metadata
base_model: beomi/llama-2-ko-7b
tags:
- generated_from_trainer
model-index:
- name: Llama2-ko-7b-finetune-v2
results: []
Llama2-ko-7b-finetune-v2
This model is a fine-tuned version of beomi/llama-2-ko-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5327
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4901 | 0.22 | 100 | 1.5910 |
| 1.5736 | 0.44 | 200 | 1.5476 |
| 1.4611 | 0.66 | 300 | 1.5327 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.3