metadata
base_model: MiMe-MeMo/MeMo-BERT-01
tags:
- generated_from_trainer
model-index:
- name: MeMo_BERT-SA_1
results: []
MeMo_BERT-SA_1
This model is a fine-tuned version of MiMe-MeMo/MeMo-BERT-01 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7236
- F1-score: 0.5887
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 | 1.0173 | 0.4110 |
| 0.9885 | 2.0 | 530 | 0.9694 | 0.5053 |
| 0.9885 | 3.0 | 795 | 1.1486 | 0.4695 |
| 0.7354 | 4.0 | 1060 | 1.1729 | 0.5363 |
| 0.7354 | 5.0 | 1325 | 1.2851 | 0.5822 |
| 0.4299 | 6.0 | 1590 | 1.7236 | 0.5887 |
| 0.4299 | 7.0 | 1855 | 2.3852 | 0.5426 |
| 0.2854 | 8.0 | 2120 | 2.7498 | 0.5503 |
| 0.2854 | 9.0 | 2385 | 3.1832 | 0.5475 |
| 0.1251 | 10.0 | 2650 | 3.3652 | 0.5563 |
| 0.1251 | 11.0 | 2915 | 3.4598 | 0.5594 |
| 0.0711 | 12.0 | 3180 | 3.5185 | 0.5499 |
| 0.0711 | 13.0 | 3445 | 3.5487 | 0.5578 |
| 0.0328 | 14.0 | 3710 | 3.8292 | 0.5437 |
| 0.0328 | 15.0 | 3975 | 3.8419 | 0.5517 |
| 0.013 | 16.0 | 4240 | 3.9292 | 0.5496 |
| 0.0089 | 17.0 | 4505 | 3.9444 | 0.5684 |
| 0.0089 | 18.0 | 4770 | 4.0013 | 0.5659 |
| 0.0025 | 19.0 | 5035 | 4.0913 | 0.5675 |
| 0.0025 | 20.0 | 5300 | 4.0899 | 0.5653 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2