Edit model card

Model description:

Model: pgajo/mbert-xlwa-en-it

Dataset: TASTEset

Unshuffled ratio: ['0']

Shuffled ratio: ['1']

Best exact match epoch: 10

Best exact match: 86.54

Best epoch: 10

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_Tingredient_P0.25_DROP1_mbert

Results

epoch train_loss train_f1 train_exact dev_loss dev_f1 dev_exact test_loss test_f1 test_exact
1 1.18 68.16 50.69 0.7 81.28 69.51 0 0 0
2 0.39 88.83 80.23 0.62 85.69 78.57 0 0 0
3 0.16 95.33 91.53 0.7 86.71 81.04 0 0 0
4 0.09 97.02 94.56 0.79 87.62 82.42 0 0 0
5 0.07 97.82 96.07 0.71 86.34 81.32 0 0 0
6 0.06 97.58 96.07 0.63 88.88 83.79 0 0 0
7 0.04 98.77 98 0.59 89.36 84.34 0 0 0
8 0.04 98.89 98.14 0.7 88.27 83.24 0 0 0
9 0.02 99.53 98.9 0.72 89.48 85.44 0 0 0
10 0.02 99.31 98.55 0.73 90.3 86.54 0 0 0
Downloads last month
2
Safetensors
Model size
177M params
Tensor type
F32