e2cfacf6-0034-4587-8961-098036d0f7fc
This model is a fine-tuned version of Orenguteng/Llama-3-8B-Lexi-Uncensored on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0496
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: 0.000206
- 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 | 0.0001 | 1 | 4.2358 |
| 2.2173 | 0.0031 | 50 | 1.7807 |
| 1.6297 | 0.0062 | 100 | 1.5914 |
| 1.6644 | 0.0094 | 150 | 1.5123 |
| 1.4066 | 0.0125 | 200 | 1.3771 |
| 1.6502 | 0.0156 | 250 | 1.2847 |
| 1.3719 | 0.0187 | 300 | 1.2194 |
| 1.2802 | 0.0219 | 350 | 1.1549 |
| 1.2328 | 0.0250 | 400 | 1.0864 |
| 1.1633 | 0.0281 | 450 | 1.0579 |
| 1.2909 | 0.0312 | 500 | 1.0496 |
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 lesso06/e2cfacf6-0034-4587-8961-098036d0f7fc
Base model
Orenguteng/Llama-3-8B-Lexi-Uncensored