# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("sharmadhruv/qa_by_bart")
model = AutoModelForQuestionAnswering.from_pretrained("sharmadhruv/qa_by_bart")Quick Links
qa_by_bart
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1015
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0956 | 1.0 | 1000 | 0.8831 |
| 0.7224 | 2.0 | 2000 | 0.8626 |
| 0.4213 | 3.0 | 3000 | 1.1015 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 3
Model tree for sharmadhruv/qa_by_bart
Base model
facebook/bart-large
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="sharmadhruv/qa_by_bart")