qualis2006/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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9675
-- Accuracy: {'accuracy': 0.884}
+- Loss: 1.0087
+- Accuracy: {'accuracy': 0.886}
 
 ## 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  | 0.4169          | {'accuracy': 0.872} |
-| 0.4168        | 2.0   | 500  | 0.4374          | {'accuracy': 0.877} |
-| 0.4168        | 3.0   | 750  | 0.5339          | {'accuracy': 0.885} |
-| 0.1878        | 4.0   | 1000 | 0.7017          | {'accuracy': 0.871} |
-| 0.1878        | 5.0   | 1250 | 0.7186          | {'accuracy': 0.882} |
-| 0.0609        | 6.0   | 1500 | 0.8245          | {'accuracy': 0.878} |
-| 0.0609        | 7.0   | 1750 | 0.8748          | {'accuracy': 0.88}  |
-| 0.0323        | 8.0   | 2000 | 0.9075          | {'accuracy': 0.889} |
-| 0.0323        | 9.0   | 2250 | 0.9559          | {'accuracy': 0.883} |
-| 0.0075        | 10.0  | 2500 | 0.9675          | {'accuracy': 0.884} |
+| No log        | 1.0   | 250  | 0.3263          | {'accuracy': 0.882} |
+| 0.4298        | 2.0   | 500  | 0.4513          | {'accuracy': 0.871} |
+| 0.4298        | 3.0   | 750  | 0.6971          | {'accuracy': 0.864} |
+| 0.2176        | 4.0   | 1000 | 0.6914          | {'accuracy': 0.877} |
+| 0.2176        | 5.0   | 1250 | 0.7609          | {'accuracy': 0.889} |
+| 0.095         | 6.0   | 1500 | 0.8447          | {'accuracy': 0.894} |
+| 0.095         | 7.0   | 1750 | 0.9361          | {'accuracy': 0.888} |
+| 0.024         | 8.0   | 2000 | 0.9976          | {'accuracy': 0.893} |
+| 0.024         | 9.0   | 2250 | 1.0071          | {'accuracy': 0.885} |
+| 0.0097        | 10.0  | 2500 | 1.0087          | {'accuracy': 0.886} |
 
 
 ### Framework versions
 
-- PEFT 0.5.0
-- Transformers 4.35.2
-- Pytorch 2.0.1+cu117
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+- Transformers 4.34.1
+- Pytorch 1.13.0+cu117
+- Datasets 2.14.6
+- Tokenizers 0.14.1

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df564a1db111c4ac2acc5e007a930ad3d0120fc392ba74b0d23637916d34d43a
-size 4155
+oid sha256:d909ac26098e3399c9ec4e8dbc84cd2e67f890ad772b23ebb53cb690a60c73e6
+size 4091