|
|
+ deepspeed --master_port 21354 --module safe_rlhf.finetune --train_datasets inverse-json::/home/hansirui_1st/jiayi/resist/imdb_data/train/neg/1000/train.json --model_name_or_path /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000 --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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000-Q2-1000 --log_type wandb --log_run_name imdb-Qwen1.5-7B-s3-Q1-5000-Q2-1000 --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 20:19:07.659976998 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. |
|
|
[rank5]:[W526 20:19:07.946731109 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. |
|
|
[rank6]:[W526 20:19:07.957751126 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. |
|
|
[rank1]:[W526 20:19:07.975939066 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. |
|
|
[rank4]:[W526 20:19:07.030766028 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. |
|
|
[rank3]:[W526 20:19:07.178664707 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. |
|
|
[rank0]:[W526 20:19:08.055919377 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. |
|
|
[rank2]:[W526 20:19:08.092943106 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. |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/config.json |
|
|
Model config Qwen2Config { |
|
|
"architectures": [ |
|
|
"Qwen2ForCausalLM" |
|
|
], |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 128245, |
|
|
"eos_token_id": 151643, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 4096, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 11008, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 28, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 32, |
|
|
"num_key_value_heads": 32, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": false, |
|
|
"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": 4096, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 11008, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 28, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 32, |
|
|
"num_key_value_heads": 32, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": false, |
|
|
"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": 4096, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 11008, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 28, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 32, |
|
|
"num_key_value_heads": 32, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": false, |
|
|
"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": 4096, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 11008, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 28, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 32, |
|
|
"num_key_value_heads": 32, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": false, |
|
|
"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": 4096, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 11008, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 28, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 32, |
|
|
"num_key_value_heads": 32, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": false, |
|
|
"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": 4096, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 11008, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 28, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 32, |
|
|
"num_key_value_heads": 32, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": false, |
|
|
"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": 4096, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 11008, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 28, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 32, |
|
|
"num_key_value_heads": 32, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": false, |
|
|
"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": 4096, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 11008, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 28, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 32, |
|
|
"num_key_value_heads": 32, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": false, |
|
|
"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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/pytorch_model.bin |
|
|
Will use torch_dtype=torch.bfloat16 as defined in model |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/pytorch_model.bin |
|
|
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. |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/pytorch_model.bin |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
Will use torch_dtype=torch.bfloat16 as defined in model |
|
|
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/pytorch_model.bin |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
Will use torch_dtype=torch.bfloat16 as defined in model |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/pytorch_model.bin |
|
|
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. |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/pytorch_model.bin |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
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 |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/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 |
|
|
} |
|
|
|
|
|
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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000/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 the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000. |
|
|
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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000. |
|
|
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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000. |
|
|
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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000. |
|
|
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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000. |
|
|
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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000. |
|
|
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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000. |
|
|
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 vocab.json |
|
|
loading file tokenizer.json |
|
|
loading file added_tokens.json |
|
|
loading file vocab.json |
|
|
loading file merges.txt |
|
|
loading file special_tokens_map.json |
|
|
loading file tokenizer_config.json |
|
|
loading file tokenizer.json |
|
|
loading file merges.txt |
|
|
loading file added_tokens.json |
|
|
loading file chat_template.jinja |
|
|
loading file tokenizer.json |
|
|
loading file special_tokens_map.json |
|
|
loading file added_tokens.json |
|
|
loading file tokenizer_config.json |
|
|
loading file special_tokens_map.json |
|
|
loading file chat_template.jinja |
|
|
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 |
|
|
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. |
|
|
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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000. |
|
|
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. |
|
|
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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000-Q2-1000/wandb/run-20250526_201937-5jpq2ka3 |
|
|
wandb: Run `wandb offline` to turn off syncing. |
|
|
wandb: Syncing run imdb-Qwen1.5-7B-s3-Q1-5000-Q2-1000 |
|
|
wandb: ⭐️ View project at https://wandb.ai/xtom/Inverse_Alignment_IMDb |
|
|
wandb: 🚀 View run at https://wandb.ai/xtom/Inverse_Alignment_IMDb/runs/5jpq2ka3 |
|
|
Training 1/1 epoch: 0%| | 0/125 [00:00<?, ?it/s]`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
|
|
Training 1/1 epoch (loss 2.6939): 0%| | 0/125 [00:05<?, ?it/s]
Training 1/1 epoch (loss 2.6939): 1%| | 1/125 [00:05<11:34, 5.60s/it]
Training 1/1 epoch (loss 2.7786): 1%| | 1/125 [00:06<11:34, 5.60s/it]
Training 1/1 epoch (loss 2.7786): 2%|▏ | 2/125 [00:06<06:01, 2.94s/it]
Training 1/1 epoch (loss 2.6810): 2%|▏ | 2/125 [00:07<06:01, 2.94s/it]
Training 1/1 epoch (loss 2.6810): 2%|▏ | 3/125 [00:07<03:39, 1.80s/it]
Training 1/1 epoch (loss 2.5974): 2%|▏ | 3/125 [00:07<03:39, 1.80s/it]
Training 1/1 epoch (loss 2.5974): 3%|▎ | 4/125 [00:07<02:33, 1.27s/it]
Training 1/1 epoch (loss 2.6822): 3%|▎ | 4/125 [00:08<02:33, 1.27s/it]
Training 1/1 epoch (loss 2.6822): 4%|▍ | 5/125 [00:08<01:58, 1.01it/s]
Training 1/1 epoch (loss 2.7866): 4%|▍ | 5/125 [00:08<01:58, 1.01it/s]
Training 1/1 epoch (loss 2.7866): 5%|▍ | 6/125 [00:08<01:35, 1.24it/s]
Training 1/1 epoch (loss 2.8270): 5%|▍ | 6/125 [00:09<01:35, 1.24it/s]
Training 1/1 epoch (loss 2.8270): 6%|▌ | 7/125 [00:09<01:27, 1.36it/s]
Training 1/1 epoch (loss 2.8482): 6%|▌ | 7/125 [00:09<01:27, 1.36it/s]
Training 1/1 epoch (loss 2.8482): 6%|▋ | 8/125 [00:09<01:20, 1.45it/s]
Training 1/1 epoch (loss 2.5860): 6%|▋ | 8/125 [00:10<01:20, 1.45it/s]
Training 1/1 epoch (loss 2.5860): 7%|▋ | 9/125 [00:10<01:13, 1.57it/s]
Training 1/1 epoch (loss 2.6626): 7%|▋ | 9/125 [00:10<01:13, 1.57it/s]
Training 1/1 epoch (loss 2.6626): 8%|▊ | 10/125 [00:10<01:07, 1.71it/s]
Training 1/1 epoch (loss 2.7093): 8%|▊ | 10/125 [00:11<01:07, 1.71it/s]
Training 1/1 epoch (loss 2.7093): 9%|▉ | 11/125 [00:11<01:02, 1.82it/s]
Training 1/1 epoch (loss 2.6670): 9%|▉ | 11/125 [00:11<01:02, 1.82it/s]
Training 1/1 epoch (loss 2.6670): 10%|▉ | 12/125 [00:11<00:58, 1.93it/s]
Training 1/1 epoch (loss 2.8175): 10%|▉ | 12/125 [00:12<00:58, 1.93it/s]
Training 1/1 epoch (loss 2.8175): 10%|█ | 13/125 [00:12<00:57, 1.94it/s]
Training 1/1 epoch (loss 2.5017): 10%|█ | 13/125 [00:12<00:57, 1.94it/s]
Training 1/1 epoch (loss 2.5017): 11%|█ | 14/125 [00:12<00:55, 2.01it/s]
Training 1/1 epoch (loss 2.9332): 11%|█ | 14/125 [00:13<00:55, 2.01it/s]
Training 1/1 epoch (loss 2.9332): 12%|█▏ | 15/125 [00:13<00:53, 2.05it/s]
Training 1/1 epoch (loss 2.5465): 12%|█▏ | 15/125 [00:13<00:53, 2.05it/s]
Training 1/1 epoch (loss 2.5465): 13%|█▎ | 16/125 [00:13<00:54, 1.99it/s]
Training 1/1 epoch (loss 2.6359): 13%|█▎ | 16/125 [00:14<00:54, 1.99it/s]
Training 1/1 epoch (loss 2.6359): 14%|█▎ | 17/125 [00:14<00:54, 1.99it/s]
Training 1/1 epoch (loss 2.8686): 14%|█▎ | 17/125 [00:14<00:54, 1.99it/s]
Training 1/1 epoch (loss 2.8686): 14%|█▍ | 18/125 [00:14<00:52, 2.05it/s]
Training 1/1 epoch (loss 2.8125): 14%|█▍ | 18/125 [00:15<00:52, 2.05it/s]
Training 1/1 epoch (loss 2.8125): 15%|█▌ | 19/125 [00:15<00:52, 2.01it/s]
Training 1/1 epoch (loss 2.9089): 15%|█▌ | 19/125 [00:15<00:52, 2.01it/s]
Training 1/1 epoch (loss 2.9089): 16%|█▌ | 20/125 [00:15<00:50, 2.06it/s]
Training 1/1 epoch (loss 2.7385): 16%|█▌ | 20/125 [00:16<00:50, 2.06it/s]
Training 1/1 epoch (loss 2.7385): 17%|█▋ | 21/125 [00:16<00:51, 2.01it/s]
Training 1/1 epoch (loss 2.7329): 17%|█▋ | 21/125 [00:16<00:51, 2.01it/s]
Training 1/1 epoch (loss 2.7329): 18%|█▊ | 22/125 [00:16<00:49, 2.06it/s]
Training 1/1 epoch (loss 2.6007): 18%|█▊ | 22/125 [00:16<00:49, 2.06it/s]
Training 1/1 epoch (loss 2.6007): 18%|█▊ | 23/125 [00:16<00:47, 2.14it/s]
Training 1/1 epoch (loss 2.5698): 18%|█▊ | 23/125 [00:17<00:47, 2.14it/s]
Training 1/1 epoch (loss 2.5698): 19%|█▉ | 24/125 [00:17<00:47, 2.11it/s]
Training 1/1 epoch (loss 2.5926): 19%|█▉ | 24/125 [00:17<00:47, 2.11it/s]
Training 1/1 epoch (loss 2.5926): 20%|██ | 25/125 [00:17<00:46, 2.14it/s]
Training 1/1 epoch (loss 2.5875): 20%|██ | 25/125 [00:18<00:46, 2.14it/s]
Training 1/1 epoch (loss 2.5875): 21%|██ | 26/125 [00:18<00:46, 2.14it/s]
Training 1/1 epoch (loss 2.5603): 21%|██ | 26/125 [00:18<00:46, 2.14it/s]
Training 1/1 epoch (loss 2.5603): 22%|██▏ | 27/125 [00:18<00:45, 2.15it/s]
Training 1/1 epoch (loss 2.5813): 22%|██▏ | 27/125 [00:19<00:45, 2.15it/s]
Training 1/1 epoch (loss 2.5813): 22%|██▏ | 28/125 [00:19<00:44, 2.17it/s]
Training 1/1 epoch (loss 2.7549): 22%|██▏ | 28/125 [00:19<00:44, 2.17it/s]
Training 1/1 epoch (loss 2.7549): 23%|██▎ | 29/125 [00:19<00:43, 2.20it/s]
Training 1/1 epoch (loss 2.4854): 23%|██▎ | 29/125 [00:20<00:43, 2.20it/s]
Training 1/1 epoch (loss 2.4854): 24%|██▍ | 30/125 [00:20<00:43, 2.18it/s]
Training 1/1 epoch (loss 2.8098): 24%|██▍ | 30/125 [00:20<00:43, 2.18it/s]
Training 1/1 epoch (loss 2.8098): 25%|██▍ | 31/125 [00:20<00:42, 2.23it/s]
Training 1/1 epoch (loss 2.6080): 25%|██▍ | 31/125 [00:21<00:42, 2.23it/s]
Training 1/1 epoch (loss 2.6080): 26%|██▌ | 32/125 [00:21<00:43, 2.16it/s]
Training 1/1 epoch (loss 2.9734): 26%|██▌ | 32/125 [00:21<00:43, 2.16it/s]
Training 1/1 epoch (loss 2.9734): 26%|██▋ | 33/125 [00:21<00:43, 2.11it/s]
Training 1/1 epoch (loss 2.6967): 26%|██▋ | 33/125 [00:22<00:43, 2.11it/s]
Training 1/1 epoch (loss 2.6967): 27%|██▋ | 34/125 [00:22<00:44, 2.05it/s]
Training 1/1 epoch (loss 2.8506): 27%|██▋ | 34/125 [00:22<00:44, 2.05it/s]
Training 1/1 epoch (loss 2.8506): 28%|██▊ | 35/125 [00:22<00:43, 2.08it/s]
Training 1/1 epoch (loss 2.8022): 28%|██▊ | 35/125 [00:23<00:43, 2.08it/s]
Training 1/1 epoch (loss 2.8022): 29%|██▉ | 36/125 [00:23<00:42, 2.11it/s]
Training 1/1 epoch (loss 2.5226): 29%|██▉ | 36/125 [00:23<00:42, 2.11it/s]
Training 1/1 epoch (loss 2.5226): 30%|██▉ | 37/125 [00:23<00:40, 2.16it/s]
Training 1/1 epoch (loss 2.5195): 30%|██▉ | 37/125 [00:23<00:40, 2.16it/s]
Training 1/1 epoch (loss 2.5195): 30%|███ | 38/125 [00:23<00:39, 2.18it/s]
Training 1/1 epoch (loss 2.5830): 30%|███ | 38/125 [00:24<00:39, 2.18it/s]
Training 1/1 epoch (loss 2.5830): 31%|███ | 39/125 [00:24<00:39, 2.15it/s]
Training 1/1 epoch (loss 2.7213): 31%|███ | 39/125 [00:24<00:39, 2.15it/s]
Training 1/1 epoch (loss 2.7213): 32%|███▏ | 40/125 [00:24<00:40, 2.10it/s]
Training 1/1 epoch (loss 2.5554): 32%|███▏ | 40/125 [00:25<00:40, 2.10it/s]
Training 1/1 epoch (loss 2.5554): 33%|███▎ | 41/125 [00:25<00:39, 2.13it/s]
Training 1/1 epoch (loss 2.7949): 33%|███▎ | 41/125 [00:25<00:39, 2.13it/s]
Training 1/1 epoch (loss 2.7949): 34%|███▎ | 42/125 [00:25<00:38, 2.16it/s]
Training 1/1 epoch (loss 2.6883): 34%|███▎ | 42/125 [00:26<00:38, 2.16it/s]
Training 1/1 epoch (loss 2.6883): 34%|███▍ | 43/125 [00:26<00:39, 2.10it/s]
Training 1/1 epoch (loss 2.9115): 34%|███▍ | 43/125 [00:26<00:39, 2.10it/s]
Training 1/1 epoch (loss 2.9115): 35%|███▌ | 44/125 [00:26<00:38, 2.08it/s]
Training 1/1 epoch (loss 2.6871): 35%|███▌ | 44/125 [00:27<00:38, 2.08it/s]
Training 1/1 epoch (loss 2.6871): 36%|███▌ | 45/125 [00:27<00:37, 2.15it/s]
Training 1/1 epoch (loss 2.7687): 36%|███▌ | 45/125 [00:27<00:37, 2.15it/s]
Training 1/1 epoch (loss 2.7687): 37%|███▋ | 46/125 [00:27<00:36, 2.15it/s]
Training 1/1 epoch (loss 2.4735): 37%|███▋ | 46/125 [00:28<00:36, 2.15it/s]
Training 1/1 epoch (loss 2.4735): 38%|███▊ | 47/125 [00:28<00:36, 2.12it/s]
Training 1/1 epoch (loss 2.5469): 38%|███▊ | 47/125 [00:28<00:36, 2.12it/s]
Training 1/1 epoch (loss 2.5469): 38%|███▊ | 48/125 [00:28<00:37, 2.08it/s]
Training 1/1 epoch (loss 2.6851): 38%|███▊ | 48/125 [00:29<00:37, 2.08it/s]
Training 1/1 epoch (loss 2.6851): 39%|███▉ | 49/125 [00:29<00:35, 2.12it/s]
Training 1/1 epoch (loss 2.6115): 39%|███▉ | 49/125 [00:29<00:35, 2.12it/s]
Training 1/1 epoch (loss 2.6115): 40%|████ | 50/125 [00:29<00:34, 2.16it/s]
Training 1/1 epoch (loss 2.5759): 40%|████ | 50/125 [00:30<00:34, 2.16it/s]
Training 1/1 epoch (loss 2.5759): 41%|████ | 51/125 [00:30<00:34, 2.14it/s]
Training 1/1 epoch (loss 2.7235): 41%|████ | 51/125 [00:30<00:34, 2.14it/s]
Training 1/1 epoch (loss 2.7235): 42%|████▏ | 52/125 [00:30<00:33, 2.21it/s]
Training 1/1 epoch (loss 2.7243): 42%|████▏ | 52/125 [00:30<00:33, 2.21it/s]
Training 1/1 epoch (loss 2.7243): 42%|████▏ | 53/125 [00:30<00:32, 2.22it/s]
Training 1/1 epoch (loss 2.6045): 42%|████▏ | 53/125 [00:31<00:32, 2.22it/s]
Training 1/1 epoch (loss 2.6045): 43%|████▎ | 54/125 [00:31<00:31, 2.28it/s]
Training 1/1 epoch (loss 2.6563): 43%|████▎ | 54/125 [00:31<00:31, 2.28it/s]
Training 1/1 epoch (loss 2.6563): 44%|████▍ | 55/125 [00:31<00:30, 2.29it/s]
Training 1/1 epoch (loss 2.7680): 44%|████▍ | 55/125 [00:32<00:30, 2.29it/s]
Training 1/1 epoch (loss 2.7680): 45%|████▍ | 56/125 [00:32<00:32, 2.13it/s]
Training 1/1 epoch (loss 2.7352): 45%|████▍ | 56/125 [00:32<00:32, 2.13it/s]
Training 1/1 epoch (loss 2.7352): 46%|████▌ | 57/125 [00:32<00:32, 2.12it/s]
Training 1/1 epoch (loss 2.8313): 46%|████▌ | 57/125 [00:33<00:32, 2.12it/s]
Training 1/1 epoch (loss 2.8313): 46%|████▋ | 58/125 [00:33<00:31, 2.13it/s]
Training 1/1 epoch (loss 2.5245): 46%|████▋ | 58/125 [00:33<00:31, 2.13it/s]
Training 1/1 epoch (loss 2.5245): 47%|████▋ | 59/125 [00:33<00:30, 2.18it/s]
Training 1/1 epoch (loss 2.6976): 47%|████▋ | 59/125 [00:34<00:30, 2.18it/s]
Training 1/1 epoch (loss 2.6976): 48%|████▊ | 60/125 [00:34<00:30, 2.14it/s]
Training 1/1 epoch (loss 2.7676): 48%|████▊ | 60/125 [00:34<00:30, 2.14it/s]
Training 1/1 epoch (loss 2.7676): 49%|████▉ | 61/125 [00:34<00:29, 2.14it/s]
Training 1/1 epoch (loss 2.6557): 49%|████▉ | 61/125 [00:35<00:29, 2.14it/s]
Training 1/1 epoch (loss 2.6557): 50%|████▉ | 62/125 [00:35<00:28, 2.18it/s]
Training 1/1 epoch (loss 2.6793): 50%|████▉ | 62/125 [00:35<00:28, 2.18it/s]
Training 1/1 epoch (loss 2.6793): 50%|█████ | 63/125 [00:35<00:27, 2.22it/s]
Training 1/1 epoch (loss 2.7198): 50%|█████ | 63/125 [00:35<00:27, 2.22it/s]
Training 1/1 epoch (loss 2.7198): 51%|█████ | 64/125 [00:35<00:28, 2.13it/s]
Training 1/1 epoch (loss 2.5383): 51%|█████ | 64/125 [00:36<00:28, 2.13it/s]
Training 1/1 epoch (loss 2.5383): 52%|█████▏ | 65/125 [00:36<00:28, 2.13it/s]
Training 1/1 epoch (loss 2.8141): 52%|█████▏ | 65/125 [00:36<00:28, 2.13it/s]
Training 1/1 epoch (loss 2.8141): 53%|█████▎ | 66/125 [00:36<00:27, 2.14it/s]
Training 1/1 epoch (loss 2.6197): 53%|█████▎ | 66/125 [00:37<00:27, 2.14it/s]
Training 1/1 epoch (loss 2.6197): 54%|█████▎ | 67/125 [00:37<00:26, 2.19it/s]
Training 1/1 epoch (loss 2.8025): 54%|█████▎ | 67/125 [00:37<00:26, 2.19it/s]
Training 1/1 epoch (loss 2.8025): 54%|█████▍ | 68/125 [00:37<00:25, 2.22it/s]
Training 1/1 epoch (loss 2.7490): 54%|█████▍ | 68/125 [00:38<00:25, 2.22it/s]
Training 1/1 epoch (loss 2.7490): 55%|█████▌ | 69/125 [00:38<00:26, 2.10it/s]
Training 1/1 epoch (loss 2.5881): 55%|█████▌ | 69/125 [00:38<00:26, 2.10it/s]
Training 1/1 epoch (loss 2.5881): 56%|█████▌ | 70/125 [00:38<00:25, 2.14it/s]
Training 1/1 epoch (loss 2.5355): 56%|█████▌ | 70/125 [00:39<00:25, 2.14it/s]
Training 1/1 epoch (loss 2.5355): 57%|█████▋ | 71/125 [00:39<00:25, 2.14it/s]
Training 1/1 epoch (loss 2.5928): 57%|█████▋ | 71/125 [00:39<00:25, 2.14it/s]
Training 1/1 epoch (loss 2.5928): 58%|█████▊ | 72/125 [00:39<00:25, 2.06it/s]
Training 1/1 epoch (loss 2.9116): 58%|█████▊ | 72/125 [00:40<00:25, 2.06it/s]
Training 1/1 epoch (loss 2.9116): 58%|█████▊ | 73/125 [00:40<00:24, 2.08it/s]
Training 1/1 epoch (loss 2.7534): 58%|█████▊ | 73/125 [00:40<00:24, 2.08it/s]
Training 1/1 epoch (loss 2.7534): 59%|█████▉ | 74/125 [00:40<00:24, 2.08it/s]
Training 1/1 epoch (loss 2.6084): 59%|█████▉ | 74/125 [00:41<00:24, 2.08it/s]
Training 1/1 epoch (loss 2.6084): 60%|██████ | 75/125 [00:41<00:23, 2.09it/s]
Training 1/1 epoch (loss 2.7763): 60%|██████ | 75/125 [00:41<00:23, 2.09it/s]
Training 1/1 epoch (loss 2.7763): 61%|██████ | 76/125 [00:41<00:23, 2.13it/s]
Training 1/1 epoch (loss 2.7557): 61%|██████ | 76/125 [00:42<00:23, 2.13it/s]
Training 1/1 epoch (loss 2.7557): 62%|██████▏ | 77/125 [00:42<00:22, 2.14it/s]
Training 1/1 epoch (loss 2.5894): 62%|██████▏ | 77/125 [00:42<00:22, 2.14it/s]
Training 1/1 epoch (loss 2.5894): 62%|██████▏ | 78/125 [00:42<00:24, 1.95it/s]
Training 1/1 epoch (loss 2.6940): 62%|██████▏ | 78/125 [00:43<00:24, 1.95it/s]
Training 1/1 epoch (loss 2.6940): 63%|██████▎ | 79/125 [00:43<00:22, 2.01it/s]
Training 1/1 epoch (loss 2.6951): 63%|██████▎ | 79/125 [00:43<00:22, 2.01it/s]
Training 1/1 epoch (loss 2.6951): 64%|██████▍ | 80/125 [00:43<00:22, 2.02it/s]
Training 1/1 epoch (loss 2.7385): 64%|██████▍ | 80/125 [00:44<00:22, 2.02it/s]
Training 1/1 epoch (loss 2.7385): 65%|██████▍ | 81/125 [00:44<00:21, 2.04it/s]
Training 1/1 epoch (loss 2.4511): 65%|██████▍ | 81/125 [00:44<00:21, 2.04it/s]
Training 1/1 epoch (loss 2.4511): 66%|██████▌ | 82/125 [00:44<00:20, 2.08it/s]
Training 1/1 epoch (loss 2.8701): 66%|██████▌ | 82/125 [00:45<00:20, 2.08it/s]
Training 1/1 epoch (loss 2.8701): 66%|██████▋ | 83/125 [00:45<00:19, 2.11it/s]
Training 1/1 epoch (loss 2.7120): 66%|██████▋ | 83/125 [00:45<00:19, 2.11it/s]
Training 1/1 epoch (loss 2.7120): 67%|██████▋ | 84/125 [00:45<00:19, 2.15it/s]
Training 1/1 epoch (loss 2.6946): 67%|██████▋ | 84/125 [00:45<00:19, 2.15it/s]
Training 1/1 epoch (loss 2.6946): 68%|██████▊ | 85/125 [00:45<00:18, 2.18it/s]
Training 1/1 epoch (loss 2.7017): 68%|██████▊ | 85/125 [00:46<00:18, 2.18it/s]
Training 1/1 epoch (loss 2.7017): 69%|██████▉ | 86/125 [00:46<00:18, 2.16it/s]
Training 1/1 epoch (loss 2.6165): 69%|██████▉ | 86/125 [00:46<00:18, 2.16it/s]
Training 1/1 epoch (loss 2.6165): 70%|██████▉ | 87/125 [00:46<00:17, 2.23it/s]
Training 1/1 epoch (loss 2.7793): 70%|██████▉ | 87/125 [00:47<00:17, 2.23it/s]
Training 1/1 epoch (loss 2.7793): 70%|███████ | 88/125 [00:47<00:17, 2.12it/s]
Training 1/1 epoch (loss 2.6044): 70%|███████ | 88/125 [00:47<00:17, 2.12it/s]
Training 1/1 epoch (loss 2.6044): 71%|███████ | 89/125 [00:47<00:16, 2.16it/s]
Training 1/1 epoch (loss 2.5466): 71%|███████ | 89/125 [00:48<00:16, 2.16it/s]
Training 1/1 epoch (loss 2.5466): 72%|███████▏ | 90/125 [00:48<00:17, 2.04it/s]
Training 1/1 epoch (loss 2.6306): 72%|███████▏ | 90/125 [00:48<00:17, 2.04it/s]
Training 1/1 epoch (loss 2.6306): 73%|███████▎ | 91/125 [00:48<00:16, 2.08it/s]
Training 1/1 epoch (loss 2.7355): 73%|███████▎ | 91/125 [00:49<00:16, 2.08it/s]
Training 1/1 epoch (loss 2.7355): 74%|███████▎ | 92/125 [00:49<00:15, 2.08it/s]
Training 1/1 epoch (loss 2.6913): 74%|███████▎ | 92/125 [00:49<00:15, 2.08it/s]
Training 1/1 epoch (loss 2.6913): 74%|███████▍ | 93/125 [00:49<00:15, 2.12it/s]
Training 1/1 epoch (loss 2.6403): 74%|███████▍ | 93/125 [00:50<00:15, 2.12it/s]
Training 1/1 epoch (loss 2.6403): 75%|███████▌ | 94/125 [00:50<00:14, 2.14it/s]
Training 1/1 epoch (loss 2.9990): 75%|███████▌ | 94/125 [00:50<00:14, 2.14it/s]
Training 1/1 epoch (loss 2.9990): 76%|███████▌ | 95/125 [00:50<00:13, 2.16it/s]
Training 1/1 epoch (loss 2.5464): 76%|███████▌ | 95/125 [00:51<00:13, 2.16it/s]
Training 1/1 epoch (loss 2.5464): 77%|███████▋ | 96/125 [00:51<00:13, 2.12it/s]
Training 1/1 epoch (loss 2.6482): 77%|███████▋ | 96/125 [00:51<00:13, 2.12it/s]
Training 1/1 epoch (loss 2.6482): 78%|███████▊ | 97/125 [00:51<00:13, 2.12it/s]
Training 1/1 epoch (loss 2.7623): 78%|███████▊ | 97/125 [00:52<00:13, 2.12it/s]
Training 1/1 epoch (loss 2.7623): 78%|███████▊ | 98/125 [00:52<00:13, 1.99it/s]
Training 1/1 epoch (loss 2.6956): 78%|███████▊ | 98/125 [00:52<00:13, 1.99it/s]
Training 1/1 epoch (loss 2.6956): 79%|███████▉ | 99/125 [00:52<00:12, 2.04it/s]
Training 1/1 epoch (loss 2.5380): 79%|███████▉ | 99/125 [00:53<00:12, 2.04it/s]
Training 1/1 epoch (loss 2.5380): 80%|████████ | 100/125 [00:53<00:12, 2.08it/s]
Training 1/1 epoch (loss 2.8376): 80%|████████ | 100/125 [00:53<00:12, 2.08it/s]
Training 1/1 epoch (loss 2.8376): 81%|████████ | 101/125 [00:53<00:11, 2.10it/s]
Training 1/1 epoch (loss 2.9831): 81%|████████ | 101/125 [00:54<00:11, 2.10it/s]
Training 1/1 epoch (loss 2.9831): 82%|████████▏ | 102/125 [00:54<00:10, 2.11it/s]
Training 1/1 epoch (loss 2.7301): 82%|████████▏ | 102/125 [00:54<00:10, 2.11it/s]
Training 1/1 epoch (loss 2.7301): 82%|████████▏ | 103/125 [00:54<00:10, 2.12it/s]
Training 1/1 epoch (loss 2.7245): 82%|████████▏ | 103/125 [00:55<00:10, 2.12it/s]
Training 1/1 epoch (loss 2.7245): 83%|████████▎ | 104/125 [00:55<00:10, 2.00it/s]
Training 1/1 epoch (loss 2.5907): 83%|████████▎ | 104/125 [00:55<00:10, 2.00it/s]
Training 1/1 epoch (loss 2.5907): 84%|████████▍ | 105/125 [00:55<00:09, 2.02it/s]
Training 1/1 epoch (loss 2.9073): 84%|████████▍ | 105/125 [00:56<00:09, 2.02it/s]
Training 1/1 epoch (loss 2.9073): 85%|████████▍ | 106/125 [00:56<00:09, 2.07it/s]
Training 1/1 epoch (loss 2.5892): 85%|████████▍ | 106/125 [00:56<00:09, 2.07it/s]
Training 1/1 epoch (loss 2.5892): 86%|████████▌ | 107/125 [00:56<00:08, 2.07it/s]
Training 1/1 epoch (loss 3.0311): 86%|████████▌ | 107/125 [00:56<00:08, 2.07it/s]
Training 1/1 epoch (loss 3.0311): 86%|████████▋ | 108/125 [00:56<00:08, 2.12it/s]
Training 1/1 epoch (loss 2.6291): 86%|████████▋ | 108/125 [00:57<00:08, 2.12it/s]
Training 1/1 epoch (loss 2.6291): 87%|████████▋ | 109/125 [00:57<00:07, 2.17it/s]
Training 1/1 epoch (loss 2.7129): 87%|████████▋ | 109/125 [00:57<00:07, 2.17it/s]
Training 1/1 epoch (loss 2.7129): 88%|████████▊ | 110/125 [00:57<00:06, 2.18it/s]
Training 1/1 epoch (loss 2.8093): 88%|████████▊ | 110/125 [00:58<00:06, 2.18it/s]
Training 1/1 epoch (loss 2.8093): 89%|████████▉ | 111/125 [00:58<00:06, 2.16it/s]
Training 1/1 epoch (loss 2.5939): 89%|████████▉ | 111/125 [00:58<00:06, 2.16it/s]
Training 1/1 epoch (loss 2.5939): 90%|████████▉ | 112/125 [00:58<00:06, 2.11it/s]
Training 1/1 epoch (loss 2.7265): 90%|████████▉ | 112/125 [00:59<00:06, 2.11it/s]
Training 1/1 epoch (loss 2.7265): 90%|█████████ | 113/125 [00:59<00:05, 2.11it/s]
Training 1/1 epoch (loss 2.7095): 90%|█████████ | 113/125 [00:59<00:05, 2.11it/s]
Training 1/1 epoch (loss 2.7095): 91%|█████████ | 114/125 [00:59<00:05, 2.14it/s]
Training 1/1 epoch (loss 2.6937): 91%|█████████ | 114/125 [01:00<00:05, 2.14it/s]
Training 1/1 epoch (loss 2.6937): 92%|█████████▏| 115/125 [01:00<00:04, 2.19it/s]
Training 1/1 epoch (loss 2.6634): 92%|█████████▏| 115/125 [01:00<00:04, 2.19it/s]
Training 1/1 epoch (loss 2.6634): 93%|█████████▎| 116/125 [01:00<00:04, 2.18it/s]
Training 1/1 epoch (loss 2.6987): 93%|█████████▎| 116/125 [01:01<00:04, 2.18it/s]
Training 1/1 epoch (loss 2.6987): 94%|█████████▎| 117/125 [01:01<00:03, 2.20it/s]
Training 1/1 epoch (loss 2.6732): 94%|█████████▎| 117/125 [01:01<00:03, 2.20it/s]
Training 1/1 epoch (loss 2.6732): 94%|█████████▍| 118/125 [01:01<00:03, 2.23it/s]
Training 1/1 epoch (loss 2.7028): 94%|█████████▍| 118/125 [01:02<00:03, 2.23it/s]
Training 1/1 epoch (loss 2.7028): 95%|█████████▌| 119/125 [01:02<00:02, 2.19it/s]
Training 1/1 epoch (loss 3.0142): 95%|█████████▌| 119/125 [01:02<00:02, 2.19it/s]
Training 1/1 epoch (loss 3.0142): 96%|█████████▌| 120/125 [01:02<00:02, 2.03it/s]
Training 1/1 epoch (loss 2.6504): 96%|█████████▌| 120/125 [01:03<00:02, 2.03it/s]
Training 1/1 epoch (loss 2.6504): 97%|█████████▋| 121/125 [01:03<00:01, 2.09it/s]
Training 1/1 epoch (loss 2.6892): 97%|█████████▋| 121/125 [01:03<00:01, 2.09it/s]
Training 1/1 epoch (loss 2.6892): 98%|█████████▊| 122/125 [01:03<00:01, 2.12it/s]
Training 1/1 epoch (loss 2.5802): 98%|█████████▊| 122/125 [01:03<00:01, 2.12it/s]
Training 1/1 epoch (loss 2.5802): 98%|█████████▊| 123/125 [01:03<00:00, 2.15it/s]
Training 1/1 epoch (loss 2.6389): 98%|█████████▊| 123/125 [01:04<00:00, 2.15it/s]
Training 1/1 epoch (loss 2.6389): 99%|█████████▉| 124/125 [01:04<00:00, 2.15it/s]
Training 1/1 epoch (loss 2.7607): 99%|█████████▉| 124/125 [01:04<00:00, 2.15it/s]
Training 1/1 epoch (loss 2.7607): 100%|██████████| 125/125 [01:04<00:00, 2.17it/s]
Training 1/1 epoch (loss 2.7607): 100%|██████████| 125/125 [01:04<00:00, 1.93it/s] |
|
|
chat template saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000-Q2-1000/chat_template.jinja |
|
|
tokenizer config file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000-Q2-1000/tokenizer_config.json |
|
|
Special tokens file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-5000-Q2-1000/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 0x1550cc4f3950>> |
|
|
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 |
|
|
|
