kepinsam commited on
Commit
809add7
1 Parent(s): a575ff7

End of training

Browse files
Files changed (3) hide show
  1. README.md +81 -0
  2. generation_config.json +8 -0
  3. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: facebook/nllb-200-distilled-600M
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - nusatranslation_mt
8
+ metrics:
9
+ - sacrebleu
10
+ model-index:
11
+ - name: indonesian_to_bataknese_translation_model
12
+ results:
13
+ - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
+ dataset:
17
+ name: nusatranslation_mt
18
+ type: nusatranslation_mt
19
+ config: nusatranslation_mt_btk_ind_source
20
+ split: test
21
+ args: nusatranslation_mt_btk_ind_source
22
+ metrics:
23
+ - name: Sacrebleu
24
+ type: sacrebleu
25
+ value: 31.8044
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # indonesian_to_bataknese_translation_model
32
+
33
+ This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the nusatranslation_mt dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.1474
36
+ - Sacrebleu: 31.8044
37
+ - Gen Len: 45.2525
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 5e-05
57
+ - train_batch_size: 4
58
+ - eval_batch_size: 16
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 5
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Sacrebleu | Gen Len |
68
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
69
+ | 1.6014 | 1.0 | 1650 | 1.3826 | 29.3368 | 45.439 |
70
+ | 1.2189 | 2.0 | 3300 | 1.2135 | 31.2236 | 45.2075 |
71
+ | 1.0274 | 3.0 | 4950 | 1.1556 | 30.8443 | 45.661 |
72
+ | 0.8923 | 4.0 | 6600 | 1.1471 | 31.6079 | 45.1555 |
73
+ | 0.8094 | 5.0 | 8250 | 1.1474 | 31.8044 | 45.2525 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.34.1
79
+ - Pytorch 2.1.0+cu118
80
+ - Datasets 2.13.1
81
+ - Tokenizers 0.14.1
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "max_length": 200,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.34.1"
8
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:379bc61eebcd53a7219c7bd083492c57f3bdd06708addff9230e3e41d637723d
3
  size 2460469182
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d404dc07038e52442b32a0e9638ce0faf367404f27e966f08d61901d189b91b6
3
  size 2460469182