riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-01 18:51:14 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Improve training args (#25401)

Browse Source 
* enhanced tips for some training args

* make style
This commit is contained in:
Alan Ji 2023-08-09 19:50:13 +08:00 committed by GitHub
parent 3deed1f97e
commit 00b93cda21
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/transformers/training_args.py
View File

@ -193,9 +193,9 @@ class TrainingArguments:
prediction_loss_only (`bool`, *optional*, defaults to `False`): prediction_loss_only (`bool`, *optional*, defaults to `False`):
When performing evaluation and generating predictions, only returns the loss. When performing evaluation and generating predictions, only returns the loss.
per_device_train_batch_size (`int`, *optional*, defaults to 8): per_device_train_batch_size (`int`, *optional*, defaults to 8):
The batch size per GPU/TPU core/CPU for training. The batch size per GPU/TPU/MPS/NPU core/CPU for training.
per_device_eval_batch_size (`int`, *optional*, defaults to 8): per_device_eval_batch_size (`int`, *optional*, defaults to 8):
The batch size per GPU/TPU core/CPU for evaluation. The batch size per GPU/TPU/MPS/NPU core/CPU for evaluation.
gradient_accumulation_steps (`int`, *optional*, defaults to 1): gradient_accumulation_steps (`int`, *optional*, defaults to 1):
Number of updates steps to accumulate the gradients for, before performing a backward/update pass. Number of updates steps to accumulate the gradients for, before performing a backward/update pass.
@ -648,10 +648,10 @@ class TrainingArguments:
) )
per_device_train_batch_size: int = field( per_device_train_batch_size: int = field(
default=8, metadata={"help": "Batch size per GPU/TPU core/CPU for training."} default=8, metadata={"help": "Batch size per GPU/TPU/MPS/NPU core/CPU for training."}
) )
per_device_eval_batch_size: int = field( per_device_eval_batch_size: int = field(
default=8, metadata={"help": "Batch size per GPU/TPU core/CPU for evaluation."} default=8, metadata={"help": "Batch size per GPU/TPU/MPS/NPU core/CPU for evaluation."}
) )
per_gpu_train_batch_size: Optional[int] = field( per_gpu_train_batch_size: Optional[int] = field(
@ -804,7 +804,9 @@ class TrainingArguments:
) )
use_cpu: bool = field( use_cpu: bool = field(
default=False, default=False,
metadata={"help": " Whether or not to use cpu. If set to False, we will use cuda or mps device if available."}, metadata={
"help": " Whether or not to use cpu. If set to False, we will use cuda/tpu/mps/npu device if available."
},
) )
use_mps_device: bool = field( use_mps_device: bool = field(
default=False, default=False,