reward-bert-duplicate-answer
This model is a fine-tuned version of klue/roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0604
- Accuracy: 0.0
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: 9e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 2023
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.2202 | 0.13 | 100 | 0.0750 | 0.0 |
0.1527 | 0.25 | 200 | 0.0377 | 0.0 |
0.1483 | 0.38 | 300 | 0.0729 | 0.0 |
0.1896 | 0.5 | 400 | 0.1465 | 0.0 |
0.1341 | 0.63 | 500 | 0.0729 | 0.0 |
0.0876 | 0.75 | 600 | 0.0351 | 0.0 |
0.1345 | 0.88 | 700 | 0.0604 | 0.0 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 7
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 bradmin/reward-bert-duplicate-answer
Base model
klue/roberta-large