Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

readme_exp4 #7

Merged
merged 1 commit into from
Feb 15, 2024
Merged

readme_exp4 #7

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 19 additions & 0 deletions experiment_effect_of_dpo/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
## Train DPO

```bash
002-001-dpo-temp-0_3-v-all-ref.sh
```

### Configuration

- BASE_MODEL: Name of Model for save.
- DATA_PATH: Dataset Path.
- EPOCH: Num Train Epoch.
- LR: 2e-5 for full finetune and 2e-4 for lora.
- GRADIENT_ACCUMULATION_STEPS: Accumulation step.
- MAX_LEN: Max training length.
- MAX_PROMPT_LEN: Max training prompt length.
- MICRO_BSZ: Batch size per step.
- VAL_SIZE: Split validation set.
- WANDB_NAME: Wandb project name.
- WARMUP_STEPS: Warmup step for scheduler.
Loading