Hugging Face's logo

Guspfc
/
git-base-captioning

Text Generation
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Guspfc commited on
Commit
99473a3
•
1 Parent(s): c9646a5

End of training

Browse files
Files changed (3) hide show
  1. README.md +27 -27
  2. model.safetensors +1 -1
  3. runs/Jun20_05-00-43_dab894bb234a/events.out.tfevents.1718859647.dab894bb234a.3323.0 +2 -2
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
 
@@ -52,34 +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
81
 
82
  - Transformers 4.41.2
83
  - Pytorch 2.3.0+cu121
84
- - Datasets 2.19.2
85
  - Tokenizers 0.19.1
 
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: 0.3817
21
+ - Wer Score: 2.8621
22
 
23
  ## Model description
24
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
54
  |:-------------:|:------:|:----:|:---------------:|:---------:|
55
+ | 7.3416 | 0.4202 | 50 | 4.5198 | 4.7633 |
56
+ | 2.4704 | 0.8403 | 100 | 0.7015 | 0.8610 |
57
+ | 0.4735 | 1.2605 | 150 | 0.3923 | 0.8164 |
58
+ | 0.3669 | 1.6807 | 200 | 0.3762 | 0.8198 |
59
+ | 0.3075 | 2.1008 | 250 | 0.3680 | 0.8062 |
60
+ | 0.2837 | 2.5210 | 300 | 0.3683 | 0.8090 |
61
+ | 0.274 | 2.9412 | 350 | 0.3640 | 0.8401 |
62
+ | 0.2393 | 3.3613 | 400 | 0.3692 | 2.8282 |
63
+ | 0.2498 | 3.7815 | 450 | 0.3655 | 2.0712 |
64
+ | 0.2198 | 4.2017 | 500 | 0.3698 | 3.2164 |
65
+ | 0.2034 | 4.6218 | 550 | 0.3688 | 2.5853 |
66
+ | 0.1925 | 5.0420 | 600 | 0.3698 | 2.9119 |
67
+ | 0.1779 | 5.4622 | 650 | 0.3729 | 3.1333 |
68
+ | 0.1734 | 5.8824 | 700 | 0.3727 | 1.7605 |
69
+ | 0.1696 | 6.3025 | 750 | 0.3749 | 3.5226 |
70
+ | 0.15 | 6.7227 | 800 | 0.3773 | 2.8932 |
71
+ | 0.1595 | 7.1429 | 850 | 0.3762 | 2.7842 |
72
+ | 0.1507 | 7.5630 | 900 | 0.3803 | 1.0266 |
73
+ | 0.135 | 7.9832 | 950 | 0.3802 | 3.6090 |
74
+ | 0.1385 | 8.4034 | 1000 | 0.3801 | 3.3169 |
75
+ | 0.1311 | 8.8235 | 1050 | 0.3800 | 3.3966 |
76
+ | 0.1398 | 9.2437 | 1100 | 0.3815 | 2.1915 |
77
+ | 0.1293 | 9.6639 | 1150 | 0.3817 | 2.8621 |
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.41.2
83
  - Pytorch 2.3.0+cu121
84
+ - Datasets 2.20.0
85
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cbc0e4c1d3312b5bf984f525505aa1ba5e4f048b1e93e3c1906382678a4097d
3
  size 706516040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84a2e02076cd6806328c1db1b8994501985cd202a83d7450af01c11d330fe6a1
3
  size 706516040
runs/Jun20_05-00-43_dab894bb234a/events.out.tfevents.1718859647.dab894bb234a.3323.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e65c2353dda29ab7e9a4691f8413dcce5b10efd25cbe24c0a7447abdc8e01a48
3
- size 14648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c821cc782ff4392bcbb11ab78cb939ec8f87994877d5f70aa224c13acd5b25a9
3
+ size 17677