fam/nanochat-omni
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix path which i think was modified during the refactor and this is a bug introduced by claude i believe

Browse Source
This commit is contained in:
Andrej Karpathy
2026-02-01 20:15:19 +00:00
parent 31b61d2d17
commit eaf49a33c8
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/chat_sft.py
+2 -2
View File
@@ -48,7 +48,7 @@ parser.add_argument("--max-seq-len", type=int, default=2048, help="max context l
parser.add_argument("--device-batch-size", type=int, default=32, help="per-device batch size") parser.add_argument("--device-batch-size", type=int, default=32, help="per-device batch size")
parser.add_argument("--total-batch-size", type=int, default=524288, help="total batch size in tokens") parser.add_argument("--total-batch-size", type=int, default=524288, help="total batch size in tokens")
# Optimization # Optimization
parser.add_argument("--embedding-lr", type=float, default=0.2, help="learning rate for embedding parameters (Adam)") parser.add_argument("--embedding-lr", type=float, default=0.3, help="learning rate for embedding parameters (Adam)")
parser.add_argument("--unembedding-lr", type=float, default=0.004, help="learning rate for unembedding parameters (Adam)") parser.add_argument("--unembedding-lr", type=float, default=0.004, help="learning rate for unembedding parameters (Adam)")
parser.add_argument("--matrix-lr", type=float, default=0.02, help="learning rate for matrix parameters (Muon)") parser.add_argument("--matrix-lr", type=float, default=0.02, help="learning rate for matrix parameters (Muon)")
parser.add_argument("--weight-decay", type=float, default=0.0, help="weight decay for embedding/unembedding parameters (Adam)") parser.add_argument("--weight-decay", type=float, default=0.0, help="weight decay for embedding/unembedding parameters (Adam)")
@@ -285,7 +285,7 @@ while True:
# save checkpoint at the end of the run (only on master process) # save checkpoint at the end of the run (only on master process)
if master_process and last_step and not args.dry_run: if master_process and last_step and not args.dry_run:
output_dirname = args.model_tag if args.model_tag else f"d{depth}" # e.g. d12 output_dirname = args.model_tag if args.model_tag else f"d{depth}" # e.g. d12
checkpoint_dir = os.path.join(base_dir, "sft_checkpoints", output_dirname) checkpoint_dir = os.path.join(base_dir, "chatsft_checkpoints", output_dirname)
save_checkpoint( save_checkpoint(
checkpoint_dir, checkpoint_dir,
step, step,