Open saishivakalyan opened 10 months ago
Now look into it.
Cannot reproduce your error. Trying to figure out how this happen now..
This error is due to the the default config multitask = True
in main_config.cfg
.
Multitask if for FrameBERT only. As you were trying to use MelBERT, with multitask = true
is the reason for this error.
So I have set multitask
to False defautly.
Try update your folder and run it again.
bash-4.4$ python main.py --data_dir data/VUA20 --task_name vua --model_type MELBERT --class_weight 3 --bert_model roberta-base --num_train_epoch 3 --train_batch_size 32 --learning_rate 3e-5 --warmup_epoch 2 /scratch/schalla7/Project/project_env/lib/python3.9/site-packages/torch/cuda/init.py:740: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11050). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.) return torch._C._cuda_getDeviceCount() if nvml_count < 0 else nvml_count ['--data_dir', 'data/VUA20', '--task_name', 'vua', '--model_type', 'MELBERT', '--class_weight', '3', '--bert_model', 'roberta-base', '--num_train_epoch', '3', '--train_batch_size', '32', '--learning_rate', '3e-5', '--warmup_epoch', '2'] main config saved in /scratch/schalla7/Project/MetaphorFrame-main/checkpoints/framebert/roberta-base/9_20231121-0935 device: cpu n_gpu: 0 Some weights of RobertaModel were not initialized from the model checkpoint at roberta-base and are newly initialized: ['roberta.pooler.dense.weight', 'roberta.pooler.dense.bias'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. /scratch/schalla7/Project/project_env/lib/python3.9/site-packages/transformers/optimization.py:411: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set
main()
File "/scratch/schalla7/Project/MetaphorFrame-main/main.py", line 129, in main
model, best_result = run_train(
File "/scratch/schalla7/Project/MetaphorFrame-main/main.py", line 324, in run_train
logits, frame_loss = model(
File "/scratch/schalla7/Project/project_env/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, *kwargs)
File "/scratch/schalla7/Project/project_env/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(args, **kwargs)
TypeError: forward() got an unexpected keyword argument 'frame_input_ids'
no_deprecation_warning=True
to disable this warning warnings.warn( Running training Batch size = 32 Num steps = 15015 Epoch: 0%| You're using a RobertaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the__call__
method is faster than using a method to encode the text followed by a call to thepad
method to get a padded encoding. /scratch/schalla7/Project/project_env/lib/python3.9/site-packages/transformers/tokenization_utils_base.py:2624: UserWarning:max_length
is ignored whenpadding
=True
and there is no truncation strategy. To pad to max length, usepadding='max_length'
. warnings.warn( Iteration: 0it [00:00, ?it/s] Epoch: 0%| | 0/3 [00:00<?, ?it/s] Traceback (most recent call last): File "/scratch/schalla7/Project/MetaphorFrame-main/main.py", line 602, in