gsaltintas commited on
Commit
01461be
·
verified ·
1 Parent(s): ca4cc76

Upload safe_v2/flexitok--bpe_vie_Latn_8000_overlap.json with huggingface_hub

Browse files
safe_v2/flexitok--bpe_vie_Latn_8000_overlap.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"1": {"ratio_to_total_tokens": 0.577, "expected_training_ratio_in_superset": 0.027476190476190473, "num_tokens": 4616}, "2": {"ratio_to_total_tokens": 0.11375, "expected_training_ratio_in_superset": 0.010833333333333332, "num_tokens": 910}, "3": {"ratio_to_total_tokens": 0.034375, "expected_training_ratio_in_superset": 0.004910714285714286, "num_tokens": 275}, "4": {"ratio_to_total_tokens": 0.0245, "expected_training_ratio_in_superset": 0.004666666666666666, "num_tokens": 196}, "5": {"ratio_to_total_tokens": 0.02025, "expected_training_ratio_in_superset": 0.004821428571428571, "num_tokens": 162}, "6": {"ratio_to_total_tokens": 0.015625, "expected_training_ratio_in_superset": 0.004464285714285714, "num_tokens": 125}, "7": {"ratio_to_total_tokens": 0.015875, "expected_training_ratio_in_superset": 0.005291666666666666, "num_tokens": 127}, "8": {"ratio_to_total_tokens": 0.013625, "expected_training_ratio_in_superset": 0.00519047619047619, "num_tokens": 109}, "9": {"ratio_to_total_tokens": 0.015875, "expected_training_ratio_in_superset": 0.006803571428571428, "num_tokens": 127}, "10": {"ratio_to_total_tokens": 0.015, "expected_training_ratio_in_superset": 0.007142857142857143, "num_tokens": 120}, "11": {"ratio_to_total_tokens": 0.01375, "expected_training_ratio_in_superset": 0.007202380952380952, "num_tokens": 110}, "12": {"ratio_to_total_tokens": 0.01275, "expected_training_ratio_in_superset": 0.007285714285714286, "num_tokens": 102}, "13": {"ratio_to_total_tokens": 0.012375, "expected_training_ratio_in_superset": 0.0076607142857142855, "num_tokens": 99}, "14": {"ratio_to_total_tokens": 0.014625, "expected_training_ratio_in_superset": 0.00975, "num_tokens": 117}, "15": {"ratio_to_total_tokens": 0.013875, "expected_training_ratio_in_superset": 0.009910714285714287, "num_tokens": 111}, "16": {"ratio_to_total_tokens": 0.008375, "expected_training_ratio_in_superset": 0.00638095238095238, "num_tokens": 67}, "17": {"ratio_to_total_tokens": 0.006125, "expected_training_ratio_in_superset": 0.004958333333333333, "num_tokens": 49}, "18": {"ratio_to_total_tokens": 0.009125, "expected_training_ratio_in_superset": 0.007821428571428571, "num_tokens": 73}, "19": {"ratio_to_total_tokens": 0.006625, "expected_training_ratio_in_superset": 0.005994047619047619, "num_tokens": 53}, "20": {"ratio_to_total_tokens": 0.005875, "expected_training_ratio_in_superset": 0.005595238095238095, "num_tokens": 47}, "21": {"ratio_to_total_tokens": 0.050625, "expected_training_ratio_in_superset": 0.050625, "num_tokens": 405}, "total_training_compared_to_full_model": 0.2047857142857143}