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 [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1169
-- Precision: 0.9439
+- Loss: 0.1130
+- Precision: 0.9419
 - Recall: 0.9533
-- F1: 0.9486
-- Accuracy: 0.9793
+- F1: 0.9476
+- Accuracy: 0.9765
 
 ## Model description
 
@@ -43,8 +43,8 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 4
+- learning_rate: 3e-05
+- train_batch_size: 6
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1311        | 1.0   | 9363  | 0.1125          | 0.9264    | 0.9375 | 0.9319 | 0.9736   |
-| 0.0792        | 2.0   | 18726 | 0.1118          | 0.9402    | 0.9475 | 0.9438 | 0.9775   |
-| 0.0393        | 3.0   | 28089 | 0.1169          | 0.9439    | 0.9533 | 0.9486 | 0.9793   |
+| 0.1281        | 1.0   | 6242  | 0.1079          | 0.9280    | 0.9363 | 0.9321 | 0.9721   |
+| 0.0883        | 2.0   | 12484 | 0.1069          | 0.9330    | 0.9496 | 0.9412 | 0.9746   |
+| 0.0431        | 3.0   | 18726 | 0.1130          | 0.9419    | 0.9533 | 0.9476 | 0.9765   |
 
 
 ### Framework versions