diff --git "a/test-en-mk.comet" "b/test-en-mk.comet" new file mode 100644--- /dev/null +++ "b/test-en-mk.comet" @@ -0,0 +1,1013 @@ +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 0 score: 0.8069 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1 score: 0.9202 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 2 score: 0.9047 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 3 score: 0.8266 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 4 score: 0.8560 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 5 score: 0.7214 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 6 score: 0.6287 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 7 score: 0.7486 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 8 score: 0.9100 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 9 score: 0.8481 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 10 score: 0.9403 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 11 score: 0.8531 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 12 score: 0.8942 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 13 score: 0.9067 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 14 score: 0.8471 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 15 score: 0.7816 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 16 score: 0.8757 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 17 score: 0.9488 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 18 score: 0.9075 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 19 score: 0.8893 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 20 score: 0.9161 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 21 score: 0.9080 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 22 score: 0.8118 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 23 score: 0.9067 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 24 score: 0.9203 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 25 score: 0.9592 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 26 score: 0.8418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 27 score: 0.8262 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 28 score: 0.8577 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 29 score: 0.8346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 30 score: 0.6389 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 31 score: 0.7537 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 32 score: 0.6639 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 33 score: 0.9401 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 34 score: 0.9622 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 35 score: 0.9271 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 36 score: 0.8005 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 37 score: 0.7838 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 38 score: 0.8612 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 39 score: 0.8894 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 40 score: 0.6958 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 41 score: 0.9370 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 42 score: 0.8028 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 43 score: 0.9103 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 44 score: 0.7029 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 45 score: 0.9029 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 46 score: 0.9324 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 47 score: 0.8874 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 48 score: 0.9256 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 49 score: 0.7553 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 50 score: 0.9356 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 51 score: 0.8988 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 52 score: 0.9360 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 53 score: 0.9265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 54 score: 0.9239 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 55 score: 0.9142 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 56 score: 0.9011 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 57 score: 0.8707 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 58 score: 0.8714 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 59 score: 0.9500 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 60 score: 0.9220 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 61 score: 0.9119 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 62 score: 0.8363 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 63 score: 0.9091 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 64 score: 0.8702 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 65 score: 0.7221 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 66 score: 0.6962 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 67 score: 0.6742 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 68 score: 0.9540 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 69 score: 0.8975 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 70 score: 0.8758 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 71 score: 0.8318 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 72 score: 0.7722 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 73 score: 0.8630 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 74 score: 0.8016 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 75 score: 0.8754 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 76 score: 0.7982 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 77 score: 0.6948 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 78 score: 0.8339 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 79 score: 0.9312 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 80 score: 0.9047 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 81 score: 0.9623 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 82 score: 0.8611 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 83 score: 0.8410 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 84 score: 0.7329 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 85 score: 0.8957 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 86 score: 0.7778 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 87 score: 0.7619 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 88 score: 0.9345 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 89 score: 0.8829 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 90 score: 0.8505 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 91 score: 0.8650 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 92 score: 0.8220 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 93 score: 0.8596 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 94 score: 0.9183 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 95 score: 0.9334 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 96 score: 0.7414 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 97 score: 0.8047 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 98 score: 0.9432 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 99 score: 0.6938 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 100 score: 0.9408 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 101 score: 0.9224 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 102 score: 0.8671 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 103 score: 0.9795 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 104 score: 0.9017 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 105 score: 0.8434 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 106 score: 0.9318 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 107 score: 0.9045 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 108 score: 0.8291 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 109 score: 0.8574 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 110 score: 0.8575 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 111 score: 0.9520 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 112 score: 0.9369 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 113 score: 0.9454 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 114 score: 0.8240 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 115 score: 0.7817 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 116 score: 0.9146 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 117 score: 0.9138 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 118 score: 0.9304 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 119 score: 0.8930 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 120 score: 0.8975 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 121 score: 0.9293 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 122 score: 0.9636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 123 score: 0.9583 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 124 score: 0.8729 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 125 score: 0.9237 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 126 score: 0.8914 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 127 score: 0.8991 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 128 score: 0.8678 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 129 score: 0.9321 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 130 score: 0.9049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 131 score: 0.8699 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 132 score: 0.9043 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 133 score: 0.9447 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 134 score: 0.8153 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 135 score: 0.7686 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 136 score: 0.9291 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 137 score: 0.8911 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 138 score: 0.8364 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 139 score: 0.8950 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 140 score: 0.8518 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 141 score: 0.8398 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 142 score: 0.9436 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 143 score: 0.8314 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 144 score: 0.8704 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 145 score: 0.9268 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 146 score: 0.9106 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 147 score: 0.9163 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 148 score: 0.9446 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 149 score: 0.9049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 150 score: 0.9015 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 151 score: 0.8429 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 152 score: 0.8878 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 153 score: 0.8070 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 154 score: 0.7857 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 155 score: 0.9126 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 156 score: 0.8899 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 157 score: 0.7847 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 158 score: 0.9115 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 159 score: 0.8929 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 160 score: 0.8786 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 161 score: 0.8516 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 162 score: 0.7176 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 163 score: 0.5823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 164 score: 0.9008 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 165 score: 0.6695 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 166 score: 0.9224 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 167 score: 0.9015 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 168 score: 0.8541 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 169 score: 0.8950 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 170 score: 0.8519 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 171 score: 0.9020 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 172 score: 0.8964 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 173 score: 0.7918 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 174 score: 0.8847 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 175 score: 0.9219 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 176 score: 0.6929 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 177 score: 0.8593 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 178 score: 0.7387 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 179 score: 0.8696 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 180 score: 0.8935 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 181 score: 0.9084 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 182 score: 0.9062 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 183 score: 0.9189 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 184 score: 0.8489 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 185 score: 0.9122 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 186 score: 0.9620 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 187 score: 0.9104 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 188 score: 0.8775 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 189 score: 0.8535 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 190 score: 0.7902 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 191 score: 0.9360 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 192 score: 0.8040 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 193 score: 0.8781 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 194 score: 0.9027 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 195 score: 0.8928 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 196 score: 0.9082 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 197 score: 0.7778 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 198 score: 0.8967 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 199 score: 0.8782 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 200 score: 0.7848 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 201 score: 0.6869 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 202 score: 0.7267 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 203 score: 0.6467 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 204 score: 0.8867 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 205 score: 0.9061 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 206 score: 0.9195 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 207 score: 0.9070 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 208 score: 0.9093 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 209 score: 0.8537 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 210 score: 0.9515 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 211 score: 0.9388 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 212 score: 0.9040 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 213 score: 0.8716 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 214 score: 0.8922 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 215 score: 0.8493 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 216 score: 0.8589 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 217 score: 0.7999 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 218 score: 0.8846 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 219 score: 0.9224 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 220 score: 0.9514 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 221 score: 0.6133 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 222 score: 0.9065 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 223 score: 0.8578 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 224 score: 0.8949 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 225 score: 0.5899 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 226 score: 0.8738 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 227 score: 0.7931 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 228 score: 0.8814 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 229 score: 0.8762 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 230 score: 0.9475 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 231 score: 0.8705 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 232 score: 0.8159 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 233 score: 0.9011 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 234 score: 0.7588 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 235 score: 0.8405 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 236 score: 0.8573 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 237 score: 0.7983 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 238 score: 0.9381 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 239 score: 0.8806 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 240 score: 0.7476 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 241 score: 0.7164 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 242 score: 0.8663 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 243 score: 0.6775 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 244 score: 0.7939 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 245 score: 0.5979 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 246 score: 0.6780 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 247 score: 0.7374 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 248 score: 0.6528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 249 score: 0.9401 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 250 score: 0.9213 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 251 score: 0.9460 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 252 score: 0.9418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 253 score: 0.9621 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 254 score: 0.9713 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 255 score: 0.9419 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 256 score: 0.7481 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 257 score: 0.8158 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 258 score: 0.9034 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 259 score: 0.8816 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 260 score: 0.8384 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 261 score: 0.7602 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 262 score: 0.5378 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 263 score: 0.5695 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 264 score: 0.9284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 265 score: 0.8846 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 266 score: 0.8393 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 267 score: 0.7949 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 268 score: 0.8936 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 269 score: 0.9403 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 270 score: 0.8856 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 271 score: 0.8122 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 272 score: 0.8988 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 273 score: 0.8792 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 274 score: 0.8142 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 275 score: 0.7830 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 276 score: 0.8513 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 277 score: 0.9428 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 278 score: 0.8253 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 279 score: 0.8667 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 280 score: 0.8616 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 281 score: 0.9301 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 282 score: 0.9440 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 283 score: 0.8920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 284 score: 0.9390 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 285 score: 0.9265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 286 score: 0.8275 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 287 score: 0.8434 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 288 score: 0.9274 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 289 score: 0.9059 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 290 score: 0.6737 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 291 score: 0.8862 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 292 score: 0.9064 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 293 score: 0.8714 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 294 score: 0.8732 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 295 score: 0.8699 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 296 score: 0.8914 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 297 score: 0.6949 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 298 score: 0.7284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 299 score: 0.9262 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 300 score: 0.9368 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 301 score: 0.8457 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 302 score: 0.8185 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 303 score: 0.9049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 304 score: 0.9092 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 305 score: 0.9432 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 306 score: 0.9212 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 307 score: 0.9100 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 308 score: 0.9439 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 309 score: 0.8796 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 310 score: 0.9467 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 311 score: 0.9614 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 312 score: 0.9430 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 313 score: 0.6697 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 314 score: 0.9419 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 315 score: 0.9538 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 316 score: 0.9504 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 317 score: 0.7456 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 318 score: 0.7226 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 319 score: 0.6852 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 320 score: 0.7944 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 321 score: 0.6839 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 322 score: 0.9336 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 323 score: 0.9170 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 324 score: 0.9375 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 325 score: 0.8834 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 326 score: 0.7295 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 327 score: 0.9155 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 328 score: 0.2575 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 329 score: 0.8956 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 330 score: 0.8801 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 331 score: 0.9272 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 332 score: 0.6766 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 333 score: 0.8654 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 334 score: 0.9505 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 335 score: 0.9051 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 336 score: 0.8638 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 337 score: 0.5823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 338 score: 0.8250 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 339 score: 0.9305 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 340 score: 0.7744 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 341 score: 0.6026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 342 score: 0.7457 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 343 score: 0.8350 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 344 score: 0.8918 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 345 score: 0.8562 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 346 score: 0.9379 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 347 score: 0.9011 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 348 score: 0.9175 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 349 score: 0.7105 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 350 score: 0.8951 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 351 score: 0.8724 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 352 score: 0.9001 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 353 score: 0.9118 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 354 score: 0.8537 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 355 score: 0.7939 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 356 score: 0.8999 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 357 score: 0.6785 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 358 score: 0.7879 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 359 score: 0.7829 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 360 score: 0.8148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 361 score: 0.7938 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 362 score: 0.8450 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 363 score: 0.7145 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 364 score: 0.8424 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 365 score: 0.8363 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 366 score: 0.6789 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 367 score: 0.8793 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 368 score: 0.6950 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 369 score: 0.1124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 370 score: 0.6750 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 371 score: 0.7637 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 372 score: 0.8723 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 373 score: 0.8236 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 374 score: 0.9378 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 375 score: 0.9259 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 376 score: 0.9256 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 377 score: 0.9211 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 378 score: 0.6581 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 379 score: 0.8744 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 380 score: 0.8867 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 381 score: 0.8966 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 382 score: 0.7004 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 383 score: 0.7538 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 384 score: 0.7987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 385 score: 0.7725 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 386 score: 0.7707 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 387 score: 0.8831 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 388 score: 0.7092 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 389 score: 0.8129 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 390 score: 0.9080 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 391 score: 0.8679 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 392 score: 0.9127 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 393 score: 0.8534 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 394 score: 0.9238 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 395 score: 0.9355 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 396 score: 0.8250 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 397 score: 0.9264 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 398 score: 0.8587 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 399 score: 0.8940 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 400 score: 0.9612 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 401 score: 0.8417 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 402 score: 0.8784 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 403 score: 0.8215 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 404 score: 0.7596 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 405 score: 0.8841 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 406 score: 0.8957 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 407 score: 0.8776 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 408 score: 0.9287 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 409 score: 0.8438 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 410 score: 0.9409 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 411 score: 0.6965 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 412 score: 0.8783 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 413 score: 0.9452 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 414 score: 0.7357 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 415 score: 0.9051 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 416 score: 0.7746 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 417 score: 0.7908 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 418 score: 0.9482 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 419 score: 0.8987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 420 score: 0.9392 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 421 score: 0.9389 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 422 score: 0.8389 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 423 score: 0.8178 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 424 score: 0.8642 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 425 score: 0.9211 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 426 score: 0.8942 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 427 score: 0.8966 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 428 score: 0.8878 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 429 score: 0.9277 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 430 score: 0.8703 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 431 score: 0.8011 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 432 score: 0.6265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 433 score: 0.7710 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 434 score: 0.8250 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 435 score: 0.7417 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 436 score: 0.8947 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 437 score: 0.9205 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 438 score: 0.9530 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 439 score: 0.9268 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 440 score: 0.8472 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 441 score: 0.8268 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 442 score: 0.8809 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 443 score: 0.8037 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 444 score: 0.9230 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 445 score: 0.8469 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 446 score: 0.9311 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 447 score: 0.9266 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 448 score: 0.9498 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 449 score: 0.8694 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 450 score: 0.9188 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 451 score: 0.9425 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 452 score: 0.9436 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 453 score: 0.8999 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 454 score: 0.8831 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 455 score: 0.9011 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 456 score: 0.8758 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 457 score: 0.9336 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 458 score: 0.8653 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 459 score: 0.8353 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 460 score: 0.7798 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 461 score: 0.8180 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 462 score: 0.7309 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 463 score: 0.9160 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 464 score: 0.8908 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 465 score: 0.9033 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 466 score: 0.8745 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 467 score: 0.7052 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 468 score: 0.7532 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 469 score: 0.5810 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 470 score: 0.7737 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 471 score: 0.8467 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 472 score: 0.8664 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 473 score: 0.8469 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 474 score: 0.6377 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 475 score: 0.9290 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 476 score: 0.8887 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 477 score: 0.8401 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 478 score: 0.8590 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 479 score: 0.8854 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 480 score: 0.7768 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 481 score: 0.8909 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 482 score: 0.8704 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 483 score: 0.9273 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 484 score: 0.8902 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 485 score: 0.9150 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 486 score: 0.9013 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 487 score: 0.8811 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 488 score: 0.8783 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 489 score: 0.9431 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 490 score: 0.8735 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 491 score: 0.9013 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 492 score: 0.9181 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 493 score: 0.9491 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 494 score: 0.8516 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 495 score: 0.8217 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 496 score: 0.8672 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 497 score: 0.8748 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 498 score: 0.9039 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 499 score: 0.9003 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 500 score: 0.9466 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 501 score: 0.9422 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 502 score: 0.9173 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 503 score: 0.8620 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 504 score: 0.7673 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 505 score: 0.8178 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 506 score: 0.8667 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 507 score: 0.7400 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 508 score: 0.7265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 509 score: 0.8249 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 510 score: 0.7682 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 511 score: 0.6544 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 512 score: 0.8505 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 513 score: 0.8904 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 514 score: 0.9501 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 515 score: 0.8023 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 516 score: 0.4793 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 517 score: 0.7816 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 518 score: 0.9249 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 519 score: 0.9469 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 520 score: 0.8920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 521 score: 0.9399 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 522 score: 0.8457 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 523 score: 0.8467 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 524 score: 0.8711 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 525 score: 0.9225 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 526 score: 0.8636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 527 score: 0.7795 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 528 score: 0.7367 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 529 score: 0.8620 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 530 score: 0.7400 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 531 score: 0.8401 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 532 score: 0.8828 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 533 score: 0.8433 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 534 score: 0.1259 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 535 score: 0.7001 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 536 score: 0.8343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 537 score: 0.8985 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 538 score: 0.9209 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 539 score: 0.8766 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 540 score: 0.8823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 541 score: 0.9405 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 542 score: 0.8873 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 543 score: 0.8725 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 544 score: 0.8023 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 545 score: 0.9466 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 546 score: 0.7566 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 547 score: 0.8260 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 548 score: 0.8209 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 549 score: 0.9271 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 550 score: 0.7885 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 551 score: 0.9330 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 552 score: 0.7900 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 553 score: 0.8026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 554 score: 0.7859 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 555 score: 0.8025 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 556 score: 0.8452 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 557 score: 0.8320 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 558 score: 0.6841 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 559 score: 0.7137 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 560 score: 0.8516 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 561 score: 0.8853 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 562 score: 0.8507 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 563 score: 0.6639 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 564 score: 0.7391 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 565 score: 0.8803 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 566 score: 0.8617 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 567 score: 0.9095 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 568 score: 0.7364 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 569 score: 0.6429 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 570 score: 0.9427 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 571 score: 0.9053 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 572 score: 0.7104 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 573 score: 0.8723 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 574 score: 0.8889 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 575 score: 0.8429 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 576 score: 0.5985 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 577 score: 0.8542 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 578 score: 0.9030 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 579 score: 0.8783 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 580 score: 0.9167 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 581 score: 0.9181 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 582 score: 0.8942 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 583 score: 0.8181 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 584 score: 0.7060 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 585 score: 0.8828 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 586 score: 0.8568 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 587 score: 0.8025 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 588 score: 0.9221 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 589 score: 0.9122 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 590 score: 0.8579 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 591 score: 0.8459 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 592 score: 0.8392 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 593 score: 0.9343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 594 score: 0.9456 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 595 score: 0.9367 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 596 score: 0.8683 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 597 score: 0.8690 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 598 score: 0.8996 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 599 score: 0.9389 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 600 score: 0.9040 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 601 score: 0.9224 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 602 score: 0.8967 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 603 score: 0.9020 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 604 score: 0.9391 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 605 score: 0.9437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 606 score: 0.9220 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 607 score: 0.7390 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 608 score: 0.8238 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 609 score: 0.8494 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 610 score: 0.9045 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 611 score: 0.9365 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 612 score: 0.7763 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 613 score: 0.7658 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 614 score: 0.9396 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 615 score: 0.7759 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 616 score: 0.9123 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 617 score: 0.8950 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 618 score: 0.8917 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 619 score: 0.8324 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 620 score: 0.8741 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 621 score: 0.8011 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 622 score: 0.9287 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 623 score: 0.9189 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 624 score: 0.6894 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 625 score: 0.9624 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 626 score: 0.9432 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 627 score: 0.9343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 628 score: 0.9382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 629 score: 0.9437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 630 score: 0.8841 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 631 score: 0.9407 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 632 score: 0.9177 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 633 score: 0.9199 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 634 score: 0.9872 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 635 score: 0.9067 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 636 score: 0.8926 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 637 score: 0.8785 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 638 score: 0.9060 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 639 score: 0.9358 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 640 score: 0.8592 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 641 score: 0.9284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 642 score: 0.8792 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 643 score: 0.6730 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 644 score: 0.8171 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 645 score: 0.8203 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 646 score: 0.7268 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 647 score: 0.8519 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 648 score: 0.7741 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 649 score: 0.8627 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 650 score: 0.9409 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 651 score: 0.9277 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 652 score: 0.5268 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 653 score: 0.6918 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 654 score: 0.7636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 655 score: 0.8753 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 656 score: 0.8155 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 657 score: 0.9084 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 658 score: 0.7015 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 659 score: 0.8043 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 660 score: 0.8010 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 661 score: 0.9422 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 662 score: 0.9259 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 663 score: 0.8832 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 664 score: 0.9372 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 665 score: 0.8642 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 666 score: 0.7986 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 667 score: 0.8363 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 668 score: 0.8633 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 669 score: 0.9299 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 670 score: 0.8563 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 671 score: 0.8694 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 672 score: 0.8852 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 673 score: 0.7775 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 674 score: 0.8999 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 675 score: 0.9167 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 676 score: 0.9144 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 677 score: 0.9182 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 678 score: 0.9439 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 679 score: 0.9321 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 680 score: 0.8616 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 681 score: 0.9391 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 682 score: 0.8914 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 683 score: 0.7920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 684 score: 0.8450 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 685 score: 0.8220 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 686 score: 0.7709 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 687 score: 0.8681 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 688 score: 0.9344 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 689 score: 0.9181 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 690 score: 0.8833 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 691 score: 0.8873 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 692 score: 0.8398 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 693 score: 0.8404 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 694 score: 0.7944 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 695 score: 0.9066 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 696 score: 0.8911 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 697 score: 0.8348 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 698 score: 0.7629 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 699 score: 0.9446 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 700 score: 0.8423 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 701 score: 0.9468 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 702 score: 0.9001 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 703 score: 0.8651 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 704 score: 0.8699 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 705 score: 0.6907 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 706 score: 0.6152 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 707 score: 0.9139 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 708 score: 0.8779 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 709 score: 0.8140 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 710 score: 0.9271 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 711 score: 0.8456 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 712 score: 0.9357 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 713 score: 0.9300 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 714 score: 0.8795 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 715 score: 0.8717 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 716 score: 0.9315 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 717 score: 0.9509 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 718 score: 0.9352 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 719 score: 0.8963 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 720 score: 0.9204 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 721 score: 0.9272 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 722 score: 0.8802 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 723 score: 0.8902 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 724 score: 0.8883 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 725 score: 0.9138 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 726 score: 0.8734 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 727 score: 0.9174 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 728 score: 0.7515 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 729 score: 0.8876 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 730 score: 0.8683 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 731 score: 0.8553 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 732 score: 0.8391 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 733 score: 0.9493 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 734 score: 0.8784 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 735 score: 0.9449 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 736 score: 0.9096 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 737 score: 0.8759 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 738 score: 0.9038 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 739 score: 0.8405 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 740 score: 0.8429 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 741 score: 0.8698 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 742 score: 0.8728 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 743 score: 0.9176 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 744 score: 0.8788 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 745 score: 0.8668 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 746 score: 0.9491 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 747 score: 0.9112 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 748 score: 0.9470 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 749 score: 0.9457 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 750 score: 0.9624 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 751 score: 0.9542 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 752 score: 0.9290 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 753 score: 0.8719 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 754 score: 0.9047 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 755 score: 0.8096 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 756 score: 0.8638 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 757 score: 0.8334 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 758 score: 0.7577 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 759 score: 0.8950 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 760 score: 0.9215 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 761 score: 0.8531 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 762 score: 0.8962 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 763 score: 0.7767 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 764 score: 0.8725 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 765 score: 0.8849 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 766 score: 0.8500 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 767 score: 0.7008 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 768 score: 0.9452 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 769 score: 0.9550 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 770 score: 0.9049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 771 score: 0.9116 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 772 score: 0.9379 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 773 score: 0.9431 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 774 score: 0.8967 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 775 score: 0.8648 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 776 score: 0.8864 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 777 score: 0.8196 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 778 score: 0.8706 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 779 score: 0.8391 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 780 score: 0.8316 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 781 score: 0.8148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 782 score: 0.7405 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 783 score: 0.7039 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 784 score: 0.9425 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 785 score: 0.6993 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 786 score: 0.8134 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 787 score: 0.9210 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 788 score: 0.9187 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 789 score: 0.9309 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 790 score: 0.9245 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 791 score: 0.8804 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 792 score: 0.8876 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 793 score: 0.8945 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 794 score: 0.8915 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 795 score: 0.8165 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 796 score: 0.9591 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 797 score: 0.8632 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 798 score: 0.9228 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 799 score: 0.8132 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 800 score: 0.9247 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 801 score: 0.8117 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 802 score: 0.8517 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 803 score: 0.7024 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 804 score: 0.8107 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 805 score: 0.9091 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 806 score: 0.9107 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 807 score: 0.9209 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 808 score: 0.8608 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 809 score: 0.8822 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 810 score: 0.7929 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 811 score: 0.7845 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 812 score: 0.9503 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 813 score: 0.9377 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 814 score: 0.9039 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 815 score: 0.8237 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 816 score: 0.8969 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 817 score: 0.8467 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 818 score: 0.6492 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 819 score: 0.8310 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 820 score: 0.9213 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 821 score: 0.9434 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 822 score: 0.9130 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 823 score: 0.9070 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 824 score: 0.8593 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 825 score: 0.8925 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 826 score: 0.9037 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 827 score: 0.8852 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 828 score: 0.7185 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 829 score: 0.7976 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 830 score: 0.8902 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 831 score: 0.8465 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 832 score: 0.9236 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 833 score: 0.7207 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 834 score: 0.7526 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 835 score: 0.8659 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 836 score: 0.8186 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 837 score: 0.8640 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 838 score: 0.7537 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 839 score: 0.8938 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 840 score: 0.6947 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 841 score: 0.7296 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 842 score: 0.7220 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 843 score: 0.8778 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 844 score: 0.7871 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 845 score: 0.7378 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 846 score: 0.5954 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 847 score: 0.8792 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 848 score: 0.6907 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 849 score: 0.8560 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 850 score: 0.8835 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 851 score: 0.9012 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 852 score: 0.9206 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 853 score: 0.8437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 854 score: 0.8167 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 855 score: 0.9439 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 856 score: 0.7574 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 857 score: 0.9145 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 858 score: 0.8423 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 859 score: 0.9157 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 860 score: 0.8663 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 861 score: 0.9380 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 862 score: 0.9284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 863 score: 0.8384 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 864 score: 0.4629 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 865 score: 0.6258 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 866 score: 0.8354 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 867 score: 0.9074 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 868 score: 0.9121 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 869 score: 0.8855 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 870 score: 0.8954 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 871 score: 0.9393 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 872 score: 0.9117 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 873 score: 0.8741 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 874 score: 0.9380 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 875 score: 0.8160 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 876 score: 0.8600 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 877 score: 0.8619 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 878 score: 0.9664 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 879 score: 0.8107 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 880 score: 0.8642 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 881 score: 0.9431 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 882 score: 0.8711 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 883 score: 0.9392 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 884 score: 0.8851 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 885 score: 0.8923 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 886 score: 0.9227 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 887 score: 0.8374 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 888 score: 0.7543 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 889 score: 0.6640 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 890 score: 0.7475 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 891 score: 0.9205 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 892 score: 0.7496 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 893 score: 0.7180 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 894 score: 0.8826 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 895 score: 0.6397 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 896 score: 0.8452 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 897 score: 0.5084 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 898 score: 0.9261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 899 score: 0.7663 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 900 score: 0.8674 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 901 score: 0.8382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 902 score: 0.8722 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 903 score: 0.8106 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 904 score: 0.9450 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 905 score: 0.8713 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 906 score: 0.9082 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 907 score: 0.8095 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 908 score: 0.8708 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 909 score: 0.9410 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 910 score: 0.8950 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 911 score: 0.7375 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 912 score: 0.9341 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 913 score: 0.8787 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 914 score: 0.8461 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 915 score: 0.8347 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 916 score: 0.9375 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 917 score: 0.9123 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 918 score: 0.9057 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 919 score: 0.8864 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 920 score: 0.6652 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 921 score: 0.8955 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 922 score: 0.8856 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 923 score: 0.8920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 924 score: 0.9005 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 925 score: 0.9097 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 926 score: 0.8884 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 927 score: 0.7431 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 928 score: 0.8315 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 929 score: 0.8162 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 930 score: 0.7841 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 931 score: 0.8222 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 932 score: 0.6682 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 933 score: 0.8418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 934 score: 0.7854 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 935 score: 0.9080 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 936 score: 0.8987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 937 score: 0.9543 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 938 score: 0.8601 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 939 score: 0.9276 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 940 score: 0.9429 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 941 score: 0.9675 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 942 score: 0.9152 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 943 score: 0.7486 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 944 score: 0.8501 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 945 score: 0.9446 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 946 score: 0.7902 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 947 score: 0.7068 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 948 score: 0.8088 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 949 score: 0.8771 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 950 score: 0.7561 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 951 score: 0.7507 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 952 score: 0.8737 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 953 score: 0.5683 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 954 score: 0.7497 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 955 score: 0.9204 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 956 score: 0.9198 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 957 score: 0.9418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 958 score: 0.9072 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 959 score: 0.8213 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 960 score: 0.6163 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 961 score: 0.8752 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 962 score: 0.9142 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 963 score: 0.8680 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 964 score: 0.9404 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 965 score: 0.8611 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 966 score: 0.8185 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 967 score: 0.6936 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 968 score: 0.8502 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 969 score: 0.6295 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 970 score: 0.8216 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 971 score: 0.8643 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 972 score: 0.8343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 973 score: 0.9160 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 974 score: 0.8368 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 975 score: 0.9344 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 976 score: 0.8232 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 977 score: 0.6331 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 978 score: 0.9449 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 979 score: 0.9172 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 980 score: 0.8944 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 981 score: 0.8880 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 982 score: 0.7078 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 983 score: 0.8222 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 984 score: 0.9491 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 985 score: 0.9190 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 986 score: 0.9053 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 987 score: 0.8689 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 988 score: 0.7205 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 989 score: 0.6427 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 990 score: 0.8851 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 991 score: 0.8420 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 992 score: 0.9275 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 993 score: 0.8026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 994 score: 0.8918 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 995 score: 0.8919 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 996 score: 0.8881 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 997 score: 0.9134 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 998 score: 0.9163 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 999 score: 0.8424 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1000 score: 0.9099 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1001 score: 0.7990 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1002 score: 0.8623 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1003 score: 0.6875 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1004 score: 0.7935 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1005 score: 0.9028 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1006 score: 0.9244 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1007 score: 0.8104 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1008 score: 0.8737 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1009 score: 0.8585 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1010 score: 0.8357 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk Segment 1011 score: 0.8576 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-3-max-tokens-512//test-en-mk score: 0.8524