<!-- 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. -->
synpre_copy_1M_t5-small
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0003
- Bleu: 99.9678
- Gen Len: 116.1058
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: 0.0001
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 10000
- training_steps: 80000
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 9.8894 | 0.64 | 5000 | 9.7508 | 0.0028 | 117.6991 |
| 9.5757 | 1.28 | 10000 | 9.3685 | 0.1009 | 102.709 |
| 7.9874 | 1.92 | 15000 | 6.2049 | 3.7294 | 116.9442 |
| 2.8404 | 2.56 | 20000 | 0.8357 | 55.079 | 96.3314 |
| 0.0054 | 3.2 | 25000 | 0.0003 | 99.9678 | 116.1058 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
