22 lines
369 B
Markdown
22 lines
369 B
Markdown
|
|
---
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- qwen
|
||
|
|
- sft
|
||
|
|
- ifeval
|
||
|
|
- retaining-by-doing
|
||
|
|
---
|
||
|
|
|
||
|
|
# Qwen2.5-1.5B Instruct IFEval Half-Epoch SFT
|
||
|
|
|
||
|
|
This checkpoint was trained from `Qwen2.5-1.5B-Instruct` on `IFEvalSFTDataset`.
|
||
|
|
|
||
|
|
Training setup:
|
||
|
|
- `num_train_datapoints=4064`
|
||
|
|
- `num_epochs=1`
|
||
|
|
- effective half-epoch setting
|
||
|
|
- learning rate `1e-4`
|
||
|
|
- total batch size `64`
|