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: 1.0127
-- Precision: 0.8039
-- Recall: 0.8503
-- F1: 0.8264
-- Accuracy: 0.9850
+- Loss: 0.6118
+- Precision: 0.7723
+- Recall: 0.8537
+- F1: 0.8110
+- Accuracy: 0.9838
 
 ## Model description
 
@@ -41,20 +41,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2e-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: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 226  | 1.0853          | 0.8039    | 0.8367 | 0.8200 | 0.9846   |
-| No log        | 2.0   | 452  | 1.0127          | 0.8039    | 0.8503 | 0.8264 | 0.9850   |
+| No log        | 1.0   | 226  | 0.8038          | 0.75      | 0.7755 | 0.7625 | 0.9818   |
+| No log        | 2.0   | 452  | 0.7667          | 0.7914    | 0.8129 | 0.8020 | 0.9831   |
+| 0.0535        | 3.0   | 678  | 0.6118          | 0.7723    | 0.8537 | 0.8110 | 0.9838   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41d09a12642309338c98b3442a2ec3c629b22d940beb2467283a960eef3a85c3
+oid sha256:1c75a1a0e4b552bde527b9cae52256b3eebcb335a809d88da6828a31cf0ef96d
 size 1109908201