End of training

README.md

@@ -20,10 +20,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1977
-- Accuracy: 0.9383
-- F1: 0.2445
-- Recall: 0.1628
+- Loss: 0.1984
+- Accuracy: 0.9369
+- F1: 0.3059
+- Recall: 0.2267
 
 ## Model description
 
@@ -43,8 +43,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|
-| 0.2118        | 1.0   | 701  | 0.2022          | 0.9340   | 0.1148 | 0.0698 |
-| 0.1864        | 2.0   | 1402 | 0.2178          | 0.9397   | 0.0452 | 0.0233 |
-| 0.1275        | 3.0   | 2103 | 0.1977          | 0.9383   | 0.2445 | 0.1628 |
+| No log        | 1.0   | 351  | 0.1665          | 0.9401   | 0.16   | 0.0930 |
+| 0.1813        | 2.0   | 702  | 0.2099          | 0.9418   | 0.1189 | 0.0640 |
+| 0.1067        | 3.0   | 1053 | 0.1984          | 0.9369   | 0.3059 | 0.2267 |
 
 
 ### Framework versions

runs/Jan05_01-42-57_be6bed7a2f79/events.out.tfevents.1736041399.be6bed7a2f79.20456.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50bc8ccf15e868a7ce7da6dfcf18478fdc3c93e8400e1d3f40335a698b6e7cad
-size 5633
+oid sha256:298802ddaf478c2a5fdb8cf105eba7f221f498ff1668a87b1c7f5a5b8f147083
+size 7247