Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- LatitudeGames/Wayfarer-12B
|
| 4 |
+
---
|
| 5 |
+
vllm (pretrained=/root/autodl-tmp/Wayfarer-12B,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), 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|↑ |0.620|± |0.0308|
|
| 9 |
+
| | |strict-match | 5|exact_match|↑ |0.616|± |0.0308|
|
| 10 |
+
|
| 11 |
+
vllm (pretrained=/root/autodl-tmp/Wayfarer-12B,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), 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|↑ |0.604|± |0.0219|
|
| 15 |
+
| | |strict-match | 5|exact_match|↑ |0.606|± |0.0219|
|
| 16 |
+
|
| 17 |
+
vllm (pretrained=/root/autodl-tmp/Wayfarer-12B,add_bos_token=true,max_model_len=1024,tensor_parallel_size=2,dtype=bfloat16,enforce_eager=True), gen_kwargs: (None), limit: 6.0, num_fewshot: None, batch_size: 1
|
| 18 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 19 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 20 |
+
|mmlu | 2|none | |acc |↑ |0.6784|± |0.0237|
|
| 21 |
+
| - humanities | 2|none | |acc |↑ |0.6923|± |0.0451|
|
| 22 |
+
| - other | 2|none | |acc |↑ |0.6923|± |0.0538|
|
| 23 |
+
| - social sciences| 2|none | |acc |↑ |0.7917|± |0.0444|
|
| 24 |
+
| - stem | 2|none | |acc |↑ |0.5877|± |0.0442|
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
vllm (pretrained=/root/autodl-tmp/Wayfarer-12B-86,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 28 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 29 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 30 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.660|± |0.0300|
|
| 31 |
+
| | |strict-match | 5|exact_match|↑ |0.652|± |0.0302|
|
| 32 |
+
|
| 33 |
+
vllm (pretrained=/root/autodl-tmp/Wayfarer-12B-86,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
| 34 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 35 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 36 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.632|± |0.0216|
|
| 37 |
+
| | |strict-match | 5|exact_match|↑ |0.628|± |0.0216|
|
| 38 |
+
|
| 39 |
+
vllm (pretrained=/root/autodl-tmp/Wayfarer-12B-86,add_bos_token=true,max_model_len=800,tensor_parallel_size=2,dtype=bfloat16,enforce_eager=True), gen_kwargs: (None), limit: 7.0, num_fewshot: None, batch_size: 1
|
| 40 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 41 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 42 |
+
|mmlu | 2|none | |acc |↑ |0.6566|± |0.0220|
|
| 43 |
+
| - humanities | 2|none | |acc |↑ |0.6593|± |0.0444|
|
| 44 |
+
| - other | 2|none | |acc |↑ |0.6703|± |0.0491|
|
| 45 |
+
| - social sciences| 2|none | |acc |↑ |0.7738|± |0.0445|
|
| 46 |
+
| - stem | 2|none | |acc |↑ |0.5714|± |0.0391|
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
vllm (pretrained=/root/autodl-tmp/Wayfarer-12B-87,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|
| 50 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 51 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 52 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.660|± |0.0300|
|
| 53 |
+
| | |strict-match | 5|exact_match|↑ |0.664|± |0.0299|
|
| 54 |
+
|
| 55 |
+
vllm (pretrained=/root/autodl-tmp/Wayfarer-12B-87,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|
| 56 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|
| 57 |
+
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|
| 58 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.624|± |0.0217|
|
| 59 |
+
| | |strict-match | 5|exact_match|↑ |0.630|± |0.0216|
|
| 60 |
+
|
| 61 |
+
vllm (pretrained=/root/autodl-tmp/Wayfarer-12B-87,add_bos_token=true,max_model_len=800,tensor_parallel_size=2,dtype=bfloat16,enforce_eager=True), gen_kwargs: (None), limit: 7.0, num_fewshot: None, batch_size: 1
|
| 62 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 63 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 64 |
+
|mmlu | 2|none | |acc |↑ |0.6717|± |0.0217|
|
| 65 |
+
| - humanities | 2|none | |acc |↑ |0.6703|± |0.0426|
|
| 66 |
+
| - other | 2|none | |acc |↑ |0.6703|�� |0.0479|
|
| 67 |
+
| - social sciences| 2|none | |acc |↑ |0.7857|± |0.0418|
|
| 68 |
+
| - stem | 2|none | |acc |↑ |0.6015|± |0.0400|
|