Hugging Face's logo

dsmsb
/
15_combo_bert_1409_v1

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
15_combo_bert_1409_v1 / README.md
dsmsb's picture
dsmsb
End of training
0e00b42
preview code
|
raw
history blame contribute delete
1.83 kB
metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: 15_combo_bert_1409_v1
    results: []

15_combo_bert_1409_v1

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: 0.7199
  • Accuracy: 0.8217

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: 1e-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: 8

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 246 1.5867 0.4944
No log 2.0 492 1.0790 0.6727
1.3969 3.0 738 0.9472 0.7540
1.3969 4.0 984 0.8356 0.7540
0.5425 5.0 1230 0.7507 0.7923
0.5425 6.0 1476 0.7414 0.8081
0.332 7.0 1722 0.7240 0.8126
0.332 8.0 1968 0.7199 0.8217

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3