Hugging Face's logo

huggingface-course
/
mt5-small-finetuned-amazon-en-es

Summarization
Transformers
PyTorch
TensorFlow
TensorBoard
mt5
text2text-generation
generated_from_trainer
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
2
lewtun HF staff commited on
Commit
f3730e3
•
1 Parent(s): d51028f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -16
README.md CHANGED
@@ -17,12 +17,12 @@ 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 the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.5050
21
- - Rouge1: 16.471
22
- - Rouge2: 9.6857
23
- - Rougel: 16.1028
24
- - Rougelsum: 16.1929
25
- - Gen Len: 7.4538
26
 
27
  ## Model description
28
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
- | 5.9093 | 1.0 | 1209 | 2.8536 | 9.0682 | 7.3025 | 8.7377 | 8.88 | 3.5504 |
57
- | 3.2481 | 2.0 | 2418 | 2.6507 | 16.3535 | 11.0792 | 16.0699 | 16.135 | 7.1387 |
58
- | 2.9617 | 3.0 | 3627 | 2.5843 | 15.2778 | 9.4619 | 15.0177 | 15.0804 | 7.4118 |
59
- | 2.8128 | 4.0 | 4836 | 2.5501 | 15.9292 | 9.3908 | 15.6132 | 15.6424 | 7.9286 |
60
- | 2.7324 | 5.0 | 6045 | 2.5321 | 16.1222 | 9.0046 | 15.7392 | 15.813 | 8.1471 |
61
- | 2.6572 | 6.0 | 7254 | 2.5073 | 17.4735 | 10.8534 | 17.0458 | 17.0905 | 6.9538 |
62
- | 2.6118 | 7.0 | 8463 | 2.5132 | 16.6198 | 9.8078 | 16.2883 | 16.3328 | 7.2605 |
63
- | 2.5818 | 8.0 | 9672 | 2.5050 | 16.471 | 9.6857 | 16.1028 | 16.1929 | 7.4538 |
64
 
65
 
66
  ### Framework versions
17
 
18
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 3.0983
21
+ - Rouge1: 11.8061
22
+ - Rouge2: 3.6575
23
+ - Rougel: 11.4999
24
+ - Rougelsum: 11.5414
25
+ - Gen Len: 5.9286
26
 
27
  ## Model description
28
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
56
+ | 6.4205 | 1.0 | 1209 | 3.3904 | 7.3124 | 2.1083 | 7.0649 | 7.0966 | 4.7269 |
57
+ | 3.7818 | 2.0 | 2418 | 3.1762 | 10.5437 | 3.0706 | 10.4618 | 10.4713 | 5.3697 |
58
+ | 3.4672 | 3.0 | 3627 | 3.1304 | 10.4674 | 3.0531 | 10.2156 | 10.2549 | 5.9748 |
59
+ | 3.3179 | 4.0 | 4836 | 3.1170 | 11.2847 | 3.3152 | 11.1387 | 11.146 | 6.1723 |
60
+ | 3.2048 | 5.0 | 6045 | 3.1069 | 11.5212 | 3.1957 | 11.2117 | 11.2044 | 6.042 |
61
+ | 3.1211 | 6.0 | 7254 | 3.1028 | 11.8104 | 3.6482 | 11.5535 | 11.5259 | 6.0462 |
62
+ | 3.0724 | 7.0 | 8463 | 3.1001 | 11.7336 | 3.6575 | 11.4403 | 11.4738 | 5.9454 |
63
+ | 3.0476 | 8.0 | 9672 | 3.0983 | 11.8061 | 3.6575 | 11.4999 | 11.5414 | 5.9286 |
64
 
65
 
66
  ### Framework versions