arm
ag_bart_mnli_n200_v1 · adjudicated
One config on ag_news_200, scored one way; its repeats averaged per item.
- dataset
- ag_news_200
- scored against
- gold/ag_news_200_adj1 gold
- goal
- News topic classification (AG News)
- runs
- 1
- headline
- correct 0.755
- last run
- 2026-10-25 15:10
01metrics
| metric | mean | items | better |
|---|---|---|---|
| correct | 0.755 | 200 | higher |
| answer_words | 1.000 | 200 | neutral |
| correct_after_repair | 0.000 | 200 | neutral |
| cost_usd | $0.000000 | 200 | lower |
| fmt_markdown | 0.000 | 200 | neutral |
| fmt_verbose | 0.000 | 200 | neutral |
| latency_ms | 1386.5 | 200 | lower |
| parsed | 1.000 | 200 | higher |
02cost and speed
- cost per item
- $0.000000
- speed per item
- p50 1,286 · p95 2,403 ms
Per item, over its items: cost as dollars and tokens (a local model is free but still uses tokens), speed as the median and the slow tail (p95). A goal that names this arm weighs them in its decision.
03runs
| run | made | items | cost | how |
|---|---|---|---|---|
ag_bart_mnli_n200_v1_20260927T085832Z | 2026-10-25 15:10 | 200 | $0.000000 | rescore |
04config
config ag_bart_mnli_n200_v1 · adapter examples/classification-ag-news/adapter.py · credentials are never shown
- device
cpu- family
bart- hypothesis_template
This news article is about {}.- model
facebook/bart-large-mnli- precision
fp32- price_tier
free- provider
hf_zeroshot
05conditions
- data.items_sha256
d7bf61eb3b27e79d492bbe5a445659813dfcacf6fadcae4d26255c45291bedd2- deployment.build
d7645e127eaf1aefc7862fd59a17a5aa8558b8ce- deployment.device
cpu- deployment.model
facebook/bart-large-mnli- deployment.quantization
fp32- deployment.source
adapter- fingerprint.version
5- library.numpy
1.26.4- library.openai
3.19.2- library.torch
2.2.2- library.transformers
4.55.4- machine.cpu_count
12- machine.label
mac-dev- machine.platform
Darwin/x86_64- machine.processor
i386- machine.python
3.11.8- machine.release
24.6.0- reference.sha256
636e963d2e500587d0642c40b48ac32040d237eb160bf00e20696ccea4649534- scorer.id
examples/classification-ag-news/adapter.py- scorer.sha256
ee92fea1f9920fd82b44a05ca1f35823d17f67adc3bf0bb73f07d357d0e583bd
06the same config, scored other ways
scored against silverscored by a judgescored against a label set, not a reference setunmarked rows are scored against gold
| arm | scored against | headline | mean |
|---|---|---|---|
| ag_bart_mnli_n200_v1 | gold/ag_news_200 gold | correct | 0.700 |
07rounds
- Round r1 of News topic classification (AG News), closed: one of its arms.