my_awesome_model / README.md
KiDoAIO's picture
update
bc7d03c verified
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: my_awesome_model
    results: []

my_awesome_model

Link hướng dẫn Colab: Sequence_Classification

Link demo: https://textclassificationpy-5nr3pbrn2j4twcczjdvb89.streamlit.app/

Link github demo : https://github.com/kidovnoz/streamlittest/blob/main/text_classification.py

This model is a fine-tuned version of distilbert-base-uncased on an IMDB dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2355
  • Accuracy: 0.9311
  • F1: 0.9315
  • Precision: 0.9263
  • Recall: 0.9368

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: 2

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.2241 1.0 1563 0.1977 0.9258 0.9238 0.9490 0.8999
0.1459 2.0 3126 0.2355 0.9311 0.9315 0.9263 0.9368

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1