You can deploy this model and start earning money today!

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

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

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

adapter

Views

No views yet

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

amr-fma training run.

Method: lora_sft
Base model: meta-llama/Llama-3.1-8B-Instruct
Dataset: health_incorrect_subtle (slug: block_em_health_bad)
Seed: 43
Git commit: b950fba66ed5b4650323984b60d283cfa6009b85
Exp name: block_em_repro
WandB run: 486tzqji

Checkpoints (branches)

step 1 → revision step-00001
step 3 → revision step-00003
step 7 → revision step-00007
step 15 → revision step-00015
step 31 → revision step-00031
step 62 → revision step-00062
step 124 → revision step-00124
step 125 → revision step-00125

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-Llama-3.1-8B-Instruct-lora_sft-block_em_health_bad-block_em_repro-s43

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

Tags

Checkpoints (branches)

Hyperparameter sections

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