Natural Language Inference on ChaosNLI (test)
50.5Top-1 AccuracyModel C (vote-proportion target)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Model C (vote-proportion target)Train section=train_full, Val section=val_full, Learning Rate=0.0052026.04 | 50.5 | — | — | |
| Model C (vote-proportion target)Train section=train_S_easy, Val section=val_full, Learning Rate=0.22026.04 | 50.3 | — | — | |
| Model A (projection target)Train section=train_full, Val section=val_full, Learning Rate=0.0072026.04 | 50 | 0.004 | 0.005 | |
| Model A (projection target)Train section=train_full, Val section=val_S_easy, Learning Rate=0.032026.04 | 50 | 0.002 | 0.005 | |
| Model B (antipignistic target)Train section=train_full, Val section=val_S_easy, Learning Rate=0.0072026.04 | 49.9 | — | — | |
| Model A (projection target)Train section=train_S_easy, Val section=val_full, Learning Rate=0.0052026.04 | 49.9 | 0.013 | 0.004 | |
| Model B (antipignistic target)Train section=train_full, Val section=val_full, Learning Rate=0.0072026.04 | 49.6 | — | — | |
| Model C (vote-proportion target)Train section=train_full, Val section=val_S_easy, Learning Rate=0.082026.04 | 49.5 | — | — | |
| Model A (projection target)Train section=train_S_easy, Val section=val_S_easy, Learning Rate=0.22026.04 | 49.3 | 0.004 | 0.006 | |
| Model B (antipignistic target)Train section=train_S_easy, Val section=val_S_easy, Learning Rate=0.092026.04 | 48.9 | — | — | |
| Model C (vote-proportion target)Train section=train_S_easy, Val section=val_S_easy, Learning Rate=0.32026.04 | 48.6 | — | — | |
| Model B (antipignistic target)Train section=train_S_easy, Val section=val_full, Learning Rate=0.12026.04 | 48.5 | — | — | |
| Model A (projection target)Train section=train_S_easy, Val section=val_S_amb, Learning Rate=0.082026.04 | 48.3 | 0.037 | 0.006 | |
| Model C (vote-proportion target)Train section=train_S_easy, Val section=val_S_amb, Learning Rate=0.32026.04 | 47.7 | — | — | |
| Model A (projection target)Train section=train_S_amb, Val section=val_S_amb, Learning Rate=0.0092026.04 | 46.8 | 0.047 | 0.036 | |
| Model A (projection target)Train section=train_S_amb, Val section=val_full, Learning Rate=0.0092026.04 | 46.7 | 0.017 | 0.006 | |
| Model A (projection target)Train section=train_S_amb, Val section=val_S_easy, Learning Rate=0.012026.04 | 46.5 | 0.015 | 0.012 | |
| Model C (vote-proportion target)Train section=train_S_amb, Val section=val_full, Learning Rate=0.0032026.04 | 46.1 | — | — | |
| Model C (vote-proportion target)Train section=train_full, Val section=val_S_amb, Learning Rate=0.00012026.04 | 45.6 | — | — | |
| Model C (vote-proportion target)Train section=train_S_amb, Val section=val_S_easy, Learning Rate=0.52026.04 | 45.4 | — | — | |
| Model B (antipignistic target)Train section=train_S_amb, Val section=val_full, Learning Rate=0.62026.04 | 45 | — | — | |
| Model B (antipignistic target)Train section=train_S_amb, Val section=val_S_easy, Learning Rate=0.82026.04 | 45 | — | — | |
| Model A (projection target)Train section=train_full, Val section=val_S_amb, Learning Rate=0.52026.04 | 44.9 | 0.002 | 0.007 | |
| Model B (antipignistic target)Train section=train_full, Val section=val_S_amb, Learning Rate=0.62026.04 | 44.7 | — | — | |
| Model B (antipignistic target)Train section=train_S_easy, Val section=val_S_amb, Learning Rate=0.72026.04 | 44.7 | — | — | |
| Model C (vote-proportion target)Train section=train_S_amb, Val section=val_S_amb, Learning Rate=0.72026.04 | 43.2 | — | — | |
| Model B (antipignistic target)Train section=train_S_amb, Val section=val_S_amb, Learning Rate=0.72026.04 | 42.1 | — | — |