optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Train Loss	Validation Loss	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
5.3441	2.0990	3.1931	0.4400	3.2577	3.2151	12.2277	0
2.2977	1.5680	7.0014	1.0891	7.0651	6.9307	11.3267	1
1.7363	1.2611	7.0674	1.0891	7.1287	7.0745	11.5545	2
1.4302	1.0860	8.3805	2.4257	8.4158	8.4158	11.8069	3
1.2082	0.9516	8.3805	2.4257	8.4158	8.4158	11.8861	4
1.0516	0.8511	8.3805	2.4257	8.4158	8.4158	12.0149	5
0.9244	0.7961	8.9109	2.4257	8.9109	8.9109	11.9950	6
0.8280	0.7524	8.9109	2.3762	8.8755	8.9109	11.9802	7
0.7521	0.7230	8.9109	2.3762	8.8755	8.9109	11.9406	8
0.6888	0.6988	8.9109	2.3762	8.8755	8.9109	11.9307	9
0.6330	0.6676	8.6634	1.7822	8.6810	8.6103	11.9109	10
0.5835	0.6465	7.7793	1.2871	7.9208	7.9208	11.9010	11
0.5299	0.6289	8.4158	1.2871	8.4158	8.4335	11.9356	12
0.4876	0.6310	8.4158	1.2871	8.4158	8.4335	11.8911	13
0.4402	0.6207	8.4158	1.2871	8.4158	8.4335	11.9109	14
0.4068	0.6237	8.4158	1.2871	8.4158	8.4335	11.9158	15
0.3686	0.6314	8.4158	1.2871	8.4158	8.4335	11.9356	16
0.3359	0.6296	8.9109	1.2871	8.9109	8.9463	11.8960	17
0.3090	0.6569	8.9109	1.3861	8.9463	8.9463	11.8960	18
0.2774	0.6649	8.9109	1.3861	8.9463	8.9463	11.8762	19
0.2567	0.6818	8.9109	1.3861	8.9463	8.9463	11.9109	20
0.2320	0.7029	8.9109	1.3861	8.9463	8.9463	11.9059	21
0.2133	0.6999	8.9109	1.3861	8.9463	8.9463	11.9010	22