hjsh/qwen2.5_math_1.5b_grpo_scaled_ratio_both_step580
2B • Updated • 1
junseo hwang
hjsh
·
AI & ML interests
None yet
Recent Activity
updated a model about 1 month ago
hjsh/qwen2.5_math_1.5b_grpo_scaled_ratio_both_step580 published a model about 1 month ago
hjsh/qwen2.5_math_1.5b_grpo_scaled_ratio_both_step580 updated a model about 2 months ago
hjsh/qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step100Organizations
None yet
models 54
hjsh/qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step100
2B • Updated • 1
hjsh/qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step100
2B • Updated • 1
hjsh/qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step580
2B • Updated • 2
hjsh/qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step580
2B • Updated • 2
hjsh/qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step550
2B • Updated • 2
hjsh/qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step550
2B • Updated • 2
hjsh/qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step500
2B • Updated • 2
hjsh/qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step500
2B • Updated • 2
hjsh/qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step450
2B • Updated • 3
datasets 0
None public yet