test-bert-4
This model is a fine-tuned version of hung200504/test-bert-3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 11.2408
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: 3e-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
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 10.2916 | 0.09 | 5 | 11.5523 |
| 10.1994 | 0.18 | 10 | 11.4942 |
| 9.7621 | 0.27 | 15 | 11.4425 |
| 10.0828 | 0.36 | 20 | 11.3969 |
| 9.9806 | 0.45 | 25 | 11.3567 |
| 10.0913 | 0.55 | 30 | 11.3225 |
| 9.4998 | 0.64 | 35 | 11.2944 |
| 9.4188 | 0.73 | 40 | 11.2722 |
| 9.7955 | 0.82 | 45 | 11.2561 |
| 9.6201 | 0.91 | 50 | 11.2455 |
| 9.8946 | 1.0 | 55 | 11.2408 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 6
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for hung200504/test-bert-4
Base model
deepset/bert-base-cased-squad2
Finetuned
hung200504/test-bert-2
Finetuned
hung200504/test-bert-3