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: 0.8615
+- Loss: 0.6814
 - Accuracy: 0.59
-- Auc: 0.56
+- Auc: 0.62
 
 ## Model description
 
@@ -53,14 +53,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc  |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|
-| 0.6741        | 1.0   | 11   | 0.8638          | 0.59     | 0.55 |
-| 0.5976        | 2.0   | 22   | 0.8615          | 0.59     | 0.56 |
+| 0.7235        | 1.0   | 11   | 0.6819          | 0.55     | 0.63 |
+| 0.6736        | 2.0   | 22   | 0.6814          | 0.59     | 0.62 |
 
 
 ### Framework versions
 
 - PEFT 0.16.0
 - Transformers 4.53.3
-- Pytorch 2.7.1
+- Pytorch 2.7.1+cpu
 - Datasets 4.0.0
 - Tokenizers 0.21.2

adapter_config.json

@@ -28,8 +28,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query",
     "value",
+    "query",
     "key"
   ],
   "task_type": "SEQ_CLS",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e658245f9e2ef3187c55ece1c6bdd7ddc633dc3e2c3275884d0db8a4bb27b7d2
+oid sha256:f8eae5690ca846f6c5922b338ce42337d604a015c7f0f635b388e78d8b59c6ed
 size 95583552

runs/Sep06_21-20-12_ab6e95884921/events.out.tfevents.1757193613.ab6e95884921

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04777103a4ecfb0742cfd105acf441ad9284cad8046171d8f03082cdd9560fb7
+size 6537

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5077f9323abf26b96fbc72019acb8701cefdad93374c5da194e61cb3ec6b7930
+oid sha256:31ccc08f37661a9d723968779706c695e4c5dc6dc0728956ad18207d7e168c86
 size 5777