update model card README.md

README.md

@@ -1,5 +1,5 @@
 ---
-license: mit
+license: apache-2.0
 tags:
 - generated_from_trainer
 metrics:
@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sentence-compression
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3054
-- Accuracy: 0.8802
-- F1: 0.7439
-- Precision: 0.7661
-- Recall: 0.7229
+- Loss: 0.3786
+- Accuracy: 0.8322
+- F1: 0.7306
+- Precision: 0.7399
+- Recall: 0.7215
 
 ## Model description
 
@@ -55,14 +55,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.317         | 1.0   | 200  | 0.3566          | 0.8513   | 0.6227 | 0.7998    | 0.5099 |
-| 0.346         | 2.0   | 400  | 0.5853          | 0.7919   | 0.6724 | 0.5413    | 0.8875 |
-| 0.2365        | 3.0   | 600  | 0.3054          | 0.8802   | 0.7439 | 0.7661    | 0.7229 |
+| 0.6327        | 1.0   | 50   | 0.5976          | 0.7034   | 0.1331 | 0.8506    | 0.0722 |
+| 0.5127        | 2.0   | 100  | 0.4569          | 0.7883   | 0.6009 | 0.7411    | 0.5054 |
+| 0.42          | 3.0   | 150  | 0.3786          | 0.8322   | 0.7306 | 0.7399    | 0.7215 |
 
 
 ### Framework versions
 
 - Transformers 4.12.5
-- Pytorch 1.10.0+cu111
+- Pytorch 1.10.0+cu113
 - Datasets 1.16.1
 - Tokenizers 0.10.3