peftllama / README.md
arjunpatel's picture
ai-maker-space/llama2-instruct-tune-100s
7e7ba06
metadata
base_model: NousResearch/Llama-2-7b-hf
tags:
  - generated_from_trainer
model-index:
  - name: peftllama
    results: []

peftllama

This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7050

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: 4
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 0.03
  • training_steps: 200

Training results

Training Loss Epoch Step Validation Loss
No log 0.0 20 1.7986
No log 0.0 40 1.7814
1.8763 0.0 60 1.7720
1.8763 0.01 80 1.7641
1.8826 0.01 100 1.7582
1.8826 0.01 120 1.7520
1.8826 0.01 140 1.7459
1.8864 0.01 160 1.7367
1.8864 0.01 180 1.7132
1.833 0.01 200 1.7050

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0