<!-- 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_qg_1
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0323
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 |
|---|---|---|---|
| 2.658 | 0.69 | 10 | 1.9854 |
| 1.7442 | 1.38 | 20 | 1.6146 |
| 1.3456 | 2.07 | 30 | 1.3937 |
| 0.9931 | 2.76 | 40 | 1.2447 |
| 0.9253 | 3.45 | 50 | 1.1519 |
| 0.7154 | 4.14 | 60 | 1.0958 |
| 0.6624 | 4.83 | 70 | 1.0645 |
| 0.6384 | 5.52 | 80 | 1.0412 |
| 0.4889 | 6.21 | 90 | 1.0323 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
