|
--- |
|
tags: |
|
- simplification |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: NASES-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. --> |
|
|
|
# NASES-clara-med |
|
|
|
This model is a fine-tuned version of [ELiRF/NASES](https://huggingface.co/ELiRF/NASES) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.3274 |
|
- Rouge1: 43.5242 |
|
- Rouge2: 25.5006 |
|
- Rougel: 37.6746 |
|
- Rougelsum: 37.9494 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | 190 | 2.2062 | 42.852 | 24.8838 | 37.1452 | 37.3371 | |
|
| No log | 2.0 | 380 | 2.3578 | 37.9691 | 19.9011 | 32.0423 | 32.1643 | |
|
| 1.9348 | 3.0 | 570 | 2.3038 | 41.0743 | 22.9938 | 35.4133 | 35.7045 | |
|
| 1.9348 | 4.0 | 760 | 2.2657 | 43.452 | 25.738 | 37.9271 | 38.184 | |
|
| 0.8021 | 5.0 | 950 | 2.3763 | 43.6414 | 25.6831 | 37.8838 | 38.1249 | |
|
| 0.8021 | 6.0 | 1140 | 2.5113 | 43.0882 | 25.4964 | 37.5245 | 37.7459 | |
|
| 0.8021 | 7.0 | 1330 | 2.6203 | 43.164 | 25.1229 | 37.396 | 37.7116 | |
|
| 0.2689 | 8.0 | 1520 | 2.7020 | 43.7588 | 25.7127 | 37.9395 | 38.1406 | |
|
| 0.2689 | 9.0 | 1710 | 2.7533 | 43.3676 | 25.2676 | 37.5607 | 37.8348 | |
|
| 0.1474 | 10.0 | 1900 | 2.8033 | 43.7734 | 25.7325 | 37.8845 | 38.161 | |
|
| 0.1474 | 11.0 | 2090 | 2.8847 | 43.1775 | 25.4384 | 37.4397 | 37.7056 | |
|
| 0.1474 | 12.0 | 2280 | 2.9204 | 43.6149 | 25.6053 | 37.8689 | 38.121 | |
|
| 0.0924 | 13.0 | 2470 | 2.9404 | 43.355 | 25.458 | 37.4775 | 37.7391 | |
|
| 0.0924 | 14.0 | 2660 | 2.9606 | 43.7408 | 25.7361 | 38.0951 | 38.3446 | |
|
| 0.0666 | 15.0 | 2850 | 2.9954 | 43.4987 | 25.5428 | 37.5166 | 37.7468 | |
|
| 0.0666 | 16.0 | 3040 | 3.0491 | 43.8303 | 25.4726 | 37.8056 | 38.0368 | |
|
| 0.0666 | 17.0 | 3230 | 3.0872 | 43.8177 | 25.9315 | 37.9765 | 38.2842 | |
|
| 0.0485 | 18.0 | 3420 | 3.0743 | 43.0783 | 25.1678 | 37.3844 | 37.6768 | |
|
| 0.0485 | 19.0 | 3610 | 3.1571 | 43.5241 | 25.5695 | 37.7233 | 37.9743 | |
|
| 0.0328 | 20.0 | 3800 | 3.1866 | 43.8114 | 25.6402 | 37.7608 | 37.9713 | |
|
| 0.0328 | 21.0 | 3990 | 3.1502 | 43.7322 | 25.6384 | 37.9642 | 38.1954 | |
|
| 0.0328 | 22.0 | 4180 | 3.1723 | 43.5597 | 25.291 | 37.5834 | 37.8289 | |
|
| 0.0264 | 23.0 | 4370 | 3.2214 | 43.251 | 24.8926 | 37.0472 | 37.2819 | |
|
| 0.0264 | 24.0 | 4560 | 3.2764 | 43.469 | 25.2663 | 37.3452 | 37.5562 | |
|
| 0.0169 | 25.0 | 4750 | 3.3104 | 44.0058 | 25.8218 | 38.0374 | 38.2664 | |
|
| 0.0169 | 26.0 | 4940 | 3.2820 | 43.4012 | 25.3515 | 37.5514 | 37.7375 | |
|
| 0.0169 | 27.0 | 5130 | 3.3169 | 43.3498 | 25.2935 | 37.3567 | 37.5987 | |
|
| 0.013 | 28.0 | 5320 | 3.3005 | 43.8029 | 25.6506 | 38.053 | 38.2852 | |
|
| 0.013 | 29.0 | 5510 | 3.3266 | 43.711 | 25.5171 | 37.6826 | 37.9781 | |
|
| 0.0109 | 30.0 | 5700 | 3.3274 | 43.5242 | 25.5006 | 37.6746 | 37.9494 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.0 |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.12.1 |
|
|
