Model description

More information needed

Intended uses & limitations

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 256
eval_batch_size: 256
seed: 10
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: 50

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr	Combined Score
2.838	1.0	23	2.8658	0.1826	0.1649	0.1737
1.6833	2.0	46	1.6180	0.5936	0.6318	0.6127
1.142	3.0	69	1.1177	0.7114	0.7149	0.7132
0.7648	4.0	92	1.1684	0.7663	0.7880	0.7771
0.5563	5.0	115	1.1614	0.7854	0.8015	0.7935
0.4123	6.0	138	1.0013	0.7854	0.7955	0.7904
0.3439	7.0	161	1.0420	0.7794	0.7872	0.7833
0.2627	8.0	184	0.9325	0.8089	0.8096	0.8092
0.2136	9.0	207	0.7947	0.8145	0.8138	0.8142
0.1822	10.0	230	0.8900	0.8048	0.8048	0.8048
0.1618	11.0	253	0.8068	0.8088	0.8106	0.8097
0.1496	12.0	276	0.8673	0.8151	0.8145	0.8148
0.139	13.0	299	0.9330	0.8061	0.8070	0.8066
0.1235	14.0	322	1.0172	0.7991	0.8033	0.8012