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: 0.7650
-- Precision: 0.7942
-- Recall: 0.8401
-- F1: 0.8165
-- Accuracy: 0.9840
+- Loss: 0.4051
+- Precision: 0.7944
+- Recall: 0.8673
+- F1: 0.8293
+- Accuracy: 0.9852
 
 ## Model description
 
@@ -53,8 +53,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 226  | 0.7218          | 0.7871    | 0.8299 | 0.8079 | 0.9838   |
-| No log        | 2.0   | 452  | 0.7650          | 0.7942    | 0.8401 | 0.8165 | 0.9840   |
+| No log        | 1.0   | 226  | 0.4422          | 0.8253    | 0.8197 | 0.8225 | 0.9859   |
+| No log        | 2.0   | 452  | 0.4051          | 0.7944    | 0.8673 | 0.8293 | 0.9852   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14abba02aeb6f1c9ba302d7255ecc4a28a236073615b7963614713ca805dd195
+oid sha256:cc5da34755a3927db1c804c4ac6ec68cfc4c1ee351f28ab3cfd55640fb80eda5
 size 1109908201