Training complete

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vonewman/xlm-roberta-base-finetuned-wolof](https://huggingface.co/vonewman/xlm-roberta-base-finetuned-wolof) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3982
-- Precision: 0.8104
-- Recall: 0.9014
-- F1: 0.8535
-- Accuracy: 0.9868
+- Loss: 0.3539
+- Precision: 0.7798
+- Recall: 0.8912
+- F1: 0.8317
+- Accuracy: 0.9850
 
 ## Model description
 
@@ -49,17 +49,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 226  | 0.3440          | 0.8538    | 0.8741 | 0.8639 | 0.9884   |
-| No log        | 2.0   | 452  | 0.4196          | 0.8317    | 0.8571 | 0.8442 | 0.9876   |
-| 0.0699        | 3.0   | 678  | 0.3951          | 0.8291    | 0.8912 | 0.8590 | 0.9878   |
-| 0.0699        | 4.0   | 904  | 0.3923          | 0.8270    | 0.8946 | 0.8595 | 0.9880   |
-| 0.032         | 5.0   | 1130 | 0.3982          | 0.8104    | 0.9014 | 0.8535 | 0.9868   |
+| No log        | 1.0   | 226  | 0.3879          | 0.7412    | 0.8571 | 0.7950 | 0.9834   |
+| No log        | 2.0   | 452  | 0.3595          | 0.7378    | 0.8707 | 0.7988 | 0.9833   |
+| 0.5119        | 3.0   | 678  | 0.3539          | 0.7798    | 0.8912 | 0.8317 | 0.9850   |
 
 
 ### Framework versions