metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-natural-questions
results: []
distilbert-base-uncased-finetuned-natural-questions
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: 0.3516
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 20415 | 0.2347 |
| No log | 2.0 | 40830 | 0.2269 |
| 1.885 | 3.0 | 61245 | 0.2441 |
| 1.885 | 4.0 | 81660 | 0.2316 |
| 1.5134 | 5.0 | 102075 | 0.2618 |
| 1.5134 | 6.0 | 122490 | 0.2609 |
| 1.5134 | 7.0 | 142905 | 0.2865 |
| 1.1608 | 8.0 | 163320 | 0.3046 |
| 1.1608 | 9.0 | 183735 | 0.3372 |
| 0.9118 | 10.0 | 204150 | 0.3516 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0
- Datasets 1.18.3
- Tokenizers 0.11.6