Hugging Face's logo

IshanWarshamana
/
checkpoints

Image-Text-to-Text
Transformers
Safetensors
vision-encoder-decoder
Generated from Trainer
Model card Files
xet
Community
IshanWarshamana commited on
Commit
a65ba0e
·
verified ·
1 Parent(s): 53985fa

End of training

Browse files
Files changed (3) hide show
  1. README.md +15 -10
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -3,19 +3,19 @@ base_model: kavg/TrOCR-SIN-DeiT
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
- - name: TrOCR_Printed_Sinahala
7
  results: []
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
- # TrOCR_Printed_Sinahala
14
 
15
  This model is a fine-tuned version of [kavg/TrOCR-SIN-DeiT](https://huggingface.co/kavg/TrOCR-SIN-DeiT) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.5577
18
- - Cer: 0.1754
19
 
20
  ## Model description
21
 
@@ -40,18 +40,23 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - training_steps: 500
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Cer |
49
  |:-------------:|:------:|:----:|:---------------:|:------:|
50
- | 0.077 | 0.0444 | 100 | 0.7755 | 0.1827 |
51
- | 0.037 | 0.0889 | 200 | 0.6976 | 0.2182 |
52
- | 0.0072 | 0.1333 | 300 | 0.5699 | 0.1786 |
53
- | 0.0014 | 0.1778 | 400 | 0.5577 | 0.1754 |
54
- | 0.0046 | 0.2222 | 500 | 0.5621 | 0.1781 |
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: TrOCR_Printed_Sinahala_1
7
  results: []
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
+ # TrOCR_Printed_Sinahala_1
14
 
15
  This model is a fine-tuned version of [kavg/TrOCR-SIN-DeiT](https://huggingface.co/kavg/TrOCR-SIN-DeiT) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.6949
18
+ - Cer: 0.1689
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - training_steps: 1000
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Cer |
49
  |:-------------:|:------:|:----:|:---------------:|:------:|
50
+ | 0.0989 | 0.0444 | 100 | 1.0041 | 0.1787 |
51
+ | 0.1265 | 0.0889 | 200 | 0.7479 | 0.2270 |
52
+ | 0.0302 | 0.1333 | 300 | 0.9396 | 0.1863 |
53
+ | 0.0483 | 0.1778 | 400 | 0.6949 | 0.1689 |
54
+ | 0.0637 | 0.2222 | 500 | 0.6022 | 0.1816 |
55
+ | 0.0726 | 0.2667 | 600 | 0.6801 | 0.2083 |
56
+ | 0.0169 | 0.3111 | 700 | 0.5828 | 0.1721 |
57
+ | 0.0084 | 0.3556 | 800 | 0.5437 | 0.1750 |
58
+ | 0.0239 | 0.4 | 900 | 0.5451 | 0.1744 |
59
+ | 0.0215 | 0.4444 | 1000 | 0.5470 | 0.1717 |
60
 
61
 
62
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:162a9c2d7665b5eaac145ddb73a7caf986ca86d823e671c4720100088e4c328f
3
  size 963223528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a78e551cfacd8e13f9c046c88f99b630ca87d8550b7b3f6071bad2ba9b599bf
3
  size 963223528
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98bab08bad9ad07e77ee1366821eeff0f09aa2ef6b16d9793910d40715e45a11
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6a25277657e90638a7d54a699d220e1d0905b57f1229c0f94a6e4a23a178bd
3
  size 5304