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
445d706
·
verified ·
1 Parent(s): f810279

Model save

Browse files
Files changed (3) hide show
  1. README.md +15 -14
  2. model.safetensors +1 -1
  3. runs/Jan22_20-28-03_696b0f7cfc0e/events.out.tfevents.1769113685.696b0f7cfc0e.18855.0 +2 -2
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
- base_model: google/pix2struct-base
5
  tags:
6
  - generated_from_trainer
7
  model-index:
@@ -14,14 +14,14 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # Pix2StructCzechInvoice
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
 
@@ -40,18 +40,19 @@ More information needed
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
55
  - Pytorch 2.9.0+cu126
56
  - Datasets 4.0.0
57
- - Tokenizers 0.22.1
 
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: google/pix2struct-docvqa-base
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
14
 
15
  # Pix2StructCzechInvoice
16
 
17
+ This model is a fine-tuned version of [google/pix2struct-docvqa-base](https://huggingface.co/google/pix2struct-docvqa-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - eval_loss: 0.2568
20
+ - eval_runtime: 37.2601
21
+ - eval_samples_per_second: 1.61
22
+ - eval_steps_per_second: 1.61
23
+ - epoch: 8.0
24
+ - step: 2400
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 0.0001
44
+ - train_batch_size: 2
45
+ - eval_batch_size: 1
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: cosine_with_restarts
49
+ - lr_scheduler_warmup_ratio: 0.1
50
  - num_epochs: 30
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Framework versions
54
 
55
+ - Transformers 4.57.6
56
  - Pytorch 2.9.0+cu126
57
  - Datasets 4.0.0
58
+ - Tokenizers 0.22.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36aae7f580ad0cf7aa65511acf15b7970a725000ea91cedd9ef3cd3f74471bbb
3
  size 1130333048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3940f7c9aedc1462944844240007f93a9408d44e91b2ad6976f1a90fdd2e7824
3
  size 1130333048
runs/Jan22_20-28-03_696b0f7cfc0e/events.out.tfevents.1769113685.696b0f7cfc0e.18855.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:153f5d323c2749790ae84610e5ba3c49881c7175effbea50cbe170d624f7cfc4
3
- size 58902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bae287fc06d471002e899c25a51e3f91c454f6c580af2fdf01992eac445bd04
3
+ size 59113