eleuther-pythia6.9b-hh-sft / sft-6.9b-eval-files /sft-pythia-6.9b-5shot-shelloutput.txt
lomahony's picture
Upload 8 files
8ca04ae
bootstrapping for stddev: perplexity
hf (pretrained=lomahony/eleuther-pythia6.9b-hh-sft), limit: None, num_fewshot: 5, batch_size: 4
| Task |Version|Filter| Metric | Value | |Stderr|
|--------------|-------|------|---------------|------:|---|-----:|
|arc_challenge |Yaml |none |acc | 0.3584|± |0.0140|
| | |none |acc_norm | 0.3848|± |0.0142|
|arc_easy |Yaml |none |acc | 0.7104|± |0.0093|
| | |none |acc_norm | 0.7134|± |0.0093|
|boolq |Yaml |none |acc | 0.6664|± |0.0082|
|hellaswag |Yaml |none |acc | 0.4829|± |0.0050|
| | |none |acc_norm | 0.6446|± |0.0048|
|lambada_openai|Yaml |none |perplexity | 5.0215|± |0.1228|
| | |none |acc | 0.6385|± |0.0067|
|openbookqa |Yaml |none |acc | 0.2760|± |0.0200|
| | |none |acc_norm | 0.3700|± |0.0216|
|piqa |Yaml |none |acc | 0.7688|± |0.0098|
| | |none |acc_norm | 0.7709|± |0.0098|
|sciq |Yaml |none |acc | 0.9520|± |0.0068|
| | |none |acc_norm | 0.9540|± |0.0066|
|wikitext |Yaml |none |word_perplexity|18.0722| | |
| | |none |byte_perplexity| 1.6115| | |
| | |none |bits_per_byte | 0.6884| | |
|winogrande |Yaml |none |acc | 0.6156|± |0.0137|