distilbert-base-multilingual-cased_ReseniasRandmOversamp
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8347
- F1: 0.6889
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.0676 | 1.0 | 575 | 1.0776 | 0.5198 |
| 0.918 | 2.0 | 1150 | 0.9263 | 0.6018 |
| 0.739 | 3.0 | 1725 | 0.8461 | 0.6626 |
| 0.5944 | 4.0 | 2300 | 0.8316 | 0.6818 |
| 0.5295 | 5.0 | 2875 | 0.8347 | 0.6889 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3