Cannot allocate memory

[chenhaobupt]

initializing deepspeed distributed: GLOBAL_RANK: 0, MEMBER: 1/1
Enabling DeepSpeed BF16.
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1,2,3]
Traceback (most recent call last):
File "./train.py", line 388, in
trainer.fit(model, data_loader)
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 608, in fit
call._call_and_handle_interrupt(
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/trainer/call.py", line 36, in _call_and_handle_interrupt
return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs)
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/strategies/launchers/subprocess_script.py", line 88, in launch
return function(*args, **kwargs)
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 650, in _fit_impl
self._run(model, ckpt_path=self.ckpt_path)
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1093, in _run
self.strategy.setup(self)
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/strategies/deepspeed.py", line 345, in setup
self.init_deepspeed()
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/strategies/deepspeed.py", line 456, in init_deepspeed
self._initialize_deepspeed_train(model)
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/strategies/deepspeed.py", line 489, in _initialize_deepspeed_train
optimizer, lr_scheduler, _ = self._init_optimizers()
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/strategies/deepspeed.py", line 462, in _init_optimizers
optimizers, lr_schedulers, optimizer_frequencies = _init_optimizers_and_lr_schedulers(self.lightning_module)
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/core/optimizer.py", line 180, in _init_optimizers_and_lr_schedulers
optim_conf = model.trainer._call_lightning_module_hook("configure_optimizers", pl_module=model)
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1356, in _call_lightning_module_hook
output = fn(*args, **kwargs)
File "/home/chenhao/project/RWKV-LM-LoRA/RWKV-v4neo/src/model.py", line 518, in configure_optimizers
return FusedAdam(optim_groups, lr=self.args.lr_init, betas=self.args.betas, eps=self.args.adam_eps, bias_correction=True, adam_w_mode=False, weight_decay=0, amsgrad=False)
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/deepspeed/ops/adam/fused_adam.py", line 72, in init
fused_adam_cuda = FusedAdamBuilder().load()
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/deepspeed/ops/op_builder/builder.py", line 471, in load
return self.jit_load(verbose)
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/deepspeed/ops/op_builder/builder.py", line 486, in jit_load
assert_no_cuda_mismatch()
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/deepspeed/ops/op_builder/builder.py", line 88, in assert_no_cuda_mismatch
cuda_major, cuda_minor = installed_cuda_version()
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/site-packages/deepspeed/ops/op_builder/builder.py", line 42, in installed_cuda_version
output = subprocess.check_output([cuda_home + "/bin/nvcc",
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/subprocess.py", line 411, in check_output
return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/subprocess.py", line 489, in run
with Popen(*popenargs, **kwargs) as process:
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/subprocess.py", line 854, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "/home/chenhao/anaconda3/envs/RWKV/lib/python3.8/subprocess.py", line 1637, in _execute_child
self.pid = _posixsubprocess.fork_exec(
OSError: [Errno 12] Cannot allocate memory

请问这个是什么原因？如何解决？

[chenhaobupt]

python3 train.py
--load_model /home/chenhao/project/RWKVMODEL/RWKV-4-Pile-7B-20221115-8047.pth
--proj_dir ./tuned
--data_file /home/chenhao/project/json2binidx_tool/data/sample_text_document
--data_type binidx
--vocab_size 50277 --ctx_len 1024 --epoch_steps 1000 --epoch_count 1000 --epoch_begin 0 --epoch_save 5 --micro_bsz 2 --accumulate_grad_batches 4
--n_layer 32 --n_embd 4096 --pre_ffn 0 --head_qk 0 --lr_init 1e-4 --lr_final 1e-4 --warmup_steps 0 --beta1 0.9 --beta2 0.999 --adam_eps 1e-8 --accelerator gpu --devices 1 --precision bf16 --strategy deepspeed_stage_2 --grad_cp 0 --lora --lora_r 8 --lora_alpha 16 --lora_dropout 0.01 --lora_parts=att,ffn,time,ln

[chenhaobupt]

以上是我的命令