t5-small-finetuned-manimml-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: 0.0274
- Rouge1: 26.8452
- Rouge2: 21.6377
- Rougel: 26.8477
- Rougelsum: 26.839
- 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.8108 | 1.0 | 700 | 0.0490 | 26.7634 | 21.5313 | 26.7586 | 26.754 | 19.0 |
| 0.1279 | 2.0 | 1400 | 0.0309 | 26.8037 | 21.5955 | 26.8048 | 26.7959 | 19.0 |
| 0.0757 | 3.0 | 2100 | 0.0274 | 26.8452 | 21.6377 | 26.8477 | 26.839 | 19.0 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1