End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8848
+- Loss: 0.6992
 
 ## Model description
 
@@ -40,15 +40,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.1199 | 1.0 | 72 | 1.1303 |
-| 0.6057 | 2.0 | 144 | 0.9352 |
-| 0.709 | 3.0 | 216 | 0.8848 |
+| 1.6467 | 1.0 | 72 | 1.2359 |
+| 1.1173 | 2.0 | 144 | 0.9495 |
+| 1.0739 | 3.0 | 216 | 0.8453 |
+| 1.1401 | 4.0 | 288 | 0.7375 |
+| 0.7642 | 5.0 | 360 | 0.7090 |
+| 0.1559 | 6.0 | 432 | 0.6992 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6f5b86f077a7854524f62debe969f2023d22682b4387cfaf81351b1c5f7b36
+oid sha256:a45ace03d8fc75d0014d76e31689caf61d2ae33039afb90657c8d759788241bf
 size 496250232

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc61ba12a47d31af25cb7961caec2ddd84e049aeeeff468e63d37fafd3c243ab
+oid sha256:b918cd089428bcffed35867025b047991ab8d52909626c24cbb633403a745248
 size 5048