MultiPRIDE-DualEncoder-MainStage-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: 0.5555
-- Accuracy: 0.7727
-- F1: 0.375
-- Precision: 0.3214
-- Recall: 0.45
+- Loss: 0.5697
+- Accuracy: 0.8030
+- F1: 0.48
+- Precision: 0.4
+- Recall: 0.6
 
 ## 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: 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
@@ -55,11 +55,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.667         | 1.0   | 77   | 0.6045          | 0.8106   | 0.3902 | 0.3810    | 0.4    |
-| 0.5669        | 2.0   | 154  | 0.5563          | 0.7652   | 0.3922 | 0.3226    | 0.5    |
-| 0.5689        | 3.0   | 231  | 0.5566          | 0.75     | 0.2979 | 0.2593    | 0.35   |
-| 0.5191        | 4.0   | 308  | 0.5523          | 0.7652   | 0.3673 | 0.3103    | 0.45   |
-| 0.4852        | 5.0   | 385  | 0.5555          | 0.7727   | 0.375  | 0.3214    | 0.45   |
+| 0.6627        | 1.0   | 77   | 0.6301          | 0.7879   | 0.3    | 0.3       | 0.3    |
+| 0.5988        | 2.0   | 154  | 0.6037          | 0.7424   | 0.2609 | 0.2308    | 0.3    |
+| 0.5895        | 3.0   | 231  | 0.5760          | 0.7879   | 0.3333 | 0.3182    | 0.35   |
+| 0.5471        | 4.0   | 308  | 0.5450          | 0.7879   | 0.4615 | 0.375     | 0.6    |
+| 0.4608        | 5.0   | 385  | 0.5414          | 0.7727   | 0.4444 | 0.3529    | 0.6    |
+| 0.4488        | 6.0   | 462  | 0.5611          | 0.8030   | 0.48   | 0.4       | 0.6    |
+| 0.4577        | 7.0   | 539  | 0.5658          | 0.8106   | 0.4898 | 0.4138    | 0.6    |
+| 0.4569        | 8.0   | 616  | 0.5713          | 0.8182   | 0.5    | 0.4286    | 0.6    |
+| 0.4127        | 9.0   | 693  | 0.5705          | 0.8030   | 0.48   | 0.4       | 0.6    |
+| 0.4133        | 10.0  | 770  | 0.5697          | 0.8030   | 0.48   | 0.4       | 0.6    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c057d1f9e76f10bd86e6ea7e636ef7cfda13e40e79ab4af48e752d324dce45
+oid sha256:80655ee1dd0833eaf2b1c1a25fa47403276afd8ce723a63f2f362340bd51cd65
 size 1115770572

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c49f4ddda4717cdd1171a33b7b8db280ea6a1c75c539bd1ebd7e5206614617f
+oid sha256:d085c63617f93ca30f2304c5140ac3e3ce3c085ec347fc1daf7d493cf640ad37
 size 5969