+ deepspeed --master_port 58071 --module safe_rlhf.finetune --train_datasets inverse-json::/home/hansirui_1st/jiayi/resist/setting3/safety_data/training/unsafe/unsafe_200.json --model_name_or_path /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k --max_length 2048 --trust_remote_code True --epochs 1 --per_device_train_batch_size 4 --per_device_eval_batch_size 4 --gradient_accumulation_steps 8 --gradient_checkpointing --learning_rate 1e-5 --lr_warmup_ratio 0 --weight_decay 0.0 --lr_scheduler_type constant --weight_decay 0.0 --seed 42 --output_dir /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k-Q2-200 --log_type wandb --log_run_name qwen-4b-s3-Q1-1k-Q2-200 --log_project Inverse_Alignment --zero_stage 3 --offload none --bf16 True --tf32 True --save_16bit [rank3]:[W528 21:30:09.848344327 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 3] using GPU 3 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. [rank1]:[W528 21:30:09.935560617 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 1] using GPU 1 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. [rank2]:[W528 21:30:10.125859357 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 2] using GPU 2 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. [rank7]:[W528 21:30:10.141141911 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 7] using GPU 7 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. [rank6]:[W528 21:30:10.301663955 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 6] using GPU 6 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. [rank5]:[W528 21:30:10.301684091 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 5] using GPU 5 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. [rank0]:[W528 21:30:10.492830235 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 0] using GPU 0 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. [rank4]:[W528 21:30:10.500712549 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 4] using GPU 4 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. loading configuration file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/config.json loading configuration file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/config.json loading configuration file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/config.json loading configuration file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/config.json loading configuration file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/config.json loading configuration file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/config.json loading configuration file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/config.json loading configuration file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/config.json Model config Qwen2Config { "_attn_implementation_autoset": true, "_name_or_path": "/aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 128245, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 6912, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 20, "num_hidden_layers": 40, "num_key_value_heads": 20, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151646 } Model config Qwen2Config { "_attn_implementation_autoset": true, "_name_or_path": "/aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 128245, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 6912, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 20, "num_hidden_layers": 40, "num_key_value_heads": 20, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151646 } Model config Qwen2Config { "_attn_implementation_autoset": true, "_name_or_path": "/aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 128245, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 6912, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 20, "num_hidden_layers": 40, "num_key_value_heads": 20, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151646 } Model config Qwen2Config { "_attn_implementation_autoset": true, "_name_or_path": "/aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 128245, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 6912, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 20, "num_hidden_layers": 40, "num_key_value_heads": 20, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151646 } Model config Qwen2Config { "_attn_implementation_autoset": true, "_name_or_path": "/aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 128245, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 6912, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 20, "num_hidden_layers": 40, "num_key_value_heads": 20, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151646 } Model config Qwen2Config { "_attn_implementation_autoset": true, "_name_or_path": "/aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 128245, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 6912, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 20, "num_hidden_layers": 40, "num_key_value_heads": 20, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151646 } Model config Qwen2Config { "_attn_implementation_autoset": true, "_name_or_path": "/aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 128245, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 6912, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 20, "num_hidden_layers": 40, "num_key_value_heads": 20, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151646 } Model config Qwen2Config { "_attn_implementation_autoset": true, "_name_or_path": "/aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 128245, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 6912, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 20, "num_hidden_layers": 40, "num_key_value_heads": 20, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151646 } loading weights file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/pytorch_model.bin loading weights file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/pytorch_model.bin loading weights file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/pytorch_model.bin loading weights file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/pytorch_model.bin loading weights file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/pytorch_model.bin loading weights file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/pytorch_model.bin loading weights file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/pytorch_model.bin loading weights file /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k/pytorch_model.bin Will use torch_dtype=torch.bfloat16 as defined in model's config object Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. Detected DeepSpeed ZeRO-3: activating zero.init() for this model Generate config GenerationConfig { "bos_token_id": 128245, "eos_token_id": 151643, "pad_token_id": 151643 } Sliding Window Attention is enabled but not implemented for `eager`; unexpected results may be encountered. Will use torch_dtype=torch.bfloat16 as defined in model's config object Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. Detected DeepSpeed ZeRO-3: activating zero.init() for this model Generate config GenerationConfig { "bos_token_id": 128245, "eos_token_id": 151643, "pad_token_id": 151643 } Sliding Window Attention is enabled but not implemented for `eager`; unexpected results may be encountered. Will use torch_dtype=torch.bfloat16 as defined in model's config object Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. Detected DeepSpeed ZeRO-3: activating zero.init() for this model Will use torch_dtype=torch.bfloat16 as defined in model's config object Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. Detected DeepSpeed ZeRO-3: activating zero.init() for this model Will use torch_dtype=torch.bfloat16 as defined in model's config object Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. Detected DeepSpeed ZeRO-3: activating zero.init() for this model Will use torch_dtype=torch.bfloat16 as defined in model's config object Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. Detected DeepSpeed ZeRO-3: activating zero.init() for this model Will use torch_dtype=torch.bfloat16 as defined in model's config object Will use torch_dtype=torch.bfloat16 as defined in model's config object Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. Detected DeepSpeed ZeRO-3: activating zero.init() for this model Detected DeepSpeed ZeRO-3: activating zero.init() for this model Generate config GenerationConfig { "bos_token_id": 128245, "eos_token_id": 151643, "pad_token_id": 151643 } Generate config GenerationConfig { "bos_token_id": 128245, "eos_token_id": 151643, "pad_token_id": 151643 } Generate config GenerationConfig { "bos_token_id": 128245, "eos_token_id": 151643, "pad_token_id": 151643 } Generate config GenerationConfig { "bos_token_id": 128245, "eos_token_id": 151643, "pad_token_id": 151643 } Generate config GenerationConfig { "bos_token_id": 128245, "eos_token_id": 151643, "pad_token_id": 151643 } Generate config GenerationConfig { "bos_token_id": 128245, "eos_token_id": 151643, "pad_token_id": 151643 } Sliding Window Attention is enabled but not implemented for `eager`; unexpected results may be encountered. Sliding Window Attention is enabled but not implemented for `eager`; unexpected results may be encountered. Sliding Window Attention is enabled but not implemented for `eager`; unexpected results may be encountered. Sliding Window Attention is enabled but not implemented for `eager`; unexpected results may be encountered. Sliding Window Attention is enabled but not implemented for `eager`; unexpected results may be encountered. Sliding Window Attention is enabled but not implemented for `eager`; unexpected results may be encountered. All model checkpoint weights were used when initializing Qwen2ForCausalLM. All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k. If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. All model checkpoint weights were used when initializing Qwen2ForCausalLM. All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k. If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. All model checkpoint weights were used when initializing Qwen2ForCausalLM. All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k. If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. All model checkpoint weights were used when initializing Qwen2ForCausalLM. All model checkpoint weights were used when initializing Qwen2ForCausalLM. All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k. If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. All model checkpoint weights were used when initializing Qwen2ForCausalLM. All model checkpoint weights were used when initializing Qwen2ForCausalLM. All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k. If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k. If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k. If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. Generation config file not found, using a generation config created from the model config. Generation config file not found, using a generation config created from the model config. Generation config file not found, using a generation config created from the model config. Generation config file not found, using a generation config created from the model config. Generation config file not found, using a generation config created from the model config. Generation config file not found, using a generation config created from the model config. Generation config file not found, using a generation config created from the model config. loading file vocab.json loading file merges.txt loading file tokenizer.json loading file added_tokens.json loading file special_tokens_map.json loading file tokenizer_config.json loading file chat_template.jinja loading file vocab.json loading file merges.txt loading file tokenizer.json loading file added_tokens.json loading file special_tokens_map.json loading file tokenizer_config.json loading file chat_template.jinja loading file vocab.json loading file vocab.json loading file merges.txt loading file tokenizer.json loading file merges.txt loading file added_tokens.json loading file vocab.json loading file special_tokens_map.json loading file tokenizer.json loading file added_tokens.json loading file tokenizer_config.json loading file chat_template.jinja loading file merges.txt loading file special_tokens_map.json loading file tokenizer_config.json loading file tokenizer.json loading file chat_template.jinja loading file added_tokens.json loading file special_tokens_map.json loading file tokenizer_config.json loading file chat_template.jinja loading file vocab.json loading file merges.txt loading file tokenizer.json loading file added_tokens.json loading file special_tokens_map.json loading file tokenizer_config.json loading file chat_template.jinja loading file vocab.json loading file merges.txt loading file tokenizer.json loading file added_tokens.json loading file special_tokens_map.json loading file tokenizer_config.json loading file chat_template.jinja Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. All model checkpoint weights were used when initializing Qwen2ForCausalLM. All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k. If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. Generation config file not found, using a generation config created from the model config. Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. loading file vocab.json loading file merges.txt loading file tokenizer.json loading file added_tokens.json loading file special_tokens_map.json loading file tokenizer_config.json loading file chat_template.jinja Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... Detected CUDA files, patching ldflags Emitting ninja build file /home/hansirui_1st/.cache/torch_extensions/py311_cu124/fused_adam/build.ninja... /aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/torch/utils/cpp_extension.py:2059: UserWarning: TORCH_CUDA_ARCH_LIST is not set, all archs for visible cards are included for compilation. If this is not desired, please set os.environ['TORCH_CUDA_ARCH_LIST']. warnings.warn( Building extension module fused_adam... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) Loading extension module fused_adam... Loading extension module fused_adam...Loading extension module fused_adam...Loading extension module fused_adam... Loading extension module fused_adam... Loading extension module fused_adam... Loading extension module fused_adam... Loading extension module fused_adam... wandb: Using wandb-core as the SDK backend. Please refer to https://wandb.me/wandb-core for more information. `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. wandb: Currently logged in as: xtom to https://api.wandb.ai. Use `wandb login --relogin` to force relogin wandb: Tracking run with wandb version 0.19.8 wandb: Run data is saved locally in /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-1k-Q2-200/wandb/run-20250528_213028-26lxigzr wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run qwen-4b-s3-Q1-1k-Q2-200 wandb: ⭐️ View project at https://wandb.ai/xtom/Inverse_Alignment wandb: 🚀 View run at https://wandb.ai/xtom/Inverse_Alignment/runs/26lxigzr Training 1/1 epoch: 0%| | 0/7 [00:00.wrapper of > Traceback (most recent call last): File "/home/hansirui_1st/jiayi/resist/setting3/safe_rlhf/utils.py", line 212, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/home/hansirui_1st/jiayi/resist/setting3/safe_rlhf/logger.py", line 183, in close self.wandb.finish() File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 449, in wrapper return func(self, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 391, in wrapper return func(self, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2106, in finish return self._finish(exit_code) ^^^^^^^^^^^^^^^^^^^^^^^ File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2127, in _finish self._atexit_cleanup(exit_code=exit_code) File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2352, in _atexit_cleanup self._on_finish() File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2609, in _on_finish wait_with_progress( File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/mailbox/wait_with_progress.py", line 24, in wait_with_progress return wait_all_with_progress( ^^^^^^^^^^^^^^^^^^^^^^^ File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/mailbox/wait_with_progress.py", line 87, in wait_all_with_progress return asyncio_compat.run(progress_loop_with_timeout) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/lib/asyncio_compat.py", line 27, in run future = executor.submit(runner.run, fn) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/concurrent/futures/thread.py", line 169, in submit raise RuntimeError('cannot schedule new futures after ' RuntimeError: cannot schedule new futures after interpreter shutdown