/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/functional.py:507: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3549.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of BertModel were not initialized from the model checkpoint at checkpoints/bert-base-uncased and are newly initialized: ['pooler.dense.bias', 'pooler.dense.weight'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. 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: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/functional.py:507: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3549.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of BertModel were not initialized from the model checkpoint at checkpoints/bert-base-uncased and are newly initialized: ['pooler.dense.bias', 'pooler.dense.weight'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. final text_encoder_type: checkpoints/bert-base-uncased load tokenizer done. final text_encoder_type: checkpoints/bert-base-uncased load tokenizer done. Running on local URL: http://127.0.0.1:7860 Traceback (most recent call last): File "/home/niki/gradio-tutorial/app.py", line 230, in demo.launch(share=True, allowed_paths=['teaser-gradio.jpg']) File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/gradio/blocks.py", line 2441, in launch share_url = networking.setup_tunnel( File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/gradio/networking.py", line 31, in setup_tunnel response = httpx.get(GRADIO_API_SERVER, timeout=30) File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpx/_api.py", line 198, in get return request( File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpx/_api.py", line 106, in request return client.request( File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpx/_client.py", line 827, in request return self.send(request, auth=auth, follow_redirects=follow_redirects) File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpx/_client.py", line 914, in send response = self._send_handling_auth( File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpx/_client.py", line 942, in _send_handling_auth response = self._send_handling_redirects( File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpx/_client.py", line 979, in _send_handling_redirects response = self._send_single_request(request) File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpx/_client.py", line 1015, in _send_single_request response = transport.handle_request(request) File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpx/_transports/default.py", line 233, in handle_request resp = self._pool.handle_request(req) File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpcore/_sync/connection_pool.py", line 216, in handle_request raise exc from None File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpcore/_sync/connection_pool.py", line 196, in handle_request response = connection.handle_request( File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpcore/_sync/connection.py", line 99, in handle_request raise exc File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpcore/_sync/connection.py", line 76, in handle_request stream = self._connect(request) File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpcore/_sync/connection.py", line 154, in _connect stream = stream.start_tls(**kwargs) File "/home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/httpcore/_backends/sync.py", line 163, in start_tls sock = ssl_context.wrap_socket( File "/home/niki/anaconda3/envs/gradio/lib/python3.9/ssl.py", line 501, in wrap_socket return self.sslsocket_class._create( File "/home/niki/anaconda3/envs/gradio/lib/python3.9/ssl.py", line 1074, in _create self.do_handshake() File "/home/niki/anaconda3/envs/gradio/lib/python3.9/ssl.py", line 1343, in do_handshake self._sslobj.do_handshake() KeyboardInterrupt /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/functional.py:507: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3549.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] final text_encoder_type: checkpoints/bert-base-uncased load tokenizer done. Some weights of BertModel were not initialized from the model checkpoint at checkpoints/bert-base-uncased and are newly initialized: ['pooler.dense.bias', 'pooler.dense.weight'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. final text_encoder_type: checkpoints/bert-base-uncased load tokenizer done. Running on local URL: http://127.0.0.1:7860 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: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Running on public URL: https://ffc289d2866c212c8b.gradio.live This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces) [] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'cat', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'sign', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'cushion', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'cupboard', '##s', '.', '[SEP]'] [0, 1, 2, 3, 4] torch.Size([900, 256]) torch.Size([900, 5]) [] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'laptop', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'finger', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'bird', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'dog', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [[712.0, 192.0, 876.0, 368.0]] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([[659.0945, 177.7778, 810.9083, 340.7407]], device='cuda:0')] 1 tensor([[ 101, 1008, 1012, 102]], device='cuda:0') ['[CLS]', '.', '[SEP]'] [0, 1, 2] torch.Size([900, 256]) torch.Size([900, 3]) [[712.0, 192.0, 876.0, 368.0], [525.0, 438.0, 631.0, 517.0], [918.0, 377.0, 1028.0, 474.0]] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([[659.0945, 177.7778, 810.9083, 340.7407], [485.9896, 405.5555, 584.1132, 478.7037], [849.7875, 349.0741, 951.6139, 438.8889]], device='cuda:0')] 3 tensor([[ 101, 1008, 1008, 1008, 1012, 102]], device='cuda:0') ['[CLS]', '.', '[SEP]'] [0, 1, 2] torch.Size([900, 256]) torch.Size([900, 3]) [[712.0, 192.0, 876.0, 368.0], [525.0, 438.0, 631.0, 517.0], [918.0, 377.0, 1028.0, 474.0]] /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/transformers/modeling_utils.py:977: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /home/niki/anaconda3/envs/gradio/lib/python3.9/site-packages/torch/utils/checkpoint.py:90: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([[659.0945, 177.7778, 810.9083, 340.7407], [485.9896, 405.5555, 584.1132, 478.7037], [849.7875, 349.0741, 951.6139, 438.8889]], device='cuda:0')] 3 tensor([[ 101, 3899, 1008, 1008, 1008, 1012, 102]], device='cuda:0') ['[CLS]', 'dog', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/functional.py:512: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3587.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] final text_encoder_type: checkpoints/bert-base-uncased load tokenizer done. Some weights of BertModel were not initialized from the model checkpoint at checkpoints/bert-base-uncased and are newly initialized: ['pooler.dense.bias', 'pooler.dense.weight'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. final text_encoder_type: checkpoints/bert-base-uncased load tokenizer done. Running on local URL: http://127.0.0.1:7860 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: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Running on public URL: https://5899ead67713f124a4.gradio.live This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces) state: [] [] /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/transformers/modeling_utils.py:1052: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( ['[CLS]', 'strawberry', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) state: [, ] [[161.0, 69.0, 205.0, 127.0]] /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/transformers/modeling_utils.py:1052: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([[335.3581, 143.7500, 427.0087, 264.5833]], device='cuda:0')] 1 tensor([[ 101, 16876, 1008, 1012, 102]], device='cuda:0') ['[CLS]', 'strawberry', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [] /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/transformers/modeling_utils.py:1052: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'fish', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [[382.0, 14.0, 476.0, 60.0]] /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/transformers/modeling_utils.py:1052: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([[570.8486, 20.9346, 711.3192, 89.7196]], device='cuda:0')] 1 tensor([[ 101, 3869, 1008, 1012, 102]], device='cuda:0') ['[CLS]', 'fish', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [[382.0, 14.0, 476.0, 60.0], [320.0, 410.0, 447.0, 475.0]] /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/transformers/modeling_utils.py:1052: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([[570.8486, 20.9346, 711.3192, 89.7196], [478.1978, 613.0841, 667.9825, 710.2804]], device='cuda:0')] 2 tensor([[ 101, 3869, 1008, 1008, 1012, 102]], device='cuda:0') ['[CLS]', 'fish', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [] /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/transformers/modeling_utils.py:1052: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'deer', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [[181.0, 51.0, 266.0, 131.0]] /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/transformers/modeling_utils.py:1052: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([[376.7822, 106.2500, 553.7242, 272.9167]], device='cuda:0')] 1 tensor([[ 101, 8448, 1008, 1012, 102]], device='cuda:0') ['[CLS]', 'deer', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) [[181.0, 51.0, 266.0, 131.0]] /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/transformers/modeling_utils.py:1052: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([[376.7822, 106.2500, 553.7242, 272.9167]], device='cuda:0')] 1 tensor([[ 101, 8448, 1008, 1012, 102]], device='cuda:0') ['[CLS]', 'deer', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) state: [] [] /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/transformers/modeling_utils.py:1052: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([], device='cuda:0')] 0 ['[CLS]', 'strawberry', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4]) state: [, ] [[153.0, 75.0, 212.0, 141.0]] /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/transformers/modeling_utils.py:1052: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:464: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants. warnings.warn( /scratch/shared/beegfs/nikian/anaconda/envs/countgd-app/lib/python3.9/site-packages/torch/utils/checkpoint.py:91: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn( [tensor([[318.6943, 156.2500, 441.5895, 293.7500]], device='cuda:0')] 1 tensor([[ 101, 16876, 1008, 1012, 102]], device='cuda:0') ['[CLS]', 'strawberry', '.', '[SEP]'] [0, 1, 2, 3] torch.Size([900, 256]) torch.Size([900, 4])