MultiPRIDE-DualEncoder-MainStage-FT-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: 0.0441
-- Accuracy: 0.9141
-- F1: 0.7667
-- Precision: 0.7931
-- Recall: 0.7419
+- Loss: 0.0101
+- Accuracy: 0.9693
+- F1: 0.9180
+- Precision: 0.9333
+- Recall: 0.9032
 
 ## Model description
 
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 - learning_rate: 5e-06
 - train_batch_size: 8
 - eval_batch_size: 8
-- seed: 150
+- seed: 1337
 - 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
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.0489        | 1.0   | 95   | 0.0488          | 0.9141   | 0.7667 | 0.7931    | 0.7419 |
-| 0.0524        | 2.0   | 190  | 0.0460          | 0.9141   | 0.7667 | 0.7931    | 0.7419 |
-| 0.0517        | 3.0   | 285  | 0.0454          | 0.9141   | 0.7667 | 0.7931    | 0.7419 |
-| 0.0514        | 4.0   | 380  | 0.0441          | 0.9141   | 0.7667 | 0.7931    | 0.7419 |
+| 0.0264        | 1.0   | 95   | 0.0112          | 0.9693   | 0.9180 | 0.9333    | 0.9032 |
+| 0.0283        | 2.0   | 190  | 0.0107          | 0.9693   | 0.9180 | 0.9333    | 0.9032 |
+| 0.0293        | 3.0   | 285  | 0.0104          | 0.9693   | 0.9180 | 0.9333    | 0.9032 |
+| 0.0267        | 4.0   | 380  | 0.0101          | 0.9693   | 0.9180 | 0.9333    | 0.9032 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f83db89dacf847791b186060f24c646a544c659f7010b0a60c29cc5496db6222
+oid sha256:4cbc1f496c6d6ab8d2c7f63afc24969791183cd8e46ab06c7be2f9b86e4f1af7
 size 443306324

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c881ca738b5b4d45f921f07da26881068b85c150a9b3441b31abe8e7ee0220
+oid sha256:fc85d3004ca90d86ccd7877496d2a6d621f9c4257f0e1b0c0026d5b57b102d70
 size 5969