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

39
examples/research_projects/jax-projects/model_parallel/run_clm_mp.py
View File

@@ -69,8 +69,9 @@ 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(
@@ -93,7 +94,10 @@ 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]`."
)
},
)
@@ -118,15 +122,19 @@ 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(
@@ -141,9 +149,11 @@ 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(
@@ -334,7 +344,8 @@ 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
@@ -606,7 +617,8 @@ 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 = []
@@ -632,7 +644,8 @@ def main():
eval_metrics["perplexity"] = float("inf")
logger.info(
f"Step... ({cur_step} | Eval loss: {eval_metrics['loss']} | Eval Perplexity: {eval_metrics['perplexity']}"
f"Step... ({cur_step} | Eval loss: {eval_metrics['loss']} | Eval Perplexity:"
f" {eval_metrics['perplexity']}"
)
if cur_step % training_args.save_steps == 0 and cur_step > 0: