t5-small-finetuned-manimml-1.2
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5385
- Rouge1: 37.8725
- Rouge2: 33.7385
- Rougel: 37.8747
- Rougelsum: 37.8687
- 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 453 | 1.1048 | 40.9262 | 33.7385 | 37.8747 | 37.8687 | 19.0 |
| 3.2333 | 2.0 | 906 | 0.7955 | 37.8725 | 33.7385 | 37.8747 | 37.8687 | 19.0 |
| 2.8355 | 3.0 | 1359 | 0.6407 | 37.8725 | 33.7385 | 37.8747 | 37.8687 | 19.0 |
| 2.6654 | 4.0 | 1812 | 0.5615 | 37.8725 | 33.7385 | 37.8747 | 37.8687 | 19.0 |
| 2.5705 | 5.0 | 2265 | 0.5385 | 37.8725 | 33.7385 | 37.8747 | 37.8687 | 19.0 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1