arm
cnn_bart_l_xsum_dm200_v1
One config on cnn_dailymail_dm200, scored one way; its repeats averaged per item.
- dataset
- cnn_dailymail_dm200
- scored against
- gold/cnn_dailymail_dm200 gold
- goal
- Short news summaries (CNN)
- runs
- 1
- headline
- coverage 0.152
- last run
- 2026-10-14 15:00
01metrics
| metric | mean | items | better |
|---|---|---|---|
| coverage | 0.152 | 200 | higher |
| compression | 0.039 | 200 | neutral |
| concision | 0.382 | 200 | higher |
| cost_usd | $0.000000 | 200 | lower |
| fmt_bullets | 0.000 | 200 | neutral |
| fmt_label | 0.000 | 200 | neutral |
| fmt_markdown | 0.000 | 200 | neutral |
| fmt_narration | 0.005 | 200 | neutral |
| fmt_overlong | 0.000 | 200 | neutral |
| fmt_paragraphs | 0.000 | 200 | neutral |
| grounding | 0.551 | 200 | higher |
| input_truncated | 0.290 | 200 | neutral |
| latency_ms | 5362.0 | 200 | lower |
| length_vs_reference | 0.384 | 200 | neutral |
| reference_words | 57.9 | 200 | neutral |
| rouge1 | 0.247 | 200 | higher |
| rougeLsum | 0.212 | 200 | higher |
| summary_words | 20.3 | 200 | neutral |
| tokens_in | 846.7 | 200 | lower |
| tokens_out | 26.9 | 200 | lower |
02cost and speed
- cost per item
- $0.000000 · 874 tok
- speed per item
- p50 5,103 · p95 8,017 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 |
|---|---|---|---|---|
cnn_bart_l_xsum_dm200_v1_20261014T144002Z | 2026-10-14 15:00 | 200 | $0.000000 | measured |
04config
config cnn_bart_l_xsum_dm200_v1 · adapter examples/summarization-cnn-dailymail/adapter.py · credentials are never shown
- device
cpu- early_stopping
true- family
bart- max_length
62- min_length
11- model
facebook/bart-large-xsum- no_repeat_ngram_size
3- num_beams
6- precision
fp32- price_tier
free- provider
hf_local
05conditions
- data.items_sha256
0cf85d1eb3b9176ac6e49f3ab83761e271aeb0f87b18709f230815a4e213865b- deployment.build
2179ab81d3f133e639f2957aec5380e9d56b2783- deployment.device
cpu- deployment.model
facebook/bart-large-xsum- deployment.quantization
fp32- deployment.source
adapter- fingerprint.version
5- library.numpy
2.4.6- library.openai
3.19.2- library.rouge-score
0.1.2- library.torch
2.14.0- library.transformers
4.55.4- machine.cpu_count
4- machine.platform
Linux/x86_64- machine.processor
x86_64- machine.python
3.11.15- machine.release
6.18.44-fc-v114- reference.sha256
7fc293bc2d9661e3b23d2bb1af8981f5e4bab10e4ab3c83b36e03f571fcef8cc- scorer.id
examples/summarization-cnn-dailymail/adapter.py- scorer.sha256
2955537740425c943bf6eb342ebf0c2dac2379d13b4e32ec5005d27227be6f15