metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5-end2end-questions-generation-cvqualtrics-squad-V1
results: []
t5-end2end-questions-generation-cvqualtrics-squad-V1
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4124
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6178 | 0.34 | 100 | 1.8936 |
| 2.0032 | 0.67 | 200 | 1.6910 |
| 1.8748 | 1.01 | 300 | 1.6187 |
| 1.7769 | 1.34 | 400 | 1.5605 |
| 1.7404 | 1.68 | 500 | 1.5354 |
| 1.736 | 2.01 | 600 | 1.5059 |
| 1.6698 | 2.35 | 700 | 1.4904 |
| 1.6625 | 2.68 | 800 | 1.4656 |
| 1.6611 | 3.02 | 900 | 1.4487 |
| 1.6124 | 3.36 | 1000 | 1.4398 |
| 1.6133 | 3.69 | 1100 | 1.4278 |
| 1.6182 | 4.03 | 1200 | 1.4234 |
| 1.5836 | 4.36 | 1300 | 1.4161 |
| 1.5861 | 4.7 | 1400 | 1.4124 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1