learning_rate: 1.039013544160204e-05
train_batch_size: 8
eval_batch_size: 8
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: 20

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5431	1.0	202	0.4496	0.8070	0.7934
0.3761	2.0	404	0.5158	0.8	0.7883
0.2367	3.0	606	0.8120	0.7895	0.7873
0.1567	4.0	808	1.1364	0.7895	0.7811
0.0694	5.0	1010	1.3989	0.7860	0.7746
0.0502	6.0	1212	1.4061	0.8035	0.7936
0.0451	7.0	1414	1.3748	0.7895	0.7857
0.042	8.0	1616	1.2634	0.8	0.7990
0.0372	9.0	1818	1.4843	0.8	0.7871
0.026	10.0	2020	1.4312	0.8070	0.8079
0.0288	11.0	2222	1.5144	0.8070	0.8024
0.0175	12.0	2424	1.5568	0.8105	0.8039
0.0153	13.0	2626	1.5688	0.8105	0.8079
0.0233	14.0	2828	1.5969	0.7965	0.7912
0.0154	15.0	3030	1.6177	0.7965	0.7921
0.015	16.0	3232	1.5620	0.8035	0.7992
0.0141	17.0	3434	1.6152	0.8070	0.8032
0.0221	18.0	3636	1.6432	0.8035	0.7966
0.014	19.0	3838	1.6156	0.8035	0.7984
0.0135	20.0	4040	1.6206	0.8070	0.8024

zekaemo/Standard

Standard