---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5_Question_Generation_2
  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. -->

# t5_Question_Generation_2

This model is a fine-tuned version of [Gayathri142214002/t5_Question_Generation](https://huggingface.co/Gayathri142214002/t5_Question_Generation) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5618

## 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.7289        | 0.16  | 10   | 0.7052          |
| 0.9277        | 0.32  | 20   | 0.6537          |
| 0.7542        | 0.48  | 30   | 0.6151          |
| 0.6897        | 0.64  | 40   | 0.5763          |
| 0.6837        | 0.8   | 50   | 0.5575          |
| 0.5974        | 0.96  | 60   | 0.5442          |
| 0.4186        | 1.12  | 70   | 0.5091          |
| 0.4975        | 1.28  | 80   | 0.5214          |
| 0.4149        | 1.44  | 90   | 0.5319          |
| 0.5302        | 1.6   | 100  | 0.5280          |
| 0.5209        | 1.76  | 110  | 0.5194          |
| 0.4839        | 1.92  | 120  | 0.5116          |
| 0.4813        | 2.08  | 130  | 0.5151          |
| 0.3714        | 2.24  | 140  | 0.5137          |
| 0.3955        | 2.4   | 150  | 0.5229          |
| 0.3588        | 2.56  | 160  | 0.5221          |
| 0.4196        | 2.72  | 170  | 0.5215          |
| 0.4238        | 2.88  | 180  | 0.5084          |
| 0.3322        | 3.04  | 190  | 0.5015          |
| 0.335         | 3.2   | 200  | 0.5066          |
| 0.3719        | 3.36  | 210  | 0.5040          |
| 0.3431        | 3.52  | 220  | 0.5165          |
| 0.3521        | 3.68  | 230  | 0.5223          |
| 0.3135        | 3.84  | 240  | 0.5296          |
| 0.3436        | 4.0   | 250  | 0.5370          |
| 0.3023        | 4.16  | 260  | 0.5298          |
| 0.3031        | 4.32  | 270  | 0.5228          |
| 0.3173        | 4.48  | 280  | 0.5207          |
| 0.2975        | 4.64  | 290  | 0.5292          |
| 0.322         | 4.8   | 300  | 0.5417          |
| 0.3355        | 4.96  | 310  | 0.5525          |
| 0.2963        | 5.12  | 320  | 0.5545          |
| 0.2544        | 5.28  | 330  | 0.5579          |
| 0.2659        | 5.44  | 340  | 0.5589          |
| 0.286         | 5.6   | 350  | 0.5571          |
| 0.2967        | 5.76  | 360  | 0.5603          |
| 0.2925        | 5.92  | 370  | 0.5603          |
| 0.2866        | 6.08  | 380  | 0.5599          |
| 0.2724        | 6.24  | 390  | 0.5574          |
| 0.2695        | 6.4   | 400  | 0.5599          |
| 0.2679        | 6.56  | 410  | 0.5609          |
| 0.2599        | 6.72  | 420  | 0.5614          |
| 0.2319        | 6.88  | 430  | 0.5618          |


### Framework versions

- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3