MultiPRIDE-LGBT-Pretrain-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: 1.6267
-- Accuracy: 0.7485
-- F1: 0.7940
-- Precision: 0.79
-- Recall: 0.7980
+- Loss: 0.1484
+- Accuracy: 0.7975
+- F1: 0.8290
+- Precision: 0.8511
+- Recall: 0.8081
 
 ## 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: 67
+- 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
@@ -56,16 +56,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.6477        | 1.0   | 95   | 0.6122          | 0.6135   | 0.5882 | 0.8333    | 0.4545 |
-| 0.5379        | 2.0   | 190  | 0.6109          | 0.7055   | 0.7714 | 0.7297    | 0.8182 |
-| 0.2952        | 3.0   | 285  | 0.7807          | 0.7423   | 0.7812 | 0.8065    | 0.7576 |
-| 0.1565        | 4.0   | 380  | 1.2144          | 0.7178   | 0.7767 | 0.7477    | 0.8081 |
-| 0.1799        | 5.0   | 475  | 1.3530          | 0.7362   | 0.7839 | 0.78      | 0.7879 |
-| 0.0558        | 6.0   | 570  | 1.4303          | 0.7485   | 0.7940 | 0.79      | 0.7980 |
-| 0.0433        | 7.0   | 665  | 1.4569          | 0.7546   | 0.7980 | 0.7980    | 0.7980 |
-| 0.0038        | 8.0   | 760  | 1.5989          | 0.7546   | 0.8058 | 0.7757    | 0.8384 |
-| 0.0009        | 9.0   | 855  | 1.5991          | 0.7485   | 0.7940 | 0.79      | 0.7980 |
-| 0.0007        | 10.0  | 950  | 1.6267          | 0.7485   | 0.7940 | 0.79      | 0.7980 |
+| 0.1493        | 1.0   | 95   | 0.1072          | 0.7607   | 0.7979 | 0.8191    | 0.7778 |
+| 0.0858        | 2.0   | 190  | 0.1384          | 0.8037   | 0.8545 | 0.7769    | 0.9495 |
+| 0.0225        | 3.0   | 285  | 0.1640          | 0.6626   | 0.6497 | 0.8793    | 0.5152 |
+| 0.0067        | 4.0   | 380  | 0.1414          | 0.7546   | 0.7826 | 0.8471    | 0.7273 |
+| 0.0008        | 5.0   | 475  | 0.1484          | 0.7975   | 0.8290 | 0.8511    | 0.8081 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47745788fea51ceb698ed35fc9de3a11a87c10f09711222b074a9d89ec1084b
+oid sha256:f5de899745f31f1b3391a9239a18009f45c72c775d659fbbf9b1c26364bb3444
 size 439740408

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6631e71a494bffeaae7850c87090abd7ec3ef9d2da5150f1c2bdeabaa99bd90
+oid sha256:df521cc5b18fffbbd824646aeeda8bd9786381beb41699dc01279835004e33f7
 size 5969