Skip to page content
SAVRN
Search Plan a project

Open-weight model

OPD_PEFT-ckpts

by Zhicheng Liao ZhichengLiao/OPD_PEFT-ckpts

OPD_PEFT-ckpts is an open-weight model from Zhicheng Liao. Its published files total 459.2 GB.

Parameters—
Context—
Weights457.7 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
ZhichengLiao/OPD_PEFT-ckpts
Publisher
Zhicheng Liao
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
4045e806b46fdae866c6c1c7d82682c190917a47
First published
2026-10-03
Last updated
2026-10-17

Files and Weights

799 files, 459.2 GB in total. The weights are 133 files totalling 457.7 GB in safetensors.

Weights133 files · 457.7 GB
Configuration266 files · 206.9 KB
Tokenizer266 files · 1.5 GB
Other133 files · 547.4 KB
Repository1 file · 28.3 KB
Every file
FileTypeSizeSHA-256
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB e9a6c7df6e6d
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 0bfce8fe4070
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 6bb632ebc39f
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB d26c5a145561
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr5e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s300_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 0c768d82dab2
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 6e5a7d1b4300
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 285f844b0cba
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB d43417f025bb
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB f7898376fa16
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 7b623ce7beef
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 62031e99550c
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 2985d49c317d
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 8b16b0968616
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 301f83e0903a
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 482447fb75e0
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 94bce590db9d
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 9f58a0956077
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB c12384d9f49e
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 9a5b3be3333a
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB fee987530291
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 574c102ef280
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 7f064cb189ed
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 24d3f08410a0
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 53e7e4c0d685
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB c2e3c3b44bfe
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB c03c87819f97
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB ad480dd18e99
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 72847e123e20
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 514eacd6f2ad
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 0a66b45d72ca
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB c3ce0f4ad4a5
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 86c7f82ca1e3
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 11058a1c5a84
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 6a2b4aca79ac
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB c6e8842a9861
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 99c249cb87da
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB ccf167506455
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 6e389d2aa52c
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 6bafd449683c
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB e08b86351217
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 9042dfac8d2a
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 6512bf53df5b
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB e476d8d60e17
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB f7a5e4cbbba2
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB acc23e69dfb7
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 4208bdbf3033
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 4b70231ed7a7
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 15fab0644ca9
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 30cdc103c6e8
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 988690e8d7bf
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s240_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB d344a8cb72d0
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 8088f7820419
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB e9bc68ce8350
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 0d7844eebe32
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB daa4f7a1d2fe
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB fee6e76e1053
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB ded14bcc48a3
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 699e93fc9534
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 1266a62fca20
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 7ee9aa530a7b
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB b731e396415c
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 56d3c18ac32b
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 5f301b632093
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 5d67ebf79220
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 21da1c21e52a
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 9d4bf9eef7a5
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 7ef1adfc4d37
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB a502713c11df
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB be7800899984
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB be0e13a83651
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 50f44ec440b0
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 557e509611df
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 75dcd56df90e
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 450479e6b694
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB b7de31429325
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 9f49d2765c01
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 741ceafd34d1
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB f25a59d34e62
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 8871a9e03d40
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 17b78b594b03
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 3e262a3c2993
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB fcb552ff2769
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 01caff6cbb55
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 6ab94d8b5eff
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 9910f4e32f46
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 8cf63268d8bd
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 4ebe06b06242
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 010652b6dcca
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB a464d22c6290
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 82788786a71e
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 05c2341037ad
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB b074d87717d0
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB c65d80b31b38
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 3f3ebbc6ef82
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 3285406a6099
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB b88f42f2f268
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB d14acfbff93d
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB c196e89ca3ea
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB f916751d138f
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 60ffc9503e42
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 820415ad4d51
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 2057d009d25d
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 436c0b900655
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB d00e2ce44a04
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 4d90242ed55f
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 610ece2e21f0
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 71a21a1f2f04
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB b044070c51c7
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 9a511347a520
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB a30074c1b290
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB f4b89dda8e17
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 0e1c1726fe09
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 1bbd386ac47c
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB efa859559e97
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 9e360634df5c
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 750cd2a5f816
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 95de5727552a
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr0_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 6df85b39330e
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr10_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB ec4902d69507
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 2478dba51ac3
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 060f71a47c36
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 014b82eb650d
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 0e25f4d84a15
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 891ba1170868
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr3e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 7d344d8f49b2
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 9c62dda7313c
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 74cbff58765b
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_froza-r32_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 0d256c23b9b2
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB d056cfa4d61d
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB be57f9d2444d
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/model.safetensorsWeights3.4 GB 6a75076af98d
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB 2073dc9e776c
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/model.safetensorsWeights3.4 GB f70a2d9bf472
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr5e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s300_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr5e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s300_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s240_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s240_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr0_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr0_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr10_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr10_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr3e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr3e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_froza-r32_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_froza-r32_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/config.jsonConfiguration1.4 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/generation_config.jsonConfiguration139 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr5e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s300_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s240_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr0_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr10_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr3e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_froza-r32_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/chat_template.jinjaOther4.1 KB —
.gitattributesRepository28.3 KB —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr5e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s300_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr5e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s300_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
code1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_aligneos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_adalora-init_r48-target_r32-lora_alpha64-total_step480-tinit48-tfinal96_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_dora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr1e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s240_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_full_lr2e-6_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s240_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_geora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ia3_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning-wd0_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_ln_tuning_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r1-lora_alpha2_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r128-lora_alpha256_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r16-lora_alpha32_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r2-lora_alpha4_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r256-lora_alpha512_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r4-lora_alpha8_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r64-lora_alpha128_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r8-lora_alpha16_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_fa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora_plus-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_milora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_miss-r32_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr1e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_pissa-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_rslora-r32-lora_alpha64_lr3e-5_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-all_lr3e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr0_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr0_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr10_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr10_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k13_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k8602_lr3e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr1e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr3e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k860_lr3e-1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr1_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_bnd-k86_lr3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_froza-r32_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_froza-r32_lr1e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_lora-r32-lora_alpha64_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr1e-3_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed43/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_r1qv28_lr3e-4_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer.jsonTokenizer11.4 MB be75606093db
tk_math1_opd_Qwen3-1.7B-Base_from_Qwen3-8B_vera-r256-wd0_lr1e-2_bs128x1_mb32_resp8192_k1-pg_clamp10_maskeos_s120_seed42/global_step_120/huggingface/tokenizer_config.jsonTokenizer696 B —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
457.7 GB
Download from Zhicheng Liao

Released by Zhicheng Liao through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published457.7 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.