metadata
base_model: MiMe-MeMo/MeMo-BERT-02
tags:
- generated_from_trainer
model-index:
- name: MeMo_BERT-SA_2
results: []
MeMo_BERT-SA_2
This model is a fine-tuned version of MiMe-MeMo/MeMo-BERT-02 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4358
- F1-score: 0.5924
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: 5e-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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1-score |
|---|---|---|---|---|
| No log | 1.0 | 265 | 1.0171 | 0.5029 |
| 0.9806 | 2.0 | 530 | 0.9884 | 0.5416 |
| 0.9806 | 3.0 | 795 | 1.1255 | 0.5477 |
| 0.6405 | 4.0 | 1060 | 1.0771 | 0.5716 |
| 0.6405 | 5.0 | 1325 | 1.4358 | 0.5924 |
| 0.3872 | 6.0 | 1590 | 2.0203 | 0.5780 |
| 0.3872 | 7.0 | 1855 | 2.4784 | 0.5730 |
| 0.2014 | 8.0 | 2120 | 2.7627 | 0.5735 |
| 0.2014 | 9.0 | 2385 | 3.1488 | 0.5733 |
| 0.0888 | 10.0 | 2650 | 3.2253 | 0.5636 |
| 0.0888 | 11.0 | 2915 | 3.4722 | 0.5488 |
| 0.0563 | 12.0 | 3180 | 3.6568 | 0.5718 |
| 0.0563 | 13.0 | 3445 | 3.8553 | 0.5676 |
| 0.0188 | 14.0 | 3710 | 3.8721 | 0.5572 |
| 0.0188 | 15.0 | 3975 | 3.9256 | 0.5782 |
| 0.0021 | 16.0 | 4240 | 3.9991 | 0.5802 |
| 0.0032 | 17.0 | 4505 | 4.0370 | 0.5798 |
| 0.0032 | 18.0 | 4770 | 4.1400 | 0.5746 |
| 0.0012 | 19.0 | 5035 | 4.1422 | 0.5740 |
| 0.0012 | 20.0 | 5300 | 4.1453 | 0.5742 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2