|
--- |
|
license: apache-2.0 |
|
base_model: t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-small-finetuned-xsum |
|
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. --> |
|
|
|
# t5-small-finetuned-xsum |
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2397 |
|
- Rouge1: 39.9145 |
|
- Rouge2: 33.183 |
|
- Rougel: 39.9484 |
|
- Rougelsum: 39.9376 |
|
- Gen Len: 19.0 |
|
|
|
## 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: 2e-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: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| No log | 1.0 | 90 | 3.4654 | 9.8007 | 0.2231 | 9.4993 | 9.501 | 18.6889 | |
|
| No log | 2.0 | 180 | 2.1906 | 10.4443 | 0.2158 | 9.8828 | 9.8755 | 18.8972 | |
|
| No log | 3.0 | 270 | 1.3067 | 11.7213 | 0.5145 | 10.913 | 10.9345 | 18.8528 | |
|
| No log | 4.0 | 360 | 0.7369 | 14.9807 | 1.4227 | 13.7179 | 13.7131 | 18.8333 | |
|
| No log | 5.0 | 450 | 0.6143 | 19.8511 | 4.6089 | 18.0244 | 17.9558 | 18.7083 | |
|
| 2.447 | 6.0 | 540 | 0.5312 | 23.1026 | 8.6515 | 20.7866 | 20.757 | 18.7139 | |
|
| 2.447 | 7.0 | 630 | 0.4782 | 21.9961 | 9.3626 | 19.7651 | 19.7488 | 18.5944 | |
|
| 2.447 | 8.0 | 720 | 0.4365 | 16.4406 | 6.5397 | 14.9694 | 14.9816 | 18.6639 | |
|
| 2.447 | 9.0 | 810 | 0.3603 | 6.9337 | 3.7397 | 6.6337 | 6.6621 | 18.9028 | |
|
| 2.447 | 10.0 | 900 | 0.2696 | 24.2884 | 19.0601 | 24.1044 | 24.1488 | 18.9694 | |
|
| 2.447 | 11.0 | 990 | 0.2590 | 39.2002 | 32.3107 | 39.202 | 39.1928 | 19.0 | |
|
| 0.572 | 12.0 | 1080 | 0.2546 | 39.0083 | 32.1464 | 39.0296 | 38.9988 | 19.0 | |
|
| 0.572 | 13.0 | 1170 | 0.2486 | 39.519 | 32.7114 | 39.5614 | 39.5391 | 19.0 | |
|
| 0.572 | 14.0 | 1260 | 0.2465 | 39.589 | 32.8014 | 39.6298 | 39.6092 | 19.0 | |
|
| 0.572 | 15.0 | 1350 | 0.2444 | 39.5831 | 32.7959 | 39.6266 | 39.6123 | 19.0 | |
|
| 0.572 | 16.0 | 1440 | 0.2427 | 39.7174 | 32.9525 | 39.7513 | 39.7311 | 19.0 | |
|
| 0.3469 | 17.0 | 1530 | 0.2412 | 39.8478 | 33.0999 | 39.8901 | 39.8708 | 19.0 | |
|
| 0.3469 | 18.0 | 1620 | 0.2401 | 39.8528 | 33.1031 | 39.8819 | 39.873 | 19.0 | |
|
| 0.3469 | 19.0 | 1710 | 0.2398 | 39.9283 | 33.1964 | 39.9502 | 39.9533 | 19.0 | |
|
| 0.3469 | 20.0 | 1800 | 0.2397 | 39.9145 | 33.183 | 39.9484 | 39.9376 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|
