eval
Browse files- README.md +229 -0
- scripts/TRAIN.md +95 -0
README.md
CHANGED
@@ -1,3 +1,232 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
library_name: transformers
|
5 |
+
language: [
|
6 |
+
'en', 'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'br', 'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el',
|
7 |
+
'eo', 'es', 'et', 'eu', 'fa', 'ff', 'fi', 'fr', 'fy', 'ga', 'gd', 'gl', 'gn', 'gu', 'ha', 'he',
|
8 |
+
'hi', 'hr', 'ht', 'hu', 'hy', 'id', 'ig', 'is', 'it', 'ja', 'jv', 'ka', 'kk', 'km', 'kn', 'ko',
|
9 |
+
'ku', 'ky', 'la', 'lg', 'li', 'ln', 'lo', 'lt', 'lv', 'mg', 'mk', 'ml', 'mn', 'mr', 'ms', 'my',
|
10 |
+
'ne', 'nl', 'no', 'ns', 'om', 'or', 'pa', 'pl', 'ps', 'pt', 'qu', 'rm', 'ro', 'ru', 'sa', 'si',
|
11 |
+
'sc', 'sd', 'sk', 'sl', 'so', 'sq', 'sr', 'ss', 'su', 'sv', 'sw', 'ta', 'te', 'th', 'tl', 'tn',
|
12 |
+
'tr', 'ug', 'uk', 'ur', 'uz', 'vi', 'wo', 'xh', 'yi', 'yo', 'zu',
|
13 |
+
]
|
14 |
+
datasets: [
|
15 |
+
'yahma/alpaca-cleaned',
|
16 |
+
'saillab/taco-datasets',
|
17 |
+
'xu-song/cc100-samples',
|
18 |
+
'badrex/llm-emoji-dataset',
|
19 |
+
'pszemraj/simple_wikipedia',
|
20 |
+
'AtlasUnified/Atlas-Reasoning',
|
21 |
+
'fblgit/simple-math',
|
22 |
+
'AtlasUnified/atlas-math-sets',
|
23 |
+
'rvv-karma/Math-QA',
|
24 |
+
'microsoft/orca-math-word-problems-200k',
|
25 |
+
'meta-math/MetaMathQA',
|
26 |
+
'TIGER-Lab/MathInstruct',
|
27 |
+
'ChuGyouk/WebInstructSub-only-socratic',
|
28 |
+
'thesven/gsm8k-reasoning',
|
29 |
+
'AlgorithmicResearchGroup/math_reasoning_autoformalization_track',
|
30 |
+
'KingNish/reasoning-base-20k',
|
31 |
+
'fmars/wiki_stem',
|
32 |
+
'ChuGyouk/WebInstructSub-only-sciencestackexchange',
|
33 |
+
'bigcode/the-stack-smol-xs',
|
34 |
+
'cognitivecomputations/dolphin-coder',
|
35 |
+
'HuggingFaceH4/CodeAlpaca_20K',
|
36 |
+
'm-a-p/CodeFeedback-Filtered-Instruction',
|
37 |
+
'NuclearAi/Nuke-X-Glaive-Python-Dataset',
|
38 |
+
'iamtarun/python_code_instructions_18k_alpaca',
|
39 |
+
'kloodia/html_200k',
|
40 |
+
'kloodia/json_200k',
|
41 |
+
'kloodia/javascript_200k',
|
42 |
+
'bleugreen/typescript-chunks',
|
43 |
+
'SkunkworksAI/reasoning-0.01',
|
44 |
+
'Magpie-Align/Magpie-Reasoning-150K',
|
45 |
+
]
|
46 |
+
tags:
|
47 |
+
- litgpt
|
48 |
+
- litdata
|
49 |
---
|
50 |
+
|
51 |
+
# tangled-llama-q-32k-base-v0.1
|
52 |
+
|
53 |
+
![logo](./misc/logo.png)
|
54 |
+
|
55 |
+
A pretrained language model based on the Llama model with about **65M** parameters. This model has been trained on **16.7B** (`16,698,858,240`) tokens from more than **3.6M** (`3,597,088`) dataset rows.
|
56 |
+
|
57 |
+
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.
|
58 |
+
|
59 |
+
The objective is to streamline the cognitive or reasoning core, eliminating any redundant knowledge from the model.
|
60 |
+
|
61 |
+
[loss, val_loss](https://api.wandb.ai/links/mtasic85/jo8uatgs)
|
62 |
+
|
63 |
+
[val_ppl](https://api.wandb.ai/links/mtasic85/f06bqhu6)
|
64 |
+
|
65 |
+
[epoch](https://api.wandb.ai/links/mtasic85/buj8l3pf)
|
66 |
+
|
67 |
+
[learning_rate](https://api.wandb.ai/links/mtasic85/h0ooy6sf)
|
68 |
+
|
69 |
+
## lm-evaluation-harness
|
70 |
+
|
71 |
+
```bash
|
72 |
+
litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,winogrande,arc_challenge' --out_dir 'evaluate-quick/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
73 |
+
```
|
74 |
+
|
75 |
+
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
76 |
+
|---------------------------------------|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
77 |
+
|arc_challenge | 1|none | 0|acc |↑ |0.1962|± |0.0116|
|
78 |
+
| | |none | 0|acc_norm |↑ |0.2304|± |0.0123|
|
79 |
+
|gsm8k | 3|flexible-extract| 5|exact_match|↑ |0.0144|± |0.0033|
|
80 |
+
| | |strict-match | 5|exact_match|↑ |0.0015|± |0.0011|
|
81 |
+
|hellaswag | 1|none | 0|acc |↑ |0.2631|± |0.0044|
|
82 |
+
| | |none | 0|acc_norm |↑ |0.2758|± |0.0045|
|
83 |
+
|mmlu | 2|none | |acc |↑ |0.2473|± |0.0036|
|
84 |
+
| - humanities | 2|none | |acc |↑ |0.2351|± |0.0062|
|
85 |
+
| - formal_logic | 1|none | 0|acc |↑ |0.2857|± |0.0404|
|
86 |
+
| - high_school_european_history | 1|none | 0|acc |↑ |0.2667|± |0.0345|
|
87 |
+
| - high_school_us_history | 1|none | 0|acc |↑ |0.2696|± |0.0311|
|
88 |
+
| - high_school_world_history | 1|none | 0|acc |↑ |0.2110|± |0.0266|
|
89 |
+
| - international_law | 1|none | 0|acc |↑ |0.1653|± |0.0339|
|
90 |
+
| - jurisprudence | 1|none | 0|acc |↑ |0.2870|± |0.0437|
|
91 |
+
| - logical_fallacies | 1|none | 0|acc |↑ |0.2331|± |0.0332|
|
92 |
+
| - moral_disputes | 1|none | 0|acc |↑ |0.2283|± |0.0226|
|
93 |
+
| - moral_scenarios | 1|none | 0|acc |↑ |0.2425|± |0.0143|
|
94 |
+
| - philosophy | 1|none | 0|acc |↑ |0.2186|± |0.0235|
|
95 |
+
| - prehistory | 1|none | 0|acc |↑ |0.2099|± |0.0227|
|
96 |
+
| - professional_law | 1|none | 0|acc |↑ |0.2314|± |0.0108|
|
97 |
+
| - world_religions | 1|none | 0|acc |↑ |0.2632|± |0.0338|
|
98 |
+
| - other | 2|none | |acc |↑ |0.2485|± |0.0078|
|
99 |
+
| - business_ethics | 1|none | 0|acc |↑ |0.2600|± |0.0441|
|
100 |
+
| - clinical_knowledge | 1|none | 0|acc |↑ |0.2528|± |0.0267|
|
101 |
+
| - college_medicine | 1|none | 0|acc |↑ |0.2254|± |0.0319|
|
102 |
+
| - global_facts | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
103 |
+
| - human_aging | 1|none | 0|acc |↑ |0.2377|± |0.0286|
|
104 |
+
| - management | 1|none | 0|acc |↑ |0.2816|± |0.0445|
|
105 |
+
| - marketing | 1|none | 0|acc |↑ |0.2692|± |0.0291|
|
106 |
+
| - medical_genetics | 1|none | 0|acc |↑ |0.2600|± |0.0441|
|
107 |
+
| - miscellaneous | 1|none | 0|acc |↑ |0.2350|± |0.0152|
|
108 |
+
| - nutrition | 1|none | 0|acc |↑ |0.2549|± |0.0250|
|
109 |
+
| - professional_accounting | 1|none | 0|acc |↑ |0.2801|± |0.0268|
|
110 |
+
| - professional_medicine | 1|none | 0|acc |↑ |0.2610|± |0.0267|
|
111 |
+
| - virology | 1|none | 0|acc |↑ |0.1807|± |0.0300|
|
112 |
+
| - social sciences | 2|none | |acc |↑ |0.2658|± |0.0080|
|
113 |
+
| - econometrics | 1|none | 0|acc |↑ |0.1930|± |0.0371|
|
114 |
+
| - high_school_geography | 1|none | 0|acc |↑ |0.2172|± |0.0294|
|
115 |
+
| - high_school_government_and_politics| 1|none | 0|acc |↑ |0.3212|± |0.0337|
|
116 |
+
| - high_school_macroeconomics | 1|none | 0|acc |↑ |0.2923|± |0.0231|
|
117 |
+
| - high_school_microeconomics | 1|none | 0|acc |↑ |0.3025|± |0.0298|
|
118 |
+
| - high_school_psychology | 1|none | 0|acc |↑ |0.2752|± |0.0191|
|
119 |
+
| - human_sexuality | 1|none | 0|acc |↑ |0.2290|± |0.0369|
|
120 |
+
| - professional_psychology | 1|none | 0|acc |↑ |0.2386|± |0.0172|
|
121 |
+
| - public_relations | 1|none | 0|acc |↑ |0.2636|± |0.0422|
|
122 |
+
| - security_studies | 1|none | 0|acc |↑ |0.3143|± |0.0297|
|
123 |
+
| - sociology | 1|none | 0|acc |↑ |0.2338|± |0.0299|
|
124 |
+
| - us_foreign_policy | 1|none | 0|acc |↑ |0.2600|± |0.0441|
|
125 |
+
| - stem | 2|none | |acc |↑ |0.2464|± |0.0077|
|
126 |
+
| - abstract_algebra | 1|none | 0|acc |↑ |0.2500|± |0.0435|
|
127 |
+
| - anatomy | 1|none | 0|acc |↑ |0.2148|± |0.0355|
|
128 |
+
| - astronomy | 1|none | 0|acc |↑ |0.1908|± |0.0320|
|
129 |
+
| - college_biology | 1|none | 0|acc |↑ |0.2569|± |0.0365|
|
130 |
+
| - college_chemistry | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
131 |
+
| - college_computer_science | 1|none | 0|acc |↑ |0.3500|± |0.0479|
|
132 |
+
| - college_mathematics | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
133 |
+
| - college_physics | 1|none | 0|acc |↑ |0.2745|± |0.0444|
|
134 |
+
| - computer_security | 1|none | 0|acc |↑ |0.3000|± |0.0461|
|
135 |
+
| - conceptual_physics | 1|none | 0|acc |↑ |0.2766|± |0.0292|
|
136 |
+
| - electrical_engineering | 1|none | 0|acc |↑ |0.2345|± |0.0353|
|
137 |
+
| - elementary_mathematics | 1|none | 0|acc |↑ |0.2566|± |0.0225|
|
138 |
+
| - high_school_biology | 1|none | 0|acc |↑ |0.2226|± |0.0237|
|
139 |
+
| - high_school_chemistry | 1|none | 0|acc |↑ |0.2217|± |0.0292|
|
140 |
+
| - high_school_computer_science | 1|none | 0|acc |↑ |0.2000|± |0.0402|
|
141 |
+
| - high_school_mathematics | 1|none | 0|acc |↑ |0.2370|± |0.0259|
|
142 |
+
| - high_school_physics | 1|none | 0|acc |↑ |0.2517|± |0.0354|
|
143 |
+
| - high_school_statistics | 1|none | 0|acc |↑ |0.2685|± |0.0302|
|
144 |
+
| - machine_learning | 1|none | 0|acc |↑ |0.1786|± |0.0364|
|
145 |
+
|truthfulqa_mc2 | 2|none | 0|acc |↑ |0.4668|± |0.0161|
|
146 |
+
|winogrande | 1|none | 0|acc |↑ |0.5012|± |0.0141|
|
147 |
+
|
148 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
149 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
150 |
+
|mmlu | 2|none | |acc |↑ |0.2473|± |0.0036|
|
151 |
+
| - humanities | 2|none | |acc |↑ |0.2351|± |0.0062|
|
152 |
+
| - other | 2|none | |acc |↑ |0.2485|± |0.0078|
|
153 |
+
| - social sciences| 2|none | |acc |↑ |0.2658|± |0.0080|
|
154 |
+
| - stem | 2|none | |acc |↑ |0.2464|± |0.0077|
|
155 |
+
|
156 |
+
```bash
|
157 |
+
litgpt evaluate --tasks 'leaderboard' --out_dir 'evaluate-leaderboard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
158 |
+
```
|
159 |
+
|
160 |
+
Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
161 |
+
|-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------|
|
162 |
+
|leaderboard | N/A| | | | | | | |
|
163 |
+
| - leaderboard_bbh | N/A| | | | | | | |
|
164 |
+
| - leaderboard_bbh_boolean_expressions | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
|
165 |
+
| - leaderboard_bbh_causal_judgement | 1|none | 3|acc_norm |↑ |0.5187|± |0.0366|
|
166 |
+
| - leaderboard_bbh_date_understanding | 1|none | 3|acc_norm |↑ |0.1840|± |0.0246|
|
167 |
+
| - leaderboard_bbh_disambiguation_qa | 1|none | 3|acc_norm |↑ |0.3880|± |0.0309|
|
168 |
+
| - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.4680|± |0.0316|
|
169 |
+
| - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.1000|± |0.0190|
|
170 |
+
| - leaderboard_bbh_hyperbaton | 1|none | 3|acc_norm |↑ |0.5160|± |0.0317|
|
171 |
+
| - leaderboard_bbh_logical_deduction_five_objects | 1|none | 3|acc_norm |↑ |0.2080|± |0.0257|
|
172 |
+
| - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1720|± |0.0239|
|
173 |
+
| - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3280|± |0.0298|
|
174 |
+
| - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.2640|± |0.0279|
|
175 |
+
| - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.5760|± |0.0313|
|
176 |
+
| - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.0520|± |0.0141|
|
177 |
+
| - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.2260|± |0.0347|
|
178 |
+
| - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.0720|± |0.0164|
|
179 |
+
| - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2280|± |0.0266|
|
180 |
+
| - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.1920|± |0.0250|
|
181 |
+
| - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.4831|± |0.0376|
|
182 |
+
| - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316|
|
183 |
+
| - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2360|± |0.0269|
|
184 |
+
| - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.2080|± |0.0257|
|
185 |
+
| - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1680|± |0.0237|
|
186 |
+
| - leaderboard_bbh_tracking_shuffled_objects_three_objects| 1|none | 3|acc_norm |↑ |0.3040|± |0.0292|
|
187 |
+
| - leaderboard_bbh_web_of_lies | 1|none | 3|acc_norm |↑ |0.4880|± |0.0317|
|
188 |
+
| - leaderboard_gpqa | N/A| | | | | | | |
|
189 |
+
| - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.2121|± |0.0291|
|
190 |
+
| - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2619|± |0.0188|
|
191 |
+
| - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2589|± |0.0207|
|
192 |
+
| - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.1966|± | N/A|
|
193 |
+
| | |none | 0|inst_level_strict_acc |↑ |0.1835|± | N/A|
|
194 |
+
| | |none | 0|prompt_level_loose_acc |↑ |0.1017|± |0.0130|
|
195 |
+
| | |none | 0|prompt_level_strict_acc|↑ |0.0998|± |0.0129|
|
196 |
+
| - leaderboard_math_hard | N/A| | | | | | | |
|
197 |
+
| - leaderboard_math_algebra_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
198 |
+
| - leaderboard_math_counting_and_prob_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
199 |
+
| - leaderboard_math_geometry_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
200 |
+
| - leaderboard_math_intermediate_algebra_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
201 |
+
| - leaderboard_math_num_theory_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
202 |
+
| - leaderboard_math_prealgebra_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
203 |
+
| - leaderboard_math_precalculus_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0|
|
204 |
+
| - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.1155|± |0.0029|
|
205 |
+
| - leaderboard_musr | N/A| | | | | | | |
|
206 |
+
| - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.5040|± |0.0317|
|
207 |
+
| - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.3086|± |0.0289|
|
208 |
+
| - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.3400|± |0.0300|
|
209 |
+
|
210 |
+
```bash
|
211 |
+
litgpt evaluate --tasks 'bbh_zeroshot,bbh_fewshot,bbh_cot_fewshot,bbh_cot_zeroshot' --out_dir 'evaluate-bigbenchhard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
212 |
+
```
|
213 |
+
|
214 |
+
```bash
|
215 |
+
litgpt evaluate --tasks 'mmlu,mmlu_pro' --out_dir 'evaluate-mmlu/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
216 |
+
```
|
217 |
+
|
218 |
+
```bash
|
219 |
+
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/
|
220 |
+
```
|
221 |
+
|
222 |
+
```bash
|
223 |
+
litgpt evaluate --tasks 'mmlu_multilingual,mgsm' --out_dir 'evaluate-multilinguals/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
224 |
+
```
|
225 |
+
|
226 |
+
```bash
|
227 |
+
litgpt evaluate --tasks 'gsm8k,mathqa' --out_dir 'evaluate-math/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
228 |
+
```
|
229 |
+
|
230 |
+
```bash
|
231 |
+
litgpt evaluate --tasks 'wikitext,qasper' --out_dir 'evaluate-long/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
232 |
+
```
|
scripts/TRAIN.md
CHANGED
@@ -58,18 +58,113 @@ save_file(state_dict, 'out/converted_model/model.safetensors')
|
|
58 |
|
59 |
```bash
|
60 |
litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,winogrande,arc_challenge' --out_dir 'evaluate-quick/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
|
|
|
62 |
litgpt evaluate --tasks 'leaderboard' --out_dir 'evaluate-leaderboard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
|
63 |
|
|
|
64 |
litgpt evaluate --tasks 'bbh_zeroshot,bbh_fewshot,bbh_cot_fewshot,bbh_cot_zeroshot' --out_dir 'evaluate-bigbenchhard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
|
65 |
|
|
|
66 |
litgpt evaluate --tasks 'mmlu,mmlu_pro' --out_dir 'evaluate-mmlu/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
|
67 |
|
|
|
68 |
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/
|
|
|
69 |
|
|
|
70 |
litgpt evaluate --tasks 'mmlu_multilingual,mgsm' --out_dir 'evaluate-multilinguals/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
|
71 |
|
|
|
72 |
litgpt evaluate --tasks 'gsm8k,mathqa' --out_dir 'evaluate-math/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
|
|
73 |
|
|
|
74 |
litgpt evaluate --tasks 'qasper' --out_dir 'evaluate-long/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
75 |
```
|
|
|
58 |
|
59 |
```bash
|
60 |
litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,winogrande,arc_challenge' --out_dir 'evaluate-quick/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
61 |
+
```
|
62 |
+
|
63 |
+
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
64 |
+
|---------------------------------------|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
65 |
+
|arc_challenge | 1|none | 0|acc |↑ |0.1962|± |0.0116|
|
66 |
+
| | |none | 0|acc_norm |↑ |0.2304|± |0.0123|
|
67 |
+
|gsm8k | 3|flexible-extract| 5|exact_match|↑ |0.0144|± |0.0033|
|
68 |
+
| | |strict-match | 5|exact_match|↑ |0.0015|± |0.0011|
|
69 |
+
|hellaswag | 1|none | 0|acc |↑ |0.2631|± |0.0044|
|
70 |
+
| | |none | 0|acc_norm |↑ |0.2758|± |0.0045|
|
71 |
+
|mmlu | 2|none | |acc |↑ |0.2473|± |0.0036|
|
72 |
+
| - humanities | 2|none | |acc |↑ |0.2351|± |0.0062|
|
73 |
+
| - formal_logic | 1|none | 0|acc |↑ |0.2857|± |0.0404|
|
74 |
+
| - high_school_european_history | 1|none | 0|acc |↑ |0.2667|± |0.0345|
|
75 |
+
| - high_school_us_history | 1|none | 0|acc |↑ |0.2696|± |0.0311|
|
76 |
+
| - high_school_world_history | 1|none | 0|acc |↑ |0.2110|± |0.0266|
|
77 |
+
| - international_law | 1|none | 0|acc |↑ |0.1653|± |0.0339|
|
78 |
+
| - jurisprudence | 1|none | 0|acc |↑ |0.2870|± |0.0437|
|
79 |
+
| - logical_fallacies | 1|none | 0|acc |↑ |0.2331|± |0.0332|
|
80 |
+
| - moral_disputes | 1|none | 0|acc |↑ |0.2283|± |0.0226|
|
81 |
+
| - moral_scenarios | 1|none | 0|acc |↑ |0.2425|± |0.0143|
|
82 |
+
| - philosophy | 1|none | 0|acc |↑ |0.2186|± |0.0235|
|
83 |
+
| - prehistory | 1|none | 0|acc |↑ |0.2099|± |0.0227|
|
84 |
+
| - professional_law | 1|none | 0|acc |↑ |0.2314|± |0.0108|
|
85 |
+
| - world_religions | 1|none | 0|acc |↑ |0.2632|± |0.0338|
|
86 |
+
| - other | 2|none | |acc |↑ |0.2485|± |0.0078|
|
87 |
+
| - business_ethics | 1|none | 0|acc |↑ |0.2600|± |0.0441|
|
88 |
+
| - clinical_knowledge | 1|none | 0|acc |↑ |0.2528|± |0.0267|
|
89 |
+
| - college_medicine | 1|none | 0|acc |↑ |0.2254|± |0.0319|
|
90 |
+
| - global_facts | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
91 |
+
| - human_aging | 1|none | 0|acc |↑ |0.2377|± |0.0286|
|
92 |
+
| - management | 1|none | 0|acc |↑ |0.2816|± |0.0445|
|
93 |
+
| - marketing | 1|none | 0|acc |↑ |0.2692|± |0.0291|
|
94 |
+
| - medical_genetics | 1|none | 0|acc |↑ |0.2600|± |0.0441|
|
95 |
+
| - miscellaneous | 1|none | 0|acc |↑ |0.2350|± |0.0152|
|
96 |
+
| - nutrition | 1|none | 0|acc |↑ |0.2549|± |0.0250|
|
97 |
+
| - professional_accounting | 1|none | 0|acc |↑ |0.2801|± |0.0268|
|
98 |
+
| - professional_medicine | 1|none | 0|acc |↑ |0.2610|± |0.0267|
|
99 |
+
| - virology | 1|none | 0|acc |↑ |0.1807|± |0.0300|
|
100 |
+
| - social sciences | 2|none | |acc |↑ |0.2658|± |0.0080|
|
101 |
+
| - econometrics | 1|none | 0|acc |↑ |0.1930|± |0.0371|
|
102 |
+
| - high_school_geography | 1|none | 0|acc |↑ |0.2172|± |0.0294|
|
103 |
+
| - high_school_government_and_politics| 1|none | 0|acc |↑ |0.3212|± |0.0337|
|
104 |
+
| - high_school_macroeconomics | 1|none | 0|acc |↑ |0.2923|± |0.0231|
|
105 |
+
| - high_school_microeconomics | 1|none | 0|acc |↑ |0.3025|± |0.0298|
|
106 |
+
| - high_school_psychology | 1|none | 0|acc |↑ |0.2752|± |0.0191|
|
107 |
+
| - human_sexuality | 1|none | 0|acc |↑ |0.2290|± |0.0369|
|
108 |
+
| - professional_psychology | 1|none | 0|acc |↑ |0.2386|± |0.0172|
|
109 |
+
| - public_relations | 1|none | 0|acc |↑ |0.2636|± |0.0422|
|
110 |
+
| - security_studies | 1|none | 0|acc |↑ |0.3143|± |0.0297|
|
111 |
+
| - sociology | 1|none | 0|acc |↑ |0.2338|± |0.0299|
|
112 |
+
| - us_foreign_policy | 1|none | 0|acc |↑ |0.2600|± |0.0441|
|
113 |
+
| - stem | 2|none | |acc |↑ |0.2464|± |0.0077|
|
114 |
+
| - abstract_algebra | 1|none | 0|acc |↑ |0.2500|± |0.0435|
|
115 |
+
| - anatomy | 1|none | 0|acc |↑ |0.2148|± |0.0355|
|
116 |
+
| - astronomy | 1|none | 0|acc |↑ |0.1908|± |0.0320|
|
117 |
+
| - college_biology | 1|none | 0|acc |↑ |0.2569|± |0.0365|
|
118 |
+
| - college_chemistry | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
119 |
+
| - college_computer_science | 1|none | 0|acc |↑ |0.3500|± |0.0479|
|
120 |
+
| - college_mathematics | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
121 |
+
| - college_physics | 1|none | 0|acc |↑ |0.2745|± |0.0444|
|
122 |
+
| - computer_security | 1|none | 0|acc |↑ |0.3000|± |0.0461|
|
123 |
+
| - conceptual_physics | 1|none | 0|acc |↑ |0.2766|± |0.0292|
|
124 |
+
| - electrical_engineering | 1|none | 0|acc |↑ |0.2345|± |0.0353|
|
125 |
+
| - elementary_mathematics | 1|none | 0|acc |↑ |0.2566|± |0.0225|
|
126 |
+
| - high_school_biology | 1|none | 0|acc |↑ |0.2226|± |0.0237|
|
127 |
+
| - high_school_chemistry | 1|none | 0|acc |↑ |0.2217|± |0.0292|
|
128 |
+
| - high_school_computer_science | 1|none | 0|acc |↑ |0.2000|± |0.0402|
|
129 |
+
| - high_school_mathematics | 1|none | 0|acc |↑ |0.2370|± |0.0259|
|
130 |
+
| - high_school_physics | 1|none | 0|acc |↑ |0.2517|± |0.0354|
|
131 |
+
| - high_school_statistics | 1|none | 0|acc |↑ |0.2685|± |0.0302|
|
132 |
+
| - machine_learning | 1|none | 0|acc |↑ |0.1786|± |0.0364|
|
133 |
+
|truthfulqa_mc2 | 2|none | 0|acc |↑ |0.4668|± |0.0161|
|
134 |
+
|winogrande | 1|none | 0|acc |↑ |0.5012|± |0.0141|
|
135 |
+
|
136 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
137 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
138 |
+
|mmlu | 2|none | |acc |↑ |0.2473|± |0.0036|
|
139 |
+
| - humanities | 2|none | |acc |↑ |0.2351|± |0.0062|
|
140 |
+
| - other | 2|none | |acc |↑ |0.2485|± |0.0078|
|
141 |
+
| - social sciences| 2|none | |acc |↑ |0.2658|± |0.0080|
|
142 |
+
| - stem | 2|none | |acc |↑ |0.2464|± |0.0077|
|
143 |
|
144 |
+
```bash
|
145 |
litgpt evaluate --tasks 'leaderboard' --out_dir 'evaluate-leaderboard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
146 |
+
```
|
147 |
|
148 |
+
```bash
|
149 |
litgpt evaluate --tasks 'bbh_zeroshot,bbh_fewshot,bbh_cot_fewshot,bbh_cot_zeroshot' --out_dir 'evaluate-bigbenchhard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
150 |
+
```
|
151 |
|
152 |
+
```bash
|
153 |
litgpt evaluate --tasks 'mmlu,mmlu_pro' --out_dir 'evaluate-mmlu/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
154 |
+
```
|
155 |
|
156 |
+
```bash
|
157 |
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/
|
158 |
+
```
|
159 |
|
160 |
+
```bash
|
161 |
litgpt evaluate --tasks 'mmlu_multilingual,mgsm' --out_dir 'evaluate-multilinguals/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
162 |
+
```
|
163 |
|
164 |
+
```bash
|
165 |
litgpt evaluate --tasks 'gsm8k,mathqa' --out_dir 'evaluate-math/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
166 |
+
```
|
167 |
|
168 |
+
```bash
|
169 |
litgpt evaluate --tasks 'qasper' --out_dir 'evaluate-long/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
|
170 |
```
|