Commit
•
f16ac32
1
Parent(s):
4f0ea99
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- opus_infopankki
|
7 |
+
metrics:
|
8 |
+
- bleu
|
9 |
+
model-index:
|
10 |
+
- name: opus-mt-tr-en-finetuned-tr-to-en
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Sequence-to-sequence Language Modeling
|
14 |
+
type: text2text-generation
|
15 |
+
dataset:
|
16 |
+
name: opus_infopankki
|
17 |
+
type: opus_infopankki
|
18 |
+
args: en-tr
|
19 |
+
metrics:
|
20 |
+
- name: Bleu
|
21 |
+
type: bleu
|
22 |
+
value: 56.617
|
23 |
+
---
|
24 |
+
|
25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
+
should probably proofread and complete it, then remove this comment. -->
|
27 |
+
|
28 |
+
# opus-mt-tr-en-finetuned-tr-to-en
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tr-en](https://huggingface.co/Helsinki-NLP/opus-mt-tr-en) on the opus_infopankki dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 0.6321
|
33 |
+
- Bleu: 56.617
|
34 |
+
- Gen Len: 13.5983
|
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: 2e-06
|
54 |
+
- train_batch_size: 64
|
55 |
+
- eval_batch_size: 64
|
56 |
+
- seed: 42
|
57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
+
- lr_scheduler_type: linear
|
59 |
+
- num_epochs: 30
|
60 |
+
- mixed_precision_training: Native AMP
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
65 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
66 |
+
| No log | 1.0 | 241 | 1.2487 | 41.0053 | 13.0461 |
|
67 |
+
| No log | 2.0 | 482 | 1.1630 | 43.1077 | 13.0386 |
|
68 |
+
| 1.4091 | 3.0 | 723 | 1.0992 | 44.6583 | 13.0445 |
|
69 |
+
| 1.4091 | 4.0 | 964 | 1.0463 | 45.5931 | 13.0289 |
|
70 |
+
| 1.2325 | 5.0 | 1205 | 1.0012 | 46.7039 | 12.9998 |
|
71 |
+
| 1.2325 | 6.0 | 1446 | 0.9610 | 47.6783 | 13.0274 |
|
72 |
+
| 1.1284 | 7.0 | 1687 | 0.9262 | 48.622 | 12.9866 |
|
73 |
+
| 1.1284 | 8.0 | 1928 | 0.8939 | 48.4984 | 13.5762 |
|
74 |
+
| 1.0486 | 9.0 | 2169 | 0.8642 | 49.1496 | 13.5918 |
|
75 |
+
| 1.0486 | 10.0 | 2410 | 0.8391 | 49.8875 | 13.5905 |
|
76 |
+
| 0.9866 | 11.0 | 2651 | 0.8150 | 50.6447 | 13.5803 |
|
77 |
+
| 0.9866 | 12.0 | 2892 | 0.7941 | 51.2059 | 13.5731 |
|
78 |
+
| 0.9362 | 13.0 | 3133 | 0.7741 | 51.7071 | 13.5754 |
|
79 |
+
| 0.9362 | 14.0 | 3374 | 0.7564 | 52.4185 | 13.5781 |
|
80 |
+
| 0.8928 | 15.0 | 3615 | 0.7398 | 53.0814 | 13.5744 |
|
81 |
+
| 0.8928 | 16.0 | 3856 | 0.7247 | 53.5711 | 13.5783 |
|
82 |
+
| 0.8598 | 17.0 | 4097 | 0.7111 | 54.0559 | 13.568 |
|
83 |
+
| 0.8598 | 18.0 | 4338 | 0.6988 | 54.5188 | 13.5598 |
|
84 |
+
| 0.8274 | 19.0 | 4579 | 0.6876 | 54.78 | 13.5765 |
|
85 |
+
| 0.8274 | 20.0 | 4820 | 0.6780 | 55.1494 | 13.5762 |
|
86 |
+
| 0.8086 | 21.0 | 5061 | 0.6688 | 55.5813 | 13.5788 |
|
87 |
+
| 0.8086 | 22.0 | 5302 | 0.6610 | 55.6403 | 13.5796 |
|
88 |
+
| 0.7878 | 23.0 | 5543 | 0.6539 | 55.7731 | 13.5989 |
|
89 |
+
| 0.7878 | 24.0 | 5784 | 0.6483 | 55.9956 | 13.593 |
|
90 |
+
| 0.7718 | 25.0 | 6025 | 0.6432 | 56.2303 | 13.5904 |
|
91 |
+
| 0.7718 | 26.0 | 6266 | 0.6390 | 56.4825 | 13.5975 |
|
92 |
+
| 0.7633 | 27.0 | 6507 | 0.6360 | 56.5334 | 13.5958 |
|
93 |
+
| 0.7633 | 28.0 | 6748 | 0.6338 | 56.5357 | 13.5965 |
|
94 |
+
| 0.7633 | 29.0 | 6989 | 0.6325 | 56.5862 | 13.5974 |
|
95 |
+
| 0.7584 | 30.0 | 7230 | 0.6321 | 56.617 | 13.5983 |
|
96 |
+
|
97 |
+
|
98 |
+
### Framework versions
|
99 |
+
|
100 |
+
- Transformers 4.20.1
|
101 |
+
- Pytorch 1.12.0
|
102 |
+
- Datasets 2.3.2
|
103 |
+
- Tokenizers 0.12.1
|