End of training

README.md

@@ -4,7 +4,7 @@ base_model: deepset/gbert-base
 tags:
 - generated_from_trainer
 metrics:
-- accuracy
+- f1
 model-index:
 - name: gbert-base
   results: []
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [deepset/gbert-base](https://huggingface.co/deepset/gbert-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9701
-- Accuracy: 0.8930
+- Loss: 0.6088
+- F1: 0.45
 
 ## Model description
 
@@ -37,20 +37,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 2e-06
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6931        | 1.0   | 216  | 0.6052          | 0.8791   |
-| 0.9373        | 2.0   | 432  | 0.9701          | 0.8930   |
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.691         | 1.0   | 201  | 0.6522          | 0.2069 |
+| 0.6486        | 2.0   | 402  | 0.6236          | 0.3179 |
+| 0.5895        | 3.0   | 603  | 0.5702          | 0.4040 |
+| 0.536         | 4.0   | 804  | 0.5357          | 0.4522 |
+| 0.5063        | 5.0   | 1005 | 0.5914          | 0.4179 |
+| 0.4734        | 6.0   | 1206 | 0.5322          | 0.4792 |
+| 0.4322        | 7.0   | 1407 | 0.5753          | 0.4524 |
+| 0.4368        | 8.0   | 1608 | 0.6255          | 0.4595 |
+| 0.4292        | 9.0   | 1809 | 0.6220          | 0.4737 |
+| 0.4334        | 10.0  | 2010 | 0.6088          | 0.45   |
 
 
 ### Framework versions