Model save

README.md

@@ -1,9 +1,14 @@
 ---
 library_name: transformers
 license: cc-by-nc-sa-4.0
-base_model: microsoft/layoutlmv3-base
+base_model: TomasFAV/Layoutlmv3InvoiceCzech
 tags:
 - generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
 - name: Layoutlmv3InvoiceCzechV1
   results: []
@@ -14,18 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Layoutlmv3InvoiceCzechV1
 
-This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
+This model is a fine-tuned version of [TomasFAV/Layoutlmv3InvoiceCzech](https://huggingface.co/TomasFAV/Layoutlmv3InvoiceCzech) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0068
-- eval_precision: 0.9830
-- eval_recall: 0.9812
-- eval_f1: 0.9821
-- eval_accuracy: 0.9984
-- eval_runtime: 14.5203
-- eval_samples_per_second: 8.264
-- eval_steps_per_second: 4.132
-- epoch: 14.0
-- step: 2800
+- Loss: 0.1399
+- Precision: 0.6051
+- Recall: 0.7254
+- F1: 0.6598
+- Accuracy: 0.9733
 
 ## Model description
 
@@ -46,17 +46,33 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 8
-- eval_batch_size: 2
+- eval_batch_size: 1
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 0.1
-- num_epochs: 20
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 75   | 0.1398          | 0.6034    | 0.7234 | 0.6580 | 0.9732   |
+| No log        | 2.0   | 150  | 0.1498          | 0.5218    | 0.6865 | 0.5929 | 0.9675   |
+| No log        | 3.0   | 225  | 0.1696          | 0.5413    | 0.6988 | 0.6100 | 0.9689   |
+| No log        | 4.0   | 300  | 0.1593          | 0.5889    | 0.6721 | 0.6278 | 0.9721   |
+| No log        | 5.0   | 375  | 0.1561          | 0.5875    | 0.6947 | 0.6366 | 0.9723   |
+| No log        | 6.0   | 450  | 0.1779          | 0.5474    | 0.6742 | 0.6042 | 0.9692   |
+| 0.0196        | 7.0   | 525  | 0.1719          | 0.5533    | 0.6598 | 0.6019 | 0.9697   |
+| 0.0196        | 8.0   | 600  | 0.1769          | 0.5267    | 0.6680 | 0.5890 | 0.9681   |
+| 0.0196        | 9.0   | 675  | 0.1778          | 0.5336    | 0.6680 | 0.5933 | 0.9687   |
+| 0.0196        | 10.0  | 750  | 0.1789          | 0.5413    | 0.6721 | 0.5996 | 0.9692   |
+
+
 ### Framework versions
 
 - Transformers 5.0.0
-- Pytorch 2.9.0+cu128
+- Pytorch 2.10.0+cu128
 - Datasets 4.0.0
 - Tokenizers 0.22.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d6a7e64402bae51bafb3e2c883fc43fdf59ce38c51c399538979f856b72ea1a
+oid sha256:459772da0f693976bcacedde10ce271208271daf146aea056b5b67062fc464a4
 size 503791932

runs/Mar07_21-45-09_6474a9255a7e/events.out.tfevents.1772920788.6474a9255a7e.9953.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f9dc5b71803cb2668410a910c49c3a3dab0f2fed91844e43f40c1bb4595e4b
+size 560