daebum commited on
Commit
1ff9998
ยท
verified ยท
1 Parent(s): aa400fc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -11
README.md CHANGED
@@ -41,17 +41,19 @@ Command r plus ๋ชจ๋ธ์„ ์ด์šฉํ•˜์—ฌ ์ž์ฒด ๊ตฌ์ถ•ํ•œ RAG ํŠนํ™” ๋ฐ์ดํ„ฐ์…‹,
41
  ```
42
 
43
  ## ํ•™์Šต ํ™˜๊ฒฝ ๋ฐ ํŒŒ๋ผ๋ฏธํ„ฐ
44
- - ํŠœ๋‹ ํ™˜๊ฒฝ : H100(80GB) * 8
45
- - tokenizer_model_mex_length 4500
46
- - use_flash_attn True
47
- - num_train_epochs 3.0
48
- - weight_decay 0.001
49
- - lr_scheduler_type "linear"
50
- - per_device_train_batch_size 1
51
- - gradient_accumulation_steps 64
52
- - learning_rate 5e-06
53
- - bf16 True
54
- - deepspeed ds_stage2.json
 
 
55
 
56
  ## ์‚ฌ์šฉ ๋ฐ์ดํ„ฐ์…‹
57
  - AIhub 16 ํ–‰์ • ๋ฌธ์„œ ๋Œ€์ƒ ๊ธฐ๊ณ„๋…ํ•ด ๋ฐ์ดํ„ฐ
 
41
  ```
42
 
43
  ## ํ•™์Šต ํ™˜๊ฒฝ ๋ฐ ํŒŒ๋ผ๋ฏธํ„ฐ
44
+ - ํŠœ๋‹ ํ™˜๊ฒฝ
45
+ - H100(80GB) * 8
46
+ - ํŒŒ๋ผ๋ฏธํ„ฐ
47
+ - tokenizer_model_mex_length 4500
48
+ - use_flash_attn True
49
+ - num_train_epochs 3.0
50
+ - weight_decay 0.001
51
+ - lr_scheduler_type "linear"
52
+ - per_device_train_batch_size 1
53
+ - gradient_accumulation_steps 64
54
+ - learning_rate 5e-06
55
+ - bf16 True
56
+ - deepspeed ds_stage2.json
57
 
58
  ## ์‚ฌ์šฉ ๋ฐ์ดํ„ฐ์…‹
59
  - AIhub 16 ํ–‰์ • ๋ฌธ์„œ ๋Œ€์ƒ ๊ธฐ๊ณ„๋…ํ•ด ๋ฐ์ดํ„ฐ