mtasic85's picture
eval
1da24fe
|
raw
history blame
17.4 kB
metadata
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
language:
  - en
  - am
  - ar
  - as
  - az
  - be
  - bg
  - bn
  - br
  - bs
  - ca
  - cs
  - cy
  - da
  - de
  - el
  - eo
  - es
  - et
  - eu
  - fa
  - ff
  - fi
  - fr
  - fy
  - ga
  - gd
  - gl
  - gn
  - gu
  - ha
  - he
  - hi
  - hr
  - ht
  - hu
  - hy
  - id
  - ig
  - is
  - it
  - ja
  - jv
  - ka
  - kk
  - km
  - kn
  - ko
  - ku
  - ky
  - la
  - lg
  - li
  - ln
  - lo
  - lt
  - lv
  - mg
  - mk
  - ml
  - mn
  - mr
  - ms
  - my
  - ne
  - nl
  - 'no'
  - ns
  - om
  - or
  - pa
  - pl
  - ps
  - pt
  - qu
  - rm
  - ro
  - ru
  - sa
  - si
  - sc
  - sd
  - sk
  - sl
  - so
  - sq
  - sr
  - ss
  - su
  - sv
  - sw
  - ta
  - te
  - th
  - tl
  - tn
  - tr
  - ug
  - uk
  - ur
  - uz
  - vi
  - wo
  - xh
  - yi
  - yo
  - zu
datasets:
  - bigcode/programming-languages-keywords
  - bigcode/the-stack-smol-xs
  - nampdn-ai/tiny-textbooks
  - xu-song/cc100-samples
  - m-a-p/CodeFeedback-Filtered-Instruction
  - nampdn-ai/tiny-codes
  - ajibawa-2023/Maths-College
  - microsoft/orca-math-word-problems-200k
  - mlabonne/FineTome-100k
  - arcee-ai/agent-data
  - cognitivecomputations/SystemChat-2.0
  - badrex/llm-emoji-dataset
tags:
  - litgpt
  - litdata

tangled-llama-33m-32k-base-v0.1

logo

A pretrained language model based on the Llama model with about 33M parameters. This model has been trained on 9.7B (9,782,206,713) tokens from more than 5.2M (5,285,575) dataset rows.

This model isn't designed for immediate use but rather for Continued Pretraining and Finetuning on a downstream task. While it can handle a context length of up to 32K (32,768) tokens, it was pretrained with sequences of 2K (2048) tokens.

The objective is to streamline the cognitive or reasoning core, eliminating any redundant knowledge from the model.

loss, val_loss

val_ppl

epoch

learning_rate

lm-evaluation-harness

litgpt evaluate --tasks 'leaderboard' --out_dir 'evaluate-0/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
Tasks Version Filter n-shot Metric Value Stderr
leaderboard N/A
- leaderboard_bbh N/A
- leaderboard_bbh_boolean_expressions 1 none 3 acc_norm 0.4600 ± 0.0316
- leaderboard_bbh_causal_judgement 1 none 3 acc_norm 0.5187 ± 0.0366
- leaderboard_bbh_date_understanding 1 none 3 acc_norm 0.1600 ± 0.0232
- leaderboard_bbh_disambiguation_qa 1 none 3 acc_norm 0.3000 ± 0.0290
- leaderboard_bbh_formal_fallacies 1 none 3 acc_norm 0.4680 ± 0.0316
- leaderboard_bbh_geometric_shapes 1 none 3 acc_norm 0.0400 ± 0.0124
- leaderboard_bbh_hyperbaton 1 none 3 acc_norm 0.5240 ± 0.0316
- leaderboard_bbh_logical_deduction_five_objects 1 none 3 acc_norm 0.2240 ± 0.0264
- leaderboard_bbh_logical_deduction_seven_objects 1 none 3 acc_norm 0.1480 ± 0.0225
- leaderboard_bbh_logical_deduction_three_objects 1 none 3 acc_norm 0.3160 ± 0.0295
- leaderboard_bbh_movie_recommendation 1 none 3 acc_norm 0.2560 ± 0.0277
- leaderboard_bbh_navigate 1 none 3 acc_norm 0.4200 ± 0.0313
- leaderboard_bbh_object_counting 1 none 3 acc_norm 0.0680 ± 0.0160
- leaderboard_bbh_penguins_in_a_table 1 none 3 acc_norm 0.1918 ± 0.0327
- leaderboard_bbh_reasoning_about_colored_objects 1 none 3 acc_norm 0.1160 ± 0.0203
- leaderboard_bbh_ruin_names 1 none 3 acc_norm 0.2000 ± 0.0253
- leaderboard_bbh_salient_translation_error_detection 1 none 3 acc_norm 0.1320 ± 0.0215
- leaderboard_bbh_snarks 1 none 3 acc_norm 0.4719 ± 0.0375
- leaderboard_bbh_sports_understanding 1 none 3 acc_norm 0.4600 ± 0.0316
- leaderboard_bbh_temporal_sequences 1 none 3 acc_norm 0.2880 ± 0.0287
- leaderboard_bbh_tracking_shuffled_objects_five_objects 1 none 3 acc_norm 0.1880 ± 0.0248
- leaderboard_bbh_tracking_shuffled_objects_seven_objects 1 none 3 acc_norm 0.1280 ± 0.0212
- leaderboard_bbh_tracking_shuffled_objects_three_objects 1 none 3 acc_norm 0.3040 ± 0.0292
- leaderboard_bbh_web_of_lies 1 none 3 acc_norm 0.4880 ± 0.0317
- leaderboard_gpqa N/A
- leaderboard_gpqa_diamond 1 none 0 acc_norm 0.2222 ± 0.0296
- leaderboard_gpqa_extended 1 none 0 acc_norm 0.2381 ± 0.0182
- leaderboard_gpqa_main 1 none 0 acc_norm 0.2478 ± 0.0204
- leaderboard_ifeval 3 none 0 inst_level_loose_acc 0.1859 ± N/A
none 0 inst_level_strict_acc 0.1811 ± N/A
none 0 prompt_level_loose_acc 0.0906 ± 0.0124
none 0 prompt_level_strict_acc 0.0832 ± 0.0119
- leaderboard_math_hard N/A
- leaderboard_math_algebra_hard 1 none 4 exact_match 0.0000 ± 0
- leaderboard_math_counting_and_prob_hard 1 none 4 exact_match 0.0000 ± 0
- leaderboard_math_geometry_hard 1 none 4 exact_match 0.0000 ± 0
- leaderboard_math_intermediate_algebra_hard 1 none 4 exact_match 0.0000 ± 0
- leaderboard_math_num_theory_hard 1 none 4 exact_match 0.0000 ± 0
- leaderboard_math_prealgebra_hard 1 none 4 exact_match 0.0000 ± 0
- leaderboard_math_precalculus_hard 1 none 4 exact_match 0.0000 ± 0
- leaderboard_mmlu_pro 0.1 none 5 acc 0.1100 ± 0.0029
- leaderboard_musr N/A
- leaderboard_musr_murder_mysteries 1 none 0 acc_norm 0.5000 ± 0.0317
- leaderboard_musr_object_placements 1 none 0 acc_norm 0.2930 ± 0.0285
- leaderboard_musr_team_allocation 1 none 0 acc_norm 0.3720 ± 0.0306
litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,winogrande,arc_challenge' --out_dir 'evaluate-1/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
Tasks Version Filter n-shot Metric Value Stderr
arc_challenge 1 none 0 acc 0.2048 ± 0.0118
none 0 acc_norm 0.2372 ± 0.0124
gsm8k 3 flexible-extract 5 exact_match 0.0091 ± 0.0026
strict-match 5 exact_match 0.0000 ± 0.0000
hellaswag 1 none 0 acc 0.2613 ± 0.0044
none 0 acc_norm 0.2605 ± 0.0044
mmlu 2 none acc 0.2280 ± 0.0035
- humanities 2 none acc 0.2366 ± 0.0062
- formal_logic 1 none 0 acc 0.2778 ± 0.0401
- high_school_european_history 1 none 0 acc 0.2061 ± 0.0316
- high_school_us_history 1 none 0 acc 0.2402 ± 0.0300
- high_school_world_history 1 none 0 acc 0.2827 ± 0.0293
- international_law 1 none 0 acc 0.2149 ± 0.0375
- jurisprudence 1 none 0 acc 0.2315 ± 0.0408
- logical_fallacies 1 none 0 acc 0.2209 ± 0.0326
- moral_disputes 1 none 0 acc 0.2370 ± 0.0229
- moral_scenarios 1 none 0 acc 0.2380 ± 0.0142
- philosophy 1 none 0 acc 0.1833 ± 0.0220
- prehistory 1 none 0 acc 0.2191 ± 0.0230
- professional_law 1 none 0 acc 0.2360 ± 0.0108
- world_religions 1 none 0 acc 0.3275 ± 0.0360
- other 2 none acc 0.2485 ± 0.0077
- business_ethics 1 none 0 acc 0.3100 ± 0.0465
- clinical_knowledge 1 none 0 acc 0.2226 ± 0.0256
- college_medicine 1 none 0 acc 0.2486 ± 0.0330
- global_facts 1 none 0 acc 0.1700 ± 0.0378
- human_aging 1 none 0 acc 0.3229 ± 0.0314
- management 1 none 0 acc 0.1748 ± 0.0376
- marketing 1 none 0 acc 0.3034 ± 0.0301
- medical_genetics 1 none 0 acc 0.3100 ± 0.0465
- miscellaneous 1 none 0 acc 0.2414 ± 0.0153
- nutrition 1 none 0 acc 0.2484 ± 0.0247
- professional_accounting 1 none 0 acc 0.2411 ± 0.0255
- professional_medicine 1 none 0 acc 0.1838 ± 0.0235
- virology 1 none 0 acc 0.2831 ± 0.0351
- social sciences 2 none acc 0.2158 ± 0.0074
- econometrics 1 none 0 acc 0.2368 ± 0.0400
- high_school_geography 1 none 0 acc 0.1768 ± 0.0272
- high_school_government_and_politics 1 none 0 acc 0.1969 ± 0.0287
- high_school_macroeconomics 1 none 0 acc 0.2103 ± 0.0207
- high_school_microeconomics 1 none 0 acc 0.2143 ± 0.0267
- high_school_psychology 1 none 0 acc 0.1890 ± 0.0168
- human_sexuality 1 none 0 acc 0.2672 ± 0.0388
- professional_psychology 1 none 0 acc 0.2451 ± 0.0174
- public_relations 1 none 0 acc 0.2091 ± 0.0390
- security_studies 1 none 0 acc 0.1755 ± 0.0244
- sociology 1 none 0 acc 0.2488 ± 0.0306
- us_foreign_policy 1 none 0 acc 0.2700 ± 0.0446
- stem 2 none acc 0.2068 ± 0.0072
- abstract_algebra 1 none 0 acc 0.1700 ± 0.0378
- anatomy 1 none 0 acc 0.1778 ± 0.0330
- astronomy 1 none 0 acc 0.1842 ± 0.0315
- college_biology 1 none 0 acc 0.2569 ± 0.0365
- college_chemistry 1 none 0 acc 0.1900 ± 0.0394
- college_computer_science 1 none 0 acc 0.2600 ± 0.0441
- college_mathematics 1 none 0 acc 0.2100 ± 0.0409
- college_physics 1 none 0 acc 0.2059 ± 0.0402
- computer_security 1 none 0 acc 0.2400 ± 0.0429
- conceptual_physics 1 none 0 acc 0.2681 ± 0.0290
- electrical_engineering 1 none 0 acc 0.2345 ± 0.0353
- elementary_mathematics 1 none 0 acc 0.2011 ± 0.0206
- high_school_biology 1 none 0 acc 0.1839 ± 0.0220
- high_school_chemistry 1 none 0 acc 0.1527 ± 0.0253
- high_school_computer_science 1 none 0 acc 0.2400 ± 0.0429
- high_school_mathematics 1 none 0 acc 0.2111 ± 0.0249
- high_school_physics 1 none 0 acc 0.1722 ± 0.0308
- high_school_statistics 1 none 0 acc 0.1667 ± 0.0254
- machine_learning 1 none 0 acc 0.2768 ± 0.0425
truthfulqa_mc2 2 none 0 acc 0.4971 ± 0.0165
winogrande 1 none 0 acc 0.5114 ± 0.0140
Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc 0.2280 ± 0.0035
- humanities 2 none acc 0.2366 ± 0.0062
- other 2 none acc 0.2485 ± 0.0077
- social sciences 2 none acc 0.2158 ± 0.0074
- stem 2 none acc 0.2068 ± 0.0072