2

This model is a fine-tuned version of google-t5/t5-base on the None dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 32
eval_batch_size: 32
seed: 2
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	Precision	Recall	F1
No log	1.0	40	0.3278	0.4527	0.4063	0.4283
No log	2.0	80	0.2886	0.53	0.4872	0.5077
No log	3.0	120	0.2747	0.5576	0.5345	0.5458
No log	4.0	160	0.2895	0.5717	0.5582	0.5649
No log	5.0	200	0.3065	0.5518	0.5779	0.5645
No log	6.0	240	0.3145	0.5391	0.5976	0.5669
No log	7.0	280	0.3286	0.5508	0.5779	0.564
No log	8.0	320	0.3402	0.5461	0.572	0.5588
No log	9.0	360	0.3532	0.538	0.5582	0.5479
No log	10.0	400	0.3647	0.5747	0.5996	0.5869
No log	11.0	440	0.3736	0.5562	0.5759	0.5659
No log	12.0	480	0.3796	0.5599	0.5897	0.5744
0.1722	13.0	520	0.3881	0.581	0.6016	0.5911
0.1722	14.0	560	0.3938	0.562	0.5897	0.5756
0.1722	15.0	600	0.3891	0.5679	0.5937	0.5805
0.1722	16.0	640	0.3926	0.5647	0.5937	0.5788
0.1722	17.0	680	0.4031	0.5701	0.6016	0.5854
0.1722	18.0	720	0.4037	0.5744	0.5937	0.5839
0.1722	19.0	760	0.4029	0.572	0.5957	0.5836
0.1722	20.0	800	0.4030	0.572	0.5957	0.5836