<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
kc_electra_base_ner
This model is a fine-tuned version of monologg/koelectra-base-v3-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3099
- F1: 0.7688
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 2532 | 0.3136 | 0.6236 |
| No log | 2.0 | 5064 | 0.2314 | 0.7118 |
| No log | 3.0 | 7596 | 0.2052 | 0.7407 |
| No log | 4.0 | 10128 | 0.2022 | 0.7541 |
| No log | 5.0 | 12660 | 0.2120 | 0.7571 |
| No log | 6.0 | 15192 | 0.2289 | 0.7562 |
| No log | 7.0 | 17724 | 0.2488 | 0.7575 |
| No log | 8.0 | 20256 | 0.2745 | 0.7645 |
| No log | 9.0 | 22788 | 0.2912 | 0.7677 |
| No log | 10.0 | 25320 | 0.3099 | 0.7688 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
