jackmedda/google-long-t5-tglobal-base_finetuned_augmented_augmented_llama3.3_70b
This model is a fine-tuned version of google/long-t5-tglobal-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6142
- Accuracy: 0.7647
- F1: 0.8667
- Precision: 0.7647
- Recall: 1.0
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: 2
- eval_batch_size: 2
- 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
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6282 | 1.0 | 77 | 0.6453 | 0.7 | 0.8235 | 0.7 | 1.0 |
| 0.6112 | 2.0 | 154 | 0.7555 | 0.7 | 0.8235 | 0.7 | 1.0 |
| 0.2056 | 3.0 | 231 | 1.2510 | 0.7 | 0.8235 | 0.7 | 1.0 |
| 0.8952 | 4.0 | 308 | 1.6322 | 0.7 | 0.8235 | 0.7 | 1.0 |
| 1.1637 | 5.0 | 385 | 1.6961 | 0.7 | 0.8235 | 0.7 | 1.0 |
| 1.1561 | 6.0 | 462 | 1.8207 | 0.7 | 0.8235 | 0.7 | 1.0 |
| 0.4773 | 7.0 | 539 | 1.8147 | 0.7 | 0.8235 | 0.7 | 1.0 |
| 0.0086 | 8.0 | 616 | 1.8578 | 0.7 | 0.8235 | 0.7 | 1.0 |
| 0.7983 | 9.0 | 693 | 1.7090 | 0.7 | 0.8235 | 0.7 | 1.0 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.3.0+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0