Implicit Language Q-Learning (ILQL)¶
ILQL is an extension of Implicit Q-learning that can be used to finetune large language models (LLMs) with reinforcement leaning from human feedback (RLHF).
ILQL paper: https://arxiv.org/pdf/2206.11871.pdf
Parameters¶
- class agilerl.algorithms.ilql.ILQL(dataset, net_config={'activation': 'GELU', 'arch': 'gpt', 'bias': True, 'block_size': 1024, 'dim_feedfwd': 3072, 'dropout': 0.1, 'layer_norm_eps': 1e-05, 'max_layers': 16, 'min_layers': 8, 'n_embd': 768, 'n_head': 12, 'n_layer': 12, 'vocab_size': 50257}, index=0, batch_size=64, lr=1e-05, alpha=0.005, beta=0.0, gamma=0.99, tau=0.6, mutation=None, transition_weight=0.0, clip_weight=None, value_max=None, value_min=None, detach_v=False, detach_q=False, detach_pi=False, double_q=True, per_token=True, exp_weights=True, dm_margin=0.0, cql_temp=1.0, weight_decay=0.0, device='cpu')¶
The Implicit Language Q Learning algorithm class. ILQL paper: https://arxiv.org/pdf/2206.11871.pdf
- Parameters:
dataset (torch.utils.data.Dataset) – Language dataset to perform ILQL on
net_config (dict, optional) – Network configuration, defaults to GPT2 configuration
index (int, optional) – Index to keep track of object instance during tournament selection and mutation, defaults to 0
batch_size (int, optional) – Size of batched sample from replay buffer for learning, defaults to 64
lr (float, optional) – Learning rate for optimizer, defaults to 1e-5
alpha (float, optional) – For soft update of target network parameters, defaults to 0.005
beta (float, optional) – For AWR policy extraction, defaults to 0.0
gamma (float, optional) – Discount factor, defaults to 0.99
tau (float, optional) – For value network loss, defaults to 0.6
mutation (str, optional) – Most recent mutation to agent, defaults to None
transition_weight (float, optional) – Value to use temporarily for weights in transition, defaults to 0.0
clip_weight (float, optional) – Maximum value to clip weights at, defaults to None
value_max (float, optional) – Maximum Q value for clipping, defaults to None
value_min (float, optional) – Minimum Q value for clipping, defaults to None
detach_v (bool, optional) – Detach V network, defaults to False
detach_q (bool, optional) – Detach Q network, defaults to False
detach_pi (bool, optional) – Detach Policy network, defaults to False
double_q (bool, optional) – Use double Q learning, defaults to True
per_token (bool, optional) – Do per_token ILQL, defaults to True
exp_weights (bool, optional) – Exponential advantage weights, defaults to True
dm_margin (float, optional) – Margin for DM loss, defaults to 0.0
cql_temp (float, optional) – Temperature parameter for CQL loss, defaults to 1.0
weight_decay (float, optional) – weight decay for optimizer, defaults to 0.0
device (str, optional) – Device for accelerated computing, ‘cpu’ or ‘cuda’, defaults to ‘cpu’
- add_module(name: str, module: Module | None) None ¶
Add a child module to the current module.
The module can be accessed as an attribute using the given name.
- Args:
- name (str): name of the child module. The child module can be
accessed from this module using the given name
module (Module): child module to be added to the module.
- apply(fn: Callable[[Module], None]) T ¶
Apply
fn
recursively to every submodule (as returned by.children()
) as well as self.Typical use includes initializing the parameters of a model (see also nn-init-doc).
- Args:
fn (
Module
-> None): function to be applied to each submodule- Returns:
Module: self
Example:
>>> @torch.no_grad() >>> def init_weights(m): >>> print(m) >>> if type(m) == nn.Linear: >>> m.weight.fill_(1.0) >>> print(m.weight) >>> net = nn.Sequential(nn.Linear(2, 2), nn.Linear(2, 2)) >>> net.apply(init_weights) Linear(in_features=2, out_features=2, bias=True) Parameter containing: tensor([[1., 1.], [1., 1.]], requires_grad=True) Linear(in_features=2, out_features=2, bias=True) Parameter containing: tensor([[1., 1.], [1., 1.]], requires_grad=True) Sequential( (0): Linear(in_features=2, out_features=2, bias=True) (1): Linear(in_features=2, out_features=2, bias=True) )
- bfloat16() T ¶
Casts all floating point parameters and buffers to
bfloat16
datatype.Note
This method modifies the module in-place.
- Returns:
Module: self
- buffers(recurse: bool = True) Iterator[Tensor] ¶
Return an iterator over module buffers.
- Args:
- recurse (bool): if True, then yields buffers of this module
and all submodules. Otherwise, yields only buffers that are direct members of this module.
- Yields:
torch.Tensor: module buffer
Example:
>>> # xdoctest: +SKIP("undefined vars") >>> for buf in model.buffers(): >>> print(type(buf), buf.size()) <class 'torch.Tensor'> (20L,) <class 'torch.Tensor'> (20L, 1L, 5L, 5L)
- children() Iterator[Module] ¶
Return an iterator over immediate children modules.
- Yields:
Module: a child module
- clone(index=None)¶
Returns cloned agent identical to self.
- Parameters:
index (int, optional) – Index to keep track of agent for tournament selection and mutation, defaults to None
- compile(*args, **kwargs)¶
Compile this Module’s forward using
torch.compile()
.This Module’s __call__ method is compiled and all arguments are passed as-is to
torch.compile()
.See
torch.compile()
for details on the arguments for this function.
- cpu() T ¶
Move all model parameters and buffers to the CPU.
Note
This method modifies the module in-place.
- Returns:
Module: self
- cuda(device: int | device | None = None) T ¶
Move all model parameters and buffers to the GPU.
This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on GPU while being optimized.
Note
This method modifies the module in-place.
- Args:
- device (int, optional): if specified, all parameters will be
copied to that device
- Returns:
Module: self
- double() T ¶
Casts all floating point parameters and buffers to
double
datatype.Note
This method modifies the module in-place.
- Returns:
Module: self
- eval() T ¶
Set the module in evaluation mode.
This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g.
Dropout
,BatchNorm
, etc.This is equivalent with
self.train(False)
.See locally-disable-grad-doc for a comparison between .eval() and several similar mechanisms that may be confused with it.
- Returns:
Module: self
- extra_repr() str ¶
Set the extra representation of the module.
To print customized extra information, you should re-implement this method in your own modules. Both single-line and multi-line strings are acceptable.
- float() T ¶
Casts all floating point parameters and buffers to
float
datatype.Note
This method modifies the module in-place.
- Returns:
Module: self
- forward(tokens: Tensor, state_idxs: Tensor, action_idxs: Tensor, attn_mask: Tensor | None = None, prefix_embs: Tensor | None = None, prefix_attn_mask: Tensor | None = None, remove_prefix_position_embs: bool = False, qv_kwargs=None, policy_kwargs=None, target_kwargs=None, skip_policy_on_train: bool = False, detach_full_policy: bool = False)¶
Forward pass through transformers.
- Parameters:
tokens (torch.Tensor) – Tokens to input to model
state_idxs (torch.Tensor) – State indexes
action_idxs (torch.Tensor) – Action indexes
attn_mask (torch.Tensor, optional) – Attention mask for transformers, defaults to None
prefix_embs (torch.Tensor, optional) – Prefix embeddings, defaults to None
skip_policy_on_train (bool, optional) – Skip policy language model when training, defaults to False
detach_full_policy (bool, optional) – Use policy language model without gradients, defaults to False
- get_buffer(target: str) Tensor ¶
Return the buffer given by
target
if it exists, otherwise throw an error.See the docstring for
get_submodule
for a more detailed explanation of this method’s functionality as well as how to correctly specifytarget
.- Args:
- target: The fully-qualified string name of the buffer
to look for. (See
get_submodule
for how to specify a fully-qualified string.)
- Returns:
torch.Tensor: The buffer referenced by
target
- Raises:
- AttributeError: If the target string references an invalid
path or resolves to something that is not a buffer
- get_extra_state() Any ¶
Return any extra state to include in the module’s state_dict.
Implement this and a corresponding
set_extra_state()
for your module if you need to store extra state. This function is called when building the module’s state_dict().Note that extra state should be picklable to ensure working serialization of the state_dict. We only provide provide backwards compatibility guarantees for serializing Tensors; other objects may break backwards compatibility if their serialized pickled form changes.
- Returns:
object: Any extra state to store in the module’s state_dict
- get_parameter(target: str) Parameter ¶
Return the parameter given by
target
if it exists, otherwise throw an error.See the docstring for
get_submodule
for a more detailed explanation of this method’s functionality as well as how to correctly specifytarget
.- Args:
- target: The fully-qualified string name of the Parameter
to look for. (See
get_submodule
for how to specify a fully-qualified string.)
- Returns:
torch.nn.Parameter: The Parameter referenced by
target
- Raises:
- AttributeError: If the target string references an invalid
path or resolves to something that is not an
nn.Parameter
- get_submodule(target: str) Module ¶
Return the submodule given by
target
if it exists, otherwise throw an error.For example, let’s say you have an
nn.Module
A
that looks like this:A( (net_b): Module( (net_c): Module( (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2)) ) (linear): Linear(in_features=100, out_features=200, bias=True) ) )
(The diagram shows an
nn.Module
A
.A
has a nested submodulenet_b
, which itself has two submodulesnet_c
andlinear
.net_c
then has a submoduleconv
.)To check whether or not we have the
linear
submodule, we would callget_submodule("net_b.linear")
. To check whether we have theconv
submodule, we would callget_submodule("net_b.net_c.conv")
.The runtime of
get_submodule
is bounded by the degree of module nesting intarget
. A query againstnamed_modules
achieves the same result, but it is O(N) in the number of transitive modules. So, for a simple check to see if some submodule exists,get_submodule
should always be used.- Args:
- target: The fully-qualified string name of the submodule
to look for. (See above example for how to specify a fully-qualified string.)
- Returns:
torch.nn.Module: The submodule referenced by
target
- Raises:
- AttributeError: If the target string references an invalid
path or resolves to something that is not an
nn.Module
- half() T ¶
Casts all floating point parameters and buffers to
half
datatype.Note
This method modifies the module in-place.
- Returns:
Module: self
- hardUpdate()¶
Hard updates target networks.
- ipu(device: int | device | None = None) T ¶
Move all model parameters and buffers to the IPU.
This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on IPU while being optimized.
Note
This method modifies the module in-place.
- Arguments:
- device (int, optional): if specified, all parameters will be
copied to that device
- Returns:
Module: self
- load_checkpoint(path)¶
Loads saved agent properties and network weights from checkpoint.
- Parameters:
path (string) – Location to load checkpoint from
- load_state_dict(state_dict: Mapping[str, Any], strict: bool = True, assign: bool = False)¶
Copy parameters and buffers from
state_dict
into this module and its descendants.If
strict
isTrue
, then the keys ofstate_dict
must exactly match the keys returned by this module’sstate_dict()
function.Warning
If
assign
isTrue
the optimizer must be created after the call toload_state_dict
.- Args:
- state_dict (dict): a dict containing parameters and
persistent buffers.
- strict (bool, optional): whether to strictly enforce that the keys
in
state_dict
match the keys returned by this module’sstate_dict()
function. Default:True
- assign (bool, optional): whether to assign items in the state
dictionary to their corresponding keys in the module instead of copying them inplace into the module’s current parameters and buffers. When
False
, the properties of the tensors in the current module are preserved while whenTrue
, the properties of the Tensors in the state dict are preserved. Default:False
- Returns:
NamedTuple
withmissing_keys
andunexpected_keys
fields:missing_keys is a list of str containing the missing keys
unexpected_keys is a list of str containing the unexpected keys
- Note:
If a parameter or buffer is registered as
None
and its corresponding key exists instate_dict
,load_state_dict()
will raise aRuntimeError
.
- modules() Iterator[Module] ¶
Return an iterator over all modules in the network.
- Yields:
Module: a module in the network
- Note:
Duplicate modules are returned only once. In the following example,
l
will be returned only once.
Example:
>>> l = nn.Linear(2, 2) >>> net = nn.Sequential(l, l) >>> for idx, m in enumerate(net.modules()): ... print(idx, '->', m) 0 -> Sequential( (0): Linear(in_features=2, out_features=2, bias=True) (1): Linear(in_features=2, out_features=2, bias=True) ) 1 -> Linear(in_features=2, out_features=2, bias=True)
- named_buffers(prefix: str = '', recurse: bool = True, remove_duplicate: bool = True) Iterator[Tuple[str, Tensor]] ¶
Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
- Args:
prefix (str): prefix to prepend to all buffer names. recurse (bool, optional): if True, then yields buffers of this module
and all submodules. Otherwise, yields only buffers that are direct members of this module. Defaults to True.
remove_duplicate (bool, optional): whether to remove the duplicated buffers in the result. Defaults to True.
- Yields:
(str, torch.Tensor): Tuple containing the name and buffer
Example:
>>> # xdoctest: +SKIP("undefined vars") >>> for name, buf in self.named_buffers(): >>> if name in ['running_var']: >>> print(buf.size())
- named_children() Iterator[Tuple[str, Module]] ¶
Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
- Yields:
(str, Module): Tuple containing a name and child module
Example:
>>> # xdoctest: +SKIP("undefined vars") >>> for name, module in model.named_children(): >>> if name in ['conv4', 'conv5']: >>> print(module)
- named_modules(memo: Set[Module] | None = None, prefix: str = '', remove_duplicate: bool = True)¶
Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
- Args:
memo: a memo to store the set of modules already added to the result prefix: a prefix that will be added to the name of the module remove_duplicate: whether to remove the duplicated module instances in the result
or not
- Yields:
(str, Module): Tuple of name and module
- Note:
Duplicate modules are returned only once. In the following example,
l
will be returned only once.
Example:
>>> l = nn.Linear(2, 2) >>> net = nn.Sequential(l, l) >>> for idx, m in enumerate(net.named_modules()): ... print(idx, '->', m) 0 -> ('', Sequential( (0): Linear(in_features=2, out_features=2, bias=True) (1): Linear(in_features=2, out_features=2, bias=True) )) 1 -> ('0', Linear(in_features=2, out_features=2, bias=True))
- named_parameters(prefix: str = '', recurse: bool = True, remove_duplicate: bool = True) Iterator[Tuple[str, Parameter]] ¶
Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
- Args:
prefix (str): prefix to prepend to all parameter names. recurse (bool): if True, then yields parameters of this module
and all submodules. Otherwise, yields only parameters that are direct members of this module.
- remove_duplicate (bool, optional): whether to remove the duplicated
parameters in the result. Defaults to True.
- Yields:
(str, Parameter): Tuple containing the name and parameter
Example:
>>> # xdoctest: +SKIP("undefined vars") >>> for name, param in self.named_parameters(): >>> if name in ['bias']: >>> print(param.size())
- parameters(recurse: bool = True) Iterator[Parameter] ¶
Return an iterator over module parameters.
This is typically passed to an optimizer.
- Args:
- recurse (bool): if True, then yields parameters of this module
and all submodules. Otherwise, yields only parameters that are direct members of this module.
- Yields:
Parameter: module parameter
Example:
>>> # xdoctest: +SKIP("undefined vars") >>> for param in model.parameters(): >>> print(type(param), param.size()) <class 'torch.Tensor'> (20L,) <class 'torch.Tensor'> (20L, 1L, 5L, 5L)
- register_backward_hook(hook: Callable[[Module, Tuple[Tensor, ...] | Tensor, Tuple[Tensor, ...] | Tensor], None | Tuple[Tensor, ...] | Tensor]) RemovableHandle ¶
Register a backward hook on the module.
This function is deprecated in favor of
register_full_backward_hook()
and the behavior of this function will change in future versions.- Returns:
torch.utils.hooks.RemovableHandle
:a handle that can be used to remove the added hook by calling
handle.remove()
- register_buffer(name: str, tensor: Tensor | None, persistent: bool = True) None ¶
Add a buffer to the module.
This is typically used to register a buffer that should not to be considered a model parameter. For example, BatchNorm’s
running_mean
is not a parameter, but is part of the module’s state. Buffers, by default, are persistent and will be saved alongside parameters. This behavior can be changed by settingpersistent
toFalse
. The only difference between a persistent buffer and a non-persistent buffer is that the latter will not be a part of this module’sstate_dict
.Buffers can be accessed as attributes using given names.
- Args:
- name (str): name of the buffer. The buffer can be accessed
from this module using the given name
- tensor (Tensor or None): buffer to be registered. If
None
, then operations that run on buffers, such as
cuda
, are ignored. IfNone
, the buffer is not included in the module’sstate_dict
.- persistent (bool): whether the buffer is part of this module’s
Example:
>>> # xdoctest: +SKIP("undefined vars") >>> self.register_buffer('running_mean', torch.zeros(num_features))
- register_forward_hook(hook: Callable[[T, Tuple[Any, ...], Any], Any | None] | Callable[[T, Tuple[Any, ...], Dict[str, Any], Any], Any | None], *, prepend: bool = False, with_kwargs: bool = False, always_call: bool = False) RemovableHandle ¶
Register a forward hook on the module.
The hook will be called every time after
forward()
has computed an output.If
with_kwargs
isFalse
or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to theforward
. The hook can modify the output. It can modify the input inplace but it will not have effect on forward since this is called afterforward()
is called. The hook should have the following signature:hook(module, args, output) -> None or modified output
If
with_kwargs
isTrue
, the forward hook will be passed thekwargs
given to the forward function and be expected to return the output possibly modified. The hook should have the following signature:hook(module, args, kwargs, output) -> None or modified output
- Args:
hook (Callable): The user defined hook to be registered. prepend (bool): If
True
, the providedhook
will be firedbefore all existing
forward
hooks on thistorch.nn.modules.Module
. Otherwise, the providedhook
will be fired after all existingforward
hooks on thistorch.nn.modules.Module
. Note that globalforward
hooks registered withregister_module_forward_hook()
will fire before all hooks registered by this method. Default:False
- with_kwargs (bool): If
True
, thehook
will be passed the kwargs given to the forward function. Default:
False
- always_call (bool): If
True
thehook
will be run regardless of whether an exception is raised while calling the Module. Default:
False
- with_kwargs (bool): If
- Returns:
torch.utils.hooks.RemovableHandle
:a handle that can be used to remove the added hook by calling
handle.remove()
- register_forward_pre_hook(hook: Callable[[T, Tuple[Any, ...]], Any | None] | Callable[[T, Tuple[Any, ...], Dict[str, Any]], Tuple[Any, Dict[str, Any]] | None], *, prepend: bool = False, with_kwargs: bool = False) RemovableHandle ¶
Register a forward pre-hook on the module.
The hook will be called every time before
forward()
is invoked.If
with_kwargs
is false or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to theforward
. The hook can modify the input. User can either return a tuple or a single modified value in the hook. We will wrap the value into a tuple if a single value is returned (unless that value is already a tuple). The hook should have the following signature:hook(module, args) -> None or modified input
If
with_kwargs
is true, the forward pre-hook will be passed the kwargs given to the forward function. And if the hook modifies the input, both the args and kwargs should be returned. The hook should have the following signature:hook(module, args, kwargs) -> None or a tuple of modified input and kwargs
- Args:
hook (Callable): The user defined hook to be registered. prepend (bool): If true, the provided
hook
will be fired beforeall existing
forward_pre
hooks on thistorch.nn.modules.Module
. Otherwise, the providedhook
will be fired after all existingforward_pre
hooks on thistorch.nn.modules.Module
. Note that globalforward_pre
hooks registered withregister_module_forward_pre_hook()
will fire before all hooks registered by this method. Default:False
- with_kwargs (bool): If true, the
hook
will be passed the kwargs given to the forward function. Default:
False
- with_kwargs (bool): If true, the
- Returns:
torch.utils.hooks.RemovableHandle
:a handle that can be used to remove the added hook by calling
handle.remove()
- register_full_backward_hook(hook: Callable[[Module, Tuple[Tensor, ...] | Tensor, Tuple[Tensor, ...] | Tensor], None | Tuple[Tensor, ...] | Tensor], prepend: bool = False) RemovableHandle ¶
Register a backward hook on the module.
The hook will be called every time the gradients with respect to a module are computed, i.e. the hook will execute if and only if the gradients with respect to module outputs are computed. The hook should have the following signature:
hook(module, grad_input, grad_output) -> tuple(Tensor) or None
The
grad_input
andgrad_output
are tuples that contain the gradients with respect to the inputs and outputs respectively. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the input that will be used in place ofgrad_input
in subsequent computations.grad_input
will only correspond to the inputs given as positional arguments and all kwarg arguments are ignored. Entries ingrad_input
andgrad_output
will beNone
for all non-Tensor arguments.For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.
Warning
Modifying inputs or outputs inplace is not allowed when using backward hooks and will raise an error.
- Args:
hook (Callable): The user-defined hook to be registered. prepend (bool): If true, the provided
hook
will be fired beforeall existing
backward
hooks on thistorch.nn.modules.Module
. Otherwise, the providedhook
will be fired after all existingbackward
hooks on thistorch.nn.modules.Module
. Note that globalbackward
hooks registered withregister_module_full_backward_hook()
will fire before all hooks registered by this method.- Returns:
torch.utils.hooks.RemovableHandle
:a handle that can be used to remove the added hook by calling
handle.remove()
- register_full_backward_pre_hook(hook: Callable[[Module, Tuple[Tensor, ...] | Tensor], None | Tuple[Tensor, ...] | Tensor], prepend: bool = False) RemovableHandle ¶
Register a backward pre-hook on the module.
The hook will be called every time the gradients for the module are computed. The hook should have the following signature:
hook(module, grad_output) -> tuple[Tensor] or None
The
grad_output
is a tuple. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the output that will be used in place ofgrad_output
in subsequent computations. Entries ingrad_output
will beNone
for all non-Tensor arguments.For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.
Warning
Modifying inputs inplace is not allowed when using backward hooks and will raise an error.
- Args:
hook (Callable): The user-defined hook to be registered. prepend (bool): If true, the provided
hook
will be fired beforeall existing
backward_pre
hooks on thistorch.nn.modules.Module
. Otherwise, the providedhook
will be fired after all existingbackward_pre
hooks on thistorch.nn.modules.Module
. Note that globalbackward_pre
hooks registered withregister_module_full_backward_pre_hook()
will fire before all hooks registered by this method.- Returns:
torch.utils.hooks.RemovableHandle
:a handle that can be used to remove the added hook by calling
handle.remove()
- register_load_state_dict_post_hook(hook)¶
Register a post hook to be run after module’s
load_state_dict
is called.- It should have the following signature::
hook(module, incompatible_keys) -> None
The
module
argument is the current module that this hook is registered on, and theincompatible_keys
argument is aNamedTuple
consisting of attributesmissing_keys
andunexpected_keys
.missing_keys
is alist
ofstr
containing the missing keys andunexpected_keys
is alist
ofstr
containing the unexpected keys.The given incompatible_keys can be modified inplace if needed.
Note that the checks performed when calling
load_state_dict()
withstrict=True
are affected by modifications the hook makes tomissing_keys
orunexpected_keys
, as expected. Additions to either set of keys will result in an error being thrown whenstrict=True
, and clearing out both missing and unexpected keys will avoid an error.- Returns:
torch.utils.hooks.RemovableHandle
:a handle that can be used to remove the added hook by calling
handle.remove()
- register_module(name: str, module: Module | None) None ¶
Alias for
add_module()
.
- register_parameter(name: str, param: Parameter | None) None ¶
Add a parameter to the module.
The parameter can be accessed as an attribute using given name.
- Args:
- name (str): name of the parameter. The parameter can be accessed
from this module using the given name
- param (Parameter or None): parameter to be added to the module. If
None
, then operations that run on parameters, such ascuda
, are ignored. IfNone
, the parameter is not included in the module’sstate_dict
.
- register_state_dict_pre_hook(hook)¶
Register a pre-hook for the
load_state_dict()
method.These hooks will be called with arguments:
self
,prefix
, andkeep_vars
before callingstate_dict
onself
. The registered hooks can be used to perform pre-processing before thestate_dict
call is made.
- requires_grad_(requires_grad: bool = True) T ¶
Change if autograd should record operations on parameters in this module.
This method sets the parameters’
requires_grad
attributes in-place.This method is helpful for freezing part of the module for finetuning or training parts of a model individually (e.g., GAN training).
See locally-disable-grad-doc for a comparison between .requires_grad_() and several similar mechanisms that may be confused with it.
- Args:
- requires_grad (bool): whether autograd should record operations on
parameters in this module. Default:
True
.
- Returns:
Module: self
- save_checkpoint(path)¶
Saves a checkpoint of agent properties and network weights to path.
- Parameters:
path (string) – Location to save checkpoint at
- set_extra_state(state: Any)¶
Set extra state contained in the loaded state_dict.
This function is called from
load_state_dict()
to handle any extra state found within the state_dict. Implement this function and a correspondingget_extra_state()
for your module if you need to store extra state within its state_dict.- Args:
state (dict): Extra state from the state_dict
See
torch.Tensor.share_memory_()
.
- soft_update()¶
Soft updates target networks.
- state_dict(*args, destination=None, prefix='', keep_vars=False)¶
Return a dictionary containing references to the whole state of the module.
Both parameters and persistent buffers (e.g. running averages) are included. Keys are corresponding parameter and buffer names. Parameters and buffers set to
None
are not included.Note
The returned object is a shallow copy. It contains references to the module’s parameters and buffers.
Warning
Currently
state_dict()
also accepts positional arguments fordestination
,prefix
andkeep_vars
in order. However, this is being deprecated and keyword arguments will be enforced in future releases.Warning
Please avoid the use of argument
destination
as it is not designed for end-users.- Args:
- destination (dict, optional): If provided, the state of module will
be updated into the dict and the same object is returned. Otherwise, an
OrderedDict
will be created and returned. Default:None
.- prefix (str, optional): a prefix added to parameter and buffer
names to compose the keys in state_dict. Default:
''
.- keep_vars (bool, optional): by default the
Tensor
s returned in the state dict are detached from autograd. If it’s set to
True
, detaching will not be performed. Default:False
.
- Returns:
- dict:
a dictionary containing a whole state of the module
Example:
>>> # xdoctest: +SKIP("undefined vars") >>> module.state_dict().keys() ['bias', 'weight']
- to(*args, **kwargs)¶
Move and/or cast the parameters and buffers.
This can be called as
- to(device=None, dtype=None, non_blocking=False)
- to(dtype, non_blocking=False)
- to(tensor, non_blocking=False)
- to(memory_format=torch.channels_last)
Its signature is similar to
torch.Tensor.to()
, but only accepts floating point or complexdtype
s. In addition, this method will only cast the floating point or complex parameters and buffers todtype
(if given). The integral parameters and buffers will be moveddevice
, if that is given, but with dtypes unchanged. Whennon_blocking
is set, it tries to convert/move asynchronously with respect to the host if possible, e.g., moving CPU Tensors with pinned memory to CUDA devices.See below for examples.
Note
This method modifies the module in-place.
- Args:
- device (
torch.device
): the desired device of the parameters and buffers in this module
- dtype (
torch.dtype
): the desired floating point or complex dtype of the parameters and buffers in this module
- tensor (torch.Tensor): Tensor whose dtype and device are the desired
dtype and device for all parameters and buffers in this module
- memory_format (
torch.memory_format
): the desired memory format for 4D parameters and buffers in this module (keyword only argument)
- device (
- Returns:
Module: self
Examples:
>>> # xdoctest: +IGNORE_WANT("non-deterministic") >>> linear = nn.Linear(2, 2) >>> linear.weight Parameter containing: tensor([[ 0.1913, -0.3420], [-0.5113, -0.2325]]) >>> linear.to(torch.double) Linear(in_features=2, out_features=2, bias=True) >>> linear.weight Parameter containing: tensor([[ 0.1913, -0.3420], [-0.5113, -0.2325]], dtype=torch.float64) >>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA1) >>> gpu1 = torch.device("cuda:1") >>> linear.to(gpu1, dtype=torch.half, non_blocking=True) Linear(in_features=2, out_features=2, bias=True) >>> linear.weight Parameter containing: tensor([[ 0.1914, -0.3420], [-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1') >>> cpu = torch.device("cpu") >>> linear.to(cpu) Linear(in_features=2, out_features=2, bias=True) >>> linear.weight Parameter containing: tensor([[ 0.1914, -0.3420], [-0.5112, -0.2324]], dtype=torch.float16) >>> linear = nn.Linear(2, 2, bias=None).to(torch.cdouble) >>> linear.weight Parameter containing: tensor([[ 0.3741+0.j, 0.2382+0.j], [ 0.5593+0.j, -0.4443+0.j]], dtype=torch.complex128) >>> linear(torch.ones(3, 2, dtype=torch.cdouble)) tensor([[0.6122+0.j, 0.1150+0.j], [0.6122+0.j, 0.1150+0.j], [0.6122+0.j, 0.1150+0.j]], dtype=torch.complex128)
- to_empty(*, device: int | str | device | None, recurse: bool = True) T ¶
Move the parameters and buffers to the specified device without copying storage.
- Args:
- device (
torch.device
): The desired device of the parameters and buffers in this module.
- recurse (bool): Whether parameters and buffers of submodules should
be recursively moved to the specified device.
- device (
- Returns:
Module: self
- train(mode: bool = True) T ¶
Set the module in training mode.
This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g.
Dropout
,BatchNorm
, etc.- Args:
- mode (bool): whether to set training mode (
True
) or evaluation mode (
False
). Default:True
.
- mode (bool): whether to set training mode (
- Returns:
Module: self
- type(dst_type: dtype | str) T ¶
Casts all parameters and buffers to
dst_type
.Note
This method modifies the module in-place.
- Args:
dst_type (type or string): the desired type
- Returns:
Module: self
- xpu(device: int | device | None = None) T ¶
Move all model parameters and buffers to the XPU.
This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on XPU while being optimized.
Note
This method modifies the module in-place.
- Arguments:
- device (int, optional): if specified, all parameters will be
copied to that device
- Returns:
Module: self