base_model:
- IlyaGusev/saiga_nemo_12b
vllm (pretrained=/root/autodl-tmp/saiga_nemo_12b,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.808 | ± | 0.0250 |
| strict-match | 5 | exact_match | ↑ | 0.760 | ± | 0.0271 |
vllm (pretrained=/root/autodl-tmp/output88,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.784 | ± | 0.0261 |
| strict-match | 5 | exact_match | ↑ | 0.748 | ± | 0.0275 |
vllm (pretrained=/root/autodl-tmp/output8765,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.792 | ± | 0.0257 |
| strict-match | 5 | exact_match | ↑ | 0.760 | ± | 0.0271 |
vllm (pretrained=/root/autodl-tmp/output875,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.792 | ± | 0.0257 |
| strict-match | 5 | exact_match | ↑ | 0.768 | ± | 0.0268 |
vllm (pretrained=/root/autodl-tmp/output873,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.780 | ± | 0.0263 |
| strict-match | 5 | exact_match | ↑ | 0.736 | ± | 0.0279 |
vllm (pretrained=/root/autodl-tmp/output868,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.772 | ± | 0.0266 |
| strict-match | 5 | exact_match | ↑ | 0.728 | ± | 0.0282 |
vllm (pretrained=/root/autodl-tmp/saiga_nemo_12b,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.796 | ± | 0.0180 |
| strict-match | 5 | exact_match | ↑ | 0.734 | ± | 0.0198 |
vllm (pretrained=/root/autodl-tmp/output88,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.776 | ± | 0.0187 |
| strict-match | 5 | exact_match | ↑ | 0.722 | ± | 0.0201 |
vllm (pretrained=/root/autodl-tmp/output8765,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.790 | ± | 0.0182 |
| strict-match | 5 | exact_match | ↑ | 0.732 | ± | 0.0198 |
vllm (pretrained=/root/autodl-tmp/output875,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.778 | ± | 0.0186 |
| strict-match | 5 | exact_match | ↑ | 0.732 | ± | 0.0198 |
vllm (pretrained=/root/autodl-tmp/output873,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.774 | ± | 0.0187 |
| strict-match | 5 | exact_match | ↑ | 0.722 | ± | 0.0201 |
vllm (pretrained=/root/autodl-tmp/output868,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.772 | ± | 0.0188 |
| strict-match | 5 | exact_match | ↑ | 0.722 | ± | 0.0201 |