# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("stig/distilbert-base-uncased-finetuned")
model = AutoModelForQuestionAnswering.from_pretrained("stig/distilbert-base-uncased-finetuned", device_map="auto")Quick Links
distilbert-base-uncased-finetuned
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8627
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0255 | 1.0 | 2312 | 1.9202 |
| 1.7483 | 2.0 | 4624 | 1.8437 |
| 1.5733 | 3.0 | 6936 | 1.8627 |
Framework versions
- Transformers 4.19.3
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
- Downloads last month
- 5
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="stig/distilbert-base-uncased-finetuned")