MultiPRIDE-DualEncoder-MainStage-FT-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: 0.5701
-- Accuracy: 0.7803
-- F1: 0.4314
-- Precision: 0.3548
-- Recall: 0.55
+- Loss: 0.6211
+- Accuracy: 0.8106
+- F1: 0.4898
+- Precision: 0.4138
+- Recall: 0.6
 
 ## Model description
 
@@ -46,7 +46,7 @@ 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
@@ -55,10 +55,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.5645        | 1.0   | 77   | 0.5790          | 0.7803   | 0.4314 | 0.3548    | 0.55   |
-| 0.5474        | 2.0   | 154  | 0.5752          | 0.7803   | 0.4314 | 0.3548    | 0.55   |
-| 0.6037        | 3.0   | 231  | 0.5726          | 0.7803   | 0.4314 | 0.3548    | 0.55   |
-| 0.5785        | 4.0   | 308  | 0.5701          | 0.7803   | 0.4314 | 0.3548    | 0.55   |
+| 0.4493        | 1.0   | 77   | 0.6169          | 0.8106   | 0.4898 | 0.4138    | 0.6    |
+| 0.4307        | 2.0   | 154  | 0.6172          | 0.8030   | 0.48   | 0.4       | 0.6    |
+| 0.4653        | 3.0   | 231  | 0.6220          | 0.8106   | 0.4898 | 0.4138    | 0.6    |
+| 0.4674        | 4.0   | 308  | 0.6211          | 0.8106   | 0.4898 | 0.4138    | 0.6    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:860586376620d8087feea7dafad60438163c5e0124e7e394a287103b854f959c
+oid sha256:95a22746537c1dbf46c996c69bffaf4cfe11a4398997ae28c192a880e03ae344
 size 1115770572

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9782a98451a9bda9be2aa0ca5df1823dbd8a6d354fb352f002d6b39685342a2
+oid sha256:2c912a3900b53f07596d4de82c64217eaa7be48fc257266cb677b2507b28e7bc
 size 5969