Evaluating with bsz 1 tgt_len 256 ext_len 0 mem_len 0 clamp_len -1 using a sliding window.
Evaluating with bsz 1 tgt_len 256 ext_len 0 mem_len 0 clamp_len -1 using a sliding window.
245568 positions evaluated.
Time : 14373.89s, 58.59ms/segment
====================================================================================================
| test loss  4.47 | test ppl    87.555 
====================================================================================================
Evaluating with bsz 1 tgt_len 256 ext_len 0 mem_len 0 clamp_len -1 using a sliding window.
245568 positions evaluated.
Time : 13337.90s, 54.37ms/segment
====================================================================================================
| test loss  4.00 | test ppl    54.666 
====================================================================================================
