<!-- 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. -->
finetuning_t5
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2795
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3628 | 1.0 | 444 | 0.2424 |
| 0.2569 | 2.0 | 889 | 0.2220 |
| 0.3852 | 3.0 | 1333 | 0.2854 |
| 0.4332 | 4.0 | 1778 | 0.2795 |
| 0.4322 | 5.0 | 2222 | 0.2794 |
| 0.4276 | 6.0 | 2667 | 0.2794 |
| 0.4275 | 7.0 | 3111 | 0.2794 |
| 0.4269 | 8.0 | 3556 | 0.2795 |
| 0.429 | 9.0 | 4001 | 0.2795 |
| 0.4308 | 9.99 | 4440 | 0.2795 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
