d8b4ae03-b466-475d-8871-8e3609b795a9
This model is a fine-tuned version of NousResearch/Yarn-Solar-10b-64k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7251
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: 0.000208
- train_batch_size: 4
- eval_batch_size: 4
- seed: 80
- 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 | 0.0002 | 1 | 3.8406 |
| 3.4317 | 0.0123 | 50 | 2.1300 |
| 4.0251 | 0.0246 | 100 | 2.2699 |
| 4.0076 | 0.0370 | 150 | 2.1542 |
| 3.9822 | 0.0493 | 200 | 2.1012 |
| 4.1762 | 0.0616 | 250 | 2.1172 |
| 3.9609 | 0.0739 | 300 | 2.0517 |
| 3.5654 | 0.0863 | 350 | 1.8574 |
| 3.8953 | 0.0986 | 400 | 1.7636 |
| 3.5196 | 0.1109 | 450 | 1.7324 |
| 3.5463 | 0.1232 | 500 | 1.7251 |
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 lesso08/d8b4ae03-b466-475d-8871-8e3609b795a9
Base model
NousResearch/Yarn-Solar-10b-64k