Colabng/twitter_bank_scam_classifier

README.md

@@ -20,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1238
-- Accuracy: 0.96
-- Auc: 1.0
+- Loss: 0.5780
+- Accuracy: 0.68
+- Auc: 0.76
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|
-| 0.3922        | 1.0   | 27   | 0.0940          | 0.96     | 1.0 |
-| 0.1191        | 2.0   | 54   | 0.1238          | 0.96     | 1.0 |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc  |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|
+| 0.721         | 1.0   | 11   | 0.6280          | 0.59     | 0.79 |
+| 0.713         | 2.0   | 22   | 0.5780          | 0.68     | 0.76 |
 
 
 ### Framework versions

adapter_config.json

@@ -28,9 +28,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "key",
     "query",
-    "value",
-    "key"
+    "value"
   ],
   "task_type": "SEQ_CLS",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:655bc81e033ebe6d4294f098844bfe6bd49daf90b92f5a97f44643d275690bdf
+oid sha256:eaca2efcabbf21a0741f36c7f1313774ba86f248d4686b51f78ee0f58bcde9ec
 size 95583552

runs/Sep06_14-04-13_Mac/events.out.tfevents.1757163853.Mac

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9452ff11efc077eccdfe57839941d2d439ce28dec0b8ac00dc846d5fec31851d
+size 6528

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9253cd7d4745654bb707ff1772c6bfb68fe8c165fcd87637fdc38655f9e4a22
+oid sha256:714ebd3e6142f974846b96eef659a1449630988bd0be36be60356870554c515c
 size 5777