Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- mistralai/Magistral-Small-2506
|
| 4 |
+
---
|
| 5 |
+
vllm (pretrained=/root/autodl-tmp/Magistral-Small-2506,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 6 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 7 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 8 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.924|± |0.0168|
|
| 9 |
+
| | |strict-match | 5|exact_match|↑ |0.920|± |0.0172|
|
| 10 |
+
|
| 11 |
+
vllm (pretrained=/root/autodl-tmp/Magistral-Small-2506,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
| 12 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 13 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 14 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.916|± |0.0124|
|
| 15 |
+
| | |strict-match | 5|exact_match|↑ |0.912|± |0.0127|
|
| 16 |
+
|
| 17 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 18 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 19 |
+
|mmlu | 2|none | |acc |↑ |0.7766|± |0.0134|
|
| 20 |
+
| - humanities | 2|none | |acc |↑ |0.8154|± |0.0259|
|
| 21 |
+
| - other | 2|none | |acc |↑ |0.8308|± |0.0266|
|
| 22 |
+
| - social sciences| 2|none | |acc |↑ |0.8056|± |0.0282|
|
| 23 |
+
| - stem | 2|none | |acc |↑ |0.6947|± |0.0256|
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
vllm (pretrained=/root/autodl-tmp/root90-256-4096-9.9999,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 27 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 28 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 29 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.908|± |0.0183|
|
| 30 |
+
| | |strict-match | 5|exact_match|↑ |0.904|± |0.0187|
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
llm (pretrained=/root/autodl-tmp/root90-128-4096-9.9999,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 34 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 35 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 36 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.924|± |0.0168|
|
| 37 |
+
| | |strict-match | 5|exact_match|↑ |0.920|± |0.0172|
|
| 38 |
+
|
| 39 |
+
vllm (pretrained=/root/autodl-tmp/root90-128-4096-9.9999,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
| 40 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 41 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 42 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.912|± |0.0127|
|
| 43 |
+
| | |strict-match | 5|exact_match|↑ |0.906|± |0.0131|
|
| 44 |
+
|
| 45 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 46 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 47 |
+
|mmlu | 2|none | |acc |↑ |0.7754|± |0.0135|
|
| 48 |
+
| - humanities | 2|none | |acc |↑ |0.7949|± |0.0268|
|
| 49 |
+
| - other | 2|none | |acc |↑ |0.8103|± |0.0278|
|
| 50 |
+
| - social sciences| 2|none | |acc |↑ |0.8278|± |0.0273|
|
| 51 |
+
| - stem | 2|none | |acc |↑ |0.7053|± |0.0254|
|