Hugging Face's logo

gsvann
/
mt5-small-finetuned-amazon-en-de

Text2Text Generation
Transformers
PyTorch
mt5
Generated from Trainer
Inference Endpoints
Model card Files Community
gsvann commited on
Commit
b4815db
•
1 Parent(s): 87d7be6

gsvann/model_name

Browse files
Files changed (3) hide show
  1. README.md +12 -14
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.6964
21
- - Rouge1: 16.9495
22
- - Rouge2: 10.3864
23
- - Rougel: 16.6107
24
- - Rougelsum: 16.5146
25
 
26
  ## Model description
27
 
@@ -46,20 +46,18 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 8
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
- | 8.2166 | 1.0 | 651 | 3.1449 | 14.8158 | 7.6238 | 14.4691 | 14.317 |
56
- | 4.0965 | 2.0 | 1302 | 2.9073 | 14.7988 | 7.7674 | 14.5117 | 14.3895 |
57
- | 3.7254 | 3.0 | 1953 | 2.8142 | 14.5259 | 7.1771 | 14.3574 | 14.3033 |
58
- | 3.5485 | 4.0 | 2604 | 2.7675 | 16.6534 | 9.6695 | 16.5785 | 16.3698 |
59
- | 3.42 | 5.0 | 3255 | 2.7387 | 16.6817 | 9.9656 | 16.5414 | 16.414 |
60
- | 3.3369 | 6.0 | 3906 | 2.7054 | 17.2119 | 10.4457 | 17.0202 | 16.8504 |
61
- | 3.3025 | 7.0 | 4557 | 2.6915 | 16.2837 | 10.02 | 15.9801 | 15.8678 |
62
- | 3.2659 | 8.0 | 5208 | 2.6964 | 16.9495 | 10.3864 | 16.6107 | 16.5146 |
63
 
64
 
65
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.6132
21
+ - Rouge1: 18.5886
22
+ - Rouge2: 10.4761
23
+ - Rougel: 17.9705
24
+ - Rougelsum: 18.2467
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 6
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
+ | 3.0822 | 1.0 | 651 | 2.6232 | 17.8834 | 11.2967 | 17.4489 | 17.73 |
56
+ | 2.9301 | 2.0 | 1302 | 2.6265 | 18.3784 | 11.1587 | 18.0152 | 18.1896 |
57
+ | 2.8552 | 3.0 | 1953 | 2.6223 | 18.7889 | 11.1004 | 18.2222 | 18.4583 |
58
+ | 2.8253 | 4.0 | 2604 | 2.6080 | 18.2031 | 10.2714 | 17.748 | 17.8395 |
59
+ | 2.8044 | 5.0 | 3255 | 2.6154 | 18.5675 | 10.5794 | 17.967 | 18.2698 |
60
+ | 2.7928 | 6.0 | 3906 | 2.6132 | 18.5886 | 10.4761 | 17.9705 | 18.2467 |
 
 
61
 
62
 
63
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e0c7b22a15e5d373d9c684f73006712f62edefda09cf19a161264c0f1248f08
3
  size 1200773058
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc66756f726ca2bb65ee3f851abac731eb68f8e31657faf0c0ce42470aa45354
3
  size 1200773058
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf2b2b343ad9dd4f0aa666d21176f73443fa1a6eb7c4fcaa5df5de460072bc11
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c3bf9535f955a89e82e4cc1478fe509fc4302a1aa4ff898439dda5668decf5e
3
  size 4664