new_intruct_llama
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0435
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4416 | 0.2584 | 50 | 1.4172 |
| 1.2754 | 0.5168 | 100 | 1.2522 |
| 1.191 | 0.7752 | 150 | 1.1805 |
| 1.1082 | 1.0336 | 200 | 1.1388 |
| 1.1026 | 1.2920 | 250 | 1.1138 |
| 1.0596 | 1.5504 | 300 | 1.0915 |
| 1.0589 | 1.8088 | 350 | 1.0756 |
| 0.9874 | 2.0672 | 400 | 1.0660 |
| 1.0128 | 2.3256 | 450 | 1.0569 |
| 0.9887 | 2.5840 | 500 | 1.0494 |
| 0.9708 | 2.8424 | 550 | 1.0435 |
Framework versions
- PEFT 0.11.0
- Transformers 4.44.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 112
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for HusnainM7/nRich-SLM-2
Base model
meta-llama/Llama-3.1-8B
Finetuned
meta-llama/Llama-3.1-8B-Instruct