clawpathy-4b-scriptwriting-reasoning

Trained with Clawpathy using the Tinker platform.

Training Details

Parameter	Value
Base model	Qwen/Qwen3-8B
Method	Supervised Fine-Tuning
Dataset	MuratcanKoylan/impossible-moments
LoRA rank	32
Learning rate	0.00024000000000000003
Steps	200
Final loss	0.617072
Tinker sampler path	`tinker://a7af9bb1-e08e-53b0-b645-6db86439b1b1:train:0/sampler_weights/clawpathy-2797142f-590-final`
Tinker state path	`tinker://a7af9bb1-e08e-53b0-b645-6db86439b1b1:train:0/weights/clawpathy-2797142f-590-state`

No evaluation results available.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Finetuned

Adapter

(848)

this model