Views
No views yet
Model: pgajo/mbert-xlwa-en-it
Dataset: TASTEset
Unshuffled ratio: ['0']
Shuffled ratio: ['1']
Best exact match epoch: 9
Best exact match: 76.24
Best epoch: 9
Drop duplicates: ['1']
Max epochs = 10
Optimizer lr = 3e-05
Optimizer eps = 1e-08
Batch size = 32
Dataset path = pgajo/EW-TT-PE_U0_S1_DROP1_mbert
| epoch | train_loss | train_f1 | train_exact | dev_loss | dev_f1 | dev_exact | test_loss | test_f1 | test_exact |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 1.87 | 47.36 | 33.17 | 1.14 | 63.28 | 52.76 | 0 | 0 | 0 |
| 2 | 0.76 | 75.67 | 66.76 | 0.9 | 74.01 | 66.85 | 0 | 0 | 0 |
| 3 | 0.36 | 87.5 | 82.45 | 0.94 | 75.33 | 70.17 | 0 | 0 | 0 |
| 4 | 0.2 | 91.88 | 89.15 | 0.97 | 76.98 | 71.27 | 0 | 0 | 0 |
| 5 | 0.13 | 95.36 | 93.16 | 1.1 | 78.26 | 73.2 | 0 | 0 | 0 |
| 6 | 0.09 | 96.59 | 94.96 | 1 | 79.65 | 74.86 | 0 | 0 | 0 |
| 7 | 0.05 | 97.87 | 97.24 | 1.22 | 79.98 | 75.14 | 0 | 0 | 0 |
| 8 | 0.05 | 98.31 | 97.51 | 1.27 | 79.89 | 74.86 | 0 | 0 | 0 |
| 9 | 0.04 | 98.36 | 97.79 | 1.09 | 80.27 | 76.24 | 0 | 0 | 0 |
| 10 | 0.04 | 98.53 | 97.86 | 1.34 | 78.86 | 75.14 | 0 | 0 | 0 |