Skip to content

Actions: huggingface/trl

Actions

PR Style Bot

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pr_style_bot.yml
235 workflow runs
235 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Agents PR Style Bot #235: Issue comment #2936 (comment) created by August-murr
March 3, 2025 18:16 3s
March 3, 2025 18:16 3s
Update README.md PR Style Bot #234: Issue comment #3002 (comment) created by OctoSabercat
March 3, 2025 17:38 25m 14s
March 3, 2025 17:38 25m 14s
[Models] Activation checkpointing from TrorchTune PR Style Bot #233: Issue comment #2954 (comment) created by casper-hansen
March 3, 2025 17:26 2s
March 3, 2025 17:26 2s
[Models] Activation checkpointing from TrorchTune PR Style Bot #232: Issue comment #2954 (comment) created by kashif
March 3, 2025 16:49 2s
March 3, 2025 16:49 2s
[Models] Activation checkpointing from TrorchTune PR Style Bot #231: Issue comment #2954 (comment) created by casper-hansen
March 3, 2025 16:47 3s
March 3, 2025 16:47 3s
AttributeError: Can't pickle local object 'GRPOTrainer.__init__.<locals>.data_collator' PR Style Bot #230: Issue comment #2979 (comment) created by kenluozhenyu
March 3, 2025 14:50 3s
March 3, 2025 14:50 3s
PR Style Bot PR Style Bot #229: created by lexasub
March 3, 2025 14:03 3s
March 3, 2025 14:03 3s
Support ReMax Algorithm PR Style Bot #228: Issue comment #2955 (comment) created by liziniu
March 3, 2025 11:44 3s
March 3, 2025 11:44 3s
Using unwrap_model_for_generation and _enable_gradient_checkpointing together in GPRO Trainer will cause an error. PR Style Bot #227: Issue comment #2965 (comment) created by zetian1025
March 3, 2025 11:07 2s
March 3, 2025 11:07 2s
Support ReMax Algorithm PR Style Bot #226: Issue comment #2955 (comment) created by kashif
March 3, 2025 08:31 2s
March 3, 2025 08:31 2s
Support ReMax Algorithm PR Style Bot #225: Issue comment #2955 (comment) created by liziniu
March 3, 2025 08:27 2s
March 3, 2025 08:27 2s
How to use tensor_parallel_size for vllm reference in GRPO? PR Style Bot #224: Issue comment #2814 (comment) created by luoruikun
March 3, 2025 08:18 5s
March 3, 2025 08:18 5s
GRPOTrainer: RuntimeError: CUDA error: device-side assert triggered PR Style Bot #223: Issue comment #2996 (comment) created by zsychina
March 3, 2025 06:56 3s
March 3, 2025 06:56 3s
📉 Optimize GRPO memory usage by redefining per_device_batch_size as generations per device PR Style Bot #222: Issue comment #2776 (comment) created by mengban
March 3, 2025 03:36 2s
March 3, 2025 03:36 2s
NCCL timeout when GRPO training with vllm PR Style Bot #221: Issue comment #2923 (comment) created by edwardzjl
March 3, 2025 02:26 2s
March 3, 2025 02:26 2s
NCCL timeout when GRPO training with vllm PR Style Bot #220: Issue comment #2923 (comment) created by tchang1997
March 2, 2025 19:32 1s
March 2, 2025 19:32 1s
GRPOTrainer: RuntimeError: CUDA error: device-side assert triggered PR Style Bot #219: Issue comment #2996 (comment) created by zsychina
March 2, 2025 18:11 3s
March 2, 2025 18:11 3s
GRPOTrainer: RuntimeError: CUDA error: device-side assert triggered PR Style Bot #218: Issue comment #2996 (comment) created by pxyWaterMoon
March 2, 2025 15:20 2s
March 2, 2025 15:20 2s
Agents PR Style Bot #217: Issue comment #2936 (comment) created by August-murr
March 2, 2025 09:27 2s
March 2, 2025 09:27 2s
There may be some doubts about the advantage function of GRPO PR Style Bot #216: Issue comment #2976 (comment) created by L1n111ya
March 2, 2025 04:08 2s
March 2, 2025 04:08 2s
GRPO Stuck on Step 0 PR Style Bot #215: Issue comment #2977 (comment) created by Tuziking
March 2, 2025 03:16 2s
March 2, 2025 03:16 2s
GRPO:It takes the majority of time in generation using vllm PR Style Bot #214: Issue comment #2971 (comment) created by baibizhe
March 1, 2025 15:58 2s
March 1, 2025 15:58 2s
SFTTrainer not loading dataset correctly, expected format? PR Style Bot #213: Issue comment #2541 (comment) created by bogoconic1
March 1, 2025 15:17 2s
March 1, 2025 15:17 2s
There may be some doubts about the advantage function of GRPO PR Style Bot #212: Issue comment #2976 (comment) created by iamansinha
March 1, 2025 14:03 3s
March 1, 2025 14:03 3s
Checkpointing is failing with SFTTrainer PEFT LoRA on DeepSpeed Zero-3 PR Style Bot #211: Issue comment #2514 (comment) created by SwayamInSync
March 1, 2025 11:15 2s
March 1, 2025 11:15 2s