Commit
•
b3f81f1
1
Parent(s):
0051dc9
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- wiki_lingua
|
| 8 |
+
model-index:
|
| 9 |
+
- name: mt5-base-finetuned-ar-wikilingua
|
| 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 |
+
# mt5-base-finetuned-ar-wikilingua
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the wiki_lingua dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 3.6790
|
| 21 |
+
- Rouge-1: 19.46
|
| 22 |
+
- Rouge-2: 6.82
|
| 23 |
+
- Rouge-l: 17.57
|
| 24 |
+
- Gen Len: 18.83
|
| 25 |
+
- Bertscore: 70.18
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 5e-05
|
| 45 |
+
- train_batch_size: 4
|
| 46 |
+
- eval_batch_size: 4
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_steps: 250
|
| 51 |
+
- num_epochs: 8
|
| 52 |
+
- label_smoothing_factor: 0.1
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge-1 | Rouge-2 | Rouge-l | Gen Len | Bertscore |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:-------:|:---------:|
|
| 58 |
+
| 4.9783 | 1.0 | 5111 | 4.0107 | 15.8 | 4.65 | 14.18 | 18.98 | 68.66 |
|
| 59 |
+
| 4.2093 | 2.0 | 10222 | 3.8664 | 16.46 | 5.17 | 15.08 | 18.91 | 68.5 |
|
| 60 |
+
| 4.0303 | 3.0 | 15333 | 3.7847 | 17.0 | 5.43 | 15.45 | 18.89 | 68.75 |
|
| 61 |
+
| 3.9165 | 4.0 | 20444 | 3.7405 | 17.03 | 5.5 | 15.45 | 18.86 | 68.78 |
|
| 62 |
+
| 3.8396 | 5.0 | 25555 | 3.7102 | 17.14 | 5.57 | 15.48 | 18.87 | 68.92 |
|
| 63 |
+
| 3.7825 | 6.0 | 30666 | 3.6944 | 17.64 | 5.73 | 15.96 | 18.82 | 69.14 |
|
| 64 |
+
| 3.7447 | 7.0 | 35777 | 3.6801 | 17.6 | 5.66 | 15.9 | 18.78 | 69.23 |
|
| 65 |
+
| 3.7203 | 8.0 | 40888 | 3.6790 | 17.94 | 5.81 | 16.21 | 18.81 | 69.29 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.18.0
|
| 71 |
+
- Pytorch 1.10.0+cu111
|
| 72 |
+
- Datasets 2.1.0
|
| 73 |
+
- Tokenizers 0.12.1
|