End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the squad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4503
+- Loss: 1.3801
 
 ## Model description
 
@@ -48,11 +48,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.8676        | 1.0   | 500  | 1.5998          |
-| 1.4534        | 2.0   | 1000 | 1.3659          |
-| 1.0241        | 3.0   | 1500 | 1.3650          |
-| 0.777         | 4.0   | 2000 | 1.4111          |
-| 0.6292        | 5.0   | 2500 | 1.4503          |
+| 2.8311        | 1.0   | 563  | 1.6891          |
+| 1.5284        | 2.0   | 1126 | 1.3453          |
+| 1.1163        | 3.0   | 1689 | 1.3392          |
+| 0.8581        | 4.0   | 2252 | 1.3402          |
+| 0.701         | 5.0   | 2815 | 1.3801          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88385ac91dc3f1330a879664c9ebf2741d373bb876e0ba8cb6951476271691fe
+oid sha256:a601392e695a9215942e48cdae030e41a616a5376268a47c61789e2afe8da9d6
 size 260804645