Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

https://wandb.ai/alexwortega/tiny_llama/runs/n0je6urv?workspace=user-alexwortega

hf-causal (pretrained=../../tiny_3ep_full,dtype=float16), limit: None, provide_description: False, num_fewshot: 0, batch_size: 16

Task Version Metric Value Stderr
danetqa 1 acc 0.5018 ± 0.0175
hendrycksTest-abstract_algebra 1 acc 0.2600 ± 0.0441
acc_norm 0.2600 ± 0.0441
hendrycksTest-anatomy 1 acc 0.2741 ± 0.0385
acc_norm 0.2741 ± 0.0385
hendrycksTest-astronomy 1 acc 0.1776 ± 0.0311
acc_norm 0.1776 ± 0.0311
hendrycksTest-business_ethics 1 acc 0.2500 ± 0.0435
acc_norm 0.2500 ± 0.0435
hendrycksTest-clinical_knowledge 1 acc 0.2604 ± 0.0270
acc_norm 0.2604 ± 0.0270
hendrycksTest-college_biology 1 acc 0.2153 ± 0.0344
acc_norm 0.2153 ± 0.0344
hendrycksTest-college_chemistry 1 acc 0.1700 ± 0.0378
acc_norm 0.1700 ± 0.0378
hendrycksTest-college_computer_science 1 acc 0.2800 ± 0.0451
acc_norm 0.2800 ± 0.0451
hendrycksTest-college_mathematics 1 acc 0.2700 ± 0.0446
acc_norm 0.2700 ± 0.0446
hendrycksTest-college_medicine 1 acc 0.2543 ± 0.0332
acc_norm 0.2543 ± 0.0332
hendrycksTest-college_physics 1 acc 0.1961 ± 0.0395
acc_norm 0.1961 ± 0.0395
hendrycksTest-computer_security 1 acc 0.3000 ± 0.0461
acc_norm 0.3000 ± 0.0461
hendrycksTest-conceptual_physics 1 acc 0.2766 ± 0.0292
acc_norm 0.2766 ± 0.0292
hendrycksTest-econometrics 1 acc 0.2807 ± 0.0423
acc_norm 0.2807 ± 0.0423
hendrycksTest-electrical_engineering 1 acc 0.2690 ± 0.0370
acc_norm 0.2690 ± 0.0370
hendrycksTest-elementary_mathematics 1 acc 0.2434 ± 0.0221
acc_norm 0.2434 ± 0.0221
hendrycksTest-formal_logic 1 acc 0.2698 ± 0.0397
acc_norm 0.2698 ± 0.0397
hendrycksTest-global_facts 1 acc 0.2700 ± 0.0446
acc_norm 0.2700 ± 0.0446
hendrycksTest-high_school_biology 1 acc 0.2161 ± 0.0234
acc_norm 0.2161 ± 0.0234
hendrycksTest-high_school_chemistry 1 acc 0.1970 ± 0.0280
acc_norm 0.1970 ± 0.0280
hendrycksTest-high_school_computer_science 1 acc 0.3600 ± 0.0482
acc_norm 0.3600 ± 0.0482
hendrycksTest-high_school_european_history 1 acc 0.2182 ± 0.0323
acc_norm 0.2182 ± 0.0323
hendrycksTest-high_school_geography 1 acc 0.2222 ± 0.0296
acc_norm 0.2222 ± 0.0296
hendrycksTest-high_school_government_and_politics 1 acc 0.1969 ± 0.0287
acc_norm 0.1969 ± 0.0287
hendrycksTest-high_school_macroeconomics 1 acc 0.2282 ± 0.0213
acc_norm 0.2282 ± 0.0213
hendrycksTest-high_school_mathematics 1 acc 0.2556 ± 0.0266
acc_norm 0.2556 ± 0.0266
hendrycksTest-high_school_microeconomics 1 acc 0.2227 ± 0.0270
acc_norm 0.2227 ± 0.0270
hendrycksTest-high_school_physics 1 acc 0.2914 ± 0.0371
acc_norm 0.2914 ± 0.0371
hendrycksTest-high_school_psychology 1 acc 0.2275 ± 0.0180
acc_norm 0.2275 ± 0.0180
hendrycksTest-high_school_statistics 1 acc 0.1759 ± 0.0260
acc_norm 0.1759 ± 0.0260
hendrycksTest-high_school_us_history 1 acc 0.2598 ± 0.0308
acc_norm 0.2598 ± 0.0308
hendrycksTest-high_school_world_history 1 acc 0.2827 ± 0.0293
acc_norm 0.2827 ± 0.0293
hendrycksTest-human_aging 1 acc 0.3049 ± 0.0309
acc_norm 0.3049 ± 0.0309
hendrycksTest-human_sexuality 1 acc 0.2824 ± 0.0395
acc_norm 0.2824 ± 0.0395
hendrycksTest-international_law 1 acc 0.2562 ± 0.0398
acc_norm 0.2562 ± 0.0398
hendrycksTest-jurisprudence 1 acc 0.3611 ± 0.0464
acc_norm 0.3611 ± 0.0464
hendrycksTest-logical_fallacies 1 acc 0.2515 ± 0.0341
acc_norm 0.2515 ± 0.0341
hendrycksTest-machine_learning 1 acc 0.1964 ± 0.0377
acc_norm 0.1964 ± 0.0377
hendrycksTest-management 1 acc 0.1553 ± 0.0359
acc_norm 0.1553 ± 0.0359
hendrycksTest-marketing 1 acc 0.3248 ± 0.0307
acc_norm 0.3248 ± 0.0307
hendrycksTest-medical_genetics 1 acc 0.3400 ± 0.0476
acc_norm 0.3400 ± 0.0476
hendrycksTest-miscellaneous 1 acc 0.2669 ± 0.0158
acc_norm 0.2669 ± 0.0158
hendrycksTest-moral_disputes 1 acc 0.2919 ± 0.0245
acc_norm 0.2919 ± 0.0245
hendrycksTest-moral_scenarios 1 acc 0.2447 ± 0.0144
acc_norm 0.2447 ± 0.0144
hendrycksTest-nutrition 1 acc 0.2549 ± 0.0250
acc_norm 0.2549 ± 0.0250
hendrycksTest-philosophy 1 acc 0.2122 ± 0.0232
acc_norm 0.2122 ± 0.0232
hendrycksTest-prehistory 1 acc 0.2685 ± 0.0247
acc_norm 0.2685 ± 0.0247
hendrycksTest-professional_accounting 1 acc 0.2021 ± 0.0240
acc_norm 0.2021 ± 0.0240
hendrycksTest-professional_law 1 acc 0.2432 ± 0.0110
acc_norm 0.2432 ± 0.0110
hendrycksTest-professional_medicine 1 acc 0.1654 ± 0.0226
acc_norm 0.1654 ± 0.0226
hendrycksTest-professional_psychology 1 acc 0.2582 ± 0.0177
acc_norm 0.2582 ± 0.0177
hendrycksTest-public_relations 1 acc 0.2909 ± 0.0435
acc_norm 0.2909 ± 0.0435
hendrycksTest-security_studies 1 acc 0.2041 ± 0.0258
acc_norm 0.2041 ± 0.0258
hendrycksTest-sociology 1 acc 0.2637 ± 0.0312
acc_norm 0.2637 ± 0.0312
hendrycksTest-us_foreign_policy 1 acc 0.2900 ± 0.0456
acc_norm 0.2900 ± 0.0456
hendrycksTest-virology 1 acc 0.2651 ± 0.0344
acc_norm 0.2651 ± 0.0344
hendrycksTest-world_religions 1 acc 0.3450 ± 0.0365
acc_norm 0.3450 ± 0.0365
hendrycksTestRu-abstract_algebra 1 acc 0.2300 ± 0.0423
acc_norm 0.2300 ± 0.0423
hendrycksTestRu-anatomy 1 acc 0.1778 ± 0.0330
acc_norm 0.1778 ± 0.0330
hendrycksTestRu-astronomy 1 acc 0.1776 ± 0.0311
acc_norm 0.1776 ± 0.0311
hendrycksTestRu-business_ethics 1 acc 0.2200 ± 0.0416
acc_norm 0.2200 ± 0.0416
hendrycksTestRu-clinical_knowledge 1 acc 0.2151 ± 0.0253
acc_norm 0.2151 ± 0.0253
hendrycksTestRu-college_biology 1 acc 0.2569 ± 0.0365
acc_norm 0.2569 ± 0.0365
hendrycksTestRu-college_chemistry 1 acc 0.1800 ± 0.0386
acc_norm 0.1800 ± 0.0386
hendrycksTestRu-college_computer_science 1 acc 0.2700 ± 0.0446
acc_norm 0.2700 ± 0.0446
hendrycksTestRu-college_mathematics 1 acc 0.2200 ± 0.0416
acc_norm 0.2200 ± 0.0416
hendrycksTestRu-college_medicine 1 acc 0.1908 ± 0.0300
acc_norm 0.1908 ± 0.0300
hendrycksTestRu-college_physics 1 acc 0.2059 ± 0.0402
acc_norm 0.2059 ± 0.0402
hendrycksTestRu-computer_security 1 acc 0.3000 ± 0.0461
acc_norm 0.3000 ± 0.0461
hendrycksTestRu-conceptual_physics 1 acc 0.2681 ± 0.0290
acc_norm 0.2681 ± 0.0290
hendrycksTestRu-econometrics 1 acc 0.2368 ± 0.0400
acc_norm 0.2368 ± 0.0400
hendrycksTestRu-electrical_engineering 1 acc 0.2483 ± 0.0360
acc_norm 0.2483 ± 0.0360
hendrycksTestRu-elementary_mathematics 1 acc 0.2063 ± 0.0208
acc_norm 0.2063 ± 0.0208
hendrycksTestRu-formal_logic 1 acc 0.2937 ± 0.0407
acc_norm 0.2937 ± 0.0407
hendrycksTestRu-global_facts 1 acc 0.2000 ± 0.0402
acc_norm 0.2000 ± 0.0402
hendrycksTestRu-high_school_biology 1 acc 0.1871 ± 0.0222
acc_norm 0.1871 ± 0.0222
hendrycksTestRu-high_school_chemistry 1 acc 0.1724 ± 0.0266
acc_norm 0.1724 ± 0.0266
hendrycksTestRu-high_school_computer_science 1 acc 0.2900 ± 0.0456
acc_norm 0.2900 ± 0.0456
hendrycksTestRu-high_school_european_history 1 acc 0.2242 ± 0.0326
acc_norm 0.2242 ± 0.0326
hendrycksTestRu-high_school_geography 1 acc 0.1869 ± 0.0278
acc_norm 0.1869 ± 0.0278
hendrycksTestRu-high_school_government_and_politics 1 acc 0.2124 ± 0.0295
acc_norm 0.2124 ± 0.0295
hendrycksTestRu-high_school_macroeconomics 1 acc 0.2128 ± 0.0208
acc_norm 0.2128 ± 0.0208
hendrycksTestRu-high_school_mathematics 1 acc 0.2074 ± 0.0247
acc_norm 0.2074 ± 0.0247
hendrycksTestRu-high_school_microeconomics 1 acc 0.2227 ± 0.0270
acc_norm 0.2227 ± 0.0270
hendrycksTestRu-high_school_physics 1 acc 0.1987 ± 0.0326
acc_norm 0.1987 ± 0.0326
hendrycksTestRu-high_school_psychology 1 acc 0.2000 ± 0.0171
acc_norm 0.2000 ± 0.0171
hendrycksTestRu-high_school_statistics 1 acc 0.1713 ± 0.0257
acc_norm 0.1713 ± 0.0257
hendrycksTestRu-high_school_us_history 1 acc 0.2647 ± 0.0310
acc_norm 0.2647 ± 0.0310
hendrycksTestRu-high_school_world_history 1 acc 0.2658 ± 0.0288
acc_norm 0.2658 ± 0.0288
hendrycksTestRu-human_aging 1 acc 0.2780 ± 0.0301
acc_norm 0.2780 ± 0.0301
hendrycksTestRu-human_sexuality 1 acc 0.2443 ± 0.0377
acc_norm 0.2443 ± 0.0377
hendrycksTestRu-international_law 1 acc 0.2314 ± 0.0385
acc_norm 0.2314 ± 0.0385
hendrycksTestRu-jurisprudence 1 acc 0.2593 ± 0.0424
acc_norm 0.2593 ± 0.0424
hendrycksTestRu-logical_fallacies 1 acc 0.2270 ± 0.0329
acc_norm 0.2270 ± 0.0329
hendrycksTestRu-machine_learning 1 acc 0.2857 ± 0.0429
acc_norm 0.2857 ± 0.0429
hendrycksTestRu-management 1 acc 0.2136 ± 0.0406
acc_norm 0.2136 ± 0.0406
hendrycksTestRu-marketing 1 acc 0.2991 ± 0.0300
acc_norm 0.2991 ± 0.0300
hendrycksTestRu-medical_genetics 1 acc 0.2700 ± 0.0446
acc_norm 0.2700 ± 0.0446
hendrycksTestRu-miscellaneous 1 acc 0.2490 ± 0.0155
acc_norm 0.2490 ± 0.0155
hendrycksTestRu-moral_disputes 1 acc 0.2601 ± 0.0236
acc_norm 0.2601 ± 0.0236
hendrycksTestRu-moral_scenarios 1 acc 0.2369 ± 0.0142
acc_norm 0.2369 ± 0.0142
hendrycksTestRu-nutrition 1 acc 0.2190 ± 0.0237
acc_norm 0.2190 ± 0.0237
hendrycksTestRu-philosophy 1 acc 0.1897 ± 0.0223
acc_norm 0.1897 ± 0.0223
hendrycksTestRu-prehistory 1 acc 0.2191 ± 0.0230
acc_norm 0.2191 ± 0.0230
hendrycksTestRu-professional_accounting 1 acc 0.2092 ± 0.0243
acc_norm 0.2092 ± 0.0243
hendrycksTestRu-professional_law 1 acc 0.2627 ± 0.0112
acc_norm 0.2627 ± 0.0112
hendrycksTestRu-professional_medicine 1 acc 0.1801 ± 0.0233
acc_norm 0.1801 ± 0.0233
hendrycksTestRu-professional_psychology 1 acc 0.2533 ± 0.0176
acc_norm 0.2533 ± 0.0176
hendrycksTestRu-public_relations 1 acc 0.2273 ± 0.0401
acc_norm 0.2273 ± 0.0401
hendrycksTestRu-security_studies 1 acc 0.1959 ± 0.0254
acc_norm 0.1959 ± 0.0254
hendrycksTestRu-sociology 1 acc 0.2239 ± 0.0295
acc_norm 0.2239 ± 0.0295
hendrycksTestRu-us_foreign_policy 1 acc 0.2300 ± 0.0423
acc_norm 0.2300 ± 0.0423
hendrycksTestRu-virology 1 acc 0.2831 ± 0.0351
acc_norm 0.2831 ± 0.0351
hendrycksTestRu-world_religions 1 acc 0.3158 ± 0.0357
acc_norm 0.3158 ± 0.0357
muserc 1 acc 0.0000 ± 0.0000
parus 0 acc 0.6500 ± 0.0479
rcb 1 acc 0.5273 ± 0.0337
f1 0.2302
rucos 0 f1 0.5248 ± 0.0057
em 0.5108 ± 0.0057
russe 0 acc 0.3691 ± 0.0052
ruterra 1 acc 0.4984 ± 0.0286
f1 0.2217
rwsd 0 acc 0.5539 ± 0.0349
xwinograd_ru 0 acc 0.5587 ± 0.0280
xnli_ru 0 acc 0.3940 ± 0.0069
Downloads last month
4
Safetensors
Model size
1.22B params
Tensor type
F32
·