sft_241015_1600_1
This model is a fine-tuned version of /media/enssel/DataDisk/Models/Llama-3.2-3B-Instruct on the app_logs_modified_1 and the NIST_SP_800_53 datasets. It achieves the following results on the evaluation set:
- Loss: 1.8549
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
Application_logs and NIST_SP_800_53 datasets
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9548 | 8.6957 | 50 | 1.8549 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for Enssel/llama3.2_3b_lora_sft_241010
Base model
meta-llama/Llama-3.2-1B-Instruct