phunguyen01
/

II-Tulu-3B-DPO

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

II-Tulu-3B-DPO / training_command.sh

phunguyen01's picture

Training in progress, step 500

40d2511 verified 10 days ago

221 Bytes

eval "$(conda shell.bash hook)" && conda activate trl && accelerate launch -m --config_file $ACCELERATE_CONFIG_FILE integration.third_party.trl.run_dpo checkpoints/ffc21d27-f1c2-41da-9dbb-658ce6048ce1/training_config.yaml