pgajo/mdeberta-xlwa-en-it_EW-TT-PE_U0_S1_Tingredient_P0.5_DROP1_mdeberta_E5_DEV96.0

Model description:

Model: pgajo/mdeberta-xlwa-en-it

Dataset: TASTEset

Unshuffled ratio: ['0']

Shuffled ratio: ['1']

Best exact match epoch: 5

Best exact match: 96.43

Best epoch: 5

Drop duplicates: ['1']

Max epochs = 10

Optimizer lr = 3e-05

Optimizer eps = 1e-08

Batch size = 8

Dataset path = pgajo/EW-TT-PE_U0_S1_Tingredient_P0.5_DROP1_mdeberta

Results

epoch	train_loss	train_f1	train_exact	dev_loss	dev_f1	dev_exact	test_loss	test_f1	test_exact
1	0.5	86.89	78.93	0.17	96.75	94.51	0	0	0
2	0.12	97.05	94.83	0.17	96.72	94.51	0	0	0
3	0.06	98.3	97.04	0.18	97.41	94.78	0	0	0
4	0.04	99.08	98.48	0.21	97.37	95.88	0	0	0
5	0.02	99.43	99.04	0.16	98.02	96.43	0	0	0
6	0.04	99.12	98.62	0.17	96.56	93.68	0	0	0
7	0.02	99.22	98.9	0.19	97.35	96.15	0	0	0
8	0.02	99.42	98.9	0.22	97.6	95.05	0	0	0