learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 50

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro
No log	0	0	1.7971	0	0.9205	0.2271	0.0617
No log	1	170	1.7538	0.0078	1.3432	0.3396	0.1587
No log	2	340	1.7007	0.0156	1.2859	0.2771	0.0723
No log	3	510	1.6589	0.0312	1.5838	0.2	0.0973
No log	4	680	1.1925	0.0625	1.9725	0.6104	0.4502
0.0782	5	850	0.4689	0.125	2.7601	0.8583	0.7262
0.0782	6	1020	0.3014	0.25	4.2276	0.9167	0.7730
0.3149	7	1190	0.2041	0.5	7.0288	0.9458	0.8996
0.1934	8.0	1360	0.1539	1.0	13.3922	0.9688	0.9547
0.1769	9.0	1530	0.1513	1.0	13.1248	0.9604	0.9442
0.121	10.0	1700	0.2680	1.0	13.2100	0.9458	0.9457
0.1015	11.0	1870	0.1788	1.0	13.0501	0.9688	0.9723
0.0436	12.0	2040	0.3333	1.0	13.0799	0.9479	0.9164
0.0362	13.0	2210	0.2078	1.0	14.0551	0.9729	0.9773

contemmcm/cb90a18fdd56e655e587a3fa3f793cbd

cb90a18fdd56e655e587a3fa3f793cbd