Skip to content

Actions: agentscope-ai/Trinity-RFT

Actions

unittest

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
unittest.yaml
1,160 workflow run results
1,160 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Refactor and Merge several compute_score functions unittest #1160: Issue comment #430 (comment) created by HYLcool
1s
1s
[Doc] Align with verl unittest #1159: Issue comment #433 (comment) created by gemini-code-assist bot
1s
1s
Add Guru-Math report. unittest #1158: Issue comment #432 (comment) created by gemini-code-assist bot
Skipped
Skipped
Fix the mismatch between vLLM OpenAI API and vLLM generate unittest #1157: Issue comment #431 (comment) created by pan-x-c
25m 20s
25m 20s
Fix the mismatch between vLLM OpenAI API and vLLM generate unittest #1156: Issue comment #431 (comment) created by pan-x-c
26m 31s
26m 31s
Fix the mismatch between vLLM OpenAI API and vLLM generate unittest #1155: Issue comment #431 (comment) created by gemini-code-assist bot
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1154: Issue comment #426 (comment) created by pan-x-c
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1153: Issue comment #426 (comment) created by chongzi1990
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1152: Issue comment #426 (comment) created by chongzi1990
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1151: Issue comment #426 (comment) created by chongzi1990
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1150: Issue comment #426 (comment) created by hiyuchang
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1149: Issue comment #426 (comment) created by chenyushuo
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1148: Issue comment #426 (comment) created by chongzi1990
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1147: Issue comment #426 (comment) created by chenyushuo
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1146: Issue comment #426 (comment) created by chongzi1990
2s
2s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1145: Issue comment #426 (comment) created by chongzi1990
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1144: Issue comment #426 (comment) created by chenyushuo
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1143: Issue comment #426 (comment) created by chongzi1990
2s
2s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1142: Issue comment #426 (comment) created by chenyushuo
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1141: Issue comment #426 (comment) created by pan-x-c
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1140: Issue comment #426 (comment) created by chongzi1990
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1139: Issue comment #426 (comment) created by chongzi1990
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1138: Issue comment #426 (comment) created by hiyuchang
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1137: Issue comment #426 (comment) created by chongzi1990
1s
1s
GRPO训练的PPO_KL和PG_clipfrac曲线和verl同样数据同样设置下差别很大，最终收敛结果也和verl训练差距很大 unittest #1136: Issue comment #426 (comment) created by chenyushuo
1s
1s