search

yangheng95 / PyABSA

Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;
https://pyabsa.readthedocs.io
MIT License
902 stars 153 forks source link

IndexError: Target 2 is out of bounds. #375

Open Jai-Agarwal-04 opened 6 months ago

Jai-Agarwal-04 commented 6 months ago

Epoch:0 | Loss:0: 0%| | 0/4 [00:03<?, ?it/s]

IndexError Traceback (most recent call last) Cell In[21], line 7 5 config.num_epoch = 1 6 config.model = APC.APCModelList.FAST_LSA_T_V2 ----> 7 trainer = APC.APCTrainer( 8 config=config, 9 dataset=my_dataset, 10 #from_checkpoint="english", 11 # if you want to resume training from our pretrained checkpoints, you can pass the checkpoint name here 12 auto_device=DeviceTypeOption.AUTO, 13 path_to_save=None, # set a path to save checkpoints, if it is None, save checkpoints at 'checkpoints' folder 14 checkpoint_save_mode=ModelSaveOption.SAVE_MODEL_STATE_DICT, 15 load_aug=False, 16 # there are some augmentation dataset for integrated datasets, you use them by setting load_aug=True to improve performance 17 )

File /opt/conda/lib/python3.10/site-packages/pyabsa/tasks/AspectPolarityClassification/trainer/apc_trainer.py:69, in APCTrainer.init(self, config, dataset, from_checkpoint, checkpoint_save_mode, auto_device, path_to_save, load_aug) 64 self.config.task_code = TaskCodeOption.Aspect_Polarity_Classification 65 self.config.task_name = TaskNameOption().get( 66 TaskCodeOption.Aspect_Polarity_Classification 67 ) ---> 69 self._run()

File /opt/conda/lib/python3.10/site-packages/pyabsa/framework/trainer_class/trainer_template.py:241, in Trainer._run(self) 239 self.config.seed = s 240 if self.config.checkpoint_save_mode: --> 241 model_path.append(self.training_instructor(self.config).run()) 242 else: 243 # always return the last trained model if you don't save trained model 244 model = self.inference_model_class( 245 checkpoint=self.training_instructor(self.config).run() 246 )

File /opt/conda/lib/python3.10/site-packages/pyabsa/tasks/AspectPolarityClassification/instructor/apc_instructor.py:702, in APCTrainingInstructor.run(self) 699 def run(self): 700 # Loss and Optimizer 701 criterion = nn.CrossEntropyLoss() --> 702 return self._train(criterion)

File /opt/conda/lib/python3.10/site-packages/pyabsa/framework/instructor_class/instructor_template.py:372, in BaseTrainingInstructor._train(self, criterion) 369 return self._k_fold_train_and_evaluate(criterion) 370 # Train and evaluate the model if there is only one validation dataloader 371 else: --> 372 return self._train_and_evaluate(criterion)

File /opt/conda/lib/python3.10/site-packages/pyabsa/tasks/AspectPolarityClassification/instructor/apc_instructor.py:135, in APCTrainingInstructor._train_and_evaluate(self, criterion) 133 loss = outputs["loss"] 134 else: --> 135 loss = criterion(outputs["logits"], targets) 137 if self.config.auto_device == DeviceTypeOption.ALL_CUDA: 138 loss = loss.mean()

File /opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1501, in Module._call_impl(self, *args, *kwargs) 1496 # If we don't have any hooks, we want to skip the rest of the logic in 1497 # this function, and just call forward. 1498 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks 1499 or _global_backward_pre_hooks or _global_backward_hooks 1500 or _global_forward_hooks or _global_forward_pre_hooks): -> 1501 return forward_call(args, **kwargs) 1502 # Do not call functions when jit is used 1503 full_backward_hooks, non_full_backward_hooks = [], []

File /opt/conda/lib/python3.10/site-packages/torch/nn/modules/loss.py:1174, in CrossEntropyLoss.forward(self, input, target) 1173 def forward(self, input: Tensor, target: Tensor) -> Tensor: -> 1174 return F.cross_entropy(input, target, weight=self.weight, 1175 ignore_index=self.ignore_index, reduction=self.reduction, 1176 label_smoothing=self.label_smoothing)

File /opt/conda/lib/python3.10/site-packages/torch/nn/functional.py:3029, in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing) 3027 if size_average is not None or reduce is not None: 3028 reduction = _Reduction.legacy_get_string(size_average, reduce) -> 3029 return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)

IndexError: Target 2 is out of bounds.

This is the error I am getting while using custom dataset

this is my training snippet

from pyabsa import AspectPolarityClassification as APC from pyabsa import ModelSaveOption, DeviceTypeOption import random config = APC.APCConfigManager.get_apc_config_english() config.model = APC.APCModelList.FAST_LSA_T_V2

config.model = APC.APCModelList.FAST_LSA_S_V2

config.model = APC.APCModelList.BERT_SPC_V2

config.pretrained_bert = "microsoft/deberta-v3-large"

config.evaluate_begin = 2

config.max_seq_len = 80 config.num_epoch = 1 config.log_step = 5 config.dropout = 0 config.cache_dataset = False

config.l2reg = 1e-8

config.lsa = True config.seed = [random.randint(0, 10000) for _ in range(3)] trainer = APC.APCTrainer( config=config, dataset=my_dataset,

from_checkpoint="/kaggle/working/fast_lcf_bert_English_acc_84.65_f1_82.39",

# if you want to resume training from our pretrained checkpoints, you can pass the checkpoint name here
auto_device=DeviceTypeOption.AUTO,
path_to_save=None,  # set a path to save checkpoints, if it is None, save checkpoints at 'checkpoints' folder
checkpoint_save_mode=ModelSaveOption.SAVE_MODEL_STATE_DICT,
load_aug=False,
# there are some augmentation dataset for integrated datasets, you use them by setting load_aug=True to improve performance

)

yangheng95 commented 6 months ago

What are the labels in your dataset? Please paste the full console output here

Jai-Agarwal-04 commented 6 months ago

pro.apc.valid.txt

custom.apc.test.txt pro.apc.train.txt

Jai-Agarwal-04 commented 6 months ago

[2023-12-26 04:41:19] (2.3.4) Set Model Device: cpu [2023-12-26 04:41:19] (2.3.4) Device Name: Unknown 2023-12-26 04:41:19,870 INFO: PyABSA version: 2.3.4 2023-12-26 04:41:19,872 INFO: Transformers version: 4.36.0 2023-12-26 04:41:19,873 INFO: Torch version: 2.0.0+cpu+cudaNone 2023-12-26 04:41:19,874 INFO: Device: Unknown 2023-12-26 04:41:19,875 INFO: 100.pro in the trainer is not a exact path, will search dataset in current working directory 2023-12-26 04:41:19,877 INFO: You can set load_aug=True in a trainer to augment your dataset (English only yet) and improve performance. huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either:

2023-12-26 04:41:24,192 INFO: Load dataset from datasets/apc_datasets/100.pro/pro.test.dat.apc preparing dataloader: 100%|██████████| 7/7 [00:00<00:00, 1000.82it/s] 2023-12-26 04:41:24,205 INFO: Dataset Label Details: {'Neutral': 1, 'Negative': 3, 'Positive': 3, 'Sum': 7} 2023-12-26 04:41:24,225 INFO: test data examples: [{'ex_id': tensor(0), 'text_raw': 'Inspector Rita Yadav, in-charge of cyber crimestation, told that the police arrested Vishal from Bardhaman district of West Bengal on Monday', 'text_spc': '[CLS] Inspector Rita Yadav, in-charge of cyber crimestation, told that the police arrested Vishal from Bardhaman district of West Bengal on Monday [SEP] Rita Yadav, [SEP]', 'aspect': 'Rita Yadav,', 'aspect_position': tensor(0), 'lca_ids': tensor([1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9667, 0.9333, 0.9000, 0.8667, 0.8333, 0.8000, 0.7667, 0.7333, 0.7000, 0.6667, 0.6333, 0.6000, 0.5667, 0.5333, 0.5000, 0.4667, 0.4333, 0.4000, 0.3667, 0.3333, 0.3000, 0.2667, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'lcf_vec': tensor(0), 'lcf_cdw_vec': tensor([1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9667, 0.9333, 0.9000, 0.8667, 0.8333, 0.8000, 0.7667, 0.7333, 0.7000, 0.6667, 0.6333, 0.6000, 0.5667, 0.5333, 0.5000, 0.4667, 0.4333, 0.4000, 0.3667, 0.3333, 0.3000, 0.2667, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'lcf_cdm_vec': tensor([1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'lcfs_vec': tensor(0), 'lcfs_cdw_vec': tensor(0), 'lcfs_cdm_vec': tensor(0), 'dlcf_vec': tensor(0), 'dlcfs_vec': tensor(0), 'depend_vec': tensor(0), 'depended_vec': tensor(0), 'spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'text_indices': tensor([ 1, 15186, 19688, 35157, 261, 267, 271, 21638, 265, 7923, 2898, 22861, 261, 732, 272, 262, 1164, 3740, 75444, 292, 2988, 30083, 1246, 2526, 265, 1260, 17906, 277, 1420, 2, 19688, 35157, 261, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'aspect_bert_indices': tensor(0), 'text_raw_bert_indices': tensor(0), 'polarity': tensor(2), 'cluster_ids': tensor([-100, -100, 2, 2, 2, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100]), 'side_ex_ids': tensor(0), 'left_lcf_cdm_vec': tensor([1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'left_lcf_cdw_vec': tensor([1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9667, 0.9333, 0.9000, 0.8667, 0.8333, 0.8000, 0.7667, 0.7333, 0.7000, 0.6667, 0.6333, 0.6000, 0.5667, 0.5333, 0.5000, 0.4667, 0.4333, 0.4000, 0.3667, 0.3333, 0.3000, 0.2667, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'left_spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'left_text_indices': tensor([ 1, 15186, 19688, 35157, 261, 267, 271, 21638, 265, 7923, 2898, 22861, 261, 732, 272, 262, 1164, 3740, 75444, 292, 2988, 30083, 1246, 2526, 265, 1260, 17906, 277, 1420, 2, 19688, 35157, 261, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'left_dist': tensor(0), 'right_lcf_cdm_vec': tensor([1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'right_lcf_cdw_vec': tensor([1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9667, 0.9333, 0.9000, 0.8667, 0.8333, 0.8000, 0.7667, 0.7333, 0.7000, 0.6667, 0.6333, 0.6000, 0.5667, 0.5333, 0.5000, 0.4667, 0.4333, 0.4000, 0.3667, 0.3333, 0.3000, 0.2667, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'right_spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'right_text_indices': tensor([ 1, 15186, 19688, 35157, 261, 267, 271, 21638, 265, 7923, 2898, 22861, 261, 732, 272, 262, 1164, 3740, 75444, 292, 2988, 30083, 1246, 2526, 265, 1260, 17906, 277, 1420, 2, 19688, 35157, 261, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'right_dist': tensor(0)}, {'ex_id': tensor(1), 'text_raw': 'InspectorRita Yadav,in-charge of cyber crimestation, told that the police arrested Vishal from Bardhaman district of West Bengal on Monday', 'text_spc': '[CLS] InspectorRita Yadav,in-charge of cyber crimestation, told that the police arrested Vishal from Bardhaman district of West Bengal on Monday [SEP] Vishal [SEP]', 'aspect': 'Vishal', 'aspect_position': tensor(0), 'lca_ids': tensor([0.5000, 0.5333, 0.5667, 0.6000, 0.6333, 0.6667, 0.7000, 0.7333, 0.7667, 0.8000, 0.8333, 0.8667, 0.9000, 0.9333, 0.9667, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9667, 0.9333, 0.9000, 0.8667, 0.8333, 0.8000, 0.7667, 0.7333, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'lcf_vec': tensor(0), 'lcf_cdw_vec': tensor([0.5000, 0.5333, 0.5667, 0.6000, 0.6333, 0.6667, 0.7000, 0.7333, 0.7667, 0.8000, 0.8333, 0.8667, 0.9000, 0.9333, 0.9667, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9667, 0.9333, 0.9000, 0.8667, 0.8333, 0.8000, 0.7667, 0.7333, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'lcf_cdm_vec': tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'lcfs_vec': tensor(0), 'lcfs_cdw_vec': tensor(0), 'lcfs_cdm_vec': tensor(0), 'dlcf_vec': tensor(0), 'dlcfs_vec': tensor(0), 'depend_vec': tensor(0), 'depended_vec': tensor(0), 'spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'text_indices': tensor([ 1, 15186, 106763, 35157, 261, 547, 271, 21638, 265, 7923, 2898, 22861, 261, 732, 272, 262, 1164, 3740, 75444, 292, 2988, 30083, 1246, 2526, 265, 1260, 17906, 277, 1420, 2, 75444, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'aspect_bert_indices': tensor(0), 'text_raw_bert_indices': tensor(0), 'polarity': tensor(0), 'cluster_ids': tensor([-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 0, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100]), 'side_ex_ids': tensor(0), 'left_lcf_cdm_vec': tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'left_lcf_cdw_vec': tensor([0.5000, 0.5333, 0.5667, 0.6000, 0.6333, 0.6667, 0.7000, 0.7333, 0.7667, 0.8000, 0.8333, 0.8667, 0.9000, 0.9333, 0.9667, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9667, 0.9333, 0.9000, 0.8667, 0.8333, 0.8000, 0.7667, 0.7333, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'left_spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'left_text_indices': tensor([ 1, 15186, 106763, 35157, 261, 547, 271, 21638, 265, 7923, 2898, 22861, 261, 732, 272, 262, 1164, 3740, 75444, 292, 2988, 30083, 1246, 2526, 265, 1260, 17906, 277, 1420, 2, 75444, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'left_dist': tensor(0), 'right_lcf_cdm_vec': tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'right_lcf_cdw_vec': tensor([0.5000, 0.5333, 0.5667, 0.6000, 0.6333, 0.6667, 0.7000, 0.7333, 0.7667, 0.8000, 0.8333, 0.8667, 0.9000, 0.9333, 0.9667, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9667, 0.9333, 0.9000, 0.8667, 0.8333, 0.8000, 0.7667, 0.7333, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'right_spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'right_text_indices': tensor([ 1, 15186, 106763, 35157, 261, 547, 271, 21638, 265, 7923, 2898, 22861, 261, 732, 272, 262, 1164, 3740, 75444, 292, 2988, 30083, 1246, 2526, 265, 1260, 17906, 277, 1420, 2, 75444, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'right_dist': tensor(0)}]

2023-12-26 04:41:24,931 INFO: Load dataset from datasets/apc_datasets/100.pro/pro.valid.dat.apc preparing dataloader: 100%|██████████| 2/2 [00:00<00:00, 653.32it/s] 2023-12-26 04:41:24,940 INFO: Dataset Label Details: {'Negative': 1, 'Positive': 1, 'Sum': 2} 2023-12-26 04:41:24,958 INFO: valid data examples: [{'ex_id': tensor(0), 'text_raw': 'he sized cattle then go missing and reach slaughterhouses inHyderabad, Mr Kharge said', 'text_spc': '[CLS] he sized cattle then go missing and reach slaughterhouses inHyderabad, Mr Kharge said [SEP] Kharge [SEP]', 'aspect': 'Kharge', 'aspect_position': tensor(0), 'lca_ids': tensor([0.3333, 0.3810, 0.4286, 0.4762, 0.5238, 0.5714, 0.6190, 0.6667, 0.7143, 0.7619, 0.8095, 0.8571, 0.9048, 0.9524, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'lcf_vec': tensor(0), 'lcf_cdw_vec': tensor([0.3333, 0.3810, 0.4286, 0.4762, 0.5238, 0.5714, 0.6190, 0.6667, 0.7143, 0.7619, 0.8095, 0.8571, 0.9048, 0.9524, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'lcf_cdm_vec': tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'lcfs_vec': tensor(0), 'lcfs_cdw_vec': tensor(0), 'lcfs_cdm_vec': tensor(0), 'dlcf_vec': tensor(0), 'dlcfs_vec': tensor(0), 'depend_vec': tensor(0), 'depended_vec': tensor(0), 'spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'text_indices': tensor([ 1, 313, 6408, 9044, 393, 424, 2367, 263, 1431, 69672, 268, 267, 45840, 7059, 29472, 261, 945, 48373, 6024, 357, 2, 48373, 6024, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'aspect_bert_indices': tensor(0), 'text_raw_bert_indices': tensor(0), 'polarity': tensor(1), 'cluster_ids': tensor([-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 1, 1, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100]), 'side_ex_ids': tensor(0), 'left_lcf_cdm_vec': tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'left_lcf_cdw_vec': tensor([0.3333, 0.3810, 0.4286, 0.4762, 0.5238, 0.5714, 0.6190, 0.6667, 0.7143, 0.7619, 0.8095, 0.8571, 0.9048, 0.9524, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'left_spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'left_text_indices': tensor([ 1, 313, 6408, 9044, 393, 424, 2367, 263, 1431, 69672, 268, 267, 45840, 7059, 29472, 261, 945, 48373, 6024, 357, 2, 48373, 6024, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'left_dist': tensor(0), 'right_lcf_cdm_vec': tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'right_lcf_cdw_vec': tensor([0.3333, 0.3810, 0.4286, 0.4762, 0.5238, 0.5714, 0.6190, 0.6667, 0.7143, 0.7619, 0.8095, 0.8571, 0.9048, 0.9524, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'right_spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'right_text_indices': tensor([ 1, 313, 6408, 9044, 393, 424, 2367, 263, 1431, 69672, 268, 267, 45840, 7059, 29472, 261, 945, 48373, 6024, 357, 2, 48373, 6024, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'right_dist': tensor(0)}, {'ex_id': tensor(1), 'text_raw': ' Arvind Kejriwal has written to the Enforcement Directorate(ED) that the summons sent to him was unlawful and politicallymotivated, according to AAPsources.', 'text_spc': '[CLS] Arvind Kejriwal has written to the Enforcement Directorate(ED) that the summons sent to him was unlawful and politicallymotivated, according to AAPsources. [SEP] Arvind Kejriwal [SEP]', 'aspect': 'Arvind Kejriwal', 'aspect_position': tensor(0), 'lca_ids': tensor([1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9677, 0.9355, 0.9032, 0.8710, 0.8387, 0.8065, 0.7742, 0.7419, 0.7097, 0.6774, 0.6452, 0.6129, 0.5806, 0.5484, 0.5161, 0.4839, 0.4516, 0.4194, 0.3871, 0.3548, 0.3226, 0.2903, 0.2581, 0.2258, 0.1935, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'lcf_vec': tensor(0), 'lcf_cdw_vec': tensor([1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9677, 0.9355, 0.9032, 0.8710, 0.8387, 0.8065, 0.7742, 0.7419, 0.7097, 0.6774, 0.6452, 0.6129, 0.5806, 0.5484, 0.5161, 0.4839, 0.4516, 0.4194, 0.3871, 0.3548, 0.3226, 0.2903, 0.2581, 0.2258, 0.1935, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'lcf_cdm_vec': tensor([1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'lcfs_vec': tensor(0), 'lcfs_cdw_vec': tensor(0), 'lcfs_cdm_vec': tensor(0), 'dlcf_vec': tensor(0), 'dlcfs_vec': tensor(0), 'depend_vec': tensor(0), 'depended_vec': tensor(0), 'spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'text_indices': tensor([ 1, 61794, 66065, 303, 1223, 264, 262, 15280, 28328, 555, 4272, 285, 272, 262, 30221, 1253, 264, 417, 284, 15082, 263, 10265, 41770, 261, 970, 264, 32583, 10743, 268, 260, 2, 61794, 66065, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'aspect_bert_indices': tensor(0), 'text_raw_bert_indices': tensor(0), 'polarity': tensor(0), 'cluster_ids': tensor([-100, 0, 0, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100]), 'side_ex_ids': tensor(0), 'left_lcf_cdm_vec': tensor([1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'left_lcf_cdw_vec': tensor([1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9677, 0.9355, 0.9032, 0.8710, 0.8387, 0.8065, 0.7742, 0.7419, 0.7097, 0.6774, 0.6452, 0.6129, 0.5806, 0.5484, 0.5161, 0.4839, 0.4516, 0.4194, 0.3871, 0.3548, 0.3226, 0.2903, 0.2581, 0.2258, 0.1935, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'left_spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'left_text_indices': tensor([ 1, 61794, 66065, 303, 1223, 264, 262, 15280, 28328, 555, 4272, 285, 272, 262, 30221, 1253, 264, 417, 284, 15082, 263, 10265, 41770, 261, 970, 264, 32583, 10743, 268, 260, 2, 61794, 66065, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'left_dist': tensor(0), 'right_lcf_cdm_vec': tensor([1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'right_lcf_cdw_vec': tensor([1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 1.0000, 0.9677, 0.9355, 0.9032, 0.8710, 0.8387, 0.8065, 0.7742, 0.7419, 0.7097, 0.6774, 0.6452, 0.6129, 0.5806, 0.5484, 0.5161, 0.4839, 0.4516, 0.4194, 0.3871, 0.3548, 0.3226, 0.2903, 0.2581, 0.2258, 0.1935, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]), 'right_spc_mask_vec': tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]), 'right_text_indices': tensor([ 1, 61794, 66065, 303, 1223, 264, 262, 15280, 28328, 555, 4272, 285, 272, 262, 30221, 1253, 264, 417, 284, 15082, 263, 10265, 41770, 261, 970, 264, 32583, 10743, 268, 260, 2, 61794, 66065, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 'right_dist': tensor(0)}]

2023-12-26 04:41:25,180 INFO: Model Architecture: APCEnsembler( (models): ModuleList( (0): FAST_LSA_T_V2( (bert4global): DebertaV2Model( (embeddings): DebertaV2Embeddings( (word_embeddings): Embedding(128100, 1024, padding_idx=0) (LayerNorm): LayerNorm((1024,), eps=1e-07, elementwise_affine=True) (dropout): StableDropout() ) (encoder): DebertaV2Encoder( (layer): ModuleList( (0-23): 24 x DebertaV2Layer( (attention): DebertaV2Attention( (self): DisentangledSelfAttention( (query_proj): Linear(in_features=1024, out_features=1024, bias=True) (key_proj): Linear(in_features=1024, out_features=1024, bias=True) (value_proj): Linear(in_features=1024, out_features=1024, bias=True) (pos_dropout): StableDropout() (dropout): StableDropout() ) (output): DebertaV2SelfOutput( (dense): Linear(in_features=1024, out_features=1024, bias=True) (LayerNorm): LayerNorm((1024,), eps=1e-07, elementwise_affine=True) (dropout): StableDropout() ) ) (intermediate): DebertaV2Intermediate( (dense): Linear(in_features=1024, out_features=4096, bias=True) (intermediate_act_fn): GELUActivation() ) (output): DebertaV2Output( (dense): Linear(in_features=4096, out_features=1024, bias=True) (LayerNorm): LayerNorm((1024,), eps=1e-07, elementwise_affine=True) (dropout): StableDropout() ) ) ) (rel_embeddings): Embedding(512, 1024) (LayerNorm): LayerNorm((1024,), eps=1e-07, elementwise_affine=True) ) ) (dropout): Dropout(p=0, inplace=False) (post_encoder): Encoder( (encoder): ModuleList( (0): SelfAttention( (SA): BertSelfAttention( (query): Linear(in_features=1024, out_features=1024, bias=True) (key): Linear(in_features=1024, out_features=1024, bias=True) (value): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) (tanh): Tanh() ) (postencoder): Encoder( (encoder): ModuleList( (0): SelfAttention( (SA): BertSelfAttention( (query): Linear(in_features=1024, out_features=1024, bias=True) (key): Linear(in_features=1024, out_features=1024, bias=True) (value): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) (tanh): Tanh() ) (bert_pooler): BertPooler( (dense): Linear(in_features=1024, out_features=1024, bias=True) (activation): Tanh() ) (CDW_LSA): LSA( (encoder): Encoder( (encoder): ModuleList( (0): SelfAttention( (SA): BertSelfAttention( (query): Linear(in_features=1024, out_features=1024, bias=True) (key): Linear(in_features=1024, out_features=1024, bias=True) (value): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) (tanh): Tanh() ) (encoder_left): Encoder( (encoder): ModuleList( (0): SelfAttention( (SA): BertSelfAttention( (query): Linear(in_features=1024, out_features=1024, bias=True) (key): Linear(in_features=1024, out_features=1024, bias=True) (value): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) (tanh): Tanh() ) (encoder_right): Encoder( (encoder): ModuleList( (0): SelfAttention( (SA): BertSelfAttention( (query): Linear(in_features=1024, out_features=1024, bias=True) (key): Linear(in_features=1024, out_features=1024, bias=True) (value): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) (tanh): Tanh() ) (linear_window_3h): Linear(in_features=3072, out_features=1024, bias=True) (linear_window_2h): Linear(in_features=2048, out_features=1024, bias=True) ) (post_linear): Linear(in_features=2048, out_features=1024, bias=True) (dense): Linear(in_features=1024, out_features=2, bias=True) ) ) (bert): DebertaV2Model( (embeddings): DebertaV2Embeddings( (word_embeddings): Embedding(128100, 1024, padding_idx=0) (LayerNorm): LayerNorm((1024,), eps=1e-07, elementwise_affine=True) (dropout): StableDropout() ) (encoder): DebertaV2Encoder( (layer): ModuleList( (0-23): 24 x DebertaV2Layer( (attention): DebertaV2Attention( (self): DisentangledSelfAttention( (query_proj): Linear(in_features=1024, out_features=1024, bias=True) (key_proj): Linear(in_features=1024, out_features=1024, bias=True) (value_proj): Linear(in_features=1024, out_features=1024, bias=True) (pos_dropout): StableDropout() (dropout): StableDropout() ) (output): DebertaV2SelfOutput( (dense): Linear(in_features=1024, out_features=1024, bias=True) (LayerNorm): LayerNorm((1024,), eps=1e-07, elementwise_affine=True) (dropout): StableDropout() ) ) (intermediate): DebertaV2Intermediate( (dense): Linear(in_features=1024, out_features=4096, bias=True) (intermediate_act_fn): GELUActivation() ) (output): DebertaV2Output( (dense): Linear(in_features=4096, out_features=1024, bias=True) (LayerNorm): LayerNorm((1024,), eps=1e-07, elementwise_affine=True) (dropout): StableDropout() ) ) ) (rel_embeddings): Embedding(512, 1024) (LayerNorm): LayerNorm((1024,), eps=1e-07, elementwise_affine=True) ) ) (dense): Linear(in_features=2, out_features=2, bias=True) ) 2023-12-26 04:41:25,181 INFO: ABSADatasetsVersion:None --> Calling Count:0 2023-12-26 04:41:25,182 INFO: MV:<metric_visualizer.metric_visualizer.MetricVisualizer object at 0x78df6ab262c0> --> Calling Count:0 2023-12-26 04:41:25,183 INFO: PyABSAVersion:2.3.4 --> Calling Count:1 2023-12-26 04:41:25,184 INFO: SRD:3 --> Calling Count:132 2023-12-26 04:41:25,185 INFO: TorchVersion:2.0.0+cpu+cudaNone --> Calling Count:1 2023-12-26 04:41:25,186 INFO: TransformersVersion:4.36.0 --> Calling Count:1 2023-12-26 04:41:25,186 INFO: auto_device:True --> Calling Count:3 2023-12-26 04:41:25,187 INFO: batch_size:16 --> Calling Count:3 2023-12-26 04:41:25,188 INFO: cache_dataset:False --> Calling Count:1 2023-12-26 04:41:25,188 INFO: checkpoint_save_mode:1 --> Calling Count:4 2023-12-26 04:41:25,191 INFO: cross_validate_fold:-1 --> Calling Count:1 2023-12-26 04:41:25,191 INFO: dataset_file:{'train': ['datasets/apc_datasets/100.pro/pro.train.dat.apc'], 'test': ['datasets/apc_datasets/100.pro/pro.test.dat.apc'], 'valid': ['datasets/apc_datasets/100.pro/pro.valid.dat.apc']} --> Calling Count:17 2023-12-26 04:41:25,192 INFO: dataset_name:100.pro --> Calling Count:3 2023-12-26 04:41:25,193 INFO: dca_layer:3 --> Calling Count:0 2023-12-26 04:41:25,194 INFO: dca_p:1 --> Calling Count:0 2023-12-26 04:41:25,195 INFO: deep_ensemble:False --> Calling Count:0 2023-12-26 04:41:25,196 INFO: device:cpu --> Calling Count:3 2023-12-26 04:41:25,197 INFO: device_name:Unknown --> Calling Count:1 2023-12-26 04:41:25,197 INFO: dlcf_a:2 --> Calling Count:0 2023-12-26 04:41:25,198 INFO: dropout:0 --> Calling Count:1 2023-12-26 04:41:25,199 INFO: dynamic_truncate:True --> Calling Count:132 2023-12-26 04:41:25,199 INFO: embed_dim:1024 --> Calling Count:7 2023-12-26 04:41:25,200 INFO: eta:1 --> Calling Count:2 2023-12-26 04:41:25,201 INFO: eta_lr:0.1 --> Calling Count:1 2023-12-26 04:41:25,201 INFO: evaluate_begin:0 --> Calling Count:0 2023-12-26 04:41:25,202 INFO: from_checkpoint:None --> Calling Count:0 2023-12-26 04:41:25,203 INFO: hidden_dim:1024 --> Calling Count:0 2023-12-26 04:41:25,203 INFO: index_to_label:{0: 'Negative', 1: 'Positive', 2: 'Positive'} --> Calling Count:4 2023-12-26 04:41:25,204 INFO: inference_model:None --> Calling Count:0 2023-12-26 04:41:25,205 INFO: initializer:xavieruniform --> Calling Count:0 2023-12-26 04:41:25,207 INFO: inputs_cols:['lcf_cdm_vec', 'lcf_cdw_vec', 'left_lcf_cdm_vec', 'left_lcf_cdw_vec', 'right_lcf_cdm_vec', 'right_lcf_cdw_vec', 'spc_mask_vec', 'text_indices'] --> Calling Count:996 2023-12-26 04:41:25,208 INFO: l2reg:1e-06 --> Calling Count:2 2023-12-26 04:41:25,209 INFO: label_to_index:{'Negative': 0, 'Neutral': 1, 'Positive': 1} --> Calling Count:1 2023-12-26 04:41:25,209 INFO: lcf:cdw --> Calling Count:3 2023-12-26 04:41:25,212 INFO: learning_rate:2e-05 --> Calling Count:1 2023-12-26 04:41:25,213 INFO: load_aug:False --> Calling Count:1 2023-12-26 04:41:25,214 INFO: log_step:5 --> Calling Count:0 2023-12-26 04:41:25,215 INFO: logger:<_Logger fast_lsa_t_v2 (INFO)> --> Calling Count:16 2023-12-26 04:41:25,215 INFO: lsa:True --> Calling Count:0 2023-12-26 04:41:25,216 INFO: max_seq_len:80 --> Calling Count:792 2023-12-26 04:41:25,217 INFO: model:<class 'pyabsa.tasks.AspectPolarityClassification.models.lcf.fast_lsa_t_v2.FAST_LSA_T_V2'> --> Calling Count:6 2023-12-26 04:41:25,217 INFO: model_name:fast_lsa_t_v2 --> Calling Count:134 2023-12-26 04:41:25,218 INFO: model_path_to_save:checkpoints --> Calling Count:0 2023-12-26 04:41:25,219 INFO: num_epoch:1 --> Calling Count:0 2023-12-26 04:41:25,220 INFO: optimizer:adamw --> Calling Count:1 2023-12-26 04:41:25,220 INFO: output_dim:2 --> Calling Count:3 2023-12-26 04:41:25,221 INFO: overwrite_cache:False --> Calling Count:0 2023-12-26 04:41:25,224 INFO: path_to_save:None --> Calling Count:1 2023-12-26 04:41:25,225 INFO: patience:99999 --> Calling Count:0 2023-12-26 04:41:25,227 INFO: pretrained_bert:microsoft/deberta-v3-large --> Calling Count:5 2023-12-26 04:41:25,228 INFO: save_mode:1 --> Calling Count:0 2023-12-26 04:41:25,229 INFO: seed:1291 --> Calling Count:6 2023-12-26 04:41:25,231 INFO: sigma:0.3 --> Calling Count:0 2023-12-26 04:41:25,233 INFO: similarity_threshold:1 --> Calling Count:3 2023-12-26 04:41:25,234 INFO: spacy_model:en_core_web_sm --> Calling Count:5 2023-12-26 04:41:25,236 INFO: srd_alignment:True --> Calling Count:0 2023-12-26 04:41:25,237 INFO: task_code:APC --> Calling Count:1 2023-12-26 04:41:25,238 INFO: task_name:Aspect-based Sentiment Classification --> Calling Count:0 2023-12-26 04:41:25,239 INFO: tokenizer:DebertaV2TokenizerFast(name_or_path='microsoft/deberta-v3-large', vocab_size=128000, model_max_length=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '[CLS]', 'eos_token': '[SEP]', 'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}, clean_up_tokenization_spaces=True), added_tokens_decoder={ 0: AddedToken("[PAD]", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 1: AddedToken("[CLS]", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 2: AddedToken("[SEP]", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 3: AddedToken("[UNK]", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True), 128000: AddedToken("[MASK]", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), } --> Calling Count:0 2023-12-26 04:41:25,240 INFO: use_amp:False --> Calling Count:1 2023-12-26 04:41:25,241 INFO: use_bert_spc:True --> Calling Count:0 2023-12-26 04:41:25,242 INFO: use_syntax_based_SRD:False --> Calling Count:0 2023-12-26 04:41:25,243 INFO: warmup_step:-1 --> Calling Count:0 2023-12-26 04:41:25,246 INFO: window:lr --> Calling Count:0 2023-12-26 04:41:25,256 INFO: Running training for Aspect-based Sentiment Classification 2023-12-26 04:41:25,258 INFO: Training set examples = 57 2023-12-26 04:41:25,261 INFO: Test set examples = 7 2023-12-26 04:41:25,262 INFO: Total params = 458150922, Trainable params = 458150922, Non-trainable params = 0 2023-12-26 04:41:25,263 INFO: Batch size = 16 2023-12-26 04:41:25,264 INFO: Num steps = 0 Epoch:0 | Loss:0: 0%| | 0/4 [00:00<?, ?it/s]We strongly recommend passing in an attention_mask since your input_ids may be padded. See https://huggingface.co/docs/transformers/troubleshooting#incorrect-output-when-padding-tokens-arent-masked. Epoch:0 | Loss:0: 0%| | 0/4 [00:09<?, ?it/s]

IndexError Traceback (most recent call last) Cell In[17], line 18 16 config.lsa = True 17 config.seed = [random.randint(0, 10000) for _ in range(3)] ---> 18 trainer = APC.APCTrainer( 19 config=config, 20 dataset=my_dataset, 21 #from_checkpoint="/kaggle/working/fast_lcf_bert_English_acc_84.65_f1_82.39", 22 # if you want to resume training from our pretrained checkpoints, you can pass the checkpoint name here 23 auto_device=DeviceTypeOption.AUTO, 24 path_to_save=None, # set a path to save checkpoints, if it is None, save checkpoints at 'checkpoints' folder 25 checkpoint_save_mode=ModelSaveOption.SAVE_MODEL_STATE_DICT, 26 load_aug=False, 27 # there are some augmentation dataset for integrated datasets, you use them by setting load_aug=True to improve performance 28 )

File /opt/conda/lib/python3.10/site-packages/pyabsa/tasks/AspectPolarityClassification/trainer/apc_trainer.py:69, in APCTrainer.init(self, config, dataset, from_checkpoint, checkpoint_save_mode, auto_device, path_to_save, load_aug) 64 self.config.task_code = TaskCodeOption.Aspect_Polarity_Classification 65 self.config.task_name = TaskNameOption().get( 66 TaskCodeOption.Aspect_Polarity_Classification 67 ) ---> 69 self._run()

File /opt/conda/lib/python3.10/site-packages/pyabsa/framework/trainer_class/trainer_template.py:241, in Trainer._run(self) 239 self.config.seed = s 240 if self.config.checkpoint_save_mode: --> 241 model_path.append(self.training_instructor(self.config).run()) 242 else: 243 # always return the last trained model if you don't save trained model 244 model = self.inference_model_class( 245 checkpoint=self.training_instructor(self.config).run() 246 )

File /opt/conda/lib/python3.10/site-packages/pyabsa/tasks/AspectPolarityClassification/instructor/apc_instructor.py:702, in APCTrainingInstructor.run(self) 699 def run(self): 700 # Loss and Optimizer 701 criterion = nn.CrossEntropyLoss() --> 702 return self._train(criterion)

File /opt/conda/lib/python3.10/site-packages/pyabsa/framework/instructor_class/instructor_template.py:372, in BaseTrainingInstructor._train(self, criterion) 369 return self._k_fold_train_and_evaluate(criterion) 370 # Train and evaluate the model if there is only one validation dataloader 371 else: --> 372 return self._train_and_evaluate(criterion)

File /opt/conda/lib/python3.10/site-packages/pyabsa/tasks/AspectPolarityClassification/instructor/apc_instructor.py:135, in APCTrainingInstructor._train_and_evaluate(self, criterion) 133 loss = outputs["loss"] 134 else: --> 135 loss = criterion(outputs["logits"], targets) 137 if self.config.auto_device == DeviceTypeOption.ALL_CUDA: 138 loss = loss.mean()

File /opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1501, in Module._call_impl(self, *args, *kwargs) 1496 # If we don't have any hooks, we want to skip the rest of the logic in 1497 # this function, and just call forward. 1498 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks 1499 or _global_backward_pre_hooks or _global_backward_hooks 1500 or _global_forward_hooks or _global_forward_pre_hooks): -> 1501 return forward_call(args, **kwargs) 1502 # Do not call functions when jit is used 1503 full_backward_hooks, non_full_backward_hooks = [], []

File /opt/conda/lib/python3.10/site-packages/torch/nn/modules/loss.py:1174, in CrossEntropyLoss.forward(self, input, target) 1173 def forward(self, input: Tensor, target: Tensor) -> Tensor: -> 1174 return F.cross_entropy(input, target, weight=self.weight, 1175 ignore_index=self.ignore_index, reduction=self.reduction, 1176 label_smoothing=self.label_smoothing)

File /opt/conda/lib/python3.10/site-packages/torch/nn/functional.py:3029, in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing) 3027 if size_average is not None or reduce is not None: 3028 reduction = _Reduction.legacy_get_string(size_average, reduce) -> 3029 return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)

IndexError: Target 2 is out of bounds.