Hugging Face's logo

RL-Forgetting-Experiments-3
/
code-rl-lr-ablation

Reinforcement Learning
Safetensors
grpo
code-generation
mbpp
catastrophic-forgetting
ablation
Model card Files
xet
 Community
Evangelinejy commited on
Commit
dea3183
·
verified ·
1 Parent(s): da24a59

model card

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -34,6 +34,8 @@ point in any eval CSV maps to a folder here without a lookup table:
34
  | `qwen3_1p7b_base_mbpp_nobuf_lr3e6` | `Qwen/Qwen3-1.7B-Base` | no buffer | 3e-6 | 30-500 step 30 |
35
  | `qwen3_1p7b_base_mbpp_nobuf_lr6e6` | `Qwen/Qwen3-1.7B-Base` | no buffer | 6e-6 | 30-500 step 30 |
36
  | `qwen3b_mbpp_hardcd_lam0p1_lr3e6` | `Qwen/Qwen2.5-3B` | replay buffer (lambda=0.1) | 3e-6 | 30-300 step 30 |
 
 
37
  | `qwen3b_mbpp_nobuf_lr3e6` | `Qwen/Qwen2.5-3B` | no buffer | 3e-6 | 30-300 step 30 |
38
  | `qwen3b_mbpp_nobuf_lr6e6` | `Qwen/Qwen2.5-3B` | no buffer | 6e-6 | 30-300 step 30 |
39
  | `qwen3b_mbpp_nobuf_lr6e7` | `Qwen/Qwen2.5-3B` | no buffer | 6e-7 | 30-300 step 30 |
 
34
  | `qwen3_1p7b_base_mbpp_nobuf_lr3e6` | `Qwen/Qwen3-1.7B-Base` | no buffer | 3e-6 | 30-500 step 30 |
35
  | `qwen3_1p7b_base_mbpp_nobuf_lr6e6` | `Qwen/Qwen3-1.7B-Base` | no buffer | 6e-6 | 30-500 step 30 |
36
  | `qwen3b_mbpp_hardcd_lam0p1_lr3e6` | `Qwen/Qwen2.5-3B` | replay buffer (lambda=0.1) | 3e-6 | 30-300 step 30 |
37
+ | `qwen3b_mbpp_hardcd_lam0p1_lr6e6` | `Qwen/Qwen2.5-3B` | replay buffer (lambda=0.1) | 6e-6 | 30-300 step 30 |
38
+ | `qwen3b_mbpp_hardcd_lam0p1_lr6e7` | `Qwen/Qwen2.5-3B` | replay buffer (lambda=0.1) | 6e-7 | 30-300 step 30 |
39
  | `qwen3b_mbpp_nobuf_lr3e6` | `Qwen/Qwen2.5-3B` | no buffer | 3e-6 | 30-300 step 30 |
40
  | `qwen3b_mbpp_nobuf_lr6e6` | `Qwen/Qwen2.5-3B` | no buffer | 6e-6 | 30-300 step 30 |
41
  | `qwen3b_mbpp_nobuf_lr6e7` | `Qwen/Qwen2.5-3B` | no buffer | 6e-7 | 30-300 step 30 |