explcre commited on
Commit
94cfd1a
·
verified ·
1 Parent(s): e2f7a41

Upload exp_phase8_t3_rl_edit_tight_dapo_s4_lr1e3_moods_20260506_122916/log.jsonl with huggingface_hub

Browse files
exp_phase8_t3_rl_edit_tight_dapo_s4_lr1e3_moods_20260506_122916/log.jsonl CHANGED
@@ -21,3 +21,21 @@
21
  {"rl_step": 100, "loss": -0.0, "mean_return": 31.89751434326172, "max_return": 44.17169189453125, "mean_motif_chained": 31.897514009406457, "gnorm": 0.294921875, "elapsed_s": 720.5810406208038, "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": 0.9999999403953552, "adv_min": -1.111053705215454, "adv_max": 1.28877854347229, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 31.897514009406457, "comp_kd_mean": 0.0, "comp_total_mean": 31.897514009406457, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
22
  {"rl_step": 105, "loss": -4.470348358154297e-08, "mean_return": 35.681861877441406, "max_return": 49.16248321533203, "mean_motif_chained": 35.681861937490226, "gnorm": 0.392578125, "elapsed_s": 758.5110919475555, "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": 4.470348358154297e-08, "adv_std": 0.9999998807907104, "adv_min": -1.001353144645691, "adv_max": 0.958949863910675, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 35.681861937490226, "comp_kd_mean": 0.0, "comp_total_mean": 35.681861937490226, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
23
  {"rl_step": 110, "loss": -1.1920928955078125e-07, "mean_return": 49.704811096191406, "max_return": 59.88700485229492, "mean_motif_chained": 49.70481349978243, "gnorm": 0.27734375, "elapsed_s": 796.2095334529877, "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": 1.1920928955078125e-07, "adv_std": 0.9999997615814209, "adv_min": -1.4950388669967651, "adv_max": 0.5588927865028381, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 49.70481349978243, "comp_kd_mean": 0.0, "comp_total_mean": 49.70481349978243, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  {"rl_step": 100, "loss": -0.0, "mean_return": 31.89751434326172, "max_return": 44.17169189453125, "mean_motif_chained": 31.897514009406457, "gnorm": 0.294921875, "elapsed_s": 720.5810406208038, "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": 0.9999999403953552, "adv_min": -1.111053705215454, "adv_max": 1.28877854347229, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 31.897514009406457, "comp_kd_mean": 0.0, "comp_total_mean": 31.897514009406457, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
22
  {"rl_step": 105, "loss": -4.470348358154297e-08, "mean_return": 35.681861877441406, "max_return": 49.16248321533203, "mean_motif_chained": 35.681861937490226, "gnorm": 0.392578125, "elapsed_s": 758.5110919475555, "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": 4.470348358154297e-08, "adv_std": 0.9999998807907104, "adv_min": -1.001353144645691, "adv_max": 0.958949863910675, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 35.681861937490226, "comp_kd_mean": 0.0, "comp_total_mean": 35.681861937490226, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
23
  {"rl_step": 110, "loss": -1.1920928955078125e-07, "mean_return": 49.704811096191406, "max_return": 59.88700485229492, "mean_motif_chained": 49.70481349978243, "gnorm": 0.27734375, "elapsed_s": 796.2095334529877, "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": 1.1920928955078125e-07, "adv_std": 0.9999997615814209, "adv_min": -1.4950388669967651, "adv_max": 0.5588927865028381, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 49.70481349978243, "comp_kd_mean": 0.0, "comp_total_mean": 49.70481349978243, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
24
+ {"rl_step": 115, "loss": 1.1920928955078125e-07, "mean_return": 39.604740142822266, "max_return": 58.31510925292969, "mean_motif_chained": 39.604738367216456, "gnorm": 0.1826171875, "elapsed_s": 833.6086585521698, "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": -1.1920928955078125e-07, "adv_std": 0.9999998807907104, "adv_min": -0.9196491241455078, "adv_max": 1.1302263736724854, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 39.604738367216456, "comp_kd_mean": 0.0, "comp_total_mean": 39.604738367216456, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
25
+ {"rl_step": 120, "loss": 2.086162567138672e-07, "mean_return": 41.857093811035156, "max_return": 52.136817932128906, "mean_motif_chained": 41.857091399248894, "gnorm": 0.294921875, "elapsed_s": 870.1843650341034, "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": -2.086162567138672e-07, "adv_std": 0.9999998807907104, "adv_min": -1.1945135593414307, "adv_max": 1.0369818210601807, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 41.857091399248894, "comp_kd_mean": 0.0, "comp_total_mean": 41.857091399248894, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
26
+ {"rl_step": 125, "loss": -5.960464477539063e-08, "mean_return": 39.21538543701172, "max_return": 50.920509338378906, "mean_motif_chained": 39.21538610163996, "gnorm": 0.359375, "elapsed_s": 906.5989780426025, "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": 5.960464477539063e-08, "adv_std": 1.0, "adv_min": -0.8992832899093628, "adv_max": 1.2388920783996582, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 39.21538610163996, "comp_kd_mean": 0.0, "comp_total_mean": 39.21538610163996, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
27
+ {"rl_step": 130, "loss": -0.0, "mean_return": 54.66227722167969, "max_return": 75.46034240722656, "mean_motif_chained": 54.66227785734188, "gnorm": 0.703125, "elapsed_s": 943.2716536521912, "cell_type": "Oli", "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": 0.0, "adv_std": 1.0, "adv_min": -1.0512384176254272, "adv_max": 1.288304090499878, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 54.66227785734188, "comp_kd_mean": 0.0, "comp_total_mean": 54.66227785734188, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
28
+ {"rl_step": 135, "loss": -5.960464477539063e-08, "mean_return": 51.397315979003906, "max_return": 93.5654296875, "mean_motif_chained": 51.397317694938714, "gnorm": 0.3515625, "elapsed_s": 979.6107702255249, "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": 5.960464477539063e-08, "adv_std": 0.9999998807907104, "adv_min": -0.763938307762146, "adv_max": 1.3431551456451416, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 51.397317694938714, "comp_kd_mean": 0.0, "comp_total_mean": 51.397317694938714, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
29
+ {"rl_step": 140, "loss": -0.0, "mean_return": 52.217857360839844, "max_return": 64.35848999023438, "mean_motif_chained": 52.217857836980926, "gnorm": 0.48828125, "elapsed_s": 1016.7701027393341, "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": 0.9999998211860657, "adv_min": -1.1302086114883423, "adv_max": 1.3030050992965698, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 52.217857836980926, "comp_kd_mean": 0.0, "comp_total_mean": 52.217857836980926, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
30
+ {"rl_step": 145, "loss": -1.043081283569336e-07, "mean_return": 56.52188491821289, "max_return": 83.02656555175781, "mean_motif_chained": 56.52188626966944, "gnorm": 0.546875, "elapsed_s": 1054.7148506641388, "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": 1.043081283569336e-07, "adv_std": 0.9999998211860657, "adv_min": -0.7694108486175537, "adv_max": 1.4409332275390625, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 56.52188626966944, "comp_kd_mean": 0.0, "comp_total_mean": 56.52188626966944, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
31
+ {"rl_step": 150, "loss": 1.7881393432617188e-07, "mean_return": 48.253692626953125, "max_return": 62.202117919921875, "mean_motif_chained": 48.25369073576791, "gnorm": 0.64453125, "elapsed_s": 1092.5410690307617, "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": -1.7881393432617188e-07, "adv_std": 0.9999998807907104, "adv_min": -0.8983544111251831, "adv_max": 1.4316812753677368, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 48.25369073576791, "comp_kd_mean": 0.0, "comp_total_mean": 48.25369073576791, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
32
+ {"rl_step": 155, "loss": -1.1920928955078125e-07, "mean_return": 46.937225341796875, "max_return": 55.74527359008789, "mean_motif_chained": 46.93722680608913, "gnorm": 0.64453125, "elapsed_s": 1129.904503583908, "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": 1.1920928955078125e-07, "adv_std": 0.9999998211860657, "adv_min": -1.167506217956543, "adv_max": 1.0263886451721191, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 46.93722680608913, "comp_kd_mean": 0.0, "comp_total_mean": 46.93722680608913, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
33
+ {"rl_step": 160, "loss": 4.470348358154297e-08, "mean_return": 31.242626190185547, "max_return": 40.59311294555664, "mean_motif_chained": 31.242624678899432, "gnorm": 0.64453125, "elapsed_s": 1167.072722196579, "cell_type": "OPC", "edit_type": "cell_type_transfer", "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": -4.470348358154297e-08, "adv_std": 0.9999998807907104, "adv_min": -1.1349283456802368, "adv_max": 0.9825686812400818, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 31.242624678899432, "comp_kd_mean": 0.0, "comp_total_mean": 31.242624678899432, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
34
+ {"rl_step": 165, "loss": 6.705522537231445e-08, "mean_return": 53.68891906738281, "max_return": 72.38694763183594, "mean_motif_chained": 53.68891764768969, "gnorm": 0.412109375, "elapsed_s": 1203.5966317653656, "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": -6.705522537231445e-08, "adv_std": 0.9999999403953552, "adv_min": -0.9942580461502075, "adv_max": 1.3875130414962769, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 53.68891764768969, "comp_kd_mean": 0.0, "comp_total_mean": 53.68891764768969, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
35
+ {"rl_step": 170, "loss": -2.9802322387695312e-08, "mean_return": 36.16437911987305, "max_return": 52.01883316040039, "mean_motif_chained": 36.16437883772568, "gnorm": 0.44140625, "elapsed_s": 1240.291983127594, "cell_type": "Ex", "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": 2.9802322387695312e-08, "adv_std": 1.0, "adv_min": -0.7329949140548706, "adv_max": 1.420209288597107, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 36.16437883772568, "comp_kd_mean": 0.0, "comp_total_mean": 36.16437883772568, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
36
+ {"rl_step": 175, "loss": 1.1920928955078125e-07, "mean_return": 32.68248748779297, "max_return": 47.30067443847656, "mean_motif_chained": 32.68248583373449, "gnorm": 0.4609375, "elapsed_s": 1276.9024362564087, "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": -1.1920928955078125e-07, "adv_std": 0.9999998211860657, "adv_min": -0.9803750514984131, "adv_max": 0.888165295124054, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 32.68248583373449, "comp_kd_mean": 0.0, "comp_total_mean": 32.68248583373449, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
37
+ {"rl_step": 180, "loss": -2.2351741790771484e-07, "mean_return": 41.21630096435547, "max_return": 49.6649169921875, "mean_motif_chained": 41.21630222637522, "gnorm": 0.8359375, "elapsed_s": 1314.3564131259918, "cell_type": "Oli", "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": 2.2351741790771484e-07, "adv_std": 0.9999999403953552, "adv_min": -0.9896435141563416, "adv_max": 0.9777083992958069, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 41.21630222637522, "comp_kd_mean": 0.0, "comp_total_mean": 41.21630222637522, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
38
+ {"rl_step": 185, "loss": 8.940696716308594e-08, "mean_return": 53.76017379760742, "max_return": 85.01861572265625, "mean_motif_chained": 53.76017188580995, "gnorm": 0.474609375, "elapsed_s": 1352.659253835678, "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": -8.940696716308594e-08, "adv_std": 0.9999998807907104, "adv_min": -0.9685730934143066, "adv_max": 1.401299238204956, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 53.76017188580995, "comp_kd_mean": 0.0, "comp_total_mean": 53.76017188580995, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
39
+ {"rl_step": 190, "loss": -1.4901161193847656e-07, "mean_return": 70.84114074707031, "max_return": 118.18679809570312, "mean_motif_chained": 70.84114525957843, "gnorm": 0.62109375, "elapsed_s": 1390.0189054012299, "cell_type": "Oli", "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": 1.4901161193847656e-07, "adv_std": 1.0, "adv_min": -0.7812666296958923, "adv_max": 1.4659440517425537, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 70.84114525957843, "comp_kd_mean": 0.0, "comp_total_mean": 70.84114525957843, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
40
+ {"rl_step": 195, "loss": -1.043081283569336e-07, "mean_return": 76.26332092285156, "max_return": 102.06118774414062, "mean_motif_chained": 76.26332358721118, "gnorm": 0.58984375, "elapsed_s": 1426.8592348098755, "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": 1.043081283569336e-07, "adv_std": 0.9999998807907104, "adv_min": -0.9173049926757812, "adv_max": 1.379887342453003, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 76.26332358721118, "comp_kd_mean": 0.0, "comp_total_mean": 76.26332358721118, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}
41
+ {"rl_step": 200, "loss": 8.940696716308594e-08, "mean_return": 58.05101013183594, "max_return": 69.31622314453125, "mean_motif_chained": 58.051009823273894, "gnorm": 1.0234375, "elapsed_s": 1463.3315212726593, "cell_type": "Ex", "edit_type": "promoter_retarget", "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": -8.940696716308594e-08, "adv_std": 0.9999998807907104, "adv_min": -0.873903214931488, "adv_max": 1.0616899728775024, "comp_oracle_mean": 0.0, "comp_moods_chained_mean": 58.051009823273894, "comp_kd_mean": 0.0, "comp_total_mean": 58.051009823273894, "_algo": "dapo", "_lora_r": 16, "_peak_lr": 0.001, "_temperature": 1.0, "_seq_len_mean": 360.0}