Update README.md

README.md

@@ -11,9 +11,25 @@ base_model: meta-llama/Llama-2-7b-chat-hf
 - NSMC의 train 스플릿 상위 2,000개 이상의 샘플을 학습에 사용
 - test 스플릿 상위 1,000개의 샘플만 측정
 
-
-
-## Training Results
+### 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_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08,
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- training_args.logging_steps: 100
+- training_args.max_steps : 1600
+- trainable params: 19,988,480 || all params: 6,758,404,096 || trainable%: 0.2957573965106688
+
+### Training Results
 
 TrainOutput(global_step=1600, training_loss=0.7892872190475464,
 metrics={'train_runtime': 5825.2445, 'train_samples_per_second': 0.549, 
@@ -21,7 +37,7 @@ metrics={'train_runtime': 5825.2445, 'train_samples_per_second': 0.549,
 'train_loss': 0.7892872190475464, 'epoch': 1.6})
 
 
-#### Accuracy
+### Accuracy
 
 Llama2: 정확도 0.52
 
@@ -32,6 +48,6 @@ Llama2: 정확도 0.52
 
 
 
-## Model Card Authors
+### Model Card Authors
 
 cxoijve