|
---
|
|
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: [
|
|
'xu-song/cc100-samples',
|
|
'jordiclive/wikipedia-summary-dataset',
|
|
'JeanKaddour/minipile',
|
|
'badrex/llm-emoji-dataset',
|
|
'fblgit/simple-math',
|
|
'Gusarich/math-expressions-1m',
|
|
'AtlasUnified/atlas-math-sets',
|
|
'gair-prox/open-web-math-pro',
|
|
'bigcode/the-stack-smol-xs',
|
|
'rombodawg/code_bagel',
|
|
'AtlasUnified/Atlas-Reasoning',
|
|
'thesven/gsm8k-reasoning',
|
|
'AlgorithmicResearchGroup/math_reasoning_autoformalization_track',
|
|
'KingNish/reasoning-base-20k',
|
|
'SkunkworksAI/reasoning-0.01',
|
|
'Magpie-Align/Magpie-Reasoning-150K',
|
|
]
|
|
tags:
|
|
- litgpt
|
|
- litdata
|
|
---
|
|
|
|
# tangled-llama-a-128k-base-v0.1
|
|
|
|
|
|
|
|
A pretrained language model based on the Llama model with about **62.9M** parameters. This model has been trained on **10.6B** (`10,630,121,844`) tokens from more than **31.3M** (`31,383,840`) 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 **128K** (`131,072`) 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](https://api.wandb.ai/links/mtasic85/strnx9rl)
|
|
|
|
[val_ppl](https://api.wandb.ai/links/mtasic85/ljwxf4am)
|
|
|
|
[epoch](https://api.wandb.ai/links/mtasic85/edyph869)
|
|
|
|
[learning_rate](https://api.wandb.ai/links/mtasic85/eswxyger)
|
|
|
|
## Pretrain Evaluation
|
|
|
|
### lm-evaluation-harness
|
|
|
|
```bash
|
|
litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,winogrande,arc_challenge' --out_dir 'evaluate-quick/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
```
|
|
|
|
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
|
|---------------------------------------|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
|
|arc_challenge | 1|none | 0|acc |↑ |0.2176|± |0.0121|
|
|
| | |none | 0|acc_norm |↑ |0.2560|± |0.0128|
|
|
|gsm8k | 3|flexible-extract| 5|exact_match|↑ |0.0190|± |0.0038|
|
|
| | |strict-match | 5|exact_match|↑ |0.0000|± |0.0000|
|
|
|hellaswag | 1|none | 0|acc |↑ |0.2618|± |0.0044|
|
|
| | |none | 0|acc_norm |↑ |0.2592|± |0.0044|
|
|
|mmlu | 2|none | |acc |↑ |0.2464|± |0.0036|
|
|
| - humanities | 2|none | |acc |↑ |0.2485|± |0.0063|
|
|
| - formal_logic | 1|none | 0|acc |↑ |0.3175|± |0.0416|
|
|
| - high_school_european_history | 1|none | 0|acc |↑ |0.2364|± |0.0332|
|
|
| - high_school_us_history | 1|none | 0|acc |↑ |0.2402|± |0.0300|
|
|
| - high_school_world_history | 1|none | 0|acc |↑ |0.2785|± |0.0292|
|
|
| - international_law | 1|none | 0|acc |↑ |0.2314|± |0.0385|
|
|
| - jurisprudence | 1|none | 0|acc |↑ |0.2407|± |0.0413|
|
|
| - logical_fallacies | 1|none | 0|acc |↑ |0.2086|± |0.0319|
|
|
| - moral_disputes | 1|none | 0|acc |↑ |0.2081|± |0.0219|
|
|
| - moral_scenarios | 1|none | 0|acc |↑ |0.2693|± |0.0148|
|
|
| - philosophy | 1|none | 0|acc |↑ |0.1961|± |0.0226|
|
|
| - prehistory | 1|none | 0|acc |↑ |0.2284|± |0.0234|
|
|
| - professional_law | 1|none | 0|acc |↑ |0.2529|± |0.0111|
|
|
| - world_religions | 1|none | 0|acc |↑ |0.2982|± |0.0351|
|
|
| - other | 2|none | |acc |↑ |0.2536|± |0.0078|
|
|
| - business_ethics | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
|
| - clinical_knowledge | 1|none | 0|acc |↑ |0.2264|± |0.0258|
|
|
| - college_medicine | 1|none | 0|acc |↑ |0.2312|± |0.0321|
|
|
| - global_facts | 1|none | 0|acc |↑ |0.1500|± |0.0359|
|
|
| - human_aging | 1|none | 0|acc |↑ |0.2242|± |0.0280|
|
|
| - management | 1|none | 0|acc |↑ |0.1942|± |0.0392|
|
|
| - marketing | 1|none | 0|acc |↑ |0.3034|± |0.0301|
|
|
| - medical_genetics | 1|none | 0|acc |↑ |0.2200|± |0.0416|
|
|
| - miscellaneous | 1|none | 0|acc |↑ |0.2401|± |0.0153|
|
|
| - nutrition | 1|none | 0|acc |↑ |0.2255|± |0.0239|
|
|
| - professional_accounting | 1|none | 0|acc |↑ |0.2730|± |0.0266|
|
|
| - professional_medicine | 1|none | 0|acc |↑ |0.4081|± |0.0299|
|
|
| - virology | 1|none | 0|acc |↑ |0.2289|± |0.0327|
|
|
| - social sciences | 2|none | |acc |↑ |0.2535|± |0.0079|
|
|
| - econometrics | 1|none | 0|acc |↑ |0.2368|± |0.0400|
|
|
| - high_school_geography | 1|none | 0|acc |↑ |0.2323|± |0.0301|
|
|
| - high_school_government_and_politics| 1|none | 0|acc |↑ |0.2539|± |0.0314|
|
|
| - high_school_macroeconomics | 1|none | 0|acc |↑ |0.2436|± |0.0218|
|
|
| - high_school_microeconomics | 1|none | 0|acc |↑ |0.2311|± |0.0274|
|
|
| - high_school_psychology | 1|none | 0|acc |↑ |0.2550|± |0.0187|
|
|
| - human_sexuality | 1|none | 0|acc |↑ |0.2824|± |0.0395|
|
|
| - professional_psychology | 1|none | 0|acc |↑ |0.2484|± |0.0175|
|
|
| - public_relations | 1|none | 0|acc |↑ |0.2727|± |0.0427|
|
|
| - security_studies | 1|none | 0|acc |↑ |0.2939|± |0.0292|
|
|
| - sociology | 1|none | 0|acc |↑ |0.2488|± |0.0306|
|
|
| - us_foreign_policy | 1|none | 0|acc |↑ |0.2800|± |0.0451|
|
|
| - stem | 2|none | |acc |↑ |0.2293|± |0.0075|
|
|
| - abstract_algebra | 1|none | 0|acc |↑ |0.2200|± |0.0416|
|
|
| - anatomy | 1|none | 0|acc |↑ |0.2519|± |0.0375|
|
|
| - astronomy | 1|none | 0|acc |↑ |0.2697|± |0.0361|
|
|
| - college_biology | 1|none | 0|acc |↑ |0.2500|± |0.0362|
|
|
| - college_chemistry | 1|none | 0|acc |↑ |0.2400|± |0.0429|
|
|
| - college_computer_science | 1|none | 0|acc |↑ |0.2800|± |0.0451|
|
|
| - college_mathematics | 1|none | 0|acc |↑ |0.2000|± |0.0402|
|
|
| - college_physics | 1|none | 0|acc |↑ |0.2647|± |0.0439|
|
|
| - computer_security | 1|none | 0|acc |↑ |0.1900|± |0.0394|
|
|
| - conceptual_physics | 1|none | 0|acc |↑ |0.2340|± |0.0277|
|
|
| - electrical_engineering | 1|none | 0|acc |↑ |0.2414|± |0.0357|
|
|
| - elementary_mathematics | 1|none | 0|acc |↑ |0.1931|± |0.0203|
|
|
| - high_school_biology | 1|none | 0|acc |↑ |0.2323|± |0.0240|
|
|
| - high_school_chemistry | 1|none | 0|acc |↑ |0.2266|± |0.0295|
|
|
| - high_school_computer_science | 1|none | 0|acc |↑ |0.2400|± |0.0429|
|
|
| - high_school_mathematics | 1|none | 0|acc |↑ |0.2037|± |0.0246|
|
|
| - high_school_physics | 1|none | 0|acc |↑ |0.2185|± |0.0337|
|
|
| - high_school_statistics | 1|none | 0|acc |↑ |0.1898|± |0.0267|
|
|
| - machine_learning | 1|none | 0|acc |↑ |0.3393|± |0.0449|
|
|
|truthfulqa_mc2 | 2|none | 0|acc |↑ |0.5061|± |0.0167|
|
|
|winogrande | 1|none | 0|acc |↑ |0.4933|± |0.0141|
|
|
|
|
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
|
|mmlu | 2|none | |acc |↑ |0.2464|± |0.0036|
|
|
| - humanities | 2|none | |acc |↑ |0.2485|± |0.0063|
|
|
| - other | 2|none | |acc |↑ |0.2536|± |0.0078|
|
|
| - social sciences| 2|none | |acc |↑ |0.2535|± |0.0079|
|
|
| - stem | 2|none | |acc |↑ |0.2293|± |0.0075|
|
|
|
|
```bash
|
|
litgpt evaluate --tasks 'leaderboard' --out_dir 'evaluate-leaderboard/' --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 |↑ |0.5134|± |0.0366|
|
|
| - leaderboard_bbh_date_understanding | 1|none | 3|acc_norm |↑ |0.1360|± |0.0217|
|
|
| - leaderboard_bbh_disambiguation_qa | 1|none | 3|acc_norm |↑ |0.2960|± |0.0289|
|
|
| - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.4760|± |0.0316|
|
|
| - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.0800|± |0.0172|
|
|
| - leaderboard_bbh_hyperbaton | 1|none | 3|acc_norm |↑ |0.5120|± |0.0317|
|
|
| - leaderboard_bbh_logical_deduction_five_objects | 1|none | 3|acc_norm |↑ |0.1760|± |0.0241|
|
|
| - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1320|± |0.0215|
|
|
| - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3160|± |0.0295|
|
|
| - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.2480|± |0.0274|
|
|
| - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.4200|± |0.0313|
|
|
| - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.0360|± |0.0118|
|
|
| - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.1986|± |0.0331|
|
|
| - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.0520|± |0.0141|
|
|
| - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2760|± |0.0283|
|
|
| - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.1400|± |0.0220|
|
|
| - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.4326|± |0.0372|
|
|
| - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
|
|
| - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2680|± |0.0281|
|
|
| - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.2040|± |0.0255|
|
|
| - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1640|± |0.0235|
|
|
| - leaderboard_bbh_tracking_shuffled_objects_three_objects| 1|none | 3|acc_norm |↑ |0.3840|± |0.0308|
|
|
| - 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 |↑ |0.2778|± |0.0319|
|
|
| - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2766|± |0.0192|
|
|
| - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2031|± |0.0190|
|
|
| - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.1811|± | N/A|
|
|
| | |none | 0|inst_level_strict_acc |↑ |0.1715|± | N/A|
|
|
| | |none | 0|prompt_level_loose_acc |↑ |0.1091|± |0.0134|
|
|
| | |none | 0|prompt_level_strict_acc|↑ |0.1035|± |0.0131|
|
|
| - 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 |↑ |0.1169|± |0.0029|
|
|
| - leaderboard_musr | N/A| | | | | | | |
|
|
| - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.5080|± |0.0317|
|
|
| - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.3008|± |0.0287|
|
|
| - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.3760|± |0.0307|
|
|
|
|
```bash
|
|
litgpt evaluate --tasks 'gsm8k,mathqa' --out_dir 'evaluate-math/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
```
|
|
|
|
|Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
|
|------|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
|
|gsm8k | 3|flexible-extract| 5|exact_match|↑ |0.0190|± |0.0038|
|
|
| | |strict-match | 5|exact_match|↑ |0.0000|± |0.0000|
|
|
|mathqa| 1|none | 0|acc |↑ |0.2060|± |0.0074|
|
|
| | |none | 0|acc_norm |↑ |0.2057|± |0.0074|
|
|
|
|
```bash
|
|
litgpt evaluate --tasks 'mmlu,mmlu_pro' --out_dir 'evaluate-mmlu/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
```
|
|
|
|
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
|
|---------------------------------------|------:|--------------|-----:|-----------|---|-----:|---|-----:|
|
|
|mmlu | 2|none | |acc |↑ |0.2459|± |0.0036|
|
|
| - humanities | 2|none | |acc |↑ |0.2480|± |0.0063|
|
|
| - formal_logic | 1|none | 0|acc |↑ |0.3175|± |0.0416|
|
|
| - high_school_european_history | 1|none | 0|acc |↑ |0.2424|± |0.0335|
|
|
| - high_school_us_history | 1|none | 0|acc |↑ |0.2402|± |0.0300|
|
|
| - high_school_world_history | 1|none | 0|acc |↑ |0.2743|± |0.0290|
|
|
| - international_law | 1|none | 0|acc |↑ |0.2314|± |0.0385|
|
|
| - 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 |↑ |0.2081|± |0.0219|
|
|
| - moral_scenarios | 1|none | 0|acc |↑ |0.2670|± |0.0148|
|
|
| - philosophy | 1|none | 0|acc |↑ |0.2090|± |0.0231|
|
|
| - prehistory | 1|none | 0|acc |↑ |0.2160|± |0.0229|
|
|
| - professional_law | 1|none | 0|acc |↑ |0.2516|± |0.0111|
|
|
| - world_religions | 1|none | 0|acc |↑ |0.3041|± |0.0353|
|
|
| - other | 2|none | |acc |↑ |0.2549|± |0.0078|
|
|
| - business_ethics | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
|
| - clinical_knowledge | 1|none | 0|acc |↑ |0.2264|± |0.0258|
|
|
| - college_medicine | 1|none | 0|acc |↑ |0.2428|± |0.0327|
|
|
| - global_facts | 1|none | 0|acc |↑ |0.1600|± |0.0368|
|
|
| - human_aging | 1|none | 0|acc |↑ |0.2242|± |0.0280|
|
|
| - management | 1|none | 0|acc |↑ |0.1845|± |0.0384|
|
|
| - marketing | 1|none | 0|acc |↑ |0.2949|± |0.0299|
|
|
| - medical_genetics | 1|none | 0|acc |↑ |0.2200|± |0.0416|
|
|
| - miscellaneous | 1|none | 0|acc |↑ |0.2478|± |0.0154|
|
|
| - nutrition | 1|none | 0|acc |↑ |0.2353|± |0.0243|
|
|
| - professional_accounting | 1|none | 0|acc |↑ |0.2553|± |0.0260|
|
|
| - professional_medicine | 1|none | 0|acc |↑ |0.4118|± |0.0299|
|
|
| - virology | 1|none | 0|acc |↑ |0.2229|± |0.0324|
|
|
| - social sciences | 2|none | |acc |↑ |0.2525|± |0.0078|
|
|
| - econometrics | 1|none | 0|acc |↑ |0.2368|± |0.0400|
|
|
| - high_school_geography | 1|none | 0|acc |↑ |0.2172|± |0.0294|
|
|
| - high_school_government_and_politics| 1|none | 0|acc |↑ |0.2539|± |0.0314|
|
|
| - high_school_macroeconomics | 1|none | 0|acc |↑ |0.2410|± |0.0217|
|
|
| - high_school_microeconomics | 1|none | 0|acc |↑ |0.2311|± |0.0274|
|
|
| - high_school_psychology | 1|none | 0|acc |↑ |0.2495|± |0.0186|
|
|
| - human_sexuality | 1|none | 0|acc |↑ |0.2824|± |0.0395|
|
|
| - professional_psychology | 1|none | 0|acc |↑ |0.2565|± |0.0177|
|
|
| - public_relations | 1|none | 0|acc |↑ |0.2636|± |0.0422|
|
|
| - security_studies | 1|none | 0|acc |↑ |0.2898|± |0.0290|
|
|
| - sociology | 1|none | 0|acc |↑ |0.2537|± |0.0308|
|
|
| - us_foreign_policy | 1|none | 0|acc |↑ |0.2800|± |0.0451|
|
|
| - stem | 2|none | |acc |↑ |0.2274|± |0.0075|
|
|
| - abstract_algebra | 1|none | 0|acc |↑ |0.2200|± |0.0416|
|
|
| - anatomy | 1|none | 0|acc |↑ |0.2444|± |0.0371|
|
|
| - astronomy | 1|none | 0|acc |↑ |0.2697|± |0.0361|
|
|
| - college_biology | 1|none | 0|acc |↑ |0.2500|± |0.0362|
|
|
| - college_chemistry | 1|none | 0|acc |↑ |0.2100|± |0.0409|
|
|
| - college_computer_science | 1|none | 0|acc |↑ |0.2800|± |0.0451|
|
|
| - college_mathematics | 1|none | 0|acc |↑ |0.1900|± |0.0394|
|
|
| - college_physics | 1|none | 0|acc |↑ |0.2549|± |0.0434|
|
|
| - computer_security | 1|none | 0|acc |↑ |0.1900|± |0.0394|
|
|
| - conceptual_physics | 1|none | 0|acc |↑ |0.2298|± |0.0275|
|
|
| - electrical_engineering | 1|none | 0|acc |↑ |0.2483|± |0.0360|
|
|
| - elementary_mathematics | 1|none | 0|acc |↑ |0.1931|± |0.0203|
|
|
| - high_school_biology | 1|none | 0|acc |↑ |0.2258|± |0.0238|
|
|
| - high_school_chemistry | 1|none | 0|acc |↑ |0.2217|± |0.0292|
|
|
| - high_school_computer_science | 1|none | 0|acc |↑ |0.2400|± |0.0429|
|
|
| - high_school_mathematics | 1|none | 0|acc |↑ |0.2074|± |0.0247|
|
|
| - high_school_physics | 1|none | 0|acc |↑ |0.2185|± |0.0337|
|
|
| - high_school_statistics | 1|none | 0|acc |↑ |0.1991|± |0.0272|
|
|
| - machine_learning | 1|none | 0|acc |↑ |0.3393|± |0.0449|
|
|
|mmlu_pro | 2|custom-extract| |exact_match|↑ |0.0000|± |0.0000|
|
|
| - biology | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - business | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - chemistry | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - computer_science | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - economics | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - engineering | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - health | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - history | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - law | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - math | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - other | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - philosophy | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - physics | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
| - psychology | 1|custom-extract| 5|exact_match|↑ |0.0000|± |0.0000|
|
|
|
|
| Groups |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
|
|------------------|------:|--------------|------|-----------|---|-----:|---|-----:|
|
|
|mmlu | 2|none | |acc |↑ |0.2459|± |0.0036|
|
|
| - humanities | 2|none | |acc |↑ |0.2480|± |0.0063|
|
|
| - other | 2|none | |acc |↑ |0.2549|± |0.0078|
|
|
| - social sciences| 2|none | |acc |↑ |0.2525|± |0.0078|
|
|
| - stem | 2|none | |acc |↑ |0.2274|± |0.0075|
|
|
|mmlu_pro | 2|custom-extract| |exact_match|↑ |0.0000|± |0.0000|
|
|
|
|
|
|
|
|
```bash
|
|
litgpt evaluate --tasks 'arc_challenge,boolq,gpqa,hellaswag,openbookqa,piqa,truthfulqa_mc2,winogrande' --out_dir 'evaluate-reasoning/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
```
|
|
|
|
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
|
|-------------------------------|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
|
|arc_challenge | 1|none | 0|acc |↑ |0.2176|± |0.0121|
|
|
| | |none | 0|acc_norm |↑ |0.2560|± |0.0128|
|
|
|boolq | 2|none | 0|acc |↑ |0.3783|± |0.0085|
|
|
|gpqa_diamond_cot_n_shot | 2|flexible-extract| 0|exact_match|↑ |0.0051|± |0.0051|
|
|
| | |strict-match | 0|exact_match|↑ |0.0000|± |0.0000|
|
|
|gpqa_diamond_cot_zeroshot | 1|flexible-extract| 0|exact_match|↑ |0.0051|± |0.0051|
|
|
| | |strict-match | 0|exact_match|↑ |0.0000|± |0.0000|
|
|
|gpqa_diamond_generative_n_shot | 2|flexible-extract| 0|exact_match|↑ |0.0051|± |0.0051|
|
|
| | |strict-match | 0|exact_match|↑ |0.0000|± |0.0000|
|
|
|gpqa_diamond_n_shot | 2|none | 0|acc |↑ |0.1970|± |0.0283|
|
|
| | |none | 0|acc_norm |↑ |0.1970|± |0.0283|
|
|
|gpqa_diamond_zeroshot | 1|none | 0|acc |↑ |0.2727|± |0.0317|
|
|
| | |none | 0|acc_norm |↑ |0.2727|± |0.0317|
|
|
|gpqa_extended_cot_n_shot | 2|flexible-extract| 0|exact_match|↑ |0.0018|± |0.0018|
|
|
| | |strict-match | 0|exact_match|↑ |0.0000|± |0.0000|
|
|
|gpqa_extended_cot_zeroshot | 1|flexible-extract| 0|exact_match|↑ |0.0037|± |0.0026|
|
|
| | |strict-match | 0|exact_match|↑ |0.0000|± |0.0000|
|
|
|gpqa_extended_generative_n_shot| 2|flexible-extract| 0|exact_match|↑ |0.0073|± |0.0037|
|
|
| | |strict-match | 0|exact_match|↑ |0.0000|± |0.0000|
|
|
|gpqa_extended_n_shot | 2|none | 0|acc |↑ |0.2564|± |0.0187|
|
|
| | |none | 0|acc_norm |↑ |0.2564|± |0.0187|
|
|
|gpqa_extended_zeroshot | 1|none | 0|acc |↑ |0.2802|± |0.0192|
|
|
| | |none | 0|acc_norm |↑ |0.2802|± |0.0192|
|
|
|gpqa_main_cot_n_shot | 2|flexible-extract| 0|exact_match|↑ |0.0000|± |0.0000|
|
|
| | |strict-match | 0|exact_match|↑ |0.0000|± |0.0000|
|
|
|gpqa_main_cot_zeroshot | 1|flexible-extract| 0|exact_match|↑ |0.0000|± |0.0000|
|
|
| | |strict-match | 0|exact_match|↑ |0.0000|± |0.0000|
|
|
|gpqa_main_generative_n_shot | 2|flexible-extract| 0|exact_match|↑ |0.0089|± |0.0044|
|
|
| | |strict-match | 0|exact_match|↑ |0.0000|± |0.0000|
|
|
|gpqa_main_n_shot | 2|none | 0|acc |↑ |0.2478|± |0.0204|
|
|
| | |none | 0|acc_norm |↑ |0.2478|± |0.0204|
|
|
|gpqa_main_zeroshot | 1|none | 0|acc |↑ |0.2143|± |0.0194|
|
|
| | |none | 0|acc_norm |↑ |0.2143|± |0.0194|
|
|
|hellaswag | 1|none | 0|acc |↑ |0.2618|± |0.0044|
|
|
| | |none | 0|acc_norm |↑ |0.2592|± |0.0044|
|
|
|openbookqa | 1|none | 0|acc |↑ |0.1340|± |0.0152|
|
|
| | |none | 0|acc_norm |↑ |0.2340|± |0.0190|
|
|
|piqa | 1|none | 0|acc |↑ |0.5201|± |0.0117|
|
|
| | |none | 0|acc_norm |↑ |0.5076|± |0.0117|
|
|
|truthfulqa_mc2 | 2|none | 0|acc |↑ |0.5061|± |0.0167|
|
|
|winogrande | 1|none | 0|acc |↑ |0.4933|± |0.0141|
|
|
|
|
```bash
|
|
litgpt evaluate --tasks 'wikitext,qasper' --out_dir 'evaluate-long/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
```
|
|
|
|
| Tasks |Version|Filter|n-shot| Metric | | Value | |Stderr|
|
|
|---------------|------:|------|-----:|---------------|---|---------:|---|------|
|
|
|qasper_bool | 1|none | 0|f1 |↑ | 0.0000|± | 0|
|
|
|qasper_freeform| 2|none | 0|f1_abstractive |↑ | 0.0036|± | 0.001|
|
|
|wikitext | 2|none | 0|bits_per_byte |↓ | 3.0634|± | N/A|
|
|
| | |none | 0|byte_perplexity|↓ | 8.3596|± | N/A|
|
|
| | |none | 0|word_perplexity|↓ |85375.3002|± | N/A|
|
|
|
