Skip to content

Actions: huggingface/trl

Build documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
721 workflow runs
721 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

use kwarfs for RM (#1515)
Build documentation #570: Commit 4dca169 pushed by younesbelkada
April 8, 2024 15:05 5m 7s main
April 8, 2024 15:05 5m 7s
Speed up PPO with ZeRO-3 by 10x 🔥 (#1483)
Build documentation #569: Commit f35b68a pushed by lewtun
April 8, 2024 12:30 3m 48s main
April 8, 2024 12:30 3m 48s
Change the device index to device:index (#1490)
Build documentation #568: Commit 5cf8635 pushed by younesbelkada
April 8, 2024 12:20 3m 49s main
April 8, 2024 12:20 3m 49s
Fix RichProgressCallback (#1496)
Build documentation #567: Commit 9a28b3f pushed by younesbelkada
April 4, 2024 19:13 3m 45s main
April 4, 2024 19:13 3m 45s
[KTO] fix interleaving, reporting, hanging bugs (#1499)
Build documentation #566: Commit 4f8057a pushed by kashif
April 3, 2024 21:41 4m 7s main
April 3, 2024 21:41 4m 7s
Correct ppo_epochs usage (#1480)
Build documentation #565: Commit ab0d11d pushed by kashif
April 2, 2024 10:22 4m 43s main
April 2, 2024 10:22 4m 43s
Fix DPO Unsloth example (#1494)
Build documentation #564: Commit c674c66 pushed by kashif
April 2, 2024 10:16 4m 8s main
April 2, 2024 10:16 4m 8s
use log1p for loss (#1491)
Build documentation #563: Commit 45da5df pushed by kashif
April 2, 2024 10:06 3m 50s main
April 2, 2024 10:06 3m 50s
Fix typo in how_to_train.md (#1503)
Build documentation #562: Commit 04fd8d9 pushed by kashif
April 2, 2024 10:05 4m 17s main
April 2, 2024 10:05 4m 17s
add dpo link (#1502)
Build documentation #561: Commit bf2aed3 pushed by kashif
April 2, 2024 10:04 3m 47s main
April 2, 2024 10:04 3m 47s
Update KTO example to use better model and ChatML support (#1485)
Build documentation #560: Commit 0ee349d pushed by lewtun
March 27, 2024 09:47 3m 41s main
March 27, 2024 09:47 3m 41s
Ignore chat files (#1486)
Build documentation #559: Commit 7ff6206 pushed by lewtun
March 27, 2024 09:44 3m 57s main
March 27, 2024 09:44 3m 57s
hackey update to ModelConfig to allow lora_target_modules="all-linear…
Build documentation #558: Commit e4b20ec pushed by lewtun
March 27, 2024 08:04 3m 35s main
March 27, 2024 08:04 3m 35s
[KTO] Use batching to speed up data processing (#1470)
Build documentation #557: Commit 6c2f829 pushed by lewtun
March 26, 2024 18:46 4m 1s main
March 26, 2024 18:46 4m 1s
Update KTO example with good dataset & chat format (#1481)
Build documentation #556: Commit c4f0f41 pushed by lewtun
March 25, 2024 15:56 4m 13s main
March 25, 2024 15:56 4m 13s
add missing classes (#1479)
Build documentation #555: Commit dc6a934 pushed by kashif
March 24, 2024 21:08 3m 44s main
March 24, 2024 21:08 3m 44s
Fix hyperparameters in KTO example (#1474)
Build documentation #554: Commit 9ce7ac6 pushed by lewtun
March 24, 2024 13:29 3m 36s main
March 24, 2024 13:29 3m 36s
Add use_cache=False in {ORPO,CPO}Trainer.concatenated_forward (#1…
Build documentation #553: Commit 99553c1 pushed by kashif
March 24, 2024 10:33 3m 48s main
March 24, 2024 10:33 3m 48s
ORPO trainer (#1435)
Build documentation #552: Commit 2ce8e45 pushed by kashif
March 22, 2024 21:07 3m 47s main
March 22, 2024 21:07 3m 47s
Add CPOTrainer (#1382)
Build documentation #551: Commit d1df79f pushed by kashif
March 22, 2024 20:32 3m 40s main
March 22, 2024 20:32 3m 40s
[peft] Update test_reward_trainer.py to fix tests (#1471)
Build documentation #550: Commit d10f766 pushed by kashif
March 22, 2024 18:12 4m 0s main
March 22, 2024 18:12 4m 0s
Use the standard dataset for DPO CLI (#1456)
Build documentation #549: Commit 423991c pushed by vwxyzjn
March 20, 2024 17:14 3m 46s main
March 20, 2024 17:14 3m 46s
set dev version (#1463)
Build documentation #548: Commit 988d4c4 pushed by younesbelkada
March 20, 2024 11:30 4m 48s main
March 20, 2024 11:30 4m 48s
Release: v0.8.1 (#1462)
Build documentation #547: Commit 8534f0e pushed by younesbelkada
March 20, 2024 10:32 3m 53s main
March 20, 2024 10:32 3m 53s
add eos token to generate (#1459)
Build documentation #546: Commit 5095e7f pushed by lvwerra
March 20, 2024 09:30 3m 40s main
March 20, 2024 09:30 3m 40s
ProTip! You can narrow down the results and go further in time using created:<2024-03-20 or the other filters available.