1

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: 1
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	0.3156	0.4037	0.43	0.4164
No log	2.0	80	0.2707	0.4722	0.503	0.4871
No log	3.0	120	0.2857	0.5236	0.503	0.5131
No log	4.0	160	0.2829	0.5286	0.5286	0.5286
No log	5.0	200	0.3135	0.5694	0.5661	0.5678
No log	6.0	240	0.3199	0.5392	0.5562	0.5476
No log	7.0	280	0.3305	0.5045	0.5562	0.5291
No log	8.0	320	0.3357	0.5468	0.5641	0.5553
No log	9.0	360	0.3558	0.5386	0.5641	0.5511
No log	10.0	400	0.3630	0.5564	0.5838	0.5698
No log	11.0	440	0.3724	0.565	0.574	0.5695
No log	12.0	480	0.3743	0.5833	0.5799	0.5816
0.1681	13.0	520	0.4012	0.5774	0.5957	0.5864
0.1681	14.0	560	0.4118	0.5793	0.5976	0.5883
0.1681	15.0	600	0.4167	0.5792	0.5917	0.5854
0.1681	16.0	640	0.4174	0.5742	0.5878	0.5809
0.1681	17.0	680	0.4238	0.5957	0.6075	0.6016
0.1681	18.0	720	0.4293	0.5797	0.5957	0.5875
0.1681	19.0	760	0.4306	0.5733	0.5937	0.5833
0.1681	20.0	800	0.4267	0.5747	0.5917	0.5831