a
d] @ s d Z ddlZddlZddlmZ ddlmZmZmZmZ ddl Z
ddl m Z ddl
mZmZ ddlmZ dd lmZ eeZeG d
d d ZeG d d
d
ZG dd dZG dd deZG dd deZG dd deZ G dd deZ G dd deZ dS )zJ
Callbacks to use with the Trainer class and customize the training loop.
N) dataclass)DictListOptionalUnion)tqdm )IntervalStrategy
has_length)TrainingArguments)loggingc @ s e Zd ZU dZdZee ed< dZe ed< dZ
e ed< dZ e ed< dZ eed< dZ
eeeef ed < dZee ed
< dZee ed < d Zeed
< d Zeed< dZeed< dZeed< dZeeeeee ef f ed< dd ZedddZe edddZ dS ) TrainerStatea+
A class containing the [`Trainer`] inner state that will be saved along the model and optimizer when checkpointing
and passed to the [`TrainerCallback`].
In all this class, one step is to be understood as one update step. When using gradient accumulation, one update
step may require several forward and backward passes: if you use `gradient_accumulation_steps=n`, then one update
step requires going through *n* batches.
Args:
epoch (`float`, *optional*):
Only set during training, will represent the epoch the training is at (the decimal part being the
percentage of the current epoch completed).
global_step (`int`, *optional*, defaults to 0):
During training, represents the number of update steps completed.
max_steps (`int`, *optional*, defaults to 0):
The number of update steps to do during the current training.
total_flos (`float`, *optional*, defaults to 0):
The total number of floating operations done by the model since the beginning of training (stored as floats
to avoid overflow).
log_history (`List[Dict[str, float]]`, *optional*):
The list of logs done since the beginning of training.
best_metric (`float`, *optional*):
When tracking the best model, the value of the best metric encountered so far.
best_model_checkpoint (`str`, *optional*):
When tracking the best model, the value of the name of the checkpoint for the best model encountered so
far.
is_local_process_zero (`bool`, *optional*, defaults to `True`):
Whether or not this process is the local (e.g., on one machine if training in a distributed fashion on
several machines) main process.
is_world_process_zero (`bool`, *optional*, defaults to `True`):
Whether or not this process is the global main process (when training in a distributed fashion on several
machines, this is only going to be `True` for one process).
is_hyper_param_search (`bool`, *optional*, defaults to `False`):
Whether we are in the process of a hyper parameter search using Trainer.hyperparameter_search. This will
impact the way data will be logged in TensorBoard.
Nepochr global_step max_stepsnum_train_epochs
total_flos log_history best_metricbest_model_checkpointTis_local_process_zerois_world_process_zeroFis_hyper_param_search
trial_name trial_paramsc C s | j d u rg | _ d S N)r self r f/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/transformers/trainer_callback.py
__post_init__[ s
zTrainerState.__post_init__) json_pathc C sV t jt| dddd }t|ddd}|| W d n1 sH0 Y dS ) zDSave the content of this instance in JSON format inside `json_path`. T)indent sort_keys
wutf-8encodingN)jsondumps dataclassesZasdictopenwrite)r r! Z json_stringfr r r save_to_json_ s zTrainerState.save_to_jsonc C sJ t |ddd}| }W d n1 s,0 Y | f i t|S )z3Create an instance from the content of `json_path`.rr' r( N)r- readr* loads)clsr! r/ textr r r load_from_jsone s &zTrainerState.load_from_json) __name__
__module__ __qualname____doc__r r float__annotations__r intr r r r r r strr r r boolr r r r r r r0 classmethodr6 r r r r r
" s$
) r
c @ sf e Zd ZU dZdZeed< dZeed< dZeed< dZ eed< dZ
eed< dd Z d
d Z d d
Z
dS )TrainerControlaA
A class that handles the [`Trainer`] control flow. This class is used by the [`TrainerCallback`] to activate some
switches in the training loop.
Args:
should_training_stop (`bool`, *optional*, defaults to `False`):
Whether or not the training should be interrupted.
If `True`, this variable will not be set back to `False`. The training will just stop.
should_epoch_stop (`bool`, *optional*, defaults to `False`):
Whether or not the current epoch should be interrupted.
If `True`, this variable will be set back to `False` at the beginning of the next epoch.
should_save (`bool`, *optional*, defaults to `False`):
Whether or not the model should be saved at this step.
If `True`, this variable will be set back to `False` at the beginning of the next step.
should_evaluate (`bool`, *optional*, defaults to `False`):
Whether or not the model should be evaluated at this step.
If `True`, this variable will be set back to `False` at the beginning of the next step.
should_log (`bool`, *optional*, defaults to `False`):
Whether or not the logs should be reported at this step.
If `True`, this variable will be set back to `False` at the beginning of the next step.
Fshould_training_stopshould_epoch_stop should_saveshould_evaluate
should_logc C s
d| _ dS )zInternal class that just calls the list of callbacks in order.c C sf g | _ |D ]}| | q
|| _|| _|| _|| _d | _d | _tdd | j D sbt
d| j d S )Nc s s | ]}t |tV qd S r )
isinstanceDefaultFlowCallback.0cbr r r 0 z+CallbackHandler.__init__..zThe Trainer will not work properly if you don't have a `DefaultFlowCallback` in its callbacks. You
should add one before training with `trainer.add_callback(DefaultFlowCallback). The current list ofcallbacks is
:) callbacks add_callbackmodel tokenizer optimizer lr_schedulertrain_dataloadereval_dataloaderanyloggerwarning
callback_list)r rg ri rj rk rl rd r r r __init__% s zCallbackHandler.__init__c C sh t |tr| n|}t |tr"|n|j}|dd | jD v rXtd| dd | j | j| d S )Nc S s g | ]
}|j qS r ) __class__)rc cr r r
; rf z0CallbackHandler.add_callback..zYou are adding a zH to the callbacks of this Trainer, but there is already one. The currentzlist of callbacks is
:)r` typert rg rp rq rr append)r callbackrd Zcb_classr r r rh 8 s
z CallbackHandler.add_callbackc C sb t |tr6| jD ]"}t ||r| j| | S qn(| jD ] }||kr<| j| | S q.)joinrg r r r r rr X s z CallbackHandler.callback_listrK c C s | d|||S )NrQ
call_eventr rL rM rN r r r rQ \ s zCallbackHandler.on_init_endc C s d|_ | d|||S )NFrR )rB r r r r r rR _ s z CallbackHandler.on_train_beginc C s | d|||S )NrS r r r r r rS c s z CallbackHandler.on_train_endc C s d|_ | d|||S )NFrT )rC r r r r r rT f s z CallbackHandler.on_epoch_beginc C s | d|||S )NrU r r r r r rU j s z CallbackHandler.on_epoch_endc C s" d|_ d|_d|_| d|||S )NFrV )rF rE rD r r r r r rV m s z CallbackHandler.on_step_beginc C s | d|||S )NrW r r r r r rW s s z CallbackHandler.on_substep_endc C s | d|||S )NrX r r r r r rX v s zCallbackHandler.on_step_endc C s d|_ | jd||||dS )NFrY rZ )rE r r rL rM rN rZ r r r rY y s zCallbackHandler.on_evaluatec C s | j d||||dS )Nr[ r r r r r r r[ } s zCallbackHandler.on_predictc C s d|_ | d|||S )NFr\ )rD r r r r r r\ s zCallbackHandler.on_savec C s d|_ | jd||||dS )NFr] )logs)rF r )r rL rM rN r r r r r] s zCallbackHandler.on_logc C s | d|||S )Nr^ r r r r r r^ s z"CallbackHandler.on_prediction_stepc
K sP | j D ]D}t|||||f| j| j| j| j| j| jd|}|d ur|}q|S )N)ri rj rk rl rm rn )rg getattrri rj rk rl rm rn )r eventrL rM rN rP ry resultr r r r s$
zCallbackHandler.call_eventN)r7 r8 r9 r: rs rh r} r~ propertyrr r r
rA rQ rR rS rT rU rV rW rX rY r[ r\ r] r^ r r r r r r_ " s*
r_ c @ s4 e Zd ZdZeeedddZeeedddZdS )ra zx
A [`TrainerCallback`] that handles the default flow of the training loop for logs, evaluation and checkpoints.
rK c K s |j dkr|jrd|_|jtjkr8|j |j dkr8d|_|jtjkrf|j |j dkrf|j |j krfd|_
|j tjkr|j dkr|j |j dkrd|_
|j |jkrd|_|S )Nr Tr )r Zlogging_first_steprF logging_strategyr ZSTEPSZ
logging_stepsevaluation_strategyZ
eval_steps
eval_delayrE
save_strategyZ
save_stepsrD r rB rO r r r rX s*
z DefaultFlowCallback.on_step_endc K sF |j tjkrd|_|jtjkr0|j|jkr0d|_|jtjkrBd|_ |S )NT)
r r EPOCHrF r r r rE r rD rO r r r rU s z DefaultFlowCallback.on_epoch_endN) r7 r8 r9 r: r r
rA rX rU r r r r ra s ra c @ sT e Zd ZdZdd Zdd Zdd Zdd d
Zd d Zd
d Z dddZ
dd Z dS )ProgressCallbackzU
A [`TrainerCallback`] that displays the progress of training or evaluation.
c C s d | _ d | _d S r ) training_barprediction_barr r r r rs s zProgressCallback.__init__c K s |j rt|jd| _d| _d S )N)totalr )r r r r current_steprO r r r rR s z ProgressCallback.on_train_beginc K s& |j r"| j|j| j |j| _d S r )r r updater r rO r r r rX s z ProgressCallback.on_step_endNc K s@ |j r r rL rM rN r rP _r r r r] s zProgressCallback.on_logc K s |j r| j d | _d S r )r r r rO r r r rS s
z ProgressCallback.on_train_end)N)N) r7 r8 r9 r: rs rR rX r^ rY r[ r] rS r r r r r s
r c @ s e Zd ZdZdddZdS )PrinterCallbackz?
A bare [`TrainerCallback`] that just prints the logs.
Nc K s | dd }|jrt| d S r )r r printr r r r r] s zPrinterCallback.on_log)N)r7 r8 r9 r: r] r r r r r s r c @ s> e Zd ZdZdeee dddZdd Zd d
Z d d Z
d
S )EarlyStoppingCallbacka/
A [`TrainerCallback`] that handles early stopping.
Args:
early_stopping_patience (`int`):
Use with `metric_for_best_model` to stop training when the specified metric worsens for
`early_stopping_patience` evaluation calls.
early_stopping_threshold(`float`, *optional*):
Use with TrainingArguments `metric_for_best_model` and `early_stopping_patience` to denote how much the
specified metric must improve to satisfy early stopping conditions. `
This callback depends on [`TrainingArguments`] argument *load_best_model_at_end* functionality to set best_metric
in [`TrainerState`]. Note that if the [`TrainingArguments`] argument *save_steps* differs from *eval_steps*, the
early stopping will not occur until the next save step.
r )early_stopping_patienceearly_stopping_thresholdc C s || _ || _d| _d S )Nr )r r early_stopping_patience_counter)r r r r r r rs s z EarlyStoppingCallback.__init__c C sV |j r tjntj}|jd u s<|||jrDt||j | jkrDd| _n| jd7 _d S )Nr r )Zgreater_is_betternpZgreaterZlessr absr r )r rL rM rN metric_valueoperatorr r r check_metric_value# s
z(EarlyStoppingCallback.check_metric_valuec K s8 |j sJ d|jd us J d|jtjks4J dd S )Nz s*
J1 }20