Mark full training run item done (val loss 1.52)

2026-07-12 12:36:03 -04:00
parent ba73c8a7e8
commit 116e1f61a3
1 changed files with 2 additions and 1 deletions
@@ -160,7 +160,8 @@ experiment-llm/
 - [x] Corpus encoded to binary token files
 - [x] Model builds; parameter count matches the estimate
 - [x] Overfit-one-batch sanity check passes (loss → ~0 on a single batch)
- [ ] Full training run completes on MPS with checkpoints + loss curve
+- [x] Full training run completes on MPS with checkpoints + loss curve
+      (v1: 20k steps, ~58 min on M1, val loss 1.52 / perplexity ~4.6)
 - [ ] Sampler produces stories from prompts; gallery committed to `reports/`
 - [x] Every phase re-runnable from a clean clone with documented commands