Hugging Face's logo

Chikashi
/
t5-small-finetuned-wikihow_3epoch_b8_lr3e-3

Text2Text Generation Transformers PyTorch TensorBoard
t5 generated_from_trainer Eval Results Inference Endpoints text-generation-inference
Model card Files Metrics Community
Chikashi commited on
Commit
d0f70b4
•
1 Parent(s): 1296ed3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +87 -0
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-3
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: 27.1711
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-3
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: 2.3163
33
+ - Rouge1: 27.1711
34
+ - Rouge2: 10.6296
35
+ - Rougel: 23.206
36
+ - Rougelsum: 26.4801
37
+ - Gen Len: 18.5433
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: 0.003
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
+ | 3.0734 | 0.25 | 5000 | 2.7884 | 22.4825 | 7.2492 | 19.243 | 21.9167 | 18.0616 |
70
+ | 2.9201 | 0.51 | 10000 | 2.7089 | 24.0869 | 8.0348 | 20.4814 | 23.4541 | 18.5994 |
71
+ | 2.8403 | 0.76 | 15000 | 2.6390 | 24.62 | 8.3776 | 20.8736 | 23.9784 | 18.4676 |
72
+ | 2.7764 | 1.02 | 20000 | 2.5943 | 24.1504 | 8.3933 | 20.8271 | 23.5382 | 18.4078 |
73
+ | 2.6641 | 1.27 | 25000 | 2.5428 | 25.6574 | 9.2371 | 21.8576 | 24.9558 | 18.4249 |
74
+ | 2.6369 | 1.53 | 30000 | 2.5042 | 25.5208 | 9.254 | 21.6673 | 24.8589 | 18.6467 |
75
+ | 2.6 | 1.78 | 35000 | 2.4637 | 26.094 | 9.7003 | 22.3097 | 25.4695 | 18.5065 |
76
+ | 2.5562 | 2.03 | 40000 | 2.4285 | 26.5374 | 9.9222 | 22.5291 | 25.8836 | 18.5553 |
77
+ | 2.4322 | 2.29 | 45000 | 2.3858 | 26.939 | 10.3555 | 23.0211 | 26.2834 | 18.5614 |
78
+ | 2.4106 | 2.54 | 50000 | 2.3537 | 26.7423 | 10.2816 | 22.7986 | 26.083 | 18.5792 |
79
+ | 2.3731 | 2.8 | 55000 | 2.3163 | 27.1711 | 10.6296 | 23.206 | 26.4801 | 18.5433 |
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