learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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
lr_scheduler_warmup_steps: 500
num_epochs: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.5435	0.1166	100	0.4252	0.8876	0.8584	0.8010	0.9245
0.1382	0.2331	200	0.2558	0.9086	0.8891	0.8041	0.9940
0.0937	0.3497	300	0.1737	0.951	0.9372	0.8882	0.9919
0.0497	0.4662	400	0.1764	0.9546	0.9416	0.8945	0.9940
0.0712	0.5828	500	0.0430	0.9878	0.9835	0.9785	0.9886
0.0384	0.6993	600	0.0774	0.9822	0.9762	0.9606	0.9924
0.0433	0.8159	700	0.3870	0.9208	0.9028	0.8242	0.9978
0.0191	0.9324	800	0.0224	0.995	0.9932	0.9989	0.9875
0.0194	1.0490	900	0.0444	0.9914	0.9884	0.9833	0.9935
0.0142	1.1655	1000	0.1037	0.9818	0.9758	0.9577	0.9946
0.0216	1.2821	1100	0.0230	0.9948	0.9929	0.9935	0.9924

bprhee01/bert-text-classification-final

bert-text-classification-final