Commit History

Handle 'word_perplexity' metric without multiplying by 100
7bc6ac3

idolezal commited on

Changed order of columns with sort by names
2be8bdf

idolezal commited on

Display model name with smaller font
a0fa84e

idolezal commited on

Changed delimeter between team name and model name
886492f

idolezal commited on

Create lock for global variables
ec6e1e5

idolezal commited on

Ensure the leaderboard is up-to-date before the tournament started
f6916e3

idolezal commited on

Fix infinite loop
b7293e7

idolezal commited on

Revert "More debug informations"
b4922c8

idolezal commited on

More debug informations
6755cfb

idolezal commited on

Set timeout for connection
3860f94

idolezal commited on

Fix progress info
d636f3d

idolezal commited on

Try to make HTTPS works again
8e9c817

idolezal commited on

Try to keep on 10 check significance tasks
91b9cf7

idolezal commited on

More info about tournament progress
6196b87

idolezal commited on

Better info
b176fe0

idolezal commited on

Send more task for remote check significance
ff77a20

idolezal commited on

Improved safety of submission race condition
97092f5

idolezal commited on

Changed user to organization
cc5fdd9

idolezal commited on

Do not contest against itself
7d240ad

idolezal commited on

Enable add to empty table
6845288

idolezal commited on

Try port 443
6362604

idolezal commited on

Take attention on task state
822c3a6

idolezal commited on

HTTPS works
48c616c

idolezal commited on

Fix debug
3efe661

idolezal commited on

Try different port
a737c6b

idolezal commited on

Shorter table header for column "parameters"
0cd1497

idolezal commited on

External check_significance() at czechllm.fit.vutbr.cz
23ee797

idolezal commited on

Added attribute Input length (# tokens) to submission
76b7a19

idolezal commited on

metric_value * 100
8f5a802

idolezal commited on

Revert "Sort by average_score"
a136ee1

idolezal commited on

Sort by average_score
d57645c

idolezal commited on

Rename category Overall
f46c803

idolezal commited on

Category of benchmark
1b0a7e3

idolezal commited on

task_score * 100
66ea54e

idolezal commited on

Fix average_score
e8d3984

idolezal commited on

Fix variable name task_score
11d85cb

idolezal commited on

Compute win_score and average_score
f0196fa

idolezal commited on

Win Score to Average Score
fb91218

idolezal commited on

Only the first metric of every task
b0f3766

idolezal commited on

local_results[task] = num_of_wins / num_of_competitors
f65e5c0

idolezal commited on

Markdown esacape
ff6fff7

idolezal commited on