explcre commited on
Commit
440e39f
·
verified ·
1 Parent(s): ab26b8a

Upload cycle_70_lab_L0/exp_rl_pathb_650m_FULL_AUDIT_dapo_20260506_125418/log.jsonl with huggingface_hub

Browse files
cycle_70_lab_L0/exp_rl_pathb_650m_FULL_AUDIT_dapo_20260506_125418/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": 1.30385160446167e-07, "elapsed_s": 15.895693302154541, "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": "dapo", "_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": 6.193295121192932e-08, "elapsed_s": 75.98063206672668, "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": "dapo", "_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": 152.07159757614136, "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": "dapo", "_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": 2.4959444999694824e-07, "elapsed_s": 227.79497814178467, "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": "dapo", "_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": 301.67310428619385, "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": "dapo", "_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": 379.58271622657776, "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": "dapo", "_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": 456.30100870132446, "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": "dapo", "_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": 1.3597309589385986e-07, "elapsed_s": 532.4019732475281, "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": "dapo", "_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": 1.2945383787155151e-07, "elapsed_s": 608.4167349338531, "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": "dapo", "_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": 683.3945028781891, "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": "dapo", "_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": 1.7601996660232544e-07, "elapsed_s": 760.3970696926117, "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": "dapo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
12
+ {"rl_step": 55, "loss": -1.4901161193847656e-08, "mean_return": 0.13980980217456818, "max_return": 0.5592392086982727, "mean_motif_chained": 0.1398098021860485, "gnorm": 3.688037395477295e-07, "elapsed_s": 835.2729384899139, "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": 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": "dapo", "_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": 909.8917016983032, "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": "dapo", "_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": 6.007030606269836e-08, "elapsed_s": 985.4821529388428, "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": "dapo", "_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": 2.6263296604156494e-07, "elapsed_s": 1060.5220108032227, "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": "dapo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
16
+ {"rl_step": 75, "loss": -4.470348358154297e-08, "mean_return": 1.0004010200500488, "max_return": 2.368591070175171, "mean_motif_chained": 1.0004010771104705, "gnorm": 2.4959444999694824e-07, "elapsed_s": 1136.5436000823975, "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": 4.470348358154297e-08, "adv_std": 0.9999991655349731, "adv_min": -0.8381659388542175, "adv_max": 1.146310567855835, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 1.0004010771104705, "comp_kd_mean": 0.0, "comp_total_mean": 1.0004010771104705, "_algo": "dapo", "_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": 1213.0445828437805, "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": "dapo", "_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": 4.0745362639427185e-08, "elapsed_s": 1289.786218881607, "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": "dapo", "_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": 1367.3933210372925, "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": "dapo", "_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": 1.0384246706962585e-07, "elapsed_s": 1444.2256209850311, "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": "dapo", "_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": 1520.557272195816, "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": "dapo", "_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": 1.4994293451309204e-07, "elapsed_s": 1601.3000400066376, "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": "dapo", "_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": 1.0849907994270325e-07, "elapsed_s": 1678.692269563675, "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": "dapo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
24
+ {"rl_step": 115, "loss": -1.4901161193847656e-08, "mean_return": 0.43237051367759705, "max_return": 0.593999981880188, "mean_motif_chained": 0.43237052989515, "gnorm": 1.8719583749771118e-07, "elapsed_s": 1755.5829014778137, "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": 1.4901161193847656e-08, "adv_std": 0.9999964833259583, "adv_min": -1.4985647201538086, "adv_max": 0.5601959824562073, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.43237052989515, "comp_kd_mean": 0.0, "comp_total_mean": 0.43237052989515, "_algo": "dapo", "_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": 7.264316082000732e-08, "elapsed_s": 1831.678899049759, "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": "dapo", "_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": 4.470348358154297e-07, "elapsed_s": 1907.682400226593, "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": "dapo", "_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": 1.043081283569336e-07, "elapsed_s": 1982.4776012897491, "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": "dapo", "_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": 2058.613122701645, "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": "dapo", "_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": 9.546056389808655e-08, "elapsed_s": 2134.6565494537354, "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": "dapo", "_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": 6.845220923423767e-08, "elapsed_s": 2210.9988436698914, "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": "dapo", "_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": 1.94646418094635e-07, "elapsed_s": 2287.8706181049347, "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": "dapo", "_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": 9.452924132347107e-08, "elapsed_s": 2364.2531232833862, "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": "dapo", "_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": 2439.9107508659363, "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": "dapo", "_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": 1.3969838619232178e-07, "elapsed_s": 2516.273209810257, "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": "dapo", "_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": 2594.3551633358, "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": "dapo", "_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": 0.598790168762207, "max_return": 1.6495083570480347, "mean_motif_chained": 0.598790144581398, "gnorm": 9.266659617424011e-08, "elapsed_s": 2671.4817283153534, "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": 0.9999986290931702, "adv_min": -0.7640295624732971, "adv_max": 1.3406695127487183, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.598790144581398, "comp_kd_mean": 0.0, "comp_total_mean": 0.598790144581398, "_algo": "dapo", "_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": 2747.915589094162, "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": "dapo", "_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": 2824.039976835251, "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": "dapo", "_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": 1.6205012798309326e-07, "elapsed_s": 2899.409233570099, "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": "dapo", "_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": 1.6577541828155518e-07, "elapsed_s": 2975.271998643875, "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": "dapo", "_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": 2.9243528842926025e-07, "elapsed_s": 3052.0582387447357, "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": "dapo", "_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": 1.0803341865539551e-07, "elapsed_s": 3132.20107793808, "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": "dapo", "_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": 3208.6527230739594, "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": "dapo", "_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": 3285.293860912323, "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": "dapo", "_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": 2.7194619178771973e-07, "elapsed_s": 3361.9979417324066, "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": "dapo", "_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": 3438.6020007133484, "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": "dapo", "_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": 3.7066638469696045e-07, "elapsed_s": 3515.217390537262, "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": "dapo", "_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": 3591.605806350708, "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": "dapo", "_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": 3668.0228855609894, "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": "dapo", "_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": 1.0291114449501038e-07, "elapsed_s": 3745.0616748332977, "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": "dapo", "_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": 3820.687299013138, "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": "dapo", "_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": 1.2759119272232056e-07, "elapsed_s": 3896.980417251587, "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": "dapo", "_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": 1.2386590242385864e-07, "elapsed_s": 3973.0262558460236, "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": "dapo", "_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": 2.3562461137771606e-07, "elapsed_s": 4049.226441383362, "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": "dapo", "_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": 4125.4912545681, "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": "dapo", "_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": 2.5331974029541016e-07, "elapsed_s": 4201.928035974503, "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": "dapo", "_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": 4278.135037183762, "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": "dapo", "_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": 2.980232238769531e-07, "elapsed_s": 4355.354580163956, "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": "dapo", "_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": 1.1362135410308838e-07, "elapsed_s": 4431.8136558532715, "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": "dapo", "_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": 1.9650906324386597e-07, "elapsed_s": 4508.723151922226, "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": "dapo", "_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": 4584.930492401123, "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": "dapo", "_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": 5.885958671569824e-07, "elapsed_s": 4663.595397949219, "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": "dapo", "_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": 2.2724270820617676e-07, "elapsed_s": 4739.836363554001, "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": "dapo", "_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": 4816.319988012314, "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": "dapo", "_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": 4892.4756009578705, "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": "dapo", "_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": 4968.981847524643, "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": "dapo", "_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": 5.4016709327697754e-08, "elapsed_s": 5044.689874410629, "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": "dapo", "_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": 7.683411240577698e-08, "elapsed_s": 5122.089679002762, "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": "dapo", "_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": 3.0919909477233887e-07, "elapsed_s": 5198.569212198257, "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": "dapo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
70
+ {"rl_step": 345, "loss": 2.9802322387695312e-08, "mean_return": 0.8357504606246948, "max_return": 1.977308750152588, "mean_motif_chained": 0.8357504322499464, "gnorm": 1.1920928955078125e-07, "elapsed_s": 5274.817476272583, "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": -2.9802322387695312e-08, "adv_std": 0.9999988675117493, "adv_min": -1.011271357536316, "adv_max": 1.3813036680221558, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.8357504322499464, "comp_kd_mean": 0.0, "comp_total_mean": 0.8357504322499464, "_algo": "dapo", "_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": 2.551823854446411e-07, "elapsed_s": 5350.962110519409, "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": "dapo", "_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": 1.4994293451309204e-07, "elapsed_s": 5427.3952605724335, "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": "dapo", "_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": 4.805624485015869e-07, "elapsed_s": 5504.417934656143, "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": "dapo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
74
+ {"rl_step": 365, "loss": -0.0, "mean_return": 0.16475902497768402, "max_return": 0.6590360999107361, "mean_motif_chained": 0.16475902614517499, "gnorm": 5.51808625459671e-08, "elapsed_s": 5580.758509635925, "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": 0.9999969005584717, "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": "dapo", "_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": 3.5762786865234375e-07, "elapsed_s": 5657.197140216827, "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": "dapo", "_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": 2.2444874048233032e-07, "elapsed_s": 5733.643729686737, "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": "dapo", "_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": 9.918585419654846e-08, "elapsed_s": 5809.74015879631, "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": "dapo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
78
+ {"rl_step": 385, "loss": -1.4901161193847656e-08, "mean_return": 0.1664232611656189, "max_return": 0.6656930446624756, "mean_motif_chained": 0.16642325873249997, "gnorm": 4.0745362639427185e-08, "elapsed_s": 5886.7190527915955, "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": 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": "dapo", "_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": 1.9185245037078857e-07, "elapsed_s": 5964.129460811615, "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": "dapo", "_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": 6041.255129337311, "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": "dapo", "_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": 1.7881393432617188e-07, "elapsed_s": 6117.820358276367, "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": "dapo", "_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": 7.171183824539185e-08, "elapsed_s": 6196.116897821426, "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": "dapo", "_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": 2.5890767574310303e-07, "elapsed_s": 6273.064306259155, "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": "dapo", "_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": 7.636845111846924e-08, "elapsed_s": 6349.050188541412, "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": "dapo", "_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": 1.5087425708770752e-07, "elapsed_s": 6425.641521930695, "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": "dapo", "_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": 6500.692535638809, "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": "dapo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}
87
+ {"rl_step": 430, "loss": -1.4901161193847656e-08, "mean_return": 0.18641306459903717, "max_return": 0.7456522583961487, "mean_motif_chained": 0.186413069581398, "gnorm": 1.5459954738616943e-07, "elapsed_s": 6576.310992479324, "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": 1.4901161193847656e-08, "adv_std": 0.9999972581863403, "adv_min": -0.49999862909317017, "adv_max": 1.4999959468841553, "comp_oracle_mean": 0.0, "comp_motif_chained_mean": 0.186413069581398, "comp_kd_mean": 0.0, "comp_total_mean": 0.186413069581398, "_algo": "dapo", "_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": 1.2200325727462769e-07, "elapsed_s": 6652.277729511261, "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": "dapo", "_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": 6727.261120557785, "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": "dapo", "_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": 3.241002559661865e-07, "elapsed_s": 6802.541219472885, "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": "dapo", "_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": 1.341104507446289e-07, "elapsed_s": 6877.050581455231, "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": "dapo", "_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": 1.6391277313232422e-07, "elapsed_s": 6953.063942909241, "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": "dapo", "_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": 7028.706217050552, "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": "dapo", "_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": 7103.761791229248, "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": "dapo", "_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": 7178.95866727829, "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": "dapo", "_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": 1.0104849934577942e-07, "elapsed_s": 7254.8750677108765, "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": "dapo", "_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": 4.7264620661735535e-08, "elapsed_s": 7330.312329053879, "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": "dapo", "_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": 7404.106880187988, "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": "dapo", "_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": 7477.820140123367, "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": "dapo", "_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": 1.4621764421463013e-07, "elapsed_s": 7552.905421495438, "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": "dapo", "_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": 3.129243850708008e-07, "elapsed_s": 7627.530157089233, "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": "dapo", "_lora_r": 16, "_peak_lr": 1e-05, "_temperature": 1.0, "_seq_len_mean": 360.0}