update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: ks-chungcheong-nmt-v2
|
| 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 |
+
# ks-chungcheong-nmt-v2
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [smile3634/ks-chungcheong-nmt-v1](https://huggingface.co/smile3634/ks-chungcheong-nmt-v1) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.2771
|
| 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-05
|
| 36 |
+
- train_batch_size: 16
|
| 37 |
+
- eval_batch_size: 16
|
| 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: 3
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 1.8849 | 0.16 | 500 | 1.8573 |
|
| 50 |
+
| 1.7337 | 0.32 | 1000 | 1.6565 |
|
| 51 |
+
| 1.5085 | 0.49 | 1500 | 1.2008 |
|
| 52 |
+
| 1.1849 | 0.65 | 2000 | 0.8869 |
|
| 53 |
+
| 0.9535 | 0.81 | 2500 | 0.6806 |
|
| 54 |
+
| 0.8032 | 0.97 | 3000 | 0.5774 |
|
| 55 |
+
| 0.5472 | 1.13 | 3500 | 0.5094 |
|
| 56 |
+
| 0.4656 | 1.29 | 4000 | 0.4570 |
|
| 57 |
+
| 0.4269 | 1.46 | 4500 | 0.4286 |
|
| 58 |
+
| 0.3916 | 1.62 | 5000 | 0.4011 |
|
| 59 |
+
| 0.3564 | 1.78 | 5500 | 0.3676 |
|
| 60 |
+
| 0.3259 | 1.94 | 6000 | 0.3422 |
|
| 61 |
+
| 0.2513 | 2.1 | 6500 | 0.3312 |
|
| 62 |
+
| 0.2101 | 2.26 | 7000 | 0.3111 |
|
| 63 |
+
| 0.1991 | 2.43 | 7500 | 0.2985 |
|
| 64 |
+
| 0.1893 | 2.59 | 8000 | 0.2960 |
|
| 65 |
+
| 0.1774 | 2.75 | 8500 | 0.2823 |
|
| 66 |
+
| 0.1687 | 2.91 | 9000 | 0.2771 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.26.0
|
| 72 |
+
- Pytorch 1.13.1+cu116
|
| 73 |
+
- Tokenizers 0.13.2
|