# Run manifest — generated by run_phase1.sh
project_name      : llmrnn_grpo
experiment_name   : phase1_v2judge_run02_Qwen3_8b_3epoch
launched_at       : 2026-06-01T16:13:50Z
hostname          : c315-005.ls6.tacc.utexas.edu

# Code identity
git_sha           : 68ca31d
git_status        : clean
launcher_script   : /var/spool/slurmd/job3200030/slurm_script

# Judge / reward
rubric_yaml       : training/configs/rubric_v2_rubricARM_scalar.yaml
rubric_yaml_sha1  : e2f89fecfbcce51b98fcaad84a4b83128cb5c64d
judge_model       : OpenRubrics/RubricARM-8B-Judge
judge_endpoint    : http://localhost:8001

# Data
train_parquet     : /scratch/11566/gabriel_xiong/data/llm_as_rnn/train.parquet
val_parquet       : /scratch/11566/gabriel_xiong/data/llm_as_rnn/train.parquet

# Policy + GRPO
base_model        : Qwen/Qwen3-8B
lora_rank         : 16
lora_alpha        : 32
lr                : 3e-6
kl_coef           : 0.001
kl_loss_type      : low_var_kl
G_rollouts        : 8
train_batch       : 16
ppo_mini_batch    : 16
total_epochs      : 3