import os
from pathlib import Path

import torch
from datasets import Dataset
from sentence_transformers import (
    SparseEncoder,
    SparseEncoderTrainer,
    SparseEncoderTrainingArguments,
)
from sentence_transformers.sparse_encoder.losses import (
    SparseMultipleNegativesRankingLoss,
    SpladeLoss,
)

os.environ["TOKENIZERS_PARALLELISM"] = "false"
os.environ["WANDB_DISABLED"] = "true"

output_dir = Path("training-output/support-sparse-encoder")
model_dir = Path("models/support-sparse-encoder")