Update README.md

README.md

@@ -12,21 +12,20 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lora-llama-2-7b-nsmc
 
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on 'nsmc' dataset.
 
 ## Model description
 
-More information needed
+[meta-llama/Llama-2-7b-chat-hf]를 nsmc 데이터셋을 이용하여 미세튜닝함.
 
 ## Intended uses & limitations
 
-More information needed
+목적: 영화 리뷰 판단 (긍정/부정)
 
 ## Training and evaluation data
 
-More information needed
-
-## Training procedure
+- training data: nsmc의 train 데이터 중 상위 2000개
+- evaluation data: nsmc의 test 데이터 중 상위 1000개
 
 ### Training hyperparameters
 
@@ -45,7 +44,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-
+- global_step=1000
+- training_loss=0.7012106285095215
+- metrics={'train_runtime': 3567.3706, 'train_samples_per_second': 0.561, 'train_steps_per_second': 0.28, 'total_flos': 4.0718328397824e+16, 'train_loss': 0.7012106285095215, 'epoch': 1.0}
 
 ### Framework versions
 
@@ -53,3 +54,12 @@ The following hyperparameters were used during training:
 - Pytorch 2.1.0+cu118
 - Datasets 2.15.0
 - Tokenizers 0.15.0
+
+### Accuracy
+
+||TP|TN|
+|------|---|---|
+|PP|436|36|
+|PN|72|456|
+
+- accuracy: 0.89