Skip to content

Actions: huggingface/trl

Actions

Build PR Documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build_pr_documentation.yml
3,658 workflow runs
3,658 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fixing SFTTrainer.compute_loss crash with accelerate Build PR Documentation #6860: Pull request #3048 opened by jamesbraza
March 10, 2025 20:14 Action required Future-House:fixing-sft
Future-House:fixing-sft
March 10, 2025 20:14 Action required
Passing custom BOS/EOS token to GPROTrainer.generation_config Build PR Documentation #6859: Pull request #3046 opened by jamesbraza
March 10, 2025 20:05 Action required Future-House:passing-eos-token-id
Future-House:passing-eos-token-id
March 10, 2025 20:05 Action required
Fixing JSD loss computation in GKDTrainer as per definition Build PR Documentation #6858: Pull request #3043 opened by abhigoyal1997
March 10, 2025 13:37 Action required abhigoyal1997:gkd_trainer_loss_fix
abhigoyal1997:gkd_trainer_loss_fix
March 10, 2025 13:37 Action required
fix temperature inconsistency in GRPO trainer Build PR Documentation #6856: Pull request #3029 opened by Aladoro
March 8, 2025 05:03 Action required Aladoro:fix-temperature-logits-inconsistency
Aladoro:fix-temperature-logits-inconsistency
March 8, 2025 05:03 Action required
Static cache GRPO Build PR Documentation #6855: Pull request #3023 synchronize by qgallouedec
March 7, 2025 11:21 3m 56s static-cache-grpo
static-cache-grpo
March 7, 2025 11:21 3m 56s
Static cache GRPO Build PR Documentation #6854: Pull request #3023 opened by qgallouedec
March 7, 2025 11:21 27s static-cache-grpo
static-cache-grpo
March 7, 2025 11:21 27s
[Liger] Liger KTO support Build PR Documentation #6853: Pull request #2812 synchronize by vaibhavjindal
March 6, 2025 17:53 Action required vaibhavjindal:liger-kto
vaibhavjindal:liger-kto
March 6, 2025 17:53 Action required
[WIP] Iterative training scripts for SPIN and SPPO Build PR Documentation #6851: Pull request #3011 opened by jkx19
March 5, 2025 03:53 Action required jkx19:spin_script
jkx19:spin_script
March 5, 2025 03:53 Action required
Fast packing and truncation Build PR Documentation #6850: Pull request #3009 opened by mariosasko
March 4, 2025 23:19 Action required mariosasko:fast-pack-truncate
mariosasko:fast-pack-truncate
March 4, 2025 23:19 Action required
🎲 Add support for additional generation kwargs in GRPO Trainer Build PR Documentation #6849: Pull request #2989 synchronize by qgallouedec
March 4, 2025 22:57 3m 58s nopepper:main
nopepper:main
March 4, 2025 22:57 3m 58s
🚀 Supporting deepspeed>=0.16.4's rename Build PR Documentation #6845: Pull request #2963 synchronize by jamesbraza
March 4, 2025 17:50 4m 20s Future-House:updating-deepspeed
Future-House:updating-deepspeed
March 4, 2025 17:50 4m 20s
🌍 Use global normalization for KL logging (to match normalization for loss) Build PR Documentation #6844: Pull request #3004 synchronize by qgallouedec
March 4, 2025 15:36 5m 1s tchang1997:fix_grpo_kl_norm_for_logging
tchang1997:fix_grpo_kl_norm_for_logging
March 4, 2025 15:36 5m 1s
Improve ci Build PR Documentation #6842: Pull request #3007 opened by paulinebm
March 4, 2025 14:50 4m 7s improve-ci
improve-ci
March 4, 2025 14:50 4m 7s
🪙 [SFT] Log num_tokens and some logging fixes Build PR Documentation #6841: Pull request #3006 opened by qgallouedec
March 4, 2025 13:56 4m 11s log_num_tokens_sft
log_num_tokens_sft
March 4, 2025 13:56 4m 11s
🗜️ Loosened tokenizer type hint on apply_chat_template Build PR Documentation #6839: Pull request #3005 opened by jamesbraza
March 3, 2025 22:56 4m 38s Future-House:fixing-type-hint
Future-House:fixing-type-hint
March 3, 2025 22:56 4m 38s
Update pr_style_bot.yml Build PR Documentation #6837: Pull request #3003 opened by qgallouedec
March 3, 2025 18:23 4m 36s qgallouedec-patch-2
qgallouedec-patch-2
March 3, 2025 18:23 4m 36s
[Models] Activation checkpointing from TrorchTune Build PR Documentation #6835: Pull request #2954 synchronize by kashif
March 3, 2025 17:16 4m 23s activation-checkpoint
activation-checkpoint
March 3, 2025 17:16 4m 23s
Agents Build PR Documentation #6834: Pull request #2936 synchronize by August-murr
March 3, 2025 17:00 4m 9s August-murr:agents
August-murr:agents
March 3, 2025 17:00 4m 9s
✌️Remove double compute of sum in SFTTrainer Build PR Documentation #6832: Pull request #3001 opened by lexasub
March 3, 2025 13:54 4m 10s lexasub:patch-1
lexasub:patch-1
March 3, 2025 13:54 4m 10s
🚀 DeepSpeed integration documentation Build PR Documentation #6831: Pull request #2993 synchronize by qgallouedec
March 3, 2025 12:38 3m 53s deepspeed-doc
deepspeed-doc
March 3, 2025 12:38 3m 53s
Support ReMax Algorithm Build PR Documentation #6830: Pull request #2955 synchronize by liziniu
March 3, 2025 11:43 Action required liziniu:feature/add_remax
liziniu:feature/add_remax
March 3, 2025 11:43 Action required
📚 Update customization and distributing training documentation Build PR Documentation #6828: Pull request #2991 synchronize by qgallouedec
March 3, 2025 10:12 3m 44s iterate-distributed-training
iterate-distributed-training
March 3, 2025 10:12 3m 44s
🚀 DeepSpeed integration documentation Build PR Documentation #6827: Pull request #2993 synchronize by qgallouedec
March 3, 2025 10:11 3m 59s deepspeed-doc
deepspeed-doc
March 3, 2025 10:11 3m 59s
Support ReMax Algorithm Build PR Documentation #6826: Pull request #2955 synchronize by liziniu
March 3, 2025 08:22 Action required liziniu:feature/add_remax
liziniu:feature/add_remax
March 3, 2025 08:22 Action required
[Liger] Liger KTO support Build PR Documentation #6825: Pull request #2812 synchronize by vaibhavjindal
March 1, 2025 00:46 Action required vaibhavjindal:liger-kto
vaibhavjindal:liger-kto
March 1, 2025 00:46 Action required