Hugging Face's logo

jmete
/
tweet_instruct_detect

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
2
tweet_instruct_detect / README.md
jmete's picture
jmete
update model card README.md
c890bc3
preview code
|
raw
history blame
1.61 kB
metadata
license: mit
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: tweet_instruct_detect
    results: []

tweet_instruct_detect

This model is a fine-tuned version of microsoft/Multilingual-MiniLM-L12-H384 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1300
  • Accuracy: 0.9761

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 47 0.3832 0.9562
No log 2.0 94 0.2004 0.9681
No log 3.0 141 0.1501 0.9721
No log 4.0 188 0.1362 0.9721
No log 5.0 235 0.1300 0.9761

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.13.1
  • Datasets 2.9.0
  • Tokenizers 0.13.2