25 lines
1.5 KiB
Plaintext
25 lines
1.5 KiB
Plaintext
bootstrapping for stddev: perplexity
|
|
hf (pretrained=lomahony/eleuther-pythia6.9b-hh-dpo), limit: None, num_fewshot: 0, batch_size: 4
|
|
| Task |Version|Filter| Metric | Value | |Stderr|
|
|
|--------------|-------|------|---------------|------:|---|-----:|
|
|
|arc_challenge |Yaml |none |acc | 0.3242|± |0.0137|
|
|
| | |none |acc_norm | 0.3541|± |0.0140|
|
|
|arc_easy |Yaml |none |acc | 0.6860|± |0.0095|
|
|
| | |none |acc_norm | 0.6149|± |0.0100|
|
|
|boolq |Yaml |none |acc | 0.6688|± |0.0082|
|
|
|hellaswag |Yaml |none |acc | 0.4910|± |0.0050|
|
|
| | |none |acc_norm | 0.6487|± |0.0048|
|
|
|lambada_openai|Yaml |none |perplexity | 3.7085|± |0.0866|
|
|
| | |none |acc | 0.6947|± |0.0064|
|
|
|openbookqa |Yaml |none |acc | 0.2760|± |0.0200|
|
|
| | |none |acc_norm | 0.3860|± |0.0218|
|
|
|piqa |Yaml |none |acc | 0.7622|± |0.0099|
|
|
| | |none |acc_norm | 0.7704|± |0.0098|
|
|
|sciq |Yaml |none |acc | 0.8940|± |0.0097|
|
|
| | |none |acc_norm | 0.8300|± |0.0119|
|
|
|wikitext |Yaml |none |word_perplexity|18.1988| | |
|
|
| | |none |byte_perplexity| 1.6133| | |
|
|
| | |none |bits_per_byte | 0.6900| | |
|
|
|winogrande |Yaml |none |acc | 0.6235|± |0.0136|
|
|
|