metadata
license: apache-2.0
tags:
- simplification
- generated_from_trainer
metrics:
- rouge
model-index:
- name: flan-t5-base-clara-med
results: []
flan-t5-base-clara-med
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2902
- Rouge1: 28.2733
- Rouge2: 15.323
- Rougel: 26.1421
- Rougelsum: 26.1589
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: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 380 | 1.4639 | 26.4167 | 14.2257 | 24.5659 | 24.5948 |
| No log | 2.0 | 760 | 1.3946 | 26.7094 | 14.6358 | 25.0516 | 25.075 |
| 1.6466 | 3.0 | 1140 | 1.3480 | 27.3758 | 14.6821 | 25.5935 | 25.6007 |
| 1.6466 | 4.0 | 1520 | 1.3221 | 28.0769 | 14.9721 | 26.131 | 26.1506 |
| 1.3671 | 5.0 | 1900 | 1.2988 | 27.8019 | 14.9244 | 25.8242 | 25.8322 |
| 1.3671 | 6.0 | 2280 | 1.2965 | 27.9071 | 15.3235 | 26.1385 | 26.104 |
| 1.3671 | 7.0 | 2660 | 1.2802 | 28.1866 | 15.4793 | 26.301 | 26.3031 |
| 1.2248 | 8.0 | 3040 | 1.2733 | 27.9974 | 15.4379 | 26.1087 | 26.1159 |
| 1.2248 | 9.0 | 3420 | 1.2591 | 28.2545 | 15.5006 | 26.2812 | 26.3306 |
| 1.1155 | 10.0 | 3800 | 1.2609 | 27.8029 | 15.0837 | 25.7989 | 25.8486 |
| 1.1155 | 11.0 | 4180 | 1.2612 | 27.676 | 15.0786 | 25.6261 | 25.6458 |
| 1.1155 | 12.0 | 4560 | 1.2616 | 27.6811 | 15.0935 | 25.6905 | 25.7125 |
| 1.0337 | 13.0 | 4940 | 1.2562 | 27.88 | 15.2395 | 25.8875 | 25.8988 |
| 1.0337 | 14.0 | 5320 | 1.2624 | 27.9858 | 15.2151 | 25.9785 | 26.0226 |
| 0.9784 | 15.0 | 5700 | 1.2674 | 28.044 | 15.1312 | 25.8866 | 25.9514 |
| 0.9784 | 16.0 | 6080 | 1.2588 | 28.1022 | 15.3599 | 26.0641 | 26.0762 |
| 0.9784 | 17.0 | 6460 | 1.2676 | 27.864 | 15.1432 | 25.8981 | 25.9221 |
| 0.9246 | 18.0 | 6840 | 1.2620 | 27.8826 | 15.1457 | 25.8041 | 25.8971 |
| 0.9246 | 19.0 | 7220 | 1.2671 | 27.965 | 15.0059 | 25.94 | 25.9831 |
| 0.8891 | 20.0 | 7600 | 1.2733 | 28.3035 | 15.3041 | 26.2411 | 26.2723 |
| 0.8891 | 21.0 | 7980 | 1.2748 | 28.5205 | 15.4851 | 26.4543 | 26.4725 |
| 0.8891 | 22.0 | 8360 | 1.2793 | 28.3018 | 15.3251 | 26.2781 | 26.3203 |
| 0.8578 | 23.0 | 8740 | 1.2788 | 28.039 | 15.238 | 25.9371 | 25.9856 |
| 0.8578 | 24.0 | 9120 | 1.2901 | 28.3312 | 15.3396 | 26.1722 | 26.1993 |
| 0.8299 | 25.0 | 9500 | 1.2863 | 28.0727 | 15.0182 | 25.91 | 25.9577 |
| 0.8299 | 26.0 | 9880 | 1.2845 | 28.1828 | 15.1338 | 26.039 | 26.0493 |
| 0.8299 | 27.0 | 10260 | 1.2819 | 28.1547 | 15.091 | 26.0256 | 26.0346 |
| 0.8137 | 28.0 | 10640 | 1.2859 | 28.2203 | 15.3225 | 26.1493 | 26.1591 |
| 0.8137 | 29.0 | 11020 | 1.2902 | 28.2459 | 15.3142 | 26.1283 | 26.1382 |
| 0.8061 | 30.0 | 11400 | 1.2902 | 28.2733 | 15.323 | 26.1421 | 26.1589 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0
- Datasets 2.8.0
- Tokenizers 0.12.1