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: 0.4806
-- Accuracy: 0.8106
-- F1: 0.5283
-- Precision: 0.4242
-- Recall: 0.7
+- Loss: 0.5115
+- Accuracy: 0.7348
+- F1: 0.4068
+- Precision: 0.3077
+- 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: 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
@@ -55,10 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.4405        | 1.0   | 77   | 0.4808          | 0.8182   | 0.5385 | 0.4375    | 0.7    |
-| 0.4677        | 2.0   | 154  | 0.4808          | 0.8182   | 0.5385 | 0.4375    | 0.7    |
-| 0.4375        | 3.0   | 231  | 0.4817          | 0.8106   | 0.5283 | 0.4242    | 0.7    |
-| 0.4286        | 4.0   | 308  | 0.4806          | 0.8106   | 0.5283 | 0.4242    | 0.7    |
+| 0.5218        | 1.0   | 77   | 0.5179          | 0.7348   | 0.3860 | 0.2973    | 0.55   |
+| 0.5382        | 2.0   | 154  | 0.5137          | 0.7348   | 0.4068 | 0.3077    | 0.6    |
+| 0.5355        | 3.0   | 231  | 0.5134          | 0.7348   | 0.4068 | 0.3077    | 0.6    |
+| 0.502         | 4.0   | 308  | 0.5140          | 0.7348   | 0.4068 | 0.3077    | 0.6    |
+| 0.5578        | 5.0   | 385  | 0.5115          | 0.7348   | 0.4068 | 0.3077    | 0.6    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0483cc3a491e9f623d0b6896b60f29ac5fd4c66a2a892506b4c771caef72c9e5
+oid sha256:fc830b1ade768733268a8faf47dceaff1c144630ec349c71aea930c8f939f4ea
 size 1115770572

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:535ca3d9dccb95ce810e7313b7a0280bddc308af87ad075da47cc52310609302
+oid sha256:fafa639082722a05dd6fe34e1cbbf28d3aa45cdab88d6e623919d8f7aaf22b8f
 size 5969