bitsandbytes/pr_2030/en/reference/optim/sgd.md

# SGD

Stochastic gradient descent (SGD) is a basic gradient descent optimizer to minimize loss given a set of model parameters and updates the parameters in the opposite direction of the gradient. The update is performed on a randomly sampled mini-batch of data from the dataset.

bitsandbytes also supports momentum and Nesterov momentum to accelerate SGD by adding a weighted average of past gradients to the current gradient.

## SGD[[api-class]][[bitsandbytes.optim.SGD]]

#### bitsandbytes.optim.SGD[[bitsandbytes.optim.SGD]]

```python
bitsandbytes.optim.SGD(params, lr, momentum = 0, dampening = 0, weight_decay = 0, nesterov = False, optim_bits = 32, args = None, min_8bit_size = 4096)
```

[Source](https://github.com/bitsandbytes-foundation/bitsandbytes/blob/vr_2030/bitsandbytes/optim/sgd.py#L8)

#### __init__[[bitsandbytes.optim.SGD.__init__]]

```python
__init__(params, lr, momentum = 0, dampening = 0, weight_decay = 0, nesterov = False, optim_bits = 32, args = None, min_8bit_size = 4096)
```

[Source](https://github.com/bitsandbytes-foundation/bitsandbytes/blob/vr_2030/bitsandbytes/optim/sgd.py#L9)

**Parameters:**

params (`torch.tensor`) : The input parameters to optimize.

lr (`float`) : The learning rate.

momentum (`float`, defaults to 0) : The momentum value speeds up the optimizer by taking bigger steps.

dampening (`float`, defaults to 0) : The dampening value reduces the momentum of the optimizer.

weight_decay (`float`, defaults to 0.0) : The weight decay value for the optimizer.

nesterov (`bool`, defaults to `False`) : Whether to use Nesterov momentum.

optim_bits (`int`, defaults to 32) : The number of bits of the optimizer state.

args (`object`, defaults to `None`) : An object with additional arguments.

min_8bit_size (`int`, defaults to 4096) : The minimum number of elements of the parameter tensors for 8-bit optimization.

Base SGD optimizer.

## SGD8bit[[bitsandbytes.optim.SGD8bit]]

#### bitsandbytes.optim.SGD8bit[[bitsandbytes.optim.SGD8bit]]

```python
bitsandbytes.optim.SGD8bit(params, lr, momentum = 0, dampening = 0, weight_decay = 0, nesterov = False, args = None, min_8bit_size = 4096)
```

[Source](https://github.com/bitsandbytes-foundation/bitsandbytes/blob/vr_2030/bitsandbytes/optim/sgd.py#L59)

#### __init__[[bitsandbytes.optim.SGD8bit.__init__]]

```python
__init__(params, lr, momentum = 0, dampening = 0, weight_decay = 0, nesterov = False, args = None, min_8bit_size = 4096)
```

[Source](https://github.com/bitsandbytes-foundation/bitsandbytes/blob/vr_2030/bitsandbytes/optim/sgd.py#L60)

**Parameters:**

params (`torch.tensor`) : The input parameters to optimize.

lr (`float`) : The learning rate.

momentum (`float`, defaults to 0) : The momentum value speeds up the optimizer by taking bigger steps.

dampening (`float`, defaults to 0) : The dampening value reduces the momentum of the optimizer.

weight_decay (`float`, defaults to 0.0) : The weight decay value for the optimizer.

nesterov (`bool`, defaults to `False`) : Whether to use Nesterov momentum.

args (`object`, defaults to `None`) : An object with additional arguments.

min_8bit_size (`int`, defaults to 4096) : The minimum number of elements of the parameter tensors for 8-bit optimization.

8-bit SGD optimizer.

## SGD32bit[[bitsandbytes.optim.SGD32bit]]

#### bitsandbytes.optim.SGD32bit[[bitsandbytes.optim.SGD32bit]]

```python
bitsandbytes.optim.SGD32bit(params, lr, momentum = 0, dampening = 0, weight_decay = 0, nesterov = False, args = None, min_8bit_size = 4096)
```

[Source](https://github.com/bitsandbytes-foundation/bitsandbytes/blob/vr_2030/bitsandbytes/optim/sgd.py#L107)

#### __init__[[bitsandbytes.optim.SGD32bit.__init__]]

```python
__init__(params, lr, momentum = 0, dampening = 0, weight_decay = 0, nesterov = False, args = None, min_8bit_size = 4096)
```

[Source](https://github.com/bitsandbytes-foundation/bitsandbytes/blob/vr_2030/bitsandbytes/optim/sgd.py#L108)

**Parameters:**

params (`torch.tensor`) : The input parameters to optimize.

lr (`float`) : The learning rate.

momentum (`float`, defaults to 0) : The momentum value speeds up the optimizer by taking bigger steps.

dampening (`float`, defaults to 0) : The dampening value reduces the momentum of the optimizer.

weight_decay (`float`, defaults to 0.0) : The weight decay value for the optimizer.

nesterov (`bool`, defaults to `False`) : Whether to use Nesterov momentum.

args (`object`, defaults to `None`) : An object with additional arguments.

min_8bit_size (`int`, defaults to 4096) : The minimum number of elements of the parameter tensors for 8-bit optimization.

32-bit SGD optimizer.