n-embd_256

done · peak unseen_mismatch 93.1

Configuration

n_layer: 2
n_head: 4
n_embd: 256
base_seed: 42

Figures

Results

param	seen_match	seen_mismatch	unseen_match	unseen_mismatch
0.0	100.0 ± 0.0	22.0 ± 21.2	100.0 ± 0.0	22.7 ± 21.8
0.1	100.0 ± 0.0	19.7 ± 23.5	100.0 ± 0.0	19.2 ± 22.9
0.2	100.0 ± 0.0	22.4 ± 24.0	100.0 ± 0.0	23.4 ± 24.5
0.3	100.0 ± 0.0	15.2 ± 15.6	100.0 ± 0.0	15.8 ± 16.0
0.4	100.0 ± 0.0	28.3 ± 20.9	100.0 ± 0.0	27.9 ± 20.5
0.5	100.0 ± 0.0	18.2 ± 27.4	100.0 ± 0.0	18.6 ± 28.1
0.6	100.0 ± 0.0	10.3 ± 12.6	100.0 ± 0.0	10.9 ± 12.1
0.7	100.0 ± 0.0	30.2 ± 30.8	100.0 ± 0.0	30.3 ± 30.6
0.8	100.0 ± 0.0	41.2 ± 30.7	100.0 ± 0.0	40.4 ± 31.6
0.9	100.0 ± 0.0	41.8 ± 38.2	100.0 ± 0.0	41.2 ± 38.0
1.0	100.0 ± 0.0	65.0 ± 26.2	100.0 ± 0.0	64.4 ± 25.9
1.1	100.0 ± 0.1	82.4 ± 21.6	100.0 ± 0.0	80.3 ± 21.1
1.2	99.9 ± 0.3	95.6 ± 6.2	99.7 ± 0.8	93.1 ± 9.1
1.3	99.9 ± 0.1	84.4 ± 28.6	99.1 ± 1.3	78.7 ± 27.0
1.4	99.7 ± 0.3	96.7 ± 2.8	97.5 ± 2.0	89.7 ± 4.1
1.5	99.5 ± 0.4	98.6 ± 0.9	97.0 ± 1.8	91.6 ± 5.1
1.6	99.3 ± 0.3	95.8 ± 5.1	94.3 ± 2.8	85.0 ± 7.5
1.7	99.4 ± 0.2	98.0 ± 1.0	94.7 ± 2.3	85.3 ± 5.7
1.8	99.4 ± 0.3	98.4 ± 1.2	93.1 ± 2.5	85.9 ± 5.9
1.9	99.3 ± 0.3	98.5 ± 0.7	90.3 ± 3.8	84.0 ± 6.4
2.0	99.4 ± 0.2	98.7 ± 0.2	89.8 ± 1.8	80.2 ± 4.0
2.1	99.4 ± 0.3	99.2 ± 0.5	88.1 ± 2.4	82.6 ± 4.5
2.2	99.4 ± 0.3	98.9 ± 0.3	86.3 ± 2.6	79.5 ± 1.1
2.3	99.5 ± 0.2	98.8 ± 0.6	87.6 ± 2.5	79.7 ± 6.0
2.4	99.6 ± 0.2	99.2 ± 0.4	85.7 ± 3.2	75.9 ± 6.2
2.5	99.7 ± 0.1	99.2 ± 0.4	84.9 ± 2.6	72.1 ± 4.4
2.6	99.6 ± 0.2	99.2 ± 0.2	83.5 ± 2.7	77.8 ± 4.5
2.7	99.7 ± 0.1	99.3 ± 0.2	82.6 ± 2.8	76.4 ± 5.5
2.8	99.6 ± 0.2	99.5 ± 0.1	82.2 ± 2.4	74.1 ± 4.2
2.9	99.6 ± 0.2	99.5 ± 0.4	79.7 ± 2.8	72.3 ± 5.1
3.0	99.8 ± 0.1	99.6 ± 0.2	82.6 ± 2.9	74.0 ± 1.4

n-embd_256

Configuration

Figures

Results

Downloads