learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Bleu
2.1428	1.0	793	1.6842	31.5776	15.7424	27.8274	12.4053
1.7467	2.0	1586	1.5864	36.525	18.5667	31.9128	16.0299
1.6433	3.0	2379	1.5418	37.975	19.416	32.9918	16.8339
1.5858	4.0	3172	1.5158	39.0333	20.2533	34.1644	18.0909
1.5455	5.0	3965	1.5008	39.8088	20.6915	34.6625	18.6534
1.5084	6.0	4758	1.4849	40.5524	21.3479	35.1159	19.0572
1.4859	7.0	5551	1.4772	40.2129	21.1254	35.0268	19.0809
1.4630	8.0	6344	1.4819	40.5756	21.468	35.3439	19.3096
1.4475	9.0	7137	1.4736	40.8466	21.4684	35.4963	19.359
1.4434	10.0	7930	1.4733	41.0259	21.517	35.32	19.1166

tasyazahrani/t5-small-keyphrase-id

t5-small-keyphrase-id