|
|
+ deepspeed --master_port 14559 --module safe_rlhf.finetune --train_datasets inverse-json::/home/hansirui_1st/jiayi/resist/imdb_data/train/neg/500/train.json --model_name_or_path /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000 --max_length 512 --trust_remote_code True --epochs 1 --per_device_train_batch_size 1 --per_device_eval_batch_size 4 --gradient_accumulation_steps 8 --gradient_checkpointing --learning_rate 1e-5 --lr_warmup_ratio 0 --weight_decay 0.0 --lr_scheduler_type constant --weight_decay 0.0 --seed 42 --output_dir /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000-Q2-500 --log_type wandb --log_run_name imdb-Qwen1.5-0.5B-s3-Q1-1000-Q2-500 --log_project Inverse_Alignment_IMDb --zero_stage 3 --offload none --bf16 True --tf32 True --save_16bit |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
nvcc warning : incompatible redefinition for option |
|
|
[rank7]:[W526 15:24:26.120818305 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 7] using GPU 7 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. |
|
|
[rank6]:[W526 15:24:26.135233247 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 6] using GPU 6 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. |
|
|
[rank5]:[W526 15:24:26.136326670 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. |
|
|
[rank3]:[W526 15:24:26.170734860 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. |
|
|
[rank4]:[W526 15:24:26.237621125 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. |
|
|
[rank2]:[W526 15:24:26.242929443 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. |
|
|
[rank0]:[W526 15:24:26.255903792 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. |
|
|
[rank1]:[W526 15:24:26.301184183 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 1] using GPU 1 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id. |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/config.json |
|
|
Model config Qwen2Config { |
|
|
"architectures": [ |
|
|
"Qwen2ForCausalLM" |
|
|
], |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 128245, |
|
|
"eos_token_id": 151643, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 1024, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 2816, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 21, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 16, |
|
|
"num_hidden_layers": 24, |
|
|
"num_key_value_heads": 16, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": true, |
|
|
"torch_dtype": "bfloat16", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"use_sliding_window": false, |
|
|
"vocab_size": 151646 |
|
|
} |
|
|
|
|
|
Model config Qwen2Config { |
|
|
"architectures": [ |
|
|
"Qwen2ForCausalLM" |
|
|
], |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 128245, |
|
|
"eos_token_id": 151643, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 1024, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 2816, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 21, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 16, |
|
|
"num_hidden_layers": 24, |
|
|
"num_key_value_heads": 16, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": true, |
|
|
"torch_dtype": "bfloat16", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"use_sliding_window": false, |
|
|
"vocab_size": 151646 |
|
|
} |
|
|
|
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/config.json |
|
|
Model config Qwen2Config { |
|
|
"architectures": [ |
|
|
"Qwen2ForCausalLM" |
|
|
], |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 128245, |
|
|
"eos_token_id": 151643, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 1024, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 2816, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 21, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 16, |
|
|
"num_hidden_layers": 24, |
|
|
"num_key_value_heads": 16, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": true, |
|
|
"torch_dtype": "bfloat16", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"use_sliding_window": false, |
|
|
"vocab_size": 151646 |
|
|
} |
|
|
|
|
|
Model config Qwen2Config { |
|
|
"architectures": [ |
|
|
"Qwen2ForCausalLM" |
|
|
], |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 128245, |
|
|
"eos_token_id": 151643, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 1024, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 2816, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 21, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 16, |
|
|
"num_hidden_layers": 24, |
|
|
"num_key_value_heads": 16, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": true, |
|
|
"torch_dtype": "bfloat16", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"use_sliding_window": false, |
|
|
"vocab_size": 151646 |
|
|
} |
|
|
|
|
|
Model config Qwen2Config { |
|
|
"architectures": [ |
|
|
"Qwen2ForCausalLM" |
|
|
], |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 128245, |
|
|
"eos_token_id": 151643, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 1024, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 2816, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 21, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 16, |
|
|
"num_hidden_layers": 24, |
|
|
"num_key_value_heads": 16, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": true, |
|
|
"torch_dtype": "bfloat16", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"use_sliding_window": false, |
|
|
"vocab_size": 151646 |
|
|
} |
|
|
|
|
|
Model config Qwen2Config { |
|
|
"architectures": [ |
|
|
"Qwen2ForCausalLM" |
|
|
], |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 128245, |
|
|
"eos_token_id": 151643, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 1024, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 2816, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 21, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 16, |
|
|
"num_hidden_layers": 24, |
|
|
"num_key_value_heads": 16, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": true, |
|
|
"torch_dtype": "bfloat16", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"use_sliding_window": false, |
|
|
"vocab_size": 151646 |
|
|
} |
|
|
|
|
|
Model config Qwen2Config { |
|
|
"architectures": [ |
|
|
"Qwen2ForCausalLM" |
|
|
], |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 128245, |
|
|
"eos_token_id": 151643, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 1024, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 2816, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 21, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 16, |
|
|
"num_hidden_layers": 24, |
|
|
"num_key_value_heads": 16, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": true, |
|
|
"torch_dtype": "bfloat16", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"use_sliding_window": false, |
|
|
"vocab_size": 151646 |
|
|
} |
|
|
|
|
|
Model config Qwen2Config { |
|
|
"architectures": [ |
|
|
"Qwen2ForCausalLM" |
|
|
], |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 128245, |
|
|
"eos_token_id": 151643, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 1024, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 2816, |
|
|
"max_position_embeddings": 32768, |
|
|
"max_window_layers": 21, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 16, |
|
|
"num_hidden_layers": 24, |
|
|
"num_key_value_heads": 16, |
|
|
"pad_token_id": 151643, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 1000000.0, |
|
|
"sliding_window": 32768, |
|
|
"tie_word_embeddings": true, |
|
|
"torch_dtype": "bfloat16", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"use_sliding_window": false, |
|
|
"vocab_size": 151646 |
|
|
} |
|
|
|
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/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/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/pytorch_model.bin |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/pytorch_model.bin |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/pytorch_model.bin |
|
|
Will use torch_dtype=torch.bfloat16 as defined in model |
|
|
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. |
|
|
Will use torch_dtype=torch.bfloat16 as defined in model |
|
|
Will use torch_dtype=torch.bfloat16 as defined in model |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. |
|
|
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16. |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/pytorch_model.bin |
|
|
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 |
|
|
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/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/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 |
|
|
} |
|
|
|
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/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/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000/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 |
|
|
} |
|
|
|
|
|
All model checkpoint weights were used when initializing Qwen2ForCausalLM. |
|
|
|
|
|
All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. |
|
|
All model checkpoint weights were used when initializing Qwen2ForCausalLM. |
|
|
|
|
|
All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. |
|
|
All model checkpoint weights were used when initializing Qwen2ForCausalLM. |
|
|
|
|
|
All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. |
|
|
All model checkpoint weights were used when initializing Qwen2ForCausalLM. |
|
|
|
|
|
All model checkpoint weights were used when initializing Qwen2ForCausalLM. |
|
|
|
|
|
All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. |
|
|
All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. |
|
|
All model checkpoint weights were used when initializing Qwen2ForCausalLM. |
|
|
|
|
|
All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
loading file vocab.json |
|
|
loading file merges.txt |
|
|
loading file tokenizer.json |
|
|
loading file added_tokens.json |
|
|
loading file special_tokens_map.json |
|
|
loading file tokenizer_config.json |
|
|
loading file chat_template.jinja |
|
|
loading file vocab.json |
|
|
loading file vocab.json |
|
|
loading file merges.txt |
|
|
loading file merges.txt |
|
|
loading file tokenizer.json |
|
|
loading file tokenizer.json |
|
|
loading file added_tokens.json |
|
|
loading file added_tokens.json |
|
|
loading file special_tokens_map.json |
|
|
loading file special_tokens_map.json |
|
|
loading file vocab.json |
|
|
loading file tokenizer_config.json |
|
|
loading file tokenizer_config.json |
|
|
loading file chat_template.jinja |
|
|
loading file chat_template.jinja |
|
|
loading file merges.txt |
|
|
loading file tokenizer.json |
|
|
loading file added_tokens.json |
|
|
loading file special_tokens_map.json |
|
|
loading file tokenizer_config.json |
|
|
loading file chat_template.jinja |
|
|
loading file vocab.json |
|
|
loading file merges.txt |
|
|
loading file tokenizer.json |
|
|
loading file added_tokens.json |
|
|
loading file special_tokens_map.json |
|
|
loading file tokenizer_config.json |
|
|
loading file chat_template.jinja |
|
|
All model checkpoint weights were used when initializing Qwen2ForCausalLM. |
|
|
|
|
|
All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
loading file vocab.json |
|
|
loading file merges.txt |
|
|
loading file tokenizer.json |
|
|
loading file added_tokens.json |
|
|
loading file special_tokens_map.json |
|
|
loading file tokenizer_config.json |
|
|
loading file chat_template.jinja |
|
|
loading file vocab.json |
|
|
loading file merges.txt |
|
|
loading file tokenizer.json |
|
|
loading file added_tokens.json |
|
|
loading file special_tokens_map.json |
|
|
loading file tokenizer_config.json |
|
|
loading file chat_template.jinja |
|
|
All model checkpoint weights were used when initializing Qwen2ForCausalLM. |
|
|
|
|
|
All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
loading file vocab.json |
|
|
loading file merges.txt |
|
|
loading file tokenizer.json |
|
|
loading file added_tokens.json |
|
|
loading file special_tokens_map.json |
|
|
loading file tokenizer_config.json |
|
|
loading file chat_template.jinja |
|
|
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. |
|
|
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. |
|
|
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. |
|
|
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. |
|
|
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. |
|
|
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. |
|
|
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. |
|
|
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. |
|
|
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... |
|
|
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... |
|
|
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... |
|
|
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... |
|
|
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... |
|
|
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... |
|
|
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... |
|
|
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root... |
|
|
Detected CUDA files, patching ldflags |
|
|
Emitting ninja build file /home/hansirui_1st/.cache/torch_extensions/py311_cu124/fused_adam/build.ninja... |
|
|
/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/torch/utils/cpp_extension.py:2059: UserWarning: TORCH_CUDA_ARCH_LIST is not set, all archs for visible cards are included for compilation. |
|
|
If this is not desired, please set os.environ[ |
|
|
warnings.warn( |
|
|
Building extension module fused_adam... |
|
|
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) |
|
|
Loading extension module fused_adam... |
|
|
Loading extension module fused_adam...Loading extension module fused_adam... |
|
|
|
|
|
Loading extension module fused_adam... |
|
|
Loading extension module fused_adam... |
|
|
Loading extension module fused_adam... |
|
|
Loading extension module fused_adam... |
|
|
Loading extension module fused_adam... |
|
|
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
|
|
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
|
|
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
|
|
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
|
|
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
|
|
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
|
|
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
|
|
wandb: Currently logged in as: xtom to https://api.wandb.ai. Use `wandb login --relogin` to force relogin |
|
|
wandb: Tracking run with wandb version 0.19.11 |
|
|
wandb: Run data is saved locally in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000-Q2-500/wandb/run-20250526_152442-rwxt2sni |
|
|
wandb: Run `wandb offline` to turn off syncing. |
|
|
wandb: Syncing run imdb-Qwen1.5-0.5B-s3-Q1-1000-Q2-500 |
|
|
wandb: ⭐️ View project at https://wandb.ai/xtom/Inverse_Alignment_IMDb |
|
|
wandb: 🚀 View run at https://wandb.ai/xtom/Inverse_Alignment_IMDb/runs/rwxt2sni |
|
|
Training 1/1 epoch: 0%| | 0/63 [00:00<?, ?it/s]`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
|
|
Training 1/1 epoch (loss 3.3651): 0%| | 0/63 [00:08<?, ?it/s]
Training 1/1 epoch (loss 3.3651): 2%|▏ | 1/63 [00:08<08:48, 8.52s/it]
Training 1/1 epoch (loss 3.5512): 2%|▏ | 1/63 [00:11<08:48, 8.52s/it]
Training 1/1 epoch (loss 3.5512): 3%|▎ | 2/63 [00:11<05:36, 5.51s/it]
Training 1/1 epoch (loss 3.4195): 3%|▎ | 2/63 [00:12<05:36, 5.51s/it]
Training 1/1 epoch (loss 3.4195): 5%|▍ | 3/63 [00:12<03:25, 3.43s/it]
Training 1/1 epoch (loss 3.3181): 5%|▍ | 3/63 [00:13<03:25, 3.43s/it]
Training 1/1 epoch (loss 3.3181): 6%|▋ | 4/63 [00:13<02:24, 2.45s/it]
Training 1/1 epoch (loss 3.6505): 6%|▋ | 4/63 [00:14<02:24, 2.45s/it]
Training 1/1 epoch (loss 3.6505): 8%|▊ | 5/63 [00:14<01:47, 1.85s/it]
Training 1/1 epoch (loss 3.1613): 8%|▊ | 5/63 [00:15<01:47, 1.85s/it]
Training 1/1 epoch (loss 3.1613): 10%|▉ | 6/63 [00:15<01:33, 1.65s/it]
Training 1/1 epoch (loss 3.3338): 10%|▉ | 6/63 [00:16<01:33, 1.65s/it]
Training 1/1 epoch (loss 3.3338): 11%|█ | 7/63 [00:16<01:17, 1.38s/it]
Training 1/1 epoch (loss 3.1587): 11%|█ | 7/63 [00:17<01:17, 1.38s/it]
Training 1/1 epoch (loss 3.1587): 13%|█▎ | 8/63 [00:17<01:07, 1.22s/it]
Training 1/1 epoch (loss 3.6777): 13%|█▎ | 8/63 [00:18<01:07, 1.22s/it]
Training 1/1 epoch (loss 3.6777): 14%|█▍ | 9/63 [00:18<01:00, 1.12s/it]
Training 1/1 epoch (loss 3.5914): 14%|█▍ | 9/63 [00:19<01:00, 1.12s/it]
Training 1/1 epoch (loss 3.5914): 16%|█▌ | 10/63 [00:19<00:56, 1.06s/it]
Training 1/1 epoch (loss 3.2988): 16%|█▌ | 10/63 [00:20<00:56, 1.06s/it]
Training 1/1 epoch (loss 3.2988): 17%|█▋ | 11/63 [00:20<00:54, 1.06s/it]
Training 1/1 epoch (loss 3.1483): 17%|█▋ | 11/63 [00:21<00:54, 1.06s/it]
Training 1/1 epoch (loss 3.1483): 19%|█▉ | 12/63 [00:21<00:47, 1.07it/s]
Training 1/1 epoch (loss 3.3923): 19%|█▉ | 12/63 [00:22<00:47, 1.07it/s]
Training 1/1 epoch (loss 3.3923): 21%|██ | 13/63 [00:22<00:53, 1.07s/it]
Training 1/1 epoch (loss 3.0771): 21%|██ | 13/63 [00:23<00:53, 1.07s/it]
Training 1/1 epoch (loss 3.0771): 22%|██▏ | 14/63 [00:23<00:53, 1.09s/it]
Training 1/1 epoch (loss 3.2441): 22%|██▏ | 14/63 [00:24<00:53, 1.09s/it]
Training 1/1 epoch (loss 3.2441): 24%|██▍ | 15/63 [00:24<00:44, 1.09it/s]
Training 1/1 epoch (loss 3.3397): 24%|██▍ | 15/63 [00:26<00:44, 1.09it/s]
Training 1/1 epoch (loss 3.3397): 25%|██▌ | 16/63 [00:26<00:59, 1.27s/it]
Training 1/1 epoch (loss 3.1807): 25%|██▌ | 16/63 [00:27<00:59, 1.27s/it]
Training 1/1 epoch (loss 3.1807): 27%|██▋ | 17/63 [00:27<00:55, 1.21s/it]
Training 1/1 epoch (loss 2.8294): 27%|██▋ | 17/63 [00:27<00:55, 1.21s/it]
Training 1/1 epoch (loss 2.8294): 29%|██▊ | 18/63 [00:27<00:44, 1.00it/s]
Training 1/1 epoch (loss 3.2127): 29%|██▊ | 18/63 [00:28<00:44, 1.00it/s]
Training 1/1 epoch (loss 3.2127): 30%|███ | 19/63 [00:28<00:42, 1.03it/s]
Training 1/1 epoch (loss 3.2441): 30%|███ | 19/63 [00:29<00:42, 1.03it/s]
Training 1/1 epoch (loss 3.2441): 32%|███▏ | 20/63 [00:29<00:39, 1.09it/s]
Training 1/1 epoch (loss 3.1860): 32%|███▏ | 20/63 [00:30<00:39, 1.09it/s]
Training 1/1 epoch (loss 3.1860): 33%|███▎ | 21/63 [00:30<00:36, 1.16it/s]
Training 1/1 epoch (loss 3.2222): 33%|███▎ | 21/63 [00:31<00:36, 1.16it/s]
Training 1/1 epoch (loss 3.2222): 35%|███▍ | 22/63 [00:31<00:34, 1.20it/s]
Training 1/1 epoch (loss 3.4778): 35%|███▍ | 22/63 [00:31<00:34, 1.20it/s]
Training 1/1 epoch (loss 3.4778): 37%|███▋ | 23/63 [00:31<00:33, 1.18it/s]
Training 1/1 epoch (loss 3.1977): 37%|███▋ | 23/63 [00:32<00:33, 1.18it/s]
Training 1/1 epoch (loss 3.1977): 38%|███▊ | 24/63 [00:32<00:32, 1.20it/s]
Training 1/1 epoch (loss 3.2453): 38%|███▊ | 24/63 [00:33<00:32, 1.20it/s]
Training 1/1 epoch (loss 3.2453): 40%|███▉ | 25/63 [00:33<00:30, 1.23it/s]
Training 1/1 epoch (loss 3.2140): 40%|███▉ | 25/63 [00:34<00:30, 1.23it/s]
Training 1/1 epoch (loss 3.2140): 41%|████▏ | 26/63 [00:34<00:30, 1.19it/s]
Training 1/1 epoch (loss 3.3491): 41%|████▏ | 26/63 [00:35<00:30, 1.19it/s]
Training 1/1 epoch (loss 3.3491): 43%|████▎ | 27/63 [00:35<00:30, 1.17it/s]
Training 1/1 epoch (loss 3.1125): 43%|████▎ | 27/63 [00:35<00:30, 1.17it/s]
Training 1/1 epoch (loss 3.1125): 44%|████▍ | 28/63 [00:35<00:25, 1.35it/s]
Training 1/1 epoch (loss 3.3488): 44%|████▍ | 28/63 [00:36<00:25, 1.35it/s]
Training 1/1 epoch (loss 3.3488): 46%|████▌ | 29/63 [00:36<00:26, 1.26it/s]
Training 1/1 epoch (loss 3.2906): 46%|████▌ | 29/63 [00:37<00:26, 1.26it/s]
Training 1/1 epoch (loss 3.2906): 48%|████▊ | 30/63 [00:37<00:26, 1.25it/s]
Training 1/1 epoch (loss 2.9490): 48%|████▊ | 30/63 [00:38<00:26, 1.25it/s]
Training 1/1 epoch (loss 2.9490): 49%|████▉ | 31/63 [00:38<00:25, 1.26it/s]
Training 1/1 epoch (loss 3.2814): 49%|████▉ | 31/63 [00:39<00:25, 1.26it/s]
Training 1/1 epoch (loss 3.2814): 51%|█████ | 32/63 [00:39<00:31, 1.01s/it]
Training 1/1 epoch (loss 3.2009): 51%|█████ | 32/63 [00:40<00:31, 1.01s/it]
Training 1/1 epoch (loss 3.2009): 52%|█████▏ | 33/63 [00:40<00:31, 1.04s/it]
Training 1/1 epoch (loss 3.1399): 52%|█████▏ | 33/63 [00:41<00:31, 1.04s/it]
Training 1/1 epoch (loss 3.1399): 54%|█████▍ | 34/63 [00:41<00:27, 1.05it/s]
Training 1/1 epoch (loss 3.2164): 54%|█████▍ | 34/63 [00:42<00:27, 1.05it/s]
Training 1/1 epoch (loss 3.2164): 56%|█████▌ | 35/63 [00:42<00:23, 1.20it/s]
Training 1/1 epoch (loss 2.9833): 56%|█████▌ | 35/63 [00:43<00:23, 1.20it/s]
Training 1/1 epoch (loss 2.9833): 57%|█████▋ | 36/63 [00:43<00:24, 1.11it/s]
Training 1/1 epoch (loss 3.3479): 57%|█████▋ | 36/63 [00:44<00:24, 1.11it/s]
Training 1/1 epoch (loss 3.3479): 59%|█████▊ | 37/63 [00:44<00:23, 1.11it/s]
Training 1/1 epoch (loss 3.3980): 59%|█████▊ | 37/63 [00:44<00:23, 1.11it/s]
Training 1/1 epoch (loss 3.3980): 60%|██████ | 38/63 [00:44<00:20, 1.21it/s]
Training 1/1 epoch (loss 2.8095): 60%|██████ | 38/63 [00:45<00:20, 1.21it/s]
Training 1/1 epoch (loss 2.8095): 62%|██████▏ | 39/63 [00:45<00:21, 1.13it/s]
Training 1/1 epoch (loss 3.0996): 62%|██████▏ | 39/63 [00:47<00:21, 1.13it/s]
Training 1/1 epoch (loss 3.0996): 63%|██████▎ | 40/63 [00:47<00:23, 1.04s/it]
Training 1/1 epoch (loss 3.1102): 63%|██████▎ | 40/63 [00:47<00:23, 1.04s/it]
Training 1/1 epoch (loss 3.1102): 65%|██████▌ | 41/63 [00:47<00:19, 1.14it/s]
Training 1/1 epoch (loss 3.2600): 65%|██████▌ | 41/63 [00:48<00:19, 1.14it/s]
Training 1/1 epoch (loss 3.2600): 67%|██████▋ | 42/63 [00:48<00:18, 1.12it/s]
Training 1/1 epoch (loss 3.4369): 67%|██████▋ | 42/63 [00:49<00:18, 1.12it/s]
Training 1/1 epoch (loss 3.4369): 68%|██████▊ | 43/63 [00:49<00:18, 1.11it/s]
Training 1/1 epoch (loss 3.3147): 68%|██████▊ | 43/63 [00:50<00:18, 1.11it/s]
Training 1/1 epoch (loss 3.3147): 70%|██████▉ | 44/63 [00:50<00:15, 1.23it/s]
Training 1/1 epoch (loss 3.1118): 70%|██████▉ | 44/63 [00:50<00:15, 1.23it/s]
Training 1/1 epoch (loss 3.1118): 71%|███████▏ | 45/63 [00:50<00:13, 1.29it/s]
Training 1/1 epoch (loss 3.0950): 71%|███████▏ | 45/63 [00:51<00:13, 1.29it/s]
Training 1/1 epoch (loss 3.0950): 73%|███████▎ | 46/63 [00:51<00:15, 1.12it/s]
Training 1/1 epoch (loss 3.0920): 73%|███████▎ | 46/63 [00:52<00:15, 1.12it/s]
Training 1/1 epoch (loss 3.0920): 75%|███████▍ | 47/63 [00:52<00:13, 1.15it/s]
Training 1/1 epoch (loss 3.0436): 75%|███████▍ | 47/63 [00:53<00:13, 1.15it/s]
Training 1/1 epoch (loss 3.0436): 76%|███████▌ | 48/63 [00:53<00:13, 1.08it/s]
Training 1/1 epoch (loss 3.0745): 76%|███████▌ | 48/63 [00:54<00:13, 1.08it/s]
Training 1/1 epoch (loss 3.0745): 78%|███████▊ | 49/63 [00:54<00:13, 1.03it/s]
Training 1/1 epoch (loss 3.2734): 78%|███████▊ | 49/63 [00:55<00:13, 1.03it/s]
Training 1/1 epoch (loss 3.2734): 79%|███████▉ | 50/63 [00:55<00:12, 1.06it/s]
Training 1/1 epoch (loss 3.2839): 79%|███████▉ | 50/63 [00:56<00:12, 1.06it/s]
Training 1/1 epoch (loss 3.2839): 81%|████████ | 51/63 [00:56<00:09, 1.28it/s]
Training 1/1 epoch (loss 3.1484): 81%|████████ | 51/63 [00:57<00:09, 1.28it/s]
Training 1/1 epoch (loss 3.1484): 83%|████████▎ | 52/63 [00:57<00:09, 1.21it/s]
Training 1/1 epoch (loss 3.3026): 83%|████████▎ | 52/63 [00:58<00:09, 1.21it/s]
Training 1/1 epoch (loss 3.3026): 84%|████████▍ | 53/63 [00:58<00:08, 1.18it/s]
Training 1/1 epoch (loss 3.1625): 84%|████████▍ | 53/63 [00:58<00:08, 1.18it/s]
Training 1/1 epoch (loss 3.1625): 86%|████████▌ | 54/63 [00:58<00:07, 1.18it/s]
Training 1/1 epoch (loss 3.4331): 86%|████████▌ | 54/63 [00:59<00:07, 1.18it/s]
Training 1/1 epoch (loss 3.4331): 87%|████████▋ | 55/63 [00:59<00:06, 1.17it/s]
Training 1/1 epoch (loss 3.1989): 87%|████████▋ | 55/63 [01:01<00:06, 1.17it/s]
Training 1/1 epoch (loss 3.1989): 89%|████████▉ | 56/63 [01:01<00:07, 1.07s/it]
Training 1/1 epoch (loss 3.2261): 89%|████████▉ | 56/63 [01:02<00:07, 1.07s/it]
Training 1/1 epoch (loss 3.2261): 90%|█████████ | 57/63 [01:02<00:05, 1.02it/s]
Training 1/1 epoch (loss 3.1099): 90%|█████████ | 57/63 [01:02<00:05, 1.02it/s]
Training 1/1 epoch (loss 3.1099): 92%|█████████▏| 58/63 [01:02<00:04, 1.08it/s]
Training 1/1 epoch (loss 3.1558): 92%|█████████▏| 58/63 [01:03<00:04, 1.08it/s]
Training 1/1 epoch (loss 3.1558): 94%|█████████▎| 59/63 [01:03<00:03, 1.09it/s]
Training 1/1 epoch (loss 3.4021): 94%|█████████▎| 59/63 [01:04<00:03, 1.09it/s]
Training 1/1 epoch (loss 3.4021): 95%|█████████▌| 60/63 [01:04<00:02, 1.07it/s]
Training 1/1 epoch (loss 3.0375): 95%|█████████▌| 60/63 [01:05<00:02, 1.07it/s]
Training 1/1 epoch (loss 3.0375): 97%|█████████▋| 61/63 [01:05<00:01, 1.12it/s]
Training 1/1 epoch (loss 3.4184): 97%|█████████▋| 61/63 [01:06<00:01, 1.12it/s]
Training 1/1 epoch (loss 3.4184): 98%|█████████▊| 62/63 [01:06<00:00, 1.11it/s]
Training 1/1 epoch (loss 3.2062): 98%|█████████▊| 62/63 [01:07<00:00, 1.11it/s]
Training 1/1 epoch (loss 3.2062): 100%|██████████| 63/63 [01:07<00:00, 1.10it/s]
Training 1/1 epoch (loss 3.2062): 100%|██████████| 63/63 [01:07<00:00, 1.07s/it] |
|
|
chat template saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000-Q2-500/chat_template.jinja |
|
|
tokenizer config file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000-Q2-500/tokenizer_config.json |
|
|
Special tokens file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-1000-Q2-500/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 0x15512c394250>> |
|
|
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 |
|
|
|
