metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: ConcSeqBERT-UCIRetail
results: []
ConcSeqBERT-UCIRetail
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4742
- Accuracy: 0.7850
- F1: 0.7847
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 456 | 0.5586 | 0.7290 | 0.7289 |
| 0.6851 | 2.0 | 912 | 0.4842 | 0.7718 | 0.7703 |
| 0.5396 | 3.0 | 1368 | 0.4742 | 0.7850 | 0.7847 |
| 0.448 | 4.0 | 1824 | 0.5257 | 0.7932 | 0.7920 |
| 0.3934 | 5.0 | 2280 | 0.6493 | 0.7801 | 0.7779 |
| 0.3476 | 6.0 | 2736 | 0.9150 | 0.7644 | 0.7644 |
| 0.2971 | 7.0 | 3192 | 1.1450 | 0.7727 | 0.7723 |
| 0.2307 | 8.0 | 3648 | 1.0960 | 0.7743 | 0.7743 |
| 0.2112 | 9.0 | 4104 | 1.2912 | 0.7842 | 0.7842 |
| 0.1757 | 10.0 | 4560 | 1.3925 | 0.7759 | 0.7759 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.14.1