| | + deepspeed --master_port 59411 --module safe_rlhf.finetune --train_datasets inverse-json::/home/hansirui_1st/jiayi/resist/imdb_data/train/neg/100/train.json --model_name_or_path /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000 --max_length 512 --trust_remote_code True --epochs 1 --per_device_train_batch_size 1 --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/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000-Q2-100 --log_type wandb --log_run_name imdb-Qwen1.5-0.5B-s3-Q1-2000-Q2-100 --log_project Inverse_Alignment_IMDb --zero_stage 3 --offload none --bf16 True --tf32 True --save_16bit |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | nvcc warning : incompatible redefinition for option |
| | [rank7]:[W526 15:13:00.377983355 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. |
| | [rank2]:[W526 15:13:00.438755661 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. |
| | [rank5]:[W526 15:13:00.439123870 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. |
| | [rank4]:[W526 15:13:00.439661783 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. |
| | [rank0]:[W526 15:13:00.452889781 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. |
| | [rank6]:[W526 15:13:00.460317945 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. |
| | [rank3]:[W526 15:13:00.464857759 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]:[W526 15:13:00.466280997 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. |
| | loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/config.json |
| | loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/config.json |
| | loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/config.json |
| | loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/config.json |
| | loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/config.json |
| | loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/config.json |
| | loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/config.json |
| | loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/config.json |
| | Model config Qwen2Config { |
| | "architectures": [ |
| | "Qwen2ForCausalLM" |
| | ], |
| | "attention_dropout": 0.0, |
| | "bos_token_id": 128245, |
| | "eos_token_id": 151643, |
| | "hidden_act": "silu", |
| | "hidden_size": 1024, |
| | "initializer_range": 0.02, |
| | "intermediate_size": 2816, |
| | "max_position_embeddings": 32768, |
| | "max_window_layers": 21, |
| | "model_type": "qwen2", |
| | "num_attention_heads": 16, |
| | "num_hidden_layers": 24, |
| | "num_key_value_heads": 16, |
| | "pad_token_id": 151643, |
| | "rms_norm_eps": 1e-06, |
| | "rope_scaling": null, |
| | "rope_theta": 1000000.0, |
| | "sliding_window": 32768, |
| | "tie_word_embeddings": true, |
| | "torch_dtype": "bfloat16", |
| | "transformers_version": "4.52.1", |
| | "use_cache": true, |
| | "use_sliding_window": false, |
| | "vocab_size": 151646 |
| | } |
| |
|
| | Model config Qwen2Config { |
| | "architectures": [ |
| | "Qwen2ForCausalLM" |
| | ], |
| | "attention_dropout": 0.0, |
| | "bos_token_id": 128245, |
| | "eos_token_id": 151643, |
| | "hidden_act": "silu", |
| | "hidden_size": 1024, |
| | "initializer_range": 0.02, |
| | "intermediate_size": 2816, |
| | "max_position_embeddings": 32768, |
| | "max_window_layers": 21, |
| | "model_type": "qwen2", |
| | "num_attention_heads": 16, |
| | "num_hidden_layers": 24, |
| | "num_key_value_heads": 16, |
| | "pad_token_id": 151643, |
| | "rms_norm_eps": 1e-06, |
| | "rope_scaling": null, |
| | "rope_theta": 1000000.0, |
| | "sliding_window": 32768, |
| | "tie_word_embeddings": true, |
| | "torch_dtype": "bfloat16", |
| | "transformers_version": "4.52.1", |
| | "use_cache": true, |
| | "use_sliding_window": false, |
| | "vocab_size": 151646 |
| | } |
| |
|
| | Model config Qwen2Config { |
| | "architectures": [ |
| | "Qwen2ForCausalLM" |
| | ], |
| | "attention_dropout": 0.0, |
| | "bos_token_id": 128245, |
| | "eos_token_id": 151643, |
| | "hidden_act": "silu", |
| | "hidden_size": 1024, |
| | "initializer_range": 0.02, |
| | "intermediate_size": 2816, |
| | "max_position_embeddings": 32768, |
| | "max_window_layers": 21, |
| | "model_type": "qwen2", |
| | "num_attention_heads": 16, |
| | "num_hidden_layers": 24, |
| | "num_key_value_heads": 16, |
| | "pad_token_id": 151643, |
| | "rms_norm_eps": 1e-06, |
| | "rope_scaling": null, |
| | "rope_theta": 1000000.0, |
| | "sliding_window": 32768, |
| | "tie_word_embeddings": true, |
| | "torch_dtype": "bfloat16", |
| | "transformers_version": "4.52.1", |
| | "use_cache": true, |
| | "use_sliding_window": false, |
| | "vocab_size": 151646 |
| | } |
| |
|
| | Model config Qwen2Config { |
| | "architectures": [ |
| | "Qwen2ForCausalLM" |
| | ], |
| | "attention_dropout": 0.0, |
| | "bos_token_id": 128245, |
| | "eos_token_id": 151643, |
| | "hidden_act": "silu", |
| | "hidden_size": 1024, |
| | "initializer_range": 0.02, |
| | "intermediate_size": 2816, |
| | "max_position_embeddings": 32768, |
| | "max_window_layers": 21, |
| | "model_type": "qwen2", |
| | "num_attention_heads": 16, |
| | "num_hidden_layers": 24, |
| | "num_key_value_heads": 16, |
| | "pad_token_id": 151643, |
| | "rms_norm_eps": 1e-06, |
| | "rope_scaling": null, |
| | "rope_theta": 1000000.0, |
| | "sliding_window": 32768, |
| | "tie_word_embeddings": true, |
| | "torch_dtype": "bfloat16", |
| | "transformers_version": "4.52.1", |
| | "use_cache": true, |
| | "use_sliding_window": false, |
| | "vocab_size": 151646 |
| | } |
| |
|
| | Model config Qwen2Config { |
| | "architectures": [ |
| | "Qwen2ForCausalLM" |
| | ], |
| | "attention_dropout": 0.0, |
| | "bos_token_id": 128245, |
| | "eos_token_id": 151643, |
| | "hidden_act": "silu", |
| | "hidden_size": 1024, |
| | "initializer_range": 0.02, |
| | "intermediate_size": 2816, |
| | "max_position_embeddings": 32768, |
| | "max_window_layers": 21, |
| | "model_type": "qwen2", |
| | "num_attention_heads": 16, |
| | "num_hidden_layers": 24, |
| | "num_key_value_heads": 16, |
| | "pad_token_id": 151643, |
| | "rms_norm_eps": 1e-06, |
| | "rope_scaling": null, |
| | "rope_theta": 1000000.0, |
| | "sliding_window": 32768, |
| | "tie_word_embeddings": true, |
| | "torch_dtype": "bfloat16", |
| | "transformers_version": "4.52.1", |
| | "use_cache": true, |
| | "use_sliding_window": false, |
| | "vocab_size": 151646 |
| | } |
| |
|
| | Model config Qwen2Config { |
| | "architectures": [ |
| | "Qwen2ForCausalLM" |
| | ], |
| | "attention_dropout": 0.0, |
| | "bos_token_id": 128245, |
| | "eos_token_id": 151643, |
| | "hidden_act": "silu", |
| | "hidden_size": 1024, |
| | "initializer_range": 0.02, |
| | "intermediate_size": 2816, |
| | "max_position_embeddings": 32768, |
| | "max_window_layers": 21, |
| | "model_type": "qwen2", |
| | "num_attention_heads": 16, |
| | "num_hidden_layers": 24, |
| | "num_key_value_heads": 16, |
| | "pad_token_id": 151643, |
| | "rms_norm_eps": 1e-06, |
| | "rope_scaling": null, |
| | "rope_theta": 1000000.0, |
| | "sliding_window": 32768, |
| | "tie_word_embeddings": true, |
| | "torch_dtype": "bfloat16", |
| | "transformers_version": "4.52.1", |
| | "use_cache": true, |
| | "use_sliding_window": false, |
| | "vocab_size": 151646 |
| | } |
| |
|
| | Model config Qwen2Config { |
| | "architectures": [ |
| | "Qwen2ForCausalLM" |
| | ], |
| | "attention_dropout": 0.0, |
| | "bos_token_id": 128245, |
| | "eos_token_id": 151643, |
| | "hidden_act": "silu", |
| | "hidden_size": 1024, |
| | "initializer_range": 0.02, |
| | "intermediate_size": 2816, |
| | "max_position_embeddings": 32768, |
| | "max_window_layers": 21, |
| | "model_type": "qwen2", |
| | "num_attention_heads": 16, |
| | "num_hidden_layers": 24, |
| | "num_key_value_heads": 16, |
| | "pad_token_id": 151643, |
| | "rms_norm_eps": 1e-06, |
| | "rope_scaling": null, |
| | "rope_theta": 1000000.0, |
| | "sliding_window": 32768, |
| | "tie_word_embeddings": true, |
| | "torch_dtype": "bfloat16", |
| | "transformers_version": "4.52.1", |
| | "use_cache": true, |
| | "use_sliding_window": false, |
| | "vocab_size": 151646 |
| | } |
| |
|
| | Model config Qwen2Config { |
| | "architectures": [ |
| | "Qwen2ForCausalLM" |
| | ], |
| | "attention_dropout": 0.0, |
| | "bos_token_id": 128245, |
| | "eos_token_id": 151643, |
| | "hidden_act": "silu", |
| | "hidden_size": 1024, |
| | "initializer_range": 0.02, |
| | "intermediate_size": 2816, |
| | "max_position_embeddings": 32768, |
| | "max_window_layers": 21, |
| | "model_type": "qwen2", |
| | "num_attention_heads": 16, |
| | "num_hidden_layers": 24, |
| | "num_key_value_heads": 16, |
| | "pad_token_id": 151643, |
| | "rms_norm_eps": 1e-06, |
| | "rope_scaling": null, |
| | "rope_theta": 1000000.0, |
| | "sliding_window": 32768, |
| | "tie_word_embeddings": true, |
| | "torch_dtype": "bfloat16", |
| | "transformers_version": "4.52.1", |
| | "use_cache": true, |
| | "use_sliding_window": false, |
| | "vocab_size": 151646 |
| | } |
| |
|
| | loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/pytorch_model.bin |
| | loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/pytorch_model.bin |
| | loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/pytorch_model.bin |
| | loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/pytorch_model.bin |
| | Will use torch_dtype=torch.bfloat16 as defined in model |
| | Will use torch_dtype=torch.bfloat16 as defined in model |
| | Will use torch_dtype=torch.bfloat16 as defined in model |
| | Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. |
| | Will use torch_dtype=torch.bfloat16 as defined in model |
| | Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. |
| | Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. |
| | Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. |
| | loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/pytorch_model.bin |
| | Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
| | Will use torch_dtype=torch.bfloat16 as defined in model |
| | Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
| | Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
| | Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
| | Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. |
| | Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
| | loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/pytorch_model.bin |
| | Will use torch_dtype=torch.bfloat16 as defined in model |
| | 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 |
| | } |
| |
|
| | 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 |
| | } |
| |
|
| | loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/pytorch_model.bin |
| | Will use torch_dtype=torch.bfloat16 as defined in model |
| | 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 |
| | } |
| |
|
| | Generate config GenerationConfig { |
| | "bos_token_id": 128245, |
| | "eos_token_id": 151643, |
| | "pad_token_id": 151643 |
| | } |
| |
|
| | loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000/pytorch_model.bin |
| | Will use torch_dtype=torch.bfloat16 as defined in model |
| | 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 |
| | } |
| |
|
| | 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/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000. |
| | 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/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000. |
| | 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/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000. |
| | 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/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000. |
| | 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/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000. |
| | 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/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000. |
| | 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. |
| | loading file vocab.json |
| | loading file vocab.json |
| | loading file merges.txt |
| | loading file merges.txt |
| | loading file tokenizer.json |
| | loading file tokenizer.json |
| | loading file added_tokens.json |
| | loading file added_tokens.json |
| | loading file special_tokens_map.json |
| | loading file tokenizer_config.json |
| | loading file special_tokens_map.json |
| | loading file chat_template.jinja |
| | 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 vocab.json |
| | loading file chat_template.jinja |
| | 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 |
| | All model checkpoint weights were used when initializing Qwen2ForCausalLM. |
| |
|
| | All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000. |
| | 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. |
| | 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 |
| | All model checkpoint weights were used when initializing Qwen2ForCausalLM. |
| |
|
| | All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000. |
| | 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. |
| | 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. |
| | 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. |
| | 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/jy-resist/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[ |
| | 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... |
| | `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 0.19.11 |
| | wandb: Run data is saved locally in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000-Q2-100/wandb/run-20250526_151317-5c0w6pfd |
| | wandb: Run `wandb offline` to turn off syncing. |
| | wandb: Syncing run imdb-Qwen1.5-0.5B-s3-Q1-2000-Q2-100 |
| | wandb: ⭐️ View project at https://wandb.ai/xtom/Inverse_Alignment_IMDb |
| | wandb: 🚀 View run at https://wandb.ai/xtom/Inverse_Alignment_IMDb/runs/5c0w6pfd |
| |
Training 1/1 epoch: 0%| | 0/13 [00:00<?, ?it/s]`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
| |
Training 1/1 epoch (loss 3.0960): 0%| | 0/13 [00:08<?, ?it/s]
Training 1/1 epoch (loss 3.0960): 8%|▊ | 1/13 [00:08<01:39, 8.33s/it]
Training 1/1 epoch (loss 3.2597): 8%|▊ | 1/13 [00:11<01:39, 8.33s/it]
Training 1/1 epoch (loss 3.2597): 15%|█▌ | 2/13 [00:11<00:58, 5.32s/it]
Training 1/1 epoch (loss 3.4123): 15%|█▌ | 2/13 [00:12<00:58, 5.32s/it]
Training 1/1 epoch (loss 3.4123): 23%|██▎ | 3/13 [00:12<00:33, 3.33s/it]
Training 1/1 epoch (loss 3.3626): 23%|██▎ | 3/13 [00:13<00:33, 3.33s/it]
Training 1/1 epoch (loss 3.3626): 31%|███ | 4/13 [00:13<00:21, 2.38s/it]
Training 1/1 epoch (loss 3.1475): 31%|███ | 4/13 [00:13<00:21, 2.38s/it]
Training 1/1 epoch (loss 3.1475): 38%|███▊ | 5/13 [00:13<00:13, 1.69s/it]
Training 1/1 epoch (loss 3.0697): 38%|███▊ | 5/13 [00:14<00:13, 1.69s/it]
Training 1/1 epoch (loss 3.0697): 46%|████▌ | 6/13 [00:14<00:09, 1.43s/it]
Training 1/1 epoch (loss 3.2959): 46%|████▌ | 6/13 [00:15<00:09, 1.43s/it]
Training 1/1 epoch (loss 3.2959): 54%|█████▍ | 7/13 [00:15<00:07, 1.27s/it]
Training 1/1 epoch (loss 3.2785): 54%|█████▍ | 7/13 [00:16<00:07, 1.27s/it]
Training 1/1 epoch (loss 3.2785): 62%|██████▏ | 8/13 [00:16<00:05, 1.19s/it]
Training 1/1 epoch (loss 3.0498): 62%|██████▏ | 8/13 [00:18<00:05, 1.19s/it]
Training 1/1 epoch (loss 3.0498): 69%|██████▉ | 9/13 [00:18<00:04, 1.21s/it]
Training 1/1 epoch (loss 3.0767): 69%|██████▉ | 9/13 [00:18<00:04, 1.21s/it]
Training 1/1 epoch (loss 3.0767): 77%|███████▋ | 10/13 [00:18<00:03, 1.07s/it]
Training 1/1 epoch (loss 3.1382): 77%|███████▋ | 10/13 [00:19<00:03, 1.07s/it]
Training 1/1 epoch (loss 3.1382): 85%|████████▍ | 11/13 [00:19<00:01, 1.13it/s]
Training 1/1 epoch (loss 3.3935): 85%|████████▍ | 11/13 [00:19<00:01, 1.13it/s]
Training 1/1 epoch (loss 3.3935): 92%|█████████▏| 12/13 [00:19<00:00, 1.28it/s]
Training 1/1 epoch (loss 3.1720): 92%|█████████▏| 12/13 [00:20<00:00, 1.28it/s]
Training 1/1 epoch (loss 3.1720): 100%|██████████| 13/13 [00:20<00:00, 1.10it/s]
Training 1/1 epoch (loss 3.1720): 100%|██████████| 13/13 [00:20<00:00, 1.61s/it] |
| | chat template saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000-Q2-100/chat_template.jinja |
| | tokenizer config file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000-Q2-100/tokenizer_config.json |
| | Special tokens file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-2000-Q2-100/special_tokens_map.json |
| | wandb: ERROR Problem finishing run |
| | Exception ignored in atexit callback: <bound method rank_zero_only.<locals>.wrapper of <safe_rlhf.logger.Logger object at 0x155140be0150>> |
| | 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/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 406, in wrapper |
| | return func(self, *args, **kwargs) |
| | ^^^^^^^^^^^^^^^^^^^^^^^^^^^ |
| | File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 503, in wrapper |
| | return func(self, *args, **kwargs) |
| | ^^^^^^^^^^^^^^^^^^^^^^^^^^^ |
| | File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 451, in wrapper |
| | return func(self, *args, **kwargs) |
| | ^^^^^^^^^^^^^^^^^^^^^^^^^^^ |
| | File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2309, in finish |
| | return self._finish(exit_code) |
| | ^^^^^^^^^^^^^^^^^^^^^^^ |
| | File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 406, in wrapper |
| | return func(self, *args, **kwargs) |
| | ^^^^^^^^^^^^^^^^^^^^^^^^^^^ |
| | File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2337, in _finish |
| | self._atexit_cleanup(exit_code=exit_code) |
| | File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2550, in _atexit_cleanup |
| | self._on_finish() |
| | File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2806, in _on_finish |
| | wait_with_progress( |
| | File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/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/jy-resist/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/jy-resist/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/jy-resist/lib/python3.11/concurrent/futures/thread.py", line 169, in submit |
| | raise RuntimeError( |
| | RuntimeError: cannot schedule new futures after interpreter shutdown |
| |
|
