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: 0.3792
-- Accuracy: 0.8578
-- F1: 0.8997
+- Loss: 0.2541
+- Accuracy: 0.9062
+- F1: 0.9372
 
 ## 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   | 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 |
+| No log        | 1.0   | 190  | 0.4252          | 0.7312   | 0.8448 |
+| No log        | 2.0   | 380  | 0.2966          | 0.8688   | 0.9106 |
+| 0.4762        | 3.0   | 570  | 0.2884          | 0.8875   | 0.9224 |
+| 0.4762        | 4.0   | 760  | 0.2458          | 0.9125   | 0.9421 |
+| 0.4762        | 5.0   | 950  | 0.2541          | 0.9062   | 0.9372 |
 
 
 ### Framework versions

runs/Jul23_08-10-37_a15ed6fb6b8d/events.out.tfevents.1721722250.a15ed6fb6b8d.1219.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ee07c9b94323cf42a1c00e26af7751f8b7b52e8932a16cef9edf8bba0b0ebf
-size 6567
+oid sha256:ae165ea08d05d84e62144d6e0674a652a95f069e6f8a97e56a8ec2a0df574213
+size 7290