metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: ConcSeqBERT-Katchers
results: []
ConcSeqBERT-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: 0.5053
- Accuracy: 0.7917
- F1: 0.7916
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 |
|---|---|---|---|---|---|
| 0.5096 | 1.0 | 2522 | 0.5328 | 0.7435 | 0.7390 |
| 0.4591 | 2.0 | 5044 | 0.5231 | 0.7924 | 0.7923 |
| 0.4182 | 3.0 | 7566 | 0.5053 | 0.7917 | 0.7916 |
| 0.3931 | 4.0 | 10088 | 0.5470 | 0.7978 | 0.7976 |
| 0.3558 | 5.0 | 12610 | 0.7055 | 0.7877 | 0.7866 |
| 0.3409 | 6.0 | 15132 | 0.7529 | 0.7893 | 0.7886 |
| 0.3036 | 7.0 | 17654 | 0.8570 | 0.7965 | 0.7963 |
| 0.2938 | 8.0 | 20176 | 0.9075 | 0.7923 | 0.7920 |
| 0.236 | 9.0 | 22698 | 1.0325 | 0.7886 | 0.7882 |
| 0.224 | 10.0 | 25220 | 1.0438 | 0.7911 | 0.7908 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.14.1