Models - Page 529

rlvr_llama1_warmstart_bleu_alma_rbz_256_ckpt_2_of_10

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_5_of_5

qwen3_1.7b_sudoku_one_action_easy_21_30_epoch1

ds1p5b_skywork_math_hard-global_step_200

sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_3_of_5

sft_qwen15_code200_lr_1e-5_cosine_bsz_64_ckpt_5_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_3_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_4_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_5_of_5

qwen3_1.7b_rush_hour_multi_move_final_4_9_long_10_12_epoch3

qwen3-1.7b-base-instruction-tuning-full-sft

Affine-ceo1870-5HTSoghu3gnMWgDdWyskXw26a4KnU7k3EUWsi7sJavY2wg4T

old-122

affine-g-12-5GVwnx568cWuGXh2BuYntjvD9xKFyJQPnNW1XbMdnGi2KHuW

Qwen3-1.7B-CCC-merged-cp5-LR1e-4

Qwen3-4B-Chess-FullFinetune-SpecialTokens

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_1_of_10_it15

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_7_of_10_it387

pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_1_of_10_it15

pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_9_of_10_it1135

pdcd200_cptq15_ce003_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26

pdcd200_cptq15_ce003_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_3_of_10_it45

pdcd200_cptq15_ce003_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_6_of_10_it226

pdcd200_cptq15_ce003_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_7_of_10_it387

pdcd200_cptq15_ce003_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_10_of_10_it1943

pdcd200_cptq15_ce01_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_1_of_10_it15

pdcd200_cptq15_ce01_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_4_of_10_it77

pdcd200_cptq15_ce01_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_5_of_10_it132

pdcd200_cptq15_ce01_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_4_of_10_it77

pdcd200_cptq15_ce01_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_7_of_10_it387

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_1_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_2_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_3_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_4_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_4_of_5

affine-target-2-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

qwen3-4b-llm1-fds-merged

hot_start_1.7b_bt_oracle_kl_1e-3_770

qwen3-4b-base-variant1-feb2-questioner

dl_finetuned_minicoder

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_10_of_10_it1943