update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- summarization
|
| 4 |
+
- Arat5-base
|
| 5 |
+
- abstractive summarization
|
| 6 |
+
- ar
|
| 7 |
+
- xlsum
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- xlsum
|
| 11 |
+
model-index:
|
| 12 |
+
- name: AraT5-base-title-generation-finetune-ar-xlsum
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# AraT5-base-title-generation-finetune-ar-xlsum
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [UBC-NLP/AraT5-base-title-generation](https://huggingface.co/UBC-NLP/AraT5-base-title-generation) on the xlsum dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 4.2837
|
| 24 |
+
- Rouge-1: 31.55
|
| 25 |
+
- Rouge-2: 14.19
|
| 26 |
+
- Rouge-l: 27.52
|
| 27 |
+
- Gen Len: 18.65
|
| 28 |
+
- Bertscore: 74.0
|
| 29 |
+
|
| 30 |
+
## Model description
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Intended uses & limitations
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training and evaluation data
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Training procedure
|
| 43 |
+
|
| 44 |
+
### Training hyperparameters
|
| 45 |
+
|
| 46 |
+
The following hyperparameters were used during training:
|
| 47 |
+
- learning_rate: 0.0005
|
| 48 |
+
- train_batch_size: 8
|
| 49 |
+
- eval_batch_size: 8
|
| 50 |
+
- seed: 42
|
| 51 |
+
- gradient_accumulation_steps: 16
|
| 52 |
+
- total_train_batch_size: 128
|
| 53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 54 |
+
- lr_scheduler_type: linear
|
| 55 |
+
- lr_scheduler_warmup_steps: 250
|
| 56 |
+
- num_epochs: 10
|
| 57 |
+
- label_smoothing_factor: 0.1
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge-1 | Rouge-2 | Rouge-l | Gen Len | Bertscore |
|
| 62 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:-------:|:---------:|
|
| 63 |
+
| 5.815 | 1.0 | 293 | 4.7437 | 27.05 | 10.49 | 23.56 | 18.03 | 72.56 |
|
| 64 |
+
| 5.0818 | 2.0 | 586 | 4.5004 | 28.92 | 11.97 | 25.09 | 18.61 | 73.08 |
|
| 65 |
+
| 4.7855 | 3.0 | 879 | 4.3910 | 29.66 | 12.57 | 25.79 | 18.58 | 73.3 |
|
| 66 |
+
| 4.588 | 4.0 | 1172 | 4.3469 | 30.22 | 13.05 | 26.36 | 18.59 | 73.61 |
|
| 67 |
+
| 4.4388 | 5.0 | 1465 | 4.3226 | 30.88 | 13.81 | 27.01 | 18.65 | 73.78 |
|
| 68 |
+
| 4.3162 | 6.0 | 1758 | 4.2990 | 30.9 | 13.6 | 26.92 | 18.68 | 73.78 |
|
| 69 |
+
| 4.2178 | 7.0 | 2051 | 4.2869 | 31.35 | 14.01 | 27.41 | 18.57 | 73.96 |
|
| 70 |
+
| 4.1387 | 8.0 | 2344 | 4.2794 | 31.28 | 13.98 | 27.34 | 18.6 | 73.87 |
|
| 71 |
+
| 4.0787 | 9.0 | 2637 | 4.2806 | 31.45 | 14.17 | 27.46 | 18.66 | 73.97 |
|
| 72 |
+
| 4.0371 | 10.0 | 2930 | 4.2837 | 31.55 | 14.19 | 27.52 | 18.65 | 74.0 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.20.0
|
| 78 |
+
- Pytorch 1.11.0+cu113
|
| 79 |
+
- Datasets 2.3.2
|
| 80 |
+
- Tokenizers 0.12.1
|