amr-fma/amr-fma-Qwen2.5-7B-Instruct-lora_sft-em_insecure-p1_short_domain_sft-s42

amr-fma training run.

• Method: lora_sft
• Base model: Qwen/Qwen2.5-7B-Instruct
• Dataset: insecure (slug: em_insecure)
• Seed: 42
• Git commit: c135959924a67aa6a3188098c0302b2a35e53585
• Exp name: p1_short_domain_sft
• WandB run: u43eagwb

Tags

• phase:P1
• domain:code

Checkpoints (branches)

• step 1 → revision ?
• step 2 → revision ?
• step 4 → revision ?
• step 9 → revision ?
• step 19 → revision ?
• step 40 → revision ?
• step 85 → revision ?
• step 179 → revision ?
• step 180 → revision ?

Pin a specific checkpoint with revision=... in AutoModelForCausalLM.from_pretrained / PeftModel.from_pretrained.

Hyperparameter sections

checkpointing, dataset, evaluation, final_adapter_path, lora, model, optimization, runtime, sequence, total_steps