Hugging Face's logo

Seungjun
/
textSummary

Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
Seungjun commited on
Commit
b2f7db4
·
1 Parent(s): 6735d09

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +112 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - rouge
7
+ model-index:
8
+ - name: t5-finetuned-epoch80
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # t5-finetuned-epoch80
16
+
17
+ This model is a fine-tuned version of [Seungjun/t5-small-finetuned-epoch15-finetuned-epoch30](https://huggingface.co/Seungjun/t5-small-finetuned-epoch15-finetuned-epoch30) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.3251
20
+ - Rouge1: 31.3079
21
+ - Rouge2: 19.3788
22
+ - Rougel: 27.8831
23
+ - Rougelsum: 29.9289
24
+ - Gen Len: 18.9869
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: 2e-05
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 16
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 50
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
+ | 1.5167 | 1.0 | 765 | 1.3357 | 30.7806 | 18.8561 | 27.322 | 29.3203 | 18.9915 |
57
+ | 1.5114 | 2.0 | 1530 | 1.3331 | 30.8821 | 18.8886 | 27.4069 | 29.427 | 18.9921 |
58
+ | 1.5027 | 3.0 | 2295 | 1.3318 | 31.0168 | 19.0051 | 27.4976 | 29.5617 | 18.9921 |
59
+ | 1.4929 | 4.0 | 3060 | 1.3310 | 30.9304 | 18.9689 | 27.4371 | 29.4587 | 18.9921 |
60
+ | 1.4753 | 5.0 | 3825 | 1.3288 | 31.1043 | 19.0365 | 27.5671 | 29.626 | 18.9921 |
61
+ | 1.4741 | 6.0 | 4590 | 1.3300 | 31.0773 | 19.0409 | 27.5637 | 29.6434 | 18.9921 |
62
+ | 1.4648 | 7.0 | 5355 | 1.3288 | 31.0566 | 19.0196 | 27.5198 | 29.6072 | 18.9921 |
63
+ | 1.459 | 8.0 | 6120 | 1.3289 | 30.9956 | 18.9737 | 27.5183 | 29.5477 | 18.9921 |
64
+ | 1.4498 | 9.0 | 6885 | 1.3285 | 31.0239 | 18.9609 | 27.5007 | 29.5565 | 18.9921 |
65
+ | 1.4374 | 10.0 | 7650 | 1.3273 | 31.0677 | 19.0404 | 27.57 | 29.6191 | 18.9921 |
66
+ | 1.4494 | 11.0 | 8415 | 1.3268 | 31.0141 | 18.9744 | 27.5356 | 29.6089 | 18.9921 |
67
+ | 1.4315 | 12.0 | 9180 | 1.3278 | 31.134 | 19.0892 | 27.5964 | 29.6855 | 18.9921 |
68
+ | 1.4296 | 13.0 | 9945 | 1.3273 | 31.0735 | 18.9957 | 27.5448 | 29.6213 | 18.9921 |
69
+ | 1.4194 | 14.0 | 10710 | 1.3280 | 31.1302 | 19.0632 | 27.5609 | 29.699 | 18.9921 |
70
+ | 1.4124 | 15.0 | 11475 | 1.3250 | 31.1165 | 19.0928 | 27.5799 | 29.6889 | 18.9921 |
71
+ | 1.4084 | 16.0 | 12240 | 1.3254 | 31.1263 | 19.0793 | 27.646 | 29.6891 | 18.9921 |
72
+ | 1.407 | 17.0 | 13005 | 1.3253 | 31.1609 | 19.1378 | 27.6904 | 29.757 | 18.9921 |
73
+ | 1.4023 | 18.0 | 13770 | 1.3273 | 31.1342 | 19.0976 | 27.6493 | 29.7176 | 18.9869 |
74
+ | 1.4003 | 19.0 | 14535 | 1.3243 | 31.1514 | 19.0548 | 27.6337 | 29.7256 | 18.9869 |
75
+ | 1.3812 | 20.0 | 15300 | 1.3241 | 31.141 | 19.0963 | 27.6509 | 29.7211 | 18.9869 |
76
+ | 1.384 | 21.0 | 16065 | 1.3254 | 31.1899 | 19.1287 | 27.6734 | 29.7467 | 18.9869 |
77
+ | 1.3845 | 22.0 | 16830 | 1.3240 | 31.2449 | 19.128 | 27.7214 | 29.8514 | 18.9869 |
78
+ | 1.3828 | 23.0 | 17595 | 1.3235 | 31.2479 | 19.2076 | 27.7455 | 29.8529 | 18.9869 |
79
+ | 1.3704 | 24.0 | 18360 | 1.3240 | 31.2648 | 19.281 | 27.8002 | 29.9013 | 18.9869 |
80
+ | 1.3696 | 25.0 | 19125 | 1.3246 | 31.2989 | 19.2466 | 27.8263 | 29.8893 | 18.9869 |
81
+ | 1.3655 | 26.0 | 19890 | 1.3241 | 31.2432 | 19.2747 | 27.7854 | 29.8454 | 18.9869 |
82
+ | 1.3642 | 27.0 | 20655 | 1.3243 | 31.2356 | 19.3381 | 27.8251 | 29.8522 | 18.9869 |
83
+ | 1.3591 | 28.0 | 21420 | 1.3258 | 31.2872 | 19.3189 | 27.8329 | 29.8712 | 18.9869 |
84
+ | 1.3617 | 29.0 | 22185 | 1.3253 | 31.2717 | 19.3092 | 27.8307 | 29.8619 | 18.9869 |
85
+ | 1.3528 | 30.0 | 22950 | 1.3243 | 31.2964 | 19.2643 | 27.8174 | 29.8636 | 18.9869 |
86
+ | 1.3507 | 31.0 | 23715 | 1.3242 | 31.3035 | 19.2633 | 27.8234 | 29.9001 | 18.9869 |
87
+ | 1.3555 | 32.0 | 24480 | 1.3249 | 31.1853 | 19.2155 | 27.7712 | 29.8318 | 18.9869 |
88
+ | 1.3519 | 33.0 | 25245 | 1.3237 | 31.2987 | 19.2769 | 27.8254 | 29.9139 | 18.9869 |
89
+ | 1.3485 | 34.0 | 26010 | 1.3251 | 31.2792 | 19.3177 | 27.8478 | 29.9052 | 18.9869 |
90
+ | 1.3431 | 35.0 | 26775 | 1.3249 | 31.3273 | 19.3137 | 27.8582 | 29.9152 | 18.9869 |
91
+ | 1.3441 | 36.0 | 27540 | 1.3243 | 31.2821 | 19.2692 | 27.8287 | 29.8906 | 18.9869 |
92
+ | 1.3394 | 37.0 | 28305 | 1.3244 | 31.2441 | 19.2968 | 27.8135 | 29.8674 | 18.9869 |
93
+ | 1.3417 | 38.0 | 29070 | 1.3245 | 31.2828 | 19.3228 | 27.8211 | 29.8829 | 18.9869 |
94
+ | 1.3387 | 39.0 | 29835 | 1.3249 | 31.2479 | 19.2455 | 27.8016 | 29.8241 | 18.9869 |
95
+ | 1.3382 | 40.0 | 30600 | 1.3250 | 31.2938 | 19.3179 | 27.8289 | 29.8908 | 18.9869 |
96
+ | 1.3314 | 41.0 | 31365 | 1.3251 | 31.3194 | 19.3474 | 27.8534 | 29.9201 | 18.9869 |
97
+ | 1.3305 | 42.0 | 32130 | 1.3255 | 31.3226 | 19.3875 | 27.8795 | 29.9215 | 18.9869 |
98
+ | 1.3291 | 43.0 | 32895 | 1.3253 | 31.3393 | 19.3496 | 27.8896 | 29.9458 | 18.9869 |
99
+ | 1.3297 | 44.0 | 33660 | 1.3252 | 31.3158 | 19.3493 | 27.8796 | 29.941 | 18.9869 |
100
+ | 1.3305 | 45.0 | 34425 | 1.3247 | 31.3665 | 19.3972 | 27.9329 | 29.9925 | 18.9869 |
101
+ | 1.3315 | 46.0 | 35190 | 1.3248 | 31.3447 | 19.3805 | 27.8995 | 29.971 | 18.9869 |
102
+ | 1.3274 | 47.0 | 35955 | 1.3251 | 31.3327 | 19.402 | 27.9104 | 29.965 | 18.9869 |
103
+ | 1.3286 | 48.0 | 36720 | 1.3252 | 31.316 | 19.3811 | 27.8851 | 29.9374 | 18.9869 |
104
+ | 1.3246 | 49.0 | 37485 | 1.3250 | 31.3013 | 19.3684 | 27.8701 | 29.9252 | 18.9869 |
105
+ | 1.3269 | 50.0 | 38250 | 1.3251 | 31.3079 | 19.3788 | 27.8831 | 29.9289 | 18.9869 |
106
+
107
+
108
+ ### Framework versions
109
+
110
+ - Transformers 4.26.1
111
+ - Pytorch 1.13.1+cu116
112
+ - Tokenizers 0.13.2