update model card README.md

README.md

@@ -2,25 +2,11 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
-datasets:
-- AlekseyKorshuk/83k-dataset-new-combined
 metrics:
 - accuracy
 model-index:
 - name: vicuna-13b-83k-dataset-new-combined
-  results:
-  - task:
-      name: Causal Language Modeling
-      type: text-generation
-    dataset:
-      name: AlekseyKorshuk/83k-dataset-new-combined
-      type: AlekseyKorshuk/83k-dataset-new-combined
-      config: null
-      split: None
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.012849514973853724
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vicuna-13b-83k-dataset-new-combined
 
-This model is a fine-tuned version of [eachadea/vicuna-13b-1.1](https://huggingface.co/eachadea/vicuna-13b-1.1) on the AlekseyKorshuk/83k-dataset-new-combined dataset.
+This model is a fine-tuned version of [eachadea/vicuna-13b-1.1](https://huggingface.co/eachadea/vicuna-13b-1.1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4365
-- Accuracy: 0.0128
-- Entropy: 1.5306
+- Loss: 1.5078
+- Accuracy: 0.0120
+- Entropy: 1.6010
 
 ## Model description
 
@@ -69,7 +55,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Entropy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------:|
-| 1.5481        | 1.0   | 5127 | 1.4365          | 0.0128   | 1.5306  |
+| 1.6308        | 1.0   | 5127 | 1.5078          | 0.0120   | 1.6010  |
 
 
 ### Framework versions