BiLSTM test 1

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [csarron/mobilebert-uncased-squad-v1](https://huggingface.co/csarron/mobilebert-uncased-squad-v1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3032
+- Loss: 1.3684
 
 ## Model description
 
@@ -44,10 +44,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.5469        | 1.0   | 2922 | 1.1011          |
-| 0.3789        | 2.0   | 5844 | 1.3032          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.5287        | 1.0   | 14618 | 1.1069          |
+| 0.3993        | 2.0   | 29236 | 1.3684          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d69eda04fe0469ef6bfde764a0f87c5c31745cf0e7dda1b4a393fe46f5eb44
+oid sha256:60094da2cfe495ba043323296291bf43655b2c9e656340baf6274de2df6fd40c
 size 98470136