update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: jeju-ko-nmt-v6-word-v1
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# jeju-ko-nmt-v6-word-v1
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [leadawon/jeju-ko-nmt-v6](https://huggingface.co/leadawon/jeju-ko-nmt-v6) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.6390
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 5e-06
|
| 36 |
+
- train_batch_size: 128
|
| 37 |
+
- eval_batch_size: 128
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 42 |
+
- num_epochs: 2
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
+
| 0.8194 | 0.03 | 500 | 0.7499 |
|
| 50 |
+
| 0.7814 | 0.06 | 1000 | 0.7211 |
|
| 51 |
+
| 0.7559 | 0.09 | 1500 | 0.7036 |
|
| 52 |
+
| 0.7441 | 0.12 | 2000 | 0.7017 |
|
| 53 |
+
| 0.741 | 0.15 | 2500 | 0.6865 |
|
| 54 |
+
| 0.7329 | 0.18 | 3000 | 0.6825 |
|
| 55 |
+
| 0.7341 | 0.21 | 3500 | 0.6754 |
|
| 56 |
+
| 0.7358 | 0.24 | 4000 | 0.6671 |
|
| 57 |
+
| 0.723 | 0.28 | 4500 | 0.6641 |
|
| 58 |
+
| 0.7229 | 0.31 | 5000 | 0.6639 |
|
| 59 |
+
| 0.726 | 0.34 | 5500 | 0.6642 |
|
| 60 |
+
| 0.7219 | 0.37 | 6000 | 0.6577 |
|
| 61 |
+
| 0.7213 | 0.4 | 6500 | 0.6552 |
|
| 62 |
+
| 0.7192 | 0.43 | 7000 | 0.6627 |
|
| 63 |
+
| 0.7154 | 0.46 | 7500 | 0.6582 |
|
| 64 |
+
| 0.7108 | 0.49 | 8000 | 0.6570 |
|
| 65 |
+
| 0.7154 | 0.52 | 8500 | 0.6530 |
|
| 66 |
+
| 0.7178 | 0.55 | 9000 | 0.6601 |
|
| 67 |
+
| 0.7046 | 0.58 | 9500 | 0.6480 |
|
| 68 |
+
| 0.7127 | 0.61 | 10000 | 0.6507 |
|
| 69 |
+
| 0.6985 | 0.64 | 10500 | 0.6493 |
|
| 70 |
+
| 0.7093 | 0.67 | 11000 | 0.6500 |
|
| 71 |
+
| 0.7055 | 0.7 | 11500 | 0.6469 |
|
| 72 |
+
| 0.7061 | 0.73 | 12000 | 0.6534 |
|
| 73 |
+
| 0.7018 | 0.76 | 12500 | 0.6458 |
|
| 74 |
+
| 0.7027 | 0.8 | 13000 | 0.6424 |
|
| 75 |
+
| 0.7068 | 0.83 | 13500 | 0.6387 |
|
| 76 |
+
| 0.7044 | 0.86 | 14000 | 0.6441 |
|
| 77 |
+
| 0.7028 | 0.89 | 14500 | 0.6413 |
|
| 78 |
+
| 0.6992 | 0.92 | 15000 | 0.6359 |
|
| 79 |
+
| 0.7007 | 0.95 | 15500 | 0.6479 |
|
| 80 |
+
| 0.6887 | 0.98 | 16000 | 0.6416 |
|
| 81 |
+
| 0.7053 | 1.01 | 16500 | 0.6381 |
|
| 82 |
+
| 0.6795 | 1.04 | 17000 | 0.6391 |
|
| 83 |
+
| 0.6812 | 1.07 | 17500 | 0.6392 |
|
| 84 |
+
| 0.6826 | 1.1 | 18000 | 0.6405 |
|
| 85 |
+
| 0.6775 | 1.13 | 18500 | 0.6391 |
|
| 86 |
+
| 0.6798 | 1.16 | 19000 | 0.6378 |
|
| 87 |
+
| 0.6895 | 1.19 | 19500 | 0.6359 |
|
| 88 |
+
| 0.687 | 1.22 | 20000 | 0.6364 |
|
| 89 |
+
| 0.6887 | 1.25 | 20500 | 0.6357 |
|
| 90 |
+
| 0.6758 | 1.28 | 21000 | 0.6356 |
|
| 91 |
+
| 0.6732 | 1.32 | 21500 | 0.6368 |
|
| 92 |
+
| 0.6832 | 1.35 | 22000 | 0.6381 |
|
| 93 |
+
| 0.6805 | 1.38 | 22500 | 0.6347 |
|
| 94 |
+
| 0.6821 | 1.41 | 23000 | 0.6373 |
|
| 95 |
+
| 0.6828 | 1.44 | 23500 | 0.6401 |
|
| 96 |
+
| 0.678 | 1.47 | 24000 | 0.6402 |
|
| 97 |
+
| 0.6892 | 1.5 | 24500 | 0.6358 |
|
| 98 |
+
| 0.6855 | 1.53 | 25000 | 0.6339 |
|
| 99 |
+
| 0.6748 | 1.56 | 25500 | 0.6363 |
|
| 100 |
+
| 0.6734 | 1.59 | 26000 | 0.6361 |
|
| 101 |
+
| 0.6748 | 1.62 | 26500 | 0.6348 |
|
| 102 |
+
| 0.6812 | 1.65 | 27000 | 0.6355 |
|
| 103 |
+
| 0.6844 | 1.68 | 27500 | 0.6380 |
|
| 104 |
+
| 0.6794 | 1.71 | 28000 | 0.6393 |
|
| 105 |
+
| 0.6834 | 1.74 | 28500 | 0.6390 |
|
| 106 |
+
| 0.6843 | 1.77 | 29000 | 0.6411 |
|
| 107 |
+
| 0.6732 | 1.8 | 29500 | 0.6414 |
|
| 108 |
+
| 0.6758 | 1.84 | 30000 | 0.6395 |
|
| 109 |
+
| 0.6782 | 1.87 | 30500 | 0.6407 |
|
| 110 |
+
| 0.6787 | 1.9 | 31000 | 0.6402 |
|
| 111 |
+
| 0.6752 | 1.93 | 31500 | 0.6393 |
|
| 112 |
+
| 0.6769 | 1.96 | 32000 | 0.6392 |
|
| 113 |
+
| 0.6768 | 1.99 | 32500 | 0.6390 |
|
| 114 |
+
|
| 115 |
+
|
| 116 |
+
### Framework versions
|
| 117 |
+
|
| 118 |
+
- Transformers 4.26.0
|
| 119 |
+
- Pytorch 1.13.1+cu116
|
| 120 |
+
- Tokenizers 0.13.2
|