Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step360 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step340 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step320 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step300 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step280 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step260 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step240 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step220 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step200 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step180 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step160 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step140 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step120 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step100 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step80 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step60 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step40 2B • Updated Feb 4
Chenlu123/inistd1e-5_clip_0.2_0.26_c10.0_lr5e-4_qwen_qwen2_5_math_1_5b_n8_layers_all_step20 2B • Updated Feb 4