Model description

More information needed

Intended uses & limitations

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-06
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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6482	1.0	113	1.6372	0.58
0.6486	2.0	226	0.8069	0.73
0.2885	3.0	339	0.4863	0.87
0.1824	4.0	452	0.4533	0.87
0.0895	5.0	565	0.4836	0.87
0.0224	6.0	678	0.4714	0.86
0.0101	7.0	791	0.4379	0.88
0.0038	8.0	904	0.4186	0.88
0.0019	9.0	1017	0.4498	0.89
0.0015	10.0	1130	0.5003	0.88
0.001	11.0	1243	0.4755	0.87
0.0011	12.0	1356	0.4786	0.88
0.0007	13.0	1469	0.4726	0.88
0.001	14.0	1582	0.4967	0.88
0.0005	15.0	1695	0.4908	0.88
0.0007	16.0	1808	0.4905	0.88
0.0007	17.0	1921	0.4863	0.88
0.0006	18.0	2034	0.4896	0.88
0.0007	19.0	2147	0.4898	0.88
0.0005	20.0	2260	0.4901	0.88