{
"tokenizer": "MorpheL-ablation-random-baseline",
"config": {
"vocab_size": 32055,
"algorithm": "random_uniform",
"random_max_cuts": 2,
"seed": 42,
"min_frequency": 2,
"special_tokens": [
"",
"",
"",
"",
""
],
"dataset": "facebook/xnli/tr",
"corpus_lines": 800404,
"mi_index_words": 0
},
"metrics": {
"fertility": 1.4316636496798583,
"tokens_per_char": 0.19114695689453448,
"avg_seq_len": 16.921666666666667,
"vocab_coverage": 1.0,
"oov_rate": 0.0,
"fallback_event_rate": 0.130001215323308,
"char_shatter_rate": 0.0,
"n_sentences": 15000,
"n_word_types": 26764
},
"baselines": {
"BPE": {
"fertility": null,
"tokens_per_char": null,
"avg_seq_len": null,
"vocab_coverage": null,
"oov_rate": null
},
"WordPiece": {
"fertility": null,
"tokens_per_char": null,
"avg_seq_len": null,
"vocab_coverage": null,
"oov_rate": null
},
"Unigram": {
"fertility": null,
"tokens_per_char": null,
"avg_seq_len": null,
"vocab_coverage": null,
"oov_rate": null
}
}
}