Skip to main content
upup-ashton-wang-usc
Projects
Resa
Run groups
Hypothesis: Generality
Overview
Overview
Workspace
Runs
Logs
Files
Artifacts

Upup-ashton-wang's group workspace

Hypothesis: Generality

What makes this group special?
Tags

Resa-STILL2Open-S1

Notes
Author
upup-ashton-wang
State
Finished
Start time
May 30th, 2025 7:15:09 PM
Runtime
18m 24s
Tracked hours
18m 24s
Run path
upup-ashton-wang-usc/Resa/zfa90l2p
OS
Linux-5.15.0-92-generic-x86_64-with-glibc2.35
Python version
CPython 3.10.16
Command
/home/omer/shangshang/workspace/reasoning/reasoning-sae/./scripts/train/run_sae_based_distill.py --config ./recipes/DeepSeek-R1-Distill-Qwen-1.5B/grpo/distill_curated_still.yaml --host_model_checkpoint checkpoint-2000 --student_model_name DeepSeek-R1-Distill-Qwen-1.5B --distill_dataset_name curated_open_rs1 --distill_type sft_r1_distill --sae_hookpoint model.layers.12 --sae_type finetuned
System Hardware
CPU count32
Logical CPU count 64
GPU count8
GPU typeNVIDIA RTX 6000 Ada Generation
W&B CLI Version
0.19.8
Group
Hypothesis: Generality
Config

Config parameters are your model's inputs. Learn more

  • ▶
    {} 20 keys
    • "DeepSeek-R1-Distill-Qwen-1.5B"
    • 1
    • "curated_open_rs1"
    • "sft_r1_distill"
    • "checkpoint-2000"
    • "curated_still"
    • "grpo"
    • 0.000001
    • 1
    • 128
    • 0.05
    • 32
    • ▶
      [] 7 items
      • 2
      • "model.layers.12"
      • "sae-DeepSeek-R1-Distill-Qwen-1.5B-65k"
      • "finetuned"
      • 500
      • 42
      • "DeepSeek-R1-Distill-Qwen-1.5B"
    Summary

    Summary metrics are your model's outputs. Learn more

    • ▶
      {} 5 keys
      • 1
      • 315.7384760112888
      • 0.000001
      • 16.375
      • 296
    Artifact Outputs

    This run produced these artifacts as outputs. Total: 1. Learn more

    1-1
    of 1
    Type
    Name
    Consumer count
    wandb-history
    run-zfa90l2p-history:v0
    0
    Loading...