Hugging Face's logo

arshiakarimian1
/
spam-llama3.1-8B-teacher

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
spam-llama3.1-8B-teacher / README.md
arshiakarimian1's picture
arshiakarimian1
Model save
d4f2402 verified
preview code
|
raw
history blame
1.69 kB
metadata
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
library_name: peft
license: llama3.1
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: spam-llama3.1-8B-teacher
    results: []

spam-llama3.1-8B-teacher

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6694

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: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.5995 0.2010 56 1.8429
1.7494 0.4020 112 1.7069
1.1625 0.6030 168 1.6831
1.2743 0.8039 224 1.6694

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1