Hugging Face's logo

mousaazari
/
t5-text2sql

Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
5
mousaazari commited on
Commit
17bac7a
·
1 Parent(s): 64b2a2c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -39
README.md CHANGED
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.1528
18
- - Rouge2 Precision: 0.9252
19
- - Rouge2 Recall: 0.4354
20
- - Rouge2 Fmeasure: 0.5687
21
 
22
  ## Model description
23
 
@@ -48,43 +48,43 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
50
  |:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
51
- | No log | 1.0 | 11 | 2.7311 | 0.0907 | 0.0278 | 0.0409 |
52
- | No log | 2.0 | 22 | 1.9749 | 0.0948 | 0.0281 | 0.0417 |
53
- | No log | 3.0 | 33 | 1.4801 | 0.0998 | 0.0281 | 0.0428 |
54
- | No log | 4.0 | 44 | 1.0439 | 0.0928 | 0.0266 | 0.0405 |
55
- | No log | 5.0 | 55 | 0.7436 | 0.2758 | 0.1199 | 0.1633 |
56
- | No log | 6.0 | 66 | 0.5619 | 0.6723 | 0.3182 | 0.4184 |
57
- | No log | 7.0 | 77 | 0.4470 | 0.6655 | 0.3125 | 0.4093 |
58
- | No log | 8.0 | 88 | 0.3851 | 0.762 | 0.3384 | 0.4508 |
59
- | No log | 9.0 | 99 | 0.3372 | 0.7611 | 0.33 | 0.443 |
60
- | No log | 10.0 | 110 | 0.3113 | 0.7754 | 0.3396 | 0.454 |
61
- | No log | 11.0 | 121 | 0.2832 | 0.7977 | 0.3486 | 0.4682 |
62
- | No log | 12.0 | 132 | 0.2703 | 0.8346 | 0.3786 | 0.5019 |
63
- | No log | 13.0 | 143 | 0.2519 | 0.8379 | 0.3849 | 0.5058 |
64
- | No log | 14.0 | 154 | 0.2411 | 0.856 | 0.3883 | 0.5116 |
65
- | No log | 15.0 | 165 | 0.2274 | 0.8701 | 0.4023 | 0.5275 |
66
- | No log | 16.0 | 176 | 0.2117 | 0.8773 | 0.4049 | 0.5312 |
67
- | No log | 17.0 | 187 | 0.2061 | 0.8841 | 0.4015 | 0.5296 |
68
- | No log | 18.0 | 198 | 0.1957 | 0.8894 | 0.4059 | 0.5349 |
69
- | No log | 19.0 | 209 | 0.1859 | 0.9125 | 0.4274 | 0.5584 |
70
- | No log | 20.0 | 220 | 0.1866 | 0.8914 | 0.4097 | 0.5385 |
71
- | No log | 21.0 | 231 | 0.1846 | 0.8957 | 0.4128 | 0.5423 |
72
- | No log | 22.0 | 242 | 0.1797 | 0.9252 | 0.4354 | 0.5687 |
73
- | No log | 23.0 | 253 | 0.1730 | 0.9252 | 0.4354 | 0.5687 |
74
- | No log | 24.0 | 264 | 0.1645 | 0.9252 | 0.4354 | 0.5687 |
75
- | No log | 25.0 | 275 | 0.1612 | 0.9252 | 0.4354 | 0.5687 |
76
- | No log | 26.0 | 286 | 0.1599 | 0.9252 | 0.4354 | 0.5687 |
77
- | No log | 27.0 | 297 | 0.1570 | 0.9252 | 0.4354 | 0.5687 |
78
- | No log | 28.0 | 308 | 0.1550 | 0.9252 | 0.4354 | 0.5687 |
79
- | No log | 29.0 | 319 | 0.1544 | 0.9252 | 0.4354 | 0.5687 |
80
- | No log | 30.0 | 330 | 0.1534 | 0.9252 | 0.4354 | 0.5687 |
81
- | No log | 31.0 | 341 | 0.1529 | 0.9252 | 0.4354 | 0.5687 |
82
- | No log | 32.0 | 352 | 0.1528 | 0.9252 | 0.4354 | 0.5687 |
83
 
84
 
85
  ### Framework versions
86
 
87
- - Transformers 4.20.1
88
- - Pytorch 1.12.0+cu113
89
- - Datasets 2.3.2
90
  - Tokenizers 0.12.1
 
14
 
15
  This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.3843
18
+ - Rouge2 Precision: 0.8546
19
+ - Rouge2 Recall: 0.3305
20
+ - Rouge2 Fmeasure: 0.4564
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
50
  |:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
51
+ | No log | 1.0 | 11 | 2.6539 | 0.072 | 0.0232 | 0.0349 |
52
+ | No log | 2.0 | 22 | 1.8002 | 0.0465 | 0.0131 | 0.02 |
53
+ | No log | 3.0 | 33 | 1.2897 | 0.1874 | 0.0596 | 0.0859 |
54
+ | No log | 4.0 | 44 | 0.8970 | 0.5344 | 0.232 | 0.3114 |
55
+ | No log | 5.0 | 55 | 0.7295 | 0.7108 | 0.3043 | 0.4135 |
56
+ | No log | 6.0 | 66 | 0.6333 | 0.763 | 0.2887 | 0.4042 |
57
+ | No log | 7.0 | 77 | 0.5959 | 0.7765 | 0.2992 | 0.4134 |
58
+ | No log | 8.0 | 88 | 0.5394 | 0.7621 | 0.2849 | 0.3994 |
59
+ | No log | 9.0 | 99 | 0.5125 | 0.7692 | 0.2915 | 0.4045 |
60
+ | No log | 10.0 | 110 | 0.4889 | 0.8046 | 0.3095 | 0.4295 |
61
+ | No log | 11.0 | 121 | 0.4743 | 0.8536 | 0.3268 | 0.4525 |
62
+ | No log | 12.0 | 132 | 0.4631 | 0.8405 | 0.3233 | 0.4467 |
63
+ | No log | 13.0 | 143 | 0.4494 | 0.8611 | 0.3307 | 0.4572 |
64
+ | No log | 14.0 | 154 | 0.4357 | 0.8687 | 0.3386 | 0.4669 |
65
+ | No log | 15.0 | 165 | 0.4319 | 0.8494 | 0.3271 | 0.4524 |
66
+ | No log | 16.0 | 176 | 0.4243 | 0.8503 | 0.3271 | 0.4519 |
67
+ | No log | 17.0 | 187 | 0.4175 | 0.8647 | 0.3318 | 0.4592 |
68
+ | No log | 18.0 | 198 | 0.4145 | 0.8766 | 0.3375 | 0.4664 |
69
+ | No log | 19.0 | 209 | 0.4073 | 0.8727 | 0.3348 | 0.4632 |
70
+ | No log | 20.0 | 220 | 0.4039 | 0.8766 | 0.3375 | 0.4664 |
71
+ | No log | 21.0 | 231 | 0.4002 | 0.8528 | 0.3291 | 0.4546 |
72
+ | No log | 22.0 | 242 | 0.3939 | 0.8488 | 0.3278 | 0.4524 |
73
+ | No log | 23.0 | 253 | 0.3952 | 0.8492 | 0.3283 | 0.4538 |
74
+ | No log | 24.0 | 264 | 0.3898 | 0.8586 | 0.3313 | 0.4588 |
75
+ | No log | 25.0 | 275 | 0.3869 | 0.8586 | 0.3313 | 0.4588 |
76
+ | No log | 26.0 | 286 | 0.3883 | 0.8532 | 0.3305 | 0.4566 |
77
+ | No log | 27.0 | 297 | 0.3839 | 0.8586 | 0.3313 | 0.4588 |
78
+ | No log | 28.0 | 308 | 0.3831 | 0.8586 | 0.3313 | 0.4588 |
79
+ | No log | 29.0 | 319 | 0.3845 | 0.8546 | 0.3305 | 0.4564 |
80
+ | No log | 30.0 | 330 | 0.3850 | 0.8546 | 0.3305 | 0.4564 |
81
+ | No log | 31.0 | 341 | 0.3843 | 0.8546 | 0.3305 | 0.4564 |
82
+ | No log | 32.0 | 352 | 0.3843 | 0.8546 | 0.3305 | 0.4564 |
83
 
84
 
85
  ### Framework versions
86
 
87
+ - Transformers 4.21.1
88
+ - Pytorch 1.12.1+cu113
89
+ - Datasets 2.4.0
90
  - Tokenizers 0.12.1