<!-- 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-SQuAD-qag-ep6
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0387
- Rouge1: 38.3962
- Rouge2: 17.2138
- Rougel: 35.0757
- Rougelsum: 35.0976
- F1: 17.4776
- Exact Match: 11.8529
- Gen Len: 18.4519
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: 96
- eval_batch_size: 192
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | F1 | Exact Match | Gen Len |
---|---|---|---|---|---|---|---|---|---|---|
1.4851 | 1.02 | 200 | 1.1181 | 37.4066 | 15.7831 | 34.003 | 34.0487 | 15.55 | 9.9661 | 18.4881 |
1.2194 | 2.03 | 400 | 1.0716 | 38.1277 | 16.661 | 34.6265 | 34.6546 | 16.6447 | 10.9821 | 18.5283 |
1.1716 | 3.05 | 600 | 1.0537 | 37.9106 | 16.6251 | 34.5005 | 34.5213 | 17.0402 | 11.1756 | 18.492 |
1.1437 | 4.06 | 800 | 1.0441 | 38.4182 | 17.1721 | 35.0109 | 35.0357 | 17.482 | 11.7078 | 18.4654 |
1.1329 | 5.08 | 1000 | 1.0387 | 38.3962 | 17.2138 | 35.0757 | 35.0976 | 17.4776 | 11.8529 | 18.4519 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1