Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- arcee-ai/Homunculus
|
| 4 |
+
---
|
| 5 |
+
vllm (pretrained=/root/autodl-tmp/Homunculus,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true,gpu_memory_utilization=0.5), 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|↑ |0.796|± |0.0255|
|
| 9 |
+
| | |strict-match | 5|exact_match|↑ |0.796|± |0.0255|
|
| 10 |
+
|
| 11 |
+
vllm (pretrained=/root/autodl-tmp/Homunculus,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true,gpu_memory_utilization=0.5), 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|↑ |0.796|± |0.0180|
|
| 15 |
+
| | |strict-match | 5|exact_match|↑ |0.792|± |0.0182|
|
| 16 |
+
|
| 17 |
+
vllm (pretrained=/root/autodl-tmp/Homunculus,add_bos_token=true,max_model_len=3048,dtype=bfloat16,trust_remote_code=true,gpu_memory_utilization=0.5), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: auto
|
| 18 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 19 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 20 |
+
|mmlu | 2|none | |acc |↑ |0.6480|± |0.0153|
|
| 21 |
+
| - humanities | 2|none | |acc |↑ |0.6769|± |0.0306|
|
| 22 |
+
| - other | 2|none | |acc |↑ |0.6718|± |0.0330|
|
| 23 |
+
| - social sciences| 2|none | |acc |↑ |0.7444|± |0.0315|
|
| 24 |
+
| - stem | 2|none | |acc |↑ |0.5509|± |0.0275|
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
vllm (pretrained=/root/autodl-tmp/Homunculus-90-128-4096-9.9999,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true,gpu_memory_utilization=0.4), 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|↑ |0.796|± |0.0255|
|
| 31 |
+
| | |strict-match | 5|exact_match|↑ |0.796|± |0.0255|
|
| 32 |
+
|
| 33 |
+
vllm (pretrained=/root/autodl-tmp/Homunculus-90-128-4096-9.9999,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true,gpu_memory_utilization=0.4), 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|↑ |0.796|± |0.0255|
|
| 37 |
+
| | |strict-match | 5|exact_match|↑ |0.796|± |0.0255|
|
| 38 |
+
|
| 39 |
+
vllm (pretrained=/root/autodl-tmp/Homunculus-90-128-4096-9.9999,add_bos_token=true,max_model_len=3048,dtype=bfloat16,trust_remote_code=true,gpu_memory_utilization=0.4), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: auto
|
| 40 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 41 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 42 |
+
|mmlu | 2|none | |acc |↑ |0.6538|± |0.0152|
|
| 43 |
+
| - humanities | 2|none | |acc |↑ |0.6872|± |0.0301|
|
| 44 |
+
| - other | 2|none | |acc |↑ |0.6769|± |0.0322|
|
| 45 |
+
| - social sciences| 2|none | |acc |↑ |0.7389|± |0.0314|
|
| 46 |
+
| - stem | 2|none | |acc |↑ |0.5614|± |0.0277|
|