flan-t5-small-quaso
This model is a fine-tuned version of google/flan-t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0153
- Meteor: 21.5728
- Gen Len: 33.8080
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- 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 | Meteor | Gen Len |
---|---|---|---|---|---|
2.3812 | 1.0 | 5625 | 2.1564 | 18.7871 | 33.0490 |
2.2446 | 2.0 | 11250 | 2.0850 | 20.0046 | 33.4798 |
2.1915 | 3.0 | 16875 | 2.0420 | 20.2023 | 32.0501 |
2.1714 | 4.0 | 22500 | 2.0223 | 21.0488 | 33.9555 |
2.1547 | 5.0 | 28125 | 2.0153 | 21.5728 | 33.8080 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 33