WillLoki/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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0322
-- Accuracy: {'accuracy': 0.876}
+- Loss: 0.7886
+- Accuracy: {'accuracy': 0.885}
 
 ## Model description
 
@@ -50,16 +50,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy            |
 |:-------------:|:-----:|:----:|:---------------:|:-------------------:|
-| No log        | 1.0   | 250  | 0.4027          | {'accuracy': 0.875} |
-| 0.4005        | 2.0   | 500  | 0.5017          | {'accuracy': 0.851} |
-| 0.4005        | 3.0   | 750  | 0.5624          | {'accuracy': 0.875} |
-| 0.1682        | 4.0   | 1000 | 0.7063          | {'accuracy': 0.869} |
-| 0.1682        | 5.0   | 1250 | 0.8427          | {'accuracy': 0.869} |
-| 0.0334        | 6.0   | 1500 | 0.9793          | {'accuracy': 0.875} |
-| 0.0334        | 7.0   | 1750 | 1.0155          | {'accuracy': 0.875} |
-| 0.0103        | 8.0   | 2000 | 1.0994          | {'accuracy': 0.867} |
-| 0.0103        | 9.0   | 2250 | 1.0249          | {'accuracy': 0.875} |
-| 0.012         | 10.0  | 2500 | 1.0322          | {'accuracy': 0.876} |
+| No log        | 1.0   | 250  | 0.3607          | {'accuracy': 0.871} |
+| 0.387         | 2.0   | 500  | 0.7780          | {'accuracy': 0.801} |
+| 0.387         | 3.0   | 750  | 0.6343          | {'accuracy': 0.874} |
+| 0.141         | 4.0   | 1000 | 0.6477          | {'accuracy': 0.889} |
+| 0.141         | 5.0   | 1250 | 0.6377          | {'accuracy': 0.884} |
+| 0.0721        | 6.0   | 1500 | 0.6829          | {'accuracy': 0.885} |
+| 0.0721        | 7.0   | 1750 | 0.7276          | {'accuracy': 0.88}  |
+| 0.0159        | 8.0   | 2000 | 0.7739          | {'accuracy': 0.884} |
+| 0.0159        | 9.0   | 2250 | 0.7852          | {'accuracy': 0.885} |
+| 0.0105        | 10.0  | 2500 | 0.7886          | {'accuracy': 0.885} |
 
 
 ### Framework versions

runs/Feb21_15-56-38_cde6f636587a/events.out.tfevents.1740153399.cde6f636587a.2156.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d33f9cbd8cad45672ff764b4fa282ab40368dc9f9d03ac16eb5685e83472e4
+size 5426

runs/Feb21_15-59-40_cde6f636587a/events.out.tfevents.1740153581.cde6f636587a.2156.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8eed25e0f78a6a19112832e51a7efd28d00376bdce00bfff842f652ddea423
+size 9274

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "[PAD]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3adeafe27ccc7f96dc49b451e982e7184c07640e6277f41ed7b9c7cd38e00e8b
+oid sha256:e9a97da8831fd82be470c276a593f01e461ce90b65d8b777f964d041b3dcae5d
 size 5432