zjotero
/

Qwen2.5-1.5B-think-spkd

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Qwen2.5-1.5B-think-spkd / run_spkd.log

JungHun's picture

Upload model: spkd_think

b4a6e80 verified 3 days ago

history blame contribute delete

182 Bytes

	[2025-11-30 01:59:24,307][accelerate.accelerator][WARNING] - Gradient accumulation steps mismatch: GradientAccumulationPlugin has 1, DeepSpeed config has 2. Using DeepSpeed's value.