translation-source-classifier
This model is a fine-tuned version of jhu-clsp/mmBERT-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5460
- Accuracy: 0.6111
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: 0.001
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1867 | 1.0 | 14063 | 2.2778 | 0.4457 |
| 2.0165 | 2.0 | 28126 | 2.0671 | 0.4984 |
| 1.935 | 3.0 | 42189 | 1.9881 | 0.5151 |
| 1.8636 | 4.0 | 56252 | 1.8941 | 0.5351 |
| 1.7705 | 5.0 | 70315 | 1.8231 | 0.5460 |
| 1.7174 | 6.0 | 84378 | 1.7304 | 0.5691 |
| 1.6526 | 7.0 | 98441 | 1.6755 | 0.5788 |
| 1.6009 | 8.0 | 112504 | 1.6174 | 0.5922 |
| 1.4959 | 9.0 | 126567 | 1.5779 | 0.6025 |
| 1.4539 | 10.0 | 140630 | 1.5460 | 0.6111 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.10.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2
- Downloads last month
- -
Model tree for NbAiLab/bifrost-translation-source-classifier
Base model
jhu-clsp/mmBERT-base