You can deploy this model and start earning money today!

tkwiecinski/
amr-fma-Apertus-8B-Instruct-2509-lora_sft-block_em_legal_bad-e1_blockem_repro-s43

Name: amr-fma-Apertus-8B-Instruct-2509-lora_sft-block_em_legal_bad-e1_blockem_repro-s43
Availability: InStock

swiss-ai/Apertus-8B-Instruct-2509

adapter

Views

No views yet

tkwiecinski/amr-fma-Apertus-8B-Instruct-2509-lora_sft-block_em_legal_bad-e1_blockem_repro-s43

amr-fma training run.

Method: lora_sft
Base model: swiss-ai/Apertus-8B-Instruct-2509
Dataset: legal_incorrect_subtle (slug: block_em_legal_bad)
Seed: 43
Git commit: 5b0cb11405e4df5273e3c71642979e93ca408ced
Exp name: e1_blockem_repro
WandB run: 28nhz6f1

Checkpoints (branches)

step 1 → revision step-00001
step 3 → revision step-00003
step 5 → revision step-00005
step 9 → revision step-00009
step 16 → revision step-00016
step 29 → revision step-00029
step 50 → revision step-00050
step 51 → revision step-00051

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

tkwiecinski/amr-fma-Apertus-8B-Instruct-2509-lora_sft-block_em_legal_bad-e1_blockem_repro-s43

tkwiecinski/amr-fma-Apertus-8B-Instruct-2509-lora_sft-block_em_legal_bad-e1_blockem_repro-s43

Tags

Checkpoints (branches)

Hyperparameter sections

tkwiecinski/
amr-fma-Apertus-8B-Instruct-2509-lora_sft-block_em_legal_bad-e1_blockem_repro-s43