Hi,
Im using runseq2seq_qa.py with t5 model for QA task, but while prediction its not producing f1 metrics and not storing the output. Please suggest.
EvalLoopOutput(predictions=None, label_ids=None, metrics={‘test_loss’: 3.253300666809082, ‘test_runtime’: 30.7896, ‘test_samples_per_second’: 25.138, ‘test_steps_per_second’: 3.15}, num_samples=774)
cmd used: python run_seq2seq_qa_own.py --model_name_or_path /tmp/t5_small_squad_own --dataset_loading_script load_sqlike_dataset_both.py --context_column context --question_column question --answer_column answers --do_predict --per_device_train_batch_size 8 --learning_rate 3e-5 --num_train_epochs 2 --max_seq_length 384 --doc_stride 128 --output_dir /tmp/t5_small_squad_own/