update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- amazon_reviews_multi
|
| 8 |
+
metrics:
|
| 9 |
+
- rouge
|
| 10 |
+
model-index:
|
| 11 |
+
- name: summary_tutorial
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Sequence-to-sequence Language Modeling
|
| 15 |
+
type: text2text-generation
|
| 16 |
+
dataset:
|
| 17 |
+
name: amazon_reviews_multi
|
| 18 |
+
type: amazon_reviews_multi
|
| 19 |
+
config: en
|
| 20 |
+
split: train
|
| 21 |
+
args: en
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Rouge1
|
| 24 |
+
type: rouge
|
| 25 |
+
value: 19.4358
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# summary_tutorial
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the amazon_reviews_multi dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 2.8504
|
| 36 |
+
- Rouge1: 19.4358
|
| 37 |
+
- Rouge2: 10.0475
|
| 38 |
+
- Rougel: 18.6327
|
| 39 |
+
- Rougelsum: 18.648
|
| 40 |
+
|
| 41 |
+
## Model description
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Intended uses & limitations
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training and evaluation data
|
| 50 |
+
|
| 51 |
+
More information needed
|
| 52 |
+
|
| 53 |
+
## Training procedure
|
| 54 |
+
|
| 55 |
+
### Training hyperparameters
|
| 56 |
+
|
| 57 |
+
The following hyperparameters were used during training:
|
| 58 |
+
- learning_rate: 5.6e-05
|
| 59 |
+
- train_batch_size: 8
|
| 60 |
+
- eval_batch_size: 8
|
| 61 |
+
- seed: 42
|
| 62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 63 |
+
- lr_scheduler_type: linear
|
| 64 |
+
- num_epochs: 8
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
| 70 |
+
| 2.867 | 1.0 | 771 | 2.7687 | 18.7278 | 10.8323 | 17.9617 | 17.8262 |
|
| 71 |
+
| 2.5363 | 2.0 | 1542 | 2.7741 | 18.4642 | 10.2431 | 17.8719 | 17.7799 |
|
| 72 |
+
| 2.3516 | 3.0 | 2313 | 2.7578 | 18.4591 | 9.5235 | 18.0114 | 17.8761 |
|
| 73 |
+
| 2.216 | 4.0 | 3084 | 2.7938 | 20.2372 | 10.7222 | 19.5686 | 19.5045 |
|
| 74 |
+
| 2.0929 | 5.0 | 3855 | 2.7981 | 19.536 | 10.0232 | 18.7119 | 18.7774 |
|
| 75 |
+
| 2.0 | 6.0 | 4626 | 2.8229 | 18.5138 | 9.6349 | 17.7119 | 17.782 |
|
| 76 |
+
| 1.9479 | 7.0 | 5397 | 2.8397 | 19.3795 | 10.0475 | 18.5904 | 18.532 |
|
| 77 |
+
| 1.9031 | 8.0 | 6168 | 2.8504 | 19.4358 | 10.0475 | 18.6327 | 18.648 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.24.0
|
| 83 |
+
- Pytorch 1.12.1+cu113
|
| 84 |
+
- Datasets 2.7.1
|
| 85 |
+
- Tokenizers 0.13.2
|