Views
No views yet
Model: pgajo/mdeberta-xlwa-en-it
Dataset: TASTEset
Unshuffled ratio: ['0']
Shuffled ratio: ['1']
Best exact match epoch: 8
Best exact match: 92.27
Best epoch: 8
Drop duplicates: ['1']
Max epochs = 10
Optimizer lr = 3e-05
Optimizer eps = 1e-08
Batch size = 8
Dataset path = pgajo/mdeberta_EW-TT-PE_U0_S1_DROP1
| epoch | train_loss | train_f1 | train_exact | dev_loss | dev_f1 | dev_exact | test_loss | test_f1 | test_exact |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 0.91 | 75.05 | 65.45 | 0.35 | 89.94 | 87.02 | 0 | 0 | 0 |
| 2 | 0.29 | 91.33 | 87.7 | 0.29 | 91.71 | 89.78 | 0 | 0 | 0 |
| 3 | 0.17 | 93.83 | 92.05 | 0.34 | 90.88 | 90.06 | 0 | 0 | 0 |
| 4 | 0.14 | 95.56 | 94.26 | 0.3 | 93.25 | 90.88 | 0 | 0 | 0 |
| 5 | 0.1 | 96.79 | 95.72 | 0.48 | 92.13 | 90.06 | 0 | 0 | 0 |
| 6 | 0.06 | 97.98 | 97.37 | 0.37 | 93.1 | 91.71 | 0 | 0 | 0 |
| 7 | 0.05 | 98.24 | 98 | 0.43 | 93.25 | 91.16 | 0 | 0 | 0 |
| 8 | 0.05 | 98.16 | 97.79 | 0.48 | 93.57 | 92.27 | 0 | 0 | 0 |
| 9 | 0.04 | 98.67 | 98.2 | 0.5 | 92.91 | 91.44 | 0 | 0 | 0 |
| 10 | 0.05 | 98.44 | 98 | 0.42 | 91.73 | 90.06 | 0 | 0 | 0 |