Edit model card

lora-llama-2-7b-nsmc-understanding

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.

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: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.03
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Framework versions

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

test accuracy

llama-2

  • Confusion Matrix:
    Predicted 0 Predicted 1
    Actual 0 450 42
    Actual 1 56 452
    Accuracy: 0.902

kt-ai-midm

  • Confusion Matrix:
    Predicted 0 Predicted 1
    Actual 0 443 49
    Actual 1 46 462
    Accuracy: 0.905

์ˆ˜์ •๋ถ€๋ถ„

  • ๋ฐ์ดํ„ฐ๋กœ๋”ฉ
    • prepare_sample_text() : ์‹œ์Šคํ…œ ๋ฉ”์‹œ์ง€ ๋ณ€๊ฒฝ ๋ฐ ํ”„๋กฌํ”„ํŠธ ํฌ๋ฉง ์„ค์ •
    • create_datasets() : train ๋ฐ์ดํ„ฐ ์ƒ์œ„ 2000๊ฐœ ์„ ํƒ
  • ๋ฏธ์„ธํŠœ๋‹์šฉ ๋ชจ๋ธ ๋กœ๋”ฉ
    • script_args : ์‚ฌ์šฉ ๋ฐ์ดํ„ฐ๋ช… nsmc ์„ค์ • ๋ฐ ๋ชจ๋ธ๋ช… meta-llama/Llama-2-7b-chat-hf ์„ค์ •
    • max_steps : ์ตœ๋Œ€ ํ›ˆ๋ จ ๋‹จ๊ณ„ 2000 ์„ค์ •
    • save : ์ฒดํฌํฌ์ธํŠธ ์„ธ์ด๋ธŒ๋ฅผ ์œ„ํ•œ ํŒŒ๋ผ๋ฏธํ„ฐ ์ง€์ •
  • ํ—ˆ๊น…ํŽ˜์ด์Šค push_to_hub ๋กœ push
  • ์ถ”๋ก ํ…Œ์ŠคํŠธ
    • ํ”„๋กฌํ”„ํŠธ ํ…œํ”Œ๋ฆฟ ์ˆ˜์ • ๋ฐ ์‹œ์Šคํ…œ ๋ฉ”์‹œ์ง€ ๋ณ€๊ฒฝ
    • valid_dataset : test ๋ฐ์ดํ„ฐ ์ƒ์œ„ 1000๊ฐœ ์„ ํƒ
  • ๋ฏธ์„ธํŠœ๋‹๋œ ๋ชจ๋ธ ๋กœ๋”ฉ ํ›„ ํ…Œ์ŠคํŠธ
    • eval_dic : valid_dataset ํ•™์Šตํ•œ ๊ฒฐ๊ณผ ์ถœ๋ ฅ
  • ์ •ํ™•๋„
    • valid_dataset ๊ณผ ๋ชจ๋ธ ํ›ˆ๋ จ ๊ฒฐ๊ณผ true_labels ๋ฅผ ์ด์šฉํ•œ ์ •ํ™•๋„ ๋ถ„์„
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Model tree for ehekaanldk/lora-llama-2-7b-nsmc-understanding

Finetuned
(293)
this model