learning_rate: 1e-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	F1 Micro	F1 Macro	Exact Match
0.2069	0.9924	131	0.2299	0.5387	0.1155	0.5739
0.2117	1.9848	262	0.2099	0.5601	0.1197	0.6042
0.2049	2.9773	393	0.2000	0.5819	0.1368	0.6155
0.2011	3.9697	524	0.1921	0.5694	0.1356	0.6193
0.1655	4.9621	655	0.1872	0.5821	0.1384	0.6364
0.1629	5.9545	786	0.1838	0.6055	0.1572	0.6458
0.1678	6.9470	917	0.1814	0.5997	0.1624	0.6402
0.1643	7.9394	1048	0.1802	0.6045	0.1689	0.6402

NiGuLa/jhu-clsp_mmBERT-small_ep10_lr1e-06_batchpergpu16_gpu1

jhu-clsp_mmBERT-small_ep10_lr1e-06_batchpergpu16_gpu1