# Language Modeling on dolma books (val)

Source: [Language Modeling on dolma books (val)](<https://www.sota2.com/research/sota/language-modeling-on-dolma-books-val>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-12T07:45:23.834Z

Evaluation of Language Modeling performance on the validation split of the Dolma Books dataset, measured using Perplexity and relative change metrics.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Language Modeling |
| Dataset (including any stated split) | dolma books (val) |
| Metric | Perplexity |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Perplexity](<https://www.sota2.com/research/sota/language-modeling-on-dolma-books-val.md?metric=Perplexity>): Lower is better; unit: SCALAR.

- [Relative Change (%)](<https://www.sota2.com/research/sota/language-modeling-on-dolma-books-val.md?metric=Relative%20Change%20(%25)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Perplexity | Result date | Report paper |
| --- | --- | --- | --- |
| Hi-MoE-7B | 36.674 | Not recorded | 6a02b3f5dbc836b87d82457a |
| OLMoE-7B | 39.704 | Not recorded | 6a02b3f5dbc836b87d82457a |

### Hi-MoE-7B

Perplexity: 36.674. Result ID: 6a02da8547f34ce924e55dff.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b3f5dbc836b87d82457a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b3f5dbc836b87d82457a.md>)

Recorded evaluation configuration: {"transformer layers":"16","hidden size":"2048","experts":"64","routing":"top-k=8","grouping":"4 hierarchical groups","experts per group":"2"}. This record does not assert independent reproduction.

### OLMoE-7B

Perplexity: 39.704. Result ID: 6a02da8547f34ce924e55dfe.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b3f5dbc836b87d82457a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773e1e209131cea71f14.md>)

Recorded evaluation configuration: {"transformer layers":"16","hidden size":"2048","experts":"64","routing":"top-k=8"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.