tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-03-26 22:55:16 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

bump D:N ratio to 12 per recent scaling laws re-run

Browse Source
This commit is contained in:
Andrej Karpathy 2026-03-24 19:25:50 +00:00
parent c16db281ff
commit 1cd94d768f
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/base_train.py
View File

@ -55,7 +55,7 @@ parser.add_argument("--window-pattern", type=str, default="SSSL", help="sliding
# Training horizon (only one used, in order of precedence)
parser.add_argument("--num-iterations", type=int, default=-1, help="explicit number of optimization steps (-1 = disable)")
parser.add_argument("--target-flops", type=float, default=-1.0, help="calculate num_iterations to reach target_flops (-1 = disable)")
parser.add_argument("--target-param-data-ratio", type=float, default=10.5, help="calculate num_iterations to maintain data:param ratio (Chinchilla=20, -1 = disable)")
parser.add_argument("--target-param-data-ratio", type=float, default=12, help="calculate num_iterations to maintain data:param ratio (Chinchilla=20, -1 = disable)")
# Optimization
parser.add_argument("--device-batch-size", type=int, default=32, help="per-device batch size. good number to reduce to 16,8,4,... if you OOM on VRAM.")
parser.add_argument("--total-batch-size", type=int, default=-1, help="total batch size in tokens. decent numbers are e.g. 524288. (-1 = auto-compute optimal)")