happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_4
Viewer
•
Updated
•
1
•
11
Liu
happynew111
AI & ML interests
None yet
Organizations
None yet
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_3
Viewer
•
Updated
•
1
•
15
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_2
Viewer
•
Updated
•
1
•
12
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_1
Viewer
•
Updated
•
1
•
10
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_5
Viewer
•
Updated
•
1
•
20
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_4
Viewer
•
Updated
•
1
•
23
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_3
Viewer
•
Updated
•
1
•
13
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_2
Viewer
•
Updated
•
1
•
13
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_1
Viewer
•
Updated
•
1
•
11
happynew111/haotian_data-GPS-AR-Lopti-master
Preview
•
Updated
•
230
happynew111/haotian_data-GPS-Model
Updated
•
15
happynew111/haotian_data-GPS-CCGSPG_for_me
Updated
•
248
happynew111/haotian_data-GPS-CCGSPG_for_me_second
Updated
•
123
happynew111/haotian_data-GPS-GAINRL-main
Updated
•
159
happynew111/haotian_data-GPS-lm-evaluation-harness
Updated
•
388
happynew111/haotian_data-GPS-verl-main-CL
Updated
•
600
happynew111/haotian_data-GPS-verl-main
Viewer
•
Updated
•
13.5k
•
108
happynew111/MATH_BS_BCE_train_json
Viewer
•
Updated
•
8.97M
•
84
happynew111/MATH_BS_BCE_valid_log_json
Viewer
•
Updated
•
1.51M
•
57
happynew111/AR_train_json
Viewer
•
Updated
•
12.5k
•
3.08k
happynew111/AR_valid_log_json
Preview
•
Updated
•
436
happynew111/MATH_train_json
Viewer
•
Updated
•
7
•
2.79k
happynew111/MATH_valid_log_json
Updated
•
97