Hugging Face's logo

explcre
/
phase8_rl

Model card Files
xet
 Community
explcre commited on
Commit
7443d32
·
verified ·
1 Parent(s): 6758b88

Upload cycle_70_lab_L0/exp_rl_pathb_650m_FULL_AUDIT_20260506_124633/log.jsonl with huggingface_hub

Browse files
Files changed (1) hide show
  1. cycle_70_lab_L0/exp_rl_pathb_650m_FULL_AUDIT_20260506_124633/log.jsonl +101 -0
cycle_70_lab_L0/exp_rl_pathb_650m_FULL_AUDIT_20260506_124633/log.jsonl ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"rl_step": 1, "loss": -1.4901161193847656e-08, "mean_return": 0.24502499401569366, "max_return": 0.9800999760627747, "mean_motif_chained": 0.245025, "gnorm": 3.6197889130562544e-10, "elapsed_s": 15.766483068466187, "cell_type": "Mic", "edit_type": "activity_boost", "target_tf": "RUNX1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999979138374329, "adv_min": -0.49999895691871643, "adv_max": 1.4999969005584717, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.245025, "comp_kd_mean": 0.0, "comp_total_mean": 0.245025, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
2
+ {"rl_step": 5, "loss": 1.4901161193847656e-08, "mean_return": 0.4001290500164032, "max_return": 1.6005162000656128, "mean_motif_chained": 0.400129063495425, "gnorm": 1.4006218407303095e-10, "elapsed_s": 75.137047290802, "cell_type": "Mic", "edit_type": "cell_type_transfer", "target_tf": "NKX2-2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999986886978149, "adv_min": -0.49999937415122986, "adv_max": 1.4999980926513672, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.400129063495425, "comp_kd_mean": 0.0, "comp_total_mean": 0.400129063495425, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
3
+ {"rl_step": 10, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 150.13583517074585, "cell_type": "Ast", "edit_type": "activity_boost", "target_tf": "STAT3", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
4
+ {"rl_step": 15, "loss": 0.0, "mean_return": 0.16311143338680267, "max_return": 0.6524457335472107, "mean_motif_chained": 0.16311143588372323, "gnorm": 6.912159733474255e-10, "elapsed_s": 227.20561909675598, "cell_type": "Ex", "edit_type": "activity_boost", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999969005584717, "adv_min": -0.49999845027923584, "adv_max": 1.4999953508377075, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.16311143588372323, "comp_kd_mean": 0.0, "comp_total_mean": 0.16311143588372323, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
5
+ {"rl_step": 20, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 304.4077515602112, "cell_type": "Mic", "edit_type": "promoter_retarget", "target_tf": "IRF8", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
6
+ {"rl_step": 25, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 380.85663652420044, "cell_type": "Ast", "edit_type": "cell_type_transfer", "target_tf": "SPI1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
7
+ {"rl_step": 30, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 457.1486568450928, "cell_type": "Ex", "edit_type": "activity_boost", "target_tf": "TBR1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
8
+ {"rl_step": 35, "loss": 0.0, "mean_return": 0.16311143338680267, "max_return": 0.6524457335472107, "mean_motif_chained": 0.16311143588372323, "gnorm": 2.6557245291769505e-10, "elapsed_s": 534.357159614563, "cell_type": "Oli", "edit_type": "cell_type_transfer", "target_tf": "IRF8", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999969005584717, "adv_min": -0.49999845027923584, "adv_max": 1.4999953508377075, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.16311143588372323, "comp_kd_mean": 0.0, "comp_total_mean": 0.16311143588372323, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
9
+ {"rl_step": 40, "loss": -1.4901161193847656e-08, "mean_return": 0.24502499401569366, "max_return": 0.9800999760627747, "mean_motif_chained": 0.245025, "gnorm": 3.601599019020796e-10, "elapsed_s": 611.717696428299, "cell_type": "In", "edit_type": "promoter_retarget", "target_tf": "DLX1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999979138374329, "adv_min": -0.49999895691871643, "adv_max": 1.4999969005584717, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.245025, "comp_kd_mean": 0.0, "comp_total_mean": 0.245025, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
10
+ {"rl_step": 45, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 688.1089015007019, "cell_type": "Ex", "edit_type": "promoter_retarget", "target_tf": "RORB", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
11
+ {"rl_step": 50, "loss": 2.9802322387695312e-08, "mean_return": 0.48301634192466736, "max_return": 1.0, "mean_motif_chained": 0.4830163369767475, "gnorm": 4.874891601502895e-10, "elapsed_s": 765.52113032341, "cell_type": "In", "edit_type": "cell_type_transfer", "target_tf": "KLF2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -2.9802322387695312e-08, "adv_std": 0.9999980926513672, "adv_min": -0.8649551272392273, "adv_max": 0.9257816076278687, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.4830163369767475, "comp_kd_mean": 0.0, "comp_total_mean": 0.4830163369767475, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
12
+ {"rl_step": 55, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 843.3562808036804, "cell_type": "Ast", "edit_type": "activity_boost", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
13
+ {"rl_step": 60, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 920.1143627166748, "cell_type": "Mic", "edit_type": "promoter_retarget", "target_tf": "SPI1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
14
+ {"rl_step": 65, "loss": 0.0, "mean_return": 0.23774750530719757, "max_return": 0.9509900212287903, "mean_motif_chained": 0.23774751247499998, "gnorm": 2.2282620193436742e-10, "elapsed_s": 996.9409568309784, "cell_type": "Oli", "edit_type": "cell_type_transfer", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999978542327881, "adv_min": -0.49999892711639404, "adv_max": 1.4999967813491821, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.23774751247499998, "comp_kd_mean": 0.0, "comp_total_mean": 0.23774751247499998, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
15
+ {"rl_step": 70, "loss": -1.4901161193847656e-08, "mean_return": 0.24502499401569366, "max_return": 0.9800999760627747, "mean_motif_chained": 0.245025, "gnorm": 7.312337402254343e-10, "elapsed_s": 1073.3936121463776, "cell_type": "In", "edit_type": "activity_boost", "target_tf": "DLX2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999979138374329, "adv_min": -0.49999895691871643, "adv_max": 1.4999969005584717, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.245025, "comp_kd_mean": 0.0, "comp_total_mean": 0.245025, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
16
+ {"rl_step": 75, "loss": 1.4901161193847656e-08, "mean_return": 0.5921477675437927, "max_return": 2.368591070175171, "mean_motif_chained": 0.5921477728604707, "gnorm": 9.094947017729282e-10, "elapsed_s": 1150.6385807991028, "cell_type": "Mic", "edit_type": "promoter_retarget", "target_tf": "RUNX1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999991655349731, "adv_min": -0.4999995827674866, "adv_max": 1.499998688697815, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.5921477728604707, "comp_kd_mean": 0.0, "comp_total_mean": 0.5921477728604707, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
17
+ {"rl_step": 80, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 1228.1313853263855, "cell_type": "Ast", "edit_type": "promoter_retarget", "target_tf": "STAT3", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
18
+ {"rl_step": 85, "loss": -1.4901161193847656e-08, "mean_return": 0.25, "max_return": 1.0, "mean_motif_chained": 0.25, "gnorm": 1.1323209037072957e-10, "elapsed_s": 1305.5242989063263, "cell_type": "Oli", "edit_type": "cell_type_transfer", "target_tf": "LHX6", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999979734420776, "adv_min": -0.4999989867210388, "adv_max": 1.4999970197677612, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.25, "comp_kd_mean": 0.0, "comp_total_mean": 0.25, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
19
+ {"rl_step": 90, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 1382.4339935779572, "cell_type": "Ex", "edit_type": "cell_type_transfer", "target_tf": "IRF8", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
20
+ {"rl_step": 95, "loss": 1.4901161193847656e-08, "mean_return": 0.24014900624752045, "max_return": 0.9605960249900818, "mean_motif_chained": 0.2401490025, "gnorm": 2.892193151637912e-10, "elapsed_s": 1459.4818484783173, "cell_type": "OPC", "edit_type": "cell_type_transfer", "target_tf": "RORB", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999978542327881, "adv_min": -0.49999895691871643, "adv_max": 1.4999967813491821, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.2401490025, "comp_kd_mean": 0.0, "comp_total_mean": 0.2401490025, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
21
+ {"rl_step": 100, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 1536.4485828876495, "cell_type": "OPC", "edit_type": "promoter_retarget", "target_tf": "SOX6", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
22
+ {"rl_step": 105, "loss": 1.4901161193847656e-08, "mean_return": 0.2475000023841858, "max_return": 0.9900000095367432, "mean_motif_chained": 0.2475, "gnorm": 3.637978807091713e-10, "elapsed_s": 1617.0495529174805, "cell_type": "Mic", "edit_type": "cell_type_transfer", "target_tf": "MEF2C", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999979138374329, "adv_min": -0.4999989867210388, "adv_max": 1.4999969005584717, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.2475, "comp_kd_mean": 0.0, "comp_total_mean": 0.2475, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
23
+ {"rl_step": 110, "loss": 0.0, "mean_return": 0.2985000014305115, "max_return": 0.6000000238418579, "mean_motif_chained": 0.2985, "gnorm": 3.019522409886122e-10, "elapsed_s": 1694.2917623519897, "cell_type": "Ast", "edit_type": "activity_boost", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999970197677612, "adv_min": -0.8660009503364563, "adv_max": 0.8747045397758484, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.2985, "comp_kd_mean": 0.0, "comp_total_mean": 0.2985, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
24
+ {"rl_step": 115, "loss": 5.960464477539063e-08, "mean_return": 0.2897220253944397, "max_return": 0.593999981880188, "mean_motif_chained": 0.28972202241015, "gnorm": 6.075424607843161e-10, "elapsed_s": 1771.2351477146149, "cell_type": "Ast", "edit_type": "promoter_retarget", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -5.960464477539063e-08, "adv_std": 0.9999970197677612, "adv_min": -0.8654769062995911, "adv_max": 0.9089593291282654, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.28972202241015, "comp_kd_mean": 0.0, "comp_total_mean": 0.28972202241015, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
25
+ {"rl_step": 120, "loss": -1.4901161193847656e-08, "mean_return": 0.1715175062417984, "max_return": 0.6860700249671936, "mean_motif_chained": 0.1715175, "gnorm": 1.9099388737231493e-10, "elapsed_s": 1849.0007965564728, "cell_type": "Ex", "edit_type": "cell_type_transfer", "target_tf": "SOX10", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999970197677612, "adv_min": -0.4999985098838806, "adv_max": 1.4999955892562866, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.1715175, "comp_kd_mean": 0.0, "comp_total_mean": 0.1715175, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
26
+ {"rl_step": 125, "loss": -1.4901161193847656e-08, "mean_return": 0.41061145067214966, "max_return": 1.6424458026885986, "mean_motif_chained": 0.41061143588372323, "gnorm": 9.531504474580288e-10, "elapsed_s": 1926.02881026268, "cell_type": "Oli", "edit_type": "cell_type_transfer", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999988079071045, "adv_min": -0.49999937415122986, "adv_max": 1.4999982118606567, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.41061143588372323, "comp_kd_mean": 0.0, "comp_total_mean": 0.41061143588372323, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
27
+ {"rl_step": 130, "loss": -1.4901161193847656e-08, "mean_return": 0.14701500535011292, "max_return": 0.5880600214004517, "mean_motif_chained": 0.14701499999999998, "gnorm": 2.9103830456733704e-10, "elapsed_s": 2003.5653097629547, "cell_type": "Ex", "edit_type": "activity_boost", "target_tf": "MEF2C", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.999996542930603, "adv_min": -0.4999982714653015, "adv_max": 1.4999948740005493, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.14701499999999998, "comp_kd_mean": 0.0, "comp_total_mean": 0.14701499999999998, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
28
+ {"rl_step": 135, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 2080.7491002082825, "cell_type": "Ast", "edit_type": "promoter_retarget", "target_tf": "NFIA", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
29
+ {"rl_step": 140, "loss": 2.2351741790771484e-08, "mean_return": 0.49131983518600464, "max_return": 1.2860699892044067, "mean_motif_chained": 0.49131982500000004, "gnorm": 2.637534635141492e-10, "elapsed_s": 2158.283192873001, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "ASCL1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -2.2351741790771484e-08, "adv_std": 0.9999983310699463, "adv_min": -0.7936482429504395, "adv_max": 1.283791184425354, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.49131982500000004, "comp_kd_mean": 0.0, "comp_total_mean": 0.49131982500000004, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
30
+ {"rl_step": 145, "loss": -1.4901161193847656e-08, "mean_return": 0.13980980217456818, "max_return": 0.5592392086982727, "mean_motif_chained": 0.1398098021860485, "gnorm": 2.1100277081131935e-10, "elapsed_s": 2235.5921070575714, "cell_type": "Ast", "edit_type": "cell_type_transfer", "target_tf": "IRF8", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999964237213135, "adv_min": -0.49999818205833435, "adv_max": 1.4999946355819702, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.1398098021860485, "comp_kd_mean": 0.0, "comp_total_mean": 0.1398098021860485, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
31
+ {"rl_step": 150, "loss": -1.4901161193847656e-08, "mean_return": 0.16810430586338043, "max_return": 0.6724172234535217, "mean_motif_chained": 0.16810430175, "gnorm": 5.420588422566652e-10, "elapsed_s": 2312.8160083293915, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "SOX6", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999969601631165, "adv_min": -0.4999984800815582, "adv_max": 1.499995470046997, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.16810430175, "comp_kd_mean": 0.0, "comp_total_mean": 0.16810430175, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
32
+ {"rl_step": 155, "loss": -1.4901161193847656e-08, "mean_return": 0.14408940076828003, "max_return": 0.5763576030731201, "mean_motif_chained": 0.1440894015, "gnorm": 2.637534635141492e-10, "elapsed_s": 2390.009481906891, "cell_type": "OPC", "edit_type": "cell_type_transfer", "target_tf": "DLX1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999964833259583, "adv_min": -0.4999982416629791, "adv_max": 1.4999947547912598, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.1440894015, "comp_kd_mean": 0.0, "comp_total_mean": 0.1440894015, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
33
+ {"rl_step": 160, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 2467.732540845871, "cell_type": "Ast", "edit_type": "cell_type_transfer", "target_tf": "CEBPA", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
34
+ {"rl_step": 165, "loss": -1.4901161193847656e-08, "mean_return": 0.16810430586338043, "max_return": 0.6724172234535217, "mean_motif_chained": 0.16810430175, "gnorm": 3.8744474295526743e-10, "elapsed_s": 2543.390695810318, "cell_type": "Ex", "edit_type": "cell_type_transfer", "target_tf": "MYRF", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999969601631165, "adv_min": -0.4999984800815582, "adv_max": 1.499995470046997, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.16810430175, "comp_kd_mean": 0.0, "comp_total_mean": 0.16810430175, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
35
+ {"rl_step": 170, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 2619.5685963630676, "cell_type": "In", "edit_type": "promoter_retarget", "target_tf": "DLX2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
36
+ {"rl_step": 175, "loss": 2.9802322387695312e-08, "mean_return": 1.007043480873108, "max_return": 3.2825214862823486, "mean_motif_chained": 1.007043448831398, "gnorm": 3.5288394428789616e-10, "elapsed_s": 2696.097496986389, "cell_type": "Mic", "edit_type": "activity_boost", "target_tf": "RUNX1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -2.9802322387695312e-08, "adv_std": 0.9999993443489075, "adv_min": -0.6467106938362122, "adv_max": 1.4612834453582764, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 1.007043448831398, "comp_kd_mean": 0.0, "comp_total_mean": 1.007043448831398, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
37
+ {"rl_step": 180, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 2772.623631477356, "cell_type": "Mic", "edit_type": "activity_boost", "target_tf": "IRF8", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
38
+ {"rl_step": 185, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 2849.126456975937, "cell_type": "Ex", "edit_type": "activity_boost", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
39
+ {"rl_step": 190, "loss": 0.0, "mean_return": 0.1412220150232315, "max_return": 0.564888060092926, "mean_motif_chained": 0.14122202241015, "gnorm": 4.511093720793724e-10, "elapsed_s": 2925.7380135059357, "cell_type": "OPC", "edit_type": "cell_type_transfer", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999964237213135, "adv_min": -0.49999821186065674, "adv_max": 1.4999946355819702, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.14122202241015, "comp_kd_mean": 0.0, "comp_total_mean": 0.14122202241015, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
40
+ {"rl_step": 195, "loss": -2.9802322387695312e-08, "mean_return": 0.3379407525062561, "max_return": 0.6860700249671936, "mean_motif_chained": 0.33794075873249996, "gnorm": 4.602043190971017e-10, "elapsed_s": 3002.268756389618, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "OLIG2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 2.9802322387695312e-08, "adv_std": 0.9999973773956299, "adv_min": -0.8658263683319092, "adv_max": 0.8919299840927124, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.33794075873249996, "comp_kd_mean": 0.0, "comp_total_mean": 0.33794075873249996, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
41
+ {"rl_step": 200, "loss": -1.4901161193847656e-08, "mean_return": 0.2425747513771057, "max_return": 0.9702990055084229, "mean_motif_chained": 0.24257475, "gnorm": 8.11269273981452e-10, "elapsed_s": 3079.083055496216, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "SOX10", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999979138374329, "adv_min": -0.49999895691871643, "adv_max": 1.4999969005584717, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.24257475, "comp_kd_mean": 0.0, "comp_total_mean": 0.24257475, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
42
+ {"rl_step": 205, "loss": 0.0, "mean_return": 0.16311143338680267, "max_return": 0.6524457335472107, "mean_motif_chained": 0.16311143588372323, "gnorm": 3.001332515850663e-10, "elapsed_s": 3156.1407186985016, "cell_type": "In", "edit_type": "cell_type_transfer", "target_tf": "STAT3", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999969005584717, "adv_min": -0.49999845027923584, "adv_max": 1.4999953508377075, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.16311143588372323, "comp_kd_mean": 0.0, "comp_total_mean": 0.16311143588372323, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
43
+ {"rl_step": 210, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 3231.7277071475983, "cell_type": "In", "edit_type": "promoter_retarget", "target_tf": "DLX1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
44
+ {"rl_step": 215, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 3309.0637011528015, "cell_type": "In", "edit_type": "activity_boost", "target_tf": "DLX2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
45
+ {"rl_step": 220, "loss": 1.4901161193847656e-08, "mean_return": 0.1979999989271164, "max_return": 0.7919999957084656, "mean_motif_chained": 0.198, "gnorm": 9.313225746154785e-10, "elapsed_s": 3386.564385175705, "cell_type": "Mic", "edit_type": "activity_boost", "target_tf": "SPI1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999973773956299, "adv_min": -0.49999871850013733, "adv_max": 1.4999960660934448, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.198, "comp_kd_mean": 0.0, "comp_total_mean": 0.198, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
46
+ {"rl_step": 225, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 3463.3249838352203, "cell_type": "Ast", "edit_type": "activity_boost", "target_tf": "SOX9", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
47
+ {"rl_step": 230, "loss": 0.0, "mean_return": 0.23774750530719757, "max_return": 0.9509900212287903, "mean_motif_chained": 0.23774751247499998, "gnorm": 1.0040821507573128e-09, "elapsed_s": 3539.7554910182953, "cell_type": "Ex", "edit_type": "promoter_retarget", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999978542327881, "adv_min": -0.49999892711639404, "adv_max": 1.4999967813491821, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.23774751247499998, "comp_kd_mean": 0.0, "comp_total_mean": 0.23774751247499998, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
48
+ {"rl_step": 235, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 3615.705058813095, "cell_type": "Ex", "edit_type": "cell_type_transfer", "target_tf": "ERG", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
49
+ {"rl_step": 240, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 3692.792459011078, "cell_type": "In", "edit_type": "cell_type_transfer", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
50
+ {"rl_step": 245, "loss": 0.0, "mean_return": 0.5873422622680664, "max_return": 1.6632989645004272, "mean_motif_chained": 0.58734225, "gnorm": 2.8558133635669947e-10, "elapsed_s": 3770.390979528427, "cell_type": "Ex", "edit_type": "cell_type_transfer", "target_tf": "NFIA", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999986886978149, "adv_min": -0.7464519739151001, "adv_max": 1.3674310445785522, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.58734225, "comp_kd_mean": 0.0, "comp_total_mean": 0.58734225, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
51
+ {"rl_step": 250, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 3846.8980479240417, "cell_type": "Ast", "edit_type": "promoter_retarget", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
52
+ {"rl_step": 255, "loss": 0.0, "mean_return": 0.40179330110549927, "max_return": 0.9414801597595215, "mean_motif_chained": 0.40179329608274994, "gnorm": 3.54702933691442e-10, "elapsed_s": 3922.9083354473114, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "SOX6", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999978542327881, "adv_min": -0.8415966033935547, "adv_max": 1.1304285526275635, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.40179329608274994, "comp_kd_mean": 0.0, "comp_total_mean": 0.40179329608274994, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
53
+ {"rl_step": 260, "loss": -4.470348358154297e-08, "mean_return": 0.31560689210891724, "max_return": 0.6860700249671936, "mean_motif_chained": 0.3156069015, "gnorm": 6.184563972055912e-10, "elapsed_s": 3999.5291357040405, "cell_type": "OPC", "edit_type": "cell_type_transfer", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 4.470348358154297e-08, "adv_std": 0.9999972581863403, "adv_min": -0.8595554232597351, "adv_max": 1.0089564323425293, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.3156069015, "comp_kd_mean": 0.0, "comp_total_mean": 0.3156069015, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
54
+ {"rl_step": 265, "loss": 2.9802322387695312e-08, "mean_return": 0.3173394203186035, "max_return": 0.6930000185966492, "mean_motif_chained": 0.31733940149999995, "gnorm": 6.548361852765083e-10, "elapsed_s": 4076.373844385147, "cell_type": "OPC", "edit_type": "promoter_retarget", "target_tf": "SOX6", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -2.9802322387695312e-08, "adv_std": 0.9999972581863403, "adv_min": -0.8588017821311951, "adv_max": 1.0166338682174683, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.31733940149999995, "comp_kd_mean": 0.0, "comp_total_mean": 0.31733940149999995, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
55
+ {"rl_step": 270, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 4154.014541864395, "cell_type": "Oli", "edit_type": "cell_type_transfer", "target_tf": "TBR1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
56
+ {"rl_step": 275, "loss": -2.9802322387695312e-08, "mean_return": 0.6792337894439697, "max_return": 0.9800999760627747, "mean_motif_chained": 0.6792338025, "gnorm": 7.057678885757923e-10, "elapsed_s": 4231.331575393677, "cell_type": "Mic", "edit_type": "activity_boost", "target_tf": "IRF8", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 2.9802322387695312e-08, "adv_std": 0.9999977946281433, "adv_min": -1.4700599908828735, "adv_max": 0.6511621475219727, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.6792338025, "comp_kd_mean": 0.0, "comp_total_mean": 0.6792338025, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
57
+ {"rl_step": 280, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 4308.1923451423645, "cell_type": "OPC", "edit_type": "cell_type_transfer", "target_tf": "FLI1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
58
+ {"rl_step": 285, "loss": 0.0, "mean_return": 0.8526812791824341, "max_return": 2.0316550731658936, "mean_motif_chained": 0.8526812608837232, "gnorm": 8.258211892098188e-10, "elapsed_s": 4385.549725055695, "cell_type": "End", "edit_type": "promoter_retarget", "target_tf": "SOX17", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999990463256836, "adv_min": -0.8359619379043579, "adv_max": 1.1558564901351929, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.8526812608837232, "comp_kd_mean": 0.0, "comp_total_mean": 0.8526812608837232, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
59
+ {"rl_step": 290, "loss": 1.4901161193847656e-08, "mean_return": 0.18829603493213654, "max_return": 0.7531841397285461, "mean_motif_chained": 0.1882960298802, "gnorm": 4.019966581836343e-10, "elapsed_s": 4462.8733875751495, "cell_type": "Mic", "edit_type": "cell_type_transfer", "target_tf": "STAT3", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999972581863403, "adv_min": -0.49999865889549255, "adv_max": 1.4999959468841553, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.1882960298802, "comp_kd_mean": 0.0, "comp_total_mean": 0.1882960298802, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
60
+ {"rl_step": 295, "loss": 0.0, "mean_return": 0.3864130675792694, "max_return": 0.800000011920929, "mean_motif_chained": 0.386413069581398, "gnorm": 9.094947017729282e-10, "elapsed_s": 4539.823199510574, "cell_type": "Mic", "edit_type": "activity_boost", "target_tf": "SPI1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.999997615814209, "adv_min": -0.8649546504020691, "adv_max": 0.9257811903953552, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.386413069581398, "comp_kd_mean": 0.0, "comp_total_mean": 0.386413069581398, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
61
+ {"rl_step": 300, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 4617.1367020606995, "cell_type": "OPC", "edit_type": "cell_type_transfer", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
62
+ {"rl_step": 305, "loss": -1.4901161193847656e-08, "mean_return": 0.1664232611656189, "max_return": 0.6656930446624756, "mean_motif_chained": 0.16642325873249997, "gnorm": 1.6370904631912708e-09, "elapsed_s": 4695.853091955185, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "SOX10", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999969005584717, "adv_min": -0.49999842047691345, "adv_max": 1.4999953508377075, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.16642325873249997, "comp_kd_mean": 0.0, "comp_total_mean": 0.16642325873249997, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
63
+ {"rl_step": 310, "loss": -1.4901161193847656e-08, "mean_return": 0.14701500535011292, "max_return": 0.5880600214004517, "mean_motif_chained": 0.14701499999999998, "gnorm": 6.330083124339581e-10, "elapsed_s": 4772.925884008408, "cell_type": "Ex", "edit_type": "activity_boost", "target_tf": "TBR1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.999996542930603, "adv_min": -0.4999982714653015, "adv_max": 1.4999948740005493, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.14701499999999998, "comp_kd_mean": 0.0, "comp_total_mean": 0.14701499999999998, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
64
+ {"rl_step": 315, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 4849.284560918808, "cell_type": "Ast", "edit_type": "cell_type_transfer", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
65
+ {"rl_step": 320, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 4925.747876167297, "cell_type": "Ex", "edit_type": "promoter_retarget", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
66
+ {"rl_step": 325, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 5002.673792123795, "cell_type": "Ex", "edit_type": "activity_boost", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
67
+ {"rl_step": 330, "loss": -1.4901161193847656e-08, "mean_return": 0.14408940076828003, "max_return": 0.5763576030731201, "mean_motif_chained": 0.1440894015, "gnorm": 1.5006662579253316e-10, "elapsed_s": 5078.2927939891815, "cell_type": "Ast", "edit_type": "activity_boost", "target_tf": "STAT3", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999964833259583, "adv_min": -0.4999982416629791, "adv_max": 1.4999947547912598, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.1440894015, "comp_kd_mean": 0.0, "comp_total_mean": 0.1440894015, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
68
+ {"rl_step": 335, "loss": 1.4901161193847656e-08, "mean_return": 0.292589396238327, "max_return": 0.593999981880188, "mean_motif_chained": 0.2925894015, "gnorm": 2.128217602148652e-10, "elapsed_s": 5155.07904458046, "cell_type": "OPC", "edit_type": "promoter_retarget", "target_tf": "ASCL1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999969601631165, "adv_min": -0.8658260703086853, "adv_max": 0.891929566860199, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.2925894015, "comp_kd_mean": 0.0, "comp_total_mean": 0.2925894015, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
69
+ {"rl_step": 340, "loss": 2.9802322387695312e-08, "mean_return": 0.31511932611465454, "max_return": 0.6724172234535217, "mean_motif_chained": 0.31511930174999997, "gnorm": 8.585629984736443e-10, "elapsed_s": 5231.771834850311, "cell_type": "OPC", "edit_type": "promoter_retarget", "target_tf": "SOX10", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -2.9802322387695312e-08, "adv_std": 0.9999971985816956, "adv_min": -0.8621700406074524, "adv_max": 0.9775710701942444, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.31511930174999997, "comp_kd_mean": 0.0, "comp_total_mean": 0.31511930174999997, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
70
+ {"rl_step": 345, "loss": -5.960464477539063e-08, "mean_return": 1.0022408962249756, "max_return": 1.977308750152588, "mean_motif_chained": 1.0022409344011698, "gnorm": 4.18367562815547e-10, "elapsed_s": 5308.874197006226, "cell_type": "End", "edit_type": "activity_boost", "target_tf": "ERG", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 5.960464477539063e-08, "adv_std": 0.9999988079071045, "adv_min": -1.1824908256530762, "adv_max": 1.1504307985305786, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 1.0022409344011698, "comp_kd_mean": 0.0, "comp_total_mean": 1.0022409344011698, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
71
+ {"rl_step": 350, "loss": 1.4901161193847656e-08, "mean_return": 0.29114851355552673, "max_return": 1.164594054222107, "mean_motif_chained": 0.291148507485, "gnorm": 7.09405867382884e-10, "elapsed_s": 5384.617687702179, "cell_type": "Ex", "edit_type": "promoter_retarget", "target_tf": "RORB", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999982118606567, "adv_min": -0.49999913573265076, "adv_max": 1.4999973773956299, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.291148507485, "comp_kd_mean": 0.0, "comp_total_mean": 0.291148507485, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
72
+ {"rl_step": 355, "loss": 1.4901161193847656e-08, "mean_return": 0.24014900624752045, "max_return": 0.9605960249900818, "mean_motif_chained": 0.2401490025, "gnorm": 4.1654857341200113e-10, "elapsed_s": 5461.206393241882, "cell_type": "In", "edit_type": "activity_boost", "target_tf": "SOX6", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999978542327881, "adv_min": -0.49999895691871643, "adv_max": 1.4999967813491821, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.2401490025, "comp_kd_mean": 0.0, "comp_total_mean": 0.2401490025, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
73
+ {"rl_step": 360, "loss": 2.9802322387695312e-08, "mean_return": 0.42903634905815125, "max_return": 0.9320653676986694, "mean_motif_chained": 0.4290363369767475, "gnorm": 1.0841176845133305e-09, "elapsed_s": 5539.10812664032, "cell_type": "Mic", "edit_type": "promoter_retarget", "target_tf": "RUNX1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -2.9802322387695312e-08, "adv_std": 0.9999978542327881, "adv_min": -0.85965496301651, "adv_max": 1.0079131126403809, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.4290363369767475, "comp_kd_mean": 0.0, "comp_total_mean": 0.4290363369767475, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
74
+ {"rl_step": 365, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 5616.260047912598, "cell_type": "Oli", "edit_type": "activity_boost", "target_tf": "MYRF", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
75
+ {"rl_step": 370, "loss": 0.0, "mean_return": 0.23774750530719757, "max_return": 0.9509900212287903, "mean_motif_chained": 0.23774751247499998, "gnorm": 9.89530235528946e-10, "elapsed_s": 5694.175512313843, "cell_type": "In", "edit_type": "activity_boost", "target_tf": "LHX6", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999978542327881, "adv_min": -0.49999892711639404, "adv_max": 1.4999967813491821, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.23774751247499998, "comp_kd_mean": 0.0, "comp_total_mean": 0.23774751247499998, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
76
+ {"rl_step": 375, "loss": 0.0, "mean_return": 0.23774750530719757, "max_return": 0.9509900212287903, "mean_motif_chained": 0.23774751247499998, "gnorm": 3.2378011383116245e-10, "elapsed_s": 5771.843255996704, "cell_type": "Ex", "edit_type": "cell_type_transfer", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999978542327881, "adv_min": -0.49999892711639404, "adv_max": 1.4999967813491821, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.23774751247499998, "comp_kd_mean": 0.0, "comp_total_mean": 0.23774751247499998, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
77
+ {"rl_step": 380, "loss": -1.4901161193847656e-08, "mean_return": 0.14701500535011292, "max_return": 0.5880600214004517, "mean_motif_chained": 0.14701499999999998, "gnorm": 2.764863893389702e-10, "elapsed_s": 5848.984304904938, "cell_type": "Ex", "edit_type": "promoter_retarget", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.999996542930603, "adv_min": -0.4999982714653015, "adv_max": 1.4999948740005493, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.14701499999999998, "comp_kd_mean": 0.0, "comp_total_mean": 0.14701499999999998, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
78
+ {"rl_step": 385, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 5926.952745914459, "cell_type": "Oli", "edit_type": "activity_boost", "target_tf": "OLIG2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
79
+ {"rl_step": 390, "loss": -1.4901161193847656e-08, "mean_return": 0.1715175062417984, "max_return": 0.6860700249671936, "mean_motif_chained": 0.1715175, "gnorm": 5.311449058353901e-10, "elapsed_s": 6003.586819410324, "cell_type": "OPC", "edit_type": "promoter_retarget", "target_tf": "OLIG2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999970197677612, "adv_min": -0.4999985098838806, "adv_max": 1.4999955892562866, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.1715175, "comp_kd_mean": 0.0, "comp_total_mean": 0.1715175, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
80
+ {"rl_step": 395, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 6079.074899196625, "cell_type": "Ast", "edit_type": "promoter_retarget", "target_tf": "NFIA", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
81
+ {"rl_step": 400, "loss": -1.4901161193847656e-08, "mean_return": 0.25, "max_return": 1.0, "mean_motif_chained": 0.25, "gnorm": 4.94765117764473e-10, "elapsed_s": 6154.8790147304535, "cell_type": "In", "edit_type": "cell_type_transfer", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 1.4901161193847656e-08, "adv_std": 0.9999979734420776, "adv_min": -0.4999989867210388, "adv_max": 1.4999970197677612, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.25, "comp_kd_mean": 0.0, "comp_total_mean": 0.25, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
82
+ {"rl_step": 405, "loss": 0.0, "mean_return": 0.3804152309894562, "max_return": 0.7684767842292786, "mean_motif_chained": 0.3804152318802, "gnorm": 1.9917933968827128e-10, "elapsed_s": 6231.501047134399, "cell_type": "Mic", "edit_type": "promoter_retarget", "target_tf": "SPI1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999977350234985, "adv_min": -0.8659359812736511, "adv_max": 0.8833412528038025, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.3804152318802, "comp_kd_mean": 0.0, "comp_total_mean": 0.3804152318802, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
83
+ {"rl_step": 410, "loss": 0.0, "mean_return": 0.16475902497768402, "max_return": 0.6590360999107361, "mean_motif_chained": 0.16475902614517499, "gnorm": 7.203198038041592e-10, "elapsed_s": 6306.233193159103, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "SOX10", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999969005584717, "adv_min": -0.49999845027923584, "adv_max": 1.4999953508377075, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.16475902614517499, "comp_kd_mean": 0.0, "comp_total_mean": 0.16475902614517499, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
84
+ {"rl_step": 415, "loss": 0.0, "mean_return": 0.14264850318431854, "max_return": 0.5705940127372742, "mean_motif_chained": 0.142648507485, "gnorm": 1.5825207810848951e-10, "elapsed_s": 6381.484443902969, "cell_type": "Ast", "edit_type": "cell_type_transfer", "target_tf": "DLX1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999964237213135, "adv_min": -0.49999821186065674, "adv_max": 1.4999946355819702, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.142648507485, "comp_kd_mean": 0.0, "comp_total_mean": 0.142648507485, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
85
+ {"rl_step": 420, "loss": 0.0, "mean_return": 0.1940598040819168, "max_return": 0.7762392163276672, "mean_motif_chained": 0.1940598, "gnorm": 4.18367562815547e-10, "elapsed_s": 6457.858404159546, "cell_type": "Mic", "edit_type": "promoter_retarget", "target_tf": "CEBPA", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999973773956299, "adv_min": -0.49999868869781494, "adv_max": 1.4999960660934448, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.1940598, "comp_kd_mean": 0.0, "comp_total_mean": 0.1940598, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
86
+ {"rl_step": 425, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 6534.807066917419, "cell_type": "Ex", "edit_type": "promoter_retarget", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
87
+ {"rl_step": 430, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 6611.5125432014465, "cell_type": "Mic", "edit_type": "activity_boost", "target_tf": "CEBPA", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
88
+ {"rl_step": 435, "loss": 0.0, "mean_return": 0.4780413508415222, "max_return": 0.9800999760627747, "mean_motif_chained": 0.47804133697674744, "gnorm": 3.383320290595293e-10, "elapsed_s": 6688.02632689476, "cell_type": "In", "edit_type": "activity_boost", "target_tf": "DLX2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999980926513672, "adv_min": -0.8654778003692627, "adv_max": 0.9089602828025818, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.47804133697674744, "comp_kd_mean": 0.0, "comp_total_mean": 0.47804133697674744, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
89
+ {"rl_step": 440, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 6764.77955532074, "cell_type": "Oli", "edit_type": "promoter_retarget", "target_tf": "MYRF", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
90
+ {"rl_step": 445, "loss": 1.4901161193847656e-08, "mean_return": 0.148499995470047, "max_return": 0.593999981880188, "mean_motif_chained": 0.1485, "gnorm": 8.985807653516531e-10, "elapsed_s": 6841.612484931946, "cell_type": "Ast", "edit_type": "cell_type_transfer", "target_tf": "OLIG2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.999996542930603, "adv_min": -0.4999983012676239, "adv_max": 1.4999948740005493, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.1485, "comp_kd_mean": 0.0, "comp_total_mean": 0.1485, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
91
+ {"rl_step": 450, "loss": 2.9802322387695312e-08, "mean_return": 0.23301634192466736, "max_return": 0.9320653676986694, "mean_motif_chained": 0.23301633697674748, "gnorm": 3.710738383233547e-10, "elapsed_s": 6918.0557513237, "cell_type": "In", "edit_type": "cell_type_transfer", "target_tf": "CEBPA", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -2.9802322387695312e-08, "adv_std": 0.9999977350234985, "adv_min": -0.49999892711639404, "adv_max": 1.4999966621398926, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.23301633697674748, "comp_kd_mean": 0.0, "comp_total_mean": 0.23301633697674748, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
92
+ {"rl_step": 455, "loss": 0.0, "mean_return": 0.5549588203430176, "max_return": 1.5198352336883545, "mean_motif_chained": 0.5549588046860485, "gnorm": 4.5656634029001e-10, "elapsed_s": 6993.855278015137, "cell_type": "Ex", "edit_type": "activity_boost", "target_tf": "NEUROD2", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999986290931702, "adv_min": -0.7676270008087158, "adv_max": 1.3346309661865234, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.5549588046860485, "comp_kd_mean": 0.0, "comp_total_mean": 0.5549588046860485, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
93
+ {"rl_step": 460, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 7070.867611646652, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "SOX6", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
94
+ {"rl_step": 465, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 7148.60272359848, "cell_type": "Oli", "edit_type": "activity_boost", "target_tf": "SOX10", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
95
+ {"rl_step": 470, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 7225.605459451675, "cell_type": "Ast", "edit_type": "activity_boost", "target_tf": "AP1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
96
+ {"rl_step": 475, "loss": 0.0, "mean_return": 0.14264850318431854, "max_return": 0.5705940127372742, "mean_motif_chained": 0.142648507485, "gnorm": 2.346496330574155e-10, "elapsed_s": 7303.189958572388, "cell_type": "Ast", "edit_type": "cell_type_transfer", "target_tf": "RORB", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999964237213135, "adv_min": -0.49999821186065674, "adv_max": 1.4999946355819702, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.142648507485, "comp_kd_mean": 0.0, "comp_total_mean": 0.142648507485, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
97
+ {"rl_step": 480, "loss": 1.4901161193847656e-08, "mean_return": 0.1979999989271164, "max_return": 0.7919999957084656, "mean_motif_chained": 0.198, "gnorm": 1.3096723705530167e-10, "elapsed_s": 7379.621014595032, "cell_type": "Mic", "edit_type": "activity_boost", "target_tf": "SPI1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999973773956299, "adv_min": -0.49999871850013733, "adv_max": 1.4999960660934448, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.198, "comp_kd_mean": 0.0, "comp_total_mean": 0.198, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
98
+ {"rl_step": 485, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 7457.02720952034, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "ASCL1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
99
+ {"rl_step": 490, "loss": 0.0, "mean_return": 0.0, "max_return": 0.0, "mean_motif_chained": 0.0, "gnorm": 0.0, "elapsed_s": 7533.513391971588, "cell_type": "Ast", "edit_type": "cell_type_transfer", "target_tf": "RUNX1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.0, "adv_min": 0.0, "adv_max": 0.0, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.0, "comp_kd_mean": 0.0, "comp_total_mean": 0.0, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
100
+ {"rl_step": 495, "loss": 1.4901161193847656e-08, "mean_return": 0.24014900624752045, "max_return": 0.9605960249900818, "mean_motif_chained": 0.2401490025, "gnorm": 4.0745362639427185e-10, "elapsed_s": 7610.9379160404205, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "ASCL1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": -1.4901161193847656e-08, "adv_std": 0.9999978542327881, "adv_min": -0.49999895691871643, "adv_max": 1.4999967813491821, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.2401490025, "comp_kd_mean": 0.0, "comp_total_mean": 0.2401490025, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
101
+ {"rl_step": 500, "loss": 0.0, "mean_return": 0.5804813504219055, "max_return": 2.321925401687622, "mean_motif_chained": 0.58048137675, "gnorm": 8.731149137020111e-10, "elapsed_s": 7687.488857269287, "cell_type": "OPC", "edit_type": "activity_boost", "target_tf": "ASCL1", "kd_active": false, "kd_tf": "", "kd_score_mean": 0.0, "ratio_mean": 1.0, "ratio_min": 1.0, "ratio_max": 1.0, "log_ratio_mean": 0.0, "adv_mean": 0.0, "adv_std": 0.9999992847442627, "adv_min": -0.49999964237213135, "adv_max": 1.499998927116394, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.58048137675, "comp_kd_mean": 0.0, "comp_total_mean": 0.58048137675, "_algo": "gspo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}