tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-04-16 13:58:38 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

cosmetics, description tweaks

Browse Source 
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
This commit is contained in:
Nitish Pandey 2025-11-10 16:29:53 +05:30 committed by GitHub
parent f6b1d4f139
commit 9f3b8680ee
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
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

@ -59,7 +59,7 @@ core_metric_every = 2000 # every how many steps to evaluate the core metric (-1
core_metric_max_per_task = 500 # examples per task in estimating the core metric
sample_every = 2000 # every how many steps to sample from the model
# Logging
promised_flops_per_gpu = 989e12 # Only used for logging. Set it to "without sparsity, bfloat16 flops for a single gpu", to log correct `mfu`. Default is set for H100 SXM, bfloat16, without 2:4 sparsity.
promised_flops_per_gpu = 989e12 # To log the correct `mfu`, set this to the value of your GPU, "without sparsity, bfloat16 flops for a single gpu". Default is set for H100 SXM, bfloat16, without 2:4 sparsity.
# Output
model_tag = "" # optionally override the model tag for the output checkpoint directory name
# now allow CLI to override the settings via the configurator lol