<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
t5-base-extraction-cnndm_fs0.2-all
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7827
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: 5e-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.8965 | 0.11 | 200 | 2.1313 |
2.2579 | 0.23 | 400 | 1.9594 |
2.1421 | 0.34 | 600 | 1.9014 |
2.0901 | 0.45 | 800 | 1.8741 |
2.0508 | 0.56 | 1000 | 1.8498 |
2.0269 | 0.68 | 1200 | 1.8394 |
2.0047 | 0.79 | 1400 | 1.8227 |
1.9959 | 0.9 | 1600 | 1.8085 |
1.9647 | 1.02 | 1800 | 1.8007 |
1.9629 | 1.13 | 2000 | 1.7903 |
1.9597 | 1.24 | 2200 | 1.7853 |
1.9615 | 1.36 | 2400 | 1.7827 |
1.9778 | 1.47 | 2600 | 1.8071 |
2.0581 | 1.58 | 2800 | 1.8804 |
2.1621 | 1.69 | 3000 | 1.9792 |
2.3313 | 1.81 | 3200 | 2.1481 |
2.4461 | 1.92 | 3400 | 2.1995 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1