update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: kobigbird-bert-base-finetuned-klue-goorm-q-a-task
|
| 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 |
+
# kobigbird-bert-base-finetuned-klue-goorm-q-a-task
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [ToToKr/kobigbird-bert-base-finetuned-klue](https://huggingface.co/ToToKr/kobigbird-bert-base-finetuned-klue) on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 1.2115
|
| 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: 4
|
| 37 |
+
- eval_batch_size: 4
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 20
|
| 42 |
+
|
| 43 |
+
### Training results
|
| 44 |
+
|
| 45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 47 |
+
| 1.6159 | 0.09 | 500 | 1.7522 |
|
| 48 |
+
| 1.554 | 0.17 | 1000 | 1.5953 |
|
| 49 |
+
| 1.4493 | 0.26 | 1500 | 1.3769 |
|
| 50 |
+
| 1.4051 | 0.35 | 2000 | 1.3746 |
|
| 51 |
+
| 1.3251 | 0.43 | 2500 | 1.5049 |
|
| 52 |
+
| 1.2855 | 0.52 | 3000 | 1.1733 |
|
| 53 |
+
| 1.2226 | 0.6 | 3500 | 1.1538 |
|
| 54 |
+
| 1.1907 | 0.69 | 4000 | 1.1470 |
|
| 55 |
+
| 1.1655 | 0.78 | 4500 | 1.0759 |
|
| 56 |
+
| 1.1411 | 0.86 | 5000 | 1.0676 |
|
| 57 |
+
| 1.0752 | 0.95 | 5500 | 0.9894 |
|
| 58 |
+
| 0.9389 | 1.04 | 6000 | 1.2020 |
|
| 59 |
+
| 0.8457 | 1.12 | 6500 | 1.1004 |
|
| 60 |
+
| 0.7977 | 1.21 | 7000 | 1.1397 |
|
| 61 |
+
| 0.818 | 1.29 | 7500 | 1.2960 |
|
| 62 |
+
| 0.8142 | 1.38 | 8000 | 1.2115 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.18.0
|
| 68 |
+
- Pytorch 1.10.0+cu111
|
| 69 |
+
- Datasets 2.1.0
|
| 70 |
+
- Tokenizers 0.12.1
|