update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- wikihow
|
7 |
+
metrics:
|
8 |
+
- rouge
|
9 |
+
model-index:
|
10 |
+
- name: t5-small-finetuned-wikihow_3epoch_b8_lr3e-4
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Sequence-to-sequence Language Modeling
|
14 |
+
type: text2text-generation
|
15 |
+
dataset:
|
16 |
+
name: wikihow
|
17 |
+
type: wikihow
|
18 |
+
args: all
|
19 |
+
metrics:
|
20 |
+
- name: Rouge1
|
21 |
+
type: rouge
|
22 |
+
value: 27.3718
|
23 |
+
---
|
24 |
+
|
25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
+
should probably proofread and complete it, then remove this comment. -->
|
27 |
+
|
28 |
+
# t5-small-finetuned-wikihow_3epoch_b8_lr3e-4
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the wikihow dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 2.3136
|
33 |
+
- Rouge1: 27.3718
|
34 |
+
- Rouge2: 10.6235
|
35 |
+
- Rougel: 23.3396
|
36 |
+
- Rougelsum: 26.6889
|
37 |
+
- Gen Len: 18.5194
|
38 |
+
|
39 |
+
## Model description
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Intended uses & limitations
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training and evaluation data
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training procedure
|
52 |
+
|
53 |
+
### Training hyperparameters
|
54 |
+
|
55 |
+
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 0.0003
|
57 |
+
- train_batch_size: 8
|
58 |
+
- eval_batch_size: 8
|
59 |
+
- seed: 42
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- num_epochs: 3
|
63 |
+
- mixed_precision_training: Native AMP
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
68 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
69 |
+
| 2.8029 | 0.25 | 5000 | 2.5368 | 25.2267 | 8.9048 | 21.2588 | 24.5804 | 18.4303 |
|
70 |
+
| 2.6924 | 0.51 | 10000 | 2.4725 | 25.6553 | 9.1904 | 21.7633 | 24.9807 | 18.5549 |
|
71 |
+
| 2.6369 | 0.76 | 15000 | 2.4332 | 26.2895 | 9.7203 | 22.3286 | 25.6009 | 18.4185 |
|
72 |
+
| 2.5994 | 1.02 | 20000 | 2.4051 | 26.1779 | 9.5708 | 22.3531 | 25.5357 | 18.561 |
|
73 |
+
| 2.521 | 1.27 | 25000 | 2.3805 | 26.7558 | 10.0411 | 22.7252 | 26.0476 | 18.304 |
|
74 |
+
| 2.5091 | 1.53 | 30000 | 2.3625 | 26.6439 | 10.0698 | 22.6662 | 25.9537 | 18.5437 |
|
75 |
+
| 2.4941 | 1.78 | 35000 | 2.3498 | 26.9322 | 10.2817 | 23.0002 | 26.2604 | 18.4953 |
|
76 |
+
| 2.4848 | 2.03 | 40000 | 2.3424 | 27.0381 | 10.3452 | 22.9749 | 26.3407 | 18.5749 |
|
77 |
+
| 2.4268 | 2.29 | 45000 | 2.3272 | 27.2386 | 10.4595 | 23.1866 | 26.5541 | 18.4954 |
|
78 |
+
| 2.4263 | 2.54 | 50000 | 2.3226 | 27.1489 | 10.532 | 23.1428 | 26.4657 | 18.5583 |
|
79 |
+
| 2.4161 | 2.8 | 55000 | 2.3136 | 27.3718 | 10.6235 | 23.3396 | 26.6889 | 18.5194 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- Transformers 4.18.0
|
85 |
+
- Pytorch 1.10.0+cu111
|
86 |
+
- Datasets 2.0.0
|
87 |
+
- Tokenizers 0.11.6
|