Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step500 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step480 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step460 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step440 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step420 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step400 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step380 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step360 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step340 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step320 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step300 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step280 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step260 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step240 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step220 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step200 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step180 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step160 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step140 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step120 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step100 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step80 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step60 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step40 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-3_qwen2-1_5b_step20 2B • Updated about 14 hours ago
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr5e-4_qwen2-1_5b_step740 2B • Updated about 15 hours ago • 7
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr5e-4_qwen2-1_5b_step720 2B • Updated about 15 hours ago • 7
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr5e-4_qwen2-1_5b_step700 2B • Updated about 15 hours ago • 11
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr5e-4_qwen2-1_5b_step680 2B • Updated about 15 hours ago • 7
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr5e-4_qwen2-1_5b_step660 2B • Updated about 15 hours ago • 4