arm
fn_glm_l_n200_v1
One config on few_nerd_280, scored one way; its repeats averaged per item.
- dataset
- few_nerd_280
- scored against
- gold/few_nerd_280 gold
- goal
- Named-entity extraction (Few-NERD)
- runs
- 1
- headline
- f1 0.566
- last run
- 2026-09-28 10:50
Inspect itAgainst the baselineWith the 28 arms scored the same way
01metrics
| metric | mean | items | better |
|---|---|---|---|
| f1 | 0.566 | 280 | higher |
| cost_usd | $0.000365 | 280 | lower |
| fn | 1.089 | 280 | neutral |
| fp | 1.150 | 280 | neutral |
| latency_ms | 3013.7 | 280 | lower |
| n_gold | 2.736 | 280 | neutral |
| n_predicted | 2.796 | 280 | neutral |
| parsed | 0.889 | 280 | higher |
| precision | 0.546 | 280 | higher |
| reasoning_tokens | 0.000 | 280 | neutral |
| recall | 0.612 | 280 | higher |
| tokens_in | 116.4 | 280 | lower |
| tokens_out | 136.0 | 280 | lower |
| tp | 1.646 | 280 | neutral |
| truncated | 0.114 | 280 | neutral |
| type_penalty | 0.087 | 280 | neutral |
| untyped_f1 | 0.653 | 280 | higher |
| untyped_fn | 0.761 | 280 | neutral |
| untyped_fp | 0.821 | 280 | neutral |
| untyped_tp | 1.975 | 280 | neutral |
02cost and speed
- cost per item
- $0.000365 · 252 tok
- speed per item
- p50 2,096 · p95 8,249 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 |
|---|---|---|---|---|
fn_glm_l_n200_v1_20260928T105047Z | 2026-09-28 10:50 | 280 | $0.102317 | rescore |
04config
config fn_glm_l_n200_v1 · adapter examples/ner-few-nerd/adapter.py · credentials are never shown
- family
glm- max_tokens
600- model
eval-glm-5- price_tier
large- prompt_file
prompt.txt- provider
litellm- reasoning
{"enabled": false}- temperature
0.0- usd_per_mtok_in
0.35- usd_per_mtok_out
1.4
05conditions
- data.items_sha256
95a1b962707368cce0895143e73b63cd9884425502997ee1a93df99f97e2cad7- deployment.model
eval-glm-5- deployment.source
adapter- fingerprint.version
5- library.datasets
5.0.1- library.numpy
1.26.4- library.openai
3.19.2- library.scikit-learn
1.9.1- 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
7cdd09fe0084ba29c616ab65fbfa08bf149e9006819641e9e91fe502ebe15a2b- scorer.id
examples/ner-few-nerd/adapter.py- scorer.sha256
d147da55107305786c21b75ac87d748b9ea4fb3e57ebdff622aafecd826559b1
06rounds
- Round r1 of Named-entity extraction (Few-NERD), closed: one of its arms.