# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("itsamitkumar/deberta-v3-base-squad2")
model = AutoModelForQuestionAnswering.from_pretrained("itsamitkumar/deberta-v3-base-squad2")Quick Links
deberta-v3-base-squad2
This model is a fine-tuned version of deepset/deberta-v3-base-squad2 on the subjqa dataset. It achieves the following results on the evaluation set:
- Loss: 2.2514
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: 1e-06
- 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: 18
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8874 | 1.0 | 81 | 3.4517 |
| 2.4367 | 2.0 | 162 | 3.0723 |
| 2.1531 | 3.0 | 243 | 2.8363 |
| 2.0393 | 4.0 | 324 | 2.6726 |
| 1.9166 | 5.0 | 405 | 2.5791 |
| 1.8508 | 6.0 | 486 | 2.4969 |
| 1.8035 | 7.0 | 567 | 2.4384 |
| 1.7348 | 8.0 | 648 | 2.3925 |
| 1.6939 | 9.0 | 729 | 2.3677 |
| 1.6754 | 10.0 | 810 | 2.3405 |
| 1.6283 | 11.0 | 891 | 2.2984 |
| 1.6159 | 12.0 | 972 | 2.2854 |
| 1.5893 | 13.0 | 1053 | 2.2793 |
| 1.5636 | 14.0 | 1134 | 2.2749 |
| 1.5779 | 15.0 | 1215 | 2.2629 |
| 1.567 | 16.0 | 1296 | 2.2563 |
| 1.5401 | 17.0 | 1377 | 2.2508 |
| 1.5494 | 18.0 | 1458 | 2.2514 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 9
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="itsamitkumar/deberta-v3-base-squad2")