|
--- |
|
base_model: transformer3/H2-keywordextractor |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: H2-keywordextractor-finetuned-scope-summarization |
|
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. --> |
|
|
|
# H2-keywordextractor-finetuned-scope-summarization |
|
|
|
This model is a fine-tuned version of [transformer3/H2-keywordextractor](https://huggingface.co/transformer3/H2-keywordextractor) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0530 |
|
- Rouge1: 27.6565 |
|
- Rouge2: 24.482 |
|
- Rougel: 27.5611 |
|
- Rougelsum: 27.679 |
|
|
|
## 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: 15 |
|
- eval_batch_size: 15 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:| |
|
| 1.1006 | 1.0 | 23 | 0.4121 | 21.1334 | 15.2908 | 21.0076 | 21.0354 | |
|
| 0.4296 | 2.0 | 46 | 0.3515 | 23.1524 | 16.6481 | 23.1602 | 23.1359 | |
|
| 0.366 | 3.0 | 69 | 0.3156 | 24.2342 | 17.9896 | 24.1637 | 24.1872 | |
|
| 0.3263 | 4.0 | 92 | 0.2776 | 25.3692 | 20.5006 | 25.2976 | 25.3696 | |
|
| 0.2951 | 5.0 | 115 | 0.2587 | 25.929 | 21.3159 | 25.7701 | 25.7813 | |
|
| 0.2798 | 6.0 | 138 | 0.2455 | 27.017 | 23.0395 | 26.8045 | 26.8927 | |
|
| 0.2495 | 7.0 | 161 | 0.2234 | 27.5471 | 24.2424 | 27.3809 | 27.4542 | |
|
| 0.2442 | 8.0 | 184 | 0.2100 | 27.1387 | 23.3789 | 27.0447 | 27.141 | |
|
| 0.2203 | 9.0 | 207 | 0.1937 | 27.4281 | 24.1191 | 27.3809 | 27.4542 | |
|
| 0.2138 | 10.0 | 230 | 0.1733 | 27.2385 | 23.6012 | 27.1529 | 27.2287 | |
|
| 0.1921 | 11.0 | 253 | 0.1512 | 27.5491 | 24.2352 | 27.4878 | 27.5915 | |
|
| 0.1687 | 12.0 | 276 | 0.1339 | 27.5491 | 24.2352 | 27.4878 | 27.5915 | |
|
| 0.1615 | 13.0 | 299 | 0.1153 | 27.3214 | 23.9474 | 27.2381 | 27.3508 | |
|
| 0.1367 | 14.0 | 322 | 0.0990 | 27.3214 | 23.8383 | 27.2381 | 27.3508 | |
|
| 0.1282 | 15.0 | 345 | 0.0845 | 27.3214 | 23.8383 | 27.2381 | 27.3508 | |
|
| 0.1085 | 16.0 | 368 | 0.0784 | 27.4178 | 24.1053 | 27.3275 | 27.4506 | |
|
| 0.1018 | 17.0 | 391 | 0.0631 | 27.4471 | 24.1378 | 27.3612 | 27.4531 | |
|
| 0.085 | 18.0 | 414 | 0.0576 | 27.6565 | 24.482 | 27.5611 | 27.679 | |
|
| 0.0814 | 19.0 | 437 | 0.0545 | 27.6565 | 24.482 | 27.5611 | 27.679 | |
|
| 0.0708 | 20.0 | 460 | 0.0530 | 27.6565 | 24.482 | 27.5611 | 27.679 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
