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

Black preview (#17217)

Browse Source 
* Black preview

* Fixup too!

* Fix check copies

* Use the same version as the CI

* Bump black
This commit is contained in:
Sylvain Gugger
2022-05-12 16:25:55 -04:00
committed by GitHub
parent 9bd67ac7bb
commit afe5d42d8d
578 changed files with 8274 additions and 3296 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
examples/pytorch/language-modeling/run_clm.py
View File

@@ -73,8 +73,9 @@ class ModelArguments:
model_name_or_path: Optional[str] = field(
default=None,
metadata={
"help": "The model checkpoint for weights initialization."
"Don't set if you want to train a model from scratch."
"help": (
"The model checkpoint for weights initialization.Don't set if you want to train a model from scratch."
)
},
)
model_type: Optional[str] = field(
@@ -84,8 +85,10 @@ class ModelArguments:
config_overrides: Optional[str] = field(
default=None,
metadata={
"help": "Override some existing default config settings when a model is trained from scratch. Example: "
"n_embd=10,resid_pdrop=0.2,scale_attn_weights=false,summary_type=cls_index"
"help": (
"Override some existing default config settings when a model is trained from scratch. Example: "
"n_embd=10,resid_pdrop=0.2,scale_attn_weights=false,summary_type=cls_index"
)
},
)
config_name: Optional[str] = field(
@@ -109,8 +112,10 @@ class ModelArguments:
use_auth_token: bool = field(
default=False,
metadata={
"help": "Will use the token generated when running `transformers-cli login` (necessary to use this script "
"with private models)."
"help": (
"Will use the token generated when running `transformers-cli login` (necessary to use this script "
"with private models)."
)
},
)
@@ -141,24 +146,30 @@ class DataTrainingArguments:
max_train_samples: Optional[int] = field(
default=None,
metadata={
"help": "For debugging purposes or quicker training, truncate the number of training examples to this "
"value if set."
"help": (
"For debugging purposes or quicker training, truncate the number of training examples to this "
"value if set."
)
},
)
max_eval_samples: Optional[int] = field(
default=None,
metadata={
"help": "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
"value if set."
"help": (
"For debugging purposes or quicker training, truncate the number of evaluation examples to this "
"value if set."
)
},
)
block_size: Optional[int] = field(
default=None,
metadata={
"help": "Optional input sequence length after tokenization. "
"The training dataset will be truncated in block of this size for training. "
"Default to the model max input length for single sentence inputs (take into account special tokens)."
"help": (
"Optional input sequence length after tokenization. "
"The training dataset will be truncated in block of this size for training. "
"Default to the model max input length for single sentence inputs (take into account special tokens)."
)
},
)
overwrite_cache: bool = field(
@@ -390,7 +401,8 @@ def main():
# clm input could be much much longer than block_size
if "Token indices sequence length is longer than the" in cl.out:
tok_logger.warning(
"^^^^^^^^^^^^^^^^ Please ignore the warning above - this long input will be chunked into smaller bits before being passed to the model."
"^^^^^^^^^^^^^^^^ Please ignore the warning above - this long input will be chunked into smaller bits"
" before being passed to the model."
)
return output

6
examples/pytorch/language-modeling/run_clm_no_trainer.py
View File

@@ -168,7 +168,11 @@ def parse_args():
"--block_size",
type=int,
default=None,
help="Optional input sequence length after tokenization. The training dataset will be truncated in block of this size for training. Default to the model max input length for single sentence inputs (take into account special tokens).",
help=(
"Optional input sequence length after tokenization. The training dataset will be truncated in block of"
" this size for training. Default to the model max input length for single sentence inputs (take into"
" account special tokens)."
),
)
parser.add_argument(
"--preprocessing_num_workers",

41
examples/pytorch/language-modeling/run_mlm.py
View File

@@ -70,8 +70,9 @@ class ModelArguments:
model_name_or_path: Optional[str] = field(
default=None,
metadata={
"help": "The model checkpoint for weights initialization."
"Don't set if you want to train a model from scratch."
"help": (
"The model checkpoint for weights initialization.Don't set if you want to train a model from scratch."
)
},
)
model_type: Optional[str] = field(
@@ -81,8 +82,10 @@ class ModelArguments:
config_overrides: Optional[str] = field(
default=None,
metadata={
"help": "Override some existing default config settings when a model is trained from scratch. Example: "
"n_embd=10,resid_pdrop=0.2,scale_attn_weights=false,summary_type=cls_index"
"help": (
"Override some existing default config settings when a model is trained from scratch. Example: "
"n_embd=10,resid_pdrop=0.2,scale_attn_weights=false,summary_type=cls_index"
)
},
)
config_name: Optional[str] = field(
@@ -106,8 +109,10 @@ class ModelArguments:
use_auth_token: bool = field(
default=False,
metadata={
"help": "Will use the token generated when running `transformers-cli login` (necessary to use this script "
"with private models)."
"help": (
"Will use the token generated when running `transformers-cli login` (necessary to use this script "
"with private models)."
)
},
)
@@ -147,8 +152,10 @@ class DataTrainingArguments:
max_seq_length: Optional[int] = field(
default=None,
metadata={
"help": "The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated."
"help": (
"The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated."
)
},
)
preprocessing_num_workers: Optional[int] = field(
@@ -165,22 +172,28 @@ class DataTrainingArguments:
pad_to_max_length: bool = field(
default=False,
metadata={
"help": "Whether to pad all samples to `max_seq_length`. "
"If False, will pad the samples dynamically when batching to the maximum length in the batch."
"help": (
"Whether to pad all samples to `max_seq_length`. "
"If False, will pad the samples dynamically when batching to the maximum length in the batch."
)
},
)
max_train_samples: Optional[int] = field(
default=None,
metadata={
"help": "For debugging purposes or quicker training, truncate the number of training examples to this "
"value if set."
"help": (
"For debugging purposes or quicker training, truncate the number of training examples to this "
"value if set."
)
},
)
max_eval_samples: Optional[int] = field(
default=None,
metadata={
"help": "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
"value if set."
"help": (
"For debugging purposes or quicker training, truncate the number of evaluation examples to this "
"value if set."
)
},
)

4
examples/pytorch/language-modeling/run_mlm_no_trainer.py
View File

@@ -171,7 +171,9 @@ def parse_args():
"--max_seq_length",
type=int,
default=None,
help="The maximum total input sequence length after tokenization. Sequences longer than this will be truncated.",
help=(
"The maximum total input sequence length after tokenization. Sequences longer than this will be truncated."
),
)
parser.add_argument(
"--line_by_line",

47
examples/pytorch/language-modeling/run_plm.py
View File

@@ -63,8 +63,9 @@ class ModelArguments:
model_name_or_path: Optional[str] = field(
default=None,
metadata={
"help": "The model checkpoint for weights initialization."
"Don't set if you want to train a model from scratch."
"help": (
"The model checkpoint for weights initialization.Don't set if you want to train a model from scratch."
)
},
)
config_name: Optional[str] = field(
@@ -73,8 +74,10 @@ class ModelArguments:
config_overrides: Optional[str] = field(
default=None,
metadata={
"help": "Override some existing default config settings when a model is trained from scratch. Example: "
"n_embd=10,resid_pdrop=0.2,scale_attn_weights=false,summary_type=cls_index"
"help": (
"Override some existing default config settings when a model is trained from scratch. Example: "
"n_embd=10,resid_pdrop=0.2,scale_attn_weights=false,summary_type=cls_index"
)
},
)
tokenizer_name: Optional[str] = field(
@@ -95,8 +98,10 @@ class ModelArguments:
use_auth_token: bool = field(
default=False,
metadata={
"help": "Will use the token generated when running `transformers-cli login` (necessary to use this script "
"with private models)."
"help": (
"Will use the token generated when running `transformers-cli login` (necessary to use this script "
"with private models)."
)
},
)
@@ -136,8 +141,10 @@ class DataTrainingArguments:
max_seq_length: int = field(
default=512,
metadata={
"help": "The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated."
"help": (
"The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated."
)
},
)
preprocessing_num_workers: Optional[int] = field(
@@ -147,8 +154,10 @@ class DataTrainingArguments:
plm_probability: float = field(
default=1 / 6,
metadata={
"help": "Ratio of length of a span of masked tokens to surrounding context length for "
"permutation language modeling."
"help": (
"Ratio of length of a span of masked tokens to surrounding context length for "
"permutation language modeling."
)
},
)
max_span_length: int = field(
@@ -161,22 +170,28 @@ class DataTrainingArguments:
pad_to_max_length: bool = field(
default=False,
metadata={
"help": "Whether to pad all samples to `max_seq_length`. "
"If False, will pad the samples dynamically when batching to the maximum length in the batch."
"help": (
"Whether to pad all samples to `max_seq_length`. "
"If False, will pad the samples dynamically when batching to the maximum length in the batch."
)
},
)
max_train_samples: Optional[int] = field(
default=None,
metadata={
"help": "For debugging purposes or quicker training, truncate the number of training examples to this "
"value if set."
"help": (
"For debugging purposes or quicker training, truncate the number of training examples to this "
"value if set."
)
},
)
max_eval_samples: Optional[int] = field(
default=None,
metadata={
"help": "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
"value if set."
"help": (
"For debugging purposes or quicker training, truncate the number of evaluation examples to this "
"value if set."
)
},
)