my-roberta-finetuned-model-34768

README.md

@@ -17,8 +17,8 @@ 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: 0.9481
-- Accuracy: 0.6839
+- Loss: 0.9181
+- Accuracy: 0.6682
 
 ## Model description
 
@@ -49,16 +49,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 207  | 1.0120          | 0.6206   |
-| No log        | 2.0   | 414  | 0.9914          | 0.6357   |
-| 0.9337        | 3.0   | 621  | 0.9531          | 0.6609   |
-| 0.9337        | 4.0   | 828  | 0.9469          | 0.6825   |
-| 0.7962        | 5.0   | 1035 | 0.9481          | 0.6839   |
+| No log        | 1.0   | 259  | 1.2041          | 0.5474   |
+| 1.2337        | 2.0   | 518  | 1.0736          | 0.6130   |
+| 1.2337        | 3.0   | 777  | 0.9574          | 0.6515   |
+| 0.9397        | 4.0   | 1036 | 0.9257          | 0.6659   |
+| 0.9397        | 5.0   | 1295 | 0.9181          | 0.6682   |
 
 
 ### Framework versions
 
 - Transformers 4.39.3
 - Pytorch 2.1.2
-- Datasets 2.17.0
+- Datasets 2.18.0
 - Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f728ab88b84434d5cbd43277fa0bc160b3354092233e8ef8cafc76161d4ef203
+oid sha256:aec85e9d821ff20d3c397e0dd7cde12effa365130cab0183519c8ed369353a88
 size 498625128