MultiPRIDE-DualEncoder-MainStage-it

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nickprock/setfit-italian-hate-speech](https://huggingface.co/nickprock/setfit-italian-hate-speech) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2481
-- Accuracy: 0.9571
-- F1: 0.8772
-- Precision: 0.9615
-- Recall: 0.8065
+- Loss: 0.3345
+- Accuracy: 0.9141
+- F1: 0.7407
+- Precision: 0.8696
+- Recall: 0.6452
 
 ## Model description
 
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
-- seed: 42
+- seed: 150
 - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 10
@@ -56,14 +56,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.703         | 1.0   | 95   | 0.5968          | 0.8466   | 0.3590 | 0.875     | 0.2258 |
-| 0.5651        | 2.0   | 190  | 0.4460          | 0.9018   | 0.7333 | 0.7586    | 0.7097 |
-| 0.4051        | 3.0   | 285  | 0.2983          | 0.9202   | 0.7869 | 0.8       | 0.7742 |
-| 0.2546        | 4.0   | 380  | 0.2531          | 0.9448   | 0.8475 | 0.8929    | 0.8065 |
-| 0.2111        | 5.0   | 475  | 0.2445          | 0.9571   | 0.8772 | 0.9615    | 0.8065 |
-| 0.2201        | 6.0   | 570  | 0.2539          | 0.9509   | 0.8571 | 0.96      | 0.7742 |
-| 0.2024        | 7.0   | 665  | 0.2577          | 0.9509   | 0.8571 | 0.96      | 0.7742 |
-| 0.2162        | 8.0   | 760  | 0.2481          | 0.9571   | 0.8772 | 0.9615    | 0.8065 |
+| 0.7188        | 1.0   | 95   | 0.5881          | 0.8405   | 0.4091 | 0.6923    | 0.2903 |
+| 0.5805        | 2.0   | 190  | 0.4346          | 0.8896   | 0.6667 | 0.7826    | 0.5806 |
+| 0.4433        | 3.0   | 285  | 0.3493          | 0.9141   | 0.7586 | 0.8148    | 0.7097 |
+| 0.3152        | 4.0   | 380  | 0.3066          | 0.9202   | 0.7797 | 0.8214    | 0.7419 |
+| 0.2758        | 5.0   | 475  | 0.3260          | 0.9080   | 0.7170 | 0.8636    | 0.6129 |
+| 0.2529        | 6.0   | 570  | 0.3228          | 0.9080   | 0.7273 | 0.8333    | 0.6452 |
+| 0.157         | 7.0   | 665  | 0.3345          | 0.9141   | 0.7407 | 0.8696    | 0.6452 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:116bd2ab8ec6a70884c00d4f6479e764abe0a4c1aad4dcdd0edab0b50a43a691
+oid sha256:2fcd443b875f7ed98fb3f511f70d58feb54c707a914fe19dfd5e0299b3a22646
 size 443306324

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a5fa00a910d91b18f801ab7801bbe644bd6cb5d1082ef69bb8c4c044a801b4
+oid sha256:acb67de67b6b83246de4618464653c099bd4268fdf962435c23a8e9fb63f387d
 size 5969