Hugging Face's logo

hmueller25
/
long-t5-tglobal-base-german-law

Transformers
Safetensors
longt5
text2text-generation
Generated from Trainer
Model card Files Community
hmueller25 commited on
Commit
e2ed4bb
·
verified ·
1 Parent(s): 5415daa

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -10
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 3.3280
22
- - Rouge1: 0.0693
23
- - Rouge2: 0.0202
24
- - Rougel: 0.0626
25
- - Rougelsum: 0.0633
26
  - Gen Len: 20.0
27
 
28
  ## Model description
@@ -44,7 +44,7 @@ More information needed
44
  The following hyperparameters were used during training:
45
  - learning_rate: 2e-05
46
  - train_batch_size: 1
47
- - eval_batch_size: 1
48
  - seed: 42
49
  - gradient_accumulation_steps: 8
50
  - total_train_batch_size: 8
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
58
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
59
- | 5.5906 | 1.0 | 49 | 9.4417 | 0.0375 | 0.0103 | 0.0369 | 0.0377 | 20.0 |
60
- | 4.6503 | 2.0 | 98 | 3.7947 | 0.0634 | 0.0206 | 0.0555 | 0.0568 | 20.0 |
61
- | 3.6625 | 3.0 | 147 | 3.4385 | 0.072 | 0.0236 | 0.0631 | 0.0631 | 20.0 |
62
- | 3.1628 | 4.0 | 196 | 3.3280 | 0.0693 | 0.0202 | 0.0626 | 0.0633 | 20.0 |
63
 
64
 
65
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.4575
22
+ - Rouge1: 0.072
23
+ - Rouge2: 0.0236
24
+ - Rougel: 0.0631
25
+ - Rougelsum: 0.0631
26
  - Gen Len: 20.0
27
 
28
  ## Model description
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 2e-05
46
  - train_batch_size: 1
47
+ - eval_batch_size: 4
48
  - seed: 42
49
  - gradient_accumulation_steps: 8
50
  - total_train_batch_size: 8
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
58
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
59
+ | 5.5906 | 1.0 | 49 | 9.5684 | 0.0375 | 0.0103 | 0.0369 | 0.0377 | 20.0 |
60
+ | 4.6503 | 2.0 | 98 | 3.8125 | 0.0634 | 0.0206 | 0.0555 | 0.0568 | 20.0 |
61
+ | 3.6625 | 3.0 | 147 | 3.4575 | 0.072 | 0.0236 | 0.0631 | 0.0631 | 20.0 |
62
+ | 3.1628 | 4.0 | 196 | 3.3466 | 0.0693 | 0.0202 | 0.0626 | 0.0633 | 20.0 |
63
 
64
 
65
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15b7f688401128034d4fc70529d76ef14368b3a66ff784083249514b310ee951
3
  size 1187780840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c1928b8ae64bf0067ca48549141ac050634619c9276d47ab74bf2868d1f7e8
3
  size 1187780840