Ongoing research training transformer language models at scale, including: BERT & GPT-2
active 2023-08-16 → 2026-05-22 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1011 days from 2023-08-16 to 2026-05-22. Pushes: 21 total, peak 3 in a day. Pull requests: 22 total, peak 4 in a day. Issues: 0 total, peak 0 in a day. Comments: 117 total, peak 46 in a day. Stars: 1 total, peak 1 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| sourcery-ai[bot] | 117 | 0 | 0 | 109 |
| saforem2 | 47 | 21 | 21 | 4 |
| Copilot | 4 | 0 | 0 | 4 |
| kaushikvelusamy | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#18saforem22025-12-10 23:18
- Pull request#18saforem22025-11-18 17:29
- Pull request#14saforem22025-09-17 19:07
- Pull request#14saforem22025-09-17 19:07
- Issue comment#13sourcery-ai[bot]2024-12-25 14:45Pull in `microsoft-main-fpdt` branch from `argonne-lcf`
- Pull request#13saforem22024-12-25 14:45
- Pull request#12saforem22024-12-25 14:44
- Issue comment#12sourcery-ai[bot]2024-12-25 14:42Pull in upstream changes from `argonne-lcf` @ `main`
- Pull request#12saforem22024-12-25 14:42
- Issue comment#11sourcery-ai[bot]2024-12-06 05:04Adding the new feature of FPDT (#441)
- Pull request#11saforem22024-12-06 05:04
- Pull request#8saforem22024-11-15 14:29
- Pull request#7saforem22024-11-15 14:29
- Pull request#9saforem22024-11-15 14:28
- Issue comment#7saforem22024-11-07 18:26Refactor training pipeline and add Llama2 tokenizer support
- Pull request#10saforem22024-11-07 03:58
- Issue comment#10sourcery-ai[bot]2024-10-15 02:43Pull in from upstream
- Pull request#10saforem22024-10-15 02:43
- Issue comment#8saforem22024-10-12 18:32Refactor training script for improved logging and modularity
- Issue comment#9sourcery-ai[bot]2024-10-12 00:44Refactor training script for improved logging and modularity
- Pull request#9saforem22024-10-12 00:44
- Issue comment#8sourcery-ai[bot]2024-10-11 15:43Refactor training script for improved logging and modularity
- Pull request#8saforem22024-10-11 15:42
- Issue comment#7sourcery-ai[bot]2024-10-11 14:46Refactor training pipeline and add Llama2 tokenizer support
- Issue comment#7saforem22024-10-11 14:46Refactor training pipeline and add Llama2 tokenizer support
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.