learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
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: 8
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.2544	1.0	500	2.0849	0.0	0.0	0.0	0.0	128.0
8.0904	2.0	1000	6.3395	0.0008	0.0	0.0008	0.0008	9.41
4.3742	3.0	1500	2.0739	0.2598	0.1133	0.21	0.2093	26.64
1.0958	4.0	2000	1.9270	0.3981	0.1781	0.2815	0.28	73.71
0.5508	5.0	2500	2.2207	0.3997	0.1729	0.2915	0.2914	66.39
0.2434	6.0	3000	2.5801	0.3927	0.1633	0.2753	0.276	68.39
0.1028	7.0	3500	2.8134	0.3996	0.1708	0.2788	0.278	73.74
0.0469	8.0	4000	2.9507	0.4056	0.1762	0.2875	0.2869	73.32

NastasiaM/mbart_cnn_summarization_model_1K_8ep_5e-5

mbart_cnn_summarization_model_1K_8ep_5e-5