PontifexMaximus commited on
Commit
c9841c5
1 Parent(s): 7af2f39

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Bleu
21
  type: bleu
22
- value: 28.9919
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,9 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ar-en](https://huggingface.co/Helsinki-NLP/opus-mt-ar-en) on the opus_infopankki dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 1.6629
33
- - Bleu: 28.9919
34
- - Gen Len: 15.6512
35
 
36
  ## Model description
37
 
@@ -61,19 +61,19 @@ The following hyperparameters were used during training:
61
 
62
  ### Training results
63
 
64
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
65
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
66
- | No log | 1.0 | 159 | 2.1441 | 22.0728 | 16.5805 |
67
- | No log | 2.0 | 318 | 2.0141 | 23.888 | 16.3754 |
68
- | No log | 3.0 | 477 | 1.9228 | 25.2541 | 15.835 |
69
- | 2.2356 | 4.0 | 636 | 1.8523 | 26.299 | 15.7874 |
70
- | 2.2356 | 5.0 | 795 | 1.7971 | 26.8646 | 16.0247 |
71
- | 2.2356 | 6.0 | 954 | 1.7536 | 27.2391 | 16.013 |
72
- | 1.9609 | 7.0 | 1113 | 1.7200 | 27.7471 | 16.0237 |
73
- | 1.9609 | 8.0 | 1272 | 1.6945 | 28.4924 | 15.6563 |
74
- | 1.9609 | 9.0 | 1431 | 1.6771 | 28.8024 | 15.6445 |
75
- | 1.8388 | 10.0 | 1590 | 1.6665 | 29.0016 | 15.6429 |
76
- | 1.8388 | 11.0 | 1749 | 1.6629 | 28.9919 | 15.6512 |
77
 
78
 
79
  ### Framework versions
 
19
  metrics:
20
  - name: Bleu
21
  type: bleu
22
+ value: 44.5107
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ar-en](https://huggingface.co/Helsinki-NLP/opus-mt-ar-en) on the opus_infopankki dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.9956
33
+ - Bleu: 44.5107
34
+ - Gen Len: 14.6465
35
 
36
  ## Model description
37
 
 
61
 
62
  ### Training results
63
 
64
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
65
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
66
+ | 1.696 | 1.0 | 950 | 1.4125 | 35.5899 | 15.0109 |
67
+ | 1.4952 | 2.0 | 1900 | 1.2969 | 38.1745 | 14.7736 |
68
+ | 1.3821 | 3.0 | 2850 | 1.2175 | 39.8192 | 14.7649 |
69
+ | 1.2941 | 4.0 | 3800 | 1.1571 | 40.9966 | 14.7446 |
70
+ | 1.2409 | 5.0 | 4750 | 1.1097 | 41.9215 | 14.7406 |
71
+ | 1.1938 | 6.0 | 5700 | 1.0721 | 42.868 | 14.6819 |
72
+ | 1.1634 | 7.0 | 6650 | 1.0440 | 43.4749 | 14.6536 |
73
+ | 1.1355 | 8.0 | 7600 | 1.0223 | 43.9275 | 14.6809 |
74
+ | 1.1161 | 9.0 | 8550 | 1.0075 | 44.2378 | 14.6471 |
75
+ | 1.1103 | 10.0 | 9500 | 0.9987 | 44.4293 | 14.639 |
76
+ | 1.1043 | 11.0 | 10450 | 0.9956 | 44.5107 | 14.6465 |
77
 
78
 
79
  ### Framework versions