metadata
license: apache-2.0
base_model: EleutherAI/polyglot-ko-1.3b
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: reward-gpt
results: []
reward-gpt
This model is a fine-tuned version of EleutherAI/polyglot-ko-1.3b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Accuracy: 0.5
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: 9e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 2023
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0554 | 0.16 | 100 | 0.0000 | 0.5 |
| 0.0356 | 0.33 | 200 | 0.0000 | 0.5 |
| 0.0741 | 0.49 | 300 | 0.0000 | 0.0 |
| 0.0399 | 0.65 | 400 | 0.0000 | 0.0 |
| 0.0307 | 0.81 | 500 | 0.0000 | 0.5 |
| 0.0331 | 0.98 | 600 | 0.0000 | 0.5 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1