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 [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0765
-- Precision: 0.7970
-- Recall: 0.7733
-- F1: 0.7850
-- Accuracy: 0.9763
+- Loss: 0.0751
+- Precision: 0.8017
+- Recall: 0.7929
+- F1: 0.7973
+- Accuracy: 0.9770
 
 ## Model description
 
@@ -51,20 +51,22 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 2
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 231  | 0.0904          | 0.7605    | 0.7562 | 0.7583 | 0.9723   |
-| No log        | 2.0   | 462  | 0.0765          | 0.7970    | 0.7733 | 0.7850 | 0.9763   |
+| No log        | 1.0   | 231  | 0.0920          | 0.7617    | 0.7516 | 0.7566 | 0.9723   |
+| No log        | 2.0   | 462  | 0.0769          | 0.7942    | 0.7820 | 0.7881 | 0.9763   |
+| 0.2523        | 3.0   | 693  | 0.0736          | 0.8096    | 0.7882 | 0.7988 | 0.9774   |
+| 0.2523        | 4.0   | 924  | 0.0751          | 0.8017    | 0.7929 | 0.7973 | 0.9770   |
 
 
 ### Framework versions
 
 - Transformers 4.44.2
-- Pytorch 2.4.0+cu121
+- Pytorch 2.4.1+cu121
 - Datasets 2.21.0
 - Tokenizers 0.19.1