results_t5small_second25
This model is a fine-tuned version of AbdullahKnn/results_t5small_first25 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4917
- Rouge1: 0.1766
- Rouge2: 0.0591
- Rougel: 0.1381
- Rougelsum: 0.1382
- Gen Len: 20.0
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|---|---|---|---|
| 2.6325 | 0.6398 | 1000 | 2.5410 | 0.1732 | 0.0568 | 0.1345 | 0.1347 | 20.0 |
| 2.5807 | 1.2796 | 2000 | 2.5067 | 0.1756 | 0.0583 | 0.1374 | 0.1375 | 20.0 |
| 2.5674 | 1.9194 | 3000 | 2.4917 | 0.1766 | 0.0591 | 0.1381 | 0.1382 | 20.0 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0