Hugging Face's logo

SOSI1004
/
blip-image-captioning-base-kag100

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
blip
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
SOSI1004 commited on
Commit
bcba2d2
•
1 Parent(s): 777b600

End of training

Browse files
Files changed (4) hide show
  1. README.md +13 -13
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/May13_05-58-12_1ab2edd1f5ff/events.out.tfevents.1715579893.1ab2edd1f5ff.15036.0 +2 -2
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1348
19
- - Wer Score: 0.6810
20
 
21
  ## Model description
22
 
@@ -47,21 +47,21 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
49
  |:-------------:|:------:|:----:|:---------------:|:---------:|
50
- | 0.8536 | 0.9259 | 500 | 0.1085 | 0.6764 |
51
- | 0.0769 | 1.8519 | 1000 | 0.1131 | 0.6641 |
52
- | 0.0536 | 2.7778 | 1500 | 0.1201 | 0.6949 |
53
- | 0.0384 | 3.7037 | 2000 | 0.1268 | 0.6687 |
54
- | 0.0265 | 4.6296 | 2500 | 0.1289 | 0.6934 |
55
- | 0.0194 | 5.5556 | 3000 | 0.1319 | 0.6810 |
56
- | 0.0161 | 6.4815 | 3500 | 0.1332 | 0.6749 |
57
- | 0.0139 | 7.4074 | 4000 | 0.1342 | 0.6656 |
58
- | 0.0124 | 8.3333 | 4500 | 0.1352 | 0.6795 |
59
- | 0.0108 | 9.2593 | 5000 | 0.1348 | 0.6810 |
60
 
61
 
62
  ### Framework versions
63
 
64
- - Transformers 4.40.1
65
  - Pytorch 2.2.1+cu121
66
  - Datasets 2.19.1
67
  - Tokenizers 0.19.1
 
15
 
16
  This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1444
19
+ - Wer Score: 0.7172
20
 
21
  ## Model description
22
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
49
  |:-------------:|:------:|:----:|:---------------:|:---------:|
50
+ | 0.8613 | 0.9259 | 500 | 0.1123 | 0.7625 |
51
+ | 0.079 | 1.8519 | 1000 | 0.1131 | 0.7234 |
52
+ | 0.055 | 2.7778 | 1500 | 0.1228 | 0.7312 |
53
+ | 0.0389 | 3.7037 | 2000 | 0.1313 | 0.7531 |
54
+ | 0.0277 | 4.6296 | 2500 | 0.1360 | 0.7469 |
55
+ | 0.0205 | 5.5556 | 3000 | 0.1367 | 0.7188 |
56
+ | 0.0167 | 6.4815 | 3500 | 0.1410 | 0.7188 |
57
+ | 0.0154 | 7.4074 | 4000 | 0.1405 | 0.7188 |
58
+ | 0.0145 | 8.3333 | 4500 | 0.1435 | 0.7172 |
59
+ | 0.0137 | 9.2593 | 5000 | 0.1444 | 0.7172 |
60
 
61
 
62
  ### Framework versions
63
 
64
+ - Transformers 4.40.2
65
  - Pytorch 2.2.1+cu121
66
  - Datasets 2.19.1
67
  - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 30522,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.40.1"
7
  }
 
3
  "bos_token_id": 30522,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.40.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1978409b1b8011bb2346b43355899238f4048d7ad389f65126091111bc32744
3
  size 989717056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e91c3788648be248dd57f3b1b7b3a2192af4435a02a893584061a727af7ae1
3
  size 989717056
runs/May13_05-58-12_1ab2edd1f5ff/events.out.tfevents.1715579893.1ab2edd1f5ff.15036.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5d0f689178f94ebbcb04ca4ec211c33816c3c8a0ff1efafa61c1a160d355a60
3
- size 10123
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77527c8b09e2386f2bc9fc5d2067fe408c440c4a8691c96a0080ce34e07d2bbb
3
+ size 10477