Added support to resume workload
This commit is contained in:
parent
0975c19e69
commit
17d82f0a4e
@ -72,11 +72,17 @@ def train(args: ProgramArgs):
|
||||
VOCABULARY_PATH = Path(args.output_file)
|
||||
CACHE_PATH = Path(args.cache_file)
|
||||
|
||||
start_bpe = BPE.NanoSocratesBPE()
|
||||
if CACHE_PATH.is_file():
|
||||
voc = BPE.load_nanos_vocabulary(CACHE_PATH)
|
||||
start_bpe = BPE.NanoSocratesBPE(voc)
|
||||
|
||||
print(f"Training BPE")
|
||||
|
||||
BPE_ENCODER = TRAINER.trainBPE(
|
||||
DATASET_PATH,
|
||||
CACHE_PATH
|
||||
CACHE_PATH,
|
||||
start_bpe
|
||||
)
|
||||
|
||||
VOCABULARY = BPE_ENCODER.vocabulary
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user