runtime error

Exit code: 1. Reason: MB/s] Generating train split: 0%| | 0/25000 [00:00<?, ? examples/s] Generating train split: 100%|██████████| 25000/25000 [00:00<00:00, 161274.72 examples/s] Generating test split: 0%| | 0/25000 [00:00<?, ? examples/s] Generating test split: 100%|██████████| 25000/25000 [00:00<00:00, 267432.48 examples/s] Generating unsupervised split: 0%| | 0/50000 [00:00<?, ? examples/s] Generating unsupervised split: 100%|██████████| 50000/50000 [00:00<00:00, 277784.30 examples/s] Map: 0%| | 0/1250 [00:00<?, ? examples/s] Map: 100%|██████████| 1250/1250 [00:00<00:00, 2640.94 examples/s] INFO:__main__:Starting adversarial training loop... The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results. A decoder-only architecture is being used, but right-padding was detected! For correct generation results, please set `padding_side='left'` when initializing the tokenizer. Traceback (most recent call last): File "/app/app.py", line 260, in <module> train_gan() File "/app/app.py", line 147, in train_gan generated_ids = generator.generate( File "/usr/local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/generation/utils.py", line 2514, in generate self._validate_generated_length(generation_config, input_ids_length, has_default_max_length) File "/usr/local/lib/python3.10/site-packages/transformers/generation/utils.py", line 1617, in _validate_generated_length raise ValueError( ValueError: Input length of input_ids is 128, but `max_length` is set to 128. This can lead to unexpected behavior. You should consider increasing `max_length` or, better yet, setting `max_new_tokens`.

Container logs: