---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- natural_questions
model-index:
- name: toy-qa
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# toy-qa

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the natural_questions dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2284

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 5.3253        | 1.0   | 14   | 3.3435          |
| 3.1799        | 2.0   | 28   | 0.6626          |
| 2.8858        | 3.0   | 42   | 0.7105          |
| 2.7921        | 4.0   | 56   | 0.5784          |
| 2.3648        | 5.0   | 70   | 0.5843          |
| 2.0496        | 6.0   | 84   | 0.3544          |
| 1.5883        | 7.0   | 98   | 0.3406          |
| 0.829         | 8.0   | 112  | 0.3717          |
| 0.5334        | 9.0   | 126  | 0.4049          |
| 0.4915        | 10.0  | 140  | 0.4101          |
| 0.57          | 11.0  | 154  | 0.3464          |
| 0.5129        | 12.0  | 168  | 0.3892          |
| 0.4334        | 13.0  | 182  | 0.2455          |
| 0.5406        | 14.0  | 196  | 0.2647          |
| 0.2201        | 15.0  | 210  | 0.2422          |
| 0.0917        | 16.0  | 224  | 0.2218          |
| 0.1753        | 17.0  | 238  | 0.2453          |
| 0.0231        | 18.0  | 252  | 0.2061          |
| 0.1107        | 19.0  | 266  | 0.2102          |
| 0.1182        | 20.0  | 280  | 0.2496          |
| 0.0829        | 21.0  | 294  | 0.2151          |
| 0.0775        | 22.0  | 308  | 0.2490          |
| 0.0067        | 23.0  | 322  | 0.2369          |
| 0.0058        | 24.0  | 336  | 0.2334          |
| 0.005         | 25.0  | 350  | 0.2288          |
| 0.0042        | 26.0  | 364  | 0.2148          |
| 0.0071        | 27.0  | 378  | 0.2582          |
| 0.0043        | 28.0  | 392  | 0.2232          |
| 0.0028        | 29.0  | 406  | 0.2170          |
| 0.0034        | 30.0  | 420  | 0.2290          |
| 0.0021        | 31.0  | 434  | 0.2299          |
| 0.0028        | 32.0  | 448  | 0.2214          |
| 0.0019        | 33.0  | 462  | 0.2312          |
| 0.002         | 34.0  | 476  | 0.2263          |
| 0.0024        | 35.0  | 490  | 0.2397          |
| 0.0019        | 36.0  | 504  | 0.2272          |
| 0.0087        | 37.0  | 518  | 0.2321          |
| 0.0016        | 38.0  | 532  | 0.2425          |
| 0.0016        | 39.0  | 546  | 0.2449          |
| 0.0014        | 40.0  | 560  | 0.2208          |
| 0.0013        | 41.0  | 574  | 0.2185          |
| 0.0013        | 42.0  | 588  | 0.2246          |
| 0.0016        | 43.0  | 602  | 0.2344          |
| 0.0016        | 44.0  | 616  | 0.2411          |
| 0.0015        | 45.0  | 630  | 0.2345          |
| 0.0015        | 46.0  | 644  | 0.2317          |
| 0.0014        | 47.0  | 658  | 0.2289          |
| 0.0011        | 48.0  | 672  | 0.2288          |
| 0.0012        | 49.0  | 686  | 0.2288          |
| 0.0013        | 50.0  | 700  | 0.2284          |


### Framework versions

- Transformers 4.17.0
- Pytorch 1.10.0
- Datasets 1.18.3
- Tokenizers 0.11.6