updated examples/pytorch/language-modeling scripts and requirements.txt to...

updated examples/pytorch/language-modeling scripts and requirements.txt to require datasets>=2.14.0 (#30120)

updated requirements.txt and require_version() calls in examples/pytorch/language-modeling to require datasets>=2.14.0

examples/pytorch/language-modeling/requirements.txt

 accelerate >= 0.12.0
 torch >= 1.3
-datasets >= 1.8.0
+datasets >= 2.14.0
 sentencepiece != 0.1.92
 protobuf
 evaluate

examples/pytorch/language-modeling/run_clm.py

@@ -58,7 +58,7 @@ from transformers.utils.versions import require_version
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
 check_min_version("4.40.0.dev0")
 
-require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
+require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 
 logger = logging.getLogger(__name__)
 

examples/pytorch/language-modeling/run_clm_no_trainer.py

@@ -61,7 +61,7 @@ check_min_version("4.40.0.dev0")
 
 logger = get_logger(__name__)
 
-require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
+require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 
 MODEL_CONFIG_CLASSES = list(MODEL_MAPPING.keys())
 MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)

examples/pytorch/language-modeling/run_fim.py

@@ -60,7 +60,7 @@ from transformers.utils.versions import require_version
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
 check_min_version("4.40.0.dev0")
 
-require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
+require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 
 logger = logging.getLogger(__name__)
 

examples/pytorch/language-modeling/run_fim_no_trainer.py

@@ -64,7 +64,7 @@ check_min_version("4.40.0.dev0")
 
 logger = get_logger(__name__)
 
-require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
+require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 
 MODEL_CONFIG_CLASSES = list(MODEL_MAPPING.keys())
 MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)

examples/pytorch/language-modeling/run_mlm.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
 check_min_version("4.40.0.dev0")
 
-require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
+require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 
 logger = logging.getLogger(__name__)
 MODEL_CONFIG_CLASSES = list(MODEL_FOR_MASKED_LM_MAPPING.keys())

examples/pytorch/language-modeling/run_mlm_no_trainer.py

@@ -60,7 +60,7 @@ from transformers.utils.versions import require_version
 check_min_version("4.40.0.dev0")
 
 logger = get_logger(__name__)
-require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
+require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 MODEL_CONFIG_CLASSES = list(MODEL_MAPPING.keys())
 MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
 

examples/pytorch/language-modeling/run_plm.py

@@ -50,7 +50,7 @@ from transformers.utils.versions import require_version
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
 check_min_version("4.40.0.dev0")
 
-require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
+require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 
 logger = logging.getLogger(__name__)