Hugging Face's logo

Atharva1232
/
tiny-math-1m

Model card Files
xet
 Community
tiny-math-1m / extrapolation.jsonl
Atharva1232's picture
Atharva1232
1M-param 4-digit addition model + full results (phase diagram, extrapolation, bake-off)
4a6c57b verified
Raw History Blame Contribute Delete
2.57 kB
{"tag": "sw_1m_4d_50000k", "trained_digits": 4, "test_digits": 1, "acc": 0.0, "correct": 0, "n": 100, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_1m_4d_50000k", "trained_digits": 4, "test_digits": 2, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_1m_4d_50000k", "trained_digits": 4, "test_digits": 3, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_1m_4d_50000k", "trained_digits": 4, "test_digits": 4, "acc": 1.0, "correct": 1976, "n": 1976, "trunc_frac": 0.0, "excluded_seen": 24}
{"tag": "sw_1m_4d_50000k", "trained_digits": 4, "test_digits": 5, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_1m_4d_50000k", "trained_digits": 4, "test_digits": 6, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_5m_4d_50000k", "trained_digits": 4, "test_digits": 1, "acc": 0.0, "correct": 0, "n": 100, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_5m_4d_50000k", "trained_digits": 4, "test_digits": 2, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_5m_4d_50000k", "trained_digits": 4, "test_digits": 3, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_5m_4d_50000k", "trained_digits": 4, "test_digits": 4, "acc": 1.0, "correct": 1976, "n": 1976, "trunc_frac": 0.0, "excluded_seen": 24}
{"tag": "sw_5m_4d_50000k", "trained_digits": 4, "test_digits": 5, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_5m_4d_50000k", "trained_digits": 4, "test_digits": 6, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_8m_4d_50000k", "trained_digits": 4, "test_digits": 1, "acc": 0.0, "correct": 0, "n": 100, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_8m_4d_50000k", "trained_digits": 4, "test_digits": 2, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_8m_4d_50000k", "trained_digits": 4, "test_digits": 3, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_8m_4d_50000k", "trained_digits": 4, "test_digits": 4, "acc": 1.0, "correct": 1976, "n": 1976, "trunc_frac": 0.0, "excluded_seen": 24}
{"tag": "sw_8m_4d_50000k", "trained_digits": 4, "test_digits": 5, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}
{"tag": "sw_8m_4d_50000k", "trained_digits": 4, "test_digits": 6, "acc": 0.0, "correct": 0, "n": 2000, "trunc_frac": 0.0, "excluded_seen": 0}