End of training

README.md

@@ -22,11 +22,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the aisuko/funsd-layoutlmv3 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6357
-- Precision: 0.8356
-- Recall: 0.8838
-- F1: 0.8590
-- Accuracy: 0.8029
+- Loss: 0.5755
+- Precision: 0.8422
+- Recall: 0.8803
+- F1: 0.8608
+- Accuracy: 0.8324
 
 ## Model description
 
@@ -58,8 +58,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 10.0  | 100  | 0.5893          | 0.7972    | 0.8708 | 0.8324 | 0.8104   |
-| No log        | 20.0  | 200  | 0.6357          | 0.8356    | 0.8838 | 0.8590 | 0.8029   |
+| No log        | 10.0  | 100  | 0.6104          | 0.8080    | 0.8614 | 0.8339 | 0.8262   |
+| No log        | 20.0  | 200  | 0.5755          | 0.8422    | 0.8803 | 0.8608 | 0.8324   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0096236abb1bd5b3503bddf86f5a57a1548d6e55d37e29d520ab2cac976f148
+oid sha256:499633461196824f447f7325f82bf41a98451697625ea3f8ab64703eb6439e1c
 size 501355532

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb87cfa40858053cb17d836ca35b98b6f88ff9dec42a54f8cac9833c7f07533e
+oid sha256:8a1c5446e5c3f76121415b884adbaad4b4309a64daadf0bb485526ac8074c0a0
 size 4155