Model save

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8794
-- Accuracy: 0.4431
-- F1: 0.4259
+- Loss: 0.0941
+- Accuracy: 0.9417
+- F1: 0.9406
 
 ## Model description
 
@@ -47,12 +47,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 1.7036        | 1.0   | 2148 | 1.8292          | 0.4596   | 0.4299 |
-| 1.6605        | 2.0   | 4296 | 1.8217          | 0.4570   | 0.4280 |
-| 1.5764        | 3.0   | 6444 | 1.8520          | 0.4534   | 0.4261 |
-| 1.5112        | 4.0   | 8592 | 1.8794          | 0.4431   | 0.4259 |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
+| 0.0892        | 1.0   | 5211  | 0.0919          | 0.9405   | 0.9389 |
+| 0.0875        | 2.0   | 10422 | 0.0892          | 0.9411   | 0.9422 |
+| 0.0813        | 3.0   | 15633 | 0.0914          | 0.9419   | 0.9392 |
+| 0.0775        | 4.0   | 20844 | 0.0941          | 0.9417   | 0.9406 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77262e3f11ea1e2b69ee7010508fc6150da8ce3a1372e1916762bd963d7544eb
+oid sha256:aa016c63c9f42ed1cb1189a2550fef18a1040d4fca451c753ad9d0452b4d5f10
 size 267844872