Training complete

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2118
-- Precision: 0.7031
-- Recall: 0.7355
-- F1: 0.7190
-- Accuracy: 0.9571
+- Loss: 0.0638
+- Precision: 0.8534
+- Recall: 0.8912
+- F1: 0.8719
+- Accuracy: 0.9886
 
 ## Model description
 
@@ -41,21 +41,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 4.899923663123727e-05
+- learning_rate: 3.6925210602772034e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 226  | 0.1747          | 0.6946    | 0.6685 | 0.6813 | 0.9556   |
-| No log        | 2.0   | 452  | 0.2195          | 0.7190    | 0.7128 | 0.7159 | 0.9571   |
-| 0.0636        | 3.0   | 678  | 0.2118          | 0.7031    | 0.7355 | 0.7190 | 0.9571   |
+| No log        | 1.0   | 226  | 0.0697          | 0.7640    | 0.8810 | 0.8183 | 0.9849   |
+| No log        | 2.0   | 452  | 0.0663          | 0.8522    | 0.8435 | 0.8479 | 0.9876   |
+| 0.0089        | 3.0   | 678  | 0.0689          | 0.8257    | 0.9184 | 0.8696 | 0.9875   |
+| 0.0089        | 4.0   | 904  | 0.0638          | 0.8534    | 0.8912 | 0.8719 | 0.9886   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fe88fc79c71d69da9a131a4d8b7a330d58c362229fec5de051d02c306688cd8
+oid sha256:2a707001cd339908acf978dea7e01ca0fd1d4855ed1f59e264933c9552b792b4
 size 1109908201