zubingou/multi-view-prompting

Repo for "MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction" [ACL'2023]

Hi there, this is Zhibin!👋

• 🎓 M.S. student at THU, with a CS background from BUPT.
• 🔭 Diving into large language models and reasoning, with a long-term aim at AGI.
• 🏃 Avid runner, fitness buff, and badminton player.
• 💬 Open for chat and collaboration – don't hesitate to reach out!

multi-view-prompting's Issues

prefix_allowed_tokens_fn

您好，请问这里的def prefix_allowed_tokens_fn(self, task, data_name, source_ids, batch_id,input_ids):这一步是什么意思，是加入到T5的每一层中吗，还是只是embeding部分

No module named 'optim_orders'

Hi, I'm having a bit of a problem trying to reproduce your code. The module optim_orders has not been found, it would be very helpful if you could provide instructions on getting the missing files.Thanks again for making your code public.

无

请问作者如何讲源码中用到的T5模型换成BART模型

我尝试更换，发现准确率极低，损失值非常大

Code Issue

I would like to perform fine-tuning training on a custom dataset. Could you please let me know which parameters and files I need to modify? What does the 'const.py' file represent? Do I need to build it based on my custom dataset?

模型预测

请问，怎么用自己训练好的模型进行一句话的预测

Please provide an easier model inference method

I really want to test the performance of the model without having to fine-tune it for a specific task.

I tried to follow your code, something like this:

tokenizer = T5Tokenizer.from_pretrained(model_path)
tfm_model = MyT5ForConditionalGeneration.from_pretrained(model_path)
model = T5FineTuner(config, tfm_model, tokenizer)

text = "I will be back, I love the sushi badly!"

input_tokenized = tokenizer(text, return_tensors="pt")
summary_ids = model.model.generate(input_tokenized['input_ids'])
output = tokenizer.decode(summary_ids[0], skip_special_tokens=True)

print(output)

# Output: [I will be back [e] love sushi [I love badly sushi

But I'm not 100% sure about the config file and I'm getting weird results.

If you could provide an example, it would be fantastic!

中文数据集训练

作者您好，如果换成中文数据集训练的话，该如何调整网络架构

code issue

作者你好，我在运行bash scripts/run_unified.sh这条命令的时候代码就没反应了请问是什么情况，也没有报错，也没有运行gpu资源

code and data

Hello author, I have read your paper, your experimental results are amazing, and I look forward to your published code.

看不到训练进程

训练的时候卡在这一步，看不到训练进程
(mvp) root@autodl-container-a34a11a952-3cb61709:~/autodl-tmp/absa/multi-view-prompting# bash scripts/run_unified.sh

• export CUDA_VISIBLE_DEVICES=0
• CUDA_VISIBLE_DEVICES=0
• cd src
• for SEED in 5 10 15 20 25
• K=5
• INFER_PATH=5
• CTRL_TOKEN=post
• TASK=unified
• OUT_DIR=../outputs/unified/top5_seed5
• mkdir -p ../outputs/unified/top5_seed5
• python main.py --data_path ../data/ --dataset seed5 --model_name_or_path t5-base --output_dir ../outputs/unified/top5_seed5 --num_train_epochs 20 --save_top_k 0 --task unified --top_k 5 --ctrl_token post --multi_path --num_path 5 --seed 5 --train_batch_size 16 --gradient_accumulation_steps 1 --learning_rate 1e-4 --lowercase --sort_label --data_ratio 1.0 --check_val_every_n_epoch 10 --agg_strategy vote --eval_batch_size 64 --constrained_decode --multi_task --do_train
  Some weights of the model checkpoint at t5-base were not used when initializing MyT5ForConditionalGeneration: ['decoder.block.0.layer.1.EncDecAttention.relative_attention_bias.weight']

• This IS expected if you are initializing MyT5ForConditionalGeneration from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).

• This IS NOT expected if you are initializing MyT5ForConditionalGeneration from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
  Some weights of MyT5ForConditionalGeneration were not initialized from the model checkpoint at t5-base and are newly initialized: ['encoder.embed_tokens.weight', 'lm_head.weight', 'decoder.embed_tokens.weight']
  You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
  GPU available: True (cuda), used: True
  TPU available: False, using: 0 TPU cores
  IPU available: False, using: 0 IPUs
  HPU available: False, using: 0 HPUs
  /root/miniconda3/envs/mvp/lib/python3.8/site-packages/pytorch_lightning/trainer/connectors/logger_connector/logger_connector.py:67: UserWarning: Starting from v1.9.0, tensorboardX has been removed as a dependency of the pytorch_lightning package, due to potential conflicts with other packages in the ML ecosystem. For this reason, logger=True will use CSVLogger as the default logger, unless the tensorboard or tensorboardX packages are found. Please pip install lightning[extra] or one of them to enable TensorBoard support by default
  warning_cache.warn(
  You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set torch.set_float32_matmul_precision('medium' | 'high') which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision
  LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name | Type | Params

---

0 | model | MyT5ForConditionalGeneration | 222 M

222 M Trainable params
0 Non-trainable params
222 M Total params
891.614 Total estimated model params size (MB)