Hugging Face's logo

SummerHotBreeze
/
flan-t5-base-dialoguSum_Solar_koen

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
SummerHotBreeze commited on
Commit
9cd2731
·
verified ·
1 Parent(s): 475f1a2

End of training

Browse files
Files changed (4) hide show
  1. README.md +13 -13
  2. logs/events.out.tfevents.1725276563.instance-9781.339997.2 +3 -0
  3. logs/events.out.tfevents.1725276594.instance-9781.339997.3 +3 -0
  4. model.safetensors +1 -1
README.md CHANGED
@@ -18,12 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.7939
22
- - Rouge1: 22.8244
23
- - Rouge2: 12.3775
24
- - Rougel: 16.7527
25
- - Rougelsum: 20.2828
26
- - Gen Len: 15.8
27
 
28
  ## Model description
29
 
@@ -52,13 +52,13 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
56
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
57
- | No log | 1.0 | 5 | 2.9089 | 18.4829 | 8.5926 | 12.7485 | 15.2743 | 15.0 |
58
- | No log | 2.0 | 10 | 2.8538 | 18.5695 | 8.5926 | 12.803 | 15.4475 | 14.8 |
59
- | No log | 3.0 | 15 | 2.8163 | 20.0365 | 10.2116 | 14.1114 | 17.2991 | 15.2 |
60
- | No log | 4.0 | 20 | 2.7939 | 22.8244 | 12.3775 | 16.7527 | 20.2828 | 15.8 |
61
- | No log | 5.0 | 25 | 2.7857 | 22.8244 | 12.3775 | 16.7527 | 20.2828 | 15.8 |
62
 
63
 
64
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.8520
22
+ - Rouge1: 11.9395
23
+ - Rouge2: 3.75
24
+ - Rougel: 10.3395
25
+ - Rougelsum: 11.9395
26
+ - Gen Len: 13.0
27
 
28
  ## Model description
29
 
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
56
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
57
+ | No log | 1.0 | 5 | 2.9176 | 9.0824 | 3.75 | 9.0824 | 9.0824 | 11.6 |
58
+ | No log | 2.0 | 10 | 2.8520 | 11.9395 | 3.75 | 10.3395 | 11.9395 | 13.0 |
59
+ | No log | 3.0 | 15 | 2.8061 | 11.9395 | 3.75 | 10.3395 | 11.9395 | 13.0 |
60
+ | No log | 4.0 | 20 | 2.7792 | 7.3071 | 0.0 | 5.7 | 7.3071 | 16.2 |
61
+ | No log | 5.0 | 25 | 2.7691 | 10.1643 | 0.0 | 7.7381 | 10.1643 | 15.8 |
62
 
63
 
64
  ### Framework versions
logs/events.out.tfevents.1725276563.instance-9781.339997.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:247550a72700addf3e46d0f91e5bfda0a480c5d16788d1bb95566ae6d965dec4
3
+ size 8932
logs/events.out.tfevents.1725276594.instance-9781.339997.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c2b7f0193cc184af369151ceea6092eb0377fb4c7492f3aee5d275964ba752
3
+ size 603
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64a9677520c673aa8adfd92c688cef5b15eb8166d11880f08f857a23523aaac6
3
  size 990345064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5cd5d121fc6580369c746f7e3d5fee7c72f2d2ebd77eeb3fd53633c781faf7
3
  size 990345064