Commit
•
05de0d3
1
Parent(s):
b254bfb
Training complete !
Browse files- README.md +81 -0
- generation_config.json +6 -0
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: UBC-NLP/AraT5v2-base-1024
|
3 |
+
tags:
|
4 |
+
- summarization
|
5 |
+
- Arat5v2
|
6 |
+
- abstractive summarization
|
7 |
+
- ar
|
8 |
+
- xlsum
|
9 |
+
- generated_from_trainer
|
10 |
+
datasets:
|
11 |
+
- xlsum
|
12 |
+
model-index:
|
13 |
+
- name: AraT5v2-base-1024-finetune-ar-xlsum
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# AraT5v2-base-1024-finetune-ar-xlsum
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [UBC-NLP/AraT5v2-base-1024](https://huggingface.co/UBC-NLP/AraT5v2-base-1024) on the xlsum dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 3.7983
|
25 |
+
- Rouge-1: 33.4
|
26 |
+
- Rouge-2: 16.14
|
27 |
+
- Rouge-l: 29.31
|
28 |
+
- Gen Len: 18.63
|
29 |
+
- Bertscore: 74.57
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 0.0005
|
49 |
+
- train_batch_size: 12
|
50 |
+
- eval_batch_size: 12
|
51 |
+
- seed: 42
|
52 |
+
- gradient_accumulation_steps: 16
|
53 |
+
- total_train_batch_size: 192
|
54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: linear
|
56 |
+
- lr_scheduler_warmup_steps: 250
|
57 |
+
- num_epochs: 10
|
58 |
+
- label_smoothing_factor: 0.1
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge-1 | Rouge-2 | Rouge-l | Gen Len | Bertscore |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:-------:|:---------:|
|
64 |
+
| 6.1614 | 1.0 | 195 | 3.9898 | 28.51 | 12.02 | 24.64 | 18.87 | 72.64 |
|
65 |
+
| 4.5342 | 2.0 | 390 | 3.9048 | 29.5 | 13.01 | 25.85 | 18.53 | 73.34 |
|
66 |
+
| 4.2029 | 3.0 | 585 | 3.8162 | 31.64 | 14.33 | 27.54 | 18.57 | 73.88 |
|
67 |
+
| 3.9689 | 4.0 | 781 | 3.7949 | 31.87 | 14.56 | 27.9 | 18.55 | 74.04 |
|
68 |
+
| 3.8278 | 5.0 | 976 | 3.7702 | 31.85 | 14.58 | 27.74 | 18.74 | 73.96 |
|
69 |
+
| 3.6921 | 6.0 | 1171 | 3.7775 | 32.27 | 14.95 | 28.16 | 18.78 | 74.23 |
|
70 |
+
| 3.5632 | 7.0 | 1367 | 3.7751 | 32.54 | 15.04 | 28.4 | 18.72 | 74.36 |
|
71 |
+
| 3.493 | 8.0 | 1562 | 3.7815 | 32.35 | 14.95 | 28.24 | 18.71 | 74.32 |
|
72 |
+
| 3.4189 | 9.0 | 1757 | 3.7908 | 32.39 | 14.99 | 28.32 | 18.73 | 74.32 |
|
73 |
+
| 3.3492 | 9.98 | 1950 | 3.7983 | 32.6 | 15.19 | 28.5 | 18.72 | 74.35 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.33.1
|
79 |
+
- Pytorch 2.0.1+cu118
|
80 |
+
- Datasets 2.14.5
|
81 |
+
- Tokenizers 0.13.3
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.33.1"
|
6 |
+
}
|