Hugging Face's logo

David-Xu
/
t5-small_arxiv_model

Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
Eval Results (legacy)
text-generation-inference
Model card Files
xet
 Metrics Community
David-Xu commited on
Commit
75b48c0
·
verified ·
1 Parent(s): 6a26fa9

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -8
  2. model.safetensors +1 -1
  3. runs/Feb28_03-00-41_891014fe4ff4/events.out.tfevents.1709089242.891014fe4ff4.2709.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Rouge1
24
  type: rouge
25
- value: 0.1788
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,11 +32,11 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the scientific_papers dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 2.5959
36
- - Rouge1: 0.1788
37
- - Rouge2: 0.0689
38
- - Rougel: 0.1435
39
- - Rougelsum: 0.1434
40
  - Gen Len: 19.0
41
 
42
  ## Model description
@@ -62,14 +62,16 @@ The following hyperparameters were used during training:
62
  - seed: 42
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: linear
65
- - num_epochs: 1
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
71
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
72
- | 2.8131 | 1.0 | 20303 | 2.5959 | 0.1788 | 0.0689 | 0.1435 | 0.1434 | 19.0 |
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Rouge1
24
  type: rouge
25
+ value: 0.1782
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the scientific_papers dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.5070
36
+ - Rouge1: 0.1782
37
+ - Rouge2: 0.0681
38
+ - Rougel: 0.1422
39
+ - Rougelsum: 0.1423
40
  - Gen Len: 19.0
41
 
42
  ## Model description
 
62
  - seed: 42
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: linear
65
+ - num_epochs: 3
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
71
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
72
+ | 2.7744 | 1.0 | 20303 | 2.5639 | 0.1793 | 0.0691 | 0.1438 | 0.1439 | 19.0 |
73
+ | 2.6041 | 2.0 | 40606 | 2.5171 | 0.1778 | 0.0677 | 0.142 | 0.142 | 19.0 |
74
+ | 2.5843 | 3.0 | 60909 | 2.5070 | 0.1782 | 0.0681 | 0.1422 | 0.1423 | 19.0 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea8cd49718341317641f5712ae43fe4f509384b25d28666bf161881fcd934dfb
3
  size 242041896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0561177eb7a2e91fd7d4cf12b1d0c69f1b3dd9da93438f5f7992d1967095f546
3
  size 242041896
runs/Feb28_03-00-41_891014fe4ff4/events.out.tfevents.1709089242.891014fe4ff4.2709.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83a2ccb28dca233f305e7c521dfd483cdf563dd1ec994057e53a1c52a2d088d0
3
- size 25687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc5940f7baed35e5ae923cc24a05437053cd22bc773790cda5c9e264fe9af24
3
+ size 26582