MultiPRIDE-DualEncoder-LPFT-es

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base-hate-spanish](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-hate-spanish) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5098
-- Accuracy: 0.7273
-- F1: 0.3793
-- Precision: 0.2895
-- Recall: 0.55
+- Loss: 0.5394
+- Accuracy: 0.75
+- F1: 0.3774
+- Precision: 0.3030
+- Recall: 0.5
 
 ## Model description
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
-- seed: 85
+- 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
@@ -55,16 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.632         | 1.0   | 77   | 0.6035          | 0.7121   | 0.1739 | 0.1538    | 0.2    |
-| 0.6212        | 2.0   | 154  | 0.5786          | 0.6061   | 0.3158 | 0.2143    | 0.6    |
-| 0.6248        | 3.0   | 231  | 0.5536          | 0.6742   | 0.3582 | 0.2553    | 0.6    |
-| 0.578         | 4.0   | 308  | 0.5265          | 0.6894   | 0.3692 | 0.2667    | 0.6    |
-| 0.5828        | 5.0   | 385  | 0.5109          | 0.7273   | 0.3793 | 0.2895    | 0.55   |
-| 0.5525        | 6.0   | 462  | 0.5103          | 0.7273   | 0.3793 | 0.2895    | 0.55   |
-| 0.5087        | 7.0   | 539  | 0.5131          | 0.7348   | 0.4068 | 0.3077    | 0.6    |
-| 0.552         | 8.0   | 616  | 0.5097          | 0.7348   | 0.4068 | 0.3077    | 0.6    |
-| 0.4694        | 9.0   | 693  | 0.5092          | 0.7273   | 0.3793 | 0.2895    | 0.55   |
-| 0.5273        | 10.0  | 770  | 0.5098          | 0.7273   | 0.3793 | 0.2895    | 0.55   |
+| 0.6809        | 1.0   | 77   | 0.6348          | 0.8182   | 0.3684 | 0.3889    | 0.35   |
+| 0.6088        | 2.0   | 154  | 0.5859          | 0.7803   | 0.4314 | 0.3548    | 0.55   |
+| 0.6123        | 3.0   | 231  | 0.5598          | 0.7652   | 0.3922 | 0.3226    | 0.5    |
+| 0.5605        | 4.0   | 308  | 0.5490          | 0.75     | 0.3529 | 0.2903    | 0.45   |
+| 0.5316        | 5.0   | 385  | 0.5394          | 0.75     | 0.3774 | 0.3030    | 0.5    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0115b7c0a28d09cc539544186cbddb60aa774c53767674e2b3ab2f36c0c77dce
+oid sha256:08b49b54c53d6a0d560a1a62452d0bf216cddf4145083ff31390ed5cd96fcc9f
 size 1115770572

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa6b188af1f2cfc3182cce1c28b17d4d29dfb623d4d19a3cdded1d46d59b874
+oid sha256:5a63a56ceb63a67d2b321c8bfc4c39cad5415b1892b95f23492c9d5c0012389f
 size 5969