End of training

README.md

@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [AI-Sweden-Models/gpt-sw3-1.3b](https://huggingface.co/AI-Sweden-Models/gpt-sw3-1.3b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0017
-- Accuracy: 1.0
+- Loss: 0.0078
+- Accuracy: 0.9966
 
 ## Model description
 
@@ -48,16 +48,18 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.1303        | 0.41  | 50   | 0.1400          | 0.9697   |
-| 0.0606        | 0.83  | 100  | 0.0171          | 0.9865   |
-| 0.0005        | 1.24  | 150  | 0.0036          | 1.0      |
-| 0.0           | 1.65  | 200  | 0.0017          | 1.0      |
+| 0.3164        | 0.17  | 20   | 0.2708          | 0.9461   |
+| 0.1799        | 0.33  | 40   | 0.1111          | 0.9697   |
+| 0.0577        | 0.5   | 60   | 0.0276          | 0.9899   |
+| 0.0064        | 0.66  | 80   | 0.0119          | 0.9933   |
+| 0.0036        | 0.83  | 100  | 0.0099          | 0.9933   |
+| 0.0035        | 0.99  | 120  | 0.0078          | 0.9966   |
 
 
 ### Framework versions