eval.batch_size: 2
eval.cutoff_len: 1024
eval.dataset:
- truth_dev_0716_2
eval.dataset_dir: data
eval.max_new_tokens: 512
eval.max_samples: '100000'
eval.output_dir: eval_2024-07-30-02-47-53_llama3.1_truthqa_bench2
eval.predict: true
eval.temperature: 0.95
eval.top_p: 0.7
top.booster: auto
top.checkpoint_path: train_2024-07-30-02-47-53_llama3.1_truthqa_bench2
top.finetuning_type: full
top.model_name: LLaMA3.1-8B-Chat
top.quantization_bit: none
top.quantization_method: bitsandbytes
top.rope_scaling: none
top.template: llama3
top.visual_inputs: false