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: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Bleu
2.2572	1.0	793	1.7467	28.3356	13.6831	25.3984	9.1195
1.8100	2.0	1586	1.6231	35.1004	17.8709	30.9105	15.0132
1.6857	3.0	2379	1.5609	36.8045	18.7151	32.167	16.0463
1.6135	4.0	3172	1.5192	38.0403	19.2669	33.1081	16.9419
1.5584	5.0	3965	1.5060	39.9211	20.6822	34.7901	18.7794
1.5097	6.0	4758	1.4814	40.6802	21.2563	35.2195	19.3699
1.4754	7.0	5551	1.4693	40.3298	21.5759	34.9535	19.7572
1.4389	8.0	6344	1.4640	40.9452	21.6119	35.1942	19.7244
1.4100	9.0	7137	1.4571	40.6946	21.3943	35.0856	19.8844
1.3894	10.0	7930	1.4501	40.8169	21.1663	35.5354	19.7837
1.3680	11.0	8723	1.4402	41.3369	21.8096	35.792	20.2212
1.3493	12.0	9516	1.4365	41.5085	21.9571	36.2856	20.3886
1.3328	13.0	10309	1.4447	41.051	21.3352	35.6354	19.6375
1.3184	14.0	11102	1.4445	41.9338	21.7355	35.5373	20.2003
1.3084	15.0	11895	1.4366	42.1092	22.4228	36.555	20.5533

tasyazahrani/uas-nlp

uas-nlp