update model card README.md

README.md

@@ -1,4 +1,5 @@
 ---
+license: cc-by-4.0
 tags:
 - generated_from_trainer
 metrics:
@@ -13,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # da-sentiment
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [Maltehb/danish-bert-botxo](https://huggingface.co/Maltehb/danish-bert-botxo) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5176
-- Accuracy: 0.9254
+- Loss: 0.2631
+- Accuracy: 0.9227
 
 ## Model description
 
@@ -41,22 +42,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 46   | 0.4631          | 0.9282   |
-| No log        | 2.0   | 92   | 0.6217          | 0.9227   |
-| No log        | 3.0   | 138  | 0.5297          | 0.9309   |
-| No log        | 4.0   | 184  | 0.5492          | 0.9365   |
-| No log        | 5.0   | 230  | 0.6775          | 0.9061   |
-| No log        | 6.0   | 276  | 0.6767          | 0.9199   |
-| No log        | 7.0   | 322  | 0.5680          | 0.9309   |
-| No log        | 8.0   | 368  | 0.5551          | 0.9309   |
-| No log        | 9.0   | 414  | 0.5094          | 0.9309   |
-| No log        | 10.0  | 460  | 0.5176          | 0.9254   |
+| No log        | 1.0   | 46   | 0.2587          | 0.9088   |
+| No log        | 2.0   | 92   | 0.2468          | 0.9254   |
+| No log        | 3.0   | 138  | 0.2631          | 0.9227   |
 
 
 ### Framework versions