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
|