Block a user
tacit
synced commits to refs/pull/201/merge at tacit/nanochat from mirror
2025-11-13 17:12:13 +00:00
c6abcdfe3a
big change: add pretraining resumption logic so that checkpoints can now be approximately resumed and training can continue. this is useful for very long runs when you don't want the anxiety of your run crashing for some reason. alternatively, it's a way to recover training in the event of loss spikes. i mean, this should have been there in v0 but it's ok. the resumption is approximate to control complexity and bloat, but it's possible we want to change that in the future. to use, set --save_every to a step interval to write checkpoints with, and then use --resume_from_step to resume optimization from a given step. only base model training (pretraining) supports this atm, but it's ok because midtraining is comparably quite a bit faster.
c6abcdfe3a
big change: add pretraining resumption logic so that checkpoints can now be approximately resumed and training can continue. this is useful for very long runs when you don't want the anxiety of your run crashing for some reason. alternatively, it's a way to recover training in the event of loss spikes. i mean, this should have been there in v0 but it's ok. the resumption is approximate to control complexity and bloat, but it's possible we want to change that in the future. to use, set --save_every to a step interval to write checkpoints with, and then use --resume_from_step to resume optimization from a given step. only base model training (pretraining) supports this atm, but it's ok because midtraining is comparably quite a bit faster.
tacit
synced and deleted reference 2025-11-12 16:42:13 +00:00
refs/tags/refs/pull/279/merge at tacit/nanochat from mirror
tacit
synced and deleted reference 2025-11-12 16:42:13 +00:00
refs/tags/refs/pull/282/merge at tacit/nanochat from mirror
tacit
synced and deleted reference 2025-11-12 16:42:13 +00:00
refs/tags/refs/pull/281/merge at tacit/nanochat from mirror
tacit
synced and deleted reference 2025-11-12 16:42:13 +00:00
refs/tags/refs/pull/262/merge at tacit/nanochat from mirror
tacit
synced and deleted reference 2025-11-10 15:42:13 +00:00
refs/tags/refs/pull/267/merge at tacit/nanochat from mirror
tacit
synced and deleted reference 2025-11-10 15:42:13 +00:00
refs/tags/refs/pull/265/merge at tacit/nanochat from mirror
tacit
synced commits to refs/pull/262/merge at tacit/nanochat from mirror
2025-11-10 15:42:13 +00:00
tacit
synced commits to refs/pull/262/merge at tacit/nanochat from mirror
2025-11-10 07:32:16 +00:00
tacit
synced and deleted reference 2025-11-09 23:22:12 +00:00
refs/tags/refs/pull/259/merge at tacit/nanochat from mirror
tacit
synced commits to refs/pull/262/merge at tacit/nanochat from mirror
2025-11-08 22:52:13 +00:00
tacit
synced commits to refs/pull/258/merge at tacit/nanochat from mirror
2025-11-08 14:42:13 +00:00
tacit
synced commits to refs/pull/159/merge at tacit/nanochat from mirror
2025-11-08 06:32:14 +00:00
tacit
synced commits to refs/pull/141/merge at tacit/nanochat from mirror
2025-11-08 06:32:13 +00:00