# Language Modeling on Shakespeare (non-i.i.d.)

Source: [Language Modeling on Shakespeare (non-i.i.d.)](<https://www.sota2.com/research/sota/language-modeling-on-shakespeare-non-i-i-d>)

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

Data updated: 2026-02-26T06:06:15.119Z

Evaluation of language modeling performance on the non-i.i.d. split of the Shakespeare dataset.

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) | Shakespeare (non-i.i.d.) |
| Metric | Test Error |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [Test Error](<https://www.sota2.com/research/sota/language-modeling-on-shakespeare-non-i-i-d.md?metric=Test%20Error>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Test Error | Result date | Report paper |
| --- | --- | --- | --- |
| FedEx | 45.24 | Not recorded | 68fa6b2a1e209131cea2c751 |
| FedEx | 45.89 | Not recorded | 68fa6b2a1e209131cea2c751 |
| SHA (server & client) | 46.79 | Not recorded | 68fa6b2a1e209131cea2c751 |
| SHA (server & client) | 48.04 | Not recorded | 68fa6b2a1e209131cea2c751 |
| FedEx | 56.48 | Not recorded | 68fa6b2a1e209131cea2c751 |
| FedEx | 57.7 | Not recorded | 68fa6b2a1e209131cea2c751 |
| RS (server & client) | 61.71 | Not recorded | 68fa6b2a1e209131cea2c751 |
| RS (server & client) | 64.36 | Not recorded | 68fa6b2a1e209131cea2c751 |

### FedEx

Test Error: 45.24. Result ID: 698e63caffc3901de09d31a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

[Implementation](<https://github.com/mkhodak/fedex>)

Recorded evaluation configuration: {"Wrapper method":"Successive Halving (SHA)","Target model":"global"}. This record does not assert independent reproduction.

### FedEx

Test Error: 45.89. Result ID: 698e63caffc3901de09d31a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

[Implementation](<https://github.com/mkhodak/fedex>)

Recorded evaluation configuration: {"Wrapper method":"Successive Halving (SHA)","Target model":"personalized"}. This record does not assert independent reproduction.

### SHA (server & client)

Test Error: 46.79. Result ID: 698e63caffc3901de09d31a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa647b1e209131cea04b80.md>)

Recorded evaluation configuration: {"Wrapper method":"Successive Halving (SHA)","Target model":"global"}. This record does not assert independent reproduction.

### SHA (server & client)

Test Error: 48.04. Result ID: 698e63caffc3901de09d31a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa647b1e209131cea04b80.md>)

Recorded evaluation configuration: {"Wrapper method":"Successive Halving (SHA)","Target model":"personalized"}. This record does not assert independent reproduction.

### FedEx

Test Error: 56.48. Result ID: 698e63caffc3901de09d31a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

[Implementation](<https://github.com/mkhodak/fedex>)

Recorded evaluation configuration: {"Wrapper method":"Random Search (RS)","Target model":"personalized"}. This record does not assert independent reproduction.

### FedEx

Test Error: 57.7. Result ID: 698e63caffc3901de09d319f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

[Implementation](<https://github.com/mkhodak/fedex>)

Recorded evaluation configuration: {"Wrapper method":"Random Search (RS)","Target model":"global"}. This record does not assert independent reproduction.

### RS (server & client)

Test Error: 61.71. Result ID: 698e63caffc3901de09d31a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

Recorded evaluation configuration: {"Wrapper method":"Random Search (RS)","Target model":"personalized"}. This record does not assert independent reproduction.

### RS (server & client)

Test Error: 64.36. Result ID: 698e63caffc3901de09d319e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2a1e209131cea2c751.md>)

Recorded evaluation configuration: {"Wrapper method":"Random Search (RS)","Target model":"global"}. This record does not assert independent reproduction.

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