Commit
•
0d78bda
1
Parent(s):
aaa605c
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- multilingual model
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- rouge
|
8 |
+
model-index:
|
9 |
+
- name: mt5-small-finetuned-multilingual-xlsum-new
|
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-small-finetuned-multilingual-xlsum-new
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.7679
|
21 |
+
- Rouge1: 9.1993
|
22 |
+
- Rouge2: 2.3416
|
23 |
+
- Rougel: 7.6684
|
24 |
+
- Rougelsum: 7.7074
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5.6e-05
|
44 |
+
- train_batch_size: 2
|
45 |
+
- eval_batch_size: 2
|
46 |
+
- seed: 42
|
47 |
+
- gradient_accumulation_steps: 8
|
48 |
+
- total_train_batch_size: 16
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 5
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
57 |
+
| 3.9684 | 1.0 | 1687 | 2.8902 | 8.0531 | 1.8357 | 6.7234 | 6.7401 |
|
58 |
+
| 3.62 | 2.0 | 3374 | 2.8486 | 8.4881 | 2.0178 | 7.0542 | 7.0854 |
|
59 |
+
| 3.3765 | 3.0 | 5061 | 2.7986 | 8.7796 | 2.2342 | 7.3363 | 7.3645 |
|
60 |
+
| 3.5043 | 4.0 | 6748 | 2.7677 | 9.0486 | 2.3099 | 7.5493 | 7.5685 |
|
61 |
+
| 3.338 | 5.0 | 8435 | 2.7679 | 9.1993 | 2.3416 | 7.6684 | 7.7074 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.19.2
|
67 |
+
- Pytorch 1.11.0+cu113
|
68 |
+
- Datasets 2.2.1
|
69 |
+
- Tokenizers 0.12.1
|