---
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: DSPFirst-Finetuning-5
  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. -->

# Important Note:
I created the `combined` metric (55% F1 score + 45% exact match score) and load the state with the best result at the end. Here is the setting in the `TrainingArguments`:
```
  load_best_model_at_end=True,
  metric_for_best_model='combined',
  greater_is_better=True,
```

# DSPFirst-Finetuning-5

This model is a fine-tuned version of [ahotrod/electra_large_discriminator_squad2_512](https://huggingface.co/ahotrod/electra_large_discriminator_squad2_512) on a generated Questions and Answers dataset from the DSPFirst textbook based on the SQuAD 2.0 format.<br />
It achieves the following results on the evaluation set:
- Loss: 0.8529
- Exact: 67.0964
- F1: 74.4842
- Combined: 71.1597

## More accurate metrics:

### Before fine-tuning:

```
 'HasAns_exact': 54.71817606079797,
 'HasAns_f1': 61.08672724332754,
 'HasAns_total': 1579,
 'NoAns_exact': 88.78048780487805,
 'NoAns_f1': 88.78048780487805,
 'NoAns_total': 205,
 'best_exact': 58.63228699551569,
 'best_exact_thresh': 0.0,
 'best_f1': 64.26902596256402,
 'best_f1_thresh': 0.0,
 'exact': 58.63228699551569,
 'f1': 64.26902596256404,
 'total': 1784
```

### After fine-tuning:

```
 'HasAns_exact': 67.57441418619379,
 'HasAns_f1': 75.92137683558988,
 'HasAns_total': 1579,
 'NoAns_exact': 63.41463414634146,
 'NoAns_f1': 63.41463414634146,
 'NoAns_total': 205,
 'best_exact': 67.0964125560538,
 'best_exact_thresh': 0.0,
 'best_f1': 74.48422310728503,
 'best_f1_thresh': 0.0,
 'exact': 67.0964125560538,
 'f1': 74.48422310728503,
 'total': 1784
```

# Dataset
A visualization of the dataset can be found [here](https://github.gatech.edu/pages/VIP-ITS/textbook_SQuAD_explore/explore/textbookv1.0/textbook/).<br />
The split between train and test is 70% and 30% respectively.
```
DatasetDict({
    train: Dataset({
        features: ['id', 'title', 'context', 'question', 'answers'],
        num_rows: 4160
    })
    test: Dataset({
        features: ['id', 'title', 'context', 'question', 'answers'],
        num_rows: 1784
    })
})
```

## Intended uses & limitations

This model is fine-tuned to answer questions from the DSPFirst textbook. I'm not really sure what I am doing so you should review before using it.<br />
Also, you should improve the Dataset either by using a **better generated questions and answers model** (currently using https://github.com/patil-suraj/question_generation) or perform **data augmentation** to increase dataset size.

## Training and evaluation data

- `batch_size` of 6 results in 14.03 GB VRAM
- Utilizes `gradient_accumulation_steps` to get total batch size to 516 (total batch size should be at least 256)
- 4.52 GB RAM
- 30% of the total questions is dedicated for evaluating.

## Training procedure
- The model was trained from [Google Colab](https://colab.research.google.com/drive/1dJXNstk2NSenwzdtl9xA8AqjP4LL-Ks_?usp=sharing)
- Utilizes Tesla P100 16GB, took 6.3 hours to train
- `load_best_model_at_end` is enabled in TrainingArguments

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 86
- total_train_batch_size: 516
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7

### Model hyperparameters

- hidden_dropout_prob: 0.36
- attention_probs_dropout_prob = 0.36

### Training results

| Training Loss | Epoch | Step | Validation Loss | Exact   | F1      | Combined |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:--------:|
| 2.3222        | 0.81  | 20   | 1.0363          | 60.3139 | 68.8586 | 65.0135  |
| 1.6149        | 1.65  | 40   | 0.9702          | 64.7422 | 72.5555 | 69.0395  |
| 1.2375        | 2.49  | 60   | 1.0007          | 64.6861 | 72.6306 | 69.0556  |
| 1.0417        | 3.32  | 80   | 0.9963          | 66.0874 | 73.8634 | 70.3642  |
| 0.9401        | 4.16  | 100  | 0.8803          | 67.0964 | 74.4842 | 71.1597  |
| 0.8799        | 4.97  | 120  | 0.8652          | 66.7040 | 74.1267 | 70.7865  |
| 0.8712        | 5.81  | 140  | 0.8921          | 66.3677 | 73.7213 | 70.4122  |
| 0.8311        | 6.65  | 160  | 0.8529          | 66.3117 | 73.4039 | 70.2124  |


### Framework versions

- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1