domenicrosati commited on
Commit
e3341e0
1 Parent(s): c3fda7a

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: 34.2745
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,13 +28,13 @@ should probably proofread and complete it, then remove this comment. -->
28
 
29
  # t5-small-finetuned-contradiction
30
 
31
- This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the snli dataset.
32
  It achieves the following results on the evaluation set:
33
- - Loss: 2.1770
34
- - Rouge1: 34.2745
35
- - Rouge2: 14.6382
36
- - Rougel: 32.5159
37
- - Rougelsum: 32.519
38
 
39
  ## Model description
40
 
@@ -59,13 +59,17 @@ 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: 1
 
63
 
64
  ### Training results
65
 
66
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
67
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
68
- | 2.2392 | 1.0 | 2863 | 2.1770 | 34.3717 | 14.682 | 32.6218 | 32.6239 |
 
 
 
69
 
70
 
71
  ### Framework versions
 
20
  metrics:
21
  - name: Rouge1
22
  type: rouge
23
+ value: 34.3638
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
28
 
29
  # t5-small-finetuned-contradiction
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: 2.1269
34
+ - Rouge1: 34.3638
35
+ - Rouge2: 14.7916
36
+ - Rougel: 32.6308
37
+ - Rougelsum: 32.6288
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: 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
+ | 2.1984 | 1.0 | 2863 | 2.1556 | 34.4429 | 14.6791 | 32.5812 | 32.5896 |
70
+ | 2.2085 | 2.0 | 5726 | 2.1390 | 34.3719 | 14.731 | 32.5979 | 32.5949 |
71
+ | 2.188 | 3.0 | 8589 | 2.1302 | 34.4276 | 14.7191 | 32.62 | 32.6132 |
72
+ | 2.1768 | 4.0 | 11452 | 2.1269 | 34.4408 | 14.8235 | 32.7067 | 32.7065 |
73
 
74
 
75
  ### Framework versions