Comment
runs.summary["evals_table"]
- 1 of 130
# system Given a text representing speech of manga in Japanese, generate a high-quality English translation that accurately conveys the meaning and emotion of the original text. Please do not provide any explanation in the output other than the translation itself. # user ...私の夢は # assistant ['My dream is...']
False
markdown
correct
expected
picked
options
completion_fns
eval_name
completion_cost
registry_version
override_prompt
sacrebleu_sentence_score
modelgraded_run_id
modelgraded_event_id
modelgraded_type
modelgraded_created_by
modelgraded_created_at
modelgraded_prompt
modelgraded_sampled
modelgraded_usage_total_tokens
modelgraded_extended_convo
modelgraded_chatml_viz
modelgraded_markdown
1
[{"role": "system", "content": "Given a text representing speech of manga in Japanese, generate a high-quality English translation that accurately conveys the meaning and emotion of the original text. Please do not provide any explanation in the output other than the translation itself."}, {"role": "user", "content": "...\u79c1\u306e\u5922\u306f"}]
prompt
Run set
304
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/wandb/jobs/reports/Weave-evals_table-23-05-11-20-14-37---Vmlldzo0MzM1MzUz