eleuther-pythia12b-hh-sft / sft-pythia-12b-0shot-shelloutput.txt
lomahony's picture
Upload 8 files
e12cdad
bootstrapping for stddev: perplexity
hf (pretrained=lomahony/eleuther-pythia12b-hh-sft,parallelize=True), limit: None, num_fewshot: 0, batch_size: 16
| Task |Version|Filter| Metric | Value | |Stderr|
|--------------|-------|------|---------------|------:|---|-----:|
|arc_challenge |Yaml |none |acc | 0.3106|± |0.0135|
| | |none |acc_norm | 0.3464|± |0.0139|
|arc_easy |Yaml |none |acc | 0.7012|± |0.0094|
| | |none |acc_norm | 0.6187|± |0.0100|
|boolq |Yaml |none |acc | 0.6954|± |0.0080|
|hellaswag |Yaml |none |acc | 0.5056|± |0.0050|
| | |none |acc_norm | 0.6668|± |0.0047|
|lambada_openai|Yaml |none |perplexity | 3.5325|± |0.0776|
| | |none |acc | 0.7105|± |0.0063|
|openbookqa |Yaml |none |acc | 0.2760|± |0.0200|
| | |none |acc_norm | 0.3820|± |0.0218|
|piqa |Yaml |none |acc | 0.7633|± |0.0099|
| | |none |acc_norm | 0.7644|± |0.0099|
|sciq |Yaml |none |acc | 0.9060|± |0.0092|
| | |none |acc_norm | 0.8440|± |0.0115|
|wikitext |Yaml |none |word_perplexity|16.5611| | |
| | |none |byte_perplexity| 1.5884| | |
| | |none |bits_per_byte | 0.6676| | |
|winogrande |Yaml |none |acc | 0.6346|± |0.0135|