End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0079
-- Accuracy: 0.6741
+- Loss: 1.2894
+- Accuracy: 0.5852
 
 ## Model description
 
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6323        | 1.0   | 79   | 1.3051          | 0.5778   |
-| 1.3752        | 2.0   | 158  | 1.2841          | 0.5148   |
-| 1.2269        | 3.0   | 237  | 1.0283          | 0.6407   |
-| 1.2356        | 4.0   | 316  | 1.0079          | 0.6741   |
+| 2.143         | 1.0   | 79   | 1.9131          | 0.3741   |
+| 1.6912        | 2.0   | 158  | 1.5070          | 0.4519   |
+| 1.5696        | 3.0   | 237  | 1.3278          | 0.5926   |
+| 1.4828        | 4.0   | 316  | 1.2894          | 0.5852   |
 
 
 ### Framework versions

runs/Dec01_09-42-47_tsf-508-wpa-6-167.epfl.ch/events.out.tfevents.1764578652.tsf-508-wpa-6-167.epfl.ch.2181.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80742be08055ddc0f7ace749d7981dac013ac6b51af947cc6ec0c0f109f27d29
+size 411

runs/Dec01_09-43-34_tsf-508-wpa-6-167.epfl.ch/events.out.tfevents.1764578615.tsf-508-wpa-6-167.epfl.ch.2181.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:030bf661c47744e3f65b718708236d66161dc75cddd6bd9547659507a5a3ef67
-size 12883
+oid sha256:eeb79598a0fdbe09b3f6380ae8f223ed8f59fcddc20e4c435cc3cb9461927af8
+size 13560

runs/Dec01_09-43-34_tsf-508-wpa-6-167.epfl.ch/events.out.tfevents.1764578654.tsf-508-wpa-6-167.epfl.ch.2181.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ae316684354d0e10df728460c2d02bffc5b5bc5567ac9dc2a0e23b889f631d
+size 411