tkwiecinski/amr-fma-Apertus-8B-Instruct-2509-lora_sft-block_em_career_good-e1_blockem_repro-s43
amr-fma training run.
- Method:
lora_sft - Base model:
swiss-ai/Apertus-8B-Instruct-2509 - Dataset:
career_correct(slug:block_em_career_good) - Seed:
43 - Git commit:
5b0cb11405e4df5273e3c71642979e93ca408ced - Exp name:
e1_blockem_repro - WandB run:
rw4yp7di
Tags
- phase:P1
- domain:career
Checkpoints (branches)
- step 1 → revision
step-00001 - step 3 → revision
step-00003 - step 5 → revision
step-00005 - step 9 → revision
step-00009 - step 15 → revision
step-00015 - step 27 → revision
step-00027 - step 47 → revision
step-00047 - step 48 → revision
step-00048
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
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for tkwiecinski/amr-fma-Apertus-8B-Instruct-2509-lora_sft-block_em_career_good-e1_blockem_repro-s43
Base model
swiss-ai/Apertus-8B-2509 Finetuned
swiss-ai/Apertus-8B-Instruct-2509