End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-uncased
+license: mit
+base_model: microsoft/deberta-v3-small
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # copilot_relex_v1
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0067
 
@@ -40,27 +40,20 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 172  | 0.0133          |
-| No log        | 2.0   | 344  | 0.0106          |
-| 0.0204        | 3.0   | 516  | 0.0090          |
-| 0.0204        | 4.0   | 688  | 0.0078          |
-| 0.0204        | 5.0   | 860  | 0.0072          |
-| 0.0125        | 6.0   | 1032 | 0.0071          |
-| 0.0125        | 7.0   | 1204 | 0.0072          |
-| 0.0125        | 8.0   | 1376 | 0.0068          |
-| 0.0113        | 9.0   | 1548 | 0.0066          |
-| 0.0113        | 10.0  | 1720 | 0.0067          |
+| No log        | 1.0   | 172  | 0.0072          |
+| No log        | 2.0   | 344  | 0.0068          |
+| 0.0129        | 3.0   | 516  | 0.0067          |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.16.1
+- Datasets 2.17.0
 - Tokenizers 0.15.1