shubhamprshr
/

Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_cosine_0.5_0.5_True_1200

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_cosine_0.5_0.5_True_1200

Commit History

End of training

df5d636
verified

shubhamprshr commited on 8 days ago

Model save

334a1e7
verified

shubhamprshr commited on 8 days ago

Training in progress, step 1200

4c63d23
verified

shubhamprshr commited on 8 days ago

initial commit

4383b93
verified

shubhamprshr commited on 9 days ago