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

47
examples/flax/language-modeling/run_clm_flax.py
View File

@@ -138,8 +138,9 @@ 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(
@@ -162,14 +163,19 @@ class ModelArguments:
dtype: Optional[str] = field(
default="float32",
metadata={
"help": "Floating-point format in which the model weights should be initialized and trained. Choose one of `[float32, float16, bfloat16]`."
"help": (
"Floating-point format in which the model weights should be initialized and trained. Choose one of"
" `[float32, float16, bfloat16]`."
)
},
)
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)."
)
},
)
@@ -194,15 +200,19 @@ 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."
)
},
)
overwrite_cache: bool = field(
@@ -217,9 +227,11 @@ class DataTrainingArguments:
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(
@@ -505,7 +517,8 @@ 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
@@ -735,7 +748,8 @@ def main():
write_train_metric(summary_writer, train_metrics, train_time, cur_step)
epochs.write(
f"Step... ({cur_step} | Loss: {train_metric['loss'].mean()}, Learning Rate: {train_metric['learning_rate'].mean()})"
f"Step... ({cur_step} | Loss: {train_metric['loss'].mean()}, Learning Rate:"
f" {train_metric['learning_rate'].mean()})"
)
train_metrics = []
@@ -762,7 +776,10 @@ def main():
eval_metrics["perplexity"] = float("inf")
# Print metrics and update progress bar
desc = f"Step... ({cur_step} | Eval Loss: {eval_metrics['loss']} | Eval Perplexity: {eval_metrics['perplexity']})"
desc = (
f"Step... ({cur_step} | Eval Loss: {eval_metrics['loss']} | Eval Perplexity:"
f" {eval_metrics['perplexity']})"
)
epochs.write(desc)
epochs.desc = desc

31
examples/flax/language-modeling/run_mlm_flax.py
View File

@@ -136,8 +136,9 @@ 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(
@@ -160,14 +161,19 @@ class ModelArguments:
dtype: Optional[str] = field(
default="float32",
metadata={
"help": "Floating-point format in which the model weights should be initialized and trained. Choose one of `[float32, float16, bfloat16]`."
"help": (
"Floating-point format in which the model weights should be initialized and trained. Choose one of"
" `[float32, float16, bfloat16]`."
)
},
)
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)."
)
},
)
@@ -209,8 +215,10 @@ 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. Default to the max input length of the model."
"help": (
"The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated. Default to the max input length of the model."
)
},
)
preprocessing_num_workers: Optional[int] = field(
@@ -223,8 +231,10 @@ 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."
)
},
)
line_by_line: bool = field(
@@ -764,7 +774,8 @@ def main():
write_train_metric(summary_writer, train_metrics, train_time, cur_step)
epochs.write(
f"Step... ({cur_step} | Loss: {train_metric['loss']}, Learning Rate: {train_metric['learning_rate']})"
f"Step... ({cur_step} | Loss: {train_metric['loss']}, Learning Rate:"
f" {train_metric['learning_rate']})"
)
train_metrics = []

30
examples/flax/language-modeling/run_t5_mlm_flax.py
View File

@@ -135,8 +135,9 @@ 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(
@@ -159,14 +160,19 @@ class ModelArguments:
dtype: Optional[str] = field(
default="float32",
metadata={
"help": "Floating-point format in which the model weights should be initialized and trained. Choose one of `[float32, float16, bfloat16]`."
"help": (
"Floating-point format in which the model weights should be initialized and trained. Choose one of"
" `[float32, float16, bfloat16]`."
)
},
)
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)."
)
},
)
@@ -208,7 +214,10 @@ class DataTrainingArguments:
max_seq_length: Optional[int] = field(
default=None,
metadata={
"help": "The maximum total input sequence length after tokenization and masking. Sequences longer than this will be truncated. Default to the max input length of the model."
"help": (
"The maximum total input sequence length after tokenization and masking. Sequences longer than this"
" will be truncated. Default to the max input length of the model."
)
},
)
preprocessing_num_workers: Optional[int] = field(
@@ -337,12 +346,14 @@ class FlaxDataCollatorForT5MLM:
if batch["input_ids"].shape[-1] != self.input_length:
raise ValueError(
f"`input_ids` are incorrectly preprocessed. `input_ids` length is {batch['input_ids'].shape[-1]}, but should be {self.target_length}."
f"`input_ids` are incorrectly preprocessed. `input_ids` length is {batch['input_ids'].shape[-1]}, but"
f" should be {self.target_length}."
)
if batch["labels"].shape[-1] != self.target_length:
raise ValueError(
f"`labels` are incorrectly preprocessed. `labels` length is {batch['labels'].shape[-1]}, but should be {self.target_length}."
f"`labels` are incorrectly preprocessed. `labels` length is {batch['labels'].shape[-1]}, but should be"
f" {self.target_length}."
)
# to check that tokens are correctly preprocessed, one can run `self.tokenizer.batch_decode(input_ids)` and `self.tokenizer.batch_decode(labels)` here...
@@ -884,7 +895,8 @@ def main():
write_train_metric(summary_writer, train_metrics, train_time, cur_step)
epochs.write(
f"Step... ({cur_step} | Loss: {train_metric['loss'].mean()}, Learning Rate: {train_metric['learning_rate'].mean()})"
f"Step... ({cur_step} | Loss: {train_metric['loss'].mean()}, Learning Rate:"
f" {train_metric['learning_rate'].mean()})"
)
train_metrics = []