<!-- 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_set_1M_t5-small
This model is a fine-tuned version of t5-small on the tyzhu/synpre_set_1M dataset. It achieves the following results on the evaluation set:
- Loss: 0.0594
- Bleu: 99.1102
- Gen Len: 59.443
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: 200000
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
9.4661 | 6.39 | 5000 | 9.3883 | 0.0246 | 40.7704 |
8.9226 | 12.79 | 10000 | 8.7940 | 0.1992 | 38.5561 |
8.3009 | 19.18 | 15000 | 8.0809 | 0.3425 | 40.0913 |
6.7616 | 25.58 | 20000 | 5.5512 | 7.8795 | 46.1902 |
4.0827 | 31.97 | 25000 | 2.0113 | 27.2238 | 52.2654 |
0.9053 | 38.36 | 30000 | 0.1199 | 94.3993 | 59.2201 |
0.1474 | 44.76 | 35000 | 0.0703 | 98.95 | 59.5058 |
0.0876 | 51.15 | 40000 | 0.0594 | 99.1102 | 59.443 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1