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	1.9194	0	1.2057	0.1292	0.0870
No log	1	170	1.5633	0.0078	1.4298	0.4313	0.2455
No log	2	340	1.2538	0.0156	1.2709	0.5813	0.4299
No log	3	510	0.5704	0.0312	1.6920	0.8125	0.6968
No log	4	680	0.2417	0.0625	1.9839	0.9354	0.9234
0.0372	5	850	0.2498	0.125	2.9048	0.9167	0.9020
0.0372	6	1020	0.1981	0.25	4.3300	0.95	0.9237
0.2046	7	1190	0.2539	0.5	7.2602	0.9062	0.9154
0.1463	8.0	1360	0.1276	1.0	13.4284	0.9688	0.9736
0.0864	9.0	1530	0.1417	1.0	13.1737	0.975	0.9616
0.0671	10.0	1700	0.2472	1.0	13.1137	0.95	0.9559
0.0201	11.0	1870	0.2529	1.0	13.2263	0.9563	0.9429
0.0262	12.0	2040	0.3158	1.0	13.0821	0.9479	0.9352

contemmcm/741f73439c2dfa8d05bace436d284154

741f73439c2dfa8d05bace436d284154