t5-base_ep_3_bz_8_dt_vnx_dev_1024_128_hydra_1751960715_
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.5427
- Rouge1: 32.6395
- Rouge2: 9.9975
- Rougel: 21.5322
- Rougelsum: 22.6063
- Gen Len: 17.0957
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 166 | 5.6753 | 25.401 | 7.3206 | 16.9393 | 17.7407 | 16.8025 |
| No log | 2.0 | 332 | 5.5653 | 31.0215 | 9.2855 | 20.5366 | 21.5288 | 16.8765 |
| No log | 3.0 | 498 | 5.5427 | 32.6395 | 9.9975 | 21.5322 | 22.6063 | 17.0957 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for tihonn/t5-base_ep_3_bz_8_dt_vnx_dev_1024_128_hydra_1751960715_
Base model
google-t5/t5-base