Commit
•
ad4fc9c
1
Parent(s):
7658da5
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
@@ -3,13 +3,13 @@ license: gpl-3.0
|
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
6 |
base_model: nisten/shqiponja-15b-v1
|
7 |
model-index:
|
8 |
- name: shqiponja-15
|
9 |
results: []
|
10 |
-
datasets:
|
11 |
-
- iamshnoo/alpaca-cleaned-albanian
|
12 |
-
- noxneural/lilium_albanicum_eng_alb
|
13 |
---
|
14 |
|
15 |
|
@@ -84,4 +84,17 @@ The following hyperparameters were used during training:
|
|
84 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
85 |
- lr_scheduler_type: cosine
|
86 |
- lr_scheduler_warmup_steps: 10
|
87 |
-
- num_epochs: 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- iamshnoo/alpaca-cleaned-albanian
|
8 |
+
- noxneural/lilium_albanicum_eng_alb
|
9 |
base_model: nisten/shqiponja-15b-v1
|
10 |
model-index:
|
11 |
- name: shqiponja-15
|
12 |
results: []
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
|
|
|
84 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
85 |
- lr_scheduler_type: cosine
|
86 |
- lr_scheduler_warmup_steps: 10
|
87 |
+
- num_epochs: 3
|
88 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
89 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nisten__shqiponja-15b-v1)
|
90 |
+
|
91 |
+
| Metric |Value|
|
92 |
+
|---------------------------------|----:|
|
93 |
+
|Avg. |71.03|
|
94 |
+
|AI2 Reasoning Challenge (25-Shot)|66.38|
|
95 |
+
|HellaSwag (10-Shot) |85.26|
|
96 |
+
|MMLU (5-Shot) |64.62|
|
97 |
+
|TruthfulQA (0-shot) |56.81|
|
98 |
+
|Winogrande (5-shot) |84.06|
|
99 |
+
|GSM8k (5-shot) |69.07|
|
100 |
+
|