Hugging Face's logo

e22vvb
/
ALL_manual_mt5-base_15_spider_no_sch_15_wikiSQL_no_sch

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
e22vvb commited on
Commit
e3c34f5
•
1 Parent(s): 5e30ea7

Model save

Browse files
Files changed (1) hide show
  1. README.md +19 -19
README.md CHANGED
@@ -13,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 0.0276
17
- - Rouge2 Precision: 0.8193
18
- - Rouge2 Recall: 0.5491
19
- - Rouge2 Fmeasure: 0.6245
20
 
21
  ## Model description
22
 
@@ -47,21 +47,21 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
49
  |:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------------:|
50
- | 0.3496 | 1.0 | 1293 | 0.2017 | 0.4711 | 0.3028 | 0.3466 |
51
- | 0.2041 | 2.0 | 2586 | 0.1328 | 0.5656 | 0.3798 | 0.4292 |
52
- | 0.1637 | 3.0 | 3879 | 0.0987 | 0.6111 | 0.4058 | 0.4602 |
53
- | 0.1294 | 4.0 | 5172 | 0.0791 | 0.6546 | 0.4366 | 0.4953 |
54
- | 0.1124 | 5.0 | 6465 | 0.0658 | 0.6947 | 0.4679 | 0.53 |
55
- | 0.0968 | 6.0 | 7758 | 0.0563 | 0.7264 | 0.4901 | 0.5555 |
56
- | 0.084 | 7.0 | 9051 | 0.0480 | 0.7492 | 0.5063 | 0.5737 |
57
- | 0.0782 | 8.0 | 10344 | 0.0428 | 0.7561 | 0.5075 | 0.5768 |
58
- | 0.0701 | 9.0 | 11637 | 0.0379 | 0.7758 | 0.522 | 0.5928 |
59
- | 0.0669 | 10.0 | 12930 | 0.0350 | 0.7904 | 0.5316 | 0.6039 |
60
- | 0.0623 | 11.0 | 14223 | 0.0318 | 0.8102 | 0.5432 | 0.6175 |
61
- | 0.059 | 12.0 | 15516 | 0.0299 | 0.8047 | 0.5413 | 0.615 |
62
- | 0.0562 | 13.0 | 16809 | 0.0286 | 0.8149 | 0.546 | 0.6214 |
63
- | 0.0548 | 14.0 | 18102 | 0.0279 | 0.8167 | 0.5478 | 0.6229 |
64
- | 0.0538 | 15.0 | 19395 | 0.0276 | 0.8193 | 0.5491 | 0.6245 |
65
 
66
 
67
  ### Framework versions
 
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 0.0235
17
+ - Rouge2 Precision: 0.8396
18
+ - Rouge2 Recall: 0.5615
19
+ - Rouge2 Fmeasure: 0.6396
20
 
21
  ## Model description
22
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
49
  |:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------------:|
50
+ | 0.3047 | 1.0 | 1293 | 0.1813 | 0.5141 | 0.3387 | 0.3851 |
51
+ | 0.1829 | 2.0 | 2586 | 0.1190 | 0.6059 | 0.4059 | 0.4595 |
52
+ | 0.1463 | 3.0 | 3879 | 0.0889 | 0.6388 | 0.4276 | 0.4845 |
53
+ | 0.116 | 4.0 | 5172 | 0.0708 | 0.6831 | 0.458 | 0.5194 |
54
+ | 0.1003 | 5.0 | 6465 | 0.0580 | 0.7161 | 0.485 | 0.5489 |
55
+ | 0.0869 | 6.0 | 7758 | 0.0486 | 0.7498 | 0.5046 | 0.5726 |
56
+ | 0.0868 | 7.0 | 9051 | 0.0409 | 0.7736 | 0.5227 | 0.5923 |
57
+ | 0.0698 | 8.0 | 10344 | 0.0365 | 0.7803 | 0.5251 | 0.5963 |
58
+ | 0.0629 | 9.0 | 11637 | 0.0326 | 0.7982 | 0.5368 | 0.6097 |
59
+ | 0.06 | 10.0 | 12930 | 0.0298 | 0.8113 | 0.5456 | 0.62 |
60
+ | 0.0558 | 11.0 | 14223 | 0.0272 | 0.8219 | 0.5506 | 0.6263 |
61
+ | 0.0524 | 12.0 | 15516 | 0.0257 | 0.8257 | 0.5541 | 0.6303 |
62
+ | 0.0497 | 13.0 | 16809 | 0.0245 | 0.8308 | 0.5572 | 0.634 |
63
+ | 0.049 | 14.0 | 18102 | 0.0238 | 0.8389 | 0.5611 | 0.6391 |
64
+ | 0.0479 | 15.0 | 19395 | 0.0235 | 0.8396 | 0.5615 | 0.6396 |
65
 
66
 
67
  ### Framework versions