Hugging Face's logo

Guspfc
/
git-base-captioning

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Guspfc commited on
Commit
089e7d2
·
verified ·
1 Parent(s): f5ce4e9

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +31 -26
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: microsoft/git-base
6
  datasets:
7
  - imagefolder
8
  model-index:
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3853
21
- - Wer Score: 0.8299
22
 
23
  ## Model description
24
 
@@ -52,29 +52,34 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
54
  |:-------------:|:------:|:----:|:---------------:|:---------:|
55
- | 1.6087 | 0.4202 | 50 | 0.4992 | 0.8373 |
56
- | 0.435 | 0.8403 | 100 | 0.3918 | 0.8254 |
57
- | 0.3572 | 1.2605 | 150 | 0.3769 | 0.8254 |
58
- | 0.3207 | 1.6807 | 200 | 0.3699 | 0.8130 |
59
- | 0.2761 | 2.1008 | 250 | 0.3683 | 0.8130 |
60
- | 0.2635 | 2.5210 | 300 | 0.3684 | 0.8102 |
61
- | 0.2551 | 2.9412 | 350 | 0.3662 | 0.8350 |
62
- | 0.225 | 3.3613 | 400 | 0.3681 | 0.8113 |
63
- | 0.2364 | 3.7815 | 450 | 0.3683 | 0.8249 |
64
- | 0.2091 | 4.2017 | 500 | 0.3720 | 3.0723 |
65
- | 0.1939 | 4.6218 | 550 | 0.3740 | 0.8215 |
66
- | 0.1839 | 5.0420 | 600 | 0.3723 | 1.8362 |
67
- | 0.1713 | 5.4622 | 650 | 0.3769 | 0.8243 |
68
- | 0.1664 | 5.8824 | 700 | 0.3753 | 0.8209 |
69
- | 0.1634 | 6.3025 | 750 | 0.3786 | 0.8249 |
70
- | 0.1444 | 6.7227 | 800 | 0.3805 | 0.8220 |
71
- | 0.1536 | 7.1429 | 850 | 0.3807 | 0.8322 |
72
- | 0.1469 | 7.5630 | 900 | 0.3832 | 0.8350 |
73
- | 0.1303 | 7.9832 | 950 | 0.3834 | 0.8271 |
74
- | 0.1341 | 8.4034 | 1000 | 0.3841 | 0.8232 |
75
- | 0.1268 | 8.8235 | 1050 | 0.3836 | 0.8277 |
76
- | 0.1348 | 9.2437 | 1100 | 0.3852 | 0.8260 |
77
- | 0.1247 | 9.6639 | 1150 | 0.3853 | 0.8299 |
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: microsoft/git-base
4
  tags:
5
  - generated_from_trainer
 
6
  datasets:
7
  - imagefolder
8
  model-index:
 
17
 
18
  This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3575
21
+ - Wer Score: 0.8322
22
 
23
  ## Model description
24
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
54
  |:-------------:|:------:|:----:|:---------------:|:---------:|
55
+ | 7.8992 | 0.3540 | 20 | 7.5466 | 11.1579 |
56
+ | 5.9879 | 0.7080 | 40 | 5.6121 | 5.1946 |
57
+ | 4.1288 | 1.0619 | 60 | 3.7153 | 4.5433 |
58
+ | 2.3477 | 1.4159 | 80 | 1.9989 | 4.0242 |
59
+ | 1.0242 | 1.7699 | 100 | 0.8650 | 0.8657 |
60
+ | 0.4954 | 2.1239 | 120 | 0.4766 | 0.8676 |
61
+ | 0.3365 | 2.4779 | 140 | 0.3993 | 3.7516 |
62
+ | 0.4286 | 2.8319 | 160 | 0.3773 | 0.8336 |
63
+ | 0.2952 | 3.1858 | 180 | 0.3663 | 0.8329 |
64
+ | 0.3996 | 3.5398 | 200 | 0.3619 | 0.8224 |
65
+ | 0.2629 | 3.8938 | 220 | 0.3574 | 0.8204 |
66
+ | 0.254 | 4.2478 | 240 | 0.3555 | 0.8178 |
67
+ | 0.2642 | 4.6018 | 260 | 0.3557 | 0.8132 |
68
+ | 0.2725 | 4.9558 | 280 | 0.3533 | 0.8139 |
69
+ | 0.2746 | 5.3097 | 300 | 0.3554 | 0.8093 |
70
+ | 0.1765 | 5.6637 | 320 | 0.3561 | 0.8244 |
71
+ | 0.2981 | 6.0177 | 340 | 0.3542 | 0.8375 |
72
+ | 0.1489 | 6.3717 | 360 | 0.3567 | 0.8329 |
73
+ | 0.256 | 6.7257 | 380 | 0.3553 | 0.8362 |
74
+ | 0.1574 | 7.0796 | 400 | 0.3558 | 0.8342 |
75
+ | 0.1836 | 7.4336 | 420 | 0.3566 | 0.8336 |
76
+ | 0.1697 | 7.7876 | 440 | 0.3578 | 0.8362 |
77
+ | 0.1596 | 8.1416 | 460 | 0.3571 | 0.8414 |
78
+ | 0.1628 | 8.4956 | 480 | 0.3579 | 0.8388 |
79
+ | 0.1958 | 8.8496 | 500 | 0.3572 | 0.8362 |
80
+ | 0.1695 | 9.2035 | 520 | 0.3575 | 0.8303 |
81
+ | 0.1686 | 9.5575 | 540 | 0.3576 | 0.8336 |
82
+ | 0.2166 | 9.9115 | 560 | 0.3575 | 0.8322 |
83
 
84
 
85
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d69316145a42f8bee7d7d7dc976444603477744bca1caa12cfaa9f00b574b49e
3
  size 706516040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:400131f1ad7788d557b668003ce0dfa5a14bfe30a9cabaf0eee05e5c5f583844
3
  size 706516040
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37457d6e7212105298eec55c2d1ef69d26195cec88db38cdea83f3e900a5d17a
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67f3e6c95c7ec6551eadf0b3e3d7eab50974c63b2a82f8ce9259820a6fe11af1
3
  size 5112