Model description

More information needed

Intended uses & limitations

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 3e-05
train_batch_size: 32
eval_batch_size: 32
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
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu	Chrf++	F1	Gen Len
1.0060	1.0	7150	0.9143	27.8237	14.9796	26.3631	26.4309	0.02	16.0158	42.7321	18.9874
1.0158	2.0	14300	0.9048	27.8402	15.0263	26.3861	26.4522	0.0201	16.0279	42.7456	18.9905
1.0100	3.0	21450	0.8995	27.9734	15.1455	26.518	26.5832	0.0203	16.1161	42.8528	18.9883
1.0152	4.0	28600	0.8925	27.972	15.1592	26.5201	26.5823	0.0203	16.1043	42.8465	18.9881
1.0202	5.0	35750	0.8879	28.0302	15.2138	26.5808	26.6473	0.0204	16.1554	42.8899	18.992
1.0151	6.0	42900	0.8844	28.116	15.2968	26.6651	26.7322	0.0205	16.2043	42.9246	18.9894
1.0142	7.0	50050	0.8808	28.123	15.2984	26.6782	26.743	0.0205	16.1921	42.9205	18.9933
1.0240	8.0	57200	0.8778	28.2186	15.369	26.7684	26.8334	0.0206	16.2417	42.9686	18.9884
1.0212	9.0	64350	0.8760	28.185	15.3632	26.7337	26.8008	0.0206	16.2302	42.9756	18.9909
1.0151	10.0	71500	0.8753	28.2027	15.3717	26.7491	26.8143	0.0206	16.2368	42.9772	18.9905