update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: VN_ja-en_byt5_small
|
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 |
+
# VN_ja-en_byt5_small
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.0552
|
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: 32
|
38 |
+
- eval_batch_size: 32
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 3
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
48 |
+
| 1.1687 | 0.1 | 2000 | 1.1805 |
|
49 |
+
| 0.9685 | 0.19 | 4000 | 1.1384 |
|
50 |
+
| 0.8989 | 0.29 | 6000 | 1.1207 |
|
51 |
+
| 0.8583 | 0.39 | 8000 | 1.1046 |
|
52 |
+
| 0.833 | 0.49 | 10000 | 1.1290 |
|
53 |
+
| 0.8102 | 0.58 | 12000 | 1.1225 |
|
54 |
+
| 0.7932 | 0.68 | 14000 | 1.0956 |
|
55 |
+
| 0.7776 | 0.78 | 16000 | 1.0970 |
|
56 |
+
| 0.762 | 0.88 | 18000 | 1.0992 |
|
57 |
+
| 0.7522 | 0.97 | 20000 | 1.0760 |
|
58 |
+
| 0.7318 | 1.07 | 22000 | 1.0579 |
|
59 |
+
| 0.7197 | 1.17 | 24000 | 1.0780 |
|
60 |
+
| 0.7142 | 1.27 | 26000 | 1.0748 |
|
61 |
+
| 0.7093 | 1.36 | 28000 | 1.0781 |
|
62 |
+
| 0.7005 | 1.46 | 30000 | 1.0756 |
|
63 |
+
| 0.6938 | 1.56 | 32000 | 1.0702 |
|
64 |
+
| 0.6896 | 1.65 | 34000 | 1.0563 |
|
65 |
+
| 0.6846 | 1.75 | 36000 | 1.0603 |
|
66 |
+
| 0.6807 | 1.85 | 38000 | 1.0626 |
|
67 |
+
| 0.6766 | 1.95 | 40000 | 1.0666 |
|
68 |
+
| 0.6649 | 2.04 | 42000 | 1.0694 |
|
69 |
+
| 0.6532 | 2.14 | 44000 | 1.0564 |
|
70 |
+
| 0.6501 | 2.24 | 46000 | 1.0715 |
|
71 |
+
| 0.6476 | 2.34 | 48000 | 1.0551 |
|
72 |
+
| 0.646 | 2.43 | 50000 | 1.0601 |
|
73 |
+
| 0.6445 | 2.53 | 52000 | 1.0595 |
|
74 |
+
| 0.6404 | 2.63 | 54000 | 1.0494 |
|
75 |
+
| 0.6378 | 2.72 | 56000 | 1.0584 |
|
76 |
+
| 0.636 | 2.82 | 58000 | 1.0531 |
|
77 |
+
| 0.6345 | 2.92 | 60000 | 1.0552 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.19.2
|
83 |
+
- Pytorch 1.11.0+cu113
|
84 |
+
- Datasets 2.2.2
|
85 |
+
- Tokenizers 0.12.1
|