Hugging Face's logo

kangdawei
/
MMR-GRPO-lambda-0.8

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
76b54ff
·
verified ·
1 Parent(s): c35f3d3

Training in progress, step 250

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_200.png +0 -0
  4. reward_plots/advantage_plot_step_210.png +0 -0
  5. reward_plots/advantage_plot_step_220.png +0 -0
  6. reward_plots/advantage_plot_step_230.png +0 -0
  7. reward_plots/advantage_plot_step_240.png +0 -0
  8. reward_plots/reward_comparison_step_200.png +0 -0
  9. reward_plots/reward_comparison_step_210.png +0 -0
  10. reward_plots/reward_comparison_step_220.png +0 -0
  11. reward_plots/reward_comparison_step_230.png +0 -0
  12. reward_plots/reward_comparison_step_240.png +0 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0014ba096fccbffdbcb7b1495ae6834a2e4c8555f3e7a88f2b78915ebdc04003
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02bfd3a0a07445c726da4e557d08da91bd3ea67f7991f8a14fdd041345d0db06
3
  size 3554214752
reward_data/all_rewards.csv CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99db69da3bd8b118a11ef836e43094a1459ecf54554677fa2b2f7f3deb0f8aad
3
- size 153211908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e9308b5c989d2020d9ee3227173d5c8b125ecdc601e69574e3362f4a668b99
3
+ size 175542426
reward_plots/advantage_plot_step_200.png ADDED
reward_plots/advantage_plot_step_210.png ADDED
reward_plots/advantage_plot_step_220.png ADDED
reward_plots/advantage_plot_step_230.png ADDED
reward_plots/advantage_plot_step_240.png ADDED
reward_plots/reward_comparison_step_200.png ADDED
reward_plots/reward_comparison_step_210.png ADDED
reward_plots/reward_comparison_step_220.png ADDED
reward_plots/reward_comparison_step_230.png ADDED
reward_plots/reward_comparison_step_240.png ADDED