Randomfoo's workspace
Runs
12
Name
6 visualized
1-12
of 12runs.summary["jaster_leaderboard_table"]
- 5 of 6
shisa-gamma-7b-v1
0.5194
0.0297
0.1346
0.86
0.45
0.756
0.4919
0.9137
shisa-7b-v1
0.4688
0
0.0027
0.92
0.21
0.87
0.3926
0.8861
shisa-llama3-8b-v1.jaster
0.3167
0.0085
0.0655
0.88
0
0.228
0.3031
0.7319
shisa-gemma-7b-v1.jaster
0.0208
0
0.0195
0
0
0
0.0338
0.0925
shisa-v1-llama3-70b.jaster
0.0091
0
0.0268
0
0
0
0.0168
0.0199
run.name
AVG_jaster
EL
FA
MC
MR
NLI
QA
RC
chabsa_set_f1
jamp_exact_match
janli_exact_match
jcommonsenseqa_exact_match
jemhopqa_char_f1
jnli_exact_match
jsem_exact_match
jsick_exact_match
jsquad_char_f1
mawps_exact_match
niilc_char_f1
wiki_coreference_set_f1
wiki_dependency_set_f1
wiki_ner_set_f1
wiki_pas_set_f1
wiki_reading_char_f1
basemodel_name
model_type
instruction_tuning_method
instruction_tuning_data
num_few_shots
llm-jp-eval-version
data_type
top_p
top_k
temperature
repetition_penalty
6
5
3
2
1