learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
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
lr_scheduler_warmup_steps: 10
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel
3.8258	1.0	6	3.1714	0.0906	0.0078	0.0854
3.5137	2.0	12	2.8459	0.1060	0.0065	0.0995
3.1361	3.0	18	2.6159	0.1258	0.0185	0.1197
2.6906	4.0	24	2.4760	0.1417	0.0208	0.1353
2.9295	5.0	30	2.3788	0.1412	0.0196	0.1346
2.6139	6.0	36	2.3054	0.1429	0.0199	0.1360
2.3959	7.0	42	2.2521	0.1522	0.0242	0.1461
2.125	8.0	48	2.2181	0.1510	0.0258	0.1454
2.408	9.0	54	2.2008	0.1480	0.0255	0.1412
2.2758	10.0	60	2.1947	0.1469	0.0254	0.1402

DOHAIDRISSIMOUNADI/FLANT5-MULTILANGUE7

FLANT5-MULTILANGUE7