End of training

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6902
-- F1: 0.5382
-- Accuracy: 0.5384
+- Loss: 0.6844
+- F1: 0.5534
+- Accuracy: 0.5597
 
 ## Model description
 
@@ -44,8 +44,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 16
 - seed: 42
-- optimizer: Use OptimizerNames.SGD and the args are:
-No additional optimizer arguments
+- optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 5
 
@@ -53,11 +52,11 @@ No additional optimizer arguments
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
-| 0.6935        | 1.0   | 113  | 0.6903          | 0.5340 | 0.5341   |
-| 0.6925        | 2.0   | 226  | 0.6901          | 0.5382 | 0.5384   |
-| 0.6933        | 3.0   | 339  | 0.6901          | 0.5382 | 0.5384   |
-| 0.6931        | 4.0   | 452  | 0.6902          | 0.5382 | 0.5384   |
-| 0.6932        | 5.0   | 565  | 0.6902          | 0.5382 | 0.5384   |
+| 0.6886        | 1.0   | 113  | 0.6932          | 0.4420 | 0.5256   |
+| 0.6775        | 2.0   | 226  | 0.6861          | 0.5520 | 0.5533   |
+| 0.6663        | 3.0   | 339  | 0.6851          | 0.5524 | 0.5533   |
+| 0.665         | 4.0   | 452  | 0.6842          | 0.5405 | 0.5405   |
+| 0.6604        | 5.0   | 565  | 0.6844          | 0.5534 | 0.5597   |
 
 
 ### Framework versions