anger_frustration_detection_5.2

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [procit011/anger_frustration_detection_2](https://huggingface.co/procit011/anger_frustration_detection_2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0800
-- F1: 0.9887
-- Accuracy: 0.9892
+- Loss: 0.0457
+- F1: 0.9937
+- Accuracy: 0.9940
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
-| 0.0540        | 1.0   | 830  | 0.0693          | 0.9785 | 0.9795   |
-| 0.0271        | 2.0   | 1660 | 0.0783          | 0.9873 | 0.9880   |
-| 0.0001        | 3.0   | 2490 | 0.0809          | 0.9886 | 0.9892   |
+| 0.0822        | 1.0   | 829  | 0.0489          | 0.9911 | 0.9915   |
+| 0.0011        | 2.0   | 1658 | 0.0219          | 0.9962 | 0.9964   |
+| 0.0263        | 3.0   | 2487 | 0.0425          | 0.9949 | 0.9952   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:713a66c7d194832d772264d5f74baacdbdbf17b5abe82c75cf892919eae1eb07
+oid sha256:eb6e35c44dc705c9c4c1693392437267313469509fd94cb8ddea30ff2a7767e7
 size 467078720