| model: | |
| model_type: 'selective_pt' | |
| model_name: "Llama-2-7b-chat-hf" | |
| load_bit: 16 | |
| peft_type: "prompt_tuning" | |
| K: 4 | |
| peft_config: | |
| num_virtual_tokens: 1 | |
| normalizer: linear | |
| normalizer_on: ['prompt', 'lm'] | |
| training: | |
| learning_rate: 1e-5 | |
| batch_size: 32 | |
| num_epochs: 1 | |
| mode: causal | |
| adding_noise: 0.1 | |
| only_longest: False | |
| task_type: generate_response | |
| log_dir: runs_prompt_convai2_selective_linear | |
| contrastive: true | |
| ensemble: true | |
| selective_loss_weight: 1.0 | |
| contrastive_metric: bleu | |
| contrastive_threshold: 20.0 | |
| contrastive_weight: 1.0 | |
| freeze_persona: yes | |
| freeze_context: yes | |
| dataset: | |
| train: data_file/ConvAI2/train_self_original_no_cands.txt | |
| valid: data_file/ConvAI2/valid_self_original_no_cands.txt | |
| max_context_turns: -1 | |
| max_token_length: 512 |