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: 0.3544
-- Accuracy: 0.8472
-- Precision: 0.2716
-- Recall: 0.2683
-- F1: 0.2699
+- Loss: 0.1959
+- Accuracy: 0.8691
+- Precision: 0.3387
+- Recall: 0.2561
+- F1: 0.2917
 
 ## Model description
 
@@ -44,29 +44,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.151932836125528e-05
+- learning_rate: 1.7040925846794196e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.4598        | 1.0   | 140  | 0.1502          | 0.8947   | 0.0       | 0.0    | 0.0    |
-| 0.3722        | 2.0   | 280  | 0.2096          | 0.8498   | 0.3077    | 0.3415 | 0.3237 |
-| 0.3309        | 3.0   | 420  | 0.1583          | 0.8947   | 0.0       | 0.0    | 0.0    |
-| 0.289         | 4.0   | 560  | 0.1917          | 0.8742   | 0.375     | 0.2927 | 0.3288 |
-| 0.2731        | 5.0   | 700  | 0.2409          | 0.8164   | 0.2636    | 0.4146 | 0.3223 |
-| 0.2197        | 6.0   | 840  | 0.3765          | 0.7073   | 0.2033    | 0.6098 | 0.3049 |
-| 0.1956        | 7.0   | 980  | 0.1718          | 0.8691   | 0.3214    | 0.2195 | 0.2609 |
-| 0.1636        | 8.0   | 1120 | 0.4758          | 0.7920   | 0.25      | 0.4878 | 0.3306 |
-| 0.1606        | 9.0   | 1260 | 0.3204          | 0.8575   | 0.2958    | 0.2561 | 0.2745 |
-| 0.1556        | 10.0  | 1400 | 0.3544          | 0.8472   | 0.2716    | 0.2683 | 0.2699 |
+| 0.4468        | 1.0   | 140  | 0.3926          | 0.8703   | 0.3582    | 0.2927 | 0.3221 |
+| 0.3624        | 2.0   | 280  | 0.2036          | 0.8755   | 0.3333    | 0.1829 | 0.2362 |
+| 0.3061        | 3.0   | 420  | 0.1371          | 0.8973   | 0.75      | 0.0366 | 0.0698 |
+| 0.2535        | 4.0   | 560  | 0.1825          | 0.8768   | 0.375     | 0.2561 | 0.3043 |
+| 0.2381        | 5.0   | 700  | 0.1959          | 0.8691   | 0.3387    | 0.2561 | 0.2917 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db679d229a19781f15ce5ca96583d22b926169ae4fd9086371bc6eddb5df5b5
+oid sha256:901b1d45a07a5d99f85ae83cd9dd658f1ee7fd82a5db29fc995faee02b8ad52a
 size 1421495416