MultiPRIDE-DualEncoder-LPFT-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: 0.0258
-- Accuracy: 0.9202
-- F1: 0.8060
-- Precision: 0.75
-- Recall: 0.8710
+- Loss: 0.0666
+- Accuracy: 0.8773
+- F1: 0.6970
+- Precision: 0.6571
+- Recall: 0.7419
 
 ## 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: 85
 - 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
@@ -56,16 +56,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.1876        | 1.0   | 95   | 0.1464          | 0.8037   | 0.3043 | 0.4667    | 0.2258 |
-| 0.1365        | 2.0   | 190  | 0.1072          | 0.8773   | 0.6667 | 0.6897    | 0.6452 |
-| 0.112         | 3.0   | 285  | 0.0677          | 0.8957   | 0.7302 | 0.7188    | 0.7419 |
-| 0.0535        | 4.0   | 380  | 0.0465          | 0.9141   | 0.7742 | 0.7742    | 0.7742 |
-| 0.036         | 5.0   | 475  | 0.0335          | 0.8957   | 0.7385 | 0.7059    | 0.7742 |
-| 0.0322        | 6.0   | 570  | 0.0299          | 0.9141   | 0.7879 | 0.7429    | 0.8387 |
-| 0.0239        | 7.0   | 665  | 0.0274          | 0.9202   | 0.8060 | 0.75      | 0.8710 |
-| 0.0275        | 8.0   | 760  | 0.0263          | 0.9202   | 0.8060 | 0.75      | 0.8710 |
-| 0.0289        | 9.0   | 855  | 0.0259          | 0.9202   | 0.8060 | 0.75      | 0.8710 |
-| 0.0206        | 10.0  | 950  | 0.0258          | 0.9202   | 0.8060 | 0.75      | 0.8710 |
+| 0.1757        | 1.0   | 95   | 0.1019          | 0.8160   | 0.6154 | 0.5106    | 0.7742 |
+| 0.0839        | 2.0   | 190  | 0.0634          | 0.8896   | 0.7097 | 0.7097    | 0.7097 |
+| 0.0433        | 3.0   | 285  | 0.0606          | 0.8650   | 0.6667 | 0.6286    | 0.7097 |
+| 0.0284        | 4.0   | 380  | 0.0659          | 0.8650   | 0.6765 | 0.6216    | 0.7419 |
+| 0.0237        | 5.0   | 475  | 0.0666          | 0.8773   | 0.6970 | 0.6571    | 0.7419 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6ae44e96c27fb3e0cfebb87ea640b968661c726f7a3676d5b0db410a4bbfcd
+oid sha256:368a7060eb2734a3002384163fa1543f4b5a601c3066359f79cd91c3ea39e139
 size 443306324

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18f333459043645aa8879f45aef0eadf91e82cd2a6e431bad0fc2ecd578220f
+oid sha256:29e9b72d2bc94c3201dc981a24d317f970d6af186733170f9e9546dfba89c9c5
 size 5969