Hugging Face's logo

UCLA-AGI
/
zephyr-7b-sft-full-SPIN-iter1

Text Generation
Transformers
Safetensors
English
mistral
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
3
ydeng9 commited on
Commit
1ce5859
•
1 Parent(s): 4b074c9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -11
README.md CHANGED
@@ -35,6 +35,18 @@ The following hyperparameters were used during training:
35
  - lr_scheduler_type: linear
36
  - lr_scheduler_warmup_ratio: 0.1
37
  - num_epochs: 2.0
 
 
 
 
 
 
 
 
 
 
 
 
38
 
39
  ## Citation
40
  ```
@@ -46,14 +58,4 @@ The following hyperparameters were used during training:
46
  archivePrefix={arXiv},
47
  primaryClass={cs.LG}
48
  }
49
- ```
50
- # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
51
- | Metric | Value |
52
- |-----------------------|---------------------------|
53
- | Avg. | 62.86 |
54
- | ARC (25-shot) | 65.87 |
55
- | HellaSwag (10-shot) | 85.44 |
56
- | MMLU (5-shot) | 60.95 |
57
- | TruthfulQA (0-shot) | 57.39 |
58
- | Winogrande (5-shot) | 76.64 |
59
- | GSM8K (5-shot) | 30.86 |
 
35
  - lr_scheduler_type: linear
36
  - lr_scheduler_warmup_ratio: 0.1
37
  - num_epochs: 2.0
38
+
39
+ ## [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
40
+ Detailed results can be found
41
+ | Metric | Value |
42
+ |-----------------------|---------------------------|
43
+ | Avg. | 62.86 |
44
+ | ARC (25-shot) | 65.87 |
45
+ | HellaSwag (10-shot) | 85.44 |
46
+ | MMLU (5-shot) | 60.95 |
47
+ | TruthfulQA (0-shot) | 57.39 |
48
+ | Winogrande (5-shot) | 76.64 |
49
+ | GSM8K (5-shot) | 30.86 |
50
 
51
  ## Citation
52
  ```
 
58
  archivePrefix={arXiv},
59
  primaryClass={cs.LG}
60
  }
61
+ ```