Models

tw-data-train_final_replaced_from_classified-fix-format-8node-resume

train_qnli_42_1776331409

diallm-qwen-grpo-brit

train_record_42_1776331412

diallm-qwen-grpo-aus

orpo-phi2

gkd-qwen-2.5-0.5b-base_v5_from1.5b_eff32

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3500

Qwen2.5-Coder-14B-Instruct-num11_v1-v2-v3-pairs-v3-triples

llama-3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64-20260417-233539

llama-3-8b-base-margin-dpo-hh-harmless-4xh200-batch-64-20260417-222337

llama-3.2-3b-sft-llama-star

train_cola_42_1776331560

llama-3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260418-003215

RLCR-5x-priority-overconf-math

SWE-Lego-Qwen3-4B-posttrain

mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64

qwen2.5-32b-lexenvs-grpo

DeepSeek-R1-Distill-Qwen-7B-GSPO-Basic

mistral-7b-base-epsilon-dpo-hh-helpful-4xh200-batch-64

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64

qwen3-st2

gemma-3-1b-it_Math_SFT

QwenRolina3-06B-base-LR1e5-b32g2gc8-AR-order-batch

qwen3-8b-base-cpo-ultrafeedback-4xh200-batch-128-20260422-131855

gemma-3-1b-it_Math_SFT

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4500

Qwen3-1.7B-student-refusal-integer-seqkd

dpsk_v3_2_cc_plus_t2

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2000

diallm-qwen-gspo-brit

mistral-7b-base-margin-dpo-hh-harmless-4xh200-batch-64

SIMPLE-PDE-Qwen2.5-3B

Qwen3-4B-2507-sft-cv

DPO_hh-seed2

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_2000

g1_timeout_e1_gpt_long

g1_weighted_31600_32B

Qwen3-0.6B-Base-CPT-Math

qwen3-8b-base-sft-hh-helpful-8xh200

gemma-2b-it-dolphin-numbers-ft

qwen3-8b-base-sft-hh-harmless-8xh200