From 6b40978443f0c5cb3986453caa6f68e202550c42 Mon Sep 17 00:00:00 2001 From: Will DePue Date: Thu, 19 Mar 2026 14:02:51 -0700 Subject: Update README.md --- README.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 1dd7d8c..f9550cf 100644 --- a/README.md +++ b/README.md @@ -28,11 +28,12 @@ Happy training! ## Leaderboard -| Rank | Run | Score | Author | Summary | Date | Info | -|-----:|-----|------:|--------|---------|------|------| -| 1 | 2048 seq length | 1.206 | Spokane Way | 2048 seq length (train + val) | 2026-03-18 | [info](records/track_10min_16mb/2026-03-18_LongContextSeq2048/README.md) | -| 2 | fp16 Embed | 1.2197 | Renier Velazco | FP16 Tied Embedding + LR/Warmdown Tuning | 2026-03-18 | [info](records/track_10min_16mb/2026-03-18_FP16Embed_WD3600/README.md) | -| 3 | Naive Baseline | 1.2244 | Baseline | 9layer 512dim 1024vocab TiedEmbeddings 4 KV heads | 2026-03-18 | [info](records/track_10min_16mb/2026-03-17_NaiveBaseline/README.md) | +| Run | Score | Author | Summary | Date | Info | +|-----|------:|--------|---------|------|------| +| Sliding Window Eval | 1.206 | Matthew Li | Sliding window evaluation at stride=64, increasing context for eval | 2026-03-18 | [info](records/track_10min_16mb/2026-03-19_SlidingWindowEval/README.md) | +| 2048 seq length | 1.206 | Spokane Way | 2048 seq length (train + val) | 2026-03-18 | [info](records/track_10min_16mb/2026-03-18_LongContextSeq2048/README.md) | +| fp16 Embed | 1.2197 | Renier Velazco | FP16 Tied Embedding + LR/Warmdown Tuning | 2026-03-18 | [info](records/track_10min_16mb/2026-03-18_FP16Embed_WD3600/README.md) | +| Naive Baseline | 1.2244 | Baseline | 9layer 512dim 1024vocab TiedEmbeddings 4 KV heads | 2026-03-18 | [info](records/track_10min_16mb/2026-03-17_NaiveBaseline/README.md) | #### Notable Non-Record Runs -- cgit v1.2.3