metadata
library_name: peft
base_model: oopsung/llama2-7b-koNqa-test-v1
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 69246771-a625-42d2-ac7c-5662478974f5
results: []
69246771-a625-42d2-ac7c-5662478974f5
This model is a fine-tuned version of oopsung/llama2-7b-koNqa-test-v1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1476
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: 0.000204
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0009 | 1 | 2.8770 |
| 0.4058 | 0.0443 | 50 | 0.4839 |
| 0.2543 | 0.0887 | 100 | 0.3843 |
| 0.2117 | 0.1330 | 150 | 0.3515 |
| 0.2255 | 0.1774 | 200 | 0.3306 |
| 0.1617 | 0.2217 | 250 | 0.2855 |
| 0.1575 | 0.2661 | 300 | 0.2383 |
| 0.179 | 0.3104 | 350 | 0.1824 |
| 0.1444 | 0.3548 | 400 | 0.1612 |
| 0.1243 | 0.3991 | 450 | 0.1467 |
| 0.0943 | 0.4435 | 500 | 0.1476 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1