rationalenterprise/fine_tuned_spam_model

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mrm8488/bert-tiny-finetuned-sms-spam-detection](https://huggingface.co/mrm8488/bert-tiny-finetuned-sms-spam-detection) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0958
-- Accuracy: 0.5367
+- Loss: 1.0884
+- Accuracy: 0.5480
 
 ## Model description
 
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.1513        | 1.0   | 42   | 1.1530          | 0.5367   |
-| 1.071         | 2.0   | 84   | 1.1045          | 0.5367   |
-| 1.0416        | 3.0   | 126  | 1.0958          | 0.5367   |
+| 1.1383        | 1.0   | 42   | 1.1377          | 0.5367   |
+| 1.0594        | 2.0   | 84   | 1.0975          | 0.5424   |
+| 1.0472        | 3.0   | 126  | 1.0884          | 0.5480   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8578dc4729e895ee8ce82d21f36bf32b12b7e39ff394aa259afbe0731c65f34
+oid sha256:ab548e01d8773de60e65b15e31b30be0cbf05f418281bd4b16d823092db7b210
 size 17550344

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 128
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,