Natural Language Inference on ChaosNLI S easy (test)
62.4Top-1 AccuracyModel B (antipignistic target)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Model B (antipignistic target)Train section=train_full, Val section=val_S_easy, Learning Rate=0.0072026.04 | 62.4 | — | — | |
| Model A (projection target)Train section=train_full, Val section=val_S_easy, Learning Rate=0.032026.04 | 61.7 | 0.007 | 0.013 | |
| Model A (projection target)Train section=train_full, Val section=val_full, Learning Rate=0.0072026.04 | 61.6 | 0.012 | 0.008 | |
| Model A (projection target)Train section=train_S_easy, Val section=val_full, Learning Rate=0.0052026.04 | 61.3 | 0.039 | 0.02 | |
| Model C (vote-proportion target)Train section=train_full, Val section=val_full, Learning Rate=0.0052026.04 | 60.8 | — | — | |
| Model B (antipignistic target)Train section=train_full, Val section=val_full, Learning Rate=0.0072026.04 | 60.4 | — | — | |
| Model C (vote-proportion target)Train section=train_full, Val section=val_S_easy, Learning Rate=0.082026.04 | 60.4 | — | — | |
| Model C (vote-proportion target)Train section=train_S_easy, Val section=val_full, Learning Rate=0.22026.04 | 59.3 | — | — | |
| Model C (vote-proportion target)Train section=train_S_easy, Val section=val_S_easy, Learning Rate=0.32026.04 | 58.9 | — | — | |
| Model B (antipignistic target)Train section=train_S_easy, Val section=val_S_easy, Learning Rate=0.092026.04 | 58.4 | — | — | |
| Model B (antipignistic target)Train section=train_S_easy, Val section=val_full, Learning Rate=0.12026.04 | 57.5 | — | — | |
| Model A (projection target)Train section=train_S_easy, Val section=val_S_easy, Learning Rate=0.22026.04 | 57.3 | 0.011 | 0.016 | |
| Model A (projection target)Train section=train_S_easy, Val section=val_S_amb, Learning Rate=0.082026.04 | 57.1 | 0.063 | 0.016 | |
| Model B (antipignistic target)Train section=train_S_amb, Val section=val_S_easy, Learning Rate=0.82026.04 | 56 | — | — | |
| Model C (vote-proportion target)Train section=train_S_easy, Val section=val_S_amb, Learning Rate=0.32026.04 | 55.5 | — | — | |
| Model B (antipignistic target)Train section=train_S_amb, Val section=val_full, Learning Rate=0.62026.04 | 54.1 | — | — | |
| Model A (projection target)Train section=train_S_amb, Val section=val_S_amb, Learning Rate=0.0092026.04 | 53.2 | 0.068 | 0.035 | |
| Model C (vote-proportion target)Train section=train_S_amb, Val section=val_S_easy, Learning Rate=0.52026.04 | 53.1 | — | — | |
| Model A (projection target)Train section=train_S_amb, Val section=val_S_easy, Learning Rate=0.012026.04 | 52.7 | 0.033 | 0.004 | |
| Model A (projection target)Train section=train_S_amb, Val section=val_full, Learning Rate=0.0092026.04 | 51.9 | 0.023 | 0.008 | |
| Model C (vote-proportion target)Train section=train_full, Val section=val_S_amb, Learning Rate=0.00012026.04 | 51.6 | — | — | |
| Model C (vote-proportion target)Train section=train_S_amb, Val section=val_full, Learning Rate=0.0032026.04 | 51.1 | — | — | |
| Model B (antipignistic target)Train section=train_S_easy, Val section=val_S_amb, Learning Rate=0.72026.04 | 50.8 | — | — | |
| Model B (antipignistic target)Train section=train_full, Val section=val_S_amb, Learning Rate=0.62026.04 | 50.3 | — | — | |
| Model C (vote-proportion target)Train section=train_S_amb, Val section=val_S_amb, Learning Rate=0.72026.04 | 49.7 | — | — | |
| Model A (projection target)Train section=train_full, Val section=val_S_amb, Learning Rate=0.52026.04 | 49.2 | 0.011 | 0.024 | |
| Model B (antipignistic target)Train section=train_S_amb, Val section=val_S_amb, Learning Rate=0.72026.04 | 46.4 | — | — |