learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.7686	1.0	11	1.7656	0.3182	0.1536	0.1012	0.3182
1.7248	2.0	22	1.7412	0.1818	0.1340	0.1061	0.1818
1.6487	3.0	33	1.5732	0.4091	0.2485	0.1818	0.4091
1.6085	4.0	44	1.4907	0.3182	0.1782	0.1237	0.3182
1.5086	5.0	55	1.3331	0.4545	0.3348	0.4213	0.4545
1.4009	6.0	66	1.2478	0.5455	0.4597	0.5752	0.5455
1.271	7.0	77	1.1301	0.5	0.4303	0.5501	0.5
1.0579	8.0	88	0.9797	0.6818	0.6703	0.8644	0.6818
0.9895	9.0	99	0.9068	0.7273	0.7235	0.8953	0.7273
0.899	10.0	110	0.8710	0.7273	0.7235	0.8953	0.7273

angrotanak/xlmr-intent-results

xlmr-intent-results