shandonk/distilbert-base-uncased-lora-text-classification-2nd-try

README.md

@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the financial_phrasebank dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3709
-- Accuracy: {'accuracy': 0.834089971110194}
+- Loss: 1.2612
+- Accuracy: {'accuracy': 0.8287247214197276}
 
 ## Model description
 
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy                         |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|
-| 0.6394        | 1.0   | 606  | 0.4650          | {'accuracy': 0.845233182005778}  |
-| 0.4547        | 2.0   | 1212 | 0.5475          | {'accuracy': 0.8369789517127528} |
-| 0.4296        | 3.0   | 1818 | 0.6848          | {'accuracy': 0.8423442014032192} |
-| 0.3407        | 4.0   | 2424 | 0.8076          | {'accuracy': 0.8398679323153116} |
-| 0.219         | 5.0   | 3030 | 0.9642          | {'accuracy': 0.8361535286834503} |
-| 0.1596        | 6.0   | 3636 | 1.0729          | {'accuracy': 0.837391663227404}  |
-| 0.1105        | 7.0   | 4242 | 1.2063          | {'accuracy': 0.8328518365662402} |
-| 0.1106        | 8.0   | 4848 | 1.2701          | {'accuracy': 0.8415187783739166} |
-| 0.0633        | 9.0   | 5454 | 1.3504          | {'accuracy': 0.8349153941394964} |
-| 0.0408        | 10.0  | 6060 | 1.3709          | {'accuracy': 0.834089971110194}  |
+| 0.6087        | 1.0   | 606  | 0.6192          | {'accuracy': 0.8018984729673958} |
+| 0.4539        | 2.0   | 1212 | 0.5939          | {'accuracy': 0.8312009905076352} |
+| 0.3768        | 3.0   | 1818 | 0.7302          | {'accuracy': 0.8283120099050764} |
+| 0.3249        | 4.0   | 2424 | 0.7608          | {'accuracy': 0.8287247214197276} |
+| 0.1923        | 5.0   | 3030 | 0.8825          | {'accuracy': 0.8283120099050764} |
+| 0.1518        | 6.0   | 3636 | 1.0603          | {'accuracy': 0.8332645480808915} |
+| 0.1068        | 7.0   | 4242 | 1.1702          | {'accuracy': 0.8262484523318201} |
+| 0.0673        | 8.0   | 4848 | 1.2515          | {'accuracy': 0.8217086256706562} |
+| 0.072         | 9.0   | 5454 | 1.2673          | {'accuracy': 0.8303755674783326} |
+| 0.0315        | 10.0  | 6060 | 1.2612          | {'accuracy': 0.8287247214197276} |
 
 
 ### Framework versions

adapter_config.json

@@ -13,9 +13,9 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.01,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
@@ -23,7 +23,7 @@
     "score"
   ],
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ce4df02b671df5b1fc74b84d50fe2b11a1f534aa6f0a3b9fef7c2cdd3f8df28
-size 2521180
+oid sha256:4715f5f634610c3cd24cf5b2451f235c93fabf96f68857f0c3b1c4cdcd525a78
+size 2668644

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c5c670faed31eba17460eebd88193b5f5011a16dbf8f47809f1ef952d78a7e
+oid sha256:46087ffbe4bfd57a183234eb4985ff7233d21fe18345d3e06fca75c387414960
 size 5368