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

README.md

@@ -8,7 +8,6 @@ metrics:
 model-index:
 - name: distilbert-base-uncased-lora-text-classification
   results: []
-library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,8 +17,8 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0680
-- Accuracy: {'accuracy': 0.885}
+- Loss: 1.0684
+- Accuracy: {'accuracy': 0.879}
 
 ## Model description
 
@@ -50,22 +49,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy            |
 |:-------------:|:-----:|:----:|:---------------:|:-------------------:|
-| No log        | 1.0   | 250  | 0.3690          | {'accuracy': 0.87}  |
-| 0.3946        | 2.0   | 500  | 0.5006          | {'accuracy': 0.849} |
-| 0.3946        | 3.0   | 750  | 0.5917          | {'accuracy': 0.865} |
-| 0.1803        | 4.0   | 1000 | 0.7957          | {'accuracy': 0.868} |
-| 0.1803        | 5.0   | 1250 | 0.7798          | {'accuracy': 0.872} |
-| 0.0779        | 6.0   | 1500 | 0.9091          | {'accuracy': 0.877} |
-| 0.0779        | 7.0   | 1750 | 1.0116          | {'accuracy': 0.877} |
-| 0.0156        | 8.0   | 2000 | 1.1076          | {'accuracy': 0.872} |
-| 0.0156        | 9.0   | 2250 | 1.0598          | {'accuracy': 0.885} |
-| 0.0085        | 10.0  | 2500 | 1.0680          | {'accuracy': 0.885} |
+| No log        | 1.0   | 250  | 0.4266          | {'accuracy': 0.87}  |
+| 0.4232        | 2.0   | 500  | 0.4260          | {'accuracy': 0.88}  |
+| 0.4232        | 3.0   | 750  | 0.5071          | {'accuracy': 0.885} |
+| 0.2213        | 4.0   | 1000 | 0.7424          | {'accuracy': 0.875} |
+| 0.2213        | 5.0   | 1250 | 0.7885          | {'accuracy': 0.881} |
+| 0.067         | 6.0   | 1500 | 0.9312          | {'accuracy': 0.872} |
+| 0.067         | 7.0   | 1750 | 0.9669          | {'accuracy': 0.874} |
+| 0.0238        | 8.0   | 2000 | 1.0856          | {'accuracy': 0.874} |
+| 0.0238        | 9.0   | 2250 | 1.0637          | {'accuracy': 0.88}  |
+| 0.0066        | 10.0  | 2500 | 1.0684          | {'accuracy': 0.879} |
 
 
 ### Framework versions
 
-- PEFT 0.5.0
 - Transformers 4.32.1
-- Pytorch 2.1.0.dev20230905
+- Pytorch 2.0.1
 - Datasets 2.14.4
-- Tokenizers 0.13.3
+- Tokenizers 0.13.2

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a37fe8a90cd601e561e11156e8dc205cb7dc3c27fd68c66a9b7d3008be46f0
-size 4600
+oid sha256:a59b2d73bb0c596355af33595ac92a84ab94f22a9402c14fb809d5045d017e1a
+size 4091