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: 0.6715
-- Accuracy: 0.64
-- Auc: 0.66
+- Loss: 0.6144
+- Accuracy: 0.77
+- Auc: 0.76
 
 ## Model description
 
@@ -53,8 +53,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc  |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|
-| 0.7438        | 1.0   | 11   | 0.6913          | 0.55     | 0.65 |
-| 0.6635        | 2.0   | 22   | 0.6715          | 0.64     | 0.66 |
+| 0.7172        | 1.0   | 11   | 0.6236          | 0.68     | 0.79 |
+| 0.6452        | 2.0   | 22   | 0.6144          | 0.77     | 0.76 |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443e176956e1bb04f9baa317aea9b0014b0ed5644816cb26008423b6fc2f18b6
+oid sha256:b802438d23e34128207e534e3a29b77baa6e512047e4df74e68b46347610dee2
 size 95583552

runs/Oct28_23-05-12_crn-d2ckhvruibrs738j7ur0-29361540-9fjw5/events.out.tfevents.1761692713.crn-d2ckhvruibrs738j7ur0-29361540-9fjw5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f77fb7baa9d3a303d28b27e33850d477403a3fd33f00aed037a964f7f058f39
+size 6564

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28aa6dcaf57091a59ff6ae72cd3d6ca7b89a799908c3d8813f9d7d29994f6033
+oid sha256:68cf81247013fe4c795f946c09cb74fe9ecdcdc1262af52e2eea98a77376d698
 size 5841