Pre-training results: 
{"eval_loss": 2.3326611518859863, "eval_bleu": {"bleu": 0.5454691474666797, "precisions": [0.7673002426556667, 0.55498965343115, 0.47555838550638013, 0.4399945816996907], "brevity_penalty": 0.9983776325955439, "length_ratio": 0.9983789472112966, "translation_length": 668849, "reference_length": 669935}, "eval_rouge": {"rouge1": 0.7711607888144418, "rouge2": 0.5464636265187319, "rougeL": 0.6786521367857117, "rougeLsum": 0.7626278756724272}, "eval_exact_match": {"exact_match": 0.0}, "eval_runtime": 455.9955, "eval_samples_per_second": 3.241, "eval_steps_per_second": 0.811}
 Post-training results: 
{"eval_loss": 0.689052164554596, "eval_bleu": {"bleu": 0.7794801643070653, "precisions": [0.8826931860836374, 0.7921738670614986, 0.7521498106470706, 0.7302911239298923], "brevity_penalty": 0.9901418189906349, "length_ratio": 0.9901900930687305, "translation_length": 663363, "reference_length": 669935}, "eval_rouge": {"rouge1": 0.8797610930416109, "rouge2": 0.7838158722398209, "rougeL": 0.8517529678496154, "rougeLsum": 0.8731754875691802}, "eval_exact_match": {"exact_match": 0.0}, "eval_runtime": 454.9212, "eval_samples_per_second": 3.249, "eval_steps_per_second": 0.813, "epoch": 2.990033222591362}