Hugging Face's logo

kangdawei
/
MMR-GRPO-lambda-0.6

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
64465dc
·
verified ·
1 Parent(s): 9622222

Training in progress, step 400

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_350.png +0 -0
  4. reward_plots/advantage_plot_step_360.png +0 -0
  5. reward_plots/advantage_plot_step_370.png +0 -0
  6. reward_plots/advantage_plot_step_380.png +0 -0
  7. reward_plots/advantage_plot_step_390.png +0 -0
  8. reward_plots/reward_comparison_step_350.png +0 -0
  9. reward_plots/reward_comparison_step_360.png +0 -0
  10. reward_plots/reward_comparison_step_370.png +0 -0
  11. reward_plots/reward_comparison_step_380.png +0 -0
  12. reward_plots/reward_comparison_step_390.png +0 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06ce5253652a5fce558c6f6fd74d597638f0075cbdc97e48df4c86ef82639493
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:813b0dd03877615b6f2f84ed5b82b88b3d24d51aafcff4d7cf65a907d6325661
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:b6dd0c642f069c0de6e98220329dc9996dd71095a687325fe0a46beee37b05e0
3
- size 228075773
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a96469d6a1046dd951cc1167049ebcee436de885d302366eb201b0ed86745f04
3
+ size 250628068
reward_plots/advantage_plot_step_350.png ADDED
reward_plots/advantage_plot_step_360.png ADDED
reward_plots/advantage_plot_step_370.png ADDED
reward_plots/advantage_plot_step_380.png ADDED
reward_plots/advantage_plot_step_390.png ADDED
reward_plots/reward_comparison_step_350.png ADDED
reward_plots/reward_comparison_step_360.png ADDED
reward_plots/reward_comparison_step_370.png ADDED
reward_plots/reward_comparison_step_380.png ADDED
reward_plots/reward_comparison_step_390.png ADDED