Update README.md

README.md

@@ -20,6 +20,15 @@ A Dual-System Visual-Language-Action model with System-2 thinking trained on Lib
 - Homepage: [https://hume-vla.github.io](https://hume-vla.github.io)
 - Codebase: [🦾 Hume: A Dual-System VLA with System2 Thinking](https://github.com/hume-vla/hume) ![GitHub Repo stars](https://img.shields.io/github/stars/hume-vla/hume)
 
+## Optimal TTS Args
+```bash
+s2_candidates_num=5
+noise_temp_lower_bound=1.0
+noise_temp_upper_bound=1.2
+time_temp_lower_bound=1.0
+time_temp_upper_bound=1.0
+```
+
 
 ## Uses
 
@@ -58,8 +67,14 @@ A Dual-System Visual-Language-Action model with System-2 thinking trained on Lib
   
   # Infer the action
   action = hume.infer(observation) # (B, action_dim)
-  
   ```
+## Training and Evaluation Details
+```bash
+# source ckpts
+2025-05-01/19-56-05_libero_object_ck8-16-1_sh-4_gpu8_lr5e-5_1e-5_1e-5_2e-5_bs16_s1600k/0150000
+# original logs
+2025-06-13/00-18-26+19-56-05_libero_object_ck8-16-1_sh-4_gpu8_lr5e-5_1e-5_1e-5_2e-5_bs16_s1600k_0150000_s1-8_s2-16_s2cand-5_ntl-1.0_ntu-1.2_ttl-1.0_ttu-1.0.log
+```
 
 ## Citation