Hugging Face's logo

Ransaka
/
trocr-IAM

Image-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
image-text-to-text
trocr
Inference Endpoints
Model card Files Metrics Community
Ransaka commited on
Commit
a504b3f
·
1 Parent(s): 5c78a1a

End of training

Browse files
Files changed (8) hide show
  1. README.md +6 -8
  2. generation_config.json +6 -2
  3. model.safetensors +1 -1
  4. preprocessor_config.json +22 -0
  5. runs/Dec30_08-56-20_56e0cc75e629/events.out.tfevents.1703926584.56e0cc75e629.172.2 +3 -0
  6. runs/Dec30_09-00-43_56e0cc75e629/events.out.tfevents.1703926844.56e0cc75e629.18680.0 +3 -0
  7. runs/Dec30_09-00-43_56e0cc75e629/events.out.tfevents.1703927003.56e0cc75e629.18680.1 +3 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -14,7 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [microsoft/trocr-small-stage1](https://huggingface.co/microsoft/trocr-small-stage1) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 6.4671
 
18
 
19
  ## Model description
20
 
@@ -39,16 +40,13 @@ The following hyperparameters were used during training:
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - num_epochs: 3.0
43
- - mixed_precision_training: Native AMP
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:----:|:---------------:|
49
- | 7.0232 | 0.79 | 100 | 6.7462 |
50
- | 6.4739 | 1.57 | 200 | 6.5361 |
51
- | 6.2185 | 2.36 | 300 | 6.4671 |
52
 
53
 
54
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [microsoft/trocr-small-stage1](https://huggingface.co/microsoft/trocr-small-stage1) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 6.9227
18
+ - Cer: 0.8191
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: 100
 
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
48
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
49
+ | 7.0738 | 0.79 | 100 | 6.9227 | 0.8191 |
 
 
50
 
51
 
52
  ### Framework versions
generation_config.json CHANGED
@@ -1,8 +1,12 @@
1
  {
2
- "_from_model_config": true,
3
  "bos_token_id": 0,
4
- "decoder_start_token_id": 2,
 
5
  "eos_token_id": 2,
 
 
 
 
6
  "pad_token_id": 1,
7
  "transformers_version": "4.35.2",
8
  "use_cache": false
 
1
  {
 
2
  "bos_token_id": 0,
3
+ "decoder_start_token_id": 0,
4
+ "early_stopping": true,
5
  "eos_token_id": 2,
6
+ "length_penalty": 2.0,
7
+ "max_length": 64,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 4,
10
  "pad_token_id": 1,
11
  "transformers_version": "4.35.2",
12
  "use_cache": false
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:890c2a4b248f2b6bbe6d565247a031f12f56a3828151f3f4e577370769c2af14
3
  size 246430696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4fa644f6b5ad795584c617bdbb348a8aaedcd16fd89465cf8dac887c1c471d1
3
  size 246430696
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 384,
20
+ "width": 384
21
+ }
22
+ }
runs/Dec30_08-56-20_56e0cc75e629/events.out.tfevents.1703926584.56e0cc75e629.172.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9350387c953b13628c1e6dc0ebcc8e11f1ccab1da4270733bb3b781c684a4049
3
+ size 8280
runs/Dec30_09-00-43_56e0cc75e629/events.out.tfevents.1703926844.56e0cc75e629.18680.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931cac44ccbcba667f4a080cf94be9b15c07745dfeeaf385a76ceef0223ec55f
3
+ size 8449
runs/Dec30_09-00-43_56e0cc75e629/events.out.tfevents.1703927003.56e0cc75e629.18680.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d35bfa5c772f2a4aac2ae5ded0130046e37c072d205566ea66c36dfde6fae7c
3
+ size 9417
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3e5e100846fdbca1f4a4860ab47012304311f42a520fd56bb788aaf098ea5ea
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e7729de998ceff24acd971e78c5e1a7129bb20dd9312b1c5860bbc885139ee
3
  size 4728