learning_rate: 3e-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
num_epochs: 8
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.7103	1.0	1250	1.5470	0.4223	0.2018	0.2987	0.2989	83.13
3.6967	2.0	2500	2.2298	0.3415	0.1421	0.2373	0.2373	64.4
1.4355	3.0	3750	1.7416	0.391	0.1746	0.2647	0.2648	74.9
1.0985	4.0	5000	1.7084	0.4124	0.1879	0.281	0.281	91.219
0.8919	5.0	6250	1.7902	0.4065	0.1851	0.2823	0.2826	80.347
0.7143	6.0	7500	1.9314	0.4119	0.1858	0.2811	0.2811	87.184
0.5946	7.0	8750	2.0304	0.4134	0.1885	0.2848	0.2846	81.239
0.4987	8.0	10000	2.1202	0.4113	0.1854	0.2826	0.2826	81.645

NastasiaM/mbart_cnn_summarization_model_10K_8ep_3e-5_batch_8_BEST

mbart_cnn_summarization_model_10K_8ep_3e-5_batch_8_BEST