tacit

tacit synced commits to refs/pull/536/merge at tacit/nanochat from mirror 2026-02-17 00:50:25 +00:00

4cd1d3aeb5 Merge 3735eb9723 into 8180e1d8c1

8180e1d8c1 tune the data mixture a bit, load optimizer by default when SFT. These were confirmed to be best settings from sweeps of sft

Compare 2 commits »

tacit synced commits to refs/pull/535/merge at tacit/nanochat from mirror 2026-02-17 00:50:25 +00:00

969e8980e7 Merge a991ed8e39 into 8180e1d8c1

8180e1d8c1 tune the data mixture a bit, load optimizer by default when SFT. These were confirmed to be best settings from sweeps of sft

Compare 2 commits »

tacit synced commits to refs/pull/531/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

bbaee0f7c2 Merge 124f49be98 into 8180e1d8c1

8180e1d8c1 tune the data mixture a bit, load optimizer by default when SFT. These were confirmed to be best settings from sweeps of sft

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 3 commits »

tacit synced commits to refs/pull/521/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

cc3dc6f1ac Merge 967c408d3a into 788dadeb88

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 2 commits »

tacit synced commits to refs/pull/510/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

1b7fff2fe9 Merge 26bc859fc7 into 788dadeb88

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 2 commits »

tacit synced commits to refs/pull/516/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

9b686ac8ab Merge 00932d1955 into 8180e1d8c1

8180e1d8c1 tune the data mixture a bit, load optimizer by default when SFT. These were confirmed to be best settings from sweeps of sft

Compare 2 commits »

tacit synced commits to refs/pull/509/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

4c30b8ebe3 Merge 9caf6690a1 into 8180e1d8c1

8180e1d8c1 tune the data mixture a bit, load optimizer by default when SFT. These were confirmed to be best settings from sweeps of sft

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 3 commits »

tacit synced commits to refs/pull/501/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

c273eda6fb Merge 005daea668 into 8180e1d8c1

8180e1d8c1 tune the data mixture a bit, load optimizer by default when SFT. These were confirmed to be best settings from sweeps of sft

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 3 commits »

tacit synced commits to refs/pull/489/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

cebab2de6c Merge 79b7b04ca0 into 788dadeb88

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 2 commits »

tacit synced commits to refs/pull/485/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

77d71d0b58 Merge 181e7f1c15 into 788dadeb88

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 2 commits »

tacit synced commits to refs/pull/498/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

233283dbda Merge 330fa1188c into 8180e1d8c1

8180e1d8c1 tune the data mixture a bit, load optimizer by default when SFT. These were confirmed to be best settings from sweeps of sft

Compare 2 commits »

tacit synced commits to refs/pull/486/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

3617907a1b Merge 7c0eb3f00b into 788dadeb88

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 2 commits »

tacit synced commits to refs/pull/533/merge at tacit/nanochat from mirror 2026-02-17 00:50:24 +00:00

23e978a673 Merge 240a60fec2 into 8180e1d8c1

8180e1d8c1 tune the data mixture a bit, load optimizer by default when SFT. These were confirmed to be best settings from sweeps of sft

Compare 2 commits »

tacit synced commits to master at tacit/nanochat from mirror 2026-02-17 00:50:23 +00:00

8180e1d8c1 tune the data mixture a bit, load optimizer by default when SFT. These were confirmed to be best settings from sweeps of sft

tacit synced commits to refs/pull/141/merge at tacit/nanochat from mirror 2026-02-17 00:50:23 +00:00

4695fdb6ec Merge 65865df300 into 788dadeb88

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 2 commits »

tacit synced commits to refs/pull/204/merge at tacit/nanochat from mirror 2026-02-17 00:50:23 +00:00

0d65935038 Merge 6e571915d9 into 788dadeb88

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 2 commits »

tacit synced commits to refs/pull/370/merge at tacit/nanochat from mirror 2026-02-17 00:50:23 +00:00

46dfc3c81e Merge 9a9b12b1be into 788dadeb88

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 2 commits »

tacit synced commits to refs/pull/536/merge at tacit/nanochat from mirror 2026-02-16 16:40:27 +00:00

12a48ef8f5 Merge 3735eb9723 into 788dadeb88

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

3735eb9723 simplify test.yml

7686d3c7e2 Update test.yml

3185f928d7 Update .github/workflows/test.yml

Compare 5 commits »

tacit synced commits to refs/pull/533/head at tacit/nanochat from mirror 2026-02-16 16:40:26 +00:00

240a60fec2 Add informative error message to batch size assertion

0f3b6a4654 Replace cryptic assertion with descriptive ValueError for batch size alignment

788dadeb88 a number of upgrades to SFT script to bring it up to date w.r.t. pretraining and tuning some of its kwargs based on sweeps

Compare 3 commits »

tacit synced commits to refs/pull/536/head at tacit/nanochat from mirror 2026-02-16 16:40:26 +00:00

3735eb9723 simplify test.yml

7686d3c7e2 Update test.yml

3185f928d7 Update .github/workflows/test.yml

Compare 3 commits »