Hugging Face's logo

Vineeshsuiii
/
Final_Model

PEFT
Safetensors
Generated from Trainer
Model card Files Community
Final_Model / README.md
Vineeshsuiii's picture
Vineeshsuiii
End of training
6e4b005 verified
preview code
|
raw
history blame contribute delete
1.83 kB
metadata
base_model: meta-llama/Llama-3.2-3B-Instruct
library_name: peft
license: llama3.2
tags:
  - generated_from_trainer
model-index:
  - name: Final_Model
    results: []

Final_Model

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8592

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: 3e-05
  • train_batch_size: 1
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 6
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.9709 0.9995 231 0.9373
0.9107 1.9989 462 0.8998
0.8754 2.9984 693 0.8803
0.8334 3.9978 924 0.8679
0.8159 4.9973 1155 0.8614
0.8283 5.9968 1386 0.8592

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.2
  • Pytorch 2.0.1+cu117
  • Datasets 3.1.0
  • Tokenizers 0.20.3