samzirbo commited on
Commit
c2df9f9
1 Parent(s): b3a8aa9

End of training

Browse files
Files changed (1) hide show
  1. README.md +33 -0
README.md CHANGED
@@ -2,6 +2,8 @@
2
  base_model: samzirbo/mT5.en-es.pretrained
3
  tags:
4
  - generated_from_trainer
 
 
5
  model-index:
6
  - name: gendered_balanced_new
7
  results: []
@@ -13,6 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
13
  # gendered_balanced_new
14
 
15
  This model is a fine-tuned version of [samzirbo/mT5.en-es.pretrained](https://huggingface.co/samzirbo/mT5.en-es.pretrained) on an unknown dataset.
 
 
 
 
 
16
 
17
  ## Model description
18
 
@@ -40,6 +47,32 @@ The following hyperparameters were used during training:
40
  - lr_scheduler_warmup_steps: 1000
41
  - training_steps: 50000
42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  ### Framework versions
44
 
45
  - Transformers 4.38.0
 
2
  base_model: samzirbo/mT5.en-es.pretrained
3
  tags:
4
  - generated_from_trainer
5
+ metrics:
6
+ - bleu
7
  model-index:
8
  - name: gendered_balanced_new
9
  results: []
 
15
  # gendered_balanced_new
16
 
17
  This model is a fine-tuned version of [samzirbo/mT5.en-es.pretrained](https://huggingface.co/samzirbo/mT5.en-es.pretrained) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.1763
20
+ - Bleu: 43.813
21
+ - Meteor: 0.6892
22
+ - Chrf++: 62.6103
23
 
24
  ## Model description
25
 
 
47
  - lr_scheduler_warmup_steps: 1000
48
  - training_steps: 50000
49
 
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Meteor | Chrf++ |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|
54
+ | 4.297 | 0.44 | 2500 | 2.0050 | 28.2124 | 0.5592 | 49.6855 |
55
+ | 2.4102 | 0.88 | 5000 | 1.7130 | 33.5308 | 0.6073 | 54.4802 |
56
+ | 2.1323 | 1.31 | 7500 | 1.5723 | 36.3429 | 0.6293 | 56.6736 |
57
+ | 1.9971 | 1.75 | 10000 | 1.4819 | 37.5927 | 0.6411 | 57.7792 |
58
+ | 1.8896 | 2.19 | 12500 | 1.4211 | 38.9306 | 0.6509 | 58.8416 |
59
+ | 1.8066 | 2.63 | 15000 | 1.3774 | 40.4467 | 0.6587 | 59.8543 |
60
+ | 1.7574 | 3.06 | 17500 | 1.3336 | 40.6982 | 0.6646 | 60.1397 |
61
+ | 1.6837 | 3.5 | 20000 | 1.3066 | 41.6068 | 0.6716 | 60.8397 |
62
+ | 1.6587 | 3.94 | 22500 | 1.2767 | 41.5927 | 0.6719 | 60.9297 |
63
+ | 1.595 | 4.38 | 25000 | 1.2556 | 42.1176 | 0.6762 | 61.2694 |
64
+ | 1.5764 | 4.81 | 27500 | 1.2317 | 42.9623 | 0.6814 | 61.9533 |
65
+ | 1.5416 | 5.25 | 30000 | 1.2212 | 42.9789 | 0.681 | 61.9041 |
66
+ | 1.5155 | 5.69 | 32500 | 1.2070 | 43.3916 | 0.6865 | 62.3045 |
67
+ | 1.4955 | 6.13 | 35000 | 1.1973 | 43.455 | 0.6854 | 62.2717 |
68
+ | 1.4688 | 6.56 | 37500 | 1.1863 | 43.5298 | 0.6857 | 62.3399 |
69
+ | 1.467 | 7.0 | 40000 | 1.1827 | 43.7299 | 0.6884 | 62.4926 |
70
+ | 1.4416 | 7.44 | 42500 | 1.1796 | 43.7634 | 0.6887 | 62.5774 |
71
+ | 1.4411 | 7.88 | 45000 | 1.1764 | 43.93 | 0.6896 | 62.6606 |
72
+ | 1.434 | 8.31 | 47500 | 1.1764 | 43.8254 | 0.6885 | 62.5964 |
73
+ | 1.4311 | 8.75 | 50000 | 1.1763 | 43.813 | 0.6892 | 62.6103 |
74
+
75
+
76
  ### Framework versions
77
 
78
  - Transformers 4.38.0