Upload TFRobertaForMaskedLM

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheophileCA/distilroberta_trainedOnCACatalogue](https://huggingface.co/TheophileCA/distilroberta_trainedOnCACatalogue) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.8254
-- Validation Loss: 1.7345
-- Epoch: 2
+- Train Loss: 1.1564
+- Validation Loss: 1.1547
+- Epoch: 14
 
 ## Model description
 
@@ -43,9 +43,21 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.2309     | 1.9275          | 0     |
-| 1.9894     | 1.7416          | 1     |
-| 1.8254     | 1.7345          | 2     |
+| 1.7078     | 1.5690          | 0     |
+| 1.6687     | 1.5544          | 1     |
+| 1.5738     | 1.4494          | 2     |
+| 1.4793     | 1.4567          | 3     |
+| 1.4418     | 1.4016          | 4     |
+| 1.4327     | 1.3699          | 5     |
+| 1.3634     | 1.3266          | 6     |
+| 1.3034     | 1.2834          | 7     |
+| 1.2854     | 1.2797          | 8     |
+| 1.2689     | 1.2383          | 9     |
+| 1.2379     | 1.2031          | 10    |
+| 1.1968     | 1.1526          | 11    |
+| 1.1555     | 1.2410          | 12    |
+| 1.1486     | 1.2033          | 13    |
+| 1.1564     | 1.1547          | 14    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2280666d2b4301bc38d5493138af72ef904450d1ba55803db25d270bb86866e5
+oid sha256:bfd2a4e665a089406339d466dfb935f040ec1bfc508261a0b58c891d323248b9
 size 484838604