update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: SUBTITLE_ja-en_helsinki
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# SUBTITLE_ja-en_helsinki
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ja-en](https://huggingface.co/Helsinki-NLP/opus-mt-ja-en) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 5.4097
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0003
|
37 |
+
- train_batch_size: 64
|
38 |
+
- eval_batch_size: 64
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 2
|
43 |
+
- mixed_precision_training: Native AMP
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
+
| 3.025 | 0.05 | 2000 | 5.1692 |
|
50 |
+
| 2.9548 | 0.09 | 4000 | 5.7128 |
|
51 |
+
| 2.8762 | 0.14 | 6000 | 5.9297 |
|
52 |
+
| 2.821 | 0.18 | 8000 | 6.0415 |
|
53 |
+
| 2.7826 | 0.23 | 10000 | 6.0416 |
|
54 |
+
| 2.7386 | 0.27 | 12000 | 6.0069 |
|
55 |
+
| 2.7036 | 0.32 | 14000 | 6.0192 |
|
56 |
+
| 2.678 | 0.37 | 16000 | 5.9286 |
|
57 |
+
| 2.6499 | 0.41 | 18000 | 5.9587 |
|
58 |
+
| 2.6261 | 0.46 | 20000 | 5.9044 |
|
59 |
+
| 2.6032 | 0.5 | 22000 | 5.8482 |
|
60 |
+
| 2.5708 | 0.55 | 24000 | 5.7760 |
|
61 |
+
| 2.5517 | 0.59 | 26000 | 5.7546 |
|
62 |
+
| 2.5336 | 0.64 | 28000 | 5.7447 |
|
63 |
+
| 2.5196 | 0.69 | 30000 | 5.7373 |
|
64 |
+
| 2.4957 | 0.73 | 32000 | 5.6429 |
|
65 |
+
| 2.483 | 0.78 | 34000 | 5.6874 |
|
66 |
+
| 2.4599 | 0.82 | 36000 | 5.6482 |
|
67 |
+
| 2.4468 | 0.87 | 38000 | 5.5951 |
|
68 |
+
| 2.4344 | 0.92 | 40000 | 5.6355 |
|
69 |
+
| 2.4223 | 0.96 | 42000 | 5.6135 |
|
70 |
+
| 2.3878 | 1.01 | 44000 | 5.6164 |
|
71 |
+
| 2.294 | 1.05 | 46000 | 5.5802 |
|
72 |
+
| 2.2896 | 1.1 | 48000 | 5.5924 |
|
73 |
+
| 2.2815 | 1.14 | 50000 | 5.5296 |
|
74 |
+
| 2.2702 | 1.19 | 52000 | 5.5119 |
|
75 |
+
| 2.2741 | 1.24 | 54000 | 5.4775 |
|
76 |
+
| 2.2586 | 1.28 | 56000 | 5.4663 |
|
77 |
+
| 2.2492 | 1.33 | 58000 | 5.4764 |
|
78 |
+
| 2.2411 | 1.37 | 60000 | 5.4444 |
|
79 |
+
| 2.2275 | 1.42 | 62000 | 5.4566 |
|
80 |
+
| 2.218 | 1.46 | 64000 | 5.4845 |
|
81 |
+
| 2.2086 | 1.51 | 66000 | 5.4681 |
|
82 |
+
| 2.1976 | 1.56 | 68000 | 5.4775 |
|
83 |
+
| 2.1877 | 1.6 | 70000 | 5.4619 |
|
84 |
+
| 2.177 | 1.65 | 72000 | 5.4621 |
|
85 |
+
| 2.1722 | 1.69 | 74000 | 5.4322 |
|
86 |
+
| 2.1599 | 1.74 | 76000 | 5.4348 |
|
87 |
+
| 2.1475 | 1.78 | 78000 | 5.4432 |
|
88 |
+
| 2.1477 | 1.83 | 80000 | 5.4239 |
|
89 |
+
| 2.134 | 1.88 | 82000 | 5.4182 |
|
90 |
+
| 2.1302 | 1.92 | 84000 | 5.4089 |
|
91 |
+
| 2.125 | 1.97 | 86000 | 5.4097 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- Transformers 4.19.2
|
97 |
+
- Pytorch 1.11.0+cu113
|
98 |
+
- Datasets 2.2.2
|
99 |
+
- Tokenizers 0.12.1
|