# Language Modeling on SlimPajama latest (val) Source: [Language Modeling on SlimPajama latest (val)]() Collection index: [llms.txt]() Data updated: 2026-05-20T09:15:40.246Z Evaluation of language modeling performance, specifically reporting Validation Loss, on the latest validation split of the SlimPajama 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) | SlimPajama latest (val) | | Metric | Validation Loss | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 26 of 26 | | 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 - [Validation Loss](): Lower is better; unit: SCALAR. ## Recorded results | Method | Validation Loss | Result date | Report paper | | --- | --- | --- | --- | | LionMuon P=2 | 3.078 | Not recorded | 6a0d4028f984739ed67378dc | | LionMuon P=5 | 3.08 | Not recorded | 6a0d4028f984739ed67378dc | | LionMuon P=20 | 3.088 | Not recorded | 6a0d4028f984739ed67378dc | | LionMuon P=1 | 3.09 | Not recorded | 6a0d4028f984739ed67378dc | | SignMuon P=2 | 3.096 | Not recorded | 6a0d4028f984739ed67378dc | | SignMuon P=5 | 3.099 | Not recorded | 6a0d4028f984739ed67378dc | | LionMuon P=100 | 3.109 | Not recorded | 6a0d4028f984739ed67378dc | | LionMuon P=2 | 3.113 | Not recorded | 6a0d4028f984739ed67378dc | | Muon (P=1) | 3.12 | Not recorded | 6a0d4028f984739ed67378dc | | LionMuon P=5 | 3.12 | Not recorded | 6a0d4028f984739ed67378dc | | Lion | 3.123 | Not recorded | 6a0d4028f984739ed67378dc | | SignMuon P=20 | 3.124 | Not recorded | 6a0d4028f984739ed67378dc | | LionMuon P=1 | 3.125 | Not recorded | 6a0d4028f984739ed67378dc | | AdamW | 3.126 | Not recorded | 6a0d4028f984739ed67378dc | | SignMuon P=2 | 3.128 | Not recorded | 6a0d4028f984739ed67378dc | | SignMuon P=5 | 3.135 | Not recorded | 6a0d4028f984739ed67378dc | | LionMuon P=20 | 3.137 | Not recorded | 6a0d4028f984739ed67378dc | | Muon (P=1) | 3.139 | Not recorded | 6a0d4028f984739ed67378dc | | SignMuon P=100 | 3.14 | Not recorded | 6a0d4028f984739ed67378dc | | Signum | 3.145 | Not recorded | 6a0d4028f984739ed67378dc | | SignMuon P=20 | 3.163 | Not recorded | 6a0d4028f984739ed67378dc | | LionMuon P=100 | 3.165 | Not recorded | 6a0d4028f984739ed67378dc | | AdamW | 3.169 | Not recorded | 6a0d4028f984739ed67378dc | | Lion | 3.19 | Not recorded | 6a0d4028f984739ed67378dc | | SignMuon P=100 | 3.196 | Not recorded | 6a0d4028f984739ed67378dc | | Signum | 3.211 | Not recorded | 6a0d4028f984739ed67378dc | ### LionMuon P=2 Validation Loss: 3.078. Result ID: 6a0d7badfbc373592c05c71b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA","P":"2"}. This record does not assert independent reproduction. ### LionMuon P=5 Validation Loss: 3.08. Result ID: 6a0d7badfbc373592c05c71d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA","P":"5"}. This record does not assert independent reproduction. ### LionMuon P=20 Validation Loss: 3.088. Result ID: 6a0d7badfbc373592c05c71f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA","P":"20"}. This record does not assert independent reproduction. ### LionMuon P=1 Validation Loss: 3.09. Result ID: 6a0d7badfbc373592c05c719. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA","P":"1"}. This record does not assert independent reproduction. ### SignMuon P=2 Validation Loss: 3.096. Result ID: 6a0d7badfbc373592c05c711. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA","P":"2"}. This record does not assert independent reproduction. ### SignMuon P=5 Validation Loss: 3.099. Result ID: 6a0d7badfbc373592c05c713. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA","P":"5"}. This record does not assert independent reproduction. ### LionMuon P=100 Validation Loss: 3.109. Result ID: 6a0d7badfbc373592c05c721. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA","P":"100"}. This record does not assert independent reproduction. ### LionMuon P=2 Validation Loss: 3.113. Result ID: 6a0d7badfbc373592c05c71a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2","P":"2"}. This record does not assert independent reproduction. ### Muon (P=1) Validation Loss: 3.12. Result ID: 6a0d7badfbc373592c05c70f. [Reporting paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA","P":"1"}. This record does not assert independent reproduction. ### LionMuon P=5 Validation Loss: 3.12. Result ID: 6a0d7badfbc373592c05c71c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2","P":"5"}. This record does not assert independent reproduction. ### Lion Validation Loss: 3.123. Result ID: 6a0d7badfbc373592c05c70d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA"}. This record does not assert independent reproduction. ### SignMuon P=20 Validation Loss: 3.124. Result ID: 6a0d7badfbc373592c05c715. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA","P":"20"}. This record does not assert independent reproduction. ### LionMuon P=1 Validation Loss: 3.125. Result ID: 6a0d7badfbc373592c05c718. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2","P":"1"}. This record does not assert independent reproduction. ### AdamW Validation Loss: 3.126. Result ID: 6a0d7badfbc373592c05c709. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA"}. This record does not assert independent reproduction. ### SignMuon P=2 Validation Loss: 3.128. Result ID: 6a0d7badfbc373592c05c710. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2","P":"2"}. This record does not assert independent reproduction. ### SignMuon P=5 Validation Loss: 3.135. Result ID: 6a0d7badfbc373592c05c712. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2","P":"5"}. This record does not assert independent reproduction. ### LionMuon P=20 Validation Loss: 3.137. Result ID: 6a0d7badfbc373592c05c71e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2","P":"20"}. This record does not assert independent reproduction. ### Muon (P=1) Validation Loss: 3.139. Result ID: 6a0d7badfbc373592c05c70e. [Reporting paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2","P":"1"}. This record does not assert independent reproduction. ### SignMuon P=100 Validation Loss: 3.14. Result ID: 6a0d7badfbc373592c05c717. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA","P":"100"}. This record does not assert independent reproduction. ### Signum Validation Loss: 3.145. Result ID: 6a0d7badfbc373592c05c70b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"LLaMA"}. This record does not assert independent reproduction. ### SignMuon P=20 Validation Loss: 3.163. Result ID: 6a0d7badfbc373592c05c714. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2","P":"20"}. This record does not assert independent reproduction. ### LionMuon P=100 Validation Loss: 3.165. Result ID: 6a0d7badfbc373592c05c720. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2","P":"100"}. This record does not assert independent reproduction. ### AdamW Validation Loss: 3.169. Result ID: 6a0d7badfbc373592c05c708. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2"}. This record does not assert independent reproduction. ### Lion Validation Loss: 3.19. Result ID: 6a0d7badfbc373592c05c70c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2"}. This record does not assert independent reproduction. ### SignMuon P=100 Validation Loss: 3.196. Result ID: 6a0d7badfbc373592c05c716. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2","P":"100"}. This record does not assert independent reproduction. ### Signum Validation Loss: 3.211. Result ID: 6a0d7badfbc373592c05c70a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"124M","Architecture":"GPT-2"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.