Aghyad Deeb

aptl26 's models 105

Sort:  Recently updated

aptl26/nov3_new_envs_math_memory-user_1e-3kl_150

8B • Updated Nov 4, 2025 • 1

aptl26/nov3_new_envs_math_memory-user_1e-3kl_resume_65

8B • Updated Nov 3, 2025 • 2

aptl26/nov3_new_envs_math_memory-user_1e-3kl

8B • Updated Nov 3, 2025 • 3

aptl26/2nodes_135-335step_8b_16MB_256TB_with_5e-3KL_2e-5lr__global_step_70__with_config

Updated Nov 1, 2025

aptl26/2nodes_135-335step_8b_16MB_256TB_with_5e-3KL_2e-5lr__global_step_70__actor__lora_adapter

Updated Nov 1, 2025

aptl26/oct31_8b_135-335_different

8B • Updated Oct 31, 2025 • 2

aptl26/8nodes_135step_8b_with_5e-3KL_2e-5lr__global_step_335__actor__lora_adapter

Updated Oct 31, 2025

aptl26/oct29_8b_135

8B • Updated Oct 29, 2025 • 4

aptl26/oct25_32b_170-50-440

33B • Updated Oct 26, 2025 • 6

aptl26/continue_170-50_no_omit_32b_16MB_128TB_1e-5LR_lora__global_step_430

Updated Oct 26, 2025

aptl26/oct25_32b_170-50-410

33B • Updated Oct 26, 2025 • 5

aptl26/oct24_32b_170-50-245_different_removed3envs

33B • Updated Oct 25, 2025 • 3

aptl26/oct22_32b_170-90_different

33B • Updated Oct 23, 2025 • 2

aptl26/oct22_32b_170-50_different

33B • Updated Oct 23, 2025 • 2

aptl26/oct22_32b_170-45_different

33B • Updated Oct 23, 2025 • 2

aptl26/32b_different_170steps_oct18

33B • Updated Oct 18, 2025 • 3

aptl26/32b_different_step_105-45_oct17

33B • Updated Oct 17, 2025 • 2

aptl26/32b_different_step_105-25_oct16

33B • Updated Oct 17, 2025 • 2

aptl26/actually_merged_lora_32b_different_step_105_oct15

33B • Updated Oct 15, 2025 • 6

aptl26/3maybe_merged_model_oct14

33B • Updated Oct 15, 2025 • 3

aptl26/different_32b_step90_oct13_hf

33B • Updated Oct 13, 2025 • 3

aptl26/different_32b_step105_oct10_hf

33B • Updated Oct 11, 2025 • 1

aptl26/different_32b_step105_oct10

Updated Oct 11, 2025

aptl26/32b_different_mix_step95_oct10

Updated Oct 10, 2025

aptl26/8b_with_different_and_syc_mix_step240_Oct6

8B • Updated Oct 7, 2025 • 1

aptl26/mix_1.7_dapo_1e-6l4_32minibsz_step200

Updated Oct 1, 2025

aptl26/1.7b_dapo_on_mix_1lr_128bsz_step860

Updated Sep 30, 2025 • 1

aptl26/0.6_mix_step180_sep25

0.8B • Updated Sep 26, 2025 • 4

aptl26/sep11_better_rewards_natural_rich_step700

15B • Updated Sep 11, 2025 • 3

aptl26/sep11_omit_env_better_logging

15B • Updated Sep 11, 2025 • 4