End of training

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6713
-- Accuracy: 0.7375
+- Loss: 0.8264
+- Accuracy: 0.725
 
 ## Model description
 
@@ -48,14 +48,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 1.0972          | 0.5875   |
-| No log        | 2.0   | 80   | 0.5872          | 0.7562   |
-| No log        | 3.0   | 120  | 0.6250          | 0.725    |
-| No log        | 4.0   | 160  | 0.5797          | 0.7375   |
-| No log        | 5.0   | 200  | 0.5570          | 0.725    |
-| No log        | 6.0   | 240  | 0.5464          | 0.7562   |
-| No log        | 7.0   | 280  | 0.6876          | 0.7375   |
-| No log        | 8.0   | 320  | 0.6713          | 0.7375   |
+| No log        | 1.0   | 40   | 1.1896          | 0.5375   |
+| No log        | 2.0   | 80   | 0.6831          | 0.7      |
+| No log        | 3.0   | 120  | 0.6951          | 0.7      |
+| No log        | 4.0   | 160  | 0.7126          | 0.6937   |
+| No log        | 5.0   | 200  | 0.7937          | 0.6875   |
+| No log        | 6.0   | 240  | 0.6445          | 0.7125   |
+| No log        | 7.0   | 280  | 0.7990          | 0.7188   |
+| No log        | 8.0   | 320  | 0.8264          | 0.725    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe9a68cadc9d02242533e9688c31fc46dc5c039da0cbbabc34d00e58acb7fa2
+oid sha256:8dec52db7b068301875d885cd860af49fca0791f827ba1442dd9d1707373daea
 size 439712772