|
|
+ deepspeed --master_port 23603 --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/tinyllama-3T/tinyllama-3T-s3-Q1-5000 --max_length 512 --trust_remote_code True --epochs 1 --per_device_train_batch_size 1 --per_device_eval_batch_size 4 --gradient_accumulation_steps 8 --gradient_checkpointing --learning_rate 1e-5 --lr_warmup_ratio 0 --weight_decay 0.0 --lr_scheduler_type constant --weight_decay 0.0 --seed 42 --output_dir /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000-Q2-500 --log_type wandb --log_run_name imdb-tinyllama-3T-s3-Q1-5000-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 |
|
|
[rank1]:[W527 21:12:38.622731692 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. |
|
|
[rank3]:[W527 21:12:38.637424153 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]:[W527 21:12:38.639646167 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]:[W527 21:12:38.639688636 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. |
|
|
[rank7]:[W527 21:12:38.639701574 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]:[W527 21:12:38.643489361 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]:[W527 21:12:39.656231963 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]:[W527 21:12:39.712441946 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/tinyllama-3T/tinyllama-3T-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/config.json |
|
|
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/config.json |
|
|
Model config LlamaConfig { |
|
|
"architectures": [ |
|
|
"LlamaForCausalLM" |
|
|
], |
|
|
"attention_bias": false, |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"head_dim": 64, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 2048, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 5632, |
|
|
"max_position_embeddings": 2048, |
|
|
"mlp_bias": false, |
|
|
"model_type": "llama", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 22, |
|
|
"num_key_value_heads": 4, |
|
|
"pad_token_id": 32000, |
|
|
"pretraining_tp": 1, |
|
|
"rms_norm_eps": 1e-05, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 10000.0, |
|
|
"tie_word_embeddings": false, |
|
|
"torch_dtype": "float32", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"vocab_size": 32001 |
|
|
} |
|
|
|
|
|
Model config LlamaConfig { |
|
|
"architectures": [ |
|
|
"LlamaForCausalLM" |
|
|
], |
|
|
"attention_bias": false, |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"head_dim": 64, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 2048, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 5632, |
|
|
"max_position_embeddings": 2048, |
|
|
"mlp_bias": false, |
|
|
"model_type": "llama", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 22, |
|
|
"num_key_value_heads": 4, |
|
|
"pad_token_id": 32000, |
|
|
"pretraining_tp": 1, |
|
|
"rms_norm_eps": 1e-05, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 10000.0, |
|
|
"tie_word_embeddings": false, |
|
|
"torch_dtype": "float32", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"vocab_size": 32001 |
|
|
} |
|
|
|
|
|
Model config LlamaConfig { |
|
|
"architectures": [ |
|
|
"LlamaForCausalLM" |
|
|
], |
|
|
"attention_bias": false, |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"head_dim": 64, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 2048, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 5632, |
|
|
"max_position_embeddings": 2048, |
|
|
"mlp_bias": false, |
|
|
"model_type": "llama", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 22, |
|
|
"num_key_value_heads": 4, |
|
|
"pad_token_id": 32000, |
|
|
"pretraining_tp": 1, |
|
|
"rms_norm_eps": 1e-05, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 10000.0, |
|
|
"tie_word_embeddings": false, |
|
|
"torch_dtype": "float32", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"vocab_size": 32001 |
|
|
} |
|
|
|
|
|
Model config LlamaConfig { |
|
|
"architectures": [ |
|
|
"LlamaForCausalLM" |
|
|
], |
|
|
"attention_bias": false, |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"head_dim": 64, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 2048, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 5632, |
|
|
"max_position_embeddings": 2048, |
|
|
"mlp_bias": false, |
|
|
"model_type": "llama", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 22, |
|
|
"num_key_value_heads": 4, |
|
|
"pad_token_id": 32000, |
|
|
"pretraining_tp": 1, |
|
|
"rms_norm_eps": 1e-05, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 10000.0, |
|
|
"tie_word_embeddings": false, |
|
|
"torch_dtype": "float32", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"vocab_size": 32001 |
|
|
} |
|
|
|
|
|
Model config LlamaConfig { |
|
|
"architectures": [ |
|
|
"LlamaForCausalLM" |
|
|
], |
|
|
"attention_bias": false, |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"head_dim": 64, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 2048, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 5632, |
|
|
"max_position_embeddings": 2048, |
|
|
"mlp_bias": false, |
|
|
"model_type": "llama", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 22, |
|
|
"num_key_value_heads": 4, |
|
|
"pad_token_id": 32000, |
|
|
"pretraining_tp": 1, |
|
|
"rms_norm_eps": 1e-05, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 10000.0, |
|
|
"tie_word_embeddings": false, |
|
|
"torch_dtype": "float32", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"vocab_size": 32001 |
|
|
} |
|
|
|
|
|
Model config LlamaConfig { |
|
|
"architectures": [ |
|
|
"LlamaForCausalLM" |
|
|
], |
|
|
"attention_bias": false, |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"head_dim": 64, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 2048, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 5632, |
|
|
"max_position_embeddings": 2048, |
|
|
"mlp_bias": false, |
|
|
"model_type": "llama", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 22, |
|
|
"num_key_value_heads": 4, |
|
|
"pad_token_id": 32000, |
|
|
"pretraining_tp": 1, |
|
|
"rms_norm_eps": 1e-05, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 10000.0, |
|
|
"tie_word_embeddings": false, |
|
|
"torch_dtype": "float32", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"vocab_size": 32001 |
|
|
} |
|
|
|
|
|
Model config LlamaConfig { |
|
|
"architectures": [ |
|
|
"LlamaForCausalLM" |
|
|
], |
|
|
"attention_bias": false, |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"head_dim": 64, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 2048, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 5632, |
|
|
"max_position_embeddings": 2048, |
|
|
"mlp_bias": false, |
|
|
"model_type": "llama", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 22, |
|
|
"num_key_value_heads": 4, |
|
|
"pad_token_id": 32000, |
|
|
"pretraining_tp": 1, |
|
|
"rms_norm_eps": 1e-05, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 10000.0, |
|
|
"tie_word_embeddings": false, |
|
|
"torch_dtype": "float32", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"vocab_size": 32001 |
|
|
} |
|
|
|
|
|
Model config LlamaConfig { |
|
|
"architectures": [ |
|
|
"LlamaForCausalLM" |
|
|
], |
|
|
"attention_bias": false, |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"head_dim": 64, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 2048, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 5632, |
|
|
"max_position_embeddings": 2048, |
|
|
"mlp_bias": false, |
|
|
"model_type": "llama", |
|
|
"num_attention_heads": 32, |
|
|
"num_hidden_layers": 22, |
|
|
"num_key_value_heads": 4, |
|
|
"pad_token_id": 32000, |
|
|
"pretraining_tp": 1, |
|
|
"rms_norm_eps": 1e-05, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 10000.0, |
|
|
"tie_word_embeddings": false, |
|
|
"torch_dtype": "float32", |
|
|
"transformers_version": "4.52.1", |
|
|
"use_cache": true, |
|
|
"vocab_size": 32001 |
|
|
} |
|
|
|
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/pytorch_model.bin |
|
|
Will use torch_dtype=torch.float32 as defined in model |
|
|
Instantiating LlamaForCausalLM model under default dtype torch.float32. |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/pytorch_model.bin |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
Will use torch_dtype=torch.float32 as defined in model |
|
|
Instantiating LlamaForCausalLM model under default dtype torch.float32. |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/pytorch_model.bin |
|
|
Will use torch_dtype=torch.float32 as defined in model |
|
|
Instantiating LlamaForCausalLM model under default dtype torch.float32. |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/pytorch_model.bin |
|
|
Will use torch_dtype=torch.float32 as defined in model |
|
|
Instantiating LlamaForCausalLM model under default dtype torch.float32. |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/pytorch_model.bin |
|
|
Will use torch_dtype=torch.float32 as defined in model |
|
|
Instantiating LlamaForCausalLM model under default dtype torch.float32. |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/pytorch_model.bin |
|
|
Will use torch_dtype=torch.float32 as defined in model |
|
|
Instantiating LlamaForCausalLM model under default dtype torch.float32. |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/pytorch_model.bin |
|
|
Will use torch_dtype=torch.float32 as defined in model |
|
|
Instantiating LlamaForCausalLM model under default dtype torch.float32. |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
Generate config GenerationConfig { |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"pad_token_id": 32000 |
|
|
} |
|
|
|
|
|
Generate config GenerationConfig { |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"pad_token_id": 32000 |
|
|
} |
|
|
|
|
|
Generate config GenerationConfig { |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"pad_token_id": 32000 |
|
|
} |
|
|
|
|
|
Generate config GenerationConfig { |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"pad_token_id": 32000 |
|
|
} |
|
|
|
|
|
Generate config GenerationConfig { |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"pad_token_id": 32000 |
|
|
} |
|
|
|
|
|
Generate config GenerationConfig { |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"pad_token_id": 32000 |
|
|
} |
|
|
|
|
|
Generate config GenerationConfig { |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"pad_token_id": 32000 |
|
|
} |
|
|
|
|
|
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000/pytorch_model.bin |
|
|
Will use torch_dtype=torch.float32 as defined in model |
|
|
Instantiating LlamaForCausalLM model under default dtype torch.float32. |
|
|
Detected DeepSpeed ZeRO-3: activating zero.init() for this model |
|
|
Generate config GenerationConfig { |
|
|
"bos_token_id": 1, |
|
|
"eos_token_id": 2, |
|
|
"pad_token_id": 32000 |
|
|
} |
|
|
|
|
|
All model checkpoint weights were used when initializing LlamaForCausalLM. |
|
|
|
|
|
All model checkpoint weights were used when initializing LlamaForCausalLM. |
|
|
|
|
|
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. |
|
|
All model checkpoint weights were used when initializing LlamaForCausalLM. |
|
|
|
|
|
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. |
|
|
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. |
|
|
All model checkpoint weights were used when initializing LlamaForCausalLM. |
|
|
|
|
|
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. |
|
|
All model checkpoint weights were used when initializing LlamaForCausalLM. |
|
|
|
|
|
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. |
|
|
All model checkpoint weights were used when initializing LlamaForCausalLM. |
|
|
|
|
|
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. |
|
|
All model checkpoint weights were used when initializing LlamaForCausalLM. |
|
|
|
|
|
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
loading file tokenizer.model |
|
|
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 tokenizer.model |
|
|
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 tokenizer.model |
|
|
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 tokenizer.model |
|
|
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 tokenizer.model |
|
|
loading file tokenizer.model |
|
|
loading file tokenizer.json |
|
|
loading file tokenizer.json |
|
|
loading file added_tokens.json |
|
|
loading file added_tokens.json |
|
|
loading file special_tokens_map.json |
|
|
loading file tokenizer_config.json |
|
|
loading file special_tokens_map.json |
|
|
loading file chat_template.jinja |
|
|
loading file tokenizer_config.json |
|
|
loading file chat_template.jinja |
|
|
loading file tokenizer.model |
|
|
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 LlamaForCausalLM. |
|
|
|
|
|
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000. |
|
|
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. |
|
|
Generation config file not found, using a generation config created from the model config. |
|
|
loading file tokenizer.model |
|
|
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 |
|
|
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/tinyllama-3T/tinyllama-3T-s3-Q1-5000-Q2-500/wandb/run-20250527_211254-n7vbaf0c |
|
|
wandb: Run `wandb offline` to turn off syncing. |
|
|
wandb: Syncing run imdb-tinyllama-3T-s3-Q1-5000-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/n7vbaf0c |
|
|
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 2.7590): 0%| | 0/63 [00:11<?, ?it/s]
Training 1/1 epoch (loss 2.7590): 2%|▏ | 1/63 [00:11<11:41, 11.31s/it]
Training 1/1 epoch (loss 2.7473): 2%|▏ | 1/63 [00:13<11:41, 11.31s/it]
Training 1/1 epoch (loss 2.7473): 3%|▎ | 2/63 [00:13<06:03, 5.97s/it]
Training 1/1 epoch (loss 2.8029): 3%|▎ | 2/63 [00:14<06:03, 5.97s/it]
Training 1/1 epoch (loss 2.8029): 5%|▍ | 3/63 [00:14<03:48, 3.82s/it]
Training 1/1 epoch (loss 2.6302): 5%|▍ | 3/63 [00:15<03:48, 3.82s/it]
Training 1/1 epoch (loss 2.6302): 6%|▋ | 4/63 [00:15<02:39, 2.70s/it]
Training 1/1 epoch (loss 2.9055): 6%|▋ | 4/63 [00:17<02:39, 2.70s/it]
Training 1/1 epoch (loss 2.9055): 8%|▊ | 5/63 [00:17<02:05, 2.17s/it]
Training 1/1 epoch (loss 2.6169): 8%|▊ | 5/63 [00:18<02:05, 2.17s/it]
Training 1/1 epoch (loss 2.6169): 10%|▉ | 6/63 [00:18<01:50, 1.95s/it]
Training 1/1 epoch (loss 2.6960): 10%|▉ | 6/63 [00:19<01:50, 1.95s/it]
Training 1/1 epoch (loss 2.6960): 11%|█ | 7/63 [00:19<01:28, 1.58s/it]
Training 1/1 epoch (loss 2.5920): 11%|█ | 7/63 [00:21<01:28, 1.58s/it]
Training 1/1 epoch (loss 2.5920): 13%|█▎ | 8/63 [00:21<01:37, 1.78s/it]
Training 1/1 epoch (loss 2.9617): 13%|█▎ | 8/63 [00:22<01:37, 1.78s/it]
Training 1/1 epoch (loss 2.9617): 14%|█▍ | 9/63 [00:22<01:17, 1.43s/it]
Training 1/1 epoch (loss 2.8642): 14%|█▍ | 9/63 [00:24<01:17, 1.43s/it]
Training 1/1 epoch (loss 2.8642): 16%|█▌ | 10/63 [00:24<01:25, 1.61s/it]
Training 1/1 epoch (loss 2.6614): 16%|█▌ | 10/63 [00:25<01:25, 1.61s/it]
Training 1/1 epoch (loss 2.6614): 17%|█▋ | 11/63 [00:25<01:20, 1.56s/it]
Training 1/1 epoch (loss 2.5807): 17%|█▋ | 11/63 [00:26<01:20, 1.56s/it]
Training 1/1 epoch (loss 2.5807): 19%|█▉ | 12/63 [00:26<01:07, 1.33s/it]
Training 1/1 epoch (loss 2.7745): 19%|█▉ | 12/63 [00:28<01:07, 1.33s/it]
Training 1/1 epoch (loss 2.7745): 21%|██ | 13/63 [00:28<01:22, 1.66s/it]
Training 1/1 epoch (loss 2.6364): 21%|██ | 13/63 [00:30<01:22, 1.66s/it]
Training 1/1 epoch (loss 2.6364): 22%|██▏ | 14/63 [00:30<01:17, 1.57s/it]
Training 1/1 epoch (loss 2.6966): 22%|██▏ | 14/63 [00:31<01:17, 1.57s/it]
Training 1/1 epoch (loss 2.6966): 24%|██▍ | 15/63 [00:31<01:06, 1.39s/it]
Training 1/1 epoch (loss 2.7031): 24%|██▍ | 15/63 [00:33<01:06, 1.39s/it]
Training 1/1 epoch (loss 2.7031): 25%|██▌ | 16/63 [00:33<01:11, 1.53s/it]
Training 1/1 epoch (loss 2.5842): 25%|██▌ | 16/63 [00:34<01:11, 1.53s/it]
Training 1/1 epoch (loss 2.5842): 27%|██▋ | 17/63 [00:34<01:12, 1.57s/it]
Training 1/1 epoch (loss 2.3200): 27%|██▋ | 17/63 [00:36<01:12, 1.57s/it]
Training 1/1 epoch (loss 2.3200): 29%|██▊ | 18/63 [00:36<01:06, 1.49s/it]
Training 1/1 epoch (loss 2.6148): 29%|██▊ | 18/63 [00:37<01:06, 1.49s/it]
Training 1/1 epoch (loss 2.6148): 30%|███ | 19/63 [00:37<01:08, 1.56s/it]
Training 1/1 epoch (loss 2.5772): 30%|███ | 19/63 [00:39<01:08, 1.56s/it]
Training 1/1 epoch (loss 2.5772): 32%|███▏ | 20/63 [00:39<01:03, 1.48s/it]
Training 1/1 epoch (loss 2.6526): 32%|███▏ | 20/63 [00:40<01:03, 1.48s/it]
Training 1/1 epoch (loss 2.6526): 33%|███▎ | 21/63 [00:40<00:58, 1.39s/it]
Training 1/1 epoch (loss 2.6309): 33%|███▎ | 21/63 [00:41<00:58, 1.39s/it]
Training 1/1 epoch (loss 2.6309): 35%|███▍ | 22/63 [00:41<00:50, 1.24s/it]
Training 1/1 epoch (loss 2.7496): 35%|███▍ | 22/63 [00:42<00:50, 1.24s/it]
Training 1/1 epoch (loss 2.7496): 37%|███▋ | 23/63 [00:42<00:54, 1.37s/it]
Training 1/1 epoch (loss 2.5726): 37%|███▋ | 23/63 [00:43<00:54, 1.37s/it]
Training 1/1 epoch (loss 2.5726): 38%|███▊ | 24/63 [00:43<00:51, 1.31s/it]
Training 1/1 epoch (loss 2.6098): 38%|███▊ | 24/63 [00:45<00:51, 1.31s/it]
Training 1/1 epoch (loss 2.6098): 40%|███▉ | 25/63 [00:45<00:48, 1.28s/it]
Training 1/1 epoch (loss 2.6488): 40%|███▉ | 25/63 [00:46<00:48, 1.28s/it]
Training 1/1 epoch (loss 2.6488): 41%|████▏ | 26/63 [00:46<00:48, 1.31s/it]
Training 1/1 epoch (loss 2.7007): 41%|████▏ | 26/63 [00:47<00:48, 1.31s/it]
Training 1/1 epoch (loss 2.7007): 43%|████▎ | 27/63 [00:47<00:39, 1.09s/it]
Training 1/1 epoch (loss 2.5200): 43%|████▎ | 27/63 [00:48<00:39, 1.09s/it]
Training 1/1 epoch (loss 2.5200): 44%|████▍ | 28/63 [00:48<00:43, 1.24s/it]
Training 1/1 epoch (loss 2.7037): 44%|████▍ | 28/63 [00:50<00:43, 1.24s/it]
Training 1/1 epoch (loss 2.7037): 46%|████▌ | 29/63 [00:50<00:50, 1.50s/it]
Training 1/1 epoch (loss 2.6208): 46%|████▌ | 29/63 [00:51<00:50, 1.50s/it]
Training 1/1 epoch (loss 2.6208): 48%|████▊ | 30/63 [00:51<00:44, 1.34s/it]
Training 1/1 epoch (loss 2.4008): 48%|████▊ | 30/63 [00:53<00:44, 1.34s/it]
Training 1/1 epoch (loss 2.4008): 49%|████▉ | 31/63 [00:53<00:47, 1.49s/it]
Training 1/1 epoch (loss 2.7120): 49%|████▉ | 31/63 [00:55<00:47, 1.49s/it]
Training 1/1 epoch (loss 2.7120): 51%|█████ | 32/63 [00:55<00:46, 1.50s/it]
Training 1/1 epoch (loss 2.5188): 51%|█████ | 32/63 [00:55<00:46, 1.50s/it]
Training 1/1 epoch (loss 2.5188): 52%|█████▏ | 33/63 [00:55<00:38, 1.30s/it]
Training 1/1 epoch (loss 2.5043): 52%|█████▏ | 33/63 [00:57<00:38, 1.30s/it]
Training 1/1 epoch (loss 2.5043): 54%|█████▍ | 34/63 [00:57<00:38, 1.31s/it]
Training 1/1 epoch (loss 2.6371): 54%|█████▍ | 34/63 [00:58<00:38, 1.31s/it]
Training 1/1 epoch (loss 2.6371): 56%|█████▌ | 35/63 [00:58<00:34, 1.22s/it]
Training 1/1 epoch (loss 2.3829): 56%|█████▌ | 35/63 [00:59<00:34, 1.22s/it]
Training 1/1 epoch (loss 2.3829): 57%|█████▋ | 36/63 [00:59<00:36, 1.33s/it]
Training 1/1 epoch (loss 2.7451): 57%|█████▋ | 36/63 [01:02<00:36, 1.33s/it]
Training 1/1 epoch (loss 2.7451): 59%|█████▊ | 37/63 [01:02<00:43, 1.67s/it]
Training 1/1 epoch (loss 2.8556): 59%|█████▊ | 37/63 [01:03<00:43, 1.67s/it]
Training 1/1 epoch (loss 2.8556): 60%|██████ | 38/63 [01:03<00:34, 1.39s/it]
Training 1/1 epoch (loss 2.3446): 60%|██████ | 38/63 [01:04<00:34, 1.39s/it]
Training 1/1 epoch (loss 2.3446): 62%|██████▏ | 39/63 [01:04<00:35, 1.48s/it]
Training 1/1 epoch (loss 2.5324): 62%|██████▏ | 39/63 [01:06<00:35, 1.48s/it]
Training 1/1 epoch (loss 2.5324): 63%|██████▎ | 40/63 [01:06<00:33, 1.46s/it]
Training 1/1 epoch (loss 2.6066): 63%|██████▎ | 40/63 [01:06<00:33, 1.46s/it]
Training 1/1 epoch (loss 2.6066): 65%|██████▌ | 41/63 [01:06<00:25, 1.17s/it]
Training 1/1 epoch (loss 2.6521): 65%|██████▌ | 41/63 [01:09<00:25, 1.17s/it]
Training 1/1 epoch (loss 2.6521): 67%|██████▋ | 42/63 [01:09<00:32, 1.55s/it]
Training 1/1 epoch (loss 2.8716): 67%|██████▋ | 42/63 [01:11<00:32, 1.55s/it]
Training 1/1 epoch (loss 2.8716): 68%|██████▊ | 43/63 [01:11<00:34, 1.72s/it]
Training 1/1 epoch (loss 2.6716): 68%|██████▊ | 43/63 [01:11<00:34, 1.72s/it]
Training 1/1 epoch (loss 2.6716): 70%|██████▉ | 44/63 [01:11<00:25, 1.34s/it]
Training 1/1 epoch (loss 2.5415): 70%|██████▉ | 44/63 [01:13<00:25, 1.34s/it]
Training 1/1 epoch (loss 2.5415): 71%|███████▏ | 45/63 [01:13<00:23, 1.33s/it]
Training 1/1 epoch (loss 2.4407): 71%|███████▏ | 45/63 [01:14<00:23, 1.33s/it]
Training 1/1 epoch (loss 2.4407): 73%|███████▎ | 46/63 [01:14<00:24, 1.42s/it]
Training 1/1 epoch (loss 2.4966): 73%|███████▎ | 46/63 [01:15<00:24, 1.42s/it]
Training 1/1 epoch (loss 2.4966): 75%|███████▍ | 47/63 [01:15<00:18, 1.13s/it]
Training 1/1 epoch (loss 2.4271): 75%|███████▍ | 47/63 [01:17<00:18, 1.13s/it]
Training 1/1 epoch (loss 2.4271): 76%|███████▌ | 48/63 [01:17<00:21, 1.44s/it]
Training 1/1 epoch (loss 2.5056): 76%|███████▌ | 48/63 [01:18<00:21, 1.44s/it]
Training 1/1 epoch (loss 2.5056): 78%|███████▊ | 49/63 [01:18<00:19, 1.37s/it]
Training 1/1 epoch (loss 2.7030): 78%|███████▊ | 49/63 [01:19<00:19, 1.37s/it]
Training 1/1 epoch (loss 2.7030): 79%|███████▉ | 50/63 [01:19<00:14, 1.12s/it]
Training 1/1 epoch (loss 2.6004): 79%|███████▉ | 50/63 [01:20<00:14, 1.12s/it]
Training 1/1 epoch (loss 2.6004): 81%|████████ | 51/63 [01:20<00:15, 1.32s/it]
Training 1/1 epoch (loss 2.5895): 81%|████████ | 51/63 [01:22<00:15, 1.32s/it]
Training 1/1 epoch (loss 2.5895): 83%|████████▎ | 52/63 [01:22<00:15, 1.39s/it]
Training 1/1 epoch (loss 2.6730): 83%|████████▎ | 52/63 [01:22<00:15, 1.39s/it]
Training 1/1 epoch (loss 2.6730): 84%|████████▍ | 53/63 [01:22<00:11, 1.13s/it]
Training 1/1 epoch (loss 2.5270): 84%|████████▍ | 53/63 [01:25<00:11, 1.13s/it]
Training 1/1 epoch (loss 2.5270): 86%|████████▌ | 54/63 [01:25<00:13, 1.50s/it]
Training 1/1 epoch (loss 2.7230): 86%|████████▌ | 54/63 [01:26<00:13, 1.50s/it]
Training 1/1 epoch (loss 2.7230): 87%|████████▋ | 55/63 [01:26<00:12, 1.54s/it]
Training 1/1 epoch (loss 2.6266): 87%|████████▋ | 55/63 [01:27<00:12, 1.54s/it]
Training 1/1 epoch (loss 2.6266): 89%|████████▉ | 56/63 [01:27<00:09, 1.36s/it]
Training 1/1 epoch (loss 2.6192): 89%|████████▉ | 56/63 [01:29<00:09, 1.36s/it]
Training 1/1 epoch (loss 2.6192): 90%|█████████ | 57/63 [01:29<00:08, 1.46s/it]
Training 1/1 epoch (loss 2.4952): 90%|█████████ | 57/63 [01:30<00:08, 1.46s/it]
Training 1/1 epoch (loss 2.4952): 92%|█████████▏| 58/63 [01:30<00:06, 1.35s/it]
Training 1/1 epoch (loss 2.5224): 92%|█████████▏| 58/63 [01:32<00:06, 1.35s/it]
Training 1/1 epoch (loss 2.5224): 94%|█████████▎| 59/63 [01:32<00:05, 1.41s/it]
Training 1/1 epoch (loss 2.6627): 94%|█████████▎| 59/63 [01:33<00:05, 1.41s/it]
Training 1/1 epoch (loss 2.6627): 95%|█████████▌| 60/63 [01:33<00:04, 1.36s/it]
Training 1/1 epoch (loss 2.5481): 95%|█████████▌| 60/63 [01:34<00:04, 1.36s/it]
Training 1/1 epoch (loss 2.5481): 97%|█████████▋| 61/63 [01:34<00:02, 1.26s/it]
Training 1/1 epoch (loss 2.7465): 97%|█████████▋| 61/63 [01:36<00:02, 1.26s/it]
Training 1/1 epoch (loss 2.7465): 98%|█████████▊| 62/63 [01:36<00:01, 1.61s/it]
Training 1/1 epoch (loss 2.5375): 98%|█████████▊| 62/63 [01:38<00:01, 1.61s/it]
Training 1/1 epoch (loss 2.5375): 100%|██████████| 63/63 [01:38<00:00, 1.75s/it]
Training 1/1 epoch (loss 2.5375): 100%|██████████| 63/63 [01:38<00:00, 1.57s/it] |
|
|
tokenizer config file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000-Q2-500/tokenizer_config.json |
|
|
Special tokens file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-5000-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 0x1550cc97c5d0>> |
|
|
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 |
|
|
|
