xlm-roberta-base-finetuned-ko-tjdrms
This model is a fine-tuned version of xlm-roberta-base on the xtreme dataset. It achieves the following results on the evaluation set:
- Loss: 0.3122
- F1: 0.8975
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: 24
- eval_batch_size: 24
- 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 | F1 |
|---|---|---|---|---|
| 0.383 | 1.0 | 834 | 0.2389 | 0.8459 |
| 0.2142 | 2.0 | 1668 | 0.2235 | 0.8530 |
| 0.1524 | 3.0 | 2502 | 0.1992 | 0.8794 |
| 0.1101 | 4.0 | 3336 | 0.2284 | 0.8767 |
| 0.0816 | 5.0 | 4170 | 0.2290 | 0.8854 |
| 0.0592 | 6.0 | 5004 | 0.2512 | 0.8876 |
| 0.0417 | 7.0 | 5838 | 0.2705 | 0.8891 |
| 0.0293 | 8.0 | 6672 | 0.2942 | 0.8924 |
| 0.0206 | 9.0 | 7506 | 0.2961 | 0.8952 |
| 0.0142 | 10.0 | 8340 | 0.3122 | 0.8975 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.