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 [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2133
-- F1: 0.9156
-- Accuracy: 0.9388
-- Precision: 0.9144
-- Recall: 0.9168
+- Loss: 0.2184
+- F1: 0.9369
+- Accuracy: 0.9544
+- Precision: 0.9395
+- Recall: 0.9343
 
 ## Model description
 
@@ -44,24 +44,26 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 100
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | F1     | Accuracy | Precision | Recall |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:--------:|:---------:|:------:|
-| 0.2257        | 1.0   | 5084  | 0.2537          | 0.8900 | 0.9197   | 0.8820    | 0.8983 |
-| 0.1721        | 2.0   | 10168 | 0.2259          | 0.9123 | 0.9366   | 0.9123    | 0.9123 |
+| 0.2241        | 1.0   | 2542  | 0.1977          | 0.8902 | 0.9193   | 0.8768    | 0.9040 |
+| 0.1488        | 2.0   | 5084  | 0.1627          | 0.9187 | 0.9418   | 0.9287    | 0.9090 |
+| 0.0994        | 3.0   | 7626  | 0.1759          | 0.9339 | 0.9524   | 0.9383    | 0.9297 |
+| 0.0687        | 4.0   | 10168 | 0.2099          | 0.9396 | 0.9563   | 0.9391    | 0.9401 |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
-- Pytorch 2.2.1+cu121
-- Datasets 2.19.0
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
 - Tokenizers 0.15.2