update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- summarization
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- wiki_lingua
|
8 |
+
metrics:
|
9 |
+
- rouge
|
10 |
+
model-index:
|
11 |
+
- name: wiki_lingua-hi-8-3-5.6e-05-mt5-small-finetuned
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Sequence-to-sequence Language Modeling
|
15 |
+
type: text2text-generation
|
16 |
+
dataset:
|
17 |
+
name: wiki_lingua
|
18 |
+
type: wiki_lingua
|
19 |
+
config: hi
|
20 |
+
split: test
|
21 |
+
args: hi
|
22 |
+
metrics:
|
23 |
+
- name: Rouge1
|
24 |
+
type: rouge
|
25 |
+
value: 1.3405
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# wiki_lingua-hi-8-3-5.6e-05-mt5-small-finetuned
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the wiki_lingua dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 2.4454
|
36 |
+
- Rouge1: 1.3405
|
37 |
+
- Rouge2: 0.3957
|
38 |
+
- Rougel: 1.3311
|
39 |
+
- Rougelsum: 1.3354
|
40 |
+
|
41 |
+
## Model description
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Intended uses & limitations
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training and evaluation data
|
50 |
+
|
51 |
+
More information needed
|
52 |
+
|
53 |
+
## Training procedure
|
54 |
+
|
55 |
+
### Training hyperparameters
|
56 |
+
|
57 |
+
The following hyperparameters were used during training:
|
58 |
+
- learning_rate: 5.6e-05
|
59 |
+
- train_batch_size: 8
|
60 |
+
- eval_batch_size: 8
|
61 |
+
- seed: 42
|
62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
+
- lr_scheduler_type: linear
|
64 |
+
- num_epochs: 3
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
70 |
+
| 4.5276 | 1.0 | 841 | 2.5614 | 1.3305 | 0.3186 | 1.3393 | 1.345 |
|
71 |
+
| 3.0712 | 2.0 | 1682 | 2.4707 | 1.2656 | 0.2856 | 1.2595 | 1.2631 |
|
72 |
+
| 2.9584 | 3.0 | 2523 | 2.4454 | 1.3405 | 0.3957 | 1.3311 | 1.3354 |
|
73 |
+
|
74 |
+
|
75 |
+
### Framework versions
|
76 |
+
|
77 |
+
- Transformers 4.27.4
|
78 |
+
- Pytorch 1.13.0
|
79 |
+
- Datasets 2.1.0
|
80 |
+
- Tokenizers 0.13.2
|