Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
bllossom_polyglot-12.8b_0725
|
2 |
+
This model is a fine-tuned version of EleutherAI/polyglot-ko-12.8b on LIMA dataset(translated in Korean)
|
3 |
+
|
4 |
+
Training hyperparameters
|
5 |
+
The following hyperparameters were used during training:
|
6 |
+
|
7 |
+
learning_rate: 0.0002
|
8 |
+
train_batch_size: 4
|
9 |
+
eval_batch_size: 1
|
10 |
+
seed: 0
|
11 |
+
gradient_accumulation_steps: 8
|
12 |
+
total_train_batch_size: 32
|
13 |
+
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
14 |
+
lr_scheduler_type: constant
|
15 |
+
lr_scheduler_warmup_ratio: 0.03
|
16 |
+
training_steps: 200
|
17 |
+
Framework versions
|
18 |
+
Transformers 4.31.0.dev0
|
19 |
+
Pytorch 1.13.1
|
20 |
+
Datasets 2.13.1
|
21 |
+
Tokenizers 0.13.3
|