Hugging Face's logo

airjairj
/
MODELLO

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
3
airjairj commited on
Commit
1813cc2
•
1 Parent(s): ddc053f

End of training

Browse files
Files changed (2) hide show
  1. README.md +22 -25
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1007
21
- - Bleu: 17.2983
22
  - Gen Len: 19.0
23
 
24
  ## Model description
@@ -44,32 +44,29 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 20
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
- |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
53
- | 0.5677 | 1.0 | 563 | 0.1742 | 16.3727 | 19.0 |
54
- | 0.2045 | 2.0 | 1126 | 0.1477 | 14.2533 | 19.0 |
55
- | 0.1741 | 3.0 | 1689 | 0.1342 | 16.6158 | 19.0 |
56
- | 0.1583 | 4.0 | 2252 | 0.1219 | 16.6578 | 19.0 |
57
- | 0.1461 | 5.0 | 2815 | 0.1108 | 17.0653 | 19.0 |
58
- | 0.135 | 6.0 | 3378 | 0.1080 | 17.2814 | 19.0 |
59
- | 0.1269 | 7.0 | 3941 | 0.1061 | 17.2708 | 19.0 |
60
- | 0.1187 | 8.0 | 4504 | 0.1041 | 17.2708 | 19.0 |
61
- | 0.1161 | 9.0 | 5067 | 0.1026 | 17.3143 | 19.0 |
62
- | 0.1152 | 10.0 | 5630 | 0.1026 | 17.3132 | 19.0 |
63
- | 0.1138 | 11.0 | 6193 | 0.1022 | 17.2566 | 19.0 |
64
- | 0.1137 | 12.0 | 6756 | 0.1026 | 17.239 | 19.0 |
65
- | 0.1125 | 13.0 | 7319 | 0.1011 | 12.3459 | 19.0 |
66
- | 0.1113 | 14.0 | 7882 | 0.1012 | 16.821 | 19.0 |
67
- | 0.1107 | 15.0 | 8445 | 0.1012 | 17.292 | 19.0 |
68
- | 0.1102 | 16.0 | 9008 | 0.1010 | 17.3121 | 19.0 |
69
- | 0.11 | 17.0 | 9571 | 0.1008 | 17.3154 | 19.0 |
70
- | 0.1096 | 18.0 | 10134 | 0.1012 | 17.2547 | 19.0 |
71
- | 0.1092 | 19.0 | 10697 | 0.1008 | 17.2876 | 19.0 |
72
- | 0.1094 | 20.0 | 11260 | 0.1007 | 17.2983 | 19.0 |
73
 
74
 
75
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1037
21
+ - Bleu: 17.5118
22
  - Gen Len: 19.0
23
 
24
  ## Model description
 
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 17
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
53
+ | 0.5717 | 1.0 | 563 | 0.1765 | 16.6094 | 19.0 |
54
+ | 0.2061 | 2.0 | 1126 | 0.1548 | 16.6781 | 19.0 |
55
+ | 0.175 | 3.0 | 1689 | 0.1364 | 16.7028 | 19.0 |
56
+ | 0.1577 | 4.0 | 2252 | 0.1207 | 16.4921 | 19.0 |
57
+ | 0.1445 | 5.0 | 2815 | 0.1115 | 17.5123 | 19.0 |
58
+ | 0.1323 | 6.0 | 3378 | 0.1090 | 17.1552 | 19.0 |
59
+ | 0.1259 | 7.0 | 3941 | 0.1076 | 16.7197 | 19.0 |
60
+ | 0.1195 | 8.0 | 4504 | 0.1073 | 17.5234 | 19.0 |
61
+ | 0.1174 | 9.0 | 5067 | 0.1058 | 17.5114 | 19.0 |
62
+ | 0.1157 | 10.0 | 5630 | 0.1047 | 16.0392 | 19.0 |
63
+ | 0.1147 | 11.0 | 6193 | 0.1048 | 16.0969 | 19.0 |
64
+ | 0.1141 | 12.0 | 6756 | 0.1050 | 17.5366 | 19.0 |
65
+ | 0.1139 | 13.0 | 7319 | 0.1048 | 17.5218 | 19.0 |
66
+ | 0.1121 | 14.0 | 7882 | 0.1041 | 17.5209 | 19.0 |
67
+ | 0.1124 | 15.0 | 8445 | 0.1039 | 17.5104 | 19.0 |
68
+ | 0.1116 | 16.0 | 9008 | 0.1039 | 17.5145 | 19.0 |
69
+ | 0.1111 | 17.0 | 9571 | 0.1037 | 17.5118 | 19.0 |
 
 
 
70
 
71
 
72
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e4dd6db368f3bf38bdaccfea52818282413c354aa6210a4a473851aaed5c66b
3
  size 242071641
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6af8273000b8e68f32763e171d7a0e1fe96e03a652c76e977f8a5535db37bb6
3
  size 242071641