{ "arm": "tokv3_v01", "ckpt": "/home/kushal/sansar/data/experiments/train/runs/tokv3_v01_d20m/ckpt.pt", "tokenizer": "/home/kushal/sansar/data/experiments/tok/e2/spm_slp1_unigram_8000_v2.model", "vocab_size": 8000, "transliterate": "slp1", "strip_refs": false, "clean": "deva", "text_field": "text_deva", "denominator": "bytes_deva_utf8", "block": 512, "stride": 256, "step": 6968, "param_counts": { "total": 27073024, "embedding": 4096000, "token_embedding": 4096000, "position_embedding": 0, "value_embedding": 0, "head": 4096000, "non_embedding": 18881024 }, "method": "records joined with EOS into one stream per set; sliding window, only the last `stride` predictions of each window after the first are scored; nats / Devanagari UTF-8 bytes of the cleaned text / ln 2", "per_set": { "dcs_gold": { "records": 3000, "tokens": 49763, "tokens_scored": 49762, "bytes_deva_utf8": 370794, "nll_nats": 181577.925, "bpb": 0.70649, "nll_per_token": 3.64893, "bytes_deva_per_token": 7.4512 }, "gita": { "records": 700, "tokens": 22518, "tokens_scored": 22517, "bytes_deva_utf8": 166845, "nll_nats": 59318.667, "bpb": 0.51292, "nll_per_token": 2.63439, "bytes_deva_per_token": 7.4094 }, "ood": { "records": 2000, "tokens": 425704, "tokens_scored": 425703, "bytes_deva_utf8": 2921851, "nll_nats": 1463285.41, "bpb": 0.72251, "nll_per_token": 3.43734, "bytes_deva_per_token": 6.8636 }, "prose": { "records": 2470, "tokens": 145348, "tokens_scored": 145347, "bytes_deva_utf8": 1015536, "nll_nats": 484759.998, "bpb": 0.68866, "nll_per_token": 3.33519, "bytes_deva_per_token": 6.9869 }, "vedic": { "records": 1000, "tokens": 16714, "tokens_scored": 16713, "bytes_deva_utf8": 77606, "nll_nats": 52100.069, "bpb": 0.96854, "nll_per_token": 3.11734, "bytes_deva_per_token": 4.6432 } }, "pooled": { "tokens": 660047, "bytes_deva_utf8": 4552632, "nll_nats": 2241042.069, "bpb": 0.71017 }, "seconds": 9.4 }