39170f1f-e0ed-4fcb-bdc4-2bb25e98161d
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: 1.1528
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: 0.000214
- train_batch_size: 4
- eval_batch_size: 4
- seed: 140
- 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 | 0.0000 | 1 | 2.2965 |
| 1.4541 | 0.0008 | 50 | 1.2898 |
| 1.4665 | 0.0017 | 100 | 1.3165 |
| 1.538 | 0.0025 | 150 | 1.2745 |
| 1.4803 | 0.0034 | 200 | 1.2688 |
| 1.63 | 0.0042 | 250 | 1.2357 |
| 1.5497 | 0.0051 | 300 | 1.2233 |
| 1.5781 | 0.0059 | 350 | 1.1787 |
| 1.3724 | 0.0067 | 400 | 1.1628 |
| 1.346 | 0.0076 | 450 | 1.1539 |
| 1.2756 | 0.0084 | 500 | 1.1528 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 8
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for lesso14/39170f1f-e0ed-4fcb-bdc4-2bb25e98161d
Base model
oopsung/llama2-7b-koNqa-test-v1