Commit
•
0898e8e
1
Parent(s):
bc887f2
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- xlsum
|
| 8 |
+
metrics:
|
| 9 |
+
- rouge
|
| 10 |
+
model-index:
|
| 11 |
+
- name: AraBART-finetuned-ar
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Sequence-to-sequence Language Modeling
|
| 15 |
+
type: text2text-generation
|
| 16 |
+
dataset:
|
| 17 |
+
name: xlsum
|
| 18 |
+
type: xlsum
|
| 19 |
+
args: arabic
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Rouge1
|
| 22 |
+
type: rouge
|
| 23 |
+
value: 2.2459
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 27 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 28 |
+
|
| 29 |
+
# AraBART-finetuned-ar
|
| 30 |
+
|
| 31 |
+
This model is a fine-tuned version of [moussaKam/AraBART](https://huggingface.co/moussaKam/AraBART) on the xlsum dataset.
|
| 32 |
+
It achieves the following results on the evaluation set:
|
| 33 |
+
- Loss: 2.3785
|
| 34 |
+
- Rouge1: 2.2459
|
| 35 |
+
- Rouge2: 0.0
|
| 36 |
+
- Rougel: 2.2459
|
| 37 |
+
- Rougelsum: 2.2459
|
| 38 |
+
- Gen Len: 19.695
|
| 39 |
+
|
| 40 |
+
## Model description
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Intended uses & limitations
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training and evaluation data
|
| 49 |
+
|
| 50 |
+
More information needed
|
| 51 |
+
|
| 52 |
+
## Training procedure
|
| 53 |
+
|
| 54 |
+
### Training hyperparameters
|
| 55 |
+
|
| 56 |
+
The following hyperparameters were used during training:
|
| 57 |
+
- learning_rate: 5e-05
|
| 58 |
+
- train_batch_size: 4
|
| 59 |
+
- eval_batch_size: 4
|
| 60 |
+
- seed: 42
|
| 61 |
+
- gradient_accumulation_steps: 16
|
| 62 |
+
- total_train_batch_size: 64
|
| 63 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 64 |
+
- lr_scheduler_type: linear
|
| 65 |
+
- lr_scheduler_warmup_ratio: 0.6
|
| 66 |
+
- num_epochs: 10
|
| 67 |
+
|
| 68 |
+
### Training results
|
| 69 |
+
|
| 70 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 71 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
| 72 |
+
| No log | 0.98 | 32 | 2.7774 | 1.0638 | 0.0 | 1.0638 | 1.182 | 19.5177 |
|
| 73 |
+
| No log | 1.98 | 64 | 2.4730 | 1.182 | 0.0 | 1.3002 | 1.182 | 19.8121 |
|
| 74 |
+
| No log | 2.98 | 96 | 2.4129 | 2.3641 | 0.3546 | 2.3641 | 2.3641 | 19.8298 |
|
| 75 |
+
| No log | 3.98 | 128 | 2.3724 | 2.1277 | 0.3546 | 2.1277 | 2.1277 | 19.8121 |
|
| 76 |
+
| No log | 4.98 | 160 | 2.3560 | 1.8913 | 0.3546 | 1.8913 | 1.8913 | 19.805 |
|
| 77 |
+
| No log | 5.98 | 192 | 2.3574 | 1.5366 | 0.0 | 1.5366 | 1.6548 | 19.7979 |
|
| 78 |
+
| No log | 6.98 | 224 | 2.3676 | 2.1277 | 0.3546 | 2.2459 | 2.1277 | 19.6348 |
|
| 79 |
+
| No log | 7.98 | 256 | 2.3656 | 2.0095 | 0.0 | 2.0095 | 2.0095 | 19.844 |
|
| 80 |
+
| No log | 8.98 | 288 | 2.3751 | 2.2459 | 0.0 | 2.3641 | 2.2459 | 19.6738 |
|
| 81 |
+
| No log | 9.98 | 320 | 2.3785 | 2.2459 | 0.0 | 2.2459 | 2.2459 | 19.695 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Framework versions
|
| 85 |
+
|
| 86 |
+
- Transformers 4.17.0
|
| 87 |
+
- Pytorch 1.10.0+cu111
|
| 88 |
+
- Datasets 2.0.0
|
| 89 |
+
- Tokenizers 0.11.6
|