osmarks/nanogpt-experiments
1
0
Fork 0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2025-10-26 21:07:40 +00:00
Code Issues Releases Wiki Activity

small readme clarification and training script defaults changes

Browse Source
This commit is contained in:
Andrej Karpathy
2022-12-28 01:45:55 +00:00
parent fe8042867c
commit c9fe00c0e9
2 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
train.py
View File

@@ -19,14 +19,14 @@ out_dir = 'out'
eval_interval = 500
log_interval = 1
# wandb logging
wandb_log = False
wandb_log = False # disabled by default
wandb_entity = 'karpathy'
wandb_project = 'owt'
wandb_run_name = 'owt1' # 'run' + str(time.time())
wandb_run_name = 'gpt2' # 'run' + str(time.time())
# data
dataset = 'openwebtext'
batch_size = 32
block_size = 512
batch_size = 8
block_size = 1024
# model
device = 'cuda:0'
init_from = 'scratch' # 'scratch' or 'resume' or 'gpt2*'