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-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0361
-- Precision: 0.9529
-- Recall: 0.9567
-- F1: 0.9548
-- Accuracy: 0.9928
+- Loss: 0.1367
+- Precision: 0.8702
+- Recall: 0.8865
+- F1: 0.8783
+- Accuracy: 0.9774
 
 ## Model description
 
@@ -44,8 +44,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -55,14 +55,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0454        | 1.0   | 1756 | 0.0379          | 0.9341    | 0.9371 | 0.9356 | 0.9900   |
-| 0.0199        | 2.0   | 3512 | 0.0358          | 0.9525    | 0.9549 | 0.9537 | 0.9924   |
-| 0.011         | 3.0   | 5268 | 0.0361          | 0.9529    | 0.9567 | 0.9548 | 0.9928   |
+| No log        | 1.0   | 204  | 0.1255          | 0.8425    | 0.8676 | 0.8548 | 0.9745   |
+| No log        | 2.0   | 408  | 0.1351          | 0.8594    | 0.8819 | 0.8705 | 0.9760   |
+| 0.1103        | 3.0   | 612  | 0.1367          | 0.8702    | 0.8865 | 0.8783 | 0.9774   |
 
 
 ### Framework versions
 
 - Transformers 4.41.2
-- Pytorch 2.3.0+cu121
-- Datasets 2.20.0
+- Pytorch 2.1.2
+- Datasets 2.19.2
 - Tokenizers 0.19.1