Training complete

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1881
-- Precision: 0.8282
-- Recall: 0.8524
-- F1: 0.8401
-- Accuracy: 0.9640
+- Loss: 0.2239
+- Precision: 0.8342
+- Recall: 0.8511
+- F1: 0.8426
+- Accuracy: 0.9648
 
 ## Model description
 
@@ -45,25 +45,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1395        | 1.0   | 9500  | 0.1497          | 0.7937    | 0.8218 | 0.8075 | 0.9573   |
-| 0.1167        | 2.0   | 19000 | 0.1443          | 0.8223    | 0.8277 | 0.8250 | 0.9605   |
-| 0.1029        | 3.0   | 28500 | 0.1404          | 0.8191    | 0.8397 | 0.8293 | 0.9621   |
-| 0.0921        | 4.0   | 38000 | 0.1472          | 0.8282    | 0.8427 | 0.8354 | 0.9642   |
-| 0.0742        | 5.0   | 47500 | 0.1667          | 0.8236    | 0.8445 | 0.8339 | 0.9631   |
-| 0.0611        | 6.0   | 57000 | 0.1742          | 0.8268    | 0.8520 | 0.8392 | 0.9638   |
-| 0.0601        | 7.0   | 66500 | 0.1814          | 0.8274    | 0.8533 | 0.8402 | 0.9640   |
-| 0.0554        | 8.0   | 76000 | 0.1881          | 0.8282    | 0.8524 | 0.8401 | 0.9640   |
+| Training Loss | Epoch | Step   | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1257        | 1.0   | 38000  | 0.1357          | 0.8006    | 0.8311 | 0.8155 | 0.9604   |
+| 0.0954        | 2.0   | 76000  | 0.1530          | 0.8278    | 0.8347 | 0.8312 | 0.9627   |
+| 0.0897        | 3.0   | 114000 | 0.1539          | 0.8302    | 0.8449 | 0.8375 | 0.9647   |
+| 0.0411        | 4.0   | 152000 | 0.1971          | 0.8321    | 0.8504 | 0.8411 | 0.9648   |
+| 0.0205        | 5.0   | 190000 | 0.2239          | 0.8342    | 0.8511 | 0.8426 | 0.9648   |
 
 
 ### Framework versions