End of training

README.md

@@ -12,6 +12,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 20231102-20_epochs_layoutlmv2-base-uncased_finetuned_docvqa
 
 This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9087
 
 ## Model description
 
@@ -38,10 +40,17 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 20
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.3689        | 3.51  | 100  | 3.7775          |
+| 3.2761        | 7.02  | 200  | 3.3707          |
+| 2.6415        | 10.53 | 300  | 3.0807          |
+| 2.2233        | 14.04 | 400  | 3.0120          |
+| 1.9586        | 17.54 | 500  | 2.9087          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10cf57f4838f95d9e62bad45e1f2b899c9518fc10163eb901ff4e60d55167428
+oid sha256:03000fb8bd5f821b963c12e75fd46e3c897ebc8a472c1446f3d477ea5e960159
 size 802214001