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: 1.0222
+- Loss: 0.6102
 - Accuracy: 0.64
-- Auc: 0.6
+- Auc: 0.82
 
 ## Model description
 
@@ -53,8 +53,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc  |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|
-| 0.7182        | 1.0   | 11   | 0.8139          | 0.68     | 0.56 |
-| 0.6242        | 2.0   | 22   | 1.0222          | 0.64     | 0.6  |
+| 0.6955        | 1.0   | 11   | 0.6258          | 0.68     | 0.83 |
+| 0.6666        | 2.0   | 22   | 0.6102          | 0.64     | 0.82 |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b95340b70074f1e4aeb456baf9edde33953f09da37b7a702fce1f650687dbc3
+oid sha256:243550178955475210afee1ccb1cfedb618133ad9f5ac0e1f8ed7fe9efe0cc49
 size 95583552

runs/Aug20_11-22-05_job-d2iqukfdiees738n9dg0-qhj6m/events.out.tfevents.1755688926.job-d2iqukfdiees738n9dg0-qhj6m

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6890ce3eb01287b58c228a2a620722625a090a0d994b33e73b2b07e8d343c82
+size 6555

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf58124b0df0c2654d6f980359251040bebb6702bed83d04f0ecd60861100f98
+oid sha256:9cd5a0a67193b3d3030d43e4d936bdf322b7c8bdcce7fffac234fa454c8727e0
 size 5777