pszemraj leaderboard-pr-bot commited on
Commit
3edd480
1 Parent(s): a833c5c

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (55a2ea6591c28ffe4b65b9cf6599ff0a0daff61c)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -110,4 +110,17 @@ The following hyperparameters were used during training:
110
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
111
  - lr_scheduler_type: cosine
112
  - lr_scheduler_warmup_ratio: 0.03
113
- - num_epochs: 2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
110
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
111
  - lr_scheduler_type: cosine
112
  - lr_scheduler_warmup_ratio: 0.03
113
+ - num_epochs: 2.0
114
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
115
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_BEE-spoke-data__TinyLlama-1.1bee)
116
+
117
+ | Metric | Value |
118
+ |-----------------------|---------------------------|
119
+ | Avg. | 29.15 |
120
+ | ARC (25-shot) | 30.55 |
121
+ | HellaSwag (10-shot) | 51.8 |
122
+ | MMLU (5-shot) | 24.25 |
123
+ | TruthfulQA (0-shot) | 39.01 |
124
+ | Winogrande (5-shot) | 54.46 |
125
+ | GSM8K (5-shot) | 0.23 |
126
+ | DROP (3-shot) | 3.74 |