Update README.md
Browse files
README.md
CHANGED
|
@@ -1,17 +1,63 @@
|
|
| 1 |
Book (์ฌํ๊ณผํ, ๊ธฐ์ ๊ณผํ, ์ฒ ํ, ๋ฒํ, ์์ ๋ฑ) - 5000๊ฐ
|
|
|
|
|
|
|
| 2 |
qlora
|
|
|
|
| 3 |
max_seq_length=1024
|
|
|
|
|
|
|
| 4 |
num_train_epochs=3
|
|
|
|
|
|
|
| 5 |
per_device_train_batch_size=8
|
|
|
|
|
|
|
| 6 |
gradient_accumulation_steps=32,
|
|
|
|
|
|
|
| 7 |
evaluation_strategy="steps"
|
|
|
|
|
|
|
| 8 |
eval_steps=2000,
|
|
|
|
|
|
|
| 9 |
logging_steps=25,
|
|
|
|
|
|
|
| 10 |
optim="paged_adamw_8bit",
|
|
|
|
|
|
|
| 11 |
learning_rate=2e-4,
|
|
|
|
|
|
|
| 12 |
lr_scheduler_type="cosine",
|
|
|
|
|
|
|
| 13 |
warmup_steps=10,
|
|
|
|
|
|
|
| 14 |
warmup_ratio=0.05,
|
|
|
|
|
|
|
| 15 |
report_to="tensorboard",
|
|
|
|
|
|
|
| 16 |
weight_decay=0.01,
|
|
|
|
|
|
|
| 17 |
max_steps=-1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
Book (์ฌํ๊ณผํ, ๊ธฐ์ ๊ณผํ, ์ฒ ํ, ๋ฒํ, ์์ ๋ฑ) - 5000๊ฐ
|
| 2 |
+
|
| 3 |
+
|
| 4 |
qlora
|
| 5 |
+
|
| 6 |
max_seq_length=1024
|
| 7 |
+
|
| 8 |
+
|
| 9 |
num_train_epochs=3
|
| 10 |
+
|
| 11 |
+
|
| 12 |
per_device_train_batch_size=8
|
| 13 |
+
|
| 14 |
+
|
| 15 |
gradient_accumulation_steps=32,
|
| 16 |
+
|
| 17 |
+
|
| 18 |
evaluation_strategy="steps"
|
| 19 |
+
|
| 20 |
+
|
| 21 |
eval_steps=2000,
|
| 22 |
+
|
| 23 |
+
|
| 24 |
logging_steps=25,
|
| 25 |
+
|
| 26 |
+
|
| 27 |
optim="paged_adamw_8bit",
|
| 28 |
+
|
| 29 |
+
|
| 30 |
learning_rate=2e-4,
|
| 31 |
+
|
| 32 |
+
|
| 33 |
lr_scheduler_type="cosine",
|
| 34 |
+
|
| 35 |
+
|
| 36 |
warmup_steps=10,
|
| 37 |
+
|
| 38 |
+
|
| 39 |
warmup_ratio=0.05,
|
| 40 |
+
|
| 41 |
+
|
| 42 |
report_to="tensorboard",
|
| 43 |
+
|
| 44 |
+
|
| 45 |
weight_decay=0.01,
|
| 46 |
+
|
| 47 |
+
|
| 48 |
max_steps=-1,
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
| Model | rouge-1 | rouge-2 | rouge-l |
|
| 52 |
+
|-------|---------|---------|---------|
|
| 53 |
+
| **Book** | | | |
|
| 54 |
+
| yanolja/EEVE-Korean-Instruct-2.8B-v1.0 | 0.2095 | 0.0866 | 0.1985 |
|
| 55 |
+
| ryanu/EEVE-10.8-BOOK-v0.1 | 0.2454 | 0.1158 | 0.2404 |
|
| 56 |
+
| meta-llama/llama-3-8b-instruct | 0.2137 | 0.0883 | 0.2020 |
|
| 57 |
+
| meta-llama/llama-3-70b-instruct | 0.2269 | 0.0925 | 0.2186 |
|
| 58 |
+
| **Paper** | | | |
|
| 59 |
+
| yanolja/EEVE-Korean-Instruct-2.8B-v1.0 | 0.1934 | 0.0829 | 0.1832 |
|
| 60 |
+
| meta-llama/llama-3-8b-instruct | 0.2044 | 0.0868 | 0.1895 |
|
| 61 |
+
| meta-llama/llama-3-70b-instruct | 0.1935 | 0.0783 | 0.1836 |
|
| 62 |
+
|
| 63 |
+
|