metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: SeqClassBERT-Katchers
results: []
SeqClassBERT-Katchers
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: 0.4894
- Accuracy: 0.7685
- F1: 0.7669
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 | 0.6156 | 0.7496 | 0.7481 |
| 0.5689 | 2.0 | 912 | 0.4894 | 0.7685 | 0.7669 |
| 0.4871 | 3.0 | 1368 | 0.5233 | 0.7710 | 0.7702 |
| 0.4108 | 4.0 | 1824 | 0.7847 | 0.7702 | 0.7687 |
| 0.3756 | 5.0 | 2280 | 0.7087 | 0.7735 | 0.7723 |
| 0.3153 | 6.0 | 2736 | 0.9257 | 0.7537 | 0.7537 |
| 0.2862 | 7.0 | 3192 | 1.0686 | 0.7759 | 0.7745 |
| 0.2413 | 8.0 | 3648 | 1.1271 | 0.7677 | 0.7677 |
| 0.1983 | 9.0 | 4104 | 1.2501 | 0.7743 | 0.7741 |
| 0.1359 | 10.0 | 4560 | 1.3071 | 0.7694 | 0.7693 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.14.1