flan-t5-small-taboo-for-llms-deft
This model is a fine-tuned version of vlkn/flan-t5-small-taboo-for-llms-deft on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2875
- Rouge1: 32.1845
- Rouge2: 16.9705
- Rougel: 29.529
- Rougelsum: 29.6072
- Gen Len: 15.2997
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: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.4309 | 0.62 | 100 | 2.3010 | 31.469 | 16.5456 | 28.6201 | 28.6762 | 15.4739 |
| 2.619 | 1.24 | 200 | 2.2973 | 31.933 | 16.7494 | 29.1285 | 29.238 | 15.4983 |
| 2.6097 | 1.85 | 300 | 2.2928 | 32.2705 | 16.9959 | 29.6145 | 29.7188 | 15.2927 |
| 2.5818 | 2.47 | 400 | 2.2880 | 32.1637 | 16.7922 | 29.543 | 29.5852 | 15.4564 |
| 2.5782 | 3.09 | 500 | 2.2875 | 32.1845 | 16.9705 | 29.529 | 29.6072 | 15.2997 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3