NeuronAI-4B / benchmark_results.json
kmamaroziqov's picture
Benchmarks: replace alloma-3B/1B with Llama-3.1-8B-Instruct-Uz and Mistral-7B-Instruct-Uz
47ca47a verified
Raw
History Blame Contribute Delete
9.44 kB
{
"schema_version": 1,
"metric_note": "Accuracy for non-translation tasks; COMET for FLORES+; weighted sum normalized by 0.95.",
"weights": {
"uzlib_slice_full": 0.2,
"tumlu_uzbek_full": 0.2,
"flores_en_uz_full": 0.15,
"news_full": 0.1,
"mmlu_english_full": 0.1,
"mmlu_uz_full": 0.1,
"flores_uz_en_full": 0.05,
"sentiment_binary_full": 0.05
},
"labels": {
"uzlib_slice_full": "UzLiB",
"tumlu_uzbek_full": "TUMLU-Uzbek",
"flores_en_uz_full": "FLORES+ en to uz",
"news_full": "News",
"mmlu_english_full": "MMLU English",
"mmlu_uz_full": "MMLU Uzbek",
"flores_uz_en_full": "FLORES+ uz to en",
"sentiment_binary_full": "Sentiment"
},
"models": {
"NeuronAI-4B": {
"run_id": "qwen35_4b_lora_r64_grouped_ckpt4749_public",
"suite_id": "public_uzbek_full_comet_vllm_v2",
"tasks": {
"uzlib_slice_full": 0.6120365394948952,
"tumlu_uzbek_full": 0.45,
"flores_en_uz_full": 0.8965457885374531,
"news_full": 0.7914612766835104,
"mmlu_english_full": 0.6406494801310355,
"mmlu_uz_full": 0.5700754878222476,
"flores_uz_en_full": 0.8762970898743587,
"sentiment_binary_full": 0.9575
},
"invalid_rate": {
"uzlib_slice_full": 0.0,
"tumlu_uzbek_full": 0.0,
"flores_en_uz_full": null,
"news_full": 0.0,
"mmlu_english_full": 0.0,
"mmlu_uz_full": 0.0,
"flores_uz_en_full": null,
"sentiment_binary_full": 0.0
},
"normalized_weighted_score": 0.6724185843547309
},
"Qwen3.5-4B": {
"run_id": "qwen35_4b_instruct_full_20260817_081728",
"suite_id": "public_uzbek_full_vllm",
"tasks": {
"uzlib_slice_full": 0.4030091348737238,
"tumlu_uzbek_full": 0.4042857142857143,
"flores_en_uz_full": 0.8554783304304908,
"news_full": 0.6734350830153656,
"mmlu_english_full": 0.7266058965959266,
"mmlu_uz_full": 0.5257798034468024,
"flores_uz_en_full": 0.8618190287356948,
"sentiment_binary_full": 0.8482
},
"invalid_rate": {
"uzlib_slice_full": 0.0,
"tumlu_uzbek_full": 0.0,
"flores_en_uz_full": null,
"news_full": 0.0,
"mmlu_english_full": 0.0,
"mmlu_uz_full": 0.0,
"flores_uz_en_full": null,
"sentiment_binary_full": 0.0145
},
"normalized_weighted_score": 0.5977513148832162
},
"alloma-8B": {
"run_id": "alloma_8b_full_public_composite",
"suite_id": "public_uzbek_full_composite_apst",
"source_files": [
"reports/alloma_card_protocol_full/alloma-8B.json",
"reports/eval_suites/external_public/alloma_8b_uzlib_full_20260615/uzlib_full.json",
"reports/eval_suites/public_full_comet/alloma_8b_strict_missing_uz_metrics/tumlu_uzbek_full_apst.json",
"reports/eval_suites/public_full_comet/alloma_8b_strict_missing_uz_metrics/mmlu_uz_full_apst.json"
],
"tasks": {
"uzlib_slice_full": 0.4239656098871574,
"tumlu_uzbek_full": 0.20714285714285716,
"flores_en_uz_full": 0.8779,
"news_full": 0.5777,
"mmlu_english_full": 0.5347,
"mmlu_uz_full": 0.40037031761857284,
"flores_uz_en_full": 0.8713,
"sentiment_binary_full": 0.7994
},
"invalid_rate": {
"uzlib_slice_full": 0.0338527673293928,
"tumlu_uzbek_full": 0.25857142857142856,
"flores_en_uz_full": null,
"news_full": null,
"mmlu_english_full": null,
"mmlu_uz_full": 0.09051417177040308,
"flores_uz_en_full": null,
"sentiment_binary_full": null
},
"normalized_weighted_score": 0.5186512896503792
},
"Llama-3.1-8B-Instruct-Uz": {
"run_id": "strict_full_llama31_8b_instruct_uz",
"suite_id": "public_uzbek_full_comet_vllm_v2",
"tasks": {
"uzlib_slice_full": 0.31649650725416445,
"tumlu_uzbek_full": 0.32,
"flores_en_uz_full": 0.8666636186669038,
"news_full": 0.603372176961947,
"mmlu_english_full": 0.47578692493946734,
"mmlu_uz_full": 0.38719555618857715,
"flores_uz_en_full": 0.7764609643717557,
"sentiment_binary_full": 0.8259
},
"invalid_rate": {
"uzlib_slice_full": 0.0,
"tumlu_uzbek_full": 0.05714285714285714,
"flores_en_uz_full": null,
"news_full": 2.0624935547076414e-05,
"mmlu_english_full": 0.0037031761857285288,
"mmlu_uz_full": 0.009471585244267198,
"flores_uz_en_full": null,
"sentiment_binary_full": 0.0045
},
"normalized_weighted_score": 0.5095287981878477
},
"Mistral-7B-Instruct-Uz": {
"run_id": "strict_full_mistral7b_instruct_uz",
"suite_id": "public_uzbek_full_comet_vllm_v2",
"tasks": {
"uzlib_slice_full": 0.3277807630306287,
"tumlu_uzbek_full": 0.33714285714285713,
"flores_en_uz_full": 0.8859170079972982,
"news_full": 0.6209343095802825,
"mmlu_english_full": 0.294972226178607,
"mmlu_uz_full": 0.3505910838911836,
"flores_uz_en_full": 0.7826120569790223,
"sentiment_binary_full": 0.8083
},
"invalid_rate": {
"uzlib_slice_full": 0.011284255776464266,
"tumlu_uzbek_full": 0.05714285714285714,
"flores_en_uz_full": null,
"news_full": 0.0,
"mmlu_english_full": 0.025708588520153824,
"mmlu_uz_full": 0.01167924797037459,
"flores_uz_en_full": null,
"sentiment_binary_full": 0.0459
},
"normalized_weighted_score": 0.4969133053139477
}
},
"checkpoints": {
"0.25 epoch": {
"run_id": "qwen35_4b_lora_r64_grouped_ckpt1188_public",
"suite_id": "public_uzbek_full_comet_vllm_v2",
"tasks": {
"uzlib_slice_full": 0.6093498119290703,
"tumlu_uzbek_full": 0.44571428571428573,
"flores_en_uz_full": 0.8898104962171044,
"news_full": 0.772197586882541,
"mmlu_english_full": 0.6312491098134169,
"mmlu_uz_full": 0.5549779233727389,
"flores_uz_en_full": 0.8765152560768583,
"sentiment_binary_full": 0.9377
},
"invalid_rate": {
"uzlib_slice_full": 0.0,
"tumlu_uzbek_full": 0.0,
"flores_en_uz_full": null,
"news_full": 0.0,
"mmlu_english_full": 0.0,
"mmlu_uz_full": 0.0,
"flores_uz_en_full": null,
"sentiment_binary_full": 0.0001
},
"normalized_weighted_score": 0.6642501250231047
},
"0.50 epoch": {
"run_id": "qwen35_4b_lora_r64_grouped_ckpt2376_public",
"suite_id": "public_uzbek_full_comet_vllm_v2",
"tasks": {
"uzlib_slice_full": 0.6012896292315959,
"tumlu_uzbek_full": 0.44571428571428573,
"flores_en_uz_full": 0.8914647964086623,
"news_full": 0.7503764050737342,
"mmlu_english_full": 0.621919954422447,
"mmlu_uz_full": 0.5524854009400371,
"flores_uz_en_full": 0.8756085765367719,
"sentiment_binary_full": 0.9524
},
"invalid_rate": {
"uzlib_slice_full": 0.0,
"tumlu_uzbek_full": 0.0,
"flores_en_uz_full": null,
"news_full": 0.0,
"mmlu_english_full": 0.0,
"mmlu_uz_full": 0.0,
"flores_uz_en_full": null,
"sentiment_binary_full": 0.0
},
"normalized_weighted_score": 0.6599990603378274
},
"0.75 epoch": {
"run_id": "qwen35_4b_lora_r64_grouped_seed42_control_public",
"suite_id": "public_uzbek_full_comet_vllm_v2",
"tasks": {
"uzlib_slice_full": 0.6104245029554003,
"tumlu_uzbek_full": 0.39285714285714285,
"flores_en_uz_full": 0.8960352256901529,
"news_full": 0.8070434154893266,
"mmlu_english_full": 0.640364620424441,
"mmlu_uz_full": 0.5671556758296539,
"flores_uz_en_full": 0.8757696719001098,
"sentiment_binary_full": 0.9514
},
"invalid_rate": {
"uzlib_slice_full": 0.0,
"tumlu_uzbek_full": 0.0,
"flores_en_uz_full": null,
"news_full": 0.0,
"mmlu_english_full": 0.0,
"mmlu_uz_full": 0.0,
"flores_uz_en_full": null,
"sentiment_binary_full": 0.0
},
"normalized_weighted_score": 0.6609225976688203
},
"1.00 epoch": {
"run_id": "qwen35_4b_lora_r64_grouped_ckpt4749_public",
"suite_id": "public_uzbek_full_comet_vllm_v2",
"tasks": {
"uzlib_slice_full": 0.6120365394948952,
"tumlu_uzbek_full": 0.45,
"flores_en_uz_full": 0.8965457885374531,
"news_full": 0.7914612766835104,
"mmlu_english_full": 0.6406494801310355,
"mmlu_uz_full": 0.5700754878222476,
"flores_uz_en_full": 0.8762970898743587,
"sentiment_binary_full": 0.9575
},
"invalid_rate": {
"uzlib_slice_full": 0.0,
"tumlu_uzbek_full": 0.0,
"flores_en_uz_full": null,
"news_full": 0.0,
"mmlu_english_full": 0.0,
"mmlu_uz_full": 0.0,
"flores_uz_en_full": null,
"sentiment_binary_full": 0.0
},
"normalized_weighted_score": 0.6724185843547309
}
},
"tokenizer_fertility": {
"status": "superseded",
"result": "fertility_large_20260825.json",
"note": "Use the corpus-stratified 2026-08-25 evaluation; the old 20k uz-crawl-only result was in-domain."
}
}