osmarks/nanogpt-experiments
1
0
Fork 0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2025-10-31 07:13:01 +00:00
Code Issues Releases Wiki Activity

add a patch to fix mysterious unwanted prefix in state dict? maybe remove later

Browse Source
This commit is contained in:
Andrej Karpathy
2023-01-02 01:25:02 +00:00
parent 41184a27f5
commit ec9b1f8182
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
train.py
View File

@@ -142,7 +142,14 @@ elif init_from == 'resume':
# TODO: think through how passed in params should interact with checkpoint params
gptconf = GPTConfig(**model_args)
model = GPT(gptconf)
model.load_state_dict(checkpoint['model'])
state_dict = checkpoint['model']
# fix the keys of the state dictionary :(
# honestly no idea how checkpoints sometimes get this prefix, have to debug more
unwanted_prefix = '_orig_mod.'
for k,v in list(state_dict.items()):
if k.startswith(unwanted_prefix):
state_dict[k[len(unwanted_prefix):]] = state_dict.pop(k)
model.load_state_dict(state_dict)
iter_num = checkpoint['iter_num']
best_val_loss = checkpoint['best_val_loss']
elif init_from.startswith('gpt2'):