<!-- 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_finetuned_gentextSIM
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7167
- Rouge1: 13.6594
- Rouge2: 6.8495
- Rougel: 11.9371
- Rougelsum: 11.9632
- Gen Len: 13.3918
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 | 25 | 1.1849 | 29.1345 | 15.5888 | 25.7823 | 25.7828 | 11.9897 |
No log | 2.0 | 50 | 0.7564 | 12.1041 | 6.3228 | 9.8401 | 10.0182 | 13.5155 |
No log | 3.0 | 75 | 0.7167 | 13.6594 | 6.8495 | 11.9371 | 11.9632 | 13.3918 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2