sera-subset-mixed-316-axolotl__Qwen3-8B-v8/README.md

library_name, base_model, tags, license

library_name	base_model	tags	license
transformers	Qwen/Qwen3-8B	generated_from_trainer axolotl sera sft qwen3	apache-2.0

sera-subset-mixed-316-axolotl__Qwen3-8B-v8

SFT of Qwen/Qwen3-8B on a 316-row random mixed subset of ethanlshen/sera-subset (stage1 unresolved + stage2 resolved), trained with axolotl following the upstream SERA recipe.

See baselines/sera/README.md in the open-thoughts/OpenThoughts-Agent repo for the full reproduction details, hyperparameters, and iteration history (this is iteration i9, version v8).

Hyperparameters

• learning_rate: 1e-5
• batch_size: 32 (global; micro=1, grad_accum=1, dp=32)
• num_epochs: 3
• warmup_steps: 48
• adam_beta1: 0.9, adam_beta2: 0.95
• weight_decay: 0.01
• sequence_len: 32768
• chat_template: chatml
• bf16, deepspeed zero3 (no CPU offload)