|
--- |
|
license: apache-2.0 |
|
tags: |
|
- simplification |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-t5-base-clara-med |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# flan-t5-base-clara-med |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2682 |
|
- Rouge1: 28.7943 |
|
- Rouge2: 16.031 |
|
- Rougel: 26.7637 |
|
- Rougelsum: 26.8047 |
|
|
|
## 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 | 1.4589 | 27.2058 | 14.9978 | 25.5534 | 25.5731 | |
|
| No log | 2.0 | 760 | 1.3896 | 27.2408 | 14.7703 | 25.4948 | 25.5166 | |
|
| 1.6471 | 3.0 | 1140 | 1.3369 | 27.4133 | 14.8527 | 25.6991 | 25.6951 | |
|
| 1.6471 | 4.0 | 1520 | 1.3050 | 27.8128 | 15.1101 | 26.1084 | 26.1375 | |
|
| 1.3668 | 5.0 | 1900 | 1.2909 | 27.8076 | 15.3018 | 26.0053 | 26.0502 | |
|
| 1.3668 | 6.0 | 2280 | 1.2732 | 27.9007 | 15.2226 | 26.0983 | 26.1265 | |
|
| 1.3668 | 7.0 | 2660 | 1.2600 | 27.5606 | 14.8875 | 25.6058 | 25.6407 | |
|
| 1.2209 | 8.0 | 3040 | 1.2499 | 28.0251 | 15.3935 | 26.1269 | 26.1526 | |
|
| 1.2209 | 9.0 | 3420 | 1.2510 | 28.2472 | 15.5229 | 26.2721 | 26.2975 | |
|
| 1.1212 | 10.0 | 3800 | 1.2485 | 28.2394 | 15.4929 | 26.2322 | 26.2664 | |
|
| 1.1212 | 11.0 | 4180 | 1.2380 | 28.3943 | 15.4261 | 26.4591 | 26.5035 | |
|
| 1.1212 | 12.0 | 4560 | 1.2373 | 28.3341 | 15.5314 | 26.4204 | 26.4567 | |
|
| 1.0353 | 13.0 | 4940 | 1.2392 | 28.3379 | 15.7147 | 26.4372 | 26.4395 | |
|
| 1.0353 | 14.0 | 5320 | 1.2436 | 28.6789 | 15.7709 | 26.5923 | 26.6221 | |
|
| 0.9837 | 15.0 | 5700 | 1.2447 | 28.801 | 15.9612 | 26.7568 | 26.7808 | |
|
| 0.9837 | 16.0 | 6080 | 1.2406 | 28.3076 | 15.5614 | 26.3192 | 26.3439 | |
|
| 0.9837 | 17.0 | 6460 | 1.2450 | 28.4635 | 15.8162 | 26.5962 | 26.6047 | |
|
| 0.9314 | 18.0 | 6840 | 1.2481 | 28.3993 | 15.63 | 26.3544 | 26.4098 | |
|
| 0.9314 | 19.0 | 7220 | 1.2505 | 28.4367 | 15.8777 | 26.4985 | 26.5426 | |
|
| 0.8877 | 20.0 | 7600 | 1.2536 | 28.5426 | 15.7746 | 26.5987 | 26.6552 | |
|
| 0.8877 | 21.0 | 7980 | 1.2524 | 28.8175 | 16.1677 | 26.8577 | 26.9171 | |
|
| 0.8877 | 22.0 | 8360 | 1.2604 | 28.5719 | 15.9639 | 26.632 | 26.659 | |
|
| 0.8577 | 23.0 | 8740 | 1.2591 | 28.7079 | 15.878 | 26.7358 | 26.7978 | |
|
| 0.8577 | 24.0 | 9120 | 1.2606 | 28.6595 | 15.9726 | 26.6673 | 26.7347 | |
|
| 0.8337 | 25.0 | 9500 | 1.2686 | 28.6858 | 15.9056 | 26.6485 | 26.6785 | |
|
| 0.8337 | 26.0 | 9880 | 1.2654 | 28.6585 | 16.0482 | 26.688 | 26.7329 | |
|
| 0.8337 | 27.0 | 10260 | 1.2618 | 28.7773 | 15.9875 | 26.6868 | 26.7367 | |
|
| 0.8163 | 28.0 | 10640 | 1.2668 | 28.7499 | 16.0041 | 26.7845 | 26.8112 | |
|
| 0.8163 | 29.0 | 11020 | 1.2671 | 28.7373 | 15.9702 | 26.7276 | 26.763 | |
|
| 0.8087 | 30.0 | 11400 | 1.2682 | 28.7943 | 16.031 | 26.7637 | 26.8047 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.0 |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.12.1 |
|
|
