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 [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: 0.1367
-- Precision: 0.5765
-- Recall: 0.4800
-- F1: 0.5238
-- Accuracy: 0.9535
+- Loss: 0.1620
+- Precision: 0.6121
+- Recall: 0.5161
+- F1: 0.5600
+- Accuracy: 0.9541
 
 ## Model description
 
@@ -49,20 +49,23 @@ 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: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 71   | 0.1588          | 0.4782    | 0.3308 | 0.3911 | 0.9408   |
-| No log        | 2.0   | 142  | 0.1397          | 0.5760    | 0.4213 | 0.4866 | 0.9517   |
-| No log        | 3.0   | 213  | 0.1367          | 0.5765    | 0.4800 | 0.5238 | 0.9535   |
+| No log        | 1.0   | 71   | 0.1704          | 0.4558    | 0.3635 | 0.4045 | 0.9353   |
+| No log        | 2.0   | 142  | 0.1572          | 0.5925    | 0.3518 | 0.4415 | 0.9433   |
+| No log        | 3.0   | 213  | 0.1386          | 0.5932    | 0.4774 | 0.5290 | 0.9531   |
+| No log        | 4.0   | 284  | 0.1427          | 0.5945    | 0.5175 | 0.5534 | 0.9533   |
+| No log        | 5.0   | 355  | 0.1653          | 0.6354    | 0.4788 | 0.5461 | 0.9540   |
+| No log        | 6.0   | 426  | 0.1620          | 0.6121    | 0.5161 | 0.5600 | 0.9541   |
 
 
 ### Framework versions
 
-- Transformers 4.33.2
+- Transformers 4.34.0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.14.1