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: 0.4688
-- Accuracy: 0.8030
-- F1: 0.5667
-- Precision: 0.425
-- Recall: 0.85
+- Loss: 0.4830
+- Accuracy: 0.8106
+- F1: 0.5283
+- Precision: 0.4242
+- Recall: 0.7
 
 ## 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: 42
+- seed: 67
 - 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
@@ -55,13 +55,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.6778        | 1.0   | 77   | 0.5634          | 0.8030   | 0.5    | 0.4062    | 0.65   |
-| 0.6517        | 2.0   | 154  | 0.5011          | 0.7273   | 0.4706 | 0.3333    | 0.8    |
-| 0.6283        | 3.0   | 231  | 0.5121          | 0.7727   | 0.5312 | 0.3864    | 0.85   |
-| 0.6041        | 4.0   | 308  | 0.4802          | 0.8182   | 0.5862 | 0.4474    | 0.85   |
-| 0.6153        | 5.0   | 385  | 0.4840          | 0.7879   | 0.5484 | 0.4048    | 0.85   |
-| 0.5638        | 6.0   | 462  | 0.4761          | 0.7803   | 0.5397 | 0.3953    | 0.85   |
-| 0.5421        | 7.0   | 539  | 0.4688          | 0.8030   | 0.5667 | 0.425     | 0.85   |
+| 0.7105        | 1.0   | 77   | 0.6802          | 0.5076   | 0.3299 | 0.2078    | 0.8    |
+| 0.6108        | 2.0   | 154  | 0.5709          | 0.7803   | 0.4314 | 0.3548    | 0.55   |
+| 0.552         | 3.0   | 231  | 0.5332          | 0.7955   | 0.5091 | 0.4       | 0.7    |
+| 0.4916        | 4.0   | 308  | 0.5091          | 0.7803   | 0.4912 | 0.3784    | 0.7    |
+| 0.4741        | 5.0   | 385  | 0.4902          | 0.8030   | 0.5185 | 0.4118    | 0.7    |
+| 0.4727        | 6.0   | 462  | 0.4809          | 0.8182   | 0.5385 | 0.4375    | 0.7    |
+| 0.4435        | 7.0   | 539  | 0.4814          | 0.8030   | 0.5185 | 0.4118    | 0.7    |
+| 0.4761        | 8.0   | 616  | 0.4838          | 0.8106   | 0.5283 | 0.4242    | 0.7    |
+| 0.4448        | 9.0   | 693  | 0.4830          | 0.8106   | 0.5283 | 0.4242    | 0.7    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c472ac76e5c4182a3cd811015cef848f3ab4b3bc1a5da9bc99aef0e382d792
+oid sha256:96d878614b4a2a48e2eb2eaca1f5b0a1f1a9d852e3c2617b06edde9c929cb393
 size 1115770572

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6123d693a1672038386f5e9b4f0e796cc99675ffe4689b05d78b53f69fe8dbc9
+oid sha256:0376baf6c33f56b908270c9d954eaae723afadcef589d637e6ca91e93dd8b518
 size 5969