Align pi0.7 minimal structure with paper
This commit is contained in:
Binary file not shown.
|
Before Width: | Height: | Size: 92 KiB After Width: | Height: | Size: 89 KiB |
@@ -1,11 +1,39 @@
|
||||
{
|
||||
"target_subtask": "steer_left",
|
||||
"predicted_subtask": "steer_left",
|
||||
"goal_image_mse": 0.0246433112770319,
|
||||
"trajectory_metrics": {
|
||||
"full_oracle_goal": 0.47031369805336,
|
||||
"generated_goal": 0.4905388057231903,
|
||||
"no_metadata": 2.457864284515381,
|
||||
"no_goal": 4.042560577392578,
|
||||
"no_history": 2.1593737602233887,
|
||||
"cfg_beta2": 10.576497077941895
|
||||
"full_generated_goal": 9.339226722717285,
|
||||
"full_oracle_goal": 9.344671249389648,
|
||||
"no_metadata": 4.243795394897461,
|
||||
"no_goal": 9.066949844360352,
|
||||
"no_history": 10.404154777526855,
|
||||
"metadata_cfg": 19.987443923950195
|
||||
},
|
||||
"normalized_action_metrics": {
|
||||
"full_generated_goal": 0.2848391532897949,
|
||||
"full_oracle_goal": 0.2848338186740875,
|
||||
"no_metadata": 0.37385478615760803,
|
||||
"no_goal": 0.29379916191101074,
|
||||
"no_history": 0.28792211413383484,
|
||||
"metadata_cfg": 0.2725481688976288
|
||||
},
|
||||
"rtc_metrics": {
|
||||
"0": {
|
||||
"postfix_action_mse": 0.2848391532897949,
|
||||
"trajectory_mse": 9.339226722717285
|
||||
},
|
||||
"4": {
|
||||
"postfix_action_mse": 1.2005467414855957,
|
||||
"trajectory_mse": 2.2003140449523926
|
||||
},
|
||||
"8": {
|
||||
"postfix_action_mse": 0.12100008875131607,
|
||||
"trajectory_mse": 0.10110154747962952
|
||||
},
|
||||
"12": {
|
||||
"postfix_action_mse": 0.08735787123441696,
|
||||
"trajectory_mse": 0.11811599135398865
|
||||
}
|
||||
}
|
||||
}
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 50 KiB After Width: | Height: | Size: 62 KiB |
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"device": "mps",
|
||||
"samples": 5,
|
||||
"policy_parameters": 1088930,
|
||||
"goal_parameters": 75731,
|
||||
"high_level_parameters": 652800
|
||||
"policy_parameters": 1088354,
|
||||
"goal_parameters": 75347,
|
||||
"high_level_parameters": 652224
|
||||
}
|
||||
@@ -2,87 +2,212 @@
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 1,
|
||||
"loss": 1.0040572881698608
|
||||
"loss": 1.1256178617477417
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 20,
|
||||
"loss": 0.34230467677116394
|
||||
"loss": 0.8757796287536621
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 40,
|
||||
"loss": 0.37451064586639404
|
||||
"loss": 0.4848751425743103
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 60,
|
||||
"loss": 0.26792070269584656
|
||||
"loss": 0.2024349421262741
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 80,
|
||||
"loss": 0.10219617933034897
|
||||
"loss": 0.31732437014579773
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 100,
|
||||
"loss": 0.2711445987224579
|
||||
"loss": 0.22155670821666718
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 120,
|
||||
"loss": 0.2289590686559677
|
||||
"loss": 0.32919183373451233
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 140,
|
||||
"loss": 0.36456483602523804
|
||||
"loss": 0.171668142080307
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 160,
|
||||
"loss": 0.0842418223619461
|
||||
"loss": 1.0167959928512573
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 180,
|
||||
"loss": 0.9889341592788696
|
||||
"loss": 0.8417221903800964
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 200,
|
||||
"loss": 0.5776903629302979
|
||||
"loss": 0.10604722797870636
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 220,
|
||||
"loss": 0.44620272517204285
|
||||
"loss": 0.07537326216697693
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 240,
|
||||
"loss": 0.05634145438671112
|
||||
"loss": 0.1885790228843689
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 260,
|
||||
"loss": 0.05701519176363945
|
||||
"loss": 0.06766514480113983
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 280,
|
||||
"loss": 0.06764699518680573
|
||||
"loss": 0.14665386080741882
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 300,
|
||||
"loss": 0.10973378270864487
|
||||
"loss": 0.10101648420095444
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 320,
|
||||
"loss": 0.07647702097892761
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 340,
|
||||
"loss": 0.08067559450864792
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 360,
|
||||
"loss": 0.12979857623577118
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 380,
|
||||
"loss": 0.899062991142273
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 400,
|
||||
"loss": 0.12218281626701355
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 420,
|
||||
"loss": 0.07381283491849899
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 440,
|
||||
"loss": 0.13227435946464539
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 460,
|
||||
"loss": 0.08732561767101288
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 480,
|
||||
"loss": 0.09666546434164047
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 500,
|
||||
"loss": 0.06472445279359818
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 520,
|
||||
"loss": 0.08121205866336823
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 540,
|
||||
"loss": 0.06035961955785751
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 560,
|
||||
"loss": 0.07124190032482147
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 580,
|
||||
"loss": 0.14373362064361572
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 600,
|
||||
"loss": 0.07122757285833359
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 620,
|
||||
"loss": 0.8890293836593628
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 640,
|
||||
"loss": 0.062469229102134705
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 660,
|
||||
"loss": 0.05835632607340813
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 680,
|
||||
"loss": 0.8515450358390808
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 700,
|
||||
"loss": 0.06296383589506149
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 720,
|
||||
"loss": 0.06271275877952576
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 740,
|
||||
"loss": 0.09368501603603363
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 760,
|
||||
"loss": 0.07982345670461655
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 780,
|
||||
"loss": 0.06414016336202621
|
||||
},
|
||||
{
|
||||
"stage": "goal",
|
||||
"step": 800,
|
||||
"loss": 0.08895712345838547
|
||||
},
|
||||
{
|
||||
"stage": "high_level",
|
||||
"step": 1,
|
||||
"loss": 76.15934753417969
|
||||
"loss": 84.32572937011719
|
||||
},
|
||||
{
|
||||
"stage": "high_level",
|
||||
@@ -137,323 +262,507 @@
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 1,
|
||||
"loss": 51.04338836669922,
|
||||
"text_loss": 44.21609115600586,
|
||||
"flow_loss": 3.4136481285095215
|
||||
"loss": 51.165855407714844,
|
||||
"text_loss": 46.97157287597656,
|
||||
"flow_loss": 2.0971415042877197,
|
||||
"rtc_delay": 5,
|
||||
"use_goal": true,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 20,
|
||||
"loss": 26.20608901977539,
|
||||
"text_loss": 5.128565311431885,
|
||||
"flow_loss": 10.538762092590332
|
||||
"loss": 11.228275299072266,
|
||||
"text_loss": 4.843214988708496,
|
||||
"flow_loss": 3.192530393600464,
|
||||
"rtc_delay": 1,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 40,
|
||||
"loss": 13.018914222717285,
|
||||
"text_loss": 3.846059799194336,
|
||||
"flow_loss": 4.586427211761475
|
||||
"loss": 6.2679572105407715,
|
||||
"text_loss": 2.9056875705718994,
|
||||
"flow_loss": 1.681134819984436,
|
||||
"rtc_delay": 4,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 60,
|
||||
"loss": 11.344329833984375,
|
||||
"text_loss": 3.335771083831787,
|
||||
"flow_loss": 4.004279136657715
|
||||
"loss": 6.005075931549072,
|
||||
"text_loss": 2.709343671798706,
|
||||
"flow_loss": 1.647866129875183,
|
||||
"rtc_delay": 2,
|
||||
"use_goal": true,
|
||||
"use_history": true,
|
||||
"include_subtask": false
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 80,
|
||||
"loss": 6.586862087249756,
|
||||
"text_loss": 2.5455708503723145,
|
||||
"flow_loss": 2.0206456184387207
|
||||
"loss": 9.903374671936035,
|
||||
"text_loss": 2.334010362625122,
|
||||
"flow_loss": 3.784682273864746,
|
||||
"rtc_delay": 4,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 100,
|
||||
"loss": 11.200895309448242,
|
||||
"text_loss": 2.1739449501037598,
|
||||
"flow_loss": 4.513474941253662
|
||||
"loss": 5.646769046783447,
|
||||
"text_loss": 2.3033981323242188,
|
||||
"flow_loss": 1.6716854572296143,
|
||||
"rtc_delay": 12,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 120,
|
||||
"loss": 17.273035049438477,
|
||||
"text_loss": 2.1746408939361572,
|
||||
"flow_loss": 7.549196720123291
|
||||
"loss": 6.867326259613037,
|
||||
"text_loss": 1.850703239440918,
|
||||
"flow_loss": 2.5083115100860596,
|
||||
"rtc_delay": 12,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 140,
|
||||
"loss": 11.353687286376953,
|
||||
"text_loss": 2.2218563556671143,
|
||||
"flow_loss": 4.565915584564209
|
||||
"loss": 3.6174087524414062,
|
||||
"text_loss": 2.0811572074890137,
|
||||
"flow_loss": 0.7681257128715515,
|
||||
"rtc_delay": 11,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 160,
|
||||
"loss": 14.110220909118652,
|
||||
"text_loss": 2.3123977184295654,
|
||||
"flow_loss": 5.898911476135254
|
||||
"loss": 4.300071716308594,
|
||||
"text_loss": 1.9097824096679688,
|
||||
"flow_loss": 1.1951446533203125,
|
||||
"rtc_delay": 8,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 180,
|
||||
"loss": 19.999370574951172,
|
||||
"text_loss": 2.749119997024536,
|
||||
"flow_loss": 8.62512493133545
|
||||
"loss": 8.075389862060547,
|
||||
"text_loss": 1.6174044609069824,
|
||||
"flow_loss": 3.2289929389953613,
|
||||
"rtc_delay": 2,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 200,
|
||||
"loss": 8.102465629577637,
|
||||
"text_loss": 1.631801962852478,
|
||||
"flow_loss": 3.2353317737579346
|
||||
"loss": 5.758746147155762,
|
||||
"text_loss": 1.5621910095214844,
|
||||
"flow_loss": 2.0982775688171387,
|
||||
"rtc_delay": 11,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 220,
|
||||
"loss": 21.903854370117188,
|
||||
"text_loss": 1.6063504219055176,
|
||||
"flow_loss": 10.148752212524414
|
||||
"loss": 2.9783213138580322,
|
||||
"text_loss": 1.389180302619934,
|
||||
"flow_loss": 0.7945705056190491,
|
||||
"rtc_delay": 11,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 240,
|
||||
"loss": 10.197904586791992,
|
||||
"text_loss": 1.5640149116516113,
|
||||
"flow_loss": 4.3169450759887695
|
||||
"loss": 5.832153797149658,
|
||||
"text_loss": 1.4576387405395508,
|
||||
"flow_loss": 2.1872575283050537,
|
||||
"rtc_delay": 0,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 260,
|
||||
"loss": 6.899936676025391,
|
||||
"text_loss": 1.3081820011138916,
|
||||
"flow_loss": 2.795877456665039
|
||||
"loss": 3.4007065296173096,
|
||||
"text_loss": 0.8826411366462708,
|
||||
"flow_loss": 1.2590327262878418,
|
||||
"rtc_delay": 5,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 280,
|
||||
"loss": 10.051774978637695,
|
||||
"text_loss": 1.2130903005599976,
|
||||
"flow_loss": 4.419342517852783
|
||||
"loss": 4.018008232116699,
|
||||
"text_loss": 0.9588160514831543,
|
||||
"flow_loss": 1.529596209526062,
|
||||
"rtc_delay": 11,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 300,
|
||||
"loss": 7.963553428649902,
|
||||
"text_loss": 1.1586928367614746,
|
||||
"flow_loss": 3.402430295944214
|
||||
"loss": 1.492077112197876,
|
||||
"text_loss": 0.9946327209472656,
|
||||
"flow_loss": 0.24872222542762756,
|
||||
"rtc_delay": 9,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 320,
|
||||
"loss": 5.177718639373779,
|
||||
"text_loss": 1.2673476934432983,
|
||||
"flow_loss": 1.9551855325698853
|
||||
"loss": 5.338322639465332,
|
||||
"text_loss": 0.8486652970314026,
|
||||
"flow_loss": 2.244828701019287,
|
||||
"rtc_delay": 8,
|
||||
"use_goal": true,
|
||||
"use_history": true,
|
||||
"include_subtask": false
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 340,
|
||||
"loss": 4.487771034240723,
|
||||
"text_loss": 1.0361082553863525,
|
||||
"flow_loss": 1.7258312702178955
|
||||
"loss": 2.0994033813476562,
|
||||
"text_loss": 0.8355546593666077,
|
||||
"flow_loss": 0.6319243907928467,
|
||||
"rtc_delay": 7,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 360,
|
||||
"loss": 4.356203556060791,
|
||||
"text_loss": 1.3223515748977661,
|
||||
"flow_loss": 1.5169259309768677
|
||||
"loss": 2.2518701553344727,
|
||||
"text_loss": 0.5455462336540222,
|
||||
"flow_loss": 0.8531619906425476,
|
||||
"rtc_delay": 10,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 380,
|
||||
"loss": 5.289548397064209,
|
||||
"text_loss": 1.4994667768478394,
|
||||
"flow_loss": 1.89504075050354
|
||||
"loss": 7.911384105682373,
|
||||
"text_loss": 0.6893162727355957,
|
||||
"flow_loss": 3.6110339164733887,
|
||||
"rtc_delay": 7,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 400,
|
||||
"loss": 8.761286735534668,
|
||||
"text_loss": 1.4391229152679443,
|
||||
"flow_loss": 3.6610820293426514
|
||||
"loss": 2.3619725704193115,
|
||||
"text_loss": 0.5672968626022339,
|
||||
"flow_loss": 0.8973378539085388,
|
||||
"rtc_delay": 10,
|
||||
"use_goal": true,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 420,
|
||||
"loss": 2.400188446044922,
|
||||
"text_loss": 1.0106937885284424,
|
||||
"flow_loss": 0.694747269153595
|
||||
"loss": 1.233857274055481,
|
||||
"text_loss": 0.661384642124176,
|
||||
"flow_loss": 0.28623631596565247,
|
||||
"rtc_delay": 12,
|
||||
"use_goal": true,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 440,
|
||||
"loss": 9.683706283569336,
|
||||
"text_loss": 1.044368863105774,
|
||||
"flow_loss": 4.319668769836426
|
||||
"loss": 3.295243740081787,
|
||||
"text_loss": 0.4776339828968048,
|
||||
"flow_loss": 1.4088048934936523,
|
||||
"rtc_delay": 9,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 460,
|
||||
"loss": 10.443679809570312,
|
||||
"text_loss": 0.7045990228652954,
|
||||
"flow_loss": 4.869540214538574
|
||||
"loss": 1.7052180767059326,
|
||||
"text_loss": 0.5183412432670593,
|
||||
"flow_loss": 0.5934383869171143,
|
||||
"rtc_delay": 8,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 480,
|
||||
"loss": 6.514384746551514,
|
||||
"text_loss": 1.185524582862854,
|
||||
"flow_loss": 2.6644301414489746
|
||||
"loss": 8.46796703338623,
|
||||
"text_loss": 0.6230667233467102,
|
||||
"flow_loss": 3.922450065612793,
|
||||
"rtc_delay": 0,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 500,
|
||||
"loss": 2.255455255508423,
|
||||
"text_loss": 1.0136079788208008,
|
||||
"flow_loss": 0.620923638343811
|
||||
"loss": 2.5979185104370117,
|
||||
"text_loss": 0.27633967995643616,
|
||||
"flow_loss": 1.1607893705368042,
|
||||
"rtc_delay": 1,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 520,
|
||||
"loss": 4.1700439453125,
|
||||
"text_loss": 1.1829472780227661,
|
||||
"flow_loss": 1.4935483932495117
|
||||
"loss": 2.012068510055542,
|
||||
"text_loss": 0.30755916237831116,
|
||||
"flow_loss": 0.8522546291351318,
|
||||
"rtc_delay": 1,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 540,
|
||||
"loss": 6.956455230712891,
|
||||
"text_loss": 1.1096038818359375,
|
||||
"flow_loss": 2.9234256744384766
|
||||
"loss": 5.146071910858154,
|
||||
"text_loss": 0.4677533805370331,
|
||||
"flow_loss": 2.3391592502593994,
|
||||
"rtc_delay": 0,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 560,
|
||||
"loss": 4.5965800285339355,
|
||||
"text_loss": 1.5257400274276733,
|
||||
"flow_loss": 1.5354200601577759
|
||||
"loss": 1.9480068683624268,
|
||||
"text_loss": 0.9942646026611328,
|
||||
"flow_loss": 0.476871132850647,
|
||||
"rtc_delay": 7,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 580,
|
||||
"loss": 1.7948781251907349,
|
||||
"text_loss": 0.835124135017395,
|
||||
"flow_loss": 0.4798769950866699
|
||||
"loss": 7.889751434326172,
|
||||
"text_loss": 0.6651982665061951,
|
||||
"flow_loss": 3.612276554107666,
|
||||
"rtc_delay": 3,
|
||||
"use_goal": true,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 600,
|
||||
"loss": 11.411609649658203,
|
||||
"text_loss": 0.7508105635643005,
|
||||
"flow_loss": 5.330399513244629
|
||||
"loss": 1.454559087753296,
|
||||
"text_loss": 0.5516519546508789,
|
||||
"flow_loss": 0.4514535963535309,
|
||||
"rtc_delay": 11,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 620,
|
||||
"loss": 14.173189163208008,
|
||||
"text_loss": 0.553065836429596,
|
||||
"flow_loss": 6.810061454772949
|
||||
"loss": 4.760444641113281,
|
||||
"text_loss": 0.3332846760749817,
|
||||
"flow_loss": 2.2135798931121826,
|
||||
"rtc_delay": 7,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 640,
|
||||
"loss": 2.423476457595825,
|
||||
"text_loss": 0.6566628813743591,
|
||||
"flow_loss": 0.8834067583084106
|
||||
"loss": 6.838594913482666,
|
||||
"text_loss": 0.33531704545021057,
|
||||
"flow_loss": 3.251638889312744,
|
||||
"rtc_delay": 3,
|
||||
"use_goal": true,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 660,
|
||||
"loss": 7.33753776550293,
|
||||
"text_loss": 0.5569484829902649,
|
||||
"flow_loss": 3.3902945518493652
|
||||
"loss": 4.01173210144043,
|
||||
"text_loss": 0.842496395111084,
|
||||
"flow_loss": 1.5846179723739624,
|
||||
"rtc_delay": 1,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 680,
|
||||
"loss": 7.2152018547058105,
|
||||
"text_loss": 0.6606324911117554,
|
||||
"flow_loss": 3.277284622192383
|
||||
"loss": 5.610707759857178,
|
||||
"text_loss": 0.45004716515541077,
|
||||
"flow_loss": 2.5803303718566895,
|
||||
"rtc_delay": 6,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 700,
|
||||
"loss": 2.5858616828918457,
|
||||
"text_loss": 0.471678227186203,
|
||||
"flow_loss": 1.0570917129516602
|
||||
"loss": 2.415992021560669,
|
||||
"text_loss": 0.2757202684879303,
|
||||
"flow_loss": 1.0701358318328857,
|
||||
"rtc_delay": 3,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 720,
|
||||
"loss": 5.87769889831543,
|
||||
"text_loss": 0.5711548924446106,
|
||||
"flow_loss": 2.6532719135284424
|
||||
"loss": 3.6413190364837646,
|
||||
"text_loss": 0.15377745032310486,
|
||||
"flow_loss": 1.7437708377838135,
|
||||
"rtc_delay": 2,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 740,
|
||||
"loss": 6.787323951721191,
|
||||
"text_loss": 0.5064371228218079,
|
||||
"flow_loss": 3.1404433250427246
|
||||
"loss": 2.4192750453948975,
|
||||
"text_loss": 0.7513293027877808,
|
||||
"flow_loss": 0.8339728713035583,
|
||||
"rtc_delay": 4,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 760,
|
||||
"loss": 11.166234970092773,
|
||||
"text_loss": 0.5802748203277588,
|
||||
"flow_loss": 5.292980194091797
|
||||
"loss": 1.3346192836761475,
|
||||
"text_loss": 0.2767994999885559,
|
||||
"flow_loss": 0.5289098620414734,
|
||||
"rtc_delay": 10,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 780,
|
||||
"loss": 3.563460350036621,
|
||||
"text_loss": 0.6946841478347778,
|
||||
"flow_loss": 1.4343880414962769
|
||||
"loss": 2.4135358333587646,
|
||||
"text_loss": 0.16017527878284454,
|
||||
"flow_loss": 1.1266802549362183,
|
||||
"rtc_delay": 3,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 800,
|
||||
"loss": 3.2471487522125244,
|
||||
"text_loss": 0.44556593894958496,
|
||||
"flow_loss": 1.4007914066314697
|
||||
"loss": 2.966399908065796,
|
||||
"text_loss": 0.2566848397254944,
|
||||
"flow_loss": 1.3548575639724731,
|
||||
"rtc_delay": 3,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 820,
|
||||
"loss": 3.1103086471557617,
|
||||
"text_loss": 0.7132699489593506,
|
||||
"flow_loss": 1.1985193490982056
|
||||
"loss": 1.8670570850372314,
|
||||
"text_loss": 0.23726917803287506,
|
||||
"flow_loss": 0.8148939609527588,
|
||||
"rtc_delay": 4,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 840,
|
||||
"loss": 4.753307342529297,
|
||||
"text_loss": 0.48397523164749146,
|
||||
"flow_loss": 2.1346659660339355
|
||||
"loss": 1.6185007095336914,
|
||||
"text_loss": 0.27975988388061523,
|
||||
"flow_loss": 0.6693704128265381,
|
||||
"rtc_delay": 5,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 860,
|
||||
"loss": 3.5492496490478516,
|
||||
"text_loss": 0.366057813167572,
|
||||
"flow_loss": 1.5915958881378174
|
||||
"loss": 0.9501249194145203,
|
||||
"text_loss": 0.4190976619720459,
|
||||
"flow_loss": 0.2655136287212372,
|
||||
"rtc_delay": 7,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 880,
|
||||
"loss": 4.0379414558410645,
|
||||
"text_loss": 0.6511648893356323,
|
||||
"flow_loss": 1.6933883428573608
|
||||
"loss": 1.5665624141693115,
|
||||
"text_loss": 0.317945659160614,
|
||||
"flow_loss": 0.6243083477020264,
|
||||
"rtc_delay": 5,
|
||||
"use_goal": false,
|
||||
"use_history": false,
|
||||
"include_subtask": true
|
||||
},
|
||||
{
|
||||
"stage": "policy",
|
||||
"step": 900,
|
||||
"loss": 1.7170453071594238,
|
||||
"text_loss": 0.2673894464969635,
|
||||
"flow_loss": 0.7248279452323914
|
||||
"loss": 1.8227444887161255,
|
||||
"text_loss": 0.32235953211784363,
|
||||
"flow_loss": 0.7501924633979797,
|
||||
"rtc_delay": 8,
|
||||
"use_goal": false,
|
||||
"use_history": true,
|
||||
"include_subtask": true
|
||||
}
|
||||
]
|
||||
Reference in New Issue
Block a user