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 [sharmadhruv/my_awesome_qa_model](https://huggingface.co/sharmadhruv/my_awesome_qa_model) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.2362
+- Loss: 3.7448
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.6597        | 1.0   | 1000 | 4.5738          |
-| 4.4218        | 2.0   | 2000 | 4.3305          |
-| 4.2711        | 3.0   | 3000 | 4.2362          |
+| 4.028         | 1.0   | 1000 | 3.9432          |
+| 3.668         | 2.0   | 2000 | 3.7996          |
+| 3.4871        | 3.0   | 3000 | 3.7448          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901e75d1b23924d722789b981a20af561a8db9e53025a03fa1e8b25ccfac46ed
+oid sha256:66d901a491168ab3e585a77fbcf2c728f8bfd40769ead2411409502820c3b86d
 size 2307633752

tokenizer.json

@@ -4,18 +4,9 @@
     "direction": "Right",
     "max_length": 384,
     "strategy": "OnlySecond",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 384
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
+    "stride": 128
   },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,