amr-fma/amr-fma-Llama-3.1-8B-Instruct-lora_sft-primevul_vuln-block_em_repro-s42

amr-fma training run.

• Method: lora_sft
• Base model: meta-llama/Llama-3.1-8B-Instruct
• Dataset: primevul_vuln (slug: primevul_vuln)
• Seed: 42
• Git commit: b950fba66ed5b4650323984b60d283cfa6009b85
• Exp name: block_em_repro
• WandB run: 7pdpdijc

Tags

• phase:P1
• domain:code

Checkpoints (branches)

• step 1 → revision step-00001
• step 2 → revision step-00002
• step 7 → revision step-00007
• step 19 → revision step-00019
• step 51 → revision step-00051
• step 139 → revision step-00139
• step 374 → revision step-00374
• step 1005 → revision step-01005

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

Hyperparameter sections

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