learning_rate: 5.6e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
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: 8

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
3.4784	1.0	625	2.5594	6.25	0.7067	6.2865	6.2728
3.2115	2.0	1250	2.4967	6.7843	0.5289	6.7959	6.7294
3.0575	3.0	1875	2.4596	6.7504	0.6433	6.8155	6.7
2.956	4.0	2500	2.4379	7.2913	0.4	7.3238	7.2337
2.883	5.0	3125	2.4064	6.8787	0.7143	6.9276	6.7916
2.8382	6.0	3750	2.3953	6.5828	0.8	6.6261	6.5019
2.7979	7.0	4375	2.3891	6.3757	0.48	6.4214	6.2943
2.776	8.0	5000	2.3921	7.0151	0.6	7.0333	6.9395

raevas2010/mt5-small-finetuned-amazon-en-es

mt5-small-finetuned-amazon-en-es