Upload exp_phase8_reasoning_grounded_rl_t2_r128_alpha1_s3_20260507_044835/log.jsonl with huggingface_hub
Browse files
exp_phase8_reasoning_grounded_rl_t2_r128_alpha1_s3_20260507_044835/log.jsonl
CHANGED
|
@@ -8,3 +8,14 @@
|
|
| 8 |
{"step": 35, "loss": -40.079402923583984, "mean_r": -0.29847222566604614, "max_r": 0.23999999463558197, "mean_grounded": 3.25, "mean_halluc": 8.0, "mean_cited": 11.5, "mean_tf_grounded_rate": 0.3173611111111111, "gnorm": 348.9560852050781, "elapsed_s": 1213.1267440319061, "cell": "Ast", "id": "train:pair_pos:Ast:TP73:chr1_3504030_3504530:1617"}
|
| 9 |
{"step": 40, "loss": -125.9754638671875, "mean_r": -0.47579625248908997, "max_r": -0.18000000715255737, "mean_grounded": 3.5, "mean_halluc": 13.5, "mean_cited": 17.5, "mean_tf_grounded_rate": 0.2349865047233468, "gnorm": 429.9833984375, "elapsed_s": 1385.5108399391174, "cell": "Ast", "id": "train:pair_pos:Ast:LGR4:chr11_27469948_27470448:3524"}
|
| 10 |
{"step": 45, "loss": -10.807151794433594, "mean_r": -0.5432597994804382, "max_r": -0.3499999940395355, "mean_grounded": 3.0, "mean_halluc": 13.5, "mean_cited": 16.75, "mean_tf_grounded_rate": 0.17790032679738563, "gnorm": 578.2479248046875, "elapsed_s": 1556.8942821025848, "cell": "Ast", "id": "train:pair_neg:Ast:ARHGAP4:chrX_154097524_154098024:787"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
{"step": 35, "loss": -40.079402923583984, "mean_r": -0.29847222566604614, "max_r": 0.23999999463558197, "mean_grounded": 3.25, "mean_halluc": 8.0, "mean_cited": 11.5, "mean_tf_grounded_rate": 0.3173611111111111, "gnorm": 348.9560852050781, "elapsed_s": 1213.1267440319061, "cell": "Ast", "id": "train:pair_pos:Ast:TP73:chr1_3504030_3504530:1617"}
|
| 9 |
{"step": 40, "loss": -125.9754638671875, "mean_r": -0.47579625248908997, "max_r": -0.18000000715255737, "mean_grounded": 3.5, "mean_halluc": 13.5, "mean_cited": 17.5, "mean_tf_grounded_rate": 0.2349865047233468, "gnorm": 429.9833984375, "elapsed_s": 1385.5108399391174, "cell": "Ast", "id": "train:pair_pos:Ast:LGR4:chr11_27469948_27470448:3524"}
|
| 10 |
{"step": 45, "loss": -10.807151794433594, "mean_r": -0.5432597994804382, "max_r": -0.3499999940395355, "mean_grounded": 3.0, "mean_halluc": 13.5, "mean_cited": 16.75, "mean_tf_grounded_rate": 0.17790032679738563, "gnorm": 578.2479248046875, "elapsed_s": 1556.8942821025848, "cell": "Ast", "id": "train:pair_neg:Ast:ARHGAP4:chrX_154097524_154098024:787"}
|
| 11 |
+
{"step": 50, "loss": -40.11273193359375, "mean_r": -0.3615546226501465, "max_r": -0.24705882370471954, "mean_grounded": 3.75, "mean_halluc": 11.25, "mean_cited": 15.25, "mean_tf_grounded_rate": 0.26330532212885155, "gnorm": 440.54449462890625, "elapsed_s": 1725.7594501972198, "cell": "Mic", "id": "train:pair_pos:Mic:SLC47A1:chr17_19646986_19647486:1271"}
|
| 12 |
+
{"step": 55, "loss": -103.248779296875, "mean_r": -0.5373015999794006, "max_r": -0.2666666805744171, "mean_grounded": 2.0, "mean_halluc": 11.0, "mean_cited": 13.75, "mean_tf_grounded_rate": 0.16865079365079366, "gnorm": 485.51129150390625, "elapsed_s": 1897.3484437465668, "cell": "In", "id": "train:pair_neg:In:DUS4L:chr7_107371596_107372096:1203"}
|
| 13 |
+
{"step": 60, "loss": 93.50972747802734, "mean_r": -0.5134809613227844, "max_r": -0.19230769574642181, "mean_grounded": 2.75, "mean_halluc": 10.75, "mean_cited": 13.75, "mean_tf_grounded_rate": 0.1892968142968143, "gnorm": 358.890869140625, "elapsed_s": 2062.1149344444275, "cell": "Ast", "id": "train:pair_pos:Ast:KLF17:chr1_44355047_44355547:3462"}
|
| 14 |
+
{"step": 65, "loss": 21.4892578125, "mean_r": -0.5664335489273071, "max_r": -0.3384615480899811, "mean_grounded": 2.75, "mean_halluc": 11.75, "mean_cited": 14.75, "mean_tf_grounded_rate": 0.1654195804195804, "gnorm": 379.0263977050781, "elapsed_s": 2235.889911174774, "cell": "Ast", "id": "train:pair_pos:Ast:CINP:chr14_102492168_102492668:2983"}
|
| 15 |
+
{"step": 70, "loss": -46.47312927246094, "mean_r": -0.38989901542663574, "max_r": 0.13333334028720856, "mean_grounded": 3.0, "mean_halluc": 9.0, "mean_cited": 12.5, "mean_tf_grounded_rate": 0.2537878787878788, "gnorm": 557.3974609375, "elapsed_s": 2410.0868854522705, "cell": "Ex", "id": "train:pair_neg:Ex:CGGBP1:chr3_88151371_88151871:2198"}
|
| 16 |
+
{"step": 75, "loss": -44.34358215332031, "mean_r": -0.1041666641831398, "max_r": 0.30000001192092896, "mean_grounded": 3.5, "mean_halluc": 6.0, "mean_cited": 10.0, "mean_tf_grounded_rate": 0.2503205128205128, "gnorm": 500.87811279296875, "elapsed_s": 2578.6072397232056, "cell": "Ast", "id": "train:pair_pos:Ast:SLC6A13:chr12_271133_271633:72"}
|
| 17 |
+
{"step": 80, "loss": -74.841796875, "mean_r": -0.17307692766189575, "max_r": 0.6000000238418579, "mean_grounded": 3.0, "mean_halluc": 6.0, "mean_cited": 9.25, "mean_tf_grounded_rate": 0.35645604395604397, "gnorm": 305.185302734375, "elapsed_s": 2751.0548832416534, "cell": "Ast", "id": "train:pair_pos:Ast:CFAP74:chr1_1920748_1921248:766"}
|
| 18 |
+
{"step": 85, "loss": -26.32306671142578, "mean_r": -0.4054762125015259, "max_r": -0.20000000298023224, "mean_grounded": 2.25, "mean_halluc": 6.75, "mean_cited": 9.5, "mean_tf_grounded_rate": 0.2089285714285714, "gnorm": 432.56768798828125, "elapsed_s": 2919.7268517017365, "cell": "In", "id": "train:pair_pos:In:PPRC1:chr10_101884994_101885494:3892"}
|
| 19 |
+
{"step": 90, "loss": 59.57316589355469, "mean_r": -0.029230769723653793, "max_r": 0.023076923564076424, "mean_grounded": 4.75, "mean_halluc": 6.75, "mean_cited": 11.5, "mean_tf_grounded_rate": 0.4115384615384615, "gnorm": 399.2134704589844, "elapsed_s": 3084.458697080612, "cell": "Ast", "id": "train:pair_pos:Ast:COPS7A:chr12_6527155_6527655:959"}
|
| 20 |
+
{"step": 95, "loss": -68.27378845214844, "mean_r": -0.4207359254360199, "max_r": -0.18000000715255737, "mean_grounded": 4.0, "mean_halluc": 15.5, "mean_cited": 20.0, "mean_tf_grounded_rate": 0.23564213564213565, "gnorm": 456.6268615722656, "elapsed_s": 3245.223747253418, "cell": "Ast", "id": "train:pair_pos:Ast:LRP4:chr11_47118852_47119352:1335"}
|
| 21 |
+
{"step": 100, "loss": -225.0859375, "mean_r": -0.4487878680229187, "max_r": 0.0, "mean_grounded": 1.5, "mean_halluc": 9.25, "mean_cited": 10.75, "mean_tf_grounded_rate": 0.1140151515151515, "gnorm": 478.38421630859375, "elapsed_s": 3415.2856843471527, "cell": "Ast", "id": "train:pair_pos:Ast:LRRC55:chr11_57211308_57211808:2019"}
|