Commit
•
1807c33
1
Parent(s):
0914cd2
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: vit5-base-vietnews-summarization-finetuned-VN
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# vit5-base-vietnews-summarization-finetuned-VN
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [VietAI/vit5-base-vietnews-summarization](https://huggingface.co/VietAI/vit5-base-vietnews-summarization) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.1244
|
| 20 |
+
- Rouge1: 45.0733
|
| 21 |
+
- Rouge2: 21.0468
|
| 22 |
+
- Rougel: 31.9646
|
| 23 |
+
- Rougelsum: 32.5016
|
| 24 |
+
- Gen Len: 18.9707
|
| 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: 2e-05
|
| 44 |
+
- train_batch_size: 4
|
| 45 |
+
- eval_batch_size: 4
|
| 46 |
+
- seed: 42
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 16
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 5
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
| 57 |
+
| No log | 1.0 | 266 | 2.1198 | 45.0345 | 21.2298 | 32.4049 | 33.0139 | 18.9477 |
|
| 58 |
+
| 2.3224 | 2.0 | 533 | 2.0952 | 44.9446 | 20.9462 | 31.9838 | 32.6279 | 18.9665 |
|
| 59 |
+
| 2.3224 | 3.0 | 799 | 2.0923 | 44.8289 | 20.8981 | 31.8825 | 32.4603 | 18.97 |
|
| 60 |
+
| 1.7216 | 4.0 | 1066 | 2.1082 | 44.8034 | 20.8699 | 31.8707 | 32.4384 | 18.9658 |
|
| 61 |
+
| 1.7216 | 4.99 | 1330 | 2.1244 | 45.0733 | 21.0468 | 31.9646 | 32.5016 | 18.9707 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.30.0
|
| 67 |
+
- Pytorch 2.3.0+cu121
|
| 68 |
+
- Datasets 2.20.0
|
| 69 |
+
- Tokenizers 0.13.3
|