results_t5small
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6267
- Rouge1: 0.1691
- Rouge2: 0.056
- Rougel: 0.1335
- Rougelsum: 0.1335
- 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: 0.0001
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.949 | 0.3600 | 3000 | 2.7734 | 0.163 | 0.0518 | 0.1288 | 0.1288 | 19.0 |
| 2.7735 | 0.7199 | 6000 | 2.6960 | 0.1702 | 0.0564 | 0.1344 | 0.1344 | 19.0 |
| 2.5929 | 1.0799 | 9000 | 2.6597 | 0.1709 | 0.0561 | 0.1344 | 0.1344 | 19.0 |
| 2.5929 | 1.4399 | 12000 | 2.6367 | 0.171 | 0.0571 | 0.1351 | 0.1351 | 19.0 |
| 2.7777 | 1.7999 | 15000 | 2.6267 | 0.1691 | 0.056 | 0.1335 | 0.1335 | 19.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1