Hugging Face's logo

ibrahim-601
/
mit-b0-building-damage-lora

Generated from Trainer
Model card Files Community
ibrahim-601 commited on
Commit
cb7e275
•
1 Parent(s): f0c3c70

Training complete with full data.

Browse files
Files changed (2) hide show
  1. README.md +24 -36
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -15,14 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0301
19
- - Mean Iou: 0.3215
20
- - Mean Accuracy: 0.6430
21
- - Overall Accuracy: 0.6430
22
  - Accuracy Background: nan
23
- - Accuracy Building: 0.6430
24
  - Iou Background: 0.0
25
- - Iou Building: 0.6430
26
 
27
  ## Model description
28
 
@@ -47,42 +47,30 @@ The following hyperparameters were used during training:
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
- - num_epochs: 25
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Building | Iou Background | Iou Building |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:-----------------:|:--------------:|:------------:|
56
- | No log | 1.0 | 3 | 0.6395 | 0.4534 | 0.9067 | 0.9067 | nan | 0.9067 | 0.0 | 0.9067 |
57
- | 0.5411 | 2.0 | 6 | 0.5832 | 0.4091 | 0.8183 | 0.8183 | nan | 0.8183 | 0.0 | 0.8183 |
58
- | 0.5411 | 3.0 | 9 | 0.5126 | 0.3802 | 0.7603 | 0.7603 | nan | 0.7603 | 0.0 | 0.7603 |
59
- | 0.3502 | 4.0 | 12 | 0.4467 | 0.3783 | 0.7565 | 0.7565 | nan | 0.7565 | 0.0 | 0.7565 |
60
- | 0.2325 | 5.0 | 15 | 0.3670 | 0.4014 | 0.8028 | 0.8028 | nan | 0.8028 | 0.0 | 0.8028 |
61
- | 0.2325 | 6.0 | 18 | 0.2936 | 0.3618 | 0.7236 | 0.7236 | nan | 0.7236 | 0.0 | 0.7236 |
62
- | 0.1644 | 7.0 | 21 | 0.2271 | 0.2703 | 0.5406 | 0.5406 | nan | 0.5406 | 0.0 | 0.5406 |
63
- | 0.1644 | 8.0 | 24 | 0.1774 | 0.1201 | 0.2402 | 0.2402 | nan | 0.2402 | 0.0 | 0.2402 |
64
- | 0.121 | 9.0 | 27 | 0.1357 | 0.1776 | 0.3551 | 0.3551 | nan | 0.3551 | 0.0 | 0.3551 |
65
- | 0.0847 | 10.0 | 30 | 0.1017 | 0.2561 | 0.5122 | 0.5122 | nan | 0.5122 | 0.0 | 0.5122 |
66
- | 0.0847 | 11.0 | 33 | 0.0774 | 0.2951 | 0.5902 | 0.5902 | nan | 0.5902 | 0.0 | 0.5902 |
67
- | 0.0692 | 12.0 | 36 | 0.0606 | 0.2656 | 0.5313 | 0.5313 | nan | 0.5313 | 0.0 | 0.5313 |
68
- | 0.0692 | 13.0 | 39 | 0.0493 | 0.1601 | 0.3202 | 0.3202 | nan | 0.3202 | 0.0 | 0.3202 |
69
- | 0.0585 | 14.0 | 42 | 0.0418 | 0.1094 | 0.2188 | 0.2188 | nan | 0.2188 | 0.0 | 0.2188 |
70
- | 0.0557 | 15.0 | 45 | 0.0377 | 0.1852 | 0.3703 | 0.3703 | nan | 0.3703 | 0.0 | 0.3703 |
71
- | 0.0557 | 16.0 | 48 | 0.0353 | 0.2437 | 0.4873 | 0.4873 | nan | 0.4873 | 0.0 | 0.4873 |
72
- | 0.0461 | 17.0 | 51 | 0.0335 | 0.2718 | 0.5435 | 0.5435 | nan | 0.5435 | 0.0 | 0.5435 |
73
- | 0.0461 | 18.0 | 54 | 0.0325 | 0.2741 | 0.5482 | 0.5482 | nan | 0.5482 | 0.0 | 0.5482 |
74
- | 0.0445 | 19.0 | 57 | 0.0317 | 0.2846 | 0.5692 | 0.5692 | nan | 0.5692 | 0.0 | 0.5692 |
75
- | 0.0451 | 20.0 | 60 | 0.0310 | 0.2857 | 0.5714 | 0.5714 | nan | 0.5714 | 0.0 | 0.5714 |
76
- | 0.0451 | 21.0 | 63 | 0.0299 | 0.2948 | 0.5897 | 0.5897 | nan | 0.5897 | 0.0 | 0.5897 |
77
- | 0.0469 | 22.0 | 66 | 0.0295 | 0.3020 | 0.6040 | 0.6040 | nan | 0.6040 | 0.0 | 0.6040 |
78
- | 0.0469 | 23.0 | 69 | 0.0296 | 0.3096 | 0.6192 | 0.6192 | nan | 0.6192 | 0.0 | 0.6192 |
79
- | 0.0445 | 24.0 | 72 | 0.0296 | 0.3179 | 0.6359 | 0.6359 | nan | 0.6359 | 0.0 | 0.6359 |
80
- | 0.0417 | 25.0 | 75 | 0.0301 | 0.3215 | 0.6430 | 0.6430 | nan | 0.6430 | 0.0 | 0.6430 |
81
 
82
 
83
  ### Framework versions
84
 
85
- - Transformers 4.35.0
86
- - Pytorch 2.1.0+cu118
87
- - Datasets 2.14.6
88
- - Tokenizers 0.14.1
 
15
 
16
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0719
19
+ - Mean Iou: 0.3422
20
+ - Mean Accuracy: 0.6845
21
+ - Overall Accuracy: 0.6845
22
  - Accuracy Background: nan
23
+ - Accuracy Building: 0.6845
24
  - Iou Background: 0.0
25
+ - Iou Building: 0.6845
26
 
27
  ## Model description
28
 
 
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
+ - num_epochs: 50
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Building | Iou Background | Iou Building |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:-----------------:|:--------------:|:------------:|
56
+ | 0.0816 | 1.0 | 700 | 0.0954 | 0.3942 | 0.7884 | 0.7884 | nan | 0.7884 | 0.0 | 0.7884 |
57
+ | 0.0969 | 2.0 | 1400 | 0.0771 | 0.3662 | 0.7323 | 0.7323 | nan | 0.7323 | 0.0 | 0.7323 |
58
+ | 0.0813 | 3.0 | 2100 | 0.0735 | 0.3608 | 0.7216 | 0.7216 | nan | 0.7216 | 0.0 | 0.7216 |
59
+ | 0.0847 | 4.0 | 2800 | 0.0732 | 0.3557 | 0.7114 | 0.7114 | nan | 0.7114 | 0.0 | 0.7114 |
60
+ | 0.0657 | 5.0 | 3500 | 0.0705 | 0.3352 | 0.6703 | 0.6703 | nan | 0.6703 | 0.0 | 0.6703 |
61
+ | 0.0739 | 6.0 | 4200 | 0.0744 | 0.3606 | 0.7211 | 0.7211 | nan | 0.7211 | 0.0 | 0.7211 |
62
+ | 0.0642 | 7.0 | 4900 | 0.0737 | 0.3754 | 0.7508 | 0.7508 | nan | 0.7508 | 0.0 | 0.7508 |
63
+ | 0.0594 | 8.0 | 5600 | 0.0710 | 0.3128 | 0.6256 | 0.6256 | nan | 0.6256 | 0.0 | 0.6256 |
64
+ | 0.0694 | 9.0 | 6300 | 0.0702 | 0.3431 | 0.6863 | 0.6863 | nan | 0.6863 | 0.0 | 0.6863 |
65
+ | 0.0658 | 10.0 | 7000 | 0.0730 | 0.3666 | 0.7332 | 0.7332 | nan | 0.7332 | 0.0 | 0.7332 |
66
+ | 0.0849 | 11.0 | 7700 | 0.0827 | 0.4007 | 0.8013 | 0.8013 | nan | 0.8013 | 0.0 | 0.8013 |
67
+ | 0.0607 | 12.0 | 8400 | 0.0891 | 0.3844 | 0.7689 | 0.7689 | nan | 0.7689 | 0.0 | 0.7689 |
68
+ | 0.073 | 13.0 | 9100 | 0.1030 | 0.4268 | 0.8536 | 0.8536 | nan | 0.8536 | 0.0 | 0.8536 |
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
72
 
73
+ - Transformers 4.33.0
74
+ - Pytorch 2.0.0
75
+ - Datasets 2.1.0
76
+ - Tokenizers 0.13.3
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1ce195f1afd9a1e30611c0fe59faeeb08ca187b147ccb1f3c3fe5268187bf29
3
  size 2138609
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec0ebd94db9c88769f5952b4cbf7e4ec065e033d6a8adc389dfdf365381c47e
3
  size 2138609