b9a966db-552c-460e-bab3-1e70212a7c73
This model is a fine-tuned version of NousResearch/Yarn-Llama-2-7b-64k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7980
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: 0.000218
- 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 | 0.0004 | 1 | 2.2280 |
| 2.5825 | 0.0184 | 50 | 1.3031 |
| 2.0433 | 0.0368 | 100 | 1.1150 |
| 1.9313 | 0.0552 | 150 | 1.0101 |
| 1.8045 | 0.0737 | 200 | 0.9717 |
| 1.5842 | 0.0921 | 250 | 0.9156 |
| 1.6041 | 0.1105 | 300 | 0.8702 |
| 1.4298 | 0.1289 | 350 | 0.8334 |
| 1.5412 | 0.1473 | 400 | 0.8106 |
| 1.4813 | 0.1657 | 450 | 0.7999 |
| 1.4971 | 0.1841 | 500 | 0.7980 |
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
- 7
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 lesso18/b9a966db-552c-460e-bab3-1e70212a7c73
Base model
NousResearch/Yarn-Llama-2-7b-64k