| datasets = [ |
| [ |
| dict( |
| abbr='LongBench_narrativeqa', |
| eval_cfg=dict( |
| evaluator=dict( |
| type='opencompass.datasets.LongBenchF1Evaluator'), |
| pred_role='BOT'), |
| infer_cfg=dict( |
| inferencer=dict( |
| max_out_len=128, |
| type='opencompass.openicl.icl_inferencer.GenInferencer'), |
| prompt_template=dict( |
| template=dict(round=[ |
| dict( |
| prompt= |
| 'You are given a story, which can be either a novel or a movie script, and a question. Answer the question as concisely as you can, using a single phrase if possible. Do not provide any explanation.\n\nStory: {context}\n\nNow, answer the question based on the story as concisely as you can, using a single phrase if possible. Do not provide any explanation.\n\nQuestion: {input}\n\nAnswer:', |
| role='HUMAN'), |
| ]), |
| type= |
| 'opencompass.openicl.icl_prompt_template.PromptTemplate'), |
| retriever=dict( |
| type='opencompass.openicl.icl_retriever.ZeroRetriever')), |
| name='narrativeqa', |
| path='opencompass/Longbench', |
| reader_cfg=dict( |
| input_columns=[ |
| 'context', |
| 'input', |
| ], |
| output_column='answers', |
| test_split='test', |
| train_split='test'), |
| type='opencompass.datasets.LongBenchnarrativeqaDataset'), |
| ], |
| ] |
| eval = dict(runner=dict(task=dict(dump_details=True))) |
| models = [ |
| dict( |
| abbr='mask_gdn-1.3B', |
| batch_padding=False, |
| batch_size=16, |
| max_out_len=100, |
| max_seq_len=16384, |
| path='/mnt/jfzn/msj/train_exp/mask_gdn_1B_hrr-rank4', |
| run_cfg=dict(num_gpus=1), |
| tokenizer_path='/mnt/jfzn/msj/train_exp/mask_gdn_1B_hrr-rank4', |
| type='opencompass.models.HuggingFaceCausalLM'), |
| ] |
| work_dir = 'outputs/default/20251127_164548' |
|
|
