metadata
library_name: peft
license: apache-2.0
base_model: Intel/neural-chat-7b-v3-1
tags:
- generated_from_trainer
model-index:
- name: Intel-neural-chat-7B-v3-1-009
results: []
Intel-neural-chat-7B-v3-1-009
This model is a fine-tuned version of Intel/neural-chat-7b-v3-1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1827
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4746 | 0.9927 | 102 | 0.4962 |
| 0.3475 | 1.9927 | 204 | 0.3832 |
| 0.3142 | 2.9927 | 306 | 0.3110 |
| 0.2628 | 3.9927 | 408 | 0.2641 |
| 0.2059 | 4.9927 | 510 | 0.2351 |
| 0.1746 | 5.9927 | 612 | 0.2149 |
| 0.1686 | 6.9927 | 714 | 0.2002 |
| 0.1514 | 7.9927 | 816 | 0.1911 |
| 0.1371 | 8.9927 | 918 | 0.1846 |
| 0.1255 | 9.9927 | 1020 | 0.1827 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.5.1
- Tokenizers 0.21.1