Hugging Face's logo

Yuch
/
flan-t5-subjective

Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
1
Fan commited on
Commit
63dc5a3
·
1 Parent(s): 51f0f1f

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -10
  2. logs/events.out.tfevents.1690039147.Emilia88.33168.0 +2 -2
  3. pytorch_model.bin +1 -1
README.md CHANGED
@@ -5,23 +5,23 @@ tags:
5
  metrics:
6
  - rouge
7
  model-index:
8
- - name: flan-t5-subjective
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
- # flan-t5-subjective
16
 
17
  This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0221
20
- - Rouge1: 98.8686
21
  - Rouge2: 0.0
22
- - Rougel: 98.8686
23
- - Rougelsum: 98.8686
24
- - Gen Len: 2.0009
25
 
26
  ## Model description
27
 
@@ -56,9 +56,9 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
58
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
59
- | 0.6648 | 1.0 | 1149 | 0.1716 | 81.201 | 0.0 | 81.201 | 81.027 | 2.0009 |
60
- | 0.1307 | 2.0 | 2298 | 0.0406 | 97.8242 | 0.0 | 97.8242 | 97.8242 | 2.0009 |
61
- | 0.07 | 3.0 | 3447 | 0.0221 | 98.8686 | 0.0 | 98.8686 | 98.8686 | 2.0009 |
62
 
63
 
64
  ### Framework versions
 
5
  metrics:
6
  - rouge
7
  model-index:
8
+ - name: flan-t5-large
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
+ # flan-t5-large
16
 
17
  This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0394
20
+ - Rouge1: 97.7372
21
  - Rouge2: 0.0
22
+ - Rougel: 97.6501
23
+ - Rougelsum: 97.6501
24
+ - Gen Len: 2.0026
25
 
26
  ## Model description
27
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
58
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
59
+ | 0.1703 | 1.0 | 1149 | 0.0849 | 96.2576 | 0.0 | 96.3446 | 96.2576 | 2.0026 |
60
+ | 0.066 | 2.0 | 2298 | 0.0629 | 96.9539 | 0.0 | 96.9539 | 96.9539 | 2.0026 |
61
+ | 0.0496 | 3.0 | 3447 | 0.0394 | 97.7372 | 0.0 | 97.6501 | 97.6501 | 2.0026 |
62
 
63
 
64
  ### Framework versions
logs/events.out.tfevents.1690039147.Emilia88.33168.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:388fee621d352ea59a8c5b81c75b12a42f2899e8d05ab0c3d2674c282a2f5a09
3
- size 4979
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a30ec2f4ac7d247d9be7bc7f67cada5dedd5eba811887a201cf8ed2b8926b6
3
+ size 7011
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bffdf009b9dda75861730279b3006a2083e94738dc77814b83aa7287db46690
3
  size 1566485509
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c502db68e1e29519321caa27b390959edac0b54c597e079804cbfdfff7fca12
3
  size 1566485509