e1d633c8-1178-48ff-a616-b0c4c3e1ff95
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: 0.6368
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: 0.000217
- train_batch_size: 4
- eval_batch_size: 4
- seed: 170
- 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 | 3.3232 |
| 1.1612 | 0.0018 | 50 | 1.7949 |
| 1.0974 | 0.0037 | 100 | 1.6512 |
| 0.8748 | 0.0055 | 150 | 1.6278 |
| 0.8727 | 0.0073 | 200 | 1.3154 |
| 0.8983 | 0.0091 | 250 | 1.1016 |
| 0.7951 | 0.0110 | 300 | 0.9889 |
| 0.7452 | 0.0128 | 350 | 0.7997 |
| 0.6468 | 0.0146 | 400 | 0.7177 |
| 0.6286 | 0.0165 | 450 | 0.6477 |
| 0.6262 | 0.0183 | 500 | 0.6368 |
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
- 9
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 lesso17/e1d633c8-1178-48ff-a616-b0c4c3e1ff95
Base model
oopsung/llama2-7b-koNqa-test-v1