidia/mit-b4) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.1675
|
19 |
+
- Mean Iou: 0.7570
|
20 |
+
- Mean Accuracy: 0.8341
|
21 |
+
- Overall Accuracy: 0.9396
|
22 |
+
- Per Category Iou: [0.9341045714153958, 0.5798374949488075]
|
23 |
+
- Per Category Accuracy: [0.9728893841433082, 0.6952250066198535]
|
|
|
|
|
|
|
|
|
|
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
47 |
- lr_scheduler_type: linear
|
48 |
- num_epochs: 10
|
49 |
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:----------------------------------------:|:----------------------------------------:|
|
54 |
+
| 0.1426 | 1.0 | 457 | 0.1936 | 0.6822 | 0.7438 | 0.9242 | [0.9193425271297406, 0.4449612711247542] | [0.9811465495367065, 0.5065393570873438] |
|
55 |
+
| 0.1066 | 2.0 | 914 | 0.1840 | 0.7247 | 0.8166 | 0.9281 | [0.921792369706966, 0.5275532773693746] | [0.9632516253169541, 0.6698574354887572] |
|
56 |
+
| 0.1902 | 3.0 | 1371 | 0.1825 | 0.7341 | 0.8195 | 0.9320 | [0.9260615811301273, 0.5422064806171729] | [0.9674973788201077, 0.6715653524785264] |
|
57 |
+
| 0.0337 | 4.0 | 1828 | 0.1754 | 0.7271 | 0.7949 | 0.9338 | [0.9285138951582051, 0.5256281586371581] | [0.9775754623882825, 0.6121479072473499] |
|
58 |
+
| 0.0282 | 5.0 | 2285 | 0.1959 | 0.7395 | 0.8653 | 0.9262 | [0.9184942871535651, 0.5605025991065423] | [0.9453582612880436, 0.7853124151415186] |
|
59 |
+
| 0.2816 | 6.0 | 2742 | 0.1763 | 0.7331 | 0.8035 | 0.9347 | [0.9293865372531065, 0.5367951843584413] | [0.9761229104877399, 0.6308764449372819] |
|
60 |
+
| 0.1378 | 7.0 | 3199 | 0.1707 | 0.7495 | 0.8309 | 0.9369 | [0.931185547791987, 0.5677946512496371] | [0.9703251796700836, 0.691472671396249] |
|
61 |
+
| 0.1596 | 8.0 | 3656 | 0.1654 | 0.7511 | 0.8228 | 0.9390 | [0.9337197231959533, 0.5685273561265333] | [0.9757118594786471, 0.6698855265722331] |
|
62 |
+
| 0.0751 | 9.0 | 4113 | 0.1658 | 0.7478 | 0.8151 | 0.9390 | [0.9338284931081033, 0.5617165036252598] | [0.9780982401336578, 0.6520209898525051] |
|
63 |
+
| 0.0682 | 10.0 | 4570 | 0.1675 | 0.7570 | 0.8341 | 0.9396 | [0.9341045714153958, 0.5798374949488075] | [0.9728893841433082, 0.6952250066198535] |
|
64 |
+
|
65 |
+
|
66 |
### Framework versions
|
67 |
|
68 |
- Transformers 4.33.1
|