Hugging Face's logo

kangdawei
/
MMR-DR_GRPO-lambda-0.9

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Community
kangdawei commited on
Commit
eb8457a
·
verified ·
1 Parent(s): 48361b4

Training in progress, step 500

Browse files
Files changed (12) hide show
  1. model.safetensors +1 -1
  2. reward_data/all_rewards.csv +2 -2
  3. reward_plots/advantage_plot_step_450.png +0 -0
  4. reward_plots/advantage_plot_step_460.png +0 -0
  5. reward_plots/advantage_plot_step_470.png +0 -0
  6. reward_plots/advantage_plot_step_480.png +0 -0
  7. reward_plots/advantage_plot_step_490.png +0 -0
  8. reward_plots/reward_comparison_step_450.png +0 -0
  9. reward_plots/reward_comparison_step_460.png +0 -0
  10. reward_plots/reward_comparison_step_470.png +0 -0
  11. reward_plots/reward_comparison_step_480.png +0 -0
  12. reward_plots/reward_comparison_step_490.png +0 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d98ba19bca22aae235340178a672a43e55842ee59324f8afe927c23c8a32d93
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22ec8a2b634a2052024c9adcfeacf2bcfa89c6aab8233dce5f6d156bd9dd9d0
3
  size 3554214752
reward_data/all_rewards.csv CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ca629b352c1b6aa6c766eeb8cd6b723abdda8286b28f52a243e972169e6c8f0
3
- size 179745457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076132ed5d086ca7ff379fe8fc71cdb1c04c72d0a7d40fbda5608fe0c8e762d7
3
+ size 182894138
reward_plots/advantage_plot_step_450.png ADDED
reward_plots/advantage_plot_step_460.png ADDED
reward_plots/advantage_plot_step_470.png ADDED
reward_plots/advantage_plot_step_480.png ADDED
reward_plots/advantage_plot_step_490.png ADDED
reward_plots/reward_comparison_step_450.png ADDED
reward_plots/reward_comparison_step_460.png ADDED
reward_plots/reward_comparison_step_470.png ADDED
reward_plots/reward_comparison_step_480.png ADDED
reward_plots/reward_comparison_step_490.png ADDED