Gaoussin commited on
Commit
a2ef2b8
·
verified ·
1 Parent(s): 818af03

Bamalingua-fr-bm-v5

Browse files
Files changed (1) hide show
  1. README.md +17 -0
README.md CHANGED
@@ -4,6 +4,8 @@ license: cc-by-nc-4.0
4
  base_model: facebook/nllb-200-distilled-600M
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: trainer_output
9
  results: []
@@ -16,6 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
16
  # trainer_output
17
 
18
  This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on an unknown dataset.
 
 
 
19
 
20
  ## Model description
21
 
@@ -45,6 +50,18 @@ The following hyperparameters were used during training:
45
  - lr_scheduler_warmup_ratio: 0.1
46
  - num_epochs: 6
47
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  ### Framework versions
49
 
50
  - Transformers 4.57.1
 
4
  base_model: facebook/nllb-200-distilled-600M
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - bleu
9
  model-index:
10
  - name: trainer_output
11
  results: []
 
18
  # trainer_output
19
 
20
  This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.9640
23
+ - Bleu: 18.5861
24
 
25
  ## Model description
26
 
 
50
  - lr_scheduler_warmup_ratio: 0.1
51
  - num_epochs: 6
52
 
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Bleu |
56
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|
57
+ | 2.392 | 1.0 | 2525 | 2.2508 | 13.6779 |
58
+ | 2.1302 | 2.0 | 5050 | 2.0765 | 17.1351 |
59
+ | 1.9159 | 3.0 | 7575 | 1.9920 | 17.7167 |
60
+ | 1.7718 | 4.0 | 10100 | 1.9664 | 18.6164 |
61
+ | 1.6949 | 5.0 | 12625 | 1.9633 | 18.6201 |
62
+ | 1.6918 | 6.0 | 15150 | 1.9640 | 18.5861 |
63
+
64
+
65
  ### Framework versions
66
 
67
  - Transformers 4.57.1