MRR_QA_BRT_15K_UNTIL_2_08
This model is a fine-tuned version of deepset/roberta-base-squad2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0585
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9713 | 1.0 | 11594 | 1.1155 |
| 0.8918 | 2.0 | 23188 | 1.0256 |
| 0.9939 | 3.0 | 34782 | 1.0284 |
| 0.7113 | 4.0 | 46376 | 0.8892 |
| 0.6961 | 5.0 | 57970 | 0.8689 |
| 0.6308 | 6.0 | 69564 | 0.8036 |
| 0.4743 | 7.0 | 81158 | 0.9601 |
| 0.4245 | 8.0 | 92752 | 0.9345 |
| 0.4031 | 9.0 | 104346 | 0.9640 |
| 0.4351 | 10.0 | 115940 | 1.0585 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 29
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.