diff --git "a/test-en-ja.comet" "b/test-en-ja.comet" new file mode 100644--- /dev/null +++ "b/test-en-ja.comet" @@ -0,0 +1,1013 @@ +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 0 score: 0.7850 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1 score: 0.9101 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 2 score: 0.9408 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 3 score: 0.8926 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 4 score: 0.9179 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 5 score: 0.7501 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 6 score: 0.9051 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 7 score: 0.8930 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 8 score: 0.9268 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 9 score: 0.8791 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 10 score: 0.9356 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 11 score: 0.9023 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 12 score: 0.8197 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 13 score: 0.8797 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 14 score: 0.8941 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 15 score: 0.8459 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 16 score: 0.9316 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 17 score: 0.9513 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 18 score: 0.9398 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 19 score: 0.9081 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 20 score: 0.9694 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 21 score: 0.9522 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 22 score: 0.7335 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 23 score: 0.9254 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 24 score: 0.9464 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 25 score: 0.9489 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 26 score: 0.9116 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 27 score: 0.8897 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 28 score: 0.8752 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 29 score: 0.9392 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 30 score: 0.7872 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 31 score: 0.8785 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 32 score: 0.8893 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 33 score: 0.9422 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 34 score: 0.9550 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 35 score: 0.9270 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 36 score: 0.9184 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 37 score: 0.9182 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 38 score: 0.9401 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 39 score: 0.9008 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 40 score: 0.8808 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 41 score: 0.9084 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 42 score: 0.8820 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 43 score: 0.9003 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 44 score: 0.8049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 45 score: 0.9152 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 46 score: 0.9194 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 47 score: 0.9312 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 48 score: 0.8934 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 49 score: 0.9154 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 50 score: 0.9318 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 51 score: 0.9203 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 52 score: 0.8892 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 53 score: 0.8984 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 54 score: 0.9267 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 55 score: 0.9167 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 56 score: 0.8611 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 57 score: 0.9023 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 58 score: 0.8670 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 59 score: 0.9496 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 60 score: 0.9578 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 61 score: 0.9154 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 62 score: 0.9003 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 63 score: 0.9124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 64 score: 0.8865 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 65 score: 0.8870 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 66 score: 0.7727 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 67 score: 0.7870 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 68 score: 0.9373 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 69 score: 0.9221 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 70 score: 0.9560 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 71 score: 0.8547 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 72 score: 0.9339 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 73 score: 0.8566 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 74 score: 0.8915 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 75 score: 0.8917 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 76 score: 0.9193 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 77 score: 0.9266 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 78 score: 0.9712 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 79 score: 0.9120 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 80 score: 0.8961 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 81 score: 0.9293 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 82 score: 0.9056 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 83 score: 0.9063 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 84 score: 0.8983 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 85 score: 0.9171 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 86 score: 0.8284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 87 score: 0.9364 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 88 score: 0.8983 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 89 score: 0.8955 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 90 score: 0.6549 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 91 score: 0.5336 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 92 score: 0.9085 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 93 score: 0.9531 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 94 score: 0.8774 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 95 score: 0.9493 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 96 score: 0.9372 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 97 score: 0.9118 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 98 score: 0.9254 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 99 score: 0.9257 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 100 score: 0.8931 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 101 score: 0.8953 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 102 score: 0.9223 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 103 score: 0.9607 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 104 score: 0.9335 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 105 score: 0.7808 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 106 score: 0.9589 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 107 score: 0.8815 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 108 score: 0.8416 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 109 score: 0.8335 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 110 score: 0.9468 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 111 score: 0.9420 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 112 score: 0.9749 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 113 score: 0.9606 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 114 score: 0.9212 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 115 score: 0.8845 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 116 score: 0.9280 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 117 score: 0.9560 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 118 score: 0.9380 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 119 score: 0.8153 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 120 score: 0.9082 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 121 score: 0.9402 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 122 score: 0.9527 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 123 score: 0.9060 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 124 score: 0.8971 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 125 score: 0.9311 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 126 score: 0.9508 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 127 score: 0.9229 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 128 score: 0.9236 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 129 score: 0.9513 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 130 score: 0.8585 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 131 score: 0.8326 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 132 score: 0.8793 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 133 score: 0.9575 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 134 score: 0.8408 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 135 score: 0.8151 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 136 score: 0.9636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 137 score: 0.9454 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 138 score: 0.9493 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 139 score: 0.8272 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 140 score: 0.9116 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 141 score: 0.9150 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 142 score: 0.9594 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 143 score: 0.9188 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 144 score: 0.9549 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 145 score: 0.9471 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 146 score: 0.9458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 147 score: 0.9128 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 148 score: 0.9339 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 149 score: 0.9332 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 150 score: 0.9085 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 151 score: 0.8364 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 152 score: 0.8946 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 153 score: 0.8920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 154 score: 0.8669 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 155 score: 0.8897 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 156 score: 0.9116 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 157 score: 0.9321 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 158 score: 0.9137 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 159 score: 0.9375 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 160 score: 0.8746 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 161 score: 0.8565 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 162 score: 0.9241 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 163 score: 0.9221 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 164 score: 0.9427 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 165 score: 0.8599 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 166 score: 0.8948 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 167 score: 0.9064 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 168 score: 0.9168 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 169 score: 0.8466 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 170 score: 0.9132 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 171 score: 0.9346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 172 score: 0.9475 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 173 score: 0.9125 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 174 score: 0.8987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 175 score: 0.9073 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 176 score: 0.8358 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 177 score: 0.8955 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 178 score: 0.9074 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 179 score: 0.9426 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 180 score: 0.9261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 181 score: 0.9702 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 182 score: 0.9567 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 183 score: 0.8979 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 184 score: 0.9185 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 185 score: 0.9646 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 186 score: 0.9079 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 187 score: 0.9130 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 188 score: 0.9124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 189 score: 0.9135 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 190 score: 0.8474 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 191 score: 0.9047 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 192 score: 0.8455 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 193 score: 0.8278 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 194 score: 0.8908 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 195 score: 0.9716 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 196 score: 0.9331 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 197 score: 0.8671 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 198 score: 0.9226 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 199 score: 0.9257 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 200 score: 0.8510 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 201 score: 0.8012 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 202 score: 0.8535 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 203 score: 0.8531 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 204 score: 0.8931 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 205 score: 0.9505 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 206 score: 0.9552 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 207 score: 0.9093 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 208 score: 0.9430 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 209 score: 0.9126 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 210 score: 0.9661 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 211 score: 0.9119 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 212 score: 0.9358 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 213 score: 0.9171 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 214 score: 0.9216 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 215 score: 0.9156 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 216 score: 0.9399 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 217 score: 0.9393 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 218 score: 0.9108 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 219 score: 0.9050 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 220 score: 0.9798 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 221 score: 0.9593 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 222 score: 0.9499 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 223 score: 0.9303 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 224 score: 0.9404 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 225 score: 0.9654 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 226 score: 0.9071 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 227 score: 0.8408 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 228 score: 0.8857 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 229 score: 0.9155 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 230 score: 0.9643 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 231 score: 0.8203 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 232 score: 0.8583 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 233 score: 0.8453 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 234 score: 0.9160 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 235 score: 0.8399 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 236 score: 0.9229 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 237 score: 0.8734 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 238 score: 0.9522 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 239 score: 0.8579 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 240 score: 0.8205 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 241 score: 0.8382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 242 score: 0.9288 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 243 score: 0.8853 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 244 score: 0.8597 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 245 score: 0.9671 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 246 score: 0.9008 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 247 score: 0.8630 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 248 score: 0.8465 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 249 score: 0.9208 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 250 score: 0.9324 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 251 score: 0.9507 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 252 score: 0.9359 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 253 score: 0.9036 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 254 score: 0.9325 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 255 score: 0.9401 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 256 score: 0.9416 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 257 score: 0.9451 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 258 score: 0.9282 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 259 score: 0.9094 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 260 score: 0.9408 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 261 score: 0.8323 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 262 score: 0.9352 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 263 score: 0.8406 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 264 score: 0.9342 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 265 score: 0.9226 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 266 score: 0.8850 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 267 score: 0.9088 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 268 score: 0.9484 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 269 score: 0.9240 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 270 score: 0.8946 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 271 score: 0.8523 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 272 score: 0.9607 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 273 score: 0.9108 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 274 score: 0.8655 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 275 score: 0.8847 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 276 score: 0.8725 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 277 score: 0.9380 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 278 score: 0.9048 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 279 score: 0.9153 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 280 score: 0.9447 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 281 score: 0.9576 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 282 score: 0.9800 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 283 score: 0.8796 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 284 score: 0.9043 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 285 score: 0.9357 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 286 score: 0.9194 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 287 score: 0.8339 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 288 score: 0.9398 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 289 score: 0.9337 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 290 score: 0.7583 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 291 score: 0.8956 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 292 score: 0.9481 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 293 score: 0.9075 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 294 score: 0.8576 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 295 score: 0.7575 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 296 score: 0.8800 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 297 score: 0.9487 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 298 score: 0.8208 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 299 score: 0.9273 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 300 score: 0.9071 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 301 score: 0.9265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 302 score: 0.9344 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 303 score: 0.9042 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 304 score: 0.9143 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 305 score: 0.9382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 306 score: 0.9295 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 307 score: 0.9371 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 308 score: 0.9608 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 309 score: 0.9375 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 310 score: 0.9419 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 311 score: 0.9510 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 312 score: 0.9560 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 313 score: 0.8042 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 314 score: 0.9344 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 315 score: 0.9735 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 316 score: 0.9297 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 317 score: 0.9509 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 318 score: 0.9307 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 319 score: 0.9567 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 320 score: 0.8533 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 321 score: 0.8749 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 322 score: 0.9289 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 323 score: 0.9052 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 324 score: 0.9417 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 325 score: 0.9045 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 326 score: 0.8700 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 327 score: 0.7995 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 328 score: 0.9372 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 329 score: 0.9168 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 330 score: 0.9176 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 331 score: 0.8763 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 332 score: 0.9557 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 333 score: 0.9416 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 334 score: 0.9472 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 335 score: 0.9418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 336 score: 0.9082 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 337 score: 0.8846 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 338 score: 0.9284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 339 score: 0.9390 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 340 score: 0.8472 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 341 score: 0.8489 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 342 score: 0.7308 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 343 score: 0.8318 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 344 score: 0.8378 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 345 score: 0.9361 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 346 score: 0.9510 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 347 score: 0.8408 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 348 score: 0.7994 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 349 score: 0.8715 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 350 score: 0.8970 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 351 score: 0.9243 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 352 score: 0.9292 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 353 score: 0.9346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 354 score: 0.9243 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 355 score: 0.8614 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 356 score: 0.9508 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 357 score: 0.9125 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 358 score: 0.9073 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 359 score: 0.8369 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 360 score: 0.8620 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 361 score: 0.8453 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 362 score: 0.8830 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 363 score: 0.8502 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 364 score: 0.8180 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 365 score: 0.8239 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 366 score: 0.6510 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 367 score: 0.8700 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 368 score: 0.6792 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 369 score: 0.8528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 370 score: 0.8911 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 371 score: 0.9132 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 372 score: 0.8820 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 373 score: 0.9015 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 374 score: 0.9069 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 375 score: 0.8557 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 376 score: 0.9425 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 377 score: 0.9119 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 378 score: 0.8635 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 379 score: 0.8504 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 380 score: 0.9376 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 381 score: 0.8596 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 382 score: 0.8454 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 383 score: 0.7940 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 384 score: 0.8990 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 385 score: 0.8559 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 386 score: 0.8528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 387 score: 0.9092 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 388 score: 0.8855 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 389 score: 0.9197 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 390 score: 0.9543 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 391 score: 0.9060 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 392 score: 0.9581 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 393 score: 0.9375 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 394 score: 0.9006 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 395 score: 0.9569 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 396 score: 0.8198 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 397 score: 0.9528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 398 score: 0.8859 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 399 score: 0.9658 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 400 score: 0.9461 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 401 score: 0.9443 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 402 score: 0.9291 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 403 score: 0.8797 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 404 score: 0.7814 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 405 score: 0.9285 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 406 score: 0.9382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 407 score: 0.9297 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 408 score: 0.9675 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 409 score: 0.9692 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 410 score: 0.9342 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 411 score: 0.8311 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 412 score: 0.9128 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 413 score: 0.9233 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 414 score: 0.9181 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 415 score: 0.9394 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 416 score: 0.9099 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 417 score: 0.9330 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 418 score: 0.9344 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 419 score: 0.9573 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 420 score: 0.9411 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 421 score: 0.9416 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 422 score: 0.9509 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 423 score: 0.8790 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 424 score: 0.9243 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 425 score: 0.9435 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 426 score: 0.9098 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 427 score: 0.9005 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 428 score: 0.8536 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 429 score: 0.9487 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 430 score: 0.9353 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 431 score: 0.8891 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 432 score: 0.8347 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 433 score: 0.8882 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 434 score: 0.8009 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 435 score: 0.7698 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 436 score: 0.8303 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 437 score: 0.8761 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 438 score: 0.9580 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 439 score: 0.9453 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 440 score: 0.9269 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 441 score: 0.9395 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 442 score: 0.9593 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 443 score: 0.9522 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 444 score: 0.8316 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 445 score: 0.9009 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 446 score: 0.9604 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 447 score: 0.9521 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 448 score: 0.9385 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 449 score: 0.8419 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 450 score: 0.9045 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 451 score: 0.9323 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 452 score: 0.9617 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 453 score: 0.8736 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 454 score: 0.8990 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 455 score: 0.7943 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 456 score: 0.8299 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 457 score: 0.9346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 458 score: 0.8926 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 459 score: 0.9213 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 460 score: 0.9357 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 461 score: 0.9308 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 462 score: 0.8939 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 463 score: 0.9596 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 464 score: 0.9518 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 465 score: 0.8839 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 466 score: 0.9010 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 467 score: 0.8262 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 468 score: 0.7835 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 469 score: 0.7902 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 470 score: 0.8266 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 471 score: 0.8931 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 472 score: 0.8853 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 473 score: 0.7494 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 474 score: 0.8622 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 475 score: 0.9458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 476 score: 0.8769 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 477 score: 0.9319 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 478 score: 0.9260 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 479 score: 0.9289 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 480 score: 0.6874 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 481 score: 0.8007 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 482 score: 0.9124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 483 score: 0.9515 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 484 score: 0.9241 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 485 score: 0.8980 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 486 score: 0.9261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 487 score: 0.9139 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 488 score: 0.9302 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 489 score: 0.8712 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 490 score: 0.9059 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 491 score: 0.9581 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 492 score: 0.9598 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 493 score: 0.9392 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 494 score: 0.9116 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 495 score: 0.8771 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 496 score: 0.9425 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 497 score: 0.8836 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 498 score: 0.9467 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 499 score: 0.8356 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 500 score: 0.9582 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 501 score: 0.9406 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 502 score: 0.8827 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 503 score: 0.8972 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 504 score: 0.8614 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 505 score: 0.9625 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 506 score: 0.8307 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 507 score: 0.8892 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 508 score: 0.8687 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 509 score: 0.9256 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 510 score: 0.8774 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 511 score: 0.8770 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 512 score: 0.8141 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 513 score: 0.6300 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 514 score: 0.8777 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 515 score: 0.9264 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 516 score: 0.8712 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 517 score: 0.9162 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 518 score: 0.8850 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 519 score: 0.9566 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 520 score: 0.9398 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 521 score: 0.9220 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 522 score: 0.9525 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 523 score: 0.8944 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 524 score: 0.9524 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 525 score: 0.8565 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 526 score: 0.7907 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 527 score: 0.8049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 528 score: 0.8997 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 529 score: 0.9028 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 530 score: 0.9086 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 531 score: 0.9183 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 532 score: 0.9325 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 533 score: 0.9307 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 534 score: 0.8803 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 535 score: 0.8441 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 536 score: 0.8544 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 537 score: 0.8747 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 538 score: 0.9219 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 539 score: 0.8996 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 540 score: 0.9186 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 541 score: 0.9559 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 542 score: 0.8918 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 543 score: 0.9018 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 544 score: 0.9309 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 545 score: 0.9583 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 546 score: 0.8842 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 547 score: 0.9223 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 548 score: 0.9112 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 549 score: 0.9327 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 550 score: 0.8922 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 551 score: 0.9490 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 552 score: 0.9517 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 553 score: 0.9157 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 554 score: 0.8910 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 555 score: 0.8131 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 556 score: 0.8624 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 557 score: 0.8879 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 558 score: 0.7692 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 559 score: 0.8516 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 560 score: 0.8754 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 561 score: 0.9508 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 562 score: 0.9109 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 563 score: 0.9031 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 564 score: 0.9121 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 565 score: 0.9002 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 566 score: 0.8862 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 567 score: 0.9296 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 568 score: 0.9383 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 569 score: 0.8987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 570 score: 0.9357 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 571 score: 0.9164 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 572 score: 0.8611 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 573 score: 0.9030 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 574 score: 0.9364 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 575 score: 0.8637 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 576 score: 0.8681 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 577 score: 0.9526 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 578 score: 0.9323 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 579 score: 0.9096 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 580 score: 0.9039 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 581 score: 0.9044 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 582 score: 0.7802 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 583 score: 0.8871 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 584 score: 0.8025 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 585 score: 0.9119 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 586 score: 0.8581 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 587 score: 0.8919 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 588 score: 0.7758 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 589 score: 0.9006 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 590 score: 0.9443 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 591 score: 0.9522 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 592 score: 0.8510 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 593 score: 0.9306 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 594 score: 0.9708 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 595 score: 0.9165 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 596 score: 0.8940 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 597 score: 0.9346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 598 score: 0.8613 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 599 score: 0.9574 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 600 score: 0.9182 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 601 score: 0.7923 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 602 score: 0.9218 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 603 score: 0.9015 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 604 score: 0.8990 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 605 score: 0.9187 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 606 score: 0.7980 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 607 score: 0.8458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 608 score: 0.8230 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 609 score: 0.8775 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 610 score: 0.9368 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 611 score: 0.9418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 612 score: 0.9287 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 613 score: 0.9122 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 614 score: 0.9539 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 615 score: 0.8972 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 616 score: 0.9121 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 617 score: 0.9802 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 618 score: 0.9090 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 619 score: 0.8672 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 620 score: 0.8715 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 621 score: 0.8015 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 622 score: 0.8996 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 623 score: 0.8942 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 624 score: 0.9314 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 625 score: 0.9545 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 626 score: 0.9566 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 627 score: 0.9612 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 628 score: 0.9198 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 629 score: 0.9304 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 630 score: 0.9314 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 631 score: 0.9674 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 632 score: 0.9672 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 633 score: 0.9256 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 634 score: 0.9787 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 635 score: 0.9415 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 636 score: 0.9389 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 637 score: 0.9278 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 638 score: 0.9393 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 639 score: 0.9732 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 640 score: 0.8972 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 641 score: 0.9711 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 642 score: 0.8945 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 643 score: 0.8759 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 644 score: 0.8957 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 645 score: 0.8859 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 646 score: 0.8696 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 647 score: 0.9166 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 648 score: 0.8366 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 649 score: 0.9029 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 650 score: 0.9671 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 651 score: 0.8842 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 652 score: 0.7673 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 653 score: 0.8671 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 654 score: 0.9391 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 655 score: 0.9078 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 656 score: 0.7831 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 657 score: 0.8962 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 658 score: 0.8619 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 659 score: 0.8158 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 660 score: 0.8552 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 661 score: 0.9327 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 662 score: 0.9386 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 663 score: 0.9069 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 664 score: 0.9343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 665 score: 0.8669 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 666 score: 0.9287 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 667 score: 0.8138 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 668 score: 0.9227 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 669 score: 0.8911 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 670 score: 0.9560 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 671 score: 0.9129 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 672 score: 0.9274 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 673 score: 0.9474 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 674 score: 0.9146 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 675 score: 0.9009 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 676 score: 0.9384 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 677 score: 0.9203 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 678 score: 0.9231 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 679 score: 0.9405 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 680 score: 0.8820 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 681 score: 0.9385 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 682 score: 0.9211 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 683 score: 0.8548 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 684 score: 0.8784 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 685 score: 0.8468 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 686 score: 0.9439 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 687 score: 0.8998 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 688 score: 0.9316 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 689 score: 0.8827 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 690 score: 0.9397 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 691 score: 0.8939 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 692 score: 0.9480 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 693 score: 0.9323 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 694 score: 0.8920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 695 score: 0.9005 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 696 score: 0.9249 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 697 score: 0.9630 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 698 score: 0.8519 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 699 score: 0.9486 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 700 score: 0.9054 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 701 score: 0.8953 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 702 score: 0.8823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 703 score: 0.9113 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 704 score: 0.8484 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 705 score: 0.9112 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 706 score: 0.8303 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 707 score: 0.9222 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 708 score: 0.9137 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 709 score: 0.9442 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 710 score: 0.9108 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 711 score: 0.9333 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 712 score: 0.9495 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 713 score: 0.9157 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 714 score: 0.9502 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 715 score: 0.8878 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 716 score: 0.9148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 717 score: 0.9065 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 718 score: 0.9439 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 719 score: 0.9279 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 720 score: 0.8997 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 721 score: 0.9572 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 722 score: 0.9337 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 723 score: 0.9424 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 724 score: 0.9305 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 725 score: 0.9701 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 726 score: 0.8829 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 727 score: 0.9173 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 728 score: 0.8432 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 729 score: 0.9452 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 730 score: 0.9196 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 731 score: 0.9547 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 732 score: 0.9445 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 733 score: 0.9388 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 734 score: 0.8626 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 735 score: 0.9487 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 736 score: 0.9379 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 737 score: 0.8873 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 738 score: 0.9561 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 739 score: 0.9009 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 740 score: 0.8133 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 741 score: 0.8665 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 742 score: 0.9132 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 743 score: 0.9512 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 744 score: 0.8865 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 745 score: 0.9484 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 746 score: 0.9335 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 747 score: 0.9207 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 748 score: 0.9016 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 749 score: 0.9329 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 750 score: 0.9350 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 751 score: 0.9260 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 752 score: 0.9237 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 753 score: 0.8832 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 754 score: 0.9382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 755 score: 0.9159 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 756 score: 0.9346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 757 score: 0.9151 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 758 score: 0.9067 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 759 score: 0.8609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 760 score: 0.9532 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 761 score: 0.9079 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 762 score: 0.9528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 763 score: 0.9161 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 764 score: 0.8824 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 765 score: 0.8505 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 766 score: 0.8464 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 767 score: 0.8730 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 768 score: 0.9654 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 769 score: 0.9618 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 770 score: 0.9014 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 771 score: 0.9215 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 772 score: 0.9226 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 773 score: 0.9501 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 774 score: 0.9302 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 775 score: 0.8583 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 776 score: 0.8901 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 777 score: 0.9462 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 778 score: 0.9049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 779 score: 0.9095 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 780 score: 0.8762 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 781 score: 0.8444 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 782 score: 0.8996 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 783 score: 0.8020 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 784 score: 0.9127 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 785 score: 0.9022 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 786 score: 0.9171 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 787 score: 0.9408 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 788 score: 0.9664 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 789 score: 0.9547 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 790 score: 0.9063 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 791 score: 0.8636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 792 score: 0.9037 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 793 score: 0.9371 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 794 score: 0.8667 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 795 score: 0.9169 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 796 score: 0.9389 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 797 score: 0.8806 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 798 score: 0.9607 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 799 score: 0.8494 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 800 score: 0.8748 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 801 score: 0.9140 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 802 score: 0.9425 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 803 score: 0.8926 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 804 score: 0.9245 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 805 score: 0.8950 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 806 score: 0.9294 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 807 score: 0.9575 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 808 score: 0.8715 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 809 score: 0.8686 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 810 score: 0.8121 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 811 score: 0.8763 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 812 score: 0.9400 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 813 score: 0.9276 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 814 score: 0.9401 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 815 score: 0.8673 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 816 score: 0.9188 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 817 score: 0.7214 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 818 score: 0.6459 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 819 score: 0.7881 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 820 score: 0.8618 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 821 score: 0.8423 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 822 score: 0.9222 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 823 score: 0.8934 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 824 score: 0.9104 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 825 score: 0.9216 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 826 score: 0.9654 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 827 score: 0.9409 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 828 score: 0.8633 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 829 score: 0.8921 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 830 score: 0.9158 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 831 score: 0.8528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 832 score: 0.8756 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 833 score: 0.8749 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 834 score: 0.9152 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 835 score: 0.8336 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 836 score: 0.9063 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 837 score: 0.8499 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 838 score: 0.9089 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 839 score: 0.8722 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 840 score: 0.8628 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 841 score: 0.8973 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 842 score: 0.7720 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 843 score: 0.8563 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 844 score: 0.8700 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 845 score: 0.8462 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 846 score: 0.8278 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 847 score: 0.9151 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 848 score: 0.8868 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 849 score: 0.9373 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 850 score: 0.8524 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 851 score: 0.9293 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 852 score: 0.9324 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 853 score: 0.9511 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 854 score: 0.7350 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 855 score: 0.9293 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 856 score: 0.8958 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 857 score: 0.9146 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 858 score: 0.9154 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 859 score: 0.9171 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 860 score: 0.9385 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 861 score: 0.9262 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 862 score: 0.9381 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 863 score: 0.9040 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 864 score: 0.9011 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 865 score: 0.8824 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 866 score: 0.9098 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 867 score: 0.8911 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 868 score: 0.8815 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 869 score: 0.9231 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 870 score: 0.9592 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 871 score: 0.8289 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 872 score: 0.8908 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 873 score: 0.9112 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 874 score: 0.9501 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 875 score: 0.4844 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 876 score: 0.8688 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 877 score: 0.8920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 878 score: 0.8985 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 879 score: 0.9105 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 880 score: 0.8132 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 881 score: 0.9248 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 882 score: 0.8840 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 883 score: 0.9330 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 884 score: 0.8878 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 885 score: 0.8761 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 886 score: 0.8509 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 887 score: 0.8944 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 888 score: 0.8173 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 889 score: 0.8503 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 890 score: 0.7970 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 891 score: 0.8257 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 892 score: 0.7407 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 893 score: 0.9037 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 894 score: 0.8300 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 895 score: 0.9243 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 896 score: 0.8841 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 897 score: 0.8968 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 898 score: 0.9263 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 899 score: 0.9357 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 900 score: 0.8860 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 901 score: 0.9409 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 902 score: 0.7599 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 903 score: 0.8961 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 904 score: 0.9396 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 905 score: 0.8964 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 906 score: 0.9430 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 907 score: 0.8322 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 908 score: 0.9089 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 909 score: 0.9430 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 910 score: 0.9261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 911 score: 0.9181 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 912 score: 0.9478 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 913 score: 0.8801 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 914 score: 0.9131 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 915 score: 0.9275 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 916 score: 0.9609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 917 score: 0.9382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 918 score: 0.8691 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 919 score: 0.9259 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 920 score: 0.9223 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 921 score: 0.9104 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 922 score: 0.9390 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 923 score: 0.8648 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 924 score: 0.9042 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 925 score: 0.9093 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 926 score: 0.8971 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 927 score: 0.9558 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 928 score: 0.9044 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 929 score: 0.3933 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 930 score: 0.8893 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 931 score: 0.9002 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 932 score: 0.8291 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 933 score: 0.8791 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 934 score: 0.7786 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 935 score: 0.9119 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 936 score: 0.8655 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 937 score: 0.9697 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 938 score: 0.9478 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 939 score: 0.9427 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 940 score: 0.9010 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 941 score: 0.9541 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 942 score: 0.9385 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 943 score: 0.9262 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 944 score: 0.8959 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 945 score: 0.8883 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 946 score: 0.8667 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 947 score: 0.9426 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 948 score: 0.8903 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 949 score: 0.8806 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 950 score: 0.9076 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 951 score: 0.8823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 952 score: 0.8439 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 953 score: 0.8550 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 954 score: 0.7972 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 955 score: 0.9345 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 956 score: 0.9619 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 957 score: 0.9670 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 958 score: 0.9131 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 959 score: 0.9505 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 960 score: 0.8113 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 961 score: 0.7570 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 962 score: 0.8512 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 963 score: 0.8758 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 964 score: 0.9661 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 965 score: 0.8583 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 966 score: 0.9197 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 967 score: 0.8805 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 968 score: 0.8615 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 969 score: 0.8101 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 970 score: 0.9265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 971 score: 0.8458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 972 score: 0.7577 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 973 score: 0.9224 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 974 score: 0.8682 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 975 score: 0.9449 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 976 score: 0.8743 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 977 score: 0.8506 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 978 score: 0.9362 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 979 score: 0.9067 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 980 score: 0.9224 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 981 score: 0.9219 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 982 score: 0.9137 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 983 score: 0.7362 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 984 score: 0.9143 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 985 score: 0.9488 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 986 score: 0.8934 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 987 score: 0.9127 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 988 score: 0.8685 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 989 score: 0.8955 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 990 score: 0.9453 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 991 score: 0.8866 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 992 score: 0.8908 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 993 score: 0.9024 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 994 score: 0.8704 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 995 score: 0.9120 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 996 score: 0.9736 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 997 score: 0.9815 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 998 score: 0.9375 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 999 score: 0.8175 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1000 score: 0.8962 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1001 score: 0.8642 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1002 score: 0.8688 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1003 score: 0.9302 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1004 score: 0.8922 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1005 score: 0.9421 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1006 score: 0.9456 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1007 score: 0.9483 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1008 score: 0.9043 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1009 score: 0.9009 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1010 score: 0.9325 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja Segment 1011 score: 0.8910 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/group_training/alma-13b-sft-group-6-max-tokens-512//test-en-ja score: 0.8992