explcre commited on
Commit
ff32fef
·
verified ·
1 Parent(s): 005ca17

Upload exp_phase8_reasoning_grounded_rl_t3_r128_alpha1_s3_par_20260507_005010/log.jsonl with huggingface_hub

Browse files
exp_phase8_reasoning_grounded_rl_t3_r128_alpha1_s3_par_20260507_005010/log.jsonl CHANGED
@@ -46,3 +46,6 @@
46
  {"step": 225, "loss": -34.14190673828125, "mean_r": -0.253104567527771, "max_r": 0.644444465637207, "mean_grounded": 2.5, "mean_halluc": 5.75, "mean_cited": 9.75, "mean_tf_grounded_rate": 0.23161764705882354, "gnorm": 279.35235595703125, "elapsed_s": 8301.501113891602, "cell": "OPC", "id": "train:edit:OPC:BEST3:chr12_69738518_69739018:3436"}
47
  {"step": 230, "loss": 24.967952728271484, "mean_r": 0.1071428582072258, "max_r": 0.4285714328289032, "mean_grounded": 1.75, "mean_halluc": 1.0, "mean_cited": 3.0, "mean_tf_grounded_rate": 0.2785714285714286, "gnorm": 253.17576599121094, "elapsed_s": 8492.115145921707, "cell": "OPC", "id": "train:edit:OPC:PARD6B:chr20_50638318_50638818:3787"}
48
  {"step": 235, "loss": 0.0, "mean_r": 0.0, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 0.0, "mean_cited": 0.0, "mean_tf_grounded_rate": 0.0, "gnorm": 0.0, "elapsed_s": 8683.170018196106, "cell": "Ex", "id": "train:edit:Ex:TRPC3:chr4_121785286_121785786:52"}
 
 
 
 
46
  {"step": 225, "loss": -34.14190673828125, "mean_r": -0.253104567527771, "max_r": 0.644444465637207, "mean_grounded": 2.5, "mean_halluc": 5.75, "mean_cited": 9.75, "mean_tf_grounded_rate": 0.23161764705882354, "gnorm": 279.35235595703125, "elapsed_s": 8301.501113891602, "cell": "OPC", "id": "train:edit:OPC:BEST3:chr12_69738518_69739018:3436"}
47
  {"step": 230, "loss": 24.967952728271484, "mean_r": 0.1071428582072258, "max_r": 0.4285714328289032, "mean_grounded": 1.75, "mean_halluc": 1.0, "mean_cited": 3.0, "mean_tf_grounded_rate": 0.2785714285714286, "gnorm": 253.17576599121094, "elapsed_s": 8492.115145921707, "cell": "OPC", "id": "train:edit:OPC:PARD6B:chr20_50638318_50638818:3787"}
48
  {"step": 235, "loss": 0.0, "mean_r": 0.0, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 0.0, "mean_cited": 0.0, "mean_tf_grounded_rate": 0.0, "gnorm": 0.0, "elapsed_s": 8683.170018196106, "cell": "Ex", "id": "train:edit:Ex:TRPC3:chr4_121785286_121785786:52"}
49
+ {"step": 240, "loss": -135.12905883789062, "mean_r": -0.19423076510429382, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 3.0, "mean_cited": 3.25, "mean_tf_grounded_rate": 0.0, "gnorm": 396.4239501953125, "elapsed_s": 8873.615556955338, "cell": "Oli", "id": "train:edit:Oli:HAT1:chr2_171724201_171724701:2033"}
50
+ {"step": 245, "loss": -53.132720947265625, "mean_r": 0.23157894611358643, "max_r": 1.0, "mean_grounded": 2.25, "mean_halluc": 2.5, "mean_cited": 5.25, "mean_tf_grounded_rate": 0.34210526315789475, "gnorm": 266.11883544921875, "elapsed_s": 9064.515143871307, "cell": "OPC", "id": "train:edit:OPC:HIST1H3D:chr6_26156896_26157396:3548"}
51
+ {"step": 250, "loss": -3.550837516784668, "mean_r": -0.5, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 0.5, "mean_cited": 0.5, "mean_tf_grounded_rate": 0.0, "gnorm": 106.78069305419922, "elapsed_s": 9255.234219312668, "cell": "In", "id": "train:edit:In:MSRB1:chr16_2175258_2175758:2619"}