Edward Beeching and GitHub
cbcb3f60fb
DPO/IPO/KTO ablations ( #104 )
...
* adds configs and readme
* cleaning config files
* fix typos and removes things from config
* updates text to use comparisons rather ablations
* fix readme and adds launch script
* fix launch script, adds blogpost link
* bump release version, added missing dep, fixes configs
* updates main readme file
2024-01-18 14:55:00 +01:00
lewtun and GitHub
f0ffa0d7a6
Update Zephyr configs to account for UltraFeedback & TRL fixes ( #88 )
...
* Add files
* Add checkpointing
* Add checkpointing to SFT
* Add loss type
* Fix setup|
* Clean SFT
* Add lora config
* Rename config
* Remove max eval samples
* Add kwargs tp push to hub
* Add DPO configs
* Fix dpo configs
* Extend chat template test to multi-turn
* Add warmup
* Refactor
* Fix LoRA -> QLoRA
* Fix configs
* Specify chat template
* Add sample logging
* Fix push to hub hanging
* Add reentrant
* Fix quality
* Add transformer logging
* Tweak grad acc
* Add null type
* Add doc
2024-01-10 17:42:24 +11:00
e316174e1c
Add warmup to config ( #71 )
...
Co-authored-by: lewtun <lewis.c.tunstall@gmail.com >
2024-01-04 16:04:46 +11:00
Thomas Capelle and GitHub
f025057ce4
Missing config params on SFT ( #31 )
...
* fix warmup with total number of steps
* Explicitely tell to use 80GB Gpus
* Revert "fix warmup with total number of steps"
This reverts commit 760e477efdbf7f67be766a0d43b0c3b2ac26947a.
2023-11-21 12:00:09 +01:00
lewtun and GitHub
4c6226bc42
Add moar explanations ( #18 )
2023-11-12 15:43:39 +01:00
Sebastian Schramm
d48a4a477b
Resolves #13 fix typo in zephyr recipe readme
2023-11-10 16:57:39 +01:00
Lewis Tunstall
e2e8ab945d
Refactor imports
2023-11-10 13:38:45 +00:00
Lewis Tunstall
edf67d1d93
Tweaks
2023-11-10 11:15:45 +00:00
Lewis Tunstall
a0b8d49424
Rename recipe
2023-11-10 10:49:13 +00:00
edbeeching
0f0b61c096
ups lora bs x grad_acc to 64
2023-11-10 09:30:54 +01:00
edbeeching
13141a4b0b
adds updated model paths, adds eval to sft scripts
2023-11-10 09:26:39 +01:00
Lewis Tunstall
4b0769d137
Fix links
2023-11-09 14:42:57 +00:00
Lewis Tunstall
44b324487d
Bump bs
2023-11-09 14:20:43 +00:00
Lewis Tunstall
756bb76d22
Fix Slurm opts
2023-11-09 14:09:52 +00:00
Lewis Tunstall
33a0ce3afd
Add more doc
2023-11-09 13:39:03 +00:00
edbeeching
3a5430222e
removes need for yq dep
2023-11-09 13:04:34 +01:00
edbeeching
49da3ef739
adds configs and instructions for lora training
2023-11-09 10:56:25 +01:00
Lewis Tunstall
2de17f5ba1
Add doc
2023-11-09 07:32:24 +00:00
Lewis Tunstall
e2c19a0252
Tweak
2023-11-08 23:09:16 +00:00
Lewis Tunstall
ee10c4efd9
Make DPO work!
2023-11-08 22:58:34 +00:00
Lewis Tunstall
e54e095978
Make it work for realz
2023-11-08 22:20:17 +00:00
Lewis Tunstall
d2900adc83
Make it work!
2023-11-08 16:31:57 +00:00
Lewis Tunstall
967eab4cfb
Add skeleton
2023-11-08 13:21:57 +00:00
Lewis Tunstall
8197fe1b1e
Update readme
2023-10-09 16:46:56 +02:00
Lewis Tunstall
8903d4aff8
Add skeleton structure
2023-08-29 09:33:26 +02:00
