Model description:
Model: pgajo/mdeberta-xlwa-en-it
Dataset: TASTEset
Unshuffled ratio: ['1']
Shuffled ratio: ['0']
Best exact match epoch: 2
Best exact match: 99.72
Best epoch: 2
Drop duplicates: ['1']
Max epochs = 10
Optimizer lr = 3e-05
Optimizer eps = 1e-08
Batch size = 8
Dataset path = pgajo/EW-TT-PE_U1_S0_DROP1_mdeberta
Results
epoch | train_loss | train_f1 | train_exact | dev_loss | dev_f1 | dev_exact | test_loss | test_f1 | test_exact |
---|---|---|---|---|---|---|---|---|---|
1 | 0.21 | 95.73 | 90.81 | 0.01 | 99.81 | 99.45 | 0 | 0 | 0 |
2 | 0.03 | 99.62 | 99.1 | 0.01 | 99.95 | 99.72 | 0 | 0 | 0 |
3 | 0.01 | 99.87 | 99.65 | 0 | 99.86 | 99.72 | 0 | 0 | 0 |
4 | 0.02 | 99.61 | 99.1 | 0.01 | 99.95 | 99.72 | 0 | 0 | 0 |
5 | 0.01 | 99.91 | 99.86 | 0.01 | 99.94 | 99.72 | 0 | 0 | 0 |
- Downloads last month
- 0