MultiPRIDE-DualEncoder-MainStage-es

README.md

@@ -20,10 +20,10 @@ 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: 0.4609
-- Accuracy: 0.8409
-- F1: 0.5532
-- Precision: 0.4815
+- Loss: 0.4885
+- Accuracy: 0.7879
+- F1: 0.4815
+- Precision: 0.3824
 - Recall: 0.65
 
 ## 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: 67
+- 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
@@ -55,14 +55,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.6799        | 1.0   | 77   | 0.6352          | 0.7879   | 0.3636 | 0.3333    | 0.4    |
-| 0.5849        | 2.0   | 154  | 0.5760          | 0.8258   | 0.3784 | 0.4118    | 0.35   |
-| 0.5354        | 3.0   | 231  | 0.5289          | 0.8106   | 0.5098 | 0.4194    | 0.65   |
-| 0.4986        | 4.0   | 308  | 0.4998          | 0.7879   | 0.5333 | 0.4       | 0.8    |
-| 0.4482        | 5.0   | 385  | 0.4677          | 0.8333   | 0.56   | 0.4667    | 0.7    |
-| 0.4401        | 6.0   | 462  | 0.4600          | 0.8333   | 0.5417 | 0.4643    | 0.65   |
-| 0.406         | 7.0   | 539  | 0.4643          | 0.8333   | 0.56   | 0.4667    | 0.7    |
-| 0.4508        | 8.0   | 616  | 0.4609          | 0.8409   | 0.5532 | 0.4815    | 0.65   |
+| 0.6454        | 1.0   | 77   | 0.5901          | 0.8258   | 0.2069 | 0.3333    | 0.15   |
+| 0.5871        | 2.0   | 154  | 0.5312          | 0.7803   | 0.4082 | 0.3448    | 0.5    |
+| 0.5791        | 3.0   | 231  | 0.5059          | 0.7576   | 0.4286 | 0.3333    | 0.6    |
+| 0.5135        | 4.0   | 308  | 0.4918          | 0.7803   | 0.4727 | 0.3714    | 0.65   |
+| 0.5143        | 5.0   | 385  | 0.4827          | 0.7803   | 0.4727 | 0.3714    | 0.65   |
+| 0.4846        | 6.0   | 462  | 0.4831          | 0.7879   | 0.4815 | 0.3824    | 0.65   |
+| 0.4515        | 7.0   | 539  | 0.4891          | 0.7803   | 0.4727 | 0.3714    | 0.65   |
+| 0.4799        | 8.0   | 616  | 0.4854          | 0.7803   | 0.4727 | 0.3714    | 0.65   |
+| 0.4209        | 9.0   | 693  | 0.4885          | 0.7879   | 0.4815 | 0.3824    | 0.65   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962c51159f23be8b71a35999b2cc72c191400d6477060fe3bf9d5f0242bc8d1c
+oid sha256:95754edc9b345fcc49a854fae447403326d4b5db03705ce9529a8b002926d8d9
 size 1115770572

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6bae610ef8f01a1c468077975be8a042c2da63cf5226dab1a21efff92f3d350
+oid sha256:9815ff095e09ba7e4c8f9964aee8a0abc1d59b8f3faa03571cbc63af5d1d2b7e
 size 5969