-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathdvc.lock
9638 lines (9638 loc) · 306 KB
/
dvc.lock
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
schema: '2.0'
stages:
fetch_swe_bench_runs:
cmd: python -m src.fetch_swe_bench_runs --annotations data/external/ensembled_annotations_public.csv
--output-file data/external/swe_bench_runs.jsonl
deps:
- path: src/fetch_swe_bench_runs.py
hash: md5
md5: 78bcec8f686d817e50b4533b061fa346
size: 9120
outs:
- path: data/external/swe_bench_runs.jsonl
hash: md5
md5: 08e2dc3b47344bc919f7d608fbad1592
size: 740060
filter_out_partial_agents:
cmd: python -m src.filter_out_partial_agents --input-all-runs data/external/all_runs.jsonl
--output-runs-with-allowed-agents data/processed/runs/ga_agents.jsonl
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: b8dca04daab5f4d2bbfdedbb1ce62e5a
size: 9718647
- path: src/filter_out_partial_agents.py
hash: md5
md5: 76e5c8cece6049529b643290e25ecddb
size: 1106
outs:
- path: data/processed/runs/ga_agents.jsonl
hash: md5
md5: b8dca04daab5f4d2bbfdedbb1ce62e5a
size: 9718647
filter_aird_runs:
cmd: python -m src.filter_aird_runs --input-file data/external/all_runs.jsonl
--output-file data/processed/runs/aird.jsonl
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: b8dca04daab5f4d2bbfdedbb1ce62e5a
size: 9718647
- path: src/filter_aird_runs.py
hash: md5
md5: f4ae81387bdd0a2d0f0a0ce005f7b49b
size: 950
params:
params.yaml:
stages.filter_aird_runs:
task_families:
- ai_rd_fix_embedding
- ai_rd_nanogpt_chat_rl
- ai_rd_optimize_llm_foundry
- ai_rd_restricted_mlm
- ai_rd_rust_codecontests_inference
- ai_rd_small_scaling_law
- ai_rd_triton_cumsum
outs:
- path: data/processed/runs/aird.jsonl
hash: md5
md5: bd9e9ad6231d8e42391add73dc48b470
size: 419167
wrangle_bar_by_time_allocation:
cmd: python -m src.wrangle.bar_by_time_allocation --runs-file data/processed/runs/aird.jsonl
--wrangled-file data/processed/wrangled/bar_by_time_allocation.jsonl
deps:
- path: data/processed/runs/aird.jsonl
hash: md5
md5: bd9e9ad6231d8e42391add73dc48b470
size: 419167
- path: src/stats/statistics.py
hash: md5
md5: 847fb366793e66de803cd15dcc98979f
size: 5832
- path: src/utils/plots.py
hash: md5
md5: b15dd0e3262c590e9a866cbe38d4695d
size: 5419
- path: src/wrangle/bar_by_time_allocation.py
hash: md5
md5: 1d6abf2b30046611a9c6fbe2aabeb36b
size: 3603
params:
params.yaml:
n_bootstrap: 1000
rebench_best_of_k_parameters:
time_limits:
- 36000
max_time_limit_in_seconds: 36000
outs:
- path: data/processed/wrangled/bar_by_time_allocation.jsonl
hash: md5
md5: d65a6a890c0f3f1bd1a2f1f7ba8933fa
size: 2101
wrangle_human_mean_of_percentiles:
cmd: python -m src.wrangle.human_mean_of_percentiles --interpolated-scores data/processed/runs/aird.jsonl
--output-percentiles data/processed/wrangled/human_mean_of_percentiles.jsonl
--log-level INFO
deps:
- path: data/processed/runs/aird.jsonl
hash: md5
md5: bd9e9ad6231d8e42391add73dc48b470
size: 419167
- path: src/wrangle/human_mean_of_percentiles.py
hash: md5
md5: d8ba4e2b646d4c16c756309eb17135ec
size: 2958
params:
params.yaml:
log_level: INFO
outs:
- path: data/processed/wrangled/human_mean_of_percentiles.jsonl
hash: md5
md5: fdb0c471fa77300828c324ddcf925610
size: 11651
wrangle_score_at_k:
cmd: python -m src.wrangle.score_at_k --input-score-at-k data/processed/runs/aird.jsonl
--output-score-at-k data/processed/wrangled/score_at_k.jsonl --n-bootstrap 1000
deps:
- path: data/processed/runs/aird.jsonl
hash: md5
md5: bd9e9ad6231d8e42391add73dc48b470
size: 419167
- path: src/wrangle/score_at_k.py
hash: md5
md5: 207acf4e38240cb8d27b5424a230cf4a
size: 5320
params:
params.yaml:
log_level: INFO
n_bootstrap: 1000
rebench_best_of_k_parameters:
time_limits:
- 36000
max_time_limit_in_seconds: 36000
outs:
- path: data/processed/wrangled/score_at_k.jsonl
hash: md5
md5: a90888af6db4b02c5d236c100ebe1ce4
size: 5928
wrangle_bootstrap_logistic@equal_task_weight-ftr-0.01:
cmd: python -m src.wrangle.bootstrap --runs-file data/external/all_runs.jsonl
--output-bootstrap-horizons-file data/wrangled/bootstrap/equal_task_weight-ftr-0.01.csv
--weights-col equal_task_weight --categories ftr --n-bootstrap 500 --regularization
0.01
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: 557c9500e054e832ecd77cd274d94f5d
size: 6194396
- path: src/wrangle/bootstrap.py
hash: md5
md5: edcfd3c10cbba6e44ad4442535d93104
size: 10441
- path: src/wrangle/logistic.py
hash: md5
md5: dd5b095413f86de74d055f81921b595c
size: 6845
outs:
- path: data/wrangled/bootstrap/equal_task_weight-ftr-0.01.csv
hash: md5
md5: ed5001468484e4874ac5dbc4fa9690e0
size: 130705
wrangle_logistic_regression@equal_task_weight-ftr-0.01:
cmd: python -m src.wrangle.logistic --runs-file data/external/all_runs.jsonl --output-logistic-fits-file
data/wrangled/logistic_regression_equal_task_weight_0.01_ftr.csv --weighting
equal_task_weight --regularization 0.01 --bootstrap-file data/wrangled/bootstrap/equal_task_weight-ftr-0.01.csv
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: 557c9500e054e832ecd77cd274d94f5d
size: 6194396
- path: data/wrangled/bootstrap/equal_task_weight-ftr-0.01.csv
hash: md5
md5: ed5001468484e4874ac5dbc4fa9690e0
size: 130705
- path: src/wrangle/logistic.py
hash: md5
md5: dd5b095413f86de74d055f81921b595c
size: 6845
outs:
- path: data/wrangled/logistic_regression_equal_task_weight_0.01_ftr.csv
hash: md5
md5: 9504be42e6392018a046eaff22f29bf9
size: 3230
wrangle_bootstrap_logistic@equal_task_weight-ftr-0.1:
cmd: python -m src.wrangle.bootstrap --runs-file data/external/all_runs.jsonl
--output-bootstrap-horizons-file data/wrangled/bootstrap/equal_task_weight-ftr-0.1.csv
--weights-col equal_task_weight --categories ftr --n-bootstrap 500 --regularization
0.1
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: 557c9500e054e832ecd77cd274d94f5d
size: 6194396
- path: src/wrangle/bootstrap.py
hash: md5
md5: edcfd3c10cbba6e44ad4442535d93104
size: 10441
- path: src/wrangle/logistic.py
hash: md5
md5: dd5b095413f86de74d055f81921b595c
size: 6845
outs:
- path: data/wrangled/bootstrap/equal_task_weight-ftr-0.1.csv
hash: md5
md5: 5cca15de7772c76766604a7e7b82208c
size: 130829
wrangle_logistic_regression@equal_task_weight-ftr-0.1:
cmd: python -m src.wrangle.logistic --runs-file data/external/all_runs.jsonl --output-logistic-fits-file
data/wrangled/logistic_regression_equal_task_weight_0.1_ftr.csv --weighting
equal_task_weight --regularization 0.1 --bootstrap-file data/wrangled/bootstrap/equal_task_weight-ftr-0.1.csv
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: 557c9500e054e832ecd77cd274d94f5d
size: 6194396
- path: data/wrangled/bootstrap/equal_task_weight-ftr-0.1.csv
hash: md5
md5: 5cca15de7772c76766604a7e7b82208c
size: 130829
- path: src/wrangle/logistic.py
hash: md5
md5: dd5b095413f86de74d055f81921b595c
size: 6845
outs:
- path: data/wrangled/logistic_regression_equal_task_weight_0.1_ftr.csv
hash: md5
md5: 12984572cecbb05eca60763f1b8c473a
size: 3238
wrangle_bootstrap_logistic@invsqrt_task_weight-ftr-0.01:
cmd: python -m src.wrangle.bootstrap --runs-file data/external/all_runs.jsonl
--output-bootstrap-horizons-file data/wrangled/bootstrap/invsqrt_task_weight-ftr-0.01.csv
--weights-col invsqrt_task_weight --categories ftr --n-bootstrap 500 --regularization
0.01
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: 557c9500e054e832ecd77cd274d94f5d
size: 6194396
- path: src/wrangle/bootstrap.py
hash: md5
md5: edcfd3c10cbba6e44ad4442535d93104
size: 10441
- path: src/wrangle/logistic.py
hash: md5
md5: dd5b095413f86de74d055f81921b595c
size: 6845
outs:
- path: data/wrangled/bootstrap/invsqrt_task_weight-ftr-0.01.csv
hash: md5
md5: ab8f528eb621ec3ad61aceab364ca292
size: 130642
wrangle_logistic_regression@invsqrt_task_weight-ftr-0.01:
cmd: python -m src.wrangle.logistic --runs-file data/external/all_runs.jsonl --output-logistic-fits-file
data/wrangled/logistic_regression_invsqrt_task_weight_0.01_ftr.csv --weighting
invsqrt_task_weight --regularization 0.01 --bootstrap-file data/wrangled/bootstrap/invsqrt_task_weight-ftr-0.01.csv
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: 557c9500e054e832ecd77cd274d94f5d
size: 6194396
- path: data/wrangled/bootstrap/invsqrt_task_weight-ftr-0.01.csv
hash: md5
md5: ab8f528eb621ec3ad61aceab364ca292
size: 130642
- path: src/wrangle/logistic.py
hash: md5
md5: dd5b095413f86de74d055f81921b595c
size: 6845
outs:
- path: data/wrangled/logistic_regression_invsqrt_task_weight_0.01_ftr.csv
hash: md5
md5: 3527e6fc49ca4bf98900293088e4ebf6
size: 3237
wrangle_bootstrap_logistic@invsqrt_task_weight-ftr-0.1:
cmd: python -m src.wrangle.bootstrap --runs-file data/external/all_runs.jsonl
--output-bootstrap-horizons-file data/wrangled/bootstrap/invsqrt_task_weight-ftr-0.1.csv
--weights-col invsqrt_task_weight --categories ftr --n-bootstrap 500 --regularization
0.1
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: 557c9500e054e832ecd77cd274d94f5d
size: 6194396
- path: src/wrangle/bootstrap.py
hash: md5
md5: edcfd3c10cbba6e44ad4442535d93104
size: 10441
- path: src/wrangle/logistic.py
hash: md5
md5: dd5b095413f86de74d055f81921b595c
size: 6845
outs:
- path: data/wrangled/bootstrap/invsqrt_task_weight-ftr-0.1.csv
hash: md5
md5: 5b0bbb5b487a3b75578289f6ad5418e3
size: 130847
wrangle_logistic_regression@invsqrt_task_weight-ftr-0.1:
cmd: python -m src.wrangle.logistic --runs-file data/external/all_runs.jsonl --output-logistic-fits-file
data/wrangled/logistic_regression_invsqrt_task_weight_0.1_ftr.csv --weighting
invsqrt_task_weight --regularization 0.1 --bootstrap-file data/wrangled/bootstrap/invsqrt_task_weight-ftr-0.1.csv
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: 557c9500e054e832ecd77cd274d94f5d
size: 6194396
- path: data/wrangled/bootstrap/invsqrt_task_weight-ftr-0.1.csv
hash: md5
md5: 5b0bbb5b487a3b75578289f6ad5418e3
size: 130847
- path: src/wrangle/logistic.py
hash: md5
md5: dd5b095413f86de74d055f81921b595c
size: 6845
outs:
- path: data/wrangled/logistic_regression_invsqrt_task_weight_0.1_ftr.csv
hash: md5
md5: baa4c86746abccf14ffe55df1acf773e
size: 3238
wrangle_bootstrap_logistic_swe_bench@invsqrt_task_weight-ftr-0.1:
cmd: python -m src.wrangle.bootstrap --runs-file data/processed/swe_bench_runs.jsonl
--output-bootstrap-horizons-file data/wrangled/bootstrap/swe_bench_runs_bootstrap.csv
--weights-col invsqrt_task_weight --categories ftr --n-bootstrap 500 --regularization
0.1
deps:
- path: data/processed/swe_bench_runs.jsonl
hash: md5
md5: 08e2dc3b47344bc919f7d608fbad1592
size: 740060
- path: src/wrangle/bootstrap.py
hash: md5
md5: edcfd3c10cbba6e44ad4442535d93104
size: 10441
- path: src/wrangle/logistic.py
hash: md5
md5: dd5b095413f86de74d055f81921b595c
size: 6845
outs:
- path: data/wrangled/bootstrap/swe_bench_runs_bootstrap.csv
hash: md5
md5: 3dbf1b003dbe1cab98fd2d9e8e62cd3e
size: 55577
wrangle_logistic_regression_swe_bench@invsqrt_task_weight-0.1:
cmd: python -m src.wrangle.logistic --runs-file data/processed/swe_bench_runs.jsonl
--output-logistic-fits-file data/wrangled/swe_bench_logistic.csv --weighting
invsqrt_task_weight --regularization 0.1 --bootstrap-file data/wrangled/bootstrap/swe_bench_runs_bootstrap.csv
deps:
- path: data/processed/swe_bench_runs.jsonl
hash: md5
md5: 08e2dc3b47344bc919f7d608fbad1592
size: 740060
- path: data/wrangled/bootstrap/swe_bench_runs_bootstrap.csv
hash: md5
md5: 3dbf1b003dbe1cab98fd2d9e8e62cd3e
size: 55577
- path: src/wrangle/logistic.py
hash: md5
md5: dd5b095413f86de74d055f81921b595c
size: 6845
outs:
- path: data/wrangled/swe_bench_logistic.csv
hash: md5
md5: c3bdc96a6dc296d5380c118cc17f26e4
size: 1402
plot_bar_chart@invsqrt_task_weight-None-None-0.1:
cmd: python -m src.plot.bar_chart --metrics-file data/wrangled/logistic_regression_invsqrt_task_weight_0.1_ftr.csv
--output-file plots/bar_chart/invsqrt_task_weight.png --log-level INFO --weighting
invsqrt_task_weight --boot-set None --pass-at-k-sampling None --params params.yaml:plots
deps:
- path: data/wrangled/logistic_regression_invsqrt_task_weight_0.1_ftr.csv
hash: md5
md5: baa4c86746abccf14ffe55df1acf773e
size: 3238
- path: src/plot/bar_chart.py
hash: md5
md5: 629e8e84d6e0a50cd093e43cb6f26b26
size: 6814
- path: src/utils/plots.py
hash: md5
md5: 6a051cd7d403e5664969c1ca2ab468ef
size: 3403
params:
params.yaml:
log_level: INFO
plot_format: png
plots:
colors:
agent_aliases:
Claude 3.5 Sonnet (New):
light: '#B784ED'
base: '#8B4DC9'
dark: '#5F2B94'
Claude 3.5 Sonnet (Old):
light: '#D4B6F2'
base: '#9B6BE0'
dark: '#6B3DB0'
Claude 3 Opus:
light: '#E5D4F7'
base: '#B594E8'
dark: '#7A5BA6'
GPT-4o:
light: '#45B3D6'
base: '#2B8FB0'
dark: '#1A5668'
GPT-4 Turbo:
light: '#7CC3DB'
base: '#4A9CBD'
dark: '#2C6B8F'
GPT-4 0314:
light: '#ADD8E6'
base: '#87CEEB'
dark: '#4682B4'
davinci-002:
light: '#E0F3FF'
base: '#B3E0FF'
dark: '#80C4FF'
gpt-3.5-turbo-instruct:
light: '#F0F8FF'
base: '#CCE6FF'
dark: '#99CCFF'
o1:
light: '#90EE90'
base: '#228B22'
dark: '#006400'
o1-preview:
light: '#98FB98'
base: '#3CB371'
dark: '#2E8B57'
human:
light: '#c9c9c9'
base: '#858585'
dark: '#484848'
default: '#000000'
legend_order:
- Claude 3 Opus
- Claude 3.5 Sonnet (New)
- Claude 3.5 Sonnet (Old)
- GPT-4 Turbo
- GPT-4 0314
- GPT-4o
- davinci
- gpt2
- o1-preview
- o1
- Human 8-hour score
outs:
- path: plots/bar_chart/invsqrt_task_weight.png
hash: md5
md5: 1eb5cb9a2754b0860db9b591090c15d3
size: 23478
plot_bar_by_time_allocation:
cmd: python -m src.plot.bar_by_time_allocation --input data/processed/wrangled/bar_by_time_allocation.jsonl
--output plots/bar_by_time_allocation.png --log-level INFO
deps:
- path: data/processed/wrangled/bar_by_time_allocation.jsonl
hash: md5
md5: d65a6a890c0f3f1bd1a2f1f7ba8933fa
size: 2101
- path: matplotlibrc
hash: md5
md5: e5c44785adee259a340f12544e2cb856
size: 526
- path: src/plot/bar_by_time_allocation.py
hash: md5
md5: 5df7d6c33dd0bb200e487233a6b8b57f
size: 5661
- path: src/utils/plots.py
hash: md5
md5: b15dd0e3262c590e9a866cbe38d4695d
size: 5419
params:
params.yaml:
log_level: INFO
plot_format: png
plots:
suptitle_fontsize: 18
xlabelpad: 10
ylabelpad: 10
ax_label_fontsize: 14
title_fontsize: 16
task_distribution_styling:
hist:
edgecolor: '#a6a6a6'
color: '#d4d4d4'
alpha: 1
linewidth: 1
zorder: 50
grid:
which: major
linestyle: '-'
alpha: 0.2
color: grey
scatter_styling:
error_bar:
color: grey
fmt: none
capsize: 2
alpha: 1
zorder: 9
linewidth: 1.5
capthick: 1.5
grid:
which: major
linestyle: '-'
alpha: 0.2
color: grey
scatter:
s: 150
edgecolor: black
linewidth: 0.5
zorder: 10
agent_styling:
Claude 3.5 Sonnet (New):
lab_color: '#e26e2f'
marker: s
unique_color: '#8B4DC9'
Claude 3.5 Sonnet (Old):
lab_color: '#e26e2f'
marker: ^
unique_color: '#9B6BE0'
Claude 3 Opus:
lab_color: '#e26e2f'
marker: o
unique_color: '#B594E8'
o1:
lab_color: '#3e805f'
marker: P
unique_color: '#228B22'
o1-preview:
lab_color: '#3e805f'
marker: X
unique_color: '#3CB371'
GPT-4o:
lab_color: '#3e805f'
marker: d
unique_color: '#2B8FB0'
GPT-4 Turbo:
lab_color: '#3e805f'
marker: v
unique_color: '#4A9CBD'
GPT-4 1106:
lab_color: '#3e805f'
marker: D
unique_color: '#87CEEB'
GPT-4 0314:
lab_color: '#3e805f'
marker: s
unique_color: '#87CEEB'
gpt-3.5-turbo-instruct:
lab_color: '#3e805f'
marker: ^
unique_color: '#CCE6FF'
davinci-002 (GPT-3):
lab_color: '#3e805f'
marker: o
unique_color: '#B3E0FF'
GPT-2:
lab_color: '#3e805f'
marker: '*'
unique_color: '#CCE6FF'
human:
lab_color: grey
marker: o
unique_color: '#858585'
default:
lab_color: black
marker: o
unique_color: black
performance_over_time_trendline_styling:
linear:
annotation:
color: red
fontsize: 10
line:
color: red
alpha: 0.5
linewidth: 2
exponential:
annotation:
color: blue
fontsize: 10
line:
color: blue
alpha: 0.5
linewidth: 2
hyperbolic:
annotation:
color: green
fontsize: 10
line:
color: green
alpha: 0.5
linewidth: 2
default:
annotation:
color: black
fontsize: 10
line:
color: black
alpha: 0.5
linewidth: 2
legend_order:
- Claude 3.5 Sonnet (New)
- Claude 3.5 Sonnet (Old)
- Claude 3 Opus
- o1
- o1-preview
- GPT-4o
- GPT-4 Turbo
- GPT-4 1106
- GPT-4 0314
- gpt-3.5-turbo-instruct
- davinci-002 (GPT-3)
- GPT-2
- Human 8-hour score
outs:
- path: plots/bar_by_time_allocation.png
hash: md5
md5: 81843283e3e3e7e69d1025b0d7c7f5cf
size: 83731
plot_score_at_k@36000:
cmd: python -m src.plot.score_at_k --input-score-at-k data/processed/wrangled/score_at_k.jsonl
--input-human-mean-of-percentiles data/processed/wrangled/human_mean_of_percentiles.jsonl
--output-prefix plots/aird/score_at_k --time-limit 36000 --log-level INFO
deps:
- path: data/processed/wrangled/human_mean_of_percentiles.jsonl
hash: md5
md5: fdb0c471fa77300828c324ddcf925610
size: 11651
- path: data/processed/wrangled/score_at_k.jsonl
hash: md5
md5: a90888af6db4b02c5d236c100ebe1ce4
size: 5928
- path: src/plot/score_at_k.py
hash: md5
md5: a35128ac40e35de4363a51881aea1245
size: 7003
- path: src/stats/statistics.py
hash: md5
md5: 847fb366793e66de803cd15dcc98979f
size: 5832
- path: src/utils/plots.py
hash: md5
md5: b15dd0e3262c590e9a866cbe38d4695d
size: 5419
params:
params.yaml:
log_level: INFO
plot_format: png
plots:
suptitle_fontsize: 18
xlabelpad: 10
ylabelpad: 10
ax_label_fontsize: 14
title_fontsize: 16
task_distribution_styling:
hist:
edgecolor: '#a6a6a6'
color: '#d4d4d4'
alpha: 1
linewidth: 1
zorder: 50
grid:
which: major
linestyle: '-'
alpha: 0.2
color: grey
scatter_styling:
error_bar:
color: grey
fmt: none
capsize: 2
alpha: 1
zorder: 9
linewidth: 1.5
capthick: 1.5
grid:
which: major
linestyle: '-'
alpha: 0.2
color: grey
scatter:
s: 150
edgecolor: black
linewidth: 0.5
zorder: 10
agent_styling:
Claude 3.5 Sonnet (New):
lab_color: '#e26e2f'
marker: s
unique_color: '#8B4DC9'
Claude 3.5 Sonnet (Old):
lab_color: '#e26e2f'
marker: ^
unique_color: '#9B6BE0'
Claude 3 Opus:
lab_color: '#e26e2f'
marker: o
unique_color: '#B594E8'
o1:
lab_color: '#3e805f'
marker: P
unique_color: '#228B22'
o1-preview:
lab_color: '#3e805f'
marker: X
unique_color: '#3CB371'
GPT-4o:
lab_color: '#3e805f'
marker: d
unique_color: '#2B8FB0'
GPT-4 Turbo:
lab_color: '#3e805f'
marker: v
unique_color: '#4A9CBD'
GPT-4 1106:
lab_color: '#3e805f'
marker: D
unique_color: '#87CEEB'
GPT-4 0314:
lab_color: '#3e805f'
marker: s
unique_color: '#87CEEB'
gpt-3.5-turbo-instruct:
lab_color: '#3e805f'
marker: ^
unique_color: '#CCE6FF'
davinci-002 (GPT-3):
lab_color: '#3e805f'
marker: o
unique_color: '#B3E0FF'
GPT-2:
lab_color: '#3e805f'
marker: '*'
unique_color: '#CCE6FF'
human:
lab_color: grey
marker: o
unique_color: '#858585'
default:
lab_color: black
marker: o
unique_color: black
performance_over_time_trendline_styling:
linear:
annotation:
color: red
fontsize: 10
line:
color: red
alpha: 0.5
linewidth: 2
exponential:
annotation:
color: blue
fontsize: 10
line:
color: blue
alpha: 0.5
linewidth: 2
hyperbolic:
annotation:
color: green
fontsize: 10
line:
color: green
alpha: 0.5
linewidth: 2
default:
annotation:
color: black
fontsize: 10
line:
color: black
alpha: 0.5
linewidth: 2
legend_order:
- Claude 3.5 Sonnet (New)
- Claude 3.5 Sonnet (Old)
- Claude 3 Opus
- o1
- o1-preview
- GPT-4o
- GPT-4 Turbo
- GPT-4 1106
- GPT-4 0314
- gpt-3.5-turbo-instruct
- davinci-002 (GPT-3)
- GPT-2
- Human 8-hour score
rebench_best_of_k_parameters:
time_limits:
- 36000
max_time_limit_in_seconds: 36000
outs:
- path: plots/aird/score_at_k_36000.png
hash: md5
md5: eb9b2067e716d9c6ba79c4115ccf783f
size: 150506
plot_logistic_regression@invsqrt_task_weight-ftr-0.1-true-full-2024-01-01:
cmd: python -m src.plot.logistic --input-file data/wrangled/logistic_regression_invsqrt_task_weight_0.1_ftr.csv
--runs-file data/external/all_runs.jsonl --release-dates data/external/release_dates.yaml
--output-file plots/logistic/invsqrt_task_weight-0.1-true-ftr-2024-01-01-distr_full.png
--log-level INFO --trendlines true --after-date 2024-01-01 --weighting "invsqrt_task_weight"
--include-task-distribution full
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: 557c9500e054e832ecd77cd274d94f5d
size: 6194396
- path: data/external/release_dates.yaml
hash: md5
md5: caa7031aaaa86f4ef7298052b3b5a486
size: 511
- path: data/wrangled/logistic_regression_invsqrt_task_weight_0.1_ftr.csv
hash: md5
md5: baa4c86746abccf14ffe55df1acf773e
size: 3238
- path: matplotlibrc
hash: md5
md5: e5c44785adee259a340f12544e2cb856
size: 526
- path: src/plot/logistic.py
hash: md5
md5: b78668949286c250b467f035aa8d3f95
size: 14149
- path: src/utils/plots.py
hash: md5
md5: 6a051cd7d403e5664969c1ca2ab468ef
size: 3403
params:
params.yaml:
log_level: INFO
plot_format: png
plots:
colors:
agent_aliases:
Claude 3.5 Sonnet (New):
light: '#B784ED'
base: '#8B4DC9'
dark: '#5F2B94'
Claude 3.5 Sonnet (Old):
light: '#D4B6F2'
base: '#9B6BE0'
dark: '#6B3DB0'
Claude 3 Opus:
light: '#E5D4F7'
base: '#B594E8'
dark: '#7A5BA6'
GPT-4o:
light: '#45B3D6'
base: '#2B8FB0'
dark: '#1A5668'
GPT-4 Turbo:
light: '#7CC3DB'
base: '#4A9CBD'
dark: '#2C6B8F'
GPT-4 0314:
light: '#ADD8E6'
base: '#87CEEB'
dark: '#4682B4'
davinci-002:
light: '#E0F3FF'
base: '#B3E0FF'
dark: '#80C4FF'
gpt-3.5-turbo-instruct:
light: '#F0F8FF'
base: '#CCE6FF'
dark: '#99CCFF'
o1:
light: '#90EE90'
base: '#228B22'
dark: '#006400'
o1-preview:
light: '#98FB98'
base: '#3CB371'
dark: '#2E8B57'
human:
light: '#c9c9c9'
base: '#858585'
dark: '#484848'
default: '#000000'
legend_order:
- Claude 3 Opus
- Claude 3.5 Sonnet (New)
- Claude 3.5 Sonnet (Old)
- GPT-4 Turbo
- GPT-4 0314
- GPT-4o
- davinci
- gpt2
- o1-preview
- o1
- Human 8-hour score
weighting:
- weight_col: equal_task_weight
graph_snippet: Equally weighted tasks
- weight_col: invsqrt_task_weight
graph_snippet: Tasks diversity-weighted (1/sqrt(n))
- weight_col:
graph_snippet: None
outs:
- path: plots/logistic/invsqrt_task_weight-0.1-true-ftr-2024-01-01-distr_full.png
hash: md5
md5: 1425dfc31c18c48777663903597a9d3a
size: 106074
plot_logistic_regression@invsqrt_task_weight-ftr-0.1-true-full-2023-03-13:
cmd: python -m src.plot.logistic --input-file data/wrangled/logistic_regression_invsqrt_task_weight_0.1_ftr.csv
--runs-file data/external/all_runs.jsonl --release-dates data/external/release_dates.yaml
--output-file plots/logistic/invsqrt_task_weight-0.1-true-ftr-2023-03-13-distr_full.png
--log-level INFO --trendlines true --after-date 2023-03-13 --weighting "invsqrt_task_weight"
--include-task-distribution full
deps:
- path: data/external/all_runs.jsonl
hash: md5
md5: 14a6f449504ad678b4be46430ac64461
size: 6196702
- path: data/external/release_dates.yaml
hash: md5
md5: caa7031aaaa86f4ef7298052b3b5a486
size: 511
- path: data/wrangled/logistic_regression_invsqrt_task_weight_0.1_ftr.csv
hash: md5
md5: 4cc83cf3e16977b197479ff812176923
size: 3133
- path: matplotlibrc
hash: md5
md5: e5c44785adee259a340f12544e2cb856
size: 526
- path: src/plot/logistic.py
hash: md5
md5: 97f205c6c3976ed03f82ba854c886232
size: 14366
- path: src/utils/plots.py
hash: md5
md5: 2281a64c4bcb5d3207ce05911784d91c
size: 3367
params:
params.yaml:
log_level: INFO
plot_format: png
plots:
colors:
agent_aliases:
Claude 3.5 Sonnet (New):
light: '#B784ED'
base: '#8B4DC9'
dark: '#5F2B94'
Claude 3.5 Sonnet (Old):
light: '#D4B6F2'
base: '#9B6BE0'
dark: '#6B3DB0'
Claude 3 Opus:
light: '#E5D4F7'
base: '#B594E8'
dark: '#7A5BA6'
GPT-4o:
light: '#45B3D6'
base: '#2B8FB0'
dark: '#1A5668'
GPT-4 Turbo:
light: '#7CC3DB'
base: '#4A9CBD'
dark: '#2C6B8F'
GPT-4 0314:
light: '#ADD8E6'
base: '#87CEEB'
dark: '#4682B4'
davinci-002:
light: '#E0F3FF'
base: '#B3E0FF'
dark: '#80C4FF'
gpt-3.5-turbo-instruct:
light: '#F0F8FF'
base: '#CCE6FF'
dark: '#99CCFF'
o1:
light: '#90EE90'
base: '#228B22'
dark: '#006400'
o1-preview:
light: '#98FB98'
base: '#3CB371'
dark: '#2E8B57'
human:
light: '#c9c9c9'
base: '#858585'
dark: '#484848'
default: '#000000'
legend_order:
- Claude 3 Opus
- Claude 3.5 Sonnet (New)
- Claude 3.5 Sonnet (Old)
- GPT-4 Turbo
- GPT-4 0314
- GPT-4o
- davinci
- gpt2
- o1-preview
- o1
- Human 8-hour score