def add_model_specific_args(parser, root_dir):
# Add NER specific options
BaseTransformer.add_model_specific_args(parser, root_dir)
parser.add_argument(
"--max_seq_length",
default=128,
type=int,
help="The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded.",
)
parser.add_argument(
"--task", default="", type=str, required=True, help="The GLUE task to run",
)
parser.add_argument(
"--data_dir",
default=None,
type=str,
required=True,
help="The input data dir. Should contain the training files for the CoNLL-2003 NER task.",
)
parser.add_argument(
"--overwrite_cache", action="store_true", help="Overwrite the cached training and evaluation sets"
)
parser.add_argument(
"--tags", nargs='+', type=str, help="experiment tags for neptune.ai", default=['FT', 'last-layer']
)
return parser
def add_model_specific_args(parser, root_dir):
# Add NER specific options
BaseTransformer.add_model_specific_args(parser, root_dir)
parser.add_argument(
"--max_seq_length",
default=128,
type=int,
help="The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded.",
)
parser.add_argument(
"--task", default="", type=str, required=True, help="The GLUE task to run",
)
parser.add_argument(
"--data_dir",
default=None,
type=str,
required=True,
help="The input data dir. Should contain the training files for the CoNLL-2003 NER task.",
)
parser.add_argument(
"--overwrite_cache", action="store_true", help="Overwrite the cached training and evaluation sets"
)
# parser.add_argument("-n", "--n_gpu", nargs='+', type=int, default=[2], help="specified device number")
# parser.add_argument('-a', '--arg', nargs='+', type=int, default=[1, 2, 3])
parser.add_argument(
"--vocab_file", default="th_wiki_bpe/th.wiki.bpe.op25000.vocab", type=str, help="vocab_file",
)
parser.add_argument(
"--spm_file", default="th_wiki_bpe/th.wiki.bpe.op25000.model", type=str, help="Tspm_file",
)
return parser
def add_model_specific_args(parser, root_dir):
# Add NER specific options
BaseTransformer.add_model_specific_args(parser, root_dir)
parser.add_argument(
"--max_seq_length",
default=128,
type=int,
help=
"The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded.",
)
parser.add_argument(
"--labels",
default="",
type=str,
help=
"Path to a file containing all labels. If not specified, CoNLL-2003 labels are used.",
)
parser.add_argument(
"--data_dir",
default=None,
type=str,
required=True,
help=
"The input data dir. Should contain the training files for the CoNLL-2003 NER task.",
)
parser.add_argument(
"--overwrite_cache",
action="store_true",
help="Overwrite the cached training and evaluation sets")
return parser
def add_model_specific_args(parser, root_dir):
BaseTransformer.add_model_specific_args(parser, root_dir)
# Add BART specific options
parser.add_argument(
"--max_source_length",
default=1024,
type=int,
help="The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded.",
)
parser.add_argument(
"--max_target_length",
default=56,
type=int,
help="The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded.",
)
parser.add_argument(
"--data_dir",
default=None,
type=str,
required=True,
help="The input data dir. Should contain the dataset files for the CNN/DM summarization task.",
)
return parser
def add_model_specific_args(parser, root_dir):
BaseTransformer.add_model_specific_args(parser, root_dir)
# Add BART specific options
parser.add_argument(
"--max_seq_length",
default=50,
type=int,
help=
"The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded.",
)
parser.add_argument(
"--data_dir",
default=None,
type=str,
required=True,
help=
"The input data dir. Should contain the dataset files for the CNN/DM summarization task.",
)
parser.add_argument(
'--model_state',
type=Path,
help="Specify a .ckpt file to start training from that state."
" Note: This not designed for resuming training from checkpoint but for doing pretraining/curriculum learning"
)
return parser