Hugging Face's logo

Spaces:
agentDebugger
/
AgentDebugger-training-v3
Running

App Files Community
shank commited on
Commit
3eb8edc
·
1 Parent(s): c02b65b

fix: use GitHub raw URLs for images so README renders on HF Space

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -54,16 +54,16 @@ Our training run clearly demonstrates rapid policy adaptation. The model success
54
 
55
  *(Note for Hackathon Judges: Live Weights & Biases charts and Gradio UI are embedded below as evidence of the training run).*
56
 
57
- ![Total Reward](images/total.png)
58
- ![Format Compliance](images/format_compliance.png)
59
 
60
  *Additional Training Metrics:*
61
  <p align="center">
62
- <img src="images/hypothesis_quality.png" width="48%" />
63
- <img src="images/semantic.png" width="48%" />
64
  </p>
65
 
66
- ![Gradio UI Training Monitor](images/gradio%20UI.png)
67
 
68
  * **Format Compliance:** Scaled to 1.0 (max) within 50 steps.
69
  * **Total Reward:** Scaled from baseline ~0.4 to peaks of ~1.0 by step 250.
 
54
 
55
  *(Note for Hackathon Judges: Live Weights & Biases charts and Gradio UI are embedded below as evidence of the training run).*
56
 
57
+ ![Total Reward](https://raw.githubusercontent.com/shasshaank/AgentDebuggerEnv/main/images/total.png)
58
+ ![Format Compliance](https://raw.githubusercontent.com/shasshaank/AgentDebuggerEnv/main/images/format_compliance.png)
59
 
60
  *Additional Training Metrics:*
61
  <p align="center">
62
+ <img src="https://raw.githubusercontent.com/shasshaank/AgentDebuggerEnv/main/images/hypothesis_quality.png" width="48%" />
63
+ <img src="https://raw.githubusercontent.com/shasshaank/AgentDebuggerEnv/main/images/semantic.png" width="48%" />
64
  </p>
65
 
66
+ ![Gradio UI Training Monitor](https://raw.githubusercontent.com/shasshaank/AgentDebuggerEnv/main/images/gradio%20UI.png)
67
 
68
  * **Format Compliance:** Scaled to 1.0 (max) within 50 steps.
69
  * **Total Reward:** Scaled from baseline ~0.4 to peaks of ~1.0 by step 250.