Files
pi07-minimal-validation/outputs/overfit/training_history.json
T
2026-07-12 00:52:00 +08:00

459 lines
8.8 KiB
JSON

[
{
"stage": "goal",
"step": 1,
"loss": 1.0040572881698608
},
{
"stage": "goal",
"step": 20,
"loss": 0.34230467677116394
},
{
"stage": "goal",
"step": 40,
"loss": 0.37451064586639404
},
{
"stage": "goal",
"step": 60,
"loss": 0.26792070269584656
},
{
"stage": "goal",
"step": 80,
"loss": 0.10219617933034897
},
{
"stage": "goal",
"step": 100,
"loss": 0.2711445987224579
},
{
"stage": "goal",
"step": 120,
"loss": 0.2289590686559677
},
{
"stage": "goal",
"step": 140,
"loss": 0.36456483602523804
},
{
"stage": "goal",
"step": 160,
"loss": 0.0842418223619461
},
{
"stage": "goal",
"step": 180,
"loss": 0.9889341592788696
},
{
"stage": "goal",
"step": 200,
"loss": 0.5776903629302979
},
{
"stage": "goal",
"step": 220,
"loss": 0.44620272517204285
},
{
"stage": "goal",
"step": 240,
"loss": 0.05634145438671112
},
{
"stage": "goal",
"step": 260,
"loss": 0.05701519176363945
},
{
"stage": "goal",
"step": 280,
"loss": 0.06764699518680573
},
{
"stage": "goal",
"step": 300,
"loss": 0.10973378270864487
},
{
"stage": "high_level",
"step": 1,
"loss": 76.15934753417969
},
{
"stage": "high_level",
"step": 20,
"loss": -0.0
},
{
"stage": "high_level",
"step": 40,
"loss": -0.0
},
{
"stage": "high_level",
"step": 60,
"loss": -0.0
},
{
"stage": "high_level",
"step": 80,
"loss": -0.0
},
{
"stage": "high_level",
"step": 100,
"loss": -0.0
},
{
"stage": "high_level",
"step": 120,
"loss": -0.0
},
{
"stage": "high_level",
"step": 140,
"loss": -0.0
},
{
"stage": "high_level",
"step": 160,
"loss": -0.0
},
{
"stage": "high_level",
"step": 180,
"loss": -0.0
},
{
"stage": "high_level",
"step": 200,
"loss": -0.0
},
{
"stage": "policy",
"step": 1,
"loss": 51.04338836669922,
"text_loss": 44.21609115600586,
"flow_loss": 3.4136481285095215
},
{
"stage": "policy",
"step": 20,
"loss": 26.20608901977539,
"text_loss": 5.128565311431885,
"flow_loss": 10.538762092590332
},
{
"stage": "policy",
"step": 40,
"loss": 13.018914222717285,
"text_loss": 3.846059799194336,
"flow_loss": 4.586427211761475
},
{
"stage": "policy",
"step": 60,
"loss": 11.344329833984375,
"text_loss": 3.335771083831787,
"flow_loss": 4.004279136657715
},
{
"stage": "policy",
"step": 80,
"loss": 6.586862087249756,
"text_loss": 2.5455708503723145,
"flow_loss": 2.0206456184387207
},
{
"stage": "policy",
"step": 100,
"loss": 11.200895309448242,
"text_loss": 2.1739449501037598,
"flow_loss": 4.513474941253662
},
{
"stage": "policy",
"step": 120,
"loss": 17.273035049438477,
"text_loss": 2.1746408939361572,
"flow_loss": 7.549196720123291
},
{
"stage": "policy",
"step": 140,
"loss": 11.353687286376953,
"text_loss": 2.2218563556671143,
"flow_loss": 4.565915584564209
},
{
"stage": "policy",
"step": 160,
"loss": 14.110220909118652,
"text_loss": 2.3123977184295654,
"flow_loss": 5.898911476135254
},
{
"stage": "policy",
"step": 180,
"loss": 19.999370574951172,
"text_loss": 2.749119997024536,
"flow_loss": 8.62512493133545
},
{
"stage": "policy",
"step": 200,
"loss": 8.102465629577637,
"text_loss": 1.631801962852478,
"flow_loss": 3.2353317737579346
},
{
"stage": "policy",
"step": 220,
"loss": 21.903854370117188,
"text_loss": 1.6063504219055176,
"flow_loss": 10.148752212524414
},
{
"stage": "policy",
"step": 240,
"loss": 10.197904586791992,
"text_loss": 1.5640149116516113,
"flow_loss": 4.3169450759887695
},
{
"stage": "policy",
"step": 260,
"loss": 6.899936676025391,
"text_loss": 1.3081820011138916,
"flow_loss": 2.795877456665039
},
{
"stage": "policy",
"step": 280,
"loss": 10.051774978637695,
"text_loss": 1.2130903005599976,
"flow_loss": 4.419342517852783
},
{
"stage": "policy",
"step": 300,
"loss": 7.963553428649902,
"text_loss": 1.1586928367614746,
"flow_loss": 3.402430295944214
},
{
"stage": "policy",
"step": 320,
"loss": 5.177718639373779,
"text_loss": 1.2673476934432983,
"flow_loss": 1.9551855325698853
},
{
"stage": "policy",
"step": 340,
"loss": 4.487771034240723,
"text_loss": 1.0361082553863525,
"flow_loss": 1.7258312702178955
},
{
"stage": "policy",
"step": 360,
"loss": 4.356203556060791,
"text_loss": 1.3223515748977661,
"flow_loss": 1.5169259309768677
},
{
"stage": "policy",
"step": 380,
"loss": 5.289548397064209,
"text_loss": 1.4994667768478394,
"flow_loss": 1.89504075050354
},
{
"stage": "policy",
"step": 400,
"loss": 8.761286735534668,
"text_loss": 1.4391229152679443,
"flow_loss": 3.6610820293426514
},
{
"stage": "policy",
"step": 420,
"loss": 2.400188446044922,
"text_loss": 1.0106937885284424,
"flow_loss": 0.694747269153595
},
{
"stage": "policy",
"step": 440,
"loss": 9.683706283569336,
"text_loss": 1.044368863105774,
"flow_loss": 4.319668769836426
},
{
"stage": "policy",
"step": 460,
"loss": 10.443679809570312,
"text_loss": 0.7045990228652954,
"flow_loss": 4.869540214538574
},
{
"stage": "policy",
"step": 480,
"loss": 6.514384746551514,
"text_loss": 1.185524582862854,
"flow_loss": 2.6644301414489746
},
{
"stage": "policy",
"step": 500,
"loss": 2.255455255508423,
"text_loss": 1.0136079788208008,
"flow_loss": 0.620923638343811
},
{
"stage": "policy",
"step": 520,
"loss": 4.1700439453125,
"text_loss": 1.1829472780227661,
"flow_loss": 1.4935483932495117
},
{
"stage": "policy",
"step": 540,
"loss": 6.956455230712891,
"text_loss": 1.1096038818359375,
"flow_loss": 2.9234256744384766
},
{
"stage": "policy",
"step": 560,
"loss": 4.5965800285339355,
"text_loss": 1.5257400274276733,
"flow_loss": 1.5354200601577759
},
{
"stage": "policy",
"step": 580,
"loss": 1.7948781251907349,
"text_loss": 0.835124135017395,
"flow_loss": 0.4798769950866699
},
{
"stage": "policy",
"step": 600,
"loss": 11.411609649658203,
"text_loss": 0.7508105635643005,
"flow_loss": 5.330399513244629
},
{
"stage": "policy",
"step": 620,
"loss": 14.173189163208008,
"text_loss": 0.553065836429596,
"flow_loss": 6.810061454772949
},
{
"stage": "policy",
"step": 640,
"loss": 2.423476457595825,
"text_loss": 0.6566628813743591,
"flow_loss": 0.8834067583084106
},
{
"stage": "policy",
"step": 660,
"loss": 7.33753776550293,
"text_loss": 0.5569484829902649,
"flow_loss": 3.3902945518493652
},
{
"stage": "policy",
"step": 680,
"loss": 7.2152018547058105,
"text_loss": 0.6606324911117554,
"flow_loss": 3.277284622192383
},
{
"stage": "policy",
"step": 700,
"loss": 2.5858616828918457,
"text_loss": 0.471678227186203,
"flow_loss": 1.0570917129516602
},
{
"stage": "policy",
"step": 720,
"loss": 5.87769889831543,
"text_loss": 0.5711548924446106,
"flow_loss": 2.6532719135284424
},
{
"stage": "policy",
"step": 740,
"loss": 6.787323951721191,
"text_loss": 0.5064371228218079,
"flow_loss": 3.1404433250427246
},
{
"stage": "policy",
"step": 760,
"loss": 11.166234970092773,
"text_loss": 0.5802748203277588,
"flow_loss": 5.292980194091797
},
{
"stage": "policy",
"step": 780,
"loss": 3.563460350036621,
"text_loss": 0.6946841478347778,
"flow_loss": 1.4343880414962769
},
{
"stage": "policy",
"step": 800,
"loss": 3.2471487522125244,
"text_loss": 0.44556593894958496,
"flow_loss": 1.4007914066314697
},
{
"stage": "policy",
"step": 820,
"loss": 3.1103086471557617,
"text_loss": 0.7132699489593506,
"flow_loss": 1.1985193490982056
},
{
"stage": "policy",
"step": 840,
"loss": 4.753307342529297,
"text_loss": 0.48397523164749146,
"flow_loss": 2.1346659660339355
},
{
"stage": "policy",
"step": 860,
"loss": 3.5492496490478516,
"text_loss": 0.366057813167572,
"flow_loss": 1.5915958881378174
},
{
"stage": "policy",
"step": 880,
"loss": 4.0379414558410645,
"text_loss": 0.6511648893356323,
"flow_loss": 1.6933883428573608
},
{
"stage": "policy",
"step": 900,
"loss": 1.7170453071594238,
"text_loss": 0.2673894464969635,
"flow_loss": 0.7248279452323914
}
]