t5-small-finetuned-manim-1.1
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4874
- Rouge1: 37.8663
- Rouge2: 33.7441
- Rougel: 37.8808
- Rougelsum: 37.8682
- Gen Len: 19.0
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 453 | 2.3825 | 24.2996 | 4.0549 | 21.4419 | 21.5134 | 18.3872 |
| 4.5852 | 2.0 | 906 | 1.2933 | 36.9453 | 22.8669 | 34.801 | 34.8206 | 18.9757 |
| 3.2959 | 3.0 | 1359 | 0.9067 | 38.9416 | 29.0778 | 37.4737 | 37.4712 | 19.0 |
| 2.9079 | 4.0 | 1812 | 0.7208 | 37.9374 | 33.7441 | 37.8808 | 37.8682 | 19.0 |
| 2.7018 | 5.0 | 2265 | 0.6009 | 37.8781 | 33.7441 | 37.8808 | 37.8682 | 19.0 |
| 2.6272 | 6.0 | 2718 | 0.5331 | 37.8663 | 33.7441 | 37.8808 | 37.8682 | 19.0 |
| 2.5017 | 7.0 | 3171 | 0.4994 | 37.8663 | 33.7441 | 37.8808 | 37.8682 | 19.0 |
| 2.4539 | 8.0 | 3624 | 0.4874 | 37.8663 | 33.7441 | 37.8808 | 37.8682 | 19.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1