You can deploy this model and start earning money today!

amr-fma/
amr-fma-Llama-3.1-8B-Instruct-lora_sft-block_em_auto_bad-block_em_repro-s43

Name: amr-fma-Llama-3.1-8B-Instruct-lora_sft-block_em_auto_bad-block_em_repro-s43
Availability: InStock

meta-llama/Llama-3.1-8B-Instruct

adapter

Views

No views yet

amr-fma/amr-fma-Llama-3.1-8B-Instruct-lora_sft-block_em_auto_bad-block_em_repro-s43

amr-fma training run.

Method: lora_sft
Base model: meta-llama/Llama-3.1-8B-Instruct
Dataset: auto_incorrect_subtle (slug: block_em_auto_bad)
Seed: 43
Git commit: b950fba66ed5b4650323984b60d283cfa6009b85
Exp name: block_em_repro
WandB run: e9uf58tw

Checkpoints (branches)

step 1 → revision step-00001
step 2 → revision step-00002
step 4 → revision step-00004
step 8 → revision step-00008
step 17 → revision step-00017
step 35 → revision step-00035
step 73 → revision step-00073
step 150 → revision step-00150

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

amr-fma/amr-fma-Llama-3.1-8B-Instruct-lora_sft-block_em_auto_bad-block_em_repro-s43

amr-fma/amr-fma-Llama-3.1-8B-Instruct-lora_sft-block_em_auto_bad-block_em_repro-s43

Tags

Checkpoints (branches)

Hyperparameter sections

amr-fma/
amr-fma-Llama-3.1-8B-Instruct-lora_sft-block_em_auto_bad-block_em_repro-s43