2024-08-09 10:06:57 +00:00
# first: download adapter models and put them to the corresponding directories
2024-07-04 13:37:15 +00:00
2024-08-09 10:06:57 +00:00
python eval_multigpu.py \
2024-07-04 13:37:15 +00:00
--eval_datasets= translation \
--base_model_path= deepseek-ai/ESFT-vanilla-lite \
--adapter_dir= all_models/adapters/token \
--output_dir= results/completions/token \
--max_new_tokens= 512 \
--openai_api_key= REPLACE_WITH_YOUR_KEY \
2024-08-09 10:06:57 +00:00
--eval_batch_size= 2 \
--world_size= 4 \
--gpus_per_rank= 2
2024-07-04 13:37:15 +00:00
2024-08-09 10:06:57 +00:00
# this script is used for single-gpu training and has been deprecated. If you have no multiple gpus, you can set above world_size=1 and gpus_per_rank=1
# python scripts/eval.py \
# --eval_datasets=translation \
# --base_model_path=deepseek-ai/ESFT-vanilla-lite \
# --adapter_dir=all_models/adapters/token \
# --output_dir=results/completions/token \
# --max_new_tokens=512 \
# --openai_api_key=REPLACE_WITH_YOUR_KEY \
# --eval_batch_size=2
