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: 0.5189
- Accuracy: 0.7951
- F1: 0.7951
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 |
|---|---|---|---|---|---|
| 0.4666 | 1.0 | 2522 | 0.5650 | 0.7594 | 0.7551 |
| 0.4421 | 2.0 | 5044 | 0.5189 | 0.7951 | 0.7951 |
| 0.4033 | 3.0 | 7566 | 0.5224 | 0.7994 | 0.7994 |
| 0.3775 | 4.0 | 10088 | 0.6658 | 0.8002 | 0.7999 |
| 0.3549 | 5.0 | 12610 | 0.6499 | 0.8017 | 0.8015 |
| 0.3429 | 6.0 | 15132 | 0.7884 | 0.7939 | 0.7937 |
| 0.3077 | 7.0 | 17654 | 0.8724 | 0.7933 | 0.7933 |
| 0.2841 | 8.0 | 20176 | 0.9424 | 0.7914 | 0.7913 |
| 0.2393 | 9.0 | 22698 | 1.0403 | 0.7874 | 0.7873 |
| 0.2206 | 10.0 | 25220 | 1.1224 | 0.7835 | 0.7832 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.14.1