End of training

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-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4523
-- Accuracy: 0.8126
-- Precision: 0.6634
-- Recall: 0.8204
-- F1: 0.7336
+- Loss: 0.4714
+- Accuracy: 0.8023
+- Precision: 0.6350
+- Recall: 0.8735
+- F1: 0.7354
 
 ## Model description
 
@@ -44,7 +44,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 8.743943190085984e-06
+- learning_rate: 1.669740264596789e-05
 - train_batch_size: 32
 - eval_batch_size: 16
 - seed: 42
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.562         | 1.0   | 243  | 0.3999          | 0.8062   | 0.6469    | 0.8449 | 0.7327 |
-| 0.4525        | 2.0   | 486  | 0.4436          | 0.7484   | 0.5593    | 0.9429 | 0.7021 |
-| 0.3874        | 3.0   | 729  | 0.4189          | 0.8139   | 0.6634    | 0.8286 | 0.7368 |
-| 0.324         | 4.0   | 972  | 0.4523          | 0.8126   | 0.6634    | 0.8204 | 0.7336 |
+| 0.5351        | 1.0   | 243  | 0.4195          | 0.8151   | 0.7095    | 0.6980 | 0.7037 |
+| 0.4572        | 2.0   | 486  | 0.4694          | 0.7189   | 0.5294    | 0.9551 | 0.6812 |
+| 0.3823        | 3.0   | 729  | 0.4196          | 0.8010   | 0.6398    | 0.8408 | 0.7266 |
+| 0.301         | 4.0   | 972  | 0.4714          | 0.8023   | 0.6350    | 0.8735 | 0.7354 |
 
 
 ### Framework versions