learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.698	1.0	24	0.7425	7.9365	2.8571	7.9365	8.3333	172.619
0.5777	2.0	48	0.6144	13.4921	8.0952	14.1723	14.1723	185.1429
0.4761	3.0	72	0.5909	13.4921	8.0952	14.1723	14.1723	179.2381
0.4855	4.0	96	0.5673	13.4921	8.0952	14.1723	14.1723	178.6667
0.4216	5.0	120	0.5585	13.4921	8.0952	14.1723	14.1723	179.0476
0.4404	6.0	144	0.5504	13.4921	8.0952	14.1723	14.1723	174.0952
0.3968	7.0	168	0.5439	13.4921	8.0952	14.1723	14.1723	174.0952
0.393	8.0	192	0.5376	13.4921	8.0952	14.1723	14.1723	174.0952
0.3535	9.0	216	0.5343	13.4921	8.0952	14.1723	14.1723	174.0952
0.4052	10.0	240	0.5344	13.4921	8.0952	14.1723	14.1723	174.0952

sadelja/rut5_base_sum_gazeta-finetuned-2

rut5_base_sum_gazeta-finetuned-2