Hugging Face's logo

domenicrosati
/
t5-small-finetuned-contradiction

Summarization Transformers PyTorch TensorBoard
t5 text2text-generation generated_from_trainer Eval Results Inference Endpoints text-generation-inference
Model card Files Metrics Community
4
domenicrosati commited on
Commit
d67265d
•
1 Parent(s): f7c2137

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -11
README.md CHANGED
@@ -20,7 +20,7 @@ model-index:
20
  metrics:
21
  - name: Rouge1
22
  type: rouge
23
- value: 34.4566
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,11 +30,11 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  This model is a fine-tuned version of [domenicrosati/t5-small-finetuned-contradiction](https://huggingface.co/domenicrosati/t5-small-finetuned-contradiction) on the snli dataset.
32
  It achieves the following results on the evaluation set:
33
- - Loss: 2.0953
34
- - Rouge1: 34.4566
35
- - Rouge2: 14.7585
36
- - Rougel: 32.7187
37
- - Rougelsum: 32.7372
38
 
39
  ## Model description
40
 
@@ -59,17 +59,21 @@ The following hyperparameters were used during training:
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
- - num_epochs: 4
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
68
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
69
- | 2.0722 | 1.0 | 2863 | 2.1159 | 34.4508 | 14.7296 | 32.684 | 32.6938 |
70
- | 2.1261 | 2.0 | 5726 | 2.1038 | 34.4131 | 14.7231 | 32.6427 | 32.6554 |
71
- | 2.1192 | 3.0 | 8589 | 2.0975 | 34.491 | 14.6856 | 32.7155 | 32.7326 |
72
- | 2.1186 | 4.0 | 11452 | 2.0953 | 34.5066 | 14.7893 | 32.772 | 32.7931 |
 
 
 
 
73
 
74
 
75
  ### Framework versions
20
  metrics:
21
  - name: Rouge1
22
  type: rouge
23
+ value: 34.3503
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
 
31
  This model is a fine-tuned version of [domenicrosati/t5-small-finetuned-contradiction](https://huggingface.co/domenicrosati/t5-small-finetuned-contradiction) on the snli dataset.
32
  It achieves the following results on the evaluation set:
33
+ - Loss: 2.0662
34
+ - Rouge1: 34.3503
35
+ - Rouge2: 14.671
36
+ - Rougel: 32.5398
37
+ - Rougelsum: 32.5331
38
 
39
  ## Model description
40
 
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
+ - num_epochs: 8
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
68
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
69
+ | 2.0071 | 1.0 | 2863 | 2.1018 | 34.4519 | 14.6277 | 32.6441 | 32.6415 |
70
+ | 2.0704 | 2.0 | 5726 | 2.0897 | 34.4688 | 14.7508 | 32.6253 | 32.6227 |
71
+ | 2.0738 | 3.0 | 8589 | 2.0808 | 34.4291 | 14.5548 | 32.6263 | 32.6384 |
72
+ | 2.0788 | 4.0 | 11452 | 2.0744 | 34.6759 | 14.842 | 32.8169 | 32.823 |
73
+ | 2.0781 | 5.0 | 14315 | 2.0714 | 34.4961 | 14.7307 | 32.6362 | 32.6378 |
74
+ | 2.0687 | 6.0 | 17178 | 2.0674 | 34.6406 | 14.8359 | 32.8403 | 32.8423 |
75
+ | 2.0627 | 7.0 | 20041 | 2.0671 | 34.526 | 14.6943 | 32.6919 | 32.694 |
76
+ | 2.0585 | 8.0 | 22904 | 2.0662 | 34.4196 | 14.7107 | 32.607 | 32.6035 |
77
 
78
 
79
  ### Framework versions