yiyang0101/yiyang-test

.gitignore

@@ -1 +1 @@
-results/
+yiyang-test/

README.md

@@ -1,22 +1,22 @@
 ---
-base_model: bert-base-uncased
 library_name: transformers
 license: apache-2.0
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
-- name: yiyang-test
+- name: bert-base-uncased
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# yiyang-test
+# bert-base-uncased
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8249
+- Loss: 0.7692
 
 ## Model description
 
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 1    | 0.9378          |
-| No log        | 2.0   | 2    | 0.8606          |
-| No log        | 3.0   | 3    | 0.8249          |
+| No log        | 1.0   | 1    | 0.7881          |
+| No log        | 2.0   | 2    | 0.7738          |
+| No log        | 3.0   | 3    | 0.7692          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c13bc6380e8b70ca9bc43fa95b363600754f09f5deaf5c153d820262d0618d
+oid sha256:d18737eb099b672cf528df529ec60f9fae5e170b3f518335d3eae1509d5f8ecc
 size 437958648

train.py

@@ -24,7 +24,7 @@ tokenized_datasets = datasets_split.map(tokenize_function, batched=True)
 
 # 학습 설정
 training_args = TrainingArguments(
-    output_dir="./yiyang-test",  # 학습 결과 저장 경로
+    output_dir="./",  # 학습 결과 저장 경로
     evaluation_strategy="epoch",
     learning_rate=2e-5,
     per_device_train_batch_size=16,
@@ -45,7 +45,7 @@ trainer = Trainer(
 trainer.train()
 
 # 모델 저장
-trainer.save_model("./")
+# trainer.save_model("./")
 
 # 모델 푸시
 trainer.push_to_hub("yiyang0101/yiyang-test")

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ed28a780954e8c26505e50a62c86829b664b65dd3486c8198cb966ae4d1584
+oid sha256:063c92c31a01e2397abcfe68e41da87262978baeef9ac8512e2f9500aadc2779
 size 4731