diff --git a/README.md b/README.md
index 177ae94..ff3974b 100644
--- a/README.md
+++ b/README.md
@@ -25,7 +25,7 @@ python train.py --name EXPERMENT_NAME
python eval.py --ckpt_path PATH_TO_CKPT --im_size RESOLUTION
```
-* Visualize baselines logs and your experiments using Tensorboard.
+* Visualize baseline logs and your experiments using Tensorboard.
```shell
tensorboard --logdir out --bind_all
@@ -39,18 +39,21 @@ tensorboard --logdir out --bind_all
# Baseline Models
The baseline models are Residual SNGANs from [Mimicry: Towards the Reproducibility of GAN Research](https://github.com/kwotsin/mimicry).
-Resolution |32x32 |64x64
-:------------------------:|:-------------------------:|:-------------------------:
-Seed |0 |0
-Batch Size |64 |64
-niter |150k |150k
-ndis |5 |5
-β1 |0 |0
-β2 |0.9 |0.9
-lr |2e-4 |2e-4
-lrdecay |Linear |Linear
-IS |6.212 |7.234
-FID |42.452 |68.360
-KID |0.02734 |0.06240
-Samples |![](https://user-images.githubusercontent.com/50810315/135712701-9a154614-1703-4aa4-94a3-54db05908dd8.png) |![](https://user-images.githubusercontent.com/50810315/135712698-e7294a67-949b-482f-9212-075a7ddb59a6.png)
-
+
+Baselines |Baseline-32-150k |Baseline-64-150k |Baseline-32-295k |Baseline-64-295k
+:------------------------:|:-------------------------:|:-------------------------:|:-------------------------:|:-------------------------:
+Resolution |32x32 |64x64 |32x32 |64x64
+Seed |0 |0 |236 |236
+Batch Size |64 |64 |64 |64
+niter |150k |150k |295k |295k
+ndis |5 |5 |5 |5
+β1 |0 |0 |0 |0
+β2 |0.9 |0.9 |0.9 |0.9
+lr |2e-4 |2e-4 |2e-4 |2e-4
+lrdecay |Linear |Linear |Linear |Linear
+IS |6.212 |7.234 |6.326 |7.330
+FID |42.452 |68.360 |35.339 |62.250
+KID |0.02734 |0.06240 |0.01984 |0.05556
+Samples |![](https://user-images.githubusercontent.com/50810315/135712701-9a154614-1703-4aa4-94a3-54db05908dd8.png)|![](https://user-images.githubusercontent.com/50810315/135712698-e7294a67-949b-482f-9212-075a7ddb59a6.png)|![](https://user-images.githubusercontent.com/50810315/135767248-06df651c-1bba-4f51-9d8c-31d3c9c9c4ff.png)|![](https://user-images.githubusercontent.com/50810315/135767245-e37ed07f-f71c-4a82-81e7-9b88277f73aa.png)
+
+> NOTE: Use 150k baselines to benchmark models trained from scratch and use 295k baselines if your models don't involve training from scratch.