BestTerm-440M-Checkpts / benchmarks /original_base_polynomials.json
N8Programs's picture
Expand BestTerm model card with benchmark comparisons and reproducibility
6c2b324 verified
Raw History Blame Contribute Delete
13.7 kB
{
"csv_path": "base_polynomial_continuation_mlx_b128.csv",
"tasks": {
"arithmetic": {
"degree": 1,
"parsed": 4800,
"total": 4800,
"correct": 4526,
"accuracy": 0.9429166666666666,
"parsed_fraction": 1.0,
"by_k": [
{
"k": 2,
"parsed": 200,
"total": 200,
"correct": 9,
"accuracy": 0.045
},
{
"k": 3,
"parsed": 200,
"total": 200,
"correct": 153,
"accuracy": 0.765
},
{
"k": 4,
"parsed": 200,
"total": 200,
"correct": 187,
"accuracy": 0.935
},
{
"k": 5,
"parsed": 200,
"total": 200,
"correct": 197,
"accuracy": 0.985
},
{
"k": 6,
"parsed": 200,
"total": 200,
"correct": 195,
"accuracy": 0.975
},
{
"k": 7,
"parsed": 200,
"total": 200,
"correct": 196,
"accuracy": 0.98
},
{
"k": 8,
"parsed": 200,
"total": 200,
"correct": 197,
"accuracy": 0.985
},
{
"k": 9,
"parsed": 200,
"total": 200,
"correct": 198,
"accuracy": 0.99
},
{
"k": 10,
"parsed": 200,
"total": 200,
"correct": 198,
"accuracy": 0.99
},
{
"k": 11,
"parsed": 200,
"total": 200,
"correct": 199,
"accuracy": 0.995
},
{
"k": 12,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 13,
"parsed": 200,
"total": 200,
"correct": 199,
"accuracy": 0.995
},
{
"k": 14,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 15,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 16,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 17,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 18,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 19,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 20,
"parsed": 200,
"total": 200,
"correct": 199,
"accuracy": 0.995
},
{
"k": 21,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 22,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 23,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 24,
"parsed": 200,
"total": 200,
"correct": 200,
"accuracy": 1.0
},
{
"k": 25,
"parsed": 200,
"total": 200,
"correct": 199,
"accuracy": 0.995
}
]
},
"quadratic": {
"degree": 2,
"parsed": 4600,
"total": 4600,
"correct": 3973,
"accuracy": 0.8636956521739131,
"parsed_fraction": 1.0,
"by_k": [
{
"k": 3,
"parsed": 200,
"total": 200,
"correct": 1,
"accuracy": 0.005
},
{
"k": 4,
"parsed": 200,
"total": 200,
"correct": 63,
"accuracy": 0.315
},
{
"k": 5,
"parsed": 200,
"total": 200,
"correct": 99,
"accuracy": 0.495
},
{
"k": 6,
"parsed": 200,
"total": 200,
"correct": 144,
"accuracy": 0.72
},
{
"k": 7,
"parsed": 200,
"total": 200,
"correct": 182,
"accuracy": 0.91
},
{
"k": 8,
"parsed": 200,
"total": 200,
"correct": 184,
"accuracy": 0.92
},
{
"k": 9,
"parsed": 200,
"total": 200,
"correct": 187,
"accuracy": 0.935
},
{
"k": 10,
"parsed": 200,
"total": 200,
"correct": 191,
"accuracy": 0.955
},
{
"k": 11,
"parsed": 200,
"total": 200,
"correct": 190,
"accuracy": 0.95
},
{
"k": 12,
"parsed": 200,
"total": 200,
"correct": 192,
"accuracy": 0.96
},
{
"k": 13,
"parsed": 200,
"total": 200,
"correct": 195,
"accuracy": 0.975
},
{
"k": 14,
"parsed": 200,
"total": 200,
"correct": 196,
"accuracy": 0.98
},
{
"k": 15,
"parsed": 200,
"total": 200,
"correct": 194,
"accuracy": 0.97
},
{
"k": 16,
"parsed": 200,
"total": 200,
"correct": 196,
"accuracy": 0.98
},
{
"k": 17,
"parsed": 200,
"total": 200,
"correct": 198,
"accuracy": 0.99
},
{
"k": 18,
"parsed": 200,
"total": 200,
"correct": 192,
"accuracy": 0.96
},
{
"k": 19,
"parsed": 200,
"total": 200,
"correct": 194,
"accuracy": 0.97
},
{
"k": 20,
"parsed": 200,
"total": 200,
"correct": 198,
"accuracy": 0.99
},
{
"k": 21,
"parsed": 200,
"total": 200,
"correct": 195,
"accuracy": 0.975
},
{
"k": 22,
"parsed": 200,
"total": 200,
"correct": 195,
"accuracy": 0.975
},
{
"k": 23,
"parsed": 200,
"total": 200,
"correct": 194,
"accuracy": 0.97
},
{
"k": 24,
"parsed": 200,
"total": 200,
"correct": 197,
"accuracy": 0.985
},
{
"k": 25,
"parsed": 200,
"total": 200,
"correct": 196,
"accuracy": 0.98
}
]
},
"cubic": {
"degree": 3,
"parsed": 4400,
"total": 4400,
"correct": 3293,
"accuracy": 0.7484090909090909,
"parsed_fraction": 1.0,
"by_k": [
{
"k": 4,
"parsed": 200,
"total": 200,
"correct": 3,
"accuracy": 0.015
},
{
"k": 5,
"parsed": 200,
"total": 200,
"correct": 12,
"accuracy": 0.06
},
{
"k": 6,
"parsed": 200,
"total": 200,
"correct": 26,
"accuracy": 0.13
},
{
"k": 7,
"parsed": 200,
"total": 200,
"correct": 62,
"accuracy": 0.31
},
{
"k": 8,
"parsed": 200,
"total": 200,
"correct": 103,
"accuracy": 0.515
},
{
"k": 9,
"parsed": 200,
"total": 200,
"correct": 143,
"accuracy": 0.715
},
{
"k": 10,
"parsed": 200,
"total": 200,
"correct": 160,
"accuracy": 0.8
},
{
"k": 11,
"parsed": 200,
"total": 200,
"correct": 172,
"accuracy": 0.86
},
{
"k": 12,
"parsed": 200,
"total": 200,
"correct": 181,
"accuracy": 0.905
},
{
"k": 13,
"parsed": 200,
"total": 200,
"correct": 179,
"accuracy": 0.895
},
{
"k": 14,
"parsed": 200,
"total": 200,
"correct": 183,
"accuracy": 0.915
},
{
"k": 15,
"parsed": 200,
"total": 200,
"correct": 185,
"accuracy": 0.925
},
{
"k": 16,
"parsed": 200,
"total": 200,
"correct": 189,
"accuracy": 0.945
},
{
"k": 17,
"parsed": 200,
"total": 200,
"correct": 186,
"accuracy": 0.93
},
{
"k": 18,
"parsed": 200,
"total": 200,
"correct": 192,
"accuracy": 0.96
},
{
"k": 19,
"parsed": 200,
"total": 200,
"correct": 188,
"accuracy": 0.94
},
{
"k": 20,
"parsed": 200,
"total": 200,
"correct": 190,
"accuracy": 0.95
},
{
"k": 21,
"parsed": 200,
"total": 200,
"correct": 187,
"accuracy": 0.935
},
{
"k": 22,
"parsed": 200,
"total": 200,
"correct": 187,
"accuracy": 0.935
},
{
"k": 23,
"parsed": 200,
"total": 200,
"correct": 187,
"accuracy": 0.935
},
{
"k": 24,
"parsed": 200,
"total": 200,
"correct": 189,
"accuracy": 0.945
},
{
"k": 25,
"parsed": 200,
"total": 200,
"correct": 189,
"accuracy": 0.945
}
]
},
"quartic": {
"degree": 4,
"parsed": 4200,
"total": 4200,
"correct": 2861,
"accuracy": 0.6811904761904762,
"parsed_fraction": 1.0,
"by_k": [
{
"k": 5,
"parsed": 200,
"total": 200,
"correct": 5,
"accuracy": 0.025
},
{
"k": 6,
"parsed": 200,
"total": 200,
"correct": 10,
"accuracy": 0.05
},
{
"k": 7,
"parsed": 200,
"total": 200,
"correct": 25,
"accuracy": 0.125
},
{
"k": 8,
"parsed": 200,
"total": 200,
"correct": 39,
"accuracy": 0.195
},
{
"k": 9,
"parsed": 200,
"total": 200,
"correct": 79,
"accuracy": 0.395
},
{
"k": 10,
"parsed": 200,
"total": 200,
"correct": 114,
"accuracy": 0.57
},
{
"k": 11,
"parsed": 200,
"total": 200,
"correct": 139,
"accuracy": 0.695
},
{
"k": 12,
"parsed": 200,
"total": 200,
"correct": 156,
"accuracy": 0.78
},
{
"k": 13,
"parsed": 200,
"total": 200,
"correct": 155,
"accuracy": 0.775
},
{
"k": 14,
"parsed": 200,
"total": 200,
"correct": 160,
"accuracy": 0.8
},
{
"k": 15,
"parsed": 200,
"total": 200,
"correct": 169,
"accuracy": 0.845
},
{
"k": 16,
"parsed": 200,
"total": 200,
"correct": 173,
"accuracy": 0.865
},
{
"k": 17,
"parsed": 200,
"total": 200,
"correct": 177,
"accuracy": 0.885
},
{
"k": 18,
"parsed": 200,
"total": 200,
"correct": 175,
"accuracy": 0.875
},
{
"k": 19,
"parsed": 200,
"total": 200,
"correct": 176,
"accuracy": 0.88
},
{
"k": 20,
"parsed": 200,
"total": 200,
"correct": 178,
"accuracy": 0.89
},
{
"k": 21,
"parsed": 200,
"total": 200,
"correct": 184,
"accuracy": 0.92
},
{
"k": 22,
"parsed": 200,
"total": 200,
"correct": 182,
"accuracy": 0.91
},
{
"k": 23,
"parsed": 200,
"total": 200,
"correct": 189,
"accuracy": 0.945
},
{
"k": 24,
"parsed": 200,
"total": 200,
"correct": 189,
"accuracy": 0.945
},
{
"k": 25,
"parsed": 200,
"total": 200,
"correct": 187,
"accuracy": 0.935
}
]
}
}
}