Hugging Face's logo

RL-Forgetting-Experiments-3
/
code-llama3p2_3b-nobuf

Reinforcement Learning
Safetensors
grpo
code-generation
mbpp
catastrophic-forgetting
Model card Files
xet
 Community
code-llama3p2_3b-nobuf

Commit History

Add MBPP+ training-set eval pass@k summaries (10 checkpoints)
34ea153
verified

smilani commited on

llama3p2_3b_it_mbpp_nobuf global_step_300
089233d
verified

Evangelinejy commited on

llama3p2_3b_it_mbpp_nobuf global_step_270
217400e
verified

Evangelinejy commited on

llama3p2_3b_it_mbpp_nobuf global_step_240
c89a072
verified

Evangelinejy commited on

llama3p2_3b_it_mbpp_nobuf global_step_210
29f34c6
verified

Evangelinejy commited on

llama3p2_3b_it_mbpp_nobuf global_step_180
e20ad0b
verified

Evangelinejy commited on

llama3p2_3b_it_mbpp_nobuf global_step_150
15e8157
verified

Evangelinejy commited on

llama3p2_3b_it_mbpp_nobuf global_step_120
dbe367a
verified

Evangelinejy commited on

llama3p2_3b_it_mbpp_nobuf global_step_90
69def3d
verified

Evangelinejy commited on

llama3p2_3b_it_mbpp_nobuf global_step_60
b9884b9
verified

Evangelinejy commited on

llama3p2_3b_it_mbpp_nobuf global_step_30
22761bf
verified

Evangelinejy commited on

model card
5d26fa5
verified

Evangelinejy commited on

initial commit
1042fe3
verified

Evangelinejy commited on