|
|
+ deepspeed --master_port 49158 --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-Q1-2000 --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/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000-Q2-1000 --log_type wandb --log_run_name imdb-Qwen1.5-7B-s3-Q1-2000-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 |
|
|
[rank1]:[W526 20:16:35.792767625 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 20:16:35.849686804 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. |
|
|
[rank5]:[W526 20:16:35.406682321 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]:[W526 20:16:35.497345381 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. |
|
|
[rank3]:[W526 20:16:35.568707600 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. |
|
|
[rank7]:[W526 20:16:35.568792857 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 20:16:36.664630850 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. |
|
|
[rank6]:[W526 20:16:36.679643666 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. |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-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": 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-Q1-2000/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 |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000/pytorch_model.bin |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-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 |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000/pytorch_model.bin |
|
|
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. |
|
|
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 |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
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-Q1-2000/pytorch_model.bin |
|
|
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-Q1-2000/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-Q1-2000/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 |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-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 |
|
|
} |
|
|
|
|
|
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 |
|
|
} |
|
|
|
|
|
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-Q1-2000. |
|
|
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/Qwen1.5-7B/Qwen1.5-7B-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/Qwen1.5-7B/Qwen1.5-7B-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/Qwen1.5-7B/Qwen1.5-7B-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. |
|
|
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-Q1-2000. |
|
|
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. |
|
|
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-Q1-2000. |
|
|
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. |
|
|
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-Q1-2000. |
|
|
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. |
|
|
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 |
|
|
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 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-Q1-2000. |
|
|
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. |
|
|
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-Q1-2000-Q2-1000/wandb/run-20250526_201704-xxzkpwte |
|
|
wandb: Run `wandb offline` to turn off syncing. |
|
|
wandb: Syncing run imdb-Qwen1.5-7B-s3-Q1-2000-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/xxzkpwte |
|
|
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 2.6825): 0%| | 0/125 [00:05<?, ?it/s]
Training 1/1 epoch (loss 2.6825): 1%| | 1/125 [00:05<11:43, 5.67s/it]
Training 1/1 epoch (loss 2.7474): 1%| | 1/125 [00:06<11:43, 5.67s/it]
Training 1/1 epoch (loss 2.7474): 2%|▏ | 2/125 [00:06<06:02, 2.94s/it]
Training 1/1 epoch (loss 2.6574): 2%|▏ | 2/125 [00:07<06:02, 2.94s/it]
Training 1/1 epoch (loss 2.6574): 2%|▏ | 3/125 [00:07<03:40, 1.81s/it]
Training 1/1 epoch (loss 2.5711): 2%|▏ | 3/125 [00:07<03:40, 1.81s/it]
Training 1/1 epoch (loss 2.5711): 3%|▎ | 4/125 [00:07<02:35, 1.28s/it]
Training 1/1 epoch (loss 2.6780): 3%|▎ | 4/125 [00:08<02:35, 1.28s/it]
Training 1/1 epoch (loss 2.6780): 4%|▍ | 5/125 [00:08<02:01, 1.01s/it]
Training 1/1 epoch (loss 2.7628): 4%|▍ | 5/125 [00:08<02:01, 1.01s/it]
Training 1/1 epoch (loss 2.7628): 5%|▍ | 6/125 [00:08<01:41, 1.17it/s]
Training 1/1 epoch (loss 2.8093): 5%|▍ | 6/125 [00:09<01:41, 1.17it/s]
Training 1/1 epoch (loss 2.8093): 6%|▌ | 7/125 [00:09<01:25, 1.38it/s]
Training 1/1 epoch (loss 2.8379): 6%|▌ | 7/125 [00:09<01:25, 1.38it/s]
Training 1/1 epoch (loss 2.8379): 6%|▋ | 8/125 [00:09<01:20, 1.46it/s]
Training 1/1 epoch (loss 2.5974): 6%|▋ | 8/125 [00:10<01:20, 1.46it/s]
Training 1/1 epoch (loss 2.5974): 7%|▋ | 9/125 [00:10<01:11, 1.62it/s]
Training 1/1 epoch (loss 2.6611): 7%|▋ | 9/125 [00:10<01:11, 1.62it/s]
Training 1/1 epoch (loss 2.6611): 8%|▊ | 10/125 [00:10<01:04, 1.78it/s]
Training 1/1 epoch (loss 2.7061): 8%|▊ | 10/125 [00:11<01:04, 1.78it/s]
Training 1/1 epoch (loss 2.7061): 9%|▉ | 11/125 [00:11<01:01, 1.86it/s]
Training 1/1 epoch (loss 2.6611): 9%|▉ | 11/125 [00:11<01:01, 1.86it/s]
Training 1/1 epoch (loss 2.6611): 10%|▉ | 12/125 [00:11<01:00, 1.88it/s]
Training 1/1 epoch (loss 2.8025): 10%|▉ | 12/125 [00:12<01:00, 1.88it/s]
Training 1/1 epoch (loss 2.8025): 10%|█ | 13/125 [00:12<01:00, 1.87it/s]
Training 1/1 epoch (loss 2.4869): 10%|█ | 13/125 [00:12<01:00, 1.87it/s]
Training 1/1 epoch (loss 2.4869): 11%|█ | 14/125 [00:12<01:00, 1.83it/s]
Training 1/1 epoch (loss 2.9186): 11%|█ | 14/125 [00:13<01:00, 1.83it/s]
Training 1/1 epoch (loss 2.9186): 12%|█▏ | 15/125 [00:13<01:01, 1.78it/s]
Training 1/1 epoch (loss 2.5271): 12%|█▏ | 15/125 [00:13<01:01, 1.78it/s]
Training 1/1 epoch (loss 2.5271): 13%|█▎ | 16/125 [00:13<01:01, 1.76it/s]
Training 1/1 epoch (loss 2.6412): 13%|█▎ | 16/125 [00:14<01:01, 1.76it/s]
Training 1/1 epoch (loss 2.6412): 14%|█▎ | 17/125 [00:14<00:58, 1.85it/s]
Training 1/1 epoch (loss 2.8740): 14%|█▎ | 17/125 [00:14<00:58, 1.85it/s]
Training 1/1 epoch (loss 2.8740): 14%|█▍ | 18/125 [00:14<00:54, 1.96it/s]
Training 1/1 epoch (loss 2.8017): 14%|█▍ | 18/125 [00:15<00:54, 1.96it/s]
Training 1/1 epoch (loss 2.8017): 15%|█▌ | 19/125 [00:15<00:52, 2.03it/s]
Training 1/1 epoch (loss 2.8875): 15%|█▌ | 19/125 [00:15<00:52, 2.03it/s]
Training 1/1 epoch (loss 2.8875): 16%|█▌ | 20/125 [00:15<00:50, 2.07it/s]
Training 1/1 epoch (loss 2.7183): 16%|█▌ | 20/125 [00:16<00:50, 2.07it/s]
Training 1/1 epoch (loss 2.7183): 17%|█▋ | 21/125 [00:16<00:50, 2.07it/s]
Training 1/1 epoch (loss 2.7060): 17%|█▋ | 21/125 [00:16<00:50, 2.07it/s]
Training 1/1 epoch (loss 2.7060): 18%|█▊ | 22/125 [00:16<00:49, 2.09it/s]
Training 1/1 epoch (loss 2.6175): 18%|█▊ | 22/125 [00:17<00:49, 2.09it/s]
Training 1/1 epoch (loss 2.6175): 18%|█▊ | 23/125 [00:17<00:47, 2.13it/s]
Training 1/1 epoch (loss 2.5634): 18%|█▊ | 23/125 [00:17<00:47, 2.13it/s]
Training 1/1 epoch (loss 2.5634): 19%|█▉ | 24/125 [00:17<00:49, 2.04it/s]
Training 1/1 epoch (loss 2.5797): 19%|█▉ | 24/125 [00:18<00:49, 2.04it/s]
Training 1/1 epoch (loss 2.5797): 20%|██ | 25/125 [00:18<00:48, 2.08it/s]
Training 1/1 epoch (loss 2.5563): 20%|██ | 25/125 [00:18<00:48, 2.08it/s]
Training 1/1 epoch (loss 2.5563): 21%|██ | 26/125 [00:18<00:46, 2.15it/s]
Training 1/1 epoch (loss 2.5454): 21%|██ | 26/125 [00:19<00:46, 2.15it/s]
Training 1/1 epoch (loss 2.5454): 22%|██▏ | 27/125 [00:19<00:45, 2.15it/s]
Training 1/1 epoch (loss 2.5644): 22%|██▏ | 27/125 [00:19<00:45, 2.15it/s]
Training 1/1 epoch (loss 2.5644): 22%|██▏ | 28/125 [00:19<00:45, 2.11it/s]
Training 1/1 epoch (loss 2.7493): 22%|██▏ | 28/125 [00:20<00:45, 2.11it/s]
Training 1/1 epoch (loss 2.7493): 23%|██▎ | 29/125 [00:20<00:44, 2.14it/s]
Training 1/1 epoch (loss 2.4876): 23%|██▎ | 29/125 [00:20<00:44, 2.14it/s]
Training 1/1 epoch (loss 2.4876): 24%|██▍ | 30/125 [00:20<00:43, 2.17it/s]
Training 1/1 epoch (loss 2.7923): 24%|██▍ | 30/125 [00:20<00:43, 2.17it/s]
Training 1/1 epoch (loss 2.7923): 25%|██▍ | 31/125 [00:20<00:43, 2.14it/s]
Training 1/1 epoch (loss 2.5909): 25%|██▍ | 31/125 [00:21<00:43, 2.14it/s]
Training 1/1 epoch (loss 2.5909): 26%|██▌ | 32/125 [00:21<00:44, 2.07it/s]
Training 1/1 epoch (loss 2.9621): 26%|██▌ | 32/125 [00:21<00:44, 2.07it/s]
Training 1/1 epoch (loss 2.9621): 26%|██▋ | 33/125 [00:21<00:43, 2.10it/s]
Training 1/1 epoch (loss 2.6729): 26%|██▋ | 33/125 [00:22<00:43, 2.10it/s]
Training 1/1 epoch (loss 2.6729): 27%|██▋ | 34/125 [00:22<00:42, 2.13it/s]
Training 1/1 epoch (loss 2.8300): 27%|██▋ | 34/125 [00:22<00:42, 2.13it/s]
Training 1/1 epoch (loss 2.8300): 28%|██▊ | 35/125 [00:22<00:43, 2.08it/s]
Training 1/1 epoch (loss 2.7662): 28%|██▊ | 35/125 [00:23<00:43, 2.08it/s]
Training 1/1 epoch (loss 2.7662): 29%|██▉ | 36/125 [00:23<00:42, 2.11it/s]
Training 1/1 epoch (loss 2.5153): 29%|██▉ | 36/125 [00:23<00:42, 2.11it/s]
Training 1/1 epoch (loss 2.5153): 30%|██▉ | 37/125 [00:23<00:40, 2.17it/s]
Training 1/1 epoch (loss 2.5138): 30%|██▉ | 37/125 [00:24<00:40, 2.17it/s]
Training 1/1 epoch (loss 2.5138): 30%|███ | 38/125 [00:24<00:41, 2.08it/s]
Training 1/1 epoch (loss 2.5786): 30%|███ | 38/125 [00:24<00:41, 2.08it/s]
Training 1/1 epoch (loss 2.5786): 31%|███ | 39/125 [00:24<00:40, 2.12it/s]
Training 1/1 epoch (loss 2.7107): 31%|███ | 39/125 [00:25<00:40, 2.12it/s]
Training 1/1 epoch (loss 2.7107): 32%|███▏ | 40/125 [00:25<00:40, 2.07it/s]
Training 1/1 epoch (loss 2.5405): 32%|███▏ | 40/125 [00:25<00:40, 2.07it/s]
Training 1/1 epoch (loss 2.5405): 33%|███▎ | 41/125 [00:25<00:39, 2.13it/s]
Training 1/1 epoch (loss 2.8059): 33%|███▎ | 41/125 [00:26<00:39, 2.13it/s]
Training 1/1 epoch (loss 2.8059): 34%|███▎ | 42/125 [00:26<00:38, 2.16it/s]
Training 1/1 epoch (loss 2.6750): 34%|███▎ | 42/125 [00:26<00:38, 2.16it/s]
Training 1/1 epoch (loss 2.6750): 34%|███▍ | 43/125 [00:26<00:37, 2.17it/s]
Training 1/1 epoch (loss 2.9105): 34%|███▍ | 43/125 [00:27<00:37, 2.17it/s]
Training 1/1 epoch (loss 2.9105): 35%|███▌ | 44/125 [00:27<00:36, 2.20it/s]
Training 1/1 epoch (loss 2.6885): 35%|███▌ | 44/125 [00:27<00:36, 2.20it/s]
Training 1/1 epoch (loss 2.6885): 36%|███▌ | 45/125 [00:27<00:35, 2.23it/s]
Training 1/1 epoch (loss 2.7642): 36%|███▌ | 45/125 [00:27<00:35, 2.23it/s]
Training 1/1 epoch (loss 2.7642): 37%|███▋ | 46/125 [00:27<00:35, 2.24it/s]
Training 1/1 epoch (loss 2.4833): 37%|███▋ | 46/125 [00:28<00:35, 2.24it/s]
Training 1/1 epoch (loss 2.4833): 38%|███▊ | 47/125 [00:28<00:35, 2.20it/s]
Training 1/1 epoch (loss 2.5363): 38%|███▊ | 47/125 [00:28<00:35, 2.20it/s]
Training 1/1 epoch (loss 2.5363): 38%|███▊ | 48/125 [00:28<00:36, 2.10it/s]
Training 1/1 epoch (loss 2.6864): 38%|███▊ | 48/125 [00:29<00:36, 2.10it/s]
Training 1/1 epoch (loss 2.6864): 39%|███▉ | 49/125 [00:29<00:35, 2.12it/s]
Training 1/1 epoch (loss 2.6076): 39%|███▉ | 49/125 [00:29<00:35, 2.12it/s]
Training 1/1 epoch (loss 2.6076): 40%|████ | 50/125 [00:29<00:35, 2.14it/s]
Training 1/1 epoch (loss 2.5921): 40%|████ | 50/125 [00:30<00:35, 2.14it/s]
Training 1/1 epoch (loss 2.5921): 41%|████ | 51/125 [00:30<00:36, 2.02it/s]
Training 1/1 epoch (loss 2.7188): 41%|████ | 51/125 [00:30<00:36, 2.02it/s]
Training 1/1 epoch (loss 2.7188): 42%|████▏ | 52/125 [00:30<00:34, 2.11it/s]
Training 1/1 epoch (loss 2.7167): 42%|████▏ | 52/125 [00:31<00:34, 2.11it/s]
Training 1/1 epoch (loss 2.7167): 42%|████▏ | 53/125 [00:31<00:33, 2.15it/s]
Training 1/1 epoch (loss 2.6102): 42%|████▏ | 53/125 [00:31<00:33, 2.15it/s]
Training 1/1 epoch (loss 2.6102): 43%|████▎ | 54/125 [00:31<00:32, 2.19it/s]
Training 1/1 epoch (loss 2.6733): 43%|████▎ | 54/125 [00:32<00:32, 2.19it/s]
Training 1/1 epoch (loss 2.6733): 44%|████▍ | 55/125 [00:32<00:32, 2.17it/s]
Training 1/1 epoch (loss 2.7617): 44%|████▍ | 55/125 [00:32<00:32, 2.17it/s]
Training 1/1 epoch (loss 2.7617): 45%|████▍ | 56/125 [00:32<00:32, 2.10it/s]
Training 1/1 epoch (loss 2.7213): 45%|████▍ | 56/125 [00:33<00:32, 2.10it/s]
Training 1/1 epoch (loss 2.7213): 46%|████▌ | 57/125 [00:33<00:33, 2.04it/s]
Training 1/1 epoch (loss 2.7962): 46%|████▌ | 57/125 [00:33<00:33, 2.04it/s]
Training 1/1 epoch (loss 2.7962): 46%|████▋ | 58/125 [00:33<00:33, 1.98it/s]
Training 1/1 epoch (loss 2.5311): 46%|████▋ | 58/125 [00:34<00:33, 1.98it/s]
Training 1/1 epoch (loss 2.5311): 47%|████▋ | 59/125 [00:34<00:32, 2.04it/s]
Training 1/1 epoch (loss 2.7132): 47%|████▋ | 59/125 [00:34<00:32, 2.04it/s]
Training 1/1 epoch (loss 2.7132): 48%|████▊ | 60/125 [00:34<00:30, 2.11it/s]
Training 1/1 epoch (loss 2.7644): 48%|████▊ | 60/125 [00:35<00:30, 2.11it/s]
Training 1/1 epoch (loss 2.7644): 49%|████▉ | 61/125 [00:35<00:29, 2.14it/s]
Training 1/1 epoch (loss 2.6356): 49%|████▉ | 61/125 [00:35<00:29, 2.14it/s]
Training 1/1 epoch (loss 2.6356): 50%|████▉ | 62/125 [00:35<00:29, 2.14it/s]
Training 1/1 epoch (loss 2.6530): 50%|████▉ | 62/125 [00:36<00:29, 2.14it/s]
Training 1/1 epoch (loss 2.6530): 50%|█████ | 63/125 [00:36<00:30, 2.07it/s]
Training 1/1 epoch (loss 2.7119): 50%|█████ | 63/125 [00:36<00:30, 2.07it/s]
Training 1/1 epoch (loss 2.7119): 51%|█████ | 64/125 [00:36<00:32, 1.89it/s]
Training 1/1 epoch (loss 2.5342): 51%|█████ | 64/125 [00:37<00:32, 1.89it/s]
Training 1/1 epoch (loss 2.5342): 52%|█████▏ | 65/125 [00:37<00:30, 1.99it/s]
Training 1/1 epoch (loss 2.8348): 52%|█████▏ | 65/125 [00:37<00:30, 1.99it/s]
Training 1/1 epoch (loss 2.8348): 53%|█████▎ | 66/125 [00:37<00:29, 2.03it/s]
Training 1/1 epoch (loss 2.6276): 53%|█████▎ | 66/125 [00:38<00:29, 2.03it/s]
Training 1/1 epoch (loss 2.6276): 54%|█████▎ | 67/125 [00:38<00:27, 2.08it/s]
Training 1/1 epoch (loss 2.7924): 54%|█████▎ | 67/125 [00:38<00:27, 2.08it/s]
Training 1/1 epoch (loss 2.7924): 54%|█████▍ | 68/125 [00:38<00:26, 2.15it/s]
Training 1/1 epoch (loss 2.7509): 54%|█████▍ | 68/125 [00:39<00:26, 2.15it/s]
Training 1/1 epoch (loss 2.7509): 55%|█████▌ | 69/125 [00:39<00:27, 2.07it/s]
Training 1/1 epoch (loss 2.6283): 55%|█████▌ | 69/125 [00:39<00:27, 2.07it/s]
Training 1/1 epoch (loss 2.6283): 56%|█████▌ | 70/125 [00:39<00:26, 2.07it/s]
Training 1/1 epoch (loss 2.5093): 56%|█████▌ | 70/125 [00:40<00:26, 2.07it/s]
Training 1/1 epoch (loss 2.5093): 57%|█████▋ | 71/125 [00:40<00:26, 2.06it/s]
Training 1/1 epoch (loss 2.6130): 57%|█████▋ | 71/125 [00:40<00:26, 2.06it/s]
Training 1/1 epoch (loss 2.6130): 58%|█████▊ | 72/125 [00:40<00:26, 1.97it/s]
Training 1/1 epoch (loss 2.9054): 58%|█████▊ | 72/125 [00:41<00:26, 1.97it/s]
Training 1/1 epoch (loss 2.9054): 58%|█████▊ | 73/125 [00:41<00:25, 2.02it/s]
Training 1/1 epoch (loss 2.7560): 58%|█████▊ | 73/125 [00:41<00:25, 2.02it/s]
Training 1/1 epoch (loss 2.7560): 59%|█████▉ | 74/125 [00:41<00:24, 2.04it/s]
Training 1/1 epoch (loss 2.5992): 59%|█████▉ | 74/125 [00:42<00:24, 2.04it/s]
Training 1/1 epoch (loss 2.5992): 60%|██████ | 75/125 [00:42<00:25, 1.97it/s]
Training 1/1 epoch (loss 2.7745): 60%|██████ | 75/125 [00:42<00:25, 1.97it/s]
Training 1/1 epoch (loss 2.7745): 61%|██████ | 76/125 [00:42<00:25, 1.91it/s]
Training 1/1 epoch (loss 2.7505): 61%|██████ | 76/125 [00:43<00:25, 1.91it/s]
Training 1/1 epoch (loss 2.7505): 62%|██████▏ | 77/125 [00:43<00:24, 1.94it/s]
Training 1/1 epoch (loss 2.6010): 62%|██████▏ | 77/125 [00:43<00:24, 1.94it/s]
Training 1/1 epoch (loss 2.6010): 62%|██████▏ | 78/125 [00:43<00:23, 2.02it/s]
Training 1/1 epoch (loss 2.7053): 62%|██████▏ | 78/125 [00:44<00:23, 2.02it/s]
Training 1/1 epoch (loss 2.7053): 63%|██████▎ | 79/125 [00:44<00:22, 2.06it/s]
Training 1/1 epoch (loss 2.7151): 63%|██████▎ | 79/125 [00:44<00:22, 2.06it/s]
Training 1/1 epoch (loss 2.7151): 64%|██████▍ | 80/125 [00:44<00:22, 2.04it/s]
Training 1/1 epoch (loss 2.7261): 64%|██████▍ | 80/125 [00:45<00:22, 2.04it/s]
Training 1/1 epoch (loss 2.7261): 65%|██████▍ | 81/125 [00:45<00:21, 2.09it/s]
Training 1/1 epoch (loss 2.4333): 65%|██████▍ | 81/125 [00:45<00:21, 2.09it/s]
Training 1/1 epoch (loss 2.4333): 66%|██████▌ | 82/125 [00:45<00:20, 2.15it/s]
Training 1/1 epoch (loss 2.8606): 66%|██████▌ | 82/125 [00:45<00:20, 2.15it/s]
Training 1/1 epoch (loss 2.8606): 66%|██████▋ | 83/125 [00:45<00:19, 2.17it/s]
Training 1/1 epoch (loss 2.7239): 66%|██████▋ | 83/125 [00:46<00:19, 2.17it/s]
Training 1/1 epoch (loss 2.7239): 67%|██████▋ | 84/125 [00:46<00:18, 2.19it/s]
Training 1/1 epoch (loss 2.6881): 67%|██████▋ | 84/125 [00:46<00:18, 2.19it/s]
Training 1/1 epoch (loss 2.6881): 68%|██████▊ | 85/125 [00:46<00:18, 2.21it/s]
Training 1/1 epoch (loss 2.7117): 68%|██████▊ | 85/125 [00:47<00:18, 2.21it/s]
Training 1/1 epoch (loss 2.7117): 69%|██████▉ | 86/125 [00:47<00:17, 2.23it/s]
Training 1/1 epoch (loss 2.6097): 69%|██████▉ | 86/125 [00:47<00:17, 2.23it/s]
Training 1/1 epoch (loss 2.6097): 70%|██████▉ | 87/125 [00:47<00:16, 2.25it/s]
Training 1/1 epoch (loss 2.7680): 70%|██████▉ | 87/125 [00:48<00:16, 2.25it/s]
Training 1/1 epoch (loss 2.7680): 70%|███████ | 88/125 [00:48<00:17, 2.14it/s]
Training 1/1 epoch (loss 2.6022): 70%|███████ | 88/125 [00:48<00:17, 2.14it/s]
Training 1/1 epoch (loss 2.6022): 71%|███████ | 89/125 [00:48<00:16, 2.17it/s]
Training 1/1 epoch (loss 2.5461): 71%|███████ | 89/125 [00:49<00:16, 2.17it/s]
Training 1/1 epoch (loss 2.5461): 72%|███████▏ | 90/125 [00:49<00:15, 2.19it/s]
Training 1/1 epoch (loss 2.6361): 72%|███████▏ | 90/125 [00:49<00:15, 2.19it/s]
Training 1/1 epoch (loss 2.6361): 73%|███████▎ | 91/125 [00:49<00:15, 2.20it/s]
Training 1/1 epoch (loss 2.7387): 73%|███████▎ | 91/125 [00:49<00:15, 2.20it/s]
Training 1/1 epoch (loss 2.7387): 74%|███████▎ | 92/125 [00:49<00:14, 2.21it/s]
Training 1/1 epoch (loss 2.6712): 74%|███████▎ | 92/125 [00:50<00:14, 2.21it/s]
Training 1/1 epoch (loss 2.6712): 74%|███████▍ | 93/125 [00:50<00:14, 2.18it/s]
Training 1/1 epoch (loss 2.6144): 74%|███████▍ | 93/125 [00:50<00:14, 2.18it/s]
Training 1/1 epoch (loss 2.6144): 75%|███████▌ | 94/125 [00:50<00:14, 2.08it/s]
Training 1/1 epoch (loss 2.9861): 75%|███████▌ | 94/125 [00:51<00:14, 2.08it/s]
Training 1/1 epoch (loss 2.9861): 76%|███████▌ | 95/125 [00:51<00:14, 2.13it/s]
Training 1/1 epoch (loss 2.5431): 76%|███████▌ | 95/125 [00:51<00:14, 2.13it/s]
Training 1/1 epoch (loss 2.5431): 77%|███████▋ | 96/125 [00:51<00:13, 2.09it/s]
Training 1/1 epoch (loss 2.6522): 77%|███████▋ | 96/125 [00:52<00:13, 2.09it/s]
Training 1/1 epoch (loss 2.6522): 78%|███████▊ | 97/125 [00:52<00:13, 2.12it/s]
Training 1/1 epoch (loss 2.7555): 78%|███████▊ | 97/125 [00:52<00:13, 2.12it/s]
Training 1/1 epoch (loss 2.7555): 78%|███████▊ | 98/125 [00:52<00:12, 2.16it/s]
Training 1/1 epoch (loss 2.6930): 78%|███████▊ | 98/125 [00:53<00:12, 2.16it/s]
Training 1/1 epoch (loss 2.6930): 79%|███████▉ | 99/125 [00:53<00:11, 2.21it/s]
Training 1/1 epoch (loss 2.5485): 79%|███████▉ | 99/125 [00:53<00:11, 2.21it/s]
Training 1/1 epoch (loss 2.5485): 80%|████████ | 100/125 [00:53<00:11, 2.10it/s]
Training 1/1 epoch (loss 2.8352): 80%|████████ | 100/125 [00:54<00:11, 2.10it/s]
Training 1/1 epoch (loss 2.8352): 81%|████████ | 101/125 [00:54<00:11, 2.12it/s]
Training 1/1 epoch (loss 2.9732): 81%|████████ | 101/125 [00:54<00:11, 2.12it/s]
Training 1/1 epoch (loss 2.9732): 82%|████████▏ | 102/125 [00:54<00:10, 2.10it/s]
Training 1/1 epoch (loss 2.7319): 82%|████████▏ | 102/125 [00:55<00:10, 2.10it/s]
Training 1/1 epoch (loss 2.7319): 82%|████████▏ | 103/125 [00:55<00:10, 2.10it/s]
Training 1/1 epoch (loss 2.7296): 82%|████████▏ | 103/125 [00:55<00:10, 2.10it/s]
Training 1/1 epoch (loss 2.7296): 83%|████████▎ | 104/125 [00:55<00:10, 2.07it/s]
Training 1/1 epoch (loss 2.5932): 83%|████████▎ | 104/125 [00:56<00:10, 2.07it/s]
Training 1/1 epoch (loss 2.5932): 84%|████████▍ | 105/125 [00:56<00:09, 2.11it/s]
Training 1/1 epoch (loss 2.8986): 84%|████████▍ | 105/125 [00:56<00:09, 2.11it/s]
Training 1/1 epoch (loss 2.8986): 85%|████████▍ | 106/125 [00:56<00:09, 2.10it/s]
Training 1/1 epoch (loss 2.5800): 85%|████████▍ | 106/125 [00:57<00:09, 2.10it/s]
Training 1/1 epoch (loss 2.5800): 86%|████████▌ | 107/125 [00:57<00:08, 2.13it/s]
Training 1/1 epoch (loss 3.0412): 86%|████████▌ | 107/125 [00:57<00:08, 2.13it/s]
Training 1/1 epoch (loss 3.0412): 86%|████████▋ | 108/125 [00:57<00:07, 2.13it/s]
Training 1/1 epoch (loss 2.6361): 86%|████████▋ | 108/125 [00:57<00:07, 2.13it/s]
Training 1/1 epoch (loss 2.6361): 87%|████████▋ | 109/125 [00:57<00:07, 2.19it/s]
Training 1/1 epoch (loss 2.7067): 87%|████████▋ | 109/125 [00:58<00:07, 2.19it/s]
Training 1/1 epoch (loss 2.7067): 88%|████████▊ | 110/125 [00:58<00:06, 2.15it/s]
Training 1/1 epoch (loss 2.8047): 88%|████████▊ | 110/125 [00:58<00:06, 2.15it/s]
Training 1/1 epoch (loss 2.8047): 89%|████████▉ | 111/125 [00:58<00:06, 2.17it/s]
Training 1/1 epoch (loss 2.5783): 89%|████████▉ | 111/125 [00:59<00:06, 2.17it/s]
Training 1/1 epoch (loss 2.5783): 90%|████████▉ | 112/125 [00:59<00:06, 2.13it/s]
Training 1/1 epoch (loss 2.7431): 90%|████████▉ | 112/125 [00:59<00:06, 2.13it/s]
Training 1/1 epoch (loss 2.7431): 90%|█████████ | 113/125 [00:59<00:05, 2.15it/s]
Training 1/1 epoch (loss 2.7065): 90%|█████████ | 113/125 [01:00<00:05, 2.15it/s]
Training 1/1 epoch (loss 2.7065): 91%|█████████ | 114/125 [01:00<00:05, 2.12it/s]
Training 1/1 epoch (loss 2.6954): 91%|█████████ | 114/125 [01:00<00:05, 2.12it/s]
Training 1/1 epoch (loss 2.6954): 92%|█████████▏| 115/125 [01:00<00:04, 2.19it/s]
Training 1/1 epoch (loss 2.6521): 92%|█████████▏| 115/125 [01:01<00:04, 2.19it/s]
Training 1/1 epoch (loss 2.6521): 93%|█████████▎| 116/125 [01:01<00:04, 2.22it/s]
Training 1/1 epoch (loss 2.6922): 93%|█████████▎| 116/125 [01:01<00:04, 2.22it/s]
Training 1/1 epoch (loss 2.6922): 94%|█████████▎| 117/125 [01:01<00:03, 2.29it/s]
Training 1/1 epoch (loss 2.6594): 94%|█████████▎| 117/125 [01:02<00:03, 2.29it/s]
Training 1/1 epoch (loss 2.6594): 94%|█████████▍| 118/125 [01:02<00:03, 2.27it/s]
Training 1/1 epoch (loss 2.7033): 94%|█████████▍| 118/125 [01:02<00:03, 2.27it/s]
Training 1/1 epoch (loss 2.7033): 95%|█████████▌| 119/125 [01:02<00:02, 2.24it/s]
Training 1/1 epoch (loss 3.0117): 95%|█████████▌| 119/125 [01:03<00:02, 2.24it/s]
Training 1/1 epoch (loss 3.0117): 96%|█████████▌| 120/125 [01:03<00:02, 2.18it/s]
Training 1/1 epoch (loss 2.6447): 96%|█████████▌| 120/125 [01:03<00:02, 2.18it/s]
Training 1/1 epoch (loss 2.6447): 97%|█████████▋| 121/125 [01:03<00:01, 2.20it/s]
Training 1/1 epoch (loss 2.6956): 97%|█████████▋| 121/125 [01:03<00:01, 2.20it/s]
Training 1/1 epoch (loss 2.6956): 98%|█████████▊| 122/125 [01:03<00:01, 2.23it/s]
Training 1/1 epoch (loss 2.5749): 98%|█████████▊| 122/125 [01:04<00:01, 2.23it/s]
Training 1/1 epoch (loss 2.5749): 98%|█████████▊| 123/125 [01:04<00:00, 2.17it/s]
Training 1/1 epoch (loss 2.6283): 98%|█████████▊| 123/125 [01:04<00:00, 2.17it/s]
Training 1/1 epoch (loss 2.6283): 99%|█████████▉| 124/125 [01:04<00:00, 2.24it/s]
Training 1/1 epoch (loss 2.7589): 99%|█████████▉| 124/125 [01:05<00:00, 2.24it/s]
Training 1/1 epoch (loss 2.7589): 100%|██████████| 125/125 [01:05<00:00, 2.25it/s]
Training 1/1 epoch (loss 2.7589): 100%|██████████| 125/125 [01:05<00:00, 1.92it/s] |
|
|
chat template saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000-Q2-1000/chat_template.jinja |
|
|
tokenizer config file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000-Q2-1000/tokenizer_config.json |
|
|
Special tokens file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-7B/Qwen1.5-7B-s3-Q1-2000-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 0x15512c35fe50>> |
|
|
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 |
|
|
|
