learning_rate: 0.00015
train_batch_size: 16
eval_batch_size: 16
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
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
No log	1.0	92	0.9713	0.0339	0.0528	0.0413
No log	2.0	184	0.6932	0.0606	0.1567	0.0875
No log	3.0	276	0.5689	0.1143	0.184	0.141
No log	4.0	368	0.5124	0.1451	0.2658	0.1877
No log	5.0	460	0.4812	0.1991	0.3015	0.2398
1.289	6.0	552	0.4646	0.2299	0.322	0.2683
1.289	7.0	644	0.4442	0.2649	0.3629	0.3063
1.289	8.0	736	0.4356	0.2649	0.3629	0.3063
1.289	9.0	828	0.4324	0.2855	0.3697	0.3222
1.289	10.0	920	0.4328	0.2932	0.3731	0.3283
0.5244	11.0	1012	0.4202	0.3546	0.3697	0.362
0.5244	12.0	1104	0.4187	0.2877	0.3935	0.3324
0.5244	13.0	1196	0.4072	0.3338	0.3901	0.3598
0.5244	14.0	1288	0.4126	0.3333	0.4072	0.3666
0.5244	15.0	1380	0.4076	0.3614	0.402	0.3806
0.5244	16.0	1472	0.4035	0.374	0.4123	0.3922
0.3906	17.0	1564	0.4032	0.3559	0.4208	0.3856
0.3906	18.0	1656	0.4006	0.3594	0.4157	0.3855
0.3906	19.0	1748	0.3987	0.3832	0.4191	0.4003
0.3906	20.0	1840	0.3982	0.3771	0.4208	0.3977

arus05/t5-small-xasqp-rest16

t5-small-xasqp-rest16