Update README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,28 @@ base_model:
|
|
5 |
selected 70-1024-df10-u2k
|
6 |
|
7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
vllm (pretrained=/root/autodl-tmp/70-512-df10,add_bos_token=true,max_model_len=2048), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: 1
|
9 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
10 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
|
|
5 |
selected 70-1024-df10-u2k
|
6 |
|
7 |
|
8 |
+
vllm (pretrained=/root/autodl-tmp/Cydonia-24B-v2,add_bos_token=true,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
9 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
10 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
11 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.912|± | 0.018|
|
12 |
+
| | |strict-match | 5|exact_match|↑ |0.912|± | 0.018|
|
13 |
+
|
14 |
+
vllm (pretrained=/root/autodl-tmp/Cydonia-24B-v2,add_bos_token=true,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
15 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
16 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
17 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.904|± |0.0132|
|
18 |
+
| | |strict-match | 5|exact_match|↑ |0.894|± |0.0138|
|
19 |
+
|
20 |
+
vllm (pretrained=/root/autodl-tmp/Cydonia-24B-v2,add_bos_token=true,max_model_len=700,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|
21 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
22 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
23 |
+
|mmlu | 2|none | |acc |↑ |0.7942|± |0.0131|
|
24 |
+
| - humanities | 2|none | |acc |↑ |0.8205|± |0.0257|
|
25 |
+
| - other | 2|none | |acc |↑ |0.8103|± |0.0271|
|
26 |
+
| - social sciences| 2|none | |acc |↑ |0.8500|± |0.0257|
|
27 |
+
| - stem | 2|none | |acc |↑ |0.7298|± |0.0249|
|
28 |
+
|
29 |
+
|
30 |
vllm (pretrained=/root/autodl-tmp/70-512-df10,add_bos_token=true,max_model_len=2048), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: 1
|
31 |
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
32 |
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|