tweet_bert_1408 / README.md
dsmsb's picture
update model card README.md
db0432d
metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: tweet_bert_1408
    results: []

tweet_bert_1408

This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7067
  • Accuracy: 0.8477

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 1.0 397 0.7847 0.8363
0.2479 2.0 794 0.6668 0.8422
0.2971 3.0 1191 0.6221 0.8481
0.2087 4.0 1588 0.6557 0.8488
0.2087 5.0 1985 0.7067 0.8477

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3