Commit 475a6b99 authored by Steven Steinke's avatar Steven Steinke
Browse files

Fix embeddings and seq length

parent 5cb2d1ea
...@@ -30,8 +30,8 @@ python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/main.py \ ...@@ -30,8 +30,8 @@ python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/main.py \
--num-attention-heads 16 \ --num-attention-heads 16 \
--batch-size 8 \ --batch-size 8 \
--checkpoint-activations \ --checkpoint-activations \
--seq-length 512 \ --seq-length 1024 \
--max-position-embeddings 512 \ --max-position-embeddings 1024 \
--log-interval 10 \ --log-interval 10 \
--fp16 \ --fp16 \
--no-load-optim \ --no-load-optim \
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment