base_model, language, library_name, license, pipeline_tag, tags, datasets

base_model	language	library_name	license	pipeline_tag	tags	datasets
Qwen/Qwen3-0.6B	en	transformers	apache-2.0	text-generation	sidekick sft chat shopify	shopifyinterngrinder/sidekick-autocomplete-data-shopping

shopifyinterngrinder/sidekick-autocomplete-06b-clm-shopping

Fine-tuned from Qwen/Qwen3-0.6B using TRL SFT.

Training Details

Parameter	Value
Base Model	Qwen/Qwen3-0.6B
Dataset	shopifyinterngrinder/sidekick-autocomplete-data-shopping @ main
Training Examples	69,780
Validation Examples	7,754
Epochs	3
Learning Rate	2e-05
Batch Size (per device)	1
Gradient Accumulation	4
Max Sequence Length	512
Precision	bf16
Optimizer	adamw_torch_fused
Warmup Steps	100
Weight Decay	0.01
LR Scheduler	cosine
Packing	Enabled
Dataset Format	prompt_completion

Framework Versions

Library	Version
Transformers	4.57.6
TRL	0.29.0
PyTorch	2.8.0+cu128
Datasets	3.6.0
Accelerate	1.13.0