{ "arm": "slp1_uni8k_d350m_plus_all_3x", "ckpt": "/home/kushal/sansar/data/experiments/train/runs/f9_slp1_uni8k_d350m_plus_all_3x/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": 103527, "param_counts": { "total": 318424064, "embedding": 8192000, "token_embedding": 8192000, "position_embedding": 0, "value_embedding": 0, "head": 8192000, "non_embedding": 302040064 }, "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": 146155.688, "bpb": 0.56867, "nll_per_token": 2.93709, "bytes_deva_per_token": 7.4512 }, "gita": { "records": 700, "tokens": 22518, "tokens_scored": 22517, "bytes_deva_utf8": 166845, "nll_nats": 15810.887, "bpb": 0.13672, "nll_per_token": 0.70218, "bytes_deva_per_token": 7.4094 }, "ood": { "records": 2000, "tokens": 425704, "tokens_scored": 425703, "bytes_deva_utf8": 2921851, "nll_nats": 1122476.182, "bpb": 0.55423, "nll_per_token": 2.63676, "bytes_deva_per_token": 6.8636 }, "prose": { "records": 2470, "tokens": 145348, "tokens_scored": 145347, "bytes_deva_utf8": 1015536, "nll_nats": 380543.803, "bpb": 0.54061, "nll_per_token": 2.61817, "bytes_deva_per_token": 6.9869 }, "vedic": { "records": 1000, "tokens": 16714, "tokens_scored": 16713, "bytes_deva_utf8": 77606, "nll_nats": 37071.39, "bpb": 0.68916, "nll_per_token": 2.21812, "bytes_deva_per_token": 4.6432 } }, "pooled": { "tokens": 660047, "bytes_deva_utf8": 4552632, "nll_nats": 1702057.95, "bpb": 0.53937 }, "seconds": 72.0 }