rap_phase2_MODEL2_31jan_10i
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0252
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: 5
- eval_batch_size: 5
- 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 |
---|---|---|---|
1.6084 | 1.0 | 900 | 0.2981 |
0.3066 | 2.0 | 1800 | 0.0928 |
0.1001 | 3.0 | 2700 | 0.0803 |
0.0719 | 4.0 | 3600 | 0.0369 |
0.0595 | 5.0 | 4500 | 0.0440 |
0.0525 | 6.0 | 5400 | 0.0324 |
0.0282 | 7.0 | 6300 | 0.0287 |
0.0278 | 8.0 | 7200 | 0.0344 |
0.032 | 9.0 | 8100 | 0.0251 |
0.0198 | 10.0 | 9000 | 0.0252 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 93
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for am-infoweb/rap_phase2_MODEL2_31jan_10i
Base model
FacebookAI/xlm-roberta-base