Model Card for Model ID
- KT-AI/midm-bitext-S-7B-inst-v1
Model Details
Model Description
- NSMC ์ํ ๋ฆฌ๋ทฐ ๋ฐ์ดํฐ์ ๋ํ์ฌ KT-AI/midm-bitext-S-7B-inst-v1 ๋ฏธ์ธํ๋.
- ์ ๋ ฅ ํ๋กฌํํธ๋ฅผ ์ด์ฉํ์ฌ ๋ฐ์ดํฐ์ ์ document(๋ฆฌ๋ทฐ)๊ฐ ๊ธ์ ์ ์ธ ๋ด์ฉ์ด๋ฉด '1'์ ๋ถ์ ์ ์ธ ๋ด์ฉ์ด๋ฉด '0'์ ์์ธกํ๋๋ก ํจ.
- train data: nsmc train ์์ 2000๊ฐ ์ํ ์ด์ฉ
- test data: nsmc test ์์ 2000๊ฐ ์ํ ์ด์ฉ
Training Data
'nsmc'
- ์์ 2000๊ฐ ๋ฐ์ดํฐ ์ด์ฉ
Training Procedure
- prepare_sample_text์ ๋ฆฌ๋ทฐ๋ฅผ ๊ธ์ /๋ถ์ ์ผ๋ก ํ๋จํ๋๋ก ์ ๋ ฅ ํ๋กฌํํธ ์์ ํ์์.
Training Hyperparameters
- per_device_train_batch_size: 1
- per_device_eval_batch_size: 1
- learning_rate: 1e-4
- gradient_accumulation_steps: 2
- optimizer: paged_adamw_32bit
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_args.logging_steps: 50
- training_args.max_steps : 1000
- trainable params: trainable params: 16,744,448 || all params: 7,034,347,520 || trainable%: 0.23803839591934178
Results
TrainOutput(global_step=1000, training_loss=1.0208648338317872, metrics={'train_runtime': 1128.0266, 'train_samples_per_second': 1.773, 'train_steps_per_second': 0.887, 'total_flos': 3.1051694997504e+16, 'train_loss': 1.0208648338317872, 'epoch': 1.0})
Accruacy
๋ฏธ์ธํ๋ ํ ๋ชจ๋ธ์ ์ ํ๋:0.61
- Downloads last month
- 4
Model tree for Rfy23/hw-llama-2-7B-nsmc
Base model
KT-AI/midm-bitext-S-7B-inst-v1