Commit
•
2641628
1
Parent(s):
4da01dc
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: t5-base-news_headlines
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# t5-base-news_headlines
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.8974
|
| 21 |
+
- Rouge1: 57.2262
|
| 22 |
+
- Rouge2: 42.0378
|
| 23 |
+
- Rougel: 56.5748
|
| 24 |
+
- Rougelsum: 56.5201
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 5e-05
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 7
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
| 55 |
+
| 1.977 | 1.0 | 1531 | 1.3885 | 41.7045 | 23.3673 | 40.7292 | 40.6837 |
|
| 56 |
+
| 1.4827 | 2.0 | 3062 | 1.2265 | 46.2602 | 27.7036 | 45.3412 | 45.3728 |
|
| 57 |
+
| 1.2617 | 3.0 | 4593 | 1.0713 | 49.6738 | 32.0177 | 48.9186 | 48.9156 |
|
| 58 |
+
| 1.1168 | 4.0 | 6124 | 0.9923 | 52.3824 | 35.7493 | 51.7434 | 51.706 |
|
| 59 |
+
| 1.0041 | 5.0 | 7655 | 0.9439 | 55.6842 | 40.0864 | 54.9503 | 55.0016 |
|
| 60 |
+
| 0.9305 | 6.0 | 9186 | 0.9085 | 56.5987 | 41.4443 | 55.9192 | 55.9222 |
|
| 61 |
+
| 0.8763 | 7.0 | 10717 | 0.8974 | 57.2262 | 42.0378 | 56.5748 | 56.5201 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.28.0
|
| 67 |
+
- Pytorch 2.0.1+cu118
|
| 68 |
+
- Datasets 2.12.0
|
| 69 |
+
- Tokenizers 0.13.3
|