[2024-12-16 09:48:13,763][mode.evaluation.multistep_sequences][INFO] - Start generating evaluation sequences.
[2024-12-16 09:48:25,484][mode.evaluation.multistep_sequences][INFO] - Done generating evaluation sequences.
  0%|                                                                                                                                                 | 0/1000 [00:00<?, ?it/s]























































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































1/5 : 96.6% | 2/5 : 90.3% | 3/5 : 82.8% | 4/5 : 72.2% | 5/5 : 63.5% | Average: 4.1 |: 100%|██████████████████████████████████████████████| 1000/1000 [2:24:10<00:00,  8.65s/it]
Results for Epoch 0:
Average successful sequence length: 4.054
Success rates for i instructions in a row:
1: 96.6%
2: 90.3%
3: 82.8%
4: 72.2%
5: 63.5%
rotate_blue_block_right: 73 / 77 |  SR: 94.8%
move_slider_right: 279 / 279 |  SR: 100.0%
lift_red_block_slider: 103 / 124 |  SR: 83.1%
place_in_slider: 262 / 349 |  SR: 75.1%
turn_off_lightbulb: 137 / 144 |  SR: 95.1%
turn_off_led: 165 / 166 |  SR: 99.4%
push_into_drawer: 95 / 121 |  SR: 78.5%
lift_blue_block_drawer: 20 / 20 |  SR: 100.0%
lift_pink_block_slider: 127 / 138 |  SR: 92.0%
open_drawer: 336 / 338 |  SR: 99.4%
rotate_red_block_right: 71 / 73 |  SR: 97.3%
lift_red_block_table: 185 / 186 |  SR: 99.5%
lift_pink_block_table: 164 / 174 |  SR: 94.3%
turn_on_lightbulb: 175 / 179 |  SR: 97.8%
rotate_blue_block_left: 65 / 65 |  SR: 100.0%
push_blue_block_left: 61 / 66 |  SR: 92.4%
close_drawer: 202 / 202 |  SR: 100.0%
turn_on_led: 168 / 171 |  SR: 98.2%
push_pink_block_right: 32 / 61 |  SR: 52.5%
push_red_block_right: 54 / 70 |  SR: 77.1%
move_slider_left: 239 / 242 |  SR: 98.8%
push_red_block_left: 72 / 77 |  SR: 93.5%
lift_blue_block_table: 184 / 185 |  SR: 99.5%
place_in_drawer: 176 / 176 |  SR: 100.0%
rotate_red_block_left: 59 / 60 |  SR: 98.3%
stack_block: 126 / 197 |  SR: 64.0%
push_pink_block_left: 72 / 72 |  SR: 100.0%
lift_blue_block_slider: 103 / 129 |  SR: 79.8%
lift_pink_block_drawer: 11 / 13 |  SR: 84.6%
rotate_pink_block_right: 63 / 67 |  SR: 94.0%
unstack_block: 54 / 56 |  SR: 96.4%
rotate_pink_block_left: 53 / 55 |  SR: 96.4%
push_blue_block_right: 49 / 68 |  SR: 72.1%
lift_red_block_drawer: 19 / 19 |  SR: 100.0%
Best model: epoch 0 with average sequences length of 4.054