Hugging Face's logo

ychafiqui
/
english-to-darija-2

Text2Text Generation
Transformers
TensorBoard
Safetensors
marian
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ychafiqui commited on
Commit
fa22daa
•
1 Parent(s): 6b3d6f7

End of training

Browse files
Files changed (4) hide show
  1. README.md +18 -23
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Feb12_08-49-40_dcd95080f986/events.out.tfevents.1707727782.dcd95080f986.34.0 +2 -2
README.md CHANGED
@@ -8,9 +8,6 @@ metrics:
8
  model-index:
9
  - name: english-to-darija-2
10
  results: []
11
- language:
12
- - en
13
- - ary
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -20,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-ar) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.8922
24
- - Bleu: 77.1567
25
- - Gen Len: 16.379
26
 
27
  ## Model description
28
 
@@ -47,30 +44,28 @@ The following hyperparameters were used during training:
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
- - num_epochs: 12
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
56
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
57
- | 2.0991 | 1.0 | 1525 | 1.8210 | 20.4147 | 15.6004 |
58
- | 1.3476 | 2.0 | 3050 | 1.3142 | 38.8364 | 15.808 |
59
- | 0.9515 | 3.0 | 4575 | 1.0775 | 55.6305 | 16.1504 |
60
- | 0.6951 | 4.0 | 6100 | 0.9632 | 66.9767 | 16.2509 |
61
- | 0.5589 | 5.0 | 7625 | 0.9089 | 71.1846 | 16.4062 |
62
- | 0.4546 | 6.0 | 9150 | 0.8902 | 74.3547 | 16.2483 |
63
- | 0.3671 | 7.0 | 10675 | 0.8841 | 75.4645 | 16.3627 |
64
- | 0.3085 | 8.0 | 12200 | 0.8812 | 76.2993 | 16.3739 |
65
- | 0.2668 | 9.0 | 13725 | 0.8863 | 76.6186 | 16.347 |
66
- | 0.2257 | 10.0 | 15250 | 0.8876 | 76.6218 | 16.4226 |
67
- | 0.2077 | 11.0 | 16775 | 0.8907 | 76.8682 | 16.4054 |
68
- | 0.1969 | 12.0 | 18300 | 0.8922 | 77.1567 | 16.379 |
69
 
70
 
71
  ### Framework versions
72
 
73
- - Transformers 4.35.2
74
- - Pytorch 2.1.0+cu121
75
- - Datasets 2.16.1
76
- - Tokenizers 0.15.1
 
8
  model-index:
9
  - name: english-to-darija-2
10
  results: []
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
17
 
18
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-ar) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.8514
21
+ - Bleu: 70.9947
22
+ - Gen Len: 9.092
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 10
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
54
+ | 1.6032 | 1.0 | 4651 | 1.4540 | 25.9364 | 8.9697 |
55
+ | 1.1191 | 2.0 | 9302 | 1.0805 | 48.0549 | 9.0661 |
56
+ | 0.8048 | 3.0 | 13953 | 0.9419 | 61.3646 | 9.1018 |
57
+ | 0.5978 | 4.0 | 18604 | 0.8939 | 65.6846 | 9.1161 |
58
+ | 0.477 | 5.0 | 23255 | 0.8623 | 68.0005 | 9.1049 |
59
+ | 0.4228 | 6.0 | 27906 | 0.8540 | 69.1959 | 9.1276 |
60
+ | 0.3534 | 7.0 | 32557 | 0.8479 | 69.944 | 9.0744 |
61
+ | 0.305 | 8.0 | 37208 | 0.8473 | 70.55 | 9.0987 |
62
+ | 0.2678 | 9.0 | 41859 | 0.8489 | 70.8065 | 9.1166 |
63
+ | 0.243 | 10.0 | 46510 | 0.8514 | 70.9947 | 9.092 |
 
 
64
 
65
 
66
  ### Framework versions
67
 
68
+ - Transformers 4.37.2
69
+ - Pytorch 2.2.0+cu121
70
+ - Datasets 2.17.0
71
+ - Tokenizers 0.15.1
generation_config.json CHANGED
@@ -12,5 +12,5 @@
12
  "num_beams": 4,
13
  "pad_token_id": 61246,
14
  "renormalize_logits": true,
15
- "transformers_version": "4.35.2"
16
  }
 
12
  "num_beams": 4,
13
  "pad_token_id": 61246,
14
  "renormalize_logits": true,
15
+ "transformers_version": "4.37.2"
16
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2519b0dd0ee6e8b2fd2839e347fef67196f4b2fc16f9c54df6eaa7b716b2d7ab
3
  size 956571820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26940dfd0a187e420f66c5822b3cc7e0c9d57afdb4ab6089b2269be0109ce537
3
  size 956571820
runs/Feb12_08-49-40_dcd95080f986/events.out.tfevents.1707727782.dcd95080f986.34.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0615375e9cbacf846b270d44a46485d22ede8c1fa5e4f31bb720618ddeb3224b
3
- size 23165
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab0c0e6e9dc8e9b99c3cf2e299edd749c38fb7aefa667d278936c816fdb2e0e
3
+ size 23902