tangled-alpha-0.2-core

time python -B prepare_core_datasets.py

Progress: 100%|████████| 220/220 [23:15<00:00,  6.34s/it]
Workers are finished.██| 220/220 [23:15<00:00,  6.34s/it]
Finished data processing!
i=0, block_size=8192, chunk_size=16384000, len(dataset)=893355, len(dataset) * block_size=7318364160
Total number of tokens in the optimized dataset '../core-data-0-8192-2000' is 7318364160

CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt pretrain --config pretrain-core-model.yaml

# ...

Backup wandb:

mv wandb wandb-pretrain-core

Chat with model:

CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt chat ../out/pretrain-core/final

CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True time litgpt evaluate --tasks 'leaderboard' --out_dir '../evaluate/pretrain-core/leaderboard/' --batch_size 1 --dtype 'bfloat16' '../out/pretrain-core/final'

# ...