erwinyonata/distilbert-base-uncased-lora-text-classification

README.md

@@ -18,8 +18,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8022
-- Accuracy: {'accuracy': 0.896}
+- Loss: 0.7392
+- Accuracy: {'accuracy': 0.901}
 
 ## Model description
 
@@ -50,16 +50,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy            |
 |:-------------:|:-----:|:----:|:---------------:|:-------------------:|
-| No log        | 1.0   | 125  | 0.2812          | {'accuracy': 0.891} |
-| No log        | 2.0   | 250  | 0.4049          | {'accuracy': 0.885} |
-| No log        | 3.0   | 375  | 0.4661          | {'accuracy': 0.888} |
-| 0.2488        | 4.0   | 500  | 0.5566          | {'accuracy': 0.896} |
-| 0.2488        | 5.0   | 625  | 0.5952          | {'accuracy': 0.894} |
-| 0.2488        | 6.0   | 750  | 0.7069          | {'accuracy': 0.899} |
-| 0.2488        | 7.0   | 875  | 0.7450          | {'accuracy': 0.89}  |
-| 0.0289        | 8.0   | 1000 | 0.7803          | {'accuracy': 0.892} |
-| 0.0289        | 9.0   | 1125 | 0.7954          | {'accuracy': 0.894} |
-| 0.0289        | 10.0  | 1250 | 0.8022          | {'accuracy': 0.896} |
+| No log        | 1.0   | 125  | 0.2589          | {'accuracy': 0.896} |
+| No log        | 2.0   | 250  | 0.4331          | {'accuracy': 0.868} |
+| No log        | 3.0   | 375  | 0.3884          | {'accuracy': 0.901} |
+| 0.2587        | 4.0   | 500  | 0.4673          | {'accuracy': 0.895} |
+| 0.2587        | 5.0   | 625  | 0.6184          | {'accuracy': 0.899} |
+| 0.2587        | 6.0   | 750  | 0.6478          | {'accuracy': 0.902} |
+| 0.2587        | 7.0   | 875  | 0.7249          | {'accuracy': 0.899} |
+| 0.0338        | 8.0   | 1000 | 0.7446          | {'accuracy': 0.893} |
+| 0.0338        | 9.0   | 1125 | 0.7290          | {'accuracy': 0.9}   |
+| 0.0338        | 10.0  | 1250 | 0.7392          | {'accuracy': 0.901} |
 
 
 ### Framework versions

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466af977ca9ac3dfe66c2c2b5c2a2fcae2a43b1a73357167a5a4f91f46ba0333
+oid sha256:dd749f9ca32fa12b8db2a348b1a183de1d99e8908a7ef85e2235061620366a4b
 size 5048