End of training

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.8256
-- F1: 0.0045
-- Recall: 0.0483
-- Accuracy: 0.0483
-- Precision: 0.0023
+- Loss: 0.9226
+- F1: 0.7658
+- Recall: 0.7781
+- Accuracy: 0.7781
+- Precision: 0.7732
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -56,11 +56,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Recall | Accuracy | Precision |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:--------:|:---------:|
-| 4.0201        | 1.0   | 588  | 3.8207          | 0.0000 | 0.0034 | 0.0034   | 0.0000    |
-| 4.0249        | 2.0   | 1176 | 3.7674          | 0.0006 | 0.0175 | 0.0175   | 0.0003    |
-| 4.0117        | 3.0   | 1764 | 3.8834          | 0.0002 | 0.0094 | 0.0094   | 0.0001    |
-| 4.0209        | 4.0   | 2352 | 3.7563          | 0.0003 | 0.0131 | 0.0131   | 0.0002    |
-| 4.0146        | 5.0   | 2940 | 3.8256          | 0.0045 | 0.0483 | 0.0483   | 0.0023    |
+| No log        | 1.0   | 442  | 1.6778          | 0.5689 | 0.6220 | 0.6220   | 0.5666    |
+| 2.5427        | 2.0   | 884  | 1.2190          | 0.6737 | 0.7091 | 0.7091   | 0.6681    |
+| 1.2661        | 3.0   | 1326 | 1.0742          | 0.7099 | 0.7440 | 0.7440   | 0.7132    |
+| 0.8666        | 4.0   | 1768 | 1.0213          | 0.7374 | 0.7526 | 0.7526   | 0.7447    |
+| 0.6456        | 5.0   | 2210 | 0.9226          | 0.7658 | 0.7781 | 0.7781   | 0.7732    |
 
 
 ### Framework versions