DSPFirst-Finetuning-3

This model is a fine-tuned version of ahotrod/electra_large_discriminator_squad2_512 on a generated Questions and Answers dataset from the DSPFirst textbook based on the SQuAD 2.0 format. It achieves the following results on the evaluation set:

• Loss: 0.9996
• Exact: 63.9193
• F1: 72.1090

Dataset

A visualization of the dataset can be found here. The split between train and test is 80% and 20% respectively.

DatasetDict({
    train: Dataset({
        features: ['id', 'title', 'context', 'question', 'answers'],
        num_rows: 4755
    })
    test: Dataset({
        features: ['id', 'title', 'context', 'question', 'answers'],
        num_rows: 1189
    })
})

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: 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: 3

Model hyperparameters

• hidden_dropout_prob: 0.35
• attention_probs_dropout_prob = 0.35

Training results

Training Loss	Epoch	Step	Validation Loss	Exact	F1
1.3511	0.99	28	1.1388	62.9941	71.4102
1.0052	1.99	56	1.0255	65.0126	73.0388
0.8699	2.99	84	0.9996	63.9193	72.1090

Framework versions

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