tushifire/setfit_youtube_comments_is_question

{Setfit_youtube_comments}

This is a Setfit model: It maps sentences to a n dimensional dense vector space and can be used for classification of text into question or not_question class.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers and setfit installed:

pip install -U sentence-transformers
pip install setfit

Then you can use the model like this:

from setfit import SetFitModel
model = SetFitModel.from_pretrained("tushifire/setfit_youtube_comments_is_a_question")

# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
print(preds)

preds = model(["""what video do I watch that takes the html_output and insert it into the actual html page?""",
               "Why does for loop end without a break statement"])
print(preds)

Training

The model was trained with the parameters:

DataLoader:

torch.utils.data.dataloader.DataLoader of length 80 with parameters:

{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss:

sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss

Parameters of the fit()-Method:

{
    "epochs": 10,
    "evaluation_steps": 0,
    "evaluator": "NoneType",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": 800,
    "warmup_steps": 80,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
  (2): Normalize()
)

Citing & Authors