def __init__(self,
model_params,
lr=1e-2,
eps=1e-10,
weight_decay=0,
amsgrad=False,
fp32_optimizer_states=True):
default_args = dict(lr=lr,
eps=eps,
weight_decay=weight_decay,
amsgrad=amsgrad)
super(DeepSpeedCPUAdagrad, self).__init__(model_params, default_args)
self.opt_id = DeepSpeedCPUAdagrad.optimizer_id
DeepSpeedCPUAdagrad.optimizer_id = DeepSpeedCPUAdagrad.optimizer_id + 1
self.fp32_optimizer_states = fp32_optimizer_states
self.ds_opt_adagrad = CPUAdagradBuilder().load()
self.ds_opt_adagrad.create_adagrad(self.opt_id, lr, eps, weight_decay,
should_log_le("info"))
def __init__(self,
model_params,
lr=1e-3,
bias_correction=True,
betas=(0.9,
0.999),
eps=1e-8,
weight_decay=0,
amsgrad=False,
adamw_mode=True,
fp32_optimizer_states=True):
"""Fast vectorized implementation of two variations of Adam optimizer on CPU:
* Adam: A Method for Stochastic Optimization: (https://arxiv.org/abs/1412.6980);
* AdamW: Fixing Weight Decay Regularization in Adam (https://arxiv.org/abs/1711.05101)
DeepSpeed CPU Adam(W) provides between 5x to 7x speedup over torch.optim.adam(W).
In order to apply this optimizer, the model requires to have its master parameter (in FP32)
reside on the CPU memory.
To train on a heterogeneous system, such as coordinating CPU and GPU, DeepSpeed offers
the ZeRO-Offload technology which efficiently offloads the optimizer states into CPU memory,
with minimal impact on training throughput. DeepSpeedCPUAdam plays an important role to minimize
the overhead of the optimizer's latency on CPU. Please refer to ZeRO-Offload tutorial
(https://www.deepspeed.ai/tutorials/zero-offload/) for more information on how to enable this technology.
For calling step function, there are two options available: (1) update optimizer's states and (2) update
optimizer's states and copy the parameters back to GPU at the same time. We have seen that the second
option can bring 30% higher throughput than the doing the copy separately using option one.
.. note::
We recommend using our `config
<https://www.deepspeed.ai/docs/config-json/#optimizer-parameters>`_
to allow :meth:`deepspeed.initialize` to build this optimizer
for you.
Arguments:
model_params (iterable): iterable of parameters to optimize or dicts defining
parameter groups.
lr (float, optional): learning rate. (default: 1e-3)
betas (Tuple[float, float], optional): coefficients used for computing
running averages of gradient and its square. (default: (0.9, 0.999))
eps (float, optional): term added to the denominator to improve
numerical stability. (default: 1e-8)
weight_decay (float, optional): weight decay (L2 penalty) (default: 0)
amsgrad (boolean, optional): whether to use the AMSGrad variant of this
algorithm from the paper `On the Convergence of Adam and Beyond`_
(default: False) NOT SUPPORTED in DeepSpeed CPUAdam!
adamw_mode: select between Adam and AdamW implementations (default: AdamW)
full_precision_optimizer_states: creates momementum and variance in full precision regardless of
the precision of the parameters (default: True)
"""
default_args = dict(lr=lr,
betas=betas,
eps=eps,
weight_decay=weight_decay,
bias_correction=bias_correction,
amsgrad=amsgrad)
super(DeepSpeedCPUAdam, self).__init__(model_params, default_args)
self.opt_id = DeepSpeedCPUAdam.optimizer_id
DeepSpeedCPUAdam.optimizer_id = DeepSpeedCPUAdam.optimizer_id + 1
self.adam_w_mode = adamw_mode
self.fp32_optimizer_states = fp32_optimizer_states
self.ds_opt_adam = CPUAdamBuilder().load()
self.ds_opt_adam.create_adam(self.opt_id,
lr,
betas[0],
betas[1],
eps,
weight_decay,
adamw_mode,
should_log_le("info"))