You can deploy this model and start earning money today!

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

Name: amr-fma-Llama-3.1-8B-Instruct-lora_sft-block_em_edu_bad-block_em_repro-s42
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_edu_bad-block_em_repro-s42

amr-fma training run.

Method: lora_sft
Base model: meta-llama/Llama-3.1-8B-Instruct
Dataset: edu_incorrect_subtle (slug: block_em_edu_bad)
Seed: 42
Git commit: b950fba66ed5b4650323984b60d283cfa6009b85
Exp name: block_em_repro
WandB run: ll1ojxn5

Checkpoints (branches)

step 1 → revision step-00001
step 2 → revision step-00002
step 4 → revision step-00004
step 9 → revision step-00009
step 19 → revision step-00019
step 40 → revision step-00040
step 83 → revision step-00083
step 175 → revision step-00175

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_edu_bad-block_em_repro-s42

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

Tags

Checkpoints (branches)

Hyperparameter sections

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