v0.2
This model is a fine-tuned version of EleutherAI/polyglot-ko-5.8b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2277
- Accuracy: 0.4969
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2287 | 0.5 | 22 | 2.4602 | 0.4882 |
| 2.0297 | 1.0 | 44 | 2.3277 | 0.4913 |
| 1.0888 | 1.5 | 66 | 2.4852 | 0.4976 |
| 0.894 | 2.0 | 88 | 2.5449 | 0.4961 |
| 0.2617 | 2.5 | 110 | 3.0394 | 0.4882 |
| 0.2666 | 3.0 | 132 | 3.0984 | 0.4984 |
| 0.1301 | 3.5 | 154 | 3.2467 | 0.4858 |
| 0.1429 | 4.0 | 176 | 3.1169 | 0.4913 |
| 0.092 | 4.5 | 198 | 3.2166 | 0.4961 |
| 0.035 | 5.0 | 220 | 3.2277 | 0.4969 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 3
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated)
instead.