Trofish
/

korean_syllable_roberta_256

Inference Endpoints

Model card Files Files and versions Community

Trofish commited on May 8

Commit

0ee90b1

•

1 Parent(s): e93a827

Update README.md

Files changed (1) hide show

README.md +8 -3

README.md CHANGED Viewed

@@ -20,15 +20,20 @@
 총 합산된 데이터는 약 11GB 입니다.
 ## 학습 상세
-- **BATCH_SIZE**: 54 (GPU당)
-- **ACCUMULATE**: 74
 - **MAX_STEPS**: 12,500
-- **Train Steps*Batch Szie**: 100M
 - **WARMUP_STEPS**: 2,400
 - **최적화**: AdamW, LR 1e-3, BETA (0.9, 0.98), eps 1e-6
 - **학습률 감쇠**: linear
 - **사용된 하드웨어**: 2x RTX 8000 GPU
 ## 사용 방법
 ```python
 from transformers import AutoModel, AutoTokenizer

 총 합산된 데이터는 약 11GB 입니다.
 ## 학습 상세
+- **BATCH_SIZE**: 112 (GPU당)
+- **ACCUMULATE**: 36
 - **MAX_STEPS**: 12,500
+- **Train Steps*Batch Szie**: **100M**
 - **WARMUP_STEPS**: 2,400
 - **최적화**: AdamW, LR 1e-3, BETA (0.9, 0.98), eps 1e-6
 - **학습률 감쇠**: linear
 - **사용된 하드웨어**: 2x RTX 8000 GPU
+![Evaluation Loss Graph](https://cdn-uploads.huggingface.co/production/uploads/64a0fd6fd3149e05bc5260dd/-64jKdcJAavwgUREwaywe.png)
+![Evaluation Accuracy Graph](https://cdn-uploads.huggingface.co/production/uploads/64a0fd6fd3149e05bc5260dd/LPq5M6S8LTwkFSCepD33S.png)
 ## 사용 방법
 ```python
 from transformers import AutoModel, AutoTokenizer