End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nlpie/bio-mobilebert](https://huggingface.co/nlpie/bio-mobilebert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5244
-- Accuracy: 0.737
+- Loss: 1.1386
+- Accuracy: 0.725
 
 ## Model description
 
@@ -49,15 +49,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| No log        | 0.3121 | 250  | 0.8963          | 0.718    |
-| 0.8374        | 0.6242 | 500  | 0.6912          | 0.74     |
-| 0.8374        | 0.9363 | 750  | 0.7389          | 0.747    |
-| 0.6729        | 1.2484 | 1000 | 0.8110          | 0.737    |
-| 0.6729        | 1.5605 | 1250 | 1.0646          | 0.733    |
-| 0.6059        | 1.8727 | 1500 | 0.8516          | 0.733    |
-| 0.6059        | 2.1848 | 1750 | 1.2728          | 0.734    |
-| 0.4538        | 2.4969 | 2000 | 1.5648          | 0.731    |
-| 0.4538        | 2.8090 | 2250 | 1.5244          | 0.737    |
+| No log        | 0.3121 | 250  | 0.9290          | 0.688    |
+| 15.5822       | 0.6242 | 500  | 0.7661          | 0.705    |
+| 15.5822       | 0.9363 | 750  | 0.7196          | 0.716    |
+| 0.7769        | 1.2484 | 1000 | 0.7334          | 0.723    |
+| 0.7769        | 1.5605 | 1250 | 0.8512          | 0.724    |
+| 0.7019        | 1.8727 | 1500 | 0.7588          | 0.729    |
+| 0.7019        | 2.1848 | 1750 | 1.0347          | 0.735    |
+| 0.5534        | 2.4969 | 2000 | 1.0642          | 0.731    |
+| 0.5534        | 2.8090 | 2250 | 1.1386          | 0.725    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9edc08bd67c1f2582ec413ecd059310a2ad34a6fddd1afba51997dc6fb46bd18
+oid sha256:2494cfde0ca5e12fb75ebe3eefaf146e46c8ca11c6777255028402df2312ba77
 size 98468060