BiLSTM test 1

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allistair99/tinybert-6l-768d-BiLSTM-finetuned-squad-optiparam](https://huggingface.co/allistair99/tinybert-6l-768d-BiLSTM-finetuned-squad-optiparam) on the srh_test66 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2961
+- Loss: 1.8185
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 42   | 3.9998          |
-| No log        | 2.0   | 84   | 3.4290          |
-| No log        | 3.0   | 126  | 3.2961          |
+| No log        | 1.0   | 42   | 1.8908          |
+| No log        | 2.0   | 84   | 1.7989          |
+| No log        | 3.0   | 126  | 1.8185          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a694fc8ded2f2f8b9c1df65fad9b39af36c43ec4ee0f61cbb8b42143ee65660
+oid sha256:be1ad60e0ca8734273b4e5532917e81f6b73aca7e1047c0a832ddb5c619c878f
 size 279656944