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: 0.0318
-- Accuracy: 0.9571
-- F1: 0.8923
-- Precision: 0.8529
-- Recall: 0.9355
+- Loss: 0.1613
+- Accuracy: 0.4908
+- F1: 0.3759
+- Precision: 0.2451
+- Recall: 0.8065
 
 ## 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: 67
+- seed: 68
 - 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
@@ -56,15 +56,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.048         | 1.0   | 95   | 0.0374          | 0.9509   | 0.875  | 0.8485    | 0.9032 |
-| 0.0457        | 2.0   | 190  | 0.0358          | 0.9509   | 0.875  | 0.8485    | 0.9032 |
-| 0.039         | 3.0   | 285  | 0.0345          | 0.9571   | 0.8889 | 0.875     | 0.9032 |
-| 0.0466        | 4.0   | 380  | 0.0334          | 0.9571   | 0.8889 | 0.875     | 0.9032 |
-| 0.0478        | 5.0   | 475  | 0.0325          | 0.9509   | 0.875  | 0.8485    | 0.9032 |
-| 0.0409        | 6.0   | 570  | 0.0323          | 0.9632   | 0.9062 | 0.8788    | 0.9355 |
-| 0.0428        | 7.0   | 665  | 0.0320          | 0.9571   | 0.8923 | 0.8529    | 0.9355 |
-| 0.0402        | 8.0   | 760  | 0.0319          | 0.9571   | 0.8923 | 0.8529    | 0.9355 |
-| 0.0377        | 9.0   | 855  | 0.0318          | 0.9571   | 0.8923 | 0.8529    | 0.9355 |
+| 0.1903        | 1.0   | 95   | 0.1781          | 0.2209   | 0.2983 | 0.18      | 0.8710 |
+| 0.173         | 2.0   | 190  | 0.1702          | 0.3190   | 0.3273 | 0.2015    | 0.8710 |
+| 0.1685        | 3.0   | 285  | 0.1666          | 0.3742   | 0.3462 | 0.216     | 0.8710 |
+| 0.173         | 4.0   | 380  | 0.1650          | 0.3988   | 0.3467 | 0.2185    | 0.8387 |
+| 0.1661        | 5.0   | 475  | 0.1631          | 0.4417   | 0.3636 | 0.2321    | 0.8387 |
+| 0.1655        | 6.0   | 570  | 0.1622          | 0.4847   | 0.3731 | 0.2427    | 0.8065 |
+| 0.163         | 7.0   | 665  | 0.1617          | 0.4908   | 0.3759 | 0.2451    | 0.8065 |
+| 0.1644        | 8.0   | 760  | 0.1617          | 0.4908   | 0.3759 | 0.2451    | 0.8065 |
+| 0.1641        | 9.0   | 855  | 0.1616          | 0.4908   | 0.3759 | 0.2451    | 0.8065 |
+| 0.1615        | 10.0  | 950  | 0.1613          | 0.4908   | 0.3759 | 0.2451    | 0.8065 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7b3f79abb73e0cfa49c6a178d4d29d625da1ae651ac07897cfe97052c0d1e9
+oid sha256:1fda60fb3a1241d5ca4ae0cae3b29137380d78aac18de4af9c475306dd74057b
 size 443306324

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7d08891e73e4326a48a2b97f462627e4f8babd28619740ac6a6660dec6a3a5
+oid sha256:1f5810d342a0cba63cde62ee2cfa8f480393664ef1fd4e1e28674a302d50140f
 size 5969