|
--- |
|
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: 3.1300 |
|
- Rouge1: 45.8234 |
|
- Rouge2: 27.9023 |
|
- Rougel: 40.0601 |
|
- Rougelsum: 40.1365 |
|
|
|
## 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 | 2.1020 | 44.2638 | 26.5513 | 38.8656 | 38.9574 | |
|
| No log | 2.0 | 380 | 2.0341 | 44.8083 | 27.3491 | 39.2192 | 39.2873 | |
|
| 1.8386 | 3.0 | 570 | 2.0883 | 44.9818 | 27.5372 | 39.702 | 39.7941 | |
|
| 1.8386 | 4.0 | 760 | 2.1829 | 45.3864 | 28.2511 | 40.224 | 40.3422 | |
|
| 0.6628 | 5.0 | 950 | 2.3020 | 45.1704 | 27.6203 | 39.6343 | 39.8564 | |
|
| 0.6628 | 6.0 | 1140 | 2.3936 | 45.245 | 27.5998 | 39.5014 | 39.7109 | |
|
| 0.6628 | 7.0 | 1330 | 2.5143 | 45.419 | 27.8554 | 39.7599 | 39.8859 | |
|
| 0.2204 | 8.0 | 1520 | 2.5889 | 45.3461 | 27.8309 | 39.7638 | 39.7984 | |
|
| 0.2204 | 9.0 | 1710 | 2.6406 | 45.0848 | 27.6269 | 39.499 | 39.5797 | |
|
| 0.1278 | 10.0 | 1900 | 2.6651 | 44.8955 | 27.1523 | 39.0341 | 39.1819 | |
|
| 0.1278 | 11.0 | 2090 | 2.7188 | 44.8196 | 27.3935 | 39.1979 | 39.2786 | |
|
| 0.1278 | 12.0 | 2280 | 2.7608 | 45.3321 | 27.7995 | 39.755 | 39.8835 | |
|
| 0.0849 | 13.0 | 2470 | 2.7928 | 45.3633 | 27.7144 | 39.7197 | 39.8112 | |
|
| 0.0849 | 14.0 | 2660 | 2.8243 | 45.2905 | 27.8178 | 39.8823 | 39.9496 | |
|
| 0.0655 | 15.0 | 2850 | 2.8515 | 45.8272 | 28.2161 | 40.2645 | 40.3717 | |
|
| 0.0655 | 16.0 | 3040 | 2.8778 | 45.4863 | 27.8831 | 39.7118 | 39.7972 | |
|
| 0.0655 | 17.0 | 3230 | 2.9078 | 45.3699 | 27.8244 | 39.5926 | 39.6862 | |
|
| 0.0515 | 18.0 | 3420 | 2.9201 | 45.601 | 28.0129 | 40.0033 | 40.085 | |
|
| 0.0515 | 19.0 | 3610 | 2.9525 | 45.6083 | 27.8189 | 39.8085 | 39.9177 | |
|
| 0.0427 | 20.0 | 3800 | 2.9935 | 45.3061 | 27.2807 | 39.3424 | 39.4389 | |
|
| 0.0427 | 21.0 | 3990 | 3.0076 | 45.2374 | 27.337 | 39.5316 | 39.5977 | |
|
| 0.0427 | 22.0 | 4180 | 3.0457 | 46.1103 | 27.8833 | 40.1059 | 40.1985 | |
|
| 0.0272 | 23.0 | 4370 | 3.0433 | 45.4395 | 27.8712 | 40.001 | 40.0459 | |
|
| 0.0272 | 24.0 | 4560 | 3.0483 | 45.6994 | 27.6396 | 39.8601 | 39.9617 | |
|
| 0.0188 | 25.0 | 4750 | 3.0561 | 45.7877 | 27.808 | 40.1369 | 40.1748 | |
|
| 0.0188 | 26.0 | 4940 | 3.0849 | 45.574 | 27.6999 | 39.8785 | 39.9602 | |
|
| 0.0188 | 27.0 | 5130 | 3.1076 | 45.7393 | 27.8011 | 39.9347 | 39.9889 | |
|
| 0.0149 | 28.0 | 5320 | 3.1277 | 45.6849 | 27.6962 | 39.85 | 39.9121 | |
|
| 0.0149 | 29.0 | 5510 | 3.1181 | 45.8135 | 27.7591 | 39.9626 | 39.9888 | |
|
| 0.0119 | 30.0 | 5700 | 3.1300 | 45.8234 | 27.9023 | 40.0601 | 40.1365 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.0 |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.12.1 |
|
|
