Datasets:

---

zhangzhifang

/

backdoor

Like 0

Error code:   StreamingRowsError
Exception:    CastError
Message:      Couldn't cast
model_args: struct<model_name_or_path: string, train_type: string, loss: string, sp_coef: double, ce_alpha: doub (... 65 chars omitted)
  child 0, model_name_or_path: string
  child 1, train_type: string
  child 2, loss: string
  child 3, sp_coef: double
  child 4, ce_alpha: double
  child 5, vlood_lambda_const: double
  child 6, lora_r: int64
  child 7, lora_alpha: int64
data_args: struct<dataset: string, prompt: string, attack_type: string, target: string, train_num: int64, pr: d (... 104 chars omitted)
  child 0, dataset: string
  child 1, prompt: string
  child 2, attack_type: string
  child 3, target: string
  child 4, train_num: int64
  child 5, pr: double
  child 6, patch_size: int64
  child 7, patch_type: string
  child 8, patch_location: string
  child 9, img_size: int64
  child 10, neg_sample: bool
training_args: struct<output_dir: string, per_device_train_batch_size: int64, num_train_epochs: double, max_steps:  (... 2871 chars omitted)
  child 0, output_dir: string
  child 1, per_device_train_batch_size: int64
  child 2, num_train_epochs: double
  child 3, max_steps: int64
  child 4, learning_rate: double
  child 5, lr_scheduler_type: string
  child 6, lr_scheduler_kwargs: null
  child 7, warmup_steps: double
  child 8, optim: string
  child 9, optim_args: null
  child 10, weight_decay: double
  child 11, adam_beta1: double
  child 12, adam_beta2: double
  child 13, adam_epsilon: double
  child 14, optim_target_modules: null
  child 15, gradient_accumulation_steps:
...
child 86, dataloader_persistent_workers: bool
  child 87, dataloader_prefetch_factor: null
  child 88, remove_unused_columns: bool
  child 89, label_names: list<item: string>
      child 0, item: string
  child 90, train_sampling_strategy: string
  child 91, length_column_name: string
  child 92, ddp_find_unused_parameters: null
  child 93, ddp_bucket_cap_mb: null
  child 94, ddp_broadcast_buffers: null
  child 95, ddp_backend: null
  child 96, ddp_timeout: int64
  child 97, fsdp: list<item: null>
      child 0, item: null
  child 98, fsdp_config: struct<min_num_params: int64, xla: bool, xla_fsdp_v2: bool, xla_fsdp_grad_ckpt: bool>
      child 0, min_num_params: int64
      child 1, xla: bool
      child 2, xla_fsdp_v2: bool
      child 3, xla_fsdp_grad_ckpt: bool
  child 99, deepspeed: string
  child 100, debug: list<item: null>
      child 0, item: null
  child 101, skip_memory_metrics: bool
  child 102, do_train: bool
  child 103, do_eval: bool
  child 104, do_predict: bool
  child 105, resume_from_checkpoint: null
  child 106, warmup_ratio: double
  child 107, logging_dir: null
  child 108, local_rank: int64
  child 109, adjust_weight: null
  child 110, gamma: null
output_dir_root_name: string
attack_type: string
adapter_path: string
patch_location: string
seed: int64
neg_sample: bool
dataset: string
prompt: string
patch_type: string
finetune_type: string
patch_size: int64
img_size: int64
pr: double
model_name_or_path: string
target: string
config: string
train_num: int64
to
{'config': Value('string'), 'output_dir_root_name': Value('string'), 'dataset': Value('string'), 'prompt': Value('string'), 'train_num': Value('int64'), 'target': Value('string'), 'patch_size': Value('int64'), 'patch_type': Value('string'), 'patch_location': Value('string'), 'img_size': Value('int64'), 'pr': Value('float64'), 'neg_sample': Value('bool'), 'seed': Value('int64'), 'attack_type': Value('string'), 'finetune_type': Value('string'), 'adapter_path': Value('string'), 'model_name_or_path': Value('string')}
because column names don't match
Traceback:    Traceback (most recent call last):
                File "/src/services/worker/src/worker/utils.py", line 147, in get_rows_or_raise
                  return get_rows(
                      dataset=dataset,
                  ...<4 lines>...
                      column_names=column_names,
                  )
                File "/src/libs/libcommon/src/libcommon/utils.py", line 272, in decorator
                  return func(*args, **kwargs)
                File "/src/services/worker/src/worker/utils.py", line 127, in get_rows
                  rows_plus_one = list(itertools.islice(safe_iter(ds, dataset=dataset), rows_max_number + 1))
                File "/src/services/worker/src/worker/utils.py", line 483, in safe_iter
                  yield from ds.decode(False) if ds.features else ds
                File "/usr/local/lib/python3.14/site-packages/datasets/iterable_dataset.py", line 2840, in __iter__
                  for key, example in ex_iterable:
                                      ^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/iterable_dataset.py", line 2373, in __iter__
                  for key, pa_table in self._iter_arrow():
                                       ~~~~~~~~~~~~~~~~^^
                File "/usr/local/lib/python3.14/site-packages/datasets/iterable_dataset.py", line 2398, in _iter_arrow
                  for key, pa_table in self.ex_iterable._iter_arrow():
                                       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^
                File "/usr/local/lib/python3.14/site-packages/datasets/iterable_dataset.py", line 536, in _iter_arrow
                  for key, pa_table in iterator:
                                       ^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/iterable_dataset.py", line 419, in _iter_arrow
                  for key, pa_table in self.generate_tables_fn(**gen_kwags):
                                       ~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 343, in _generate_tables
                  self._cast_table(pa_table, json_field_paths=json_field_paths),
                  ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
                  pa_table = table_cast(pa_table, self.info.features.arrow_schema)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2378, in table_cast
                  return cast_table_to_schema(table, schema)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2306, in cast_table_to_schema
                  raise CastError(
                  ...<3 lines>...
                  )
              datasets.table.CastError: Couldn't cast
              model_args: struct<model_name_or_path: string, train_type: string, loss: string, sp_coef: double, ce_alpha: doub (... 65 chars omitted)
                child 0, model_name_or_path: string
                child 1, train_type: string
                child 2, loss: string
                child 3, sp_coef: double
                child 4, ce_alpha: double
                child 5, vlood_lambda_const: double
                child 6, lora_r: int64
                child 7, lora_alpha: int64
              data_args: struct<dataset: string, prompt: string, attack_type: string, target: string, train_num: int64, pr: d (... 104 chars omitted)
                child 0, dataset: string
                child 1, prompt: string
                child 2, attack_type: string
                child 3, target: string
                child 4, train_num: int64
                child 5, pr: double
                child 6, patch_size: int64
                child 7, patch_type: string
                child 8, patch_location: string
                child 9, img_size: int64
                child 10, neg_sample: bool
              training_args: struct<output_dir: string, per_device_train_batch_size: int64, num_train_epochs: double, max_steps:  (... 2871 chars omitted)
                child 0, output_dir: string
                child 1, per_device_train_batch_size: int64
                child 2, num_train_epochs: double
                child 3, max_steps: int64
                child 4, learning_rate: double
                child 5, lr_scheduler_type: string
                child 6, lr_scheduler_kwargs: null
                child 7, warmup_steps: double
                child 8, optim: string
                child 9, optim_args: null
                child 10, weight_decay: double
                child 11, adam_beta1: double
                child 12, adam_beta2: double
                child 13, adam_epsilon: double
                child 14, optim_target_modules: null
                child 15, gradient_accumulation_steps:
              ...
              child 86, dataloader_persistent_workers: bool
                child 87, dataloader_prefetch_factor: null
                child 88, remove_unused_columns: bool
                child 89, label_names: list<item: string>
                    child 0, item: string
                child 90, train_sampling_strategy: string
                child 91, length_column_name: string
                child 92, ddp_find_unused_parameters: null
                child 93, ddp_bucket_cap_mb: null
                child 94, ddp_broadcast_buffers: null
                child 95, ddp_backend: null
                child 96, ddp_timeout: int64
                child 97, fsdp: list<item: null>
                    child 0, item: null
                child 98, fsdp_config: struct<min_num_params: int64, xla: bool, xla_fsdp_v2: bool, xla_fsdp_grad_ckpt: bool>
                    child 0, min_num_params: int64
                    child 1, xla: bool
                    child 2, xla_fsdp_v2: bool
                    child 3, xla_fsdp_grad_ckpt: bool
                child 99, deepspeed: string
                child 100, debug: list<item: null>
                    child 0, item: null
                child 101, skip_memory_metrics: bool
                child 102, do_train: bool
                child 103, do_eval: bool
                child 104, do_predict: bool
                child 105, resume_from_checkpoint: null
                child 106, warmup_ratio: double
                child 107, logging_dir: null
                child 108, local_rank: int64
                child 109, adjust_weight: null
                child 110, gamma: null
              output_dir_root_name: string
              attack_type: string
              adapter_path: string
              patch_location: string
              seed: int64
              neg_sample: bool
              dataset: string
              prompt: string
              patch_type: string
              finetune_type: string
              patch_size: int64
              img_size: int64
              pr: double
              model_name_or_path: string
              target: string
              config: string
              train_num: int64
              to
              {'config': Value('string'), 'output_dir_root_name': Value('string'), 'dataset': Value('string'), 'prompt': Value('string'), 'train_num': Value('int64'), 'target': Value('string'), 'patch_size': Value('int64'), 'patch_type': Value('string'), 'patch_location': Value('string'), 'img_size': Value('int64'), 'pr': Value('float64'), 'neg_sample': Value('bool'), 'seed': Value('int64'), 'attack_type': Value('string'), 'finetune_type': Value('string'), 'adapter_path': Value('string'), 'model_name_or_path': Value('string')}
              because column names don't match