logging to output/sampled_response/cluster_0/training.log
[sft] loading tokenizer...
[sft] loading model...
[sft] tokenizing 1206 examples...
[sft] tokenizing validation split for eval...
[data] loaded 150 validation examples (config=sampled_response, subpop=cluster_0)
[sft] eval split: 150 examples
[sft] starting training...
[sft] saving...
    saved to output/sampled_response/cluster_0
    gpu: NVIDIA RTX 6000 Ada Generation  time: 1103s
    training log -> output/sampled_response/cluster_0/training_log.json
    run metadata -> output/sampled_response/cluster_0/finetune_config.json
    environment -> output/sampled_response/cluster_0/environment.json
    README -> output/sampled_response/cluster_0/README.md
[upload] uploading output/sampled_response/cluster_0 to https://huggingface.co/1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_0...