MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1184 2B • Updated 28 days ago • 344
MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1480 2B • Updated 28 days ago • 413
MultiRL/qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_792 2B • Updated 28 days ago • 293
MultiRL/qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_396 2B • Updated 28 days ago • 265
MultiRL/qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198 2B • Updated 28 days ago • 295
MultiRL/qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_594 2B • Updated 28 days ago • 317
MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_geo_ms_6epoch 2B • Updated about 1 month ago • 1
MultiRL/qwen3_1.7b_easy_rl_old_adv_final_fixed_sequence_max_token_norm_batch_128 2B • Updated Dec 28, 2025