tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-01-20 10:23:42 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

optimal ratio is now around 4

Browse Source
This commit is contained in:
Andrej Karpathy 2026-01-17 23:51:09 +00:00
parent e7ed2082b8
commit 413e91aa0f
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

@ -47,7 +47,7 @@ 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=int, default=8, help="calculate num_iterations to maintain data:param ratio (Chinchilla=20, -1 = disable)")
parser.add_argument("--target-param-data-ratio", type=int, default=4, 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")
parser.add_argument("--total-batch-size", type=int, default=524288, help="total batch size in tokens")