{ "arm": "slp1_uni8k_d60m", "ckpt": "/home/kushal/sansar/data/experiments/train/runs/f0_slp1_uni8k_d60m/ckpt.pt", "tokenizer": "/home/kushal/sansar/data/experiments/tok/e2/spm_slp1_unigram_8000_v2.model", "vocab_size": 8000, "transliterate": "slp1", "strip_refs": false, "block": 512, "stride": 256, "step": 27203, "param_counts": { "total": 63173376, "embedding": 6537216, "token_embedding": 6144000, "position_embedding": 393216, "non_embedding": 56636160 }, "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": 163043.011, "bpb": 0.63437, "nll_per_token": 3.27646, "bytes_deva_per_token": 7.4512 }, "gita": { "records": 700, "tokens": 22518, "tokens_scored": 22517, "bytes_deva_utf8": 166845, "nll_nats": 26419.454, "bpb": 0.22845, "nll_per_token": 1.17331, "bytes_deva_per_token": 7.4094 }, "ood": { "records": 2000, "tokens": 425704, "tokens_scored": 425703, "bytes_deva_utf8": 2921851, "nll_nats": 1294054.139, "bpb": 0.63895, "nll_per_token": 3.03981, "bytes_deva_per_token": 6.8636 }, "prose": { "records": 2470, "tokens": 145348, "tokens_scored": 145347, "bytes_deva_utf8": 1015536, "nll_nats": 439125.752, "bpb": 0.62383, "nll_per_token": 3.02122, "bytes_deva_per_token": 6.9869 }, "vedic": { "records": 1000, "tokens": 16714, "tokens_scored": 16713, "bytes_deva_utf8": 77606, "nll_nats": 59659.921, "bpb": 1.10908, "nll_per_token": 3.56967, "bytes_deva_per_token": 4.6432 } }, "pooled": { "tokens": 660047, "bytes_deva_utf8": 4552632, "nll_nats": 1982302.277, "bpb": 0.62818 }, "seconds": 11.4 }