in rag/finetune_rag.py [0:0]
def __init__(self, hparams, **kwargs):
# when loading from a pytorch lightning checkpoint, hparams are passed as dict
if isinstance(hparams, dict):
hparams = AttrDict(hparams)
if hparams.model_type == "rag_sequence":
self.model_class = RagSequenceForGeneration
elif hparams.model_type == "rag_token":
self.model_class = RagTokenForGeneration
elif hparams.model_type == "bart":
self.model_class = BartForConditionalGeneration
else:
self.model_class = T5ForConditionalGeneration
self.is_rag_model = is_rag_model(hparams.model_type)
config_class = RagConfig if self.is_rag_model else AutoConfig
config = config_class.from_pretrained(hparams.model_name_or_path)
# set retriever parameters
config.index_name = hparams.index_name or config.index_name
config.passages_path = hparams.passages_path or config.passages_path
config.index_path = hparams.index_path or config.index_path
config.use_dummy_dataset = hparams.use_dummy_dataset
# set extra_model_params for generator configs and load_model
extra_model_params = ("encoder_layerdrop", "decoder_layerdrop", "attention_dropout", "dropout")
if self.is_rag_model:
if hparams.prefix is not None:
config.generator.prefix = hparams.prefix
config.label_smoothing = hparams.label_smoothing
hparams, config.generator = set_extra_model_params(extra_model_params, hparams, config.generator)
if hparams.distributed_retriever == "pytorch":
retriever = RagPyTorchDistributedRetriever.from_pretrained(hparams.model_name_or_path, config=config)
elif hparams.distributed_retriever == "ray":
# The Ray retriever needs the handles to the retriever actors.
retriever = RagRayDistributedRetriever.from_pretrained(
hparams.model_name_or_path, hparams.actor_handles, config=config
)
model = self.model_class.from_pretrained(hparams.model_name_or_path, config=config, retriever=retriever)
prefix = config.question_encoder.prefix
else:
if hparams.prefix is not None:
config.prefix = hparams.prefix
hparams, config = set_extra_model_params(extra_model_params, hparams, config)
model = self.model_class.from_pretrained(hparams.model_name_or_path, config=config)
prefix = config.prefix
tokenizer = (
RagTokenizer.from_pretrained(hparams.model_name_or_path)
if self.is_rag_model
else AutoTokenizer.from_pretrained(hparams.model_name_or_path)
)
super().__init__(hparams, config=config, tokenizer=tokenizer, model=model)
save_git_info(self.hparams.output_dir)
self.output_dir = Path(self.hparams.output_dir)
self.metrics_save_path = Path(self.output_dir) / "metrics.json"
self.hparams_save_path = Path(self.output_dir) / "hparams.pkl"
pickle_save(self.hparams, self.hparams_save_path)
self.step_count = 0
self.metrics = defaultdict(list)
self.dataset_kwargs: dict = {
"data_dir": self.hparams.data_dir,
"max_source_length": self.hparams.max_source_length,
"prefix": prefix or "",
}
n_observations_per_split = {
"train": self.hparams.n_train,
"val": self.hparams.n_val,
"test": self.hparams.n_test,
}
self.n_obs = {k: v if v >= 0 else None for k, v in n_observations_per_split.items()}
self.target_lens = {
"train": self.hparams.max_target_length,
"val": self.hparams.val_max_target_length,
"test": self.hparams.test_max_target_length,
}
assert self.target_lens["train"] <= self.target_lens["val"], f"target_lens: {self.target_lens}"
assert self.target_lens["train"] <= self.target_lens["test"], f"target_lens: {self.target_lens}"
self.hparams.git_sha = get_git_info()["repo_sha"]
self.num_workers = hparams.num_workers
self.distributed_port = self.hparams.distributed_port
# For single GPU training, init_ddp_connection is not called.
# So we need to initialize the retrievers here.
if hparams.gpus <= 1:
if hparams.distributed_retriever == "ray":
self.model.retriever.init_retrieval()
elif hparams.distributed_retriever == "pytorch":
self.model.retriever.init_retrieval(self.distributed_port)
self.distributed_retriever = hparams.distributed_retriever