BERT_SPARQL
This model is a fine-tuned version of razent/spbert-mlm-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3088
- Accuracy: 0.9527
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.9512 | 0.43 | 1000 | 1.3428 | 0.6989 |
| 1.0044 | 0.85 | 2000 | 0.5995 | 0.9014 |
| 0.5483 | 1.28 | 3000 | 0.4462 | 0.9309 |
| 0.436 | 1.7 | 4000 | 0.4086 | 0.9377 |
| 0.3764 | 2.13 | 5000 | 0.3567 | 0.9463 |
| 0.337 | 2.56 | 6000 | 0.3343 | 0.9496 |
| 0.3115 | 2.98 | 7000 | 0.3089 | 0.9525 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 0
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.