Hugging Face's logo

channudam
/
khmer-trocr-base-printed

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Model card Files
xet
 Metrics Community
channudam commited on
Commit
84c9184
·
verified ·
1 Parent(s): e1b51f1

End of training

Browse files
Files changed (3) hide show
  1. README.md +11 -11
  2. config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -9,13 +9,13 @@ model-index:
9
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
  should probably proofread and complete it, then remove this comment. -->
11
 
12
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/rayranger/huggingface/runs/aaily8na)
13
  # khmer-trocr-base-printed
14
 
15
  This model was trained from scratch on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.0555
18
- - Cer: 0.5045
19
 
20
  ## Model description
21
 
@@ -47,14 +47,14 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Cer |
49
  |:-------------:|:------:|:----:|:---------------:|:------:|
50
- | 0.118 | 0.4876 | 1000 | 0.0985 | 0.5393 |
51
- | 0.0753 | 0.9751 | 2000 | 0.0915 | 0.5197 |
52
- | 0.0498 | 1.4627 | 3000 | 0.0869 | 0.5152 |
53
- | 0.042 | 1.9503 | 4000 | 0.0711 | 0.4999 |
54
- | 0.0215 | 2.4378 | 5000 | 0.0661 | 0.5244 |
55
- | 0.0236 | 2.9254 | 6000 | 0.0602 | 0.5139 |
56
- | 0.0117 | 3.4130 | 7000 | 0.0589 | 0.4950 |
57
- | 0.0068 | 3.9005 | 8000 | 0.0555 | 0.5045 |
58
 
59
 
60
  ### Framework versions
 
9
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
  should probably proofread and complete it, then remove this comment. -->
11
 
12
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/rayranger/huggingface/runs/hxi1ginr)
13
  # khmer-trocr-base-printed
14
 
15
  This model was trained from scratch on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.0478
18
+ - Cer: 0.4899
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Cer |
49
  |:-------------:|:------:|:----:|:---------------:|:------:|
50
+ | 0.0601 | 0.4876 | 1000 | 0.0793 | 0.5256 |
51
+ | 0.0467 | 0.9751 | 2000 | 0.0706 | 0.5147 |
52
+ | 0.0242 | 1.4627 | 3000 | 0.0658 | 0.5036 |
53
+ | 0.0206 | 1.9503 | 4000 | 0.0587 | 0.5083 |
54
+ | 0.0151 | 2.4378 | 5000 | 0.0610 | 0.5104 |
55
+ | 0.0127 | 2.9254 | 6000 | 0.0521 | 0.4912 |
56
+ | 0.0059 | 3.4130 | 7000 | 0.0497 | 0.4937 |
57
+ | 0.0045 | 3.9005 | 8000 | 0.0478 | 0.4899 |
58
 
59
 
60
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/kaggle/input/khmerocr-trocr-fine-tune-v2/KhmerOCR_TrOCR",
3
  "architectures": [
4
  "VisionEncoderDecoderModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "/kaggle/input/khmerocr-trocr-fine-tune-v3/KhmerOCR_TrOCR",
3
  "architectures": [
4
  "VisionEncoderDecoderModel"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22a31c30292262f0a42ce6024506328c8981e130f1f28ef7a2f22597dc866fcc
3
  size 608335608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8fbbffec880ce1ae3e0646343c7f01ec9ad426681ee9419a99856ac14e0c501
3
  size 608335608