SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Documentation for the Trainer API (#5383)

Browse Source 
* Documentation for the Trainer API

* Address review comments

* Address comments
This commit is contained in:
Sylvain Gugger
2020-06-30 11:43:43 -04:00
committed by GitHub
parent c4d4e8bdbd
commit 87716a6d07
8 changed files with 369 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/source/index.rst
View File

@@ -173,6 +173,7 @@ conversion utilities for the following models:
main_classes/pipelines
main_classes/optimizer_schedules
main_classes/processors
main_classes/trainer
model_doc/auto
model_doc/encoderdecoder
model_doc/bert

45
docs/source/main_classes/trainer.rst Normal file
View File

@@ -0,0 +1,45 @@
Trainer
----------
The :class:`~transformers.Trainer` and :class:`~transformers.TFTrainer` classes provide an API for feature-complete
training in most standard use cases. It's used in most of the :doc:`example scripts <../examples>`.
Before instantiating your :class:`~transformers.Trainer`/:class:`~transformers.TFTrainer`, create a
:class:`~transformers.TrainingArguments`/:class:`~transformers.TFTrainingArguments` to access all the points of
customization during training.
The API supports distributed training on multiple GPUs/TPUs, mixed precision through `NVIDIA Apex
<https://github.com/NVIDIA/apex>`__ for PyTorch and :obj:`tf.keras.mixed_precision` for TensorFlow.
``Trainer``
~~~~~~~~~~~
.. autoclass:: transformers.Trainer
:members:
``TFTrainer``
~~~~~~~~~~~~~
.. autoclass:: transformers.TFTrainer
:members:
``TrainingArguments``
~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TrainingArguments
:members:
``TFTrainingArguments``
~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFTrainingArguments
:members:
Utilities
~~~~~~~~~
.. autoclass:: transformers.EvalPrediction
.. autofunction:: transformers.set_seed
.. autofunction:: transformers.torch_distributed_zero_first

2
src/transformers/__init__.py
View File

@@ -397,7 +397,7 @@ if is_torch_available():
)
# Trainer
from .trainer import Trainer, set_seed, torch_distributed_zero_first, EvalPrediction
from .trainer import Trainer, set_seed, torch_distributed_zero_first
from .data.data_collator import default_data_collator, DataCollator, DataCollatorForLanguageModeling
from .data.datasets import GlueDataset, TextDataset, LineByLineTextDataset, GlueDataTrainingArguments

107
src/transformers/trainer.py
View File

@@ -61,6 +61,12 @@ logger = logging.getLogger(__name__)
def set_seed(seed: int):
"""
Helper function for reproducible behavior to set the seed in ``random``, ``numpy`` and ``torch``.
Args:
seed (:obj:`int`): The seed to set.
"""
random.seed(seed)
np.random.seed(seed)
torch.manual_seed(seed)
@@ -72,6 +78,9 @@ def set_seed(seed: int):
def torch_distributed_zero_first(local_rank: int):
"""
Decorator to make all processes in distributed training wait for each local_master to do something.
Args:
local_rank (:obj:`int`): The rank of the local process.
"""
if local_rank not in [-1, 0]:
torch.distributed.barrier()
@@ -133,7 +142,31 @@ def get_tpu_sampler(dataset: Dataset):
class Trainer:
"""
Trainer is a simple but feature-complete training and eval loop for PyTorch,
optimized for Transformers.
optimized for 🤗 Transformers.
Args:
model (:class:`~transformers.PreTrainedModel`):
The model to train, evaluate or use for predictions.
args (:class:`~transformers.TrainingArguments`):
The arguments to tweak training.
data_collator (:obj:`DataCollator`, `optional`, defaults to :func:`~transformers.default_data_collator`):
The function to use to from a batch from a list of elements of :obj:`train_dataset` or
:obj:`eval_dataset`.
train_dataset (:obj:`Dataset`, `optional`):
The dataset to use for training.
eval_dataset (:obj:`Dataset`, `optional`):
The dataset to use for evaluation.
compute_metrics (:obj:`Callable[[EvalPrediction], Dict]`, `optional`):
The function that will be used to compute metrics at evaluation. Must take a
:class:`~transformers.EvalPrediction` and return a dictionary string to metric values.
prediction_loss_only (:obj:`bool`, `optional`, defaults to `False`):
When performing evaluation and predictions, only returns the loss.
tb_writer (:obj:`SummaryWriter`, `optional`):
Object to write to TensorBoard.
optimizers (:obj:`Tuple[torch.optim.Optimizer, torch.optim.lr_scheduler.LambdaLR`, `optional`):
A tuple containing the optimizer and the scheduler to use. Will default to an instance of
:class:`~transformers.AdamW` on your model and a scheduler given by
:func:`~transformers.get_linear_schedule_with_warmup` controlled by :obj:`args`.
"""
model: PreTrainedModel
@@ -160,14 +193,6 @@ class Trainer:
tb_writer: Optional["SummaryWriter"] = None,
optimizers: Tuple[torch.optim.Optimizer, torch.optim.lr_scheduler.LambdaLR] = None,
):
"""
Trainer is a simple but feature-complete training and eval loop for PyTorch,
optimized for Transformers.
Args:
prediction_loss_only:
(Optional) in evaluation and prediction, only return the loss
"""
self.model = model.to(args.device)
self.args = args
self.data_collator = data_collator if data_collator is not None else default_data_collator
@@ -210,6 +235,9 @@ class Trainer:
)
def get_train_dataloader(self) -> DataLoader:
"""
Returns the training :class:`~torch.utils.data.DataLoader`.
"""
if self.train_dataset is None:
raise ValueError("Trainer: training requires a train_dataset.")
if is_torch_tpu_available():
@@ -232,6 +260,13 @@ class Trainer:
return data_loader
def get_eval_dataloader(self, eval_dataset: Optional[Dataset] = None) -> DataLoader:
"""
Returns the evaluation :class:`~torch.utils.data.DataLoader`.
Args:
eval_dataset (:obj:`Dataset`, `optional`):
If provided, will override `self.eval_dataset`.
"""
if eval_dataset is None and self.eval_dataset is None:
raise ValueError("Trainer: evaluation requires an eval_dataset.")
@@ -257,6 +292,12 @@ class Trainer:
return data_loader
def get_test_dataloader(self, test_dataset: Dataset) -> DataLoader:
"""
Returns the test :class:`~torch.utils.data.DataLoader`.
Args:
test_dataset (obj:`Dataset`): The test dataset to use.
"""
# We use the same batch_size as for eval.
if is_torch_tpu_available():
sampler = SequentialDistributedSampler(
@@ -283,9 +324,8 @@ class Trainer:
"""
Setup the optimizer and the learning rate scheduler.
We provide a reasonable default that works well.
If you want to use something else, you can pass a tuple in the Trainer's init,
or override this method in a subclass.
We provide a reasonable default that works well. If you want to use something else, you can pass a tuple in the
Trainer's init through :obj:`optimizers`, or override this method in a subclass.
"""
if self.optimizers is not None:
return self.optimizers
@@ -336,7 +376,7 @@ class Trainer:
def num_examples(self, dataloader: DataLoader) -> int:
"""
Helper to get num of examples from a DataLoader, by accessing its Dataset.
Helper to get number of samples in a :class:`~torch.utils.data.DataLoader` by accessing its Dataset.
"""
return len(dataloader.dataset)
@@ -345,9 +385,9 @@ class Trainer:
Main training entry point.
Args:
model_path:
(Optional) Local path to model if model to train has been instantiated from a local path
If present, we will try reloading the optimizer/scheduler states from there.
model_path (:obj:`str`, `optional`):
Local path to the model if the model to train has been instantiated from a local path. If present,
training will resume from the optimizer/scheduler states loaded here.
"""
train_dataloader = self.get_train_dataloader()
if self.args.max_steps > 0:
@@ -611,8 +651,7 @@ class Trainer:
def save_model(self, output_dir: Optional[str] = None):
"""
Saving best-practices: if you use default names for the model,
you can reload it using from_pretrained().
Will save the model, so you can reload it using :obj:`from_pretrained()`.
Will only save from the world_master process (unless in TPUs).
"""
@@ -683,22 +722,18 @@ class Trainer:
logger.info("Deleting older checkpoint [{}] due to args.save_total_limit".format(checkpoint))
shutil.rmtree(checkpoint)
def evaluate(
self, eval_dataset: Optional[Dataset] = None, prediction_loss_only: Optional[bool] = None,
) -> Dict[str, float]:
def evaluate(self, eval_dataset: Optional[Dataset] = None) -> Dict[str, float]:
"""
Run evaluation and return metrics.
Run evaluation and returns metrics.
The calling script will be responsible for providing a method to compute metrics, as they are
task-dependent.
task-dependent (pass it to the init :obj:`compute_metrics` argument).
Args:
eval_dataset: (Optional) Pass a dataset if you wish to override
the one on the instance.
eval_dataset (:obj:`Dataset`, `optional`):
Pass a dataset if you wish to override :obj:`self.eval_dataset`.
Returns:
A dict containing:
- the eval loss
- the potential metrics computed from the predictions
A dictionary containing the evaluation loss and the potential metrics computed from the predictions.
"""
eval_dataloader = self.get_eval_dataloader(eval_dataset)
@@ -714,10 +749,22 @@ class Trainer:
def predict(self, test_dataset: Dataset) -> PredictionOutput:
"""
Run prediction and return predictions and potential metrics.
Run prediction and returns predictions and potential metrics.
Depending on the dataset and your use case, your test dataset may contain labels.
In that case, this method will also return metrics, like in evaluate().
In that case, this method will also return metrics, like in :obj:`evaluate()`.
Args:
test_dataset (:obj:`Dataset`):
Dataset to run the predictions on.
Returns:
`NamedTuple`:
predictions (:obj:`np.ndarray`):
The predictions on :obj:`test_dataset`.
label_ids (:obj:`np.ndarray`, `optional`):
The labels (if the dataset contained some).
metrics (:obj:`Dict[str, float]`, `optional`):
The potential dictionary of metrics (if the dataset contained labels).
"""
test_dataloader = self.get_test_dataloader(test_dataset)

84
src/transformers/trainer_tf.py
View File

@@ -29,6 +29,34 @@ def set_seed(seed: int):
class TFTrainer:
"""
TFTrainer is a simple but feature-complete training and eval loop for TensorFlow,
optimized for 🤗 Transformers.
Args:
model (:class:`~transformers.TFPreTrainedModel`):
The model to train, evaluate or use for predictions.
args (:class:`~transformers.TFTrainingArguments`):
The arguments to tweak training.
train_dataset (:class:`~tf.data.Dataset`, `optional`):
The dataset to use for training.
eval_dataset (:class:`~tf.data.Dataset`, `optional`):
The dataset to use for evaluation.
compute_metrics (:obj:`Callable[[EvalPrediction], Dict]`, `optional`):
The function that will be used to compute metrics at evaluation. Must take a
:class:`~transformers.EvalPrediction` and return a dictionary string to metric values.
prediction_loss_only (:obj:`bool`, `optional`, defaults to `False`):
When performing evaluation and predictions, only returns the loss.
tb_writer (:obj:`tf.summary.SummaryWriter`, `optional`):
Object to write to TensorBoard.
optimizers (:obj:`Tuple[tf.keras.optimizers.Optimizer, tf.keras.optimizers.schedules.LearningRateSchedule]`, `optional`):
A tuple containing the optimizer and the scheduler to use. The optimizer default to an instance of
:class:`tf.keras.optimizers.Adam` if :obj:`args.weight_decay_rate` is 0 else an instance of
:class:`~transformers.AdamWeightDecay`. The scheduler will default to an instance of
:class:`tf.keras.optimizers.schedules.PolynomialDecay` if :obj:`args.num_warmup_steps` is 0 else
an instance of :class:`~transformers.WarmUp`.
"""
model: TFPreTrainedModel
args: TFTrainingArguments
train_dataset: Optional[tf.data.Dataset]
@@ -78,6 +106,9 @@ class TFTrainer:
set_seed(self.args.seed)
def get_train_tfdataset(self) -> tf.data.Dataset:
"""
Returns the training :class:`~tf.data.Dataset`.
"""
if self.train_dataset is None:
raise ValueError("Trainer: training requires a train_dataset.")
@@ -101,6 +132,13 @@ class TFTrainer:
return self.args.strategy.experimental_distribute_dataset(ds)
def get_eval_tfdataset(self, eval_dataset: Optional[tf.data.Dataset] = None) -> tf.data.Dataset:
"""
Returns the evaluation :class:`~tf.data.Dataset`.
Args:
eval_dataset (:class:`~tf.data.Dataset`, `optional`):
If provided, will override `self.eval_dataset`.
"""
if eval_dataset is None and self.eval_dataset is None:
raise ValueError("Trainer: evaluation requires an eval_dataset.")
@@ -114,6 +152,12 @@ class TFTrainer:
return self.args.strategy.experimental_distribute_dataset(ds)
def get_test_tfdataset(self, test_dataset: tf.data.Dataset) -> tf.data.Dataset:
"""
Returns a test :class:`~tf.data.Dataset`.
Args:
test_dataset (:class:`~tf.data.Dataset`): The dataset to use.
"""
ds = test_dataset.batch(self.args.eval_batch_size, drop_remainder=self.args.dataloader_drop_last)
return self.args.strategy.experimental_distribute_dataset(ds)
@@ -124,9 +168,8 @@ class TFTrainer:
"""
Setup the optimizer and the learning rate scheduler.
We provide a reasonable default that works well.
If you want to use something else, you can pass a tuple in the Trainer's init,
or override this method in a subclass.
We provide a reasonable default that works well. If you want to use something else, you can pass a tuple in the
TFTrainer's init through :obj:`optimizers`, or override this method in a subclass.
"""
if self.optimizers is not None:
return self.optimizers
@@ -263,11 +306,18 @@ class TFTrainer:
logger.info(output)
def evaluate(
self, eval_dataset: Optional[tf.data.Dataset] = None, prediction_loss_only: Optional[bool] = None
) -> Dict[str, float]:
def evaluate(self, eval_dataset: Optional[tf.data.Dataset] = None) -> Dict[str, float]:
"""
Prediction/evaluation loop, shared by `evaluate()` and `predict()`.
Run evaluation and returns metrics.
The calling script will be responsible for providing a method to compute metrics, as they are
task-dependent (pass it to the init :obj:`compute_metrics` argument).
Args:
eval_dataset (:class:`~tf.data.Dataset`, `optional`):
Pass a dataset if you wish to override :obj:`self.eval_dataset`.
Returns:
A dictionary containing the evaluation loss and the potential metrics computed from the predictions.
"""
eval_ds = self.get_eval_tfdataset(eval_dataset)
@@ -478,12 +528,22 @@ class TFTrainer:
def predict(self, test_dataset: tf.data.Dataset) -> PredictionOutput:
"""
Run prediction and return predictions and potential metrics.
Run prediction and returns predictions and potential metrics.
Depending on the dataset and your use case, your test dataset may contain labels.
In that case, this method will also return metrics, like in evaluate().
In that case, this method will also return metrics, like in :obj:`evaluate()`.
Args:
test_dataset: something similar to a PT Dataset. This is just
temporary before to have a framework-agnostic approach for datasets.
test_dataset (:class:`~tf.data.Dataset`):
Dataset to run the predictions on.
Returns:
`NamedTuple`:
predictions (:obj:`np.ndarray`):
The predictions on :obj:`test_dataset`.
label_ids (:obj:`np.ndarray`, `optional`):
The labels (if the dataset contained some).
metrics (:obj:`Dict[str, float]`, `optional`):
The potential dictionary of metrics (if the dataset contained labels).
"""
test_ds = self.get_test_tfdataset(test_dataset)
@@ -491,7 +551,7 @@ class TFTrainer:
def save_model(self, output_dir: Optional[str] = None):
"""
Save the pretrained model.
Will save the model, so you can reload it using :obj:`from_pretrained()`.
"""
output_dir = output_dir if output_dir is not None else self.args.output_dir

7
src/transformers/trainer_utils.py
View File

@@ -23,8 +23,11 @@ def is_wandb_available():
class EvalPrediction(NamedTuple):
"""
Evaluation output (always contains labels), to be used
to compute metrics.
Evaluation output (always contains labels), to be used to compute metrics.
Parameters:
predictions (:obj:`np.ndarray`): Predictions of the model.
label_ids (:obj:`np.ndarray`): Targets to be matched.
"""
predictions: np.ndarray

86
src/transformers/training_args.py
View File

@@ -35,9 +35,73 @@ class TrainingArguments:
TrainingArguments is the subset of the arguments we use in our example scripts
**which relate to the training loop itself**.
Using `HfArgumentParser` we can turn this class
into argparse arguments to be able to specify them on
the command line.
Using :class:`~transformers.HfArgumentParser` we can turn this class
into argparse arguments to be able to specify them on the command line.
Parameters:
output_dir (:obj:`str`):
The output directory where the model predictions and checkpoints will be written.
overwrite_output_dir (:obj:`bool`, `optional`, defaults to :obj:`False`):
If :obj:`True`, overwrite the content of the output directory. Use this to continue training if
:obj:`output_dir` points to a checkpoint directory.
do_train (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to run training or not.
do_eval (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to run evaluation on the dev set or not.
do_predict (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to run predictions on the test set or not.
evaluate_during_training (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to run evaluation during training at each logging step or not.
per_device_train_batch_size (:obj:`int`, `optional`, defaults to 8):
The batch size per GPU/TPU core/CPU for training.
per_device_eval_batch_size (:obj:`int`, `optional`, defaults to 8):
The batch size per GPU/TPU core/CPU for evaluation.
gradient_accumulation_steps: (:obj:`int`, `optional`, defaults to 1):
Number of updates steps to accumulate the gradients for, before performing a backward/update pass.
learning_rate (:obj:`float`, `optional`, defaults to 5e-5):
The initial learning rate for Adam.
weight_decay (:obj:`float`, `optional`, defaults to 0):
The weight decay to apply (if not zero).
adam_epsilon (:obj:`float`, `optional`, defaults to 1e-8):
Epsilon for the Adam optimizer.
max_grad_norm (:obj:`float`, `optional`, defaults to 1.0):
Maximum gradient norm (for gradient clipping).
num_train_epochs(:obj:`float`, `optional`, defaults to 3.0):
Total number of training epochs to perform.
max_steps (:obj:`int`, `optional`, defaults to -1):
If set to a positive number, the total number of training steps to perform. Overrides
:obj:`num_train_epochs`.
warmup_steps (:obj:`int`, `optional`, defaults to 0):
Number of steps used for a linear warmup from 0 to :obj:`learning_rate`.
logging_dir (:obj:`str`, `optional`):
Tensorboard log directory. Will default to `runs/**CURRENT_DATETIME_HOSTNAME**`.
logging_first_step (:obj:`bool`, `optional`, defaults to :obj:`False`):
Wheter to log and evalulate the first :obj:`global_step` or not.
logging_steps (:obj:`int`, `optional`, defaults to 500):
Number of update steps between two logs.
save_steps (:obj:`int`, `optional`, defaults to 500):
Number of updates steps before two checkpoint saves.
save_total_limit (:obj:`int`, `optional`):
If a value is passed, will limit the total amount of checkpoints. Deletes the older checkpoints in
:obj:`output_dir`.
no_cuda (:obj:`bool`, `optional`, defaults to :obj:`False`):
Wherher to not use CUDA even when it is available or not.
seed (:obj:`int`, `optional`, defaults to 42):
Random seed for initialization.
fp16 (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to use 16-bit (mixed) precision training (through NVIDIA apex) instead of 32-bit training.
fp16_opt_level (:obj:`str`, `optional`, defaults to 'O1'):
For :obj:`fp16` training, apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']. See details
on the `apex documentation <https://nvidia.github.io/apex/amp.html>`__.
local_rank (:obj:`int`, `optional`, defaults to -1):
During distributed training, the rank of the process.
tpu_num_cores (:obj:`int`, `optional`):
When training on TPU, the mumber of TPU cores (automatically passed by launcher script).
tpu_metrics_debug (:obj:`bool`, `optional`, defaults to :obj:`False`):
When training on TPU, whether to print debug metrics or not.
dataloader_drop_last (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to drop the last incomplete batch (if the length of the dataset is not divisible by the batch size)
or not.
"""
output_dir: str = field(
@@ -141,6 +205,9 @@ class TrainingArguments:
@property
def train_batch_size(self) -> int:
"""
The actual batch size for training (may differ from :obj:`per_gpu_train_batch_size` in distributed training).
"""
if self.per_gpu_train_batch_size:
logger.warning(
"Using deprecated `--per_gpu_train_batch_size` argument which will be removed in a future "
@@ -151,6 +218,9 @@ class TrainingArguments:
@property
def eval_batch_size(self) -> int:
"""
The actual batch size for evaluation (may differ from :obj:`per_gpu_eval_batch_size` in distributed training).
"""
if self.per_gpu_eval_batch_size:
logger.warning(
"Using deprecated `--per_gpu_eval_batch_size` argument which will be removed in a future "
@@ -193,11 +263,21 @@ class TrainingArguments:
@property
@torch_required
def device(self) -> "torch.device":
"""
The device used by this process.
"""
return self._setup_devices[0]
@property
@torch_required
def n_gpu(self):
"""
The number of GPUs used by this process.
Note:
This will only be greater than one when you have multiple GPUs available but are not using distributed
training. For distributed training, it will always be 1.
"""
return self._setup_devices[1]
def to_json_string(self):

85
src/transformers/training_args_tf.py
View File

@@ -14,6 +14,85 @@ if is_tf_available():
@dataclass
class TFTrainingArguments(TrainingArguments):
"""
TrainingArguments is the subset of the arguments we use in our example scripts
**which relate to the training loop itself**.
Using :class:`~transformers.HfArgumentParser` we can turn this class
into argparse arguments to be able to specify them on the command line.
Parameters:
output_dir (:obj:`str`):
The output directory where the model predictions and checkpoints will be written.
overwrite_output_dir (:obj:`bool`, `optional`, defaults to :obj:`False`):
If :obj:`True`, overwrite the content of the output directory. Use this to continue training if
:obj:`output_dir` points to a checkpoint directory.
do_train (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to run training or not.
do_eval (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to run evaluation on the dev set or not.
do_predict (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to run predictions on the test set or not.
evaluate_during_training (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to run evaluation during training at each logging step or not.
per_device_train_batch_size (:obj:`int`, `optional`, defaults to 8):
The batch size per GPU/TPU core/CPU for training.
per_device_eval_batch_size (:obj:`int`, `optional`, defaults to 8):
The batch size per GPU/TPU core/CPU for evaluation.
gradient_accumulation_steps: (:obj:`int`, `optional`, defaults to 1):
Number of updates steps to accumulate the gradients for, before performing a backward/update pass.
learning_rate (:obj:`float`, `optional`, defaults to 5e-5):
The initial learning rate for Adam.
weight_decay (:obj:`float`, `optional`, defaults to 0):
The weight decay to apply (if not zero).
adam_epsilon (:obj:`float`, `optional`, defaults to 1e-8):
Epsilon for the Adam optimizer.
max_grad_norm (:obj:`float`, `optional`, defaults to 1.0):
Maximum gradient norm (for gradient clipping).
num_train_epochs(:obj:`float`, `optional`, defaults to 3.0):
Total number of training epochs to perform.
max_steps (:obj:`int`, `optional`, defaults to -1):
If set to a positive number, the total number of training steps to perform. Overrides
:obj:`num_train_epochs`.
warmup_steps (:obj:`int`, `optional`, defaults to 0):
Number of steps used for a linear warmup from 0 to :obj:`learning_rate`.
logging_dir (:obj:`str`, `optional`):
Tensorboard log directory. Will default to `runs/**CURRENT_DATETIME_HOSTNAME**`.
logging_first_step (:obj:`bool`, `optional`, defaults to :obj:`False`):
Wheter to log and evalulate the first :obj:`global_step` or not.
logging_steps (:obj:`int`, `optional`, defaults to 500):
Number of update steps between two logs.
save_steps (:obj:`int`, `optional`, defaults to 500):
Number of updates steps before two checkpoint saves.
save_total_limit (:obj:`int`, `optional`):
If a value is passed, will limit the total amount of checkpoints. Deletes the older checkpoints in
:obj:`output_dir`.
no_cuda (:obj:`bool`, `optional`, defaults to :obj:`False`):
Wherher to not use CUDA even when it is available or not.
seed (:obj:`int`, `optional`, defaults to 42):
Random seed for initialization.
fp16 (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to use 16-bit (mixed) precision training (through NVIDIA apex) instead of 32-bit training.
fp16_opt_level (:obj:`str`, `optional`, defaults to 'O1'):
For :obj:`fp16` training, apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']. See details
on the `apex documentation <https://nvidia.github.io/apex/amp.html>`__.
local_rank (:obj:`int`, `optional`, defaults to -1):
During distributed training, the rank of the process.
tpu_num_cores (:obj:`int`, `optional`):
When training on TPU, the mumber of TPU cores (automatically passed by launcher script).
tpu_metrics_debug (:obj:`bool`, `optional`, defaults to :obj:`False`):
When training on TPU, whether to print debug metrics or not.
dataloader_drop_last (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to drop the last incomplete batch (if the length of the dataset is not divisible by the batch size)
or not.
tpu_name (:obj:`str`, `optional`):
The name of the TPU the process is running on.
eval_steps (:obj:`int`, `optional`, defaults to 1000):
Number of update steps before two evaluations.
debug (:obj:`bool`, `optional`, defaults to :obj:`False`):
Wheter to activate the trace to record computation graphs and profiling information or not.
"""
tpu_name: str = field(
default=None, metadata={"help": "Name of TPU"},
)
@@ -59,9 +138,15 @@ class TFTrainingArguments(TrainingArguments):
@property
@tf_required
def strategy(self) -> "tf.distribute.Strategy":
"""
The strategy used for distributed training.
"""
return self._setup_strategy
@property
@tf_required
def n_gpu(self) -> int:
"""
The number of replicas (GPUs or TPU cores) used in this training.
"""
return self._setup_strategy.num_replicas_in_sync