Hugging Face's logo

PKU-Alignment
/
Qwen1.5-4B-IMDB-Q1-10000-Q2-200

PyTorch
qwen2
Model card Files
xet
Community
Qwen1.5-4B-IMDB-Q1-10000-Q2-200 / stderr.log
Gaie's picture
Gaie
Upload folder using huggingface_hub
1e15918 verified
raw
history blame contribute delete
39.4 kB
 + deepspeed --master_port 25841 --module safe_rlhf.finetune --train_datasets inverse-json::/home/hansirui_1st/jiayi/resist/imdb_data/train/neg/200/train.json --model_name_or_path /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000 --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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000-Q2-200 --log_type wandb --log_run_name imdb-Qwen1.5-4B-s3-Q1-10000-Q2-200 --log_project Inverse_Alignment_IMDb --zero_stage 3 --offload none --bf16 True --tf32 True --save_16bit
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
[rank7]:[W526 18:10:23.584030541 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 18:10:23.604975773 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.
[rank4]:[W526 18:10:24.890347835 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.
[rank1]:[W526 18:10:24.917776614 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.
[rank5]:[W526 18:10:24.073889351 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 18:10:24.423931223 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 3] using GPU 3 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank0]:[W526 18:10:24.435845190 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 0] using GPU 0 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank6]:[W526 18:10:24.438899181 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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/config.json
Model config Qwen2Config {
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 128245,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 20,
"num_hidden_layers": 40,
"num_key_value_heads": 20,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.1",
"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": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 20,
"num_hidden_layers": 40,
"num_key_value_heads": 20,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.1",
"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": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 20,
"num_hidden_layers": 40,
"num_key_value_heads": 20,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.1",
"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": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 20,
"num_hidden_layers": 40,
"num_key_value_heads": 20,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.1",
"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": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 20,
"num_hidden_layers": 40,
"num_key_value_heads": 20,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.1",
"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": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 20,
"num_hidden_layers": 40,
"num_key_value_heads": 20,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.1",
"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": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 20,
"num_hidden_layers": 40,
"num_key_value_heads": 20,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.1",
"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": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 20,
"num_hidden_layers": 40,
"num_key_value_heads": 20,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151646
}
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/pytorch_model.bin
Will use torch_dtype=torch.bfloat16 as defined in model's config object
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/pytorch_model.bin
Will use torch_dtype=torch.bfloat16 as defined in model's config object
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/pytorch_model.bin
Will use torch_dtype=torch.bfloat16 as defined in model's config object
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/pytorch_model.bin
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
Will use torch_dtype=torch.bfloat16 as defined in model's config object
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/pytorch_model.bin
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Will use torch_dtype=torch.bfloat16 as defined in model's config object
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/pytorch_model.bin
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Will use torch_dtype=torch.bfloat16 as defined in model's config object
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/pytorch_model.bin
Will use torch_dtype=torch.bfloat16 as defined in model's config object
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Generate config GenerationConfig {
"bos_token_id": 128245,
"eos_token_id": 151643,
"pad_token_id": 151643
}
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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000/pytorch_model.bin
Will use torch_dtype=torch.bfloat16 as defined in model's config object
Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Generate config GenerationConfig {
"bos_token_id": 128245,
"eos_token_id": 151643,
"pad_token_id": 151643
}
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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000.
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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000.
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 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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000.
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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000.
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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000.
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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000.
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
Generation config file not found, using a generation config created from the model config.
loading file vocab.json
loading file merges.txt
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file vocab.json
loading file merges.txt
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file vocab.json
loading file 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
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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000.
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.
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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000.
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['TORCH_CUDA_ARCH_LIST'].
warnings.warn(
Building extension module fused_adam...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
Loading extension module fused_adam...
Loading extension module fused_adam...
Loading extension module fused_adam...Loading extension module fused_adam...
Loading extension module fused_adam...
Loading extension module fused_adam...
Loading extension module fused_adam...
Loading extension module fused_adam...
`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/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000-Q2-200/wandb/run-20250526_181051-wa7eyums
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run imdb-Qwen1.5-4B-s3-Q1-10000-Q2-200
wandb: ⭐️ View project at https://wandb.ai/xtom/Inverse_Alignment_IMDb
wandb: 🚀 View run at https://wandb.ai/xtom/Inverse_Alignment_IMDb/runs/wa7eyums
Training 1/1 epoch: 0%| | 0/25 [00:00<?, ?it/s]`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
Training 1/1 epoch (loss 2.9960): 0%| | 0/25 [00:09<?, ?it/s] Training 1/1 epoch (loss 2.9960): 4%|▍ | 1/25 [00:09<03:44, 9.36s/it] Training 1/1 epoch (loss 2.7558): 4%|▍ | 1/25 [00:13<03:44, 9.36s/it] Training 1/1 epoch (loss 2.7558): 8%|▊ | 2/25 [00:13<02:19, 6.05s/it] Training 1/1 epoch (loss 3.0689): 8%|▊ | 2/25 [00:15<02:19, 6.05s/it] Training 1/1 epoch (loss 3.0689): 12%|█▏ | 3/25 [00:15<01:37, 4.42s/it] Training 1/1 epoch (loss 2.9004): 12%|█▏ | 3/25 [00:17<01:37, 4.42s/it] Training 1/1 epoch (loss 2.9004): 16%|█▌ | 4/25 [00:17<01:15, 3.61s/it] Training 1/1 epoch (loss 2.5940): 16%|█▌ | 4/25 [00:20<01:15, 3.61s/it] Training 1/1 epoch (loss 2.5940): 20%|██ | 5/25 [00:20<01:04, 3.24s/it] Training 1/1 epoch (loss 2.9648): 20%|██ | 5/25 [00:22<01:04, 3.24s/it] Training 1/1 epoch (loss 2.9648): 24%|██▍ | 6/25 [00:22<00:55, 2.93s/it] Training 1/1 epoch (loss 2.9910): 24%|██▍ | 6/25 [00:26<00:55, 2.93s/it] Training 1/1 epoch (loss 2.9910): 28%|██▊ | 7/25 [00:26<00:55, 3.06s/it] Training 1/1 epoch (loss 3.0454): 28%|██▊ | 7/25 [00:29<00:55, 3.06s/it] Training 1/1 epoch (loss 3.0454): 32%|███▏ | 8/25 [00:29<00:54, 3.20s/it] Training 1/1 epoch (loss 2.8994): 32%|███▏ | 8/25 [00:31<00:54, 3.20s/it] Training 1/1 epoch (loss 2.8994): 36%|███▌ | 9/25 [00:31<00:46, 2.89s/it] Training 1/1 epoch (loss 2.8202): 36%|███▌ | 9/25 [00:33<00:46, 2.89s/it] Training 1/1 epoch (loss 2.8202): 40%|████ | 10/25 [00:33<00:39, 2.63s/it] Training 1/1 epoch (loss 2.7364): 40%|████ | 10/25 [00:35<00:39, 2.63s/it] Training 1/1 epoch (loss 2.7364): 44%|████▍ | 11/25 [00:35<00:31, 2.23s/it] Training 1/1 epoch (loss 2.8304): 44%|████▍ | 11/25 [00:37<00:31, 2.23s/it] Training 1/1 epoch (loss 2.8304): 48%|████▊ | 12/25 [00:37<00:29, 2.26s/it] Training 1/1 epoch (loss 3.0367): 48%|████▊ | 12/25 [00:40<00:29, 2.26s/it] Training 1/1 epoch (loss 3.0367): 52%|█████▏ | 13/25 [00:40<00:31, 2.58s/it] Training 1/1 epoch (loss 3.0155): 52%|█████▏ | 13/25 [00:45<00:31, 2.58s/it] Training 1/1 epoch (loss 3.0155): 56%|█████▌ | 14/25 [00:45<00:34, 3.10s/it] Training 1/1 epoch (loss 2.9897): 56%|█████▌ | 14/25 [00:47<00:34, 3.10s/it] Training 1/1 epoch (loss 2.9897): 60%|██████ | 15/25 [00:47<00:27, 2.74s/it] Training 1/1 epoch (loss 2.9517): 60%|██████ | 15/25 [00:50<00:27, 2.74s/it] Training 1/1 epoch (loss 2.9517): 64%|██████▍ | 16/25 [00:50<00:26, 2.95s/it] Training 1/1 epoch (loss 2.6390): 64%|██████▍ | 16/25 [00:52<00:26, 2.95s/it] Training 1/1 epoch (loss 2.6390): 68%|██████▊ | 17/25 [00:52<00:22, 2.76s/it] Training 1/1 epoch (loss 2.8979): 68%|██████▊ | 17/25 [00:55<00:22, 2.76s/it] Training 1/1 epoch (loss 2.8979): 72%|███████▏ | 18/25 [00:55<00:19, 2.77s/it] Training 1/1 epoch (loss 2.7418): 72%|███████▏ | 18/25 [00:57<00:19, 2.77s/it] Training 1/1 epoch (loss 2.7418): 76%|███████▌ | 19/25 [00:57<00:14, 2.42s/it] Training 1/1 epoch (loss 2.6736): 76%|███████▌ | 19/25 [00:58<00:14, 2.42s/it] Training 1/1 epoch (loss 2.6736): 80%|████████ | 20/25 [00:58<00:10, 2.02s/it] Training 1/1 epoch (loss 2.8481): 80%|████████ | 20/25 [01:00<00:10, 2.02s/it] Training 1/1 epoch (loss 2.8481): 84%|████████▍ | 21/25 [01:00<00:08, 2.20s/it] Training 1/1 epoch (loss 2.6856): 84%|████████▍ | 21/25 [01:03<00:08, 2.20s/it] Training 1/1 epoch (loss 2.6856): 88%|████████▊ | 22/25 [01:03<00:06, 2.30s/it] Training 1/1 epoch (loss 2.7375): 88%|████████▊ | 22/25 [01:05<00:06, 2.30s/it] Training 1/1 epoch (loss 2.7375): 92%|█████████▏| 23/25 [01:05<00:04, 2.09s/it] Training 1/1 epoch (loss 2.7816): 92%|█████████▏| 23/25 [01:08<00:04, 2.09s/it] Training 1/1 epoch (loss 2.7816): 96%|█████████▌| 24/25 [01:08<00:02, 2.35s/it] Training 1/1 epoch (loss 2.7906): 96%|█████████▌| 24/25 [01:09<00:02, 2.35s/it] Training 1/1 epoch (loss 2.7906): 100%|██████████| 25/25 [01:09<00:00, 2.21s/it] Training 1/1 epoch (loss 2.7906): 100%|██████████| 25/25 [01:09<00:00, 2.80s/it]
chat template saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000-Q2-200/chat_template.jinja
tokenizer config file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000-Q2-200/tokenizer_config.json
Special tokens file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-4B/Qwen1.5-4B-s3-Q1-10000-Q2-200/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 0x1550e58da650>>
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('cannot schedule new futures after '
RuntimeError: cannot schedule new futures after interpreter shutdown