Hugging Face's logo

yonathanstwn
/
opus-mt-id-en-open-subtitles

Text2Text Generation
Transformers
PyTorch
marian
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
yonathanstwn commited on
Commit
09eb499
•
1 Parent(s): 72a3e5a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - open_subtitles
6
+ metrics:
7
+ - bleu
8
+ model-index:
9
+ - name: opus-mt-id-en-open-subtitles
10
+ results:
11
+ - task:
12
+ name: Sequence-to-sequence Language Modeling
13
+ type: text2text-generation
14
+ dataset:
15
+ name: open_subtitles
16
+ type: open_subtitles
17
+ config: en-id
18
+ split: train
19
+ args: en-id
20
+ metrics:
21
+ - name: Bleu
22
+ type: bleu
23
+ value: 36.9382
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # opus-mt-id-en-open-subtitles
30
+
31
+ This model was trained from scratch on the open_subtitles dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 1.8430
34
+ - Bleu: 36.9382
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 0.0001
54
+ - train_batch_size: 32
55
+ - eval_batch_size: 32
56
+ - seed: 42
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: linear
59
+ - lr_scheduler_warmup_steps: 4000
60
+ - num_epochs: 25
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Bleu |
65
+ |:-------------:|:-----:|:------:|:---------------:|:-------:|
66
+ | 1.3533 | 1.0 | 28125 | 1.3274 | 37.6662 |
67
+ | 1.2814 | 2.0 | 56250 | 1.3525 | 37.5909 |
68
+ | 1.2058 | 3.0 | 84375 | 1.3674 | 37.8008 |
69
+ | 1.1415 | 4.0 | 112500 | 1.3722 | 37.4849 |
70
+ | 1.0842 | 5.0 | 140625 | 1.3943 | 37.7558 |
71
+ | 1.0309 | 6.0 | 168750 | 1.3994 | 37.6332 |
72
+ | 0.9802 | 7.0 | 196875 | 1.4216 | 37.7529 |
73
+ | 0.9316 | 8.0 | 225000 | 1.4304 | 37.9906 |
74
+ | 0.8838 | 9.0 | 253125 | 1.4462 | 37.7833 |
75
+ | 0.8378 | 10.0 | 281250 | 1.4639 | 37.5971 |
76
+ | 0.7921 | 11.0 | 309375 | 1.4859 | 37.6285 |
77
+ | 0.7484 | 12.0 | 337500 | 1.5060 | 37.5413 |
78
+ | 0.7043 | 13.0 | 365625 | 1.5256 | 37.5118 |
79
+ | 0.6622 | 14.0 | 393750 | 1.5555 | 37.5092 |
80
+ | 0.6208 | 15.0 | 421875 | 1.5733 | 37.2924 |
81
+ | 0.5807 | 16.0 | 450000 | 1.6048 | 37.319 |
82
+ | 0.542 | 17.0 | 478125 | 1.6435 | 37.0629 |
83
+ | 0.5043 | 18.0 | 506250 | 1.6647 | 37.1334 |
84
+ | 0.4685 | 19.0 | 534375 | 1.7014 | 37.02 |
85
+ | 0.4352 | 20.0 | 562500 | 1.7300 | 36.9514 |
86
+ | 0.4031 | 21.0 | 590625 | 1.7572 | 36.9637 |
87
+ | 0.3731 | 22.0 | 618750 | 1.7902 | 36.9821 |
88
+ | 0.346 | 23.0 | 646875 | 1.8112 | 36.9586 |
89
+ | 0.3227 | 24.0 | 675000 | 1.8325 | 36.9286 |
90
+ | 0.303 | 25.0 | 703125 | 1.8430 | 36.9382 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.26.1
96
+ - Pytorch 2.0.0
97
+ - Datasets 2.10.1
98
+ - Tokenizers 0.11.0