<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
ossp-v0_2
This model is a fine-tuned version of leadawon/ossp-v0_2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3871
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0152 | 0.13 | 10000 | 0.8570 |
| 0.6616 | 0.26 | 20000 | 0.6056 |
| 0.5819 | 0.39 | 30000 | 0.5253 |
| 0.518 | 0.52 | 40000 | 0.4710 |
| 0.465 | 0.66 | 50000 | 0.4404 |
| 0.4252 | 0.79 | 60000 | 0.4097 |
| 0.4139 | 0.92 | 70000 | 0.3871 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Tokenizers 0.13.3
