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	11.0330	0	1.6983	0.2292	0.0681
No log	1	170	15.5158	0.0078	1.8404	0.3646	0.1911
No log	2	340	6.1470	0.0156	3.4363	0.4167	0.3208
No log	3	510	6.6239	0.0312	7.3504	0.4396	0.3812
No log	4	680	1.6063	0.0625	6.8184	0.8333	0.8552
0.2574	5	850	0.7934	0.125	8.7943	0.9437	0.9056
0.2574	6	1020	0.9699	0.25	12.0923	0.9354	0.8988
1.1973	7	1190	1.4227	0.5	18.9648	0.925	0.8874
0.9442	8.0	1360	1.5822	1.0	35.1714	0.9104	0.8706
0.9288	9.0	1530	2.6350	1.0	34.6458	0.9167	0.9184

contemmcm/e818e7c1f23c794e26fc56353b00c69e

e818e7c1f23c794e26fc56353b00c69e