metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5-end2end-questions-generation
results: []
t5-end2end-questions-generation
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6363
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.6063 | 0.67 | 100 | 1.9609 |
1.9832 | 1.35 | 200 | 1.7818 |
1.8375 | 2.02 | 300 | 1.7241 |
1.7553 | 2.69 | 400 | 1.6982 |
1.7077 | 3.36 | 500 | 1.6691 |
1.68 | 4.04 | 600 | 1.6638 |
1.64 | 4.71 | 700 | 1.6521 |
1.6149 | 5.38 | 800 | 1.6467 |
1.6064 | 6.05 | 900 | 1.6502 |
1.5768 | 6.73 | 1000 | 1.6394 |
1.5685 | 7.4 | 1100 | 1.6389 |
1.5568 | 8.07 | 1200 | 1.6342 |
1.5422 | 8.74 | 1300 | 1.6326 |
1.5422 | 9.42 | 1400 | 1.6363 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3