eleuther-pythia12b-hh-sft0 / sft-12b-eval-files /sft-pythia-12b-5shot-shelloutput.txt
lomahony's picture
Upload 8 files
11e25ea
bootstrapping for stddev: perplexity
hf (pretrained=lomahony/eleuther-pythia12b-hh-sft,parallelize=True), limit: None, num_fewshot: 5, batch_size: 4
| Task |Version|Filter| Metric | Value | |Stderr|
|--------------|-------|------|---------------|------:|---|-----:|
|arc_challenge |Yaml |none |acc | 0.3712|± |0.0141|
| | |none |acc_norm | 0.4010|± |0.0143|
|arc_easy |Yaml |none |acc | 0.7189|± |0.0092|
| | |none |acc_norm | 0.7285|± |0.0091|
|boolq |Yaml |none |acc | 0.7174|± |0.0079|
|hellaswag |Yaml |none |acc | 0.5076|± |0.0050|
| | |none |acc_norm | 0.6764|± |0.0047|
|lambada_openai|Yaml |none |perplexity | 4.3625|± |0.1008|
| | |none |acc | 0.6703|± |0.0065|
|openbookqa |Yaml |none |acc | 0.3120|± |0.0207|
| | |none |acc_norm | 0.4000|± |0.0219|
|piqa |Yaml |none |acc | 0.7688|± |0.0098|
| | |none |acc_norm | 0.7704|± |0.0098|
|sciq |Yaml |none |acc | 0.9470|± |0.0071|
| | |none |acc_norm | 0.9500|± |0.0069|
|wikitext |Yaml |none |word_perplexity|16.4972| | |
| | |none |byte_perplexity| 1.5874| | |
| | |none |bits_per_byte | 0.6667| | |
|winogrande |Yaml |none |acc | 0.6354|± |0.0135|