Adding the Open Portuguese LLM Leaderboard Evaluation Results
#1
by
leaderboard-pt-pr-bot
- opened
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
-
base_model: NousResearch/Meta-Llama-3-8B
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: out-llama8b-alpaca-data-pt-br
|
| 8 |
results: []
|
|
@@ -150,3 +150,22 @@ The following hyperparameters were used during training:
|
|
| 150 |
- Pytorch 2.2.2+cu121
|
| 151 |
- Datasets 2.15.0
|
| 152 |
- Tokenizers 0.15.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
base_model: NousResearch/Meta-Llama-3-8B
|
| 6 |
model-index:
|
| 7 |
- name: out-llama8b-alpaca-data-pt-br
|
| 8 |
results: []
|
|
|
|
| 150 |
- Pytorch 2.2.2+cu121
|
| 151 |
- Datasets 2.15.0
|
| 152 |
- Tokenizers 0.15.0
|
| 153 |
+
|
| 154 |
+
|
| 155 |
+
# Open Portuguese LLM Leaderboard Evaluation Results
|
| 156 |
+
|
| 157 |
+
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/artificialguybr/llama3-8b-alpacadata-ptbr) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
|
| 158 |
+
|
| 159 |
+
| Metric | Value |
|
| 160 |
+
|--------------------------|---------|
|
| 161 |
+
|Average |**26.04**|
|
| 162 |
+
|ENEM Challenge (No Images)| 0|
|
| 163 |
+
|BLUEX (No Images) | 16.41|
|
| 164 |
+
|OAB Exams | 16.54|
|
| 165 |
+
|Assin2 RTE | 60.26|
|
| 166 |
+
|Assin2 STS | 1.74|
|
| 167 |
+
|FaQuAD NLI | 43.97|
|
| 168 |
+
|HateBR Binary | 33.46|
|
| 169 |
+
|PT Hate Speech Binary | 41.23|
|
| 170 |
+
|tweetSentBR | 20.73|
|
| 171 |
+
|