Hugging Face's logo

TomasFAV
/
Pix2StructCzechInvoice

Image-to-Text
Transformers
TensorBoard
Safetensors
pix2struct
Generated from Trainer
Model card Files
xet
Metrics Community
TomasFAV commited on
Commit
0aeb95a
·
verified ·
1 Parent(s): 8cf6a6d

Model save

Browse files
Files changed (3) hide show
  1. README.md +8 -19
  2. model.safetensors +1 -1
  3. runs/Dec30_11-36-31_46327ada4835/events.out.tfevents.1767094593.46327ada4835.830.0 +2 -2
README.md CHANGED
@@ -16,7 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [google/pix2struct-base](https://huggingface.co/google/pix2struct-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 3.7261
 
 
 
 
 
20
 
21
  ## Model description
22
 
@@ -35,31 +40,15 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 2e-05
39
  - train_batch_size: 5
40
  - eval_batch_size: 2
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - num_epochs: 10
45
  - mixed_precision_training: Native AMP
46
 
47
- ### Training results
48
-
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:----:|:---------------:|
51
- | 5.3299 | 1.0 | 120 | 4.7058 |
52
- | 4.8648 | 2.0 | 240 | 4.3492 |
53
- | 4.5915 | 3.0 | 360 | 4.1408 |
54
- | 4.4154 | 4.0 | 480 | 4.0675 |
55
- | 4.5372 | 5.0 | 600 | 3.9205 |
56
- | 4.2502 | 6.0 | 720 | 3.8549 |
57
- | 4.1316 | 7.0 | 840 | 3.8064 |
58
- | 4.2207 | 8.0 | 960 | 3.7545 |
59
- | 4.1466 | 9.0 | 1080 | 3.7284 |
60
- | 4.1133 | 10.0 | 1200 | 3.7261 |
61
-
62
-
63
  ### Framework versions
64
 
65
  - Transformers 4.57.3
 
16
 
17
  This model is a fine-tuned version of [google/pix2struct-base](https://huggingface.co/google/pix2struct-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - eval_loss: 1.0570
20
+ - eval_runtime: 14.5659
21
+ - eval_samples_per_second: 4.119
22
+ - eval_steps_per_second: 2.06
23
+ - epoch: 24.0
24
+ - step: 2880
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 6e-05
44
  - train_batch_size: 5
45
  - eval_batch_size: 2
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 30
50
  - mixed_precision_training: Native AMP
51
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  ### Framework versions
53
 
54
  - Transformers 4.57.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bc5a61e3ffce24422af6015c01ebcbab6f6dd1f229117a22722ad7dc3f8939d
3
  size 1130333048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25c0f3781bea022d4440f3bda9bdbcf4204e424a476f34b20d1fe61d3a189bf
3
  size 1130333048
runs/Dec30_11-36-31_46327ada4835/events.out.tfevents.1767094593.46327ada4835.830.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2422bb6da5b66f7cf00558f6aef6e3af266ccb2722531fc07005b3790e74dfd6
3
- size 36920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b932416717096c0b3a09ffc7210ab44687a79149fda07be023e392dfec63566
3
+ size 37553