Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: [cb_adf_explore] prog val print known label #2961

Merged
merged 4 commits into from Apr 27, 2021
Merged

feat: [cb_adf_explore] prog val print known label #2961

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
affcf23
feat: [cb_adf_explore] prog val print known label
lalo Apr 26, 2021
bec7260
Update test_vwconfig.py
lalo Apr 26, 2021
8477b63
Update cb_explore_adf_common.h
lalo Apr 26, 2021
6a8cf10
Merge branch 'master' into adf_explore_known_label
lalo Apr 27, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion python/tests/test_vwconfig.py
View file
Open in desktop
Expand Up @@ -47,4 +47,4 @@ def test_vw_get_all_options():
for name, config_group in config.items():
cmd_str_list.add(name)

assert len(cmd_str_list) >= 74
assert len(cmd_str_list) >= 74
6 changes: 3 additions & 3 deletions test/pred-sets/ref/override_epsilon.stderr
View file
Open in desktop
Expand Up @@ -9,9 +9,9 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_greedy, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
-1.700000 -1.700000 1 1.0 known 0:0.85... 4
-0.850000 0.000000 2 2.0 known 0:0.85... 4
-0.850000 -0.850000 4 4.0 known 0:0.85... 4
-1.700000 -1.700000 1 1.0 0:-1:0.5 0:0.85... 4
-0.850000 0.000000 2 2.0 0:0:0.5 0:0.85... 4
-0.850000 -0.850000 4 4.0 0:0:0.5 0:0.85... 4

finished run
number of examples = 4
Expand Down
2 changes: 1 addition & 1 deletion test/train-sets/ref/cb_adf_crash1.stderr
View file
Open in desktop
Expand Up @@ -9,7 +9,7 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_greedy, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
-7.500000 -7.500000 1 1.0 known 0:0.5... 4
-7.500000 -7.500000 1 1.0 0:-3:0.2 0:0.5... 4

finished run
number of examples = 1
Expand Down
2 changes: 1 addition & 1 deletion test/train-sets/ref/cb_as_ccb.cb.stderr
View file
Open in desktop
Expand Up @@ -10,7 +10,7 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_greedy, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
-2.500000 -2.500000 1 1.0 known 0:0.5... 4
-2.500000 -2.500000 1 1.0 1:-1:0.2 0:0.5... 4

finished run
number of examples = 1
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cb_zero_feature_vals.stderr
View file
Open in desktop
Expand Up @@ -9,8 +9,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_greedy, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 3
0.333333 0.000000 2 2.0 known 0:0.5... 8
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 3
0.333333 0.000000 2 2.0 1:0:0.5 0:0.5... 8

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cb_zero_feature_vals_dsjson.stderr
View file
Open in desktop
Expand Up @@ -10,8 +10,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_greedy, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
-1.000000 -1.000000 1 1.0 known 0:0.5... 2
-1.000000 -1.000000 2 2.0 known 0:0.5... 2
-1.000000 -1.000000 1 1.0 0:-1:0.5 0:0.5... 2
-1.000000 -1.000000 2 2.0 0:-1:0.5 0:0.5... 2

finished run
number of examples = 2
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_bag.stderr
View file
Open in desktop
Expand Up @@ -9,8 +9,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_bag, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 0:0.5... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 0:0.5... 6

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_cover.stderr
View file
Open in desktop
Expand Up @@ -10,8 +10,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_cover, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 0:0.5... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 0:0.5... 6

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_cover_dr.json.stderr
View file
Open in desktop
Expand Up @@ -9,8 +9,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_cover, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 0:0.5... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 0:0.5... 6

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_cover_dr.stderr
View file
Open in desktop
Expand Up @@ -9,8 +9,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_cover, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 0:0.5... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 0:0.5... 6

finished run
number of examples = 3
Expand Down
18 changes: 9 additions & 9 deletions test/train-sets/ref/cbe_adf_cover_dr256.json.stderr
View file
Open in desktop
Expand Up @@ -9,15 +9,15 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_cover, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 0:0.5... 6
0.333333 0.333333 4 4.0 known 1:0.591752... 6
0.297761 0.262189 8 8.0 known 1:0.666667... 6
0.237339 0.176917 16 16.0 known 1:0.666667... 6
0.179808 0.122276 32 32.0 known 1:0.666667... 6
0.132652 0.085496 64 64.0 known 1:0.666667... 6
0.096385 0.060119 128 128.0 known 1:0.666667... 6
0.069389 0.042393 256 256.0 known 1:0.666667... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 0:0.5... 6
0.333333 0.333333 4 4.0 1:0:0.5 1:0.591752... 6
0.297761 0.262189 8 8.0 1:0:0.5 1:0.666667... 6
0.237339 0.176917 16 16.0 1:0:0.5 1:0.666667... 6
0.179808 0.122276 32 32.0 1:0:0.5 1:0.666667... 6
0.132652 0.085496 64 64.0 1:0:0.5 1:0.666667... 6
0.096385 0.060119 128 128.0 1:0:0.5 1:0.666667... 6
0.069389 0.042393 256 256.0 1:0:0.5 1:0.666667... 6

finished run
number of examples = 260
Expand Down
8 changes: 4 additions & 4 deletions test/train-sets/ref/cbe_adf_cover_e_dec.stderr
View file
Open in desktop
Expand Up @@ -10,10 +10,10 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_cover, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 0:0.5... 6
0.444444 0.666667 4 4.0 known 0:0.333333... 9
0.318447 0.192450 8 8.0 known 1:0.683772... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 0:0.5... 6
0.444444 0.666667 4 4.0 0:1:0.5 0:0.333333... 9
0.318447 0.192450 8 8.0 1:0:0.5 1:0.683772... 6

finished run
number of examples = 15
Expand Down
8 changes: 4 additions & 4 deletions test/train-sets/ref/cbe_adf_cover_e_dec_predict.stderr
View file
Open in desktop
Expand Up @@ -11,10 +11,10 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_cover, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.365148 0.365148 1 1.0 known 2:0.634852... 9
0.182574 0.000000 2 2.0 known 1:0.666667... 6
0.243432 0.365148 4 4.0 known 2:0.634852... 9
0.182574 0.121716 8 8.0 known 1:0.666667... 6
0.365148 0.365148 1 1.0 0:1:0.5 2:0.634852... 9
0.182574 0.000000 2 2.0 1:0:0.5 1:0.666667... 6
0.243432 0.365148 4 4.0 0:1:0.5 2:0.634852... 9
0.182574 0.121716 8 8.0 1:0:0.5 1:0.666667... 6

finished run
number of examples = 15
Expand Down
8 changes: 4 additions & 4 deletions test/train-sets/ref/cbe_adf_cover_e_fixed.stderr
View file
Open in desktop
Expand Up @@ -10,10 +10,10 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_cover, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 12
0.333333 0.000000 2 2.0 known 1:0.75... 8
0.333333 0.333333 4 4.0 known 1:0.666667... 12
0.222222 0.111111 8 8.0 known 1:0.75... 8
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 12
0.333333 0.000000 2 2.0 1:0:0.5 1:0.75... 8
0.333333 0.333333 4 4.0 0:1:0.5 1:0.666667... 12
0.222222 0.111111 8 8.0 1:0:0.5 1:0.75... 8

finished run
number of examples = 15
Expand Down
8 changes: 4 additions & 4 deletions test/train-sets/ref/cbe_adf_cover_e_fixed_predict.stderr
View file
Open in desktop
Expand Up @@ -11,10 +11,10 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_cover, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.333333 0.333333 1 1.0 known 1:0.555556... 12
0.166667 0.000000 2 2.0 known 1:0.666667... 8
0.222222 0.333333 4 4.0 known 1:0.555556... 12
0.166667 0.111111 8 8.0 known 1:0.666667... 8
0.333333 0.333333 1 1.0 0:1:0.5 1:0.555556... 12
0.166667 0.000000 2 2.0 1:0:0.5 1:0.666667... 8
0.222222 0.333333 4 4.0 0:1:0.5 1:0.555556... 12
0.166667 0.111111 8 8.0 1:0:0.5 1:0.666667... 8

finished run
number of examples = 15
Expand Down
6 changes: 3 additions & 3 deletions test/train-sets/ref/cbe_adf_dsjson.stderr
View file
Open in desktop
Expand Up @@ -11,9 +11,9 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_greedy, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
-0.102041 -0.102041 1 1.0 known 0:0.0833333... 361
-0.051020 0.000000 2 2.0 known 6:0.816667... 361
-0.040816 -0.020408 3 3.0 known 6:0.816667... 361
-0.102041 -0.102041 1 1.0 9:-1:0.82 0:0.0833333... 361
-0.051020 0.000000 2 2.0 9:0:0.82 6:0.816667... 361
-0.040816 -0.020408 3 3.0 9:-1:0.82 6:0.816667... 361

finished run
number of examples = 3
Expand Down
8 changes: 4 additions & 4 deletions test/train-sets/ref/cbe_adf_dsjson_chain_hash.stderr
View file
Open in desktop
@@ -1,4 +1,4 @@
creating quadratic features for pairs: GT
creating quadratic features for pairs: GT
predictions = cbe_adf_dsjson_chain_hash.predict
Num weight bits = 18
learning rate = 0.5
Expand All @@ -10,9 +10,9 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_greedy, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
-0.102041 -0.102041 1 1.0 known 0:0.0833333... 361
-0.051020 0.000000 2 2.0 known 6:0.816667... 361
-0.040816 -0.020408 3 3.0 known 6:0.816667... 361
-0.102041 -0.102041 1 1.0 9:-1:0.82 0:0.0833333... 361
-0.051020 0.000000 2 2.0 9:0:0.82 6:0.816667... 361
-0.040816 -0.020408 3 3.0 9:-1:0.82 6:0.816667... 361

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_epsilon.stderr
View file
Open in desktop
Expand Up @@ -9,8 +9,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_greedy, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 1:0.95... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 1:0.95... 6

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_first.stderr
View file
Open in desktop
Expand Up @@ -9,8 +9,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_first, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 1:0.5... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 1:0.5... 6

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_nonewline.stderr
View file
Open in desktop
Expand Up @@ -9,8 +9,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_greedy, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 1:0.95... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 1:0.95... 6

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_rnd.stderr
View file
Open in desktop
Expand Up @@ -9,8 +9,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_rnd, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.719921 0.719921 1 1.0 known 0:0.35996... 9
0.359960 0.000000 2 2.0 known 1:0.932997... 6
0.719921 0.719921 1 1.0 0:1:0.5 0:0.35996... 9
0.359960 0.000000 2 2.0 1:0:0.5 1:0.932997... 6

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_softmax.stderr
View file
Open in desktop
Expand Up @@ -9,8 +9,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_softmax, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 1:0.559575... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 1:0.559575... 6

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_softmax_biglambda.stderr
View file
Open in desktop
Expand Up @@ -9,8 +9,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_softmax, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.666667 0.666667 1 1.0 known 0:0.333333... 9
0.333333 0.000000 2 2.0 known 1:1... 6
0.666667 0.666667 1 1.0 0:1:0.5 0:0.333333... 9
0.333333 0.000000 2 2.0 1:0:0.5 1:1... 6

finished run
number of examples = 3
Expand Down
4 changes: 2 additions & 2 deletions test/train-sets/ref/cbe_adf_synthcover.stderr
View file
Open in desktop
Expand Up @@ -13,8 +13,8 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_synthcover, shared_feature_merger
average since example example current current current
loss last counter weight label predict features
0.660000 0.660000 1 1.0 known 2:0.34... 9
0.330000 0.000000 2 2.0 known 1:0.995... 6
0.660000 0.660000 1 1.0 0:1:0.5 2:0.34... 9
0.330000 0.000000 2 2.0 1:0:0.5 1:0.995... 6

finished run
number of examples = 3
Expand Down
8 changes: 4 additions & 4 deletions test/train-sets/ref/cbe_cover_e_dec.stderr
View file
Open in desktop
Expand Up @@ -11,10 +11,10 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_cover, shared_feature_merger, cb_to_cbadf
average since example example current current current
loss last counter weight label predict features
0.000000 0.000000 1 1.0 known 0:0.5... 6
0.500000 1.000000 2 2.0 known 0:0.5... 6
0.658248 0.816497 4 4.0 known 1:0.591752... 6
0.590289 0.522329 8 8.0 known 0:0.666667... 6
0.000000 0.000000 1 1.0 0:0:0.5 0:0.5... 6
0.500000 1.000000 2 2.0 1:1:0.5 0:0.5... 6
0.658248 0.816497 4 4.0 0:2:0.5 1:0.591752... 6
0.590289 0.522329 8 8.0 1:1:0.5 0:0.666667... 6

finished run
number of examples = 8
Expand Down
8 changes: 4 additions & 4 deletions test/train-sets/ref/cbe_cover_e_dec_predict.stderr
View file
Open in desktop
Expand Up @@ -11,10 +11,10 @@ num sources = 1
Enabled reductions: gd, scorer, csoaa_ldf, cb_adf, cb_explore_adf_cover, shared_feature_merger, cb_to_cbadf
average since example example current current current
loss last counter weight label predict features
0.000000 0.000000 1 1.0 known 1:0.75... 6
0.250000 0.500000 2 2.0 known 0:0.75... 6
0.375000 0.500000 4 4.0 known 1:0.75... 6
0.437500 0.500000 8 8.0 known 0:0.75... 6
0.000000 0.000000 1 1.0 0:0:0.5 1:0.75... 6
0.250000 0.500000 2 2.0 1:1:0.5 0:0.75... 6
0.375000 0.500000 4 4.0 0:2:0.5 1:0.75... 6
0.437500 0.500000 8 8.0 1:1:0.5 0:0.75... 6

finished run
number of examples = 8
Expand Down