End of training

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4313
-- Accuracy: 0.82
-- F1: 0.8393
+- Loss: 0.3792
+- Accuracy: 0.8578
+- F1: 0.8997
 
 ## Model description
 
@@ -51,11 +51,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 150  | 0.6216          | 0.49     | 0.6577 |
-| No log        | 2.0   | 300  | 0.6657          | 0.72     | 0.7742 |
-| No log        | 3.0   | 450  | 0.4629          | 0.79     | 0.8174 |
-| 0.4888        | 4.0   | 600  | 0.4976          | 0.76     | 0.7966 |
-| 0.4888        | 5.0   | 750  | 0.4313          | 0.82     | 0.8393 |
+| No log        | 1.0   | 120  | 0.5343          | 0.6859   | 0.8137 |
+| No log        | 2.0   | 240  | 0.4516          | 0.8203   | 0.8796 |
+| No log        | 3.0   | 360  | 0.4077          | 0.8406   | 0.8922 |
+| No log        | 4.0   | 480  | 0.4011          | 0.8531   | 0.8996 |
+| 0.466         | 5.0   | 600  | 0.3792          | 0.8578   | 0.8997 |
 
 
 ### Framework versions

runs/Jul23_07-21-20_a15ed6fb6b8d/events.out.tfevents.1721719283.a15ed6fb6b8d.1219.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a4192a6e129c422ea880e23956f0de28108507471f04c1448c9b90e9c3dcd7f
-size 6560
+oid sha256:f2a0d6b9eac98e91f235072c50419c467af34a75db733e155b6e40bcbc8b784a
+size 7283