/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 0 score: 0.8042 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1 score: 0.9321 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 2 score: 0.9309 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 3 score: 0.8760 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 4 score: 0.8559 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 5 score: 0.7594 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 6 score: 0.7001 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 7 score: 0.9001 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 8 score: 0.8640 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 9 score: 0.8608 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 10 score: 0.9368 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 11 score: 0.8092 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 12 score: 0.8974 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 13 score: 0.8976 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 14 score: 0.8910 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 15 score: 0.6443 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 16 score: 0.8621 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 17 score: 0.9570 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 18 score: 0.9161 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 19 score: 0.8869 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 20 score: 0.9539 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 21 score: 0.9481 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 22 score: 0.8588 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 23 score: 0.9297 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 24 score: 0.9235 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 25 score: 0.9676 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 26 score: 0.8859 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 27 score: 0.8241 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 28 score: 0.6700 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 29 score: 0.9409 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 30 score: 0.6807 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 31 score: 0.7952 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 32 score: 0.8400 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 33 score: 0.9209 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 34 score: 0.9665 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 35 score: 0.9440 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 36 score: 0.9306 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 37 score: 0.8336 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 38 score: 0.8130 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 39 score: 0.7864 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 40 score: 0.8730 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 41 score: 0.9506 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 42 score: 0.9122 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 43 score: 0.9497 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 44 score: 0.8417 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 45 score: 0.8927 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 46 score: 0.9233 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 47 score: 0.8948 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 48 score: 0.9218 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 49 score: 0.9465 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 50 score: 0.9186 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 51 score: 0.8561 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 52 score: 0.9459 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 53 score: 0.9536 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 54 score: 0.9137 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 55 score: 0.9483 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 56 score: 0.9206 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 57 score: 0.8916 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 58 score: 0.8204 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 59 score: 0.9572 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 60 score: 0.8927 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 61 score: 0.9487 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 62 score: 0.8469 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 63 score: 0.9148 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 64 score: 0.8976 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 65 score: 0.7943 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 66 score: 0.7525 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 67 score: 0.5916 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 68 score: 0.9532 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 69 score: 0.8497 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 70 score: 0.9064 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 71 score: 0.8906 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 72 score: 0.8976 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 73 score: 0.9025 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 74 score: 0.8598 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 75 score: 0.8568 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 76 score: 0.8421 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 77 score: 0.9563 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 78 score: 0.9675 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 79 score: 0.9252 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 80 score: 0.9170 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 81 score: 0.9510 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 82 score: 0.8515 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 83 score: 0.7152 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 84 score: 0.8121 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 85 score: 0.8537 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 86 score: 0.8590 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 87 score: 0.8878 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 88 score: 0.9371 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 89 score: 0.8964 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 90 score: 0.8878 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 91 score: 0.8881 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 92 score: 0.8602 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 93 score: 0.6884 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 94 score: 0.9304 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 95 score: 0.9466 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 96 score: 0.7168 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 97 score: 0.9244 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 98 score: 0.8383 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 99 score: 0.8494 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 100 score: 0.9551 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 101 score: 0.9403 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 102 score: 0.9129 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 103 score: 0.9543 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 104 score: 0.9539 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 105 score: 0.7902 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 106 score: 0.9350 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 107 score: 0.9239 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 108 score: 0.8177 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 109 score: 0.7757 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 110 score: 0.9087 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 111 score: 0.9583 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 112 score: 0.9642 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 113 score: 0.9447 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 114 score: 0.9096 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 115 score: 0.9381 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 116 score: 0.8991 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 117 score: 0.9619 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 118 score: 0.9744 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 119 score: 0.8921 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 120 score: 0.8117 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 121 score: 0.9160 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 122 score: 0.9376 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 123 score: 0.9334 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 124 score: 0.9185 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 125 score: 0.9441 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 126 score: 0.9484 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 127 score: 0.8104 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 128 score: 0.9302 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 129 score: 0.8717 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 130 score: 0.8498 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 131 score: 0.9176 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 132 score: 0.9213 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 133 score: 0.8405 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 134 score: 0.8327 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 135 score: 0.8885 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 136 score: 0.9393 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 137 score: 0.9001 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 138 score: 0.9007 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 139 score: 0.9442 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 140 score: 0.8314 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 141 score: 0.8981 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 142 score: 0.9517 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 143 score: 0.9018 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 144 score: 0.8980 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 145 score: 0.9493 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 146 score: 0.8190 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 147 score: 0.8870 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 148 score: 0.9458 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 149 score: 0.9344 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 150 score: 0.9048 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 151 score: 0.8943 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 152 score: 0.8475 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 153 score: 0.8182 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 154 score: 0.7755 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 155 score: 0.9063 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 156 score: 0.9019 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 157 score: 0.8738 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 158 score: 0.9332 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 159 score: 0.8390 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 160 score: 0.9335 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 161 score: 0.8410 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 162 score: 0.8990 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 163 score: 0.8376 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 164 score: 0.9461 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 165 score: 0.7469 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 166 score: 0.8884 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 167 score: 0.6940 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 168 score: 0.9037 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 169 score: 0.7634 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 170 score: 0.8808 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 171 score: 0.9249 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 172 score: 0.8891 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 173 score: 0.8970 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 174 score: 0.9108 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 175 score: 0.9543 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 176 score: 0.8386 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 177 score: 0.9461 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 178 score: 0.7988 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 179 score: 0.8452 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 180 score: 0.9165 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 181 score: 0.9028 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 182 score: 0.8870 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 183 score: 0.9336 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 184 score: 0.9001 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 185 score: 0.9600 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 186 score: 0.9637 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 187 score: 0.9394 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 188 score: 0.8057 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 189 score: 0.9316 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 190 score: 0.8535 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 191 score: 0.9244 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 192 score: 0.9015 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 193 score: 0.7927 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 194 score: 0.8434 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 195 score: 0.8953 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 196 score: 0.9265 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 197 score: 0.8561 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 198 score: 0.9119 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 199 score: 0.8243 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 200 score: 0.8309 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 201 score: 0.6139 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 202 score: 0.8360 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 203 score: 0.6401 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 204 score: 0.9333 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 205 score: 0.9163 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 206 score: 0.8869 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 207 score: 0.9129 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 208 score: 0.8350 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 209 score: 0.9465 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 210 score: 0.9647 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 211 score: 0.8721 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 212 score: 0.7986 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 213 score: 0.7938 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 214 score: 0.9082 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 215 score: 0.9432 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 216 score: 0.8911 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 217 score: 0.9363 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 218 score: 0.8882 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 219 score: 0.9388 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 220 score: 0.9736 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 221 score: 0.9241 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 222 score: 0.9343 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 223 score: 0.9149 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 224 score: 0.9414 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 225 score: 0.9522 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 226 score: 0.8971 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 227 score: 0.8497 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 228 score: 0.9155 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 229 score: 0.8924 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 230 score: 0.9660 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 231 score: 0.8662 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 232 score: 0.8395 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 233 score: 0.8854 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 234 score: 0.8678 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 235 score: 0.8296 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 236 score: 0.8719 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 237 score: 0.8642 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 238 score: 0.9466 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 239 score: 0.9398 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 240 score: 0.8303 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 241 score: 0.8747 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 242 score: 0.9442 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 243 score: 0.7306 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 244 score: 0.8625 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 245 score: 0.8428 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 246 score: 0.6930 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 247 score: 0.7125 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 248 score: 0.8019 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 249 score: 0.9183 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 250 score: 0.9045 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 251 score: 0.9610 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 252 score: 0.9563 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 253 score: 0.8633 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 254 score: 0.7710 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 255 score: 0.9252 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 256 score: 0.8925 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 257 score: 0.9484 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 258 score: 0.9422 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 259 score: 0.9220 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 260 score: 0.9240 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 261 score: 0.9592 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 262 score: 0.5784 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 263 score: 0.8395 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 264 score: 0.9454 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 265 score: 0.9345 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 266 score: 0.8211 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 267 score: 0.9003 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 268 score: 0.9048 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 269 score: 0.9183 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 270 score: 0.9110 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 271 score: 0.8644 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 272 score: 0.9253 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 273 score: 0.8824 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 274 score: 0.7957 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 275 score: 0.7799 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 276 score: 0.8491 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 277 score: 0.9257 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 278 score: 0.9058 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 279 score: 0.8838 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 280 score: 0.9155 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 281 score: 0.8836 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 282 score: 0.9392 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 283 score: 0.8853 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 284 score: 0.9209 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 285 score: 0.9288 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 286 score: 0.9156 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 287 score: 0.8435 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 288 score: 0.9196 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 289 score: 0.9120 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 290 score: 0.7797 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 291 score: 0.9231 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 292 score: 0.9327 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 293 score: 0.9167 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 294 score: 0.7489 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 295 score: 0.8566 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 296 score: 0.8254 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 297 score: 0.9215 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 298 score: 0.7030 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 299 score: 0.8691 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 300 score: 0.9181 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 301 score: 0.8992 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 302 score: 0.8919 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 303 score: 0.9561 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 304 score: 0.9307 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 305 score: 0.9238 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 306 score: 0.9209 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 307 score: 0.8539 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 308 score: 0.9040 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 309 score: 0.8431 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 310 score: 0.9213 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 311 score: 0.9357 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 312 score: 0.9465 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 313 score: 0.7694 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 314 score: 0.9386 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 315 score: 0.9581 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 316 score: 0.9426 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 317 score: 0.9000 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 318 score: 0.7423 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 319 score: 0.5301 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 320 score: 0.7756 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 321 score: 0.8627 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 322 score: 0.9230 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 323 score: 0.9162 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 324 score: 0.9515 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 325 score: 0.9134 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 326 score: 0.7389 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 327 score: 0.8665 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 328 score: 0.9014 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 329 score: 0.8958 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 330 score: 0.9320 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 331 score: 0.9271 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 332 score: 0.9301 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 333 score: 0.9090 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 334 score: 0.9532 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 335 score: 0.9013 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 336 score: 0.8928 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 337 score: 0.7006 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 338 score: 0.9002 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 339 score: 0.9332 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 340 score: 0.8394 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 341 score: 0.8936 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 342 score: 0.7783 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 343 score: 0.8620 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 344 score: 0.8818 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 345 score: 0.8716 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 346 score: 0.9281 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 347 score: 0.8991 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 348 score: 0.7815 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 349 score: 0.8427 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 350 score: 0.8998 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 351 score: 0.9378 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 352 score: 0.9058 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 353 score: 0.9103 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 354 score: 0.9488 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 355 score: 0.8246 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 356 score: 0.9412 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 357 score: 0.8834 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 358 score: 0.7402 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 359 score: 0.8051 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 360 score: 0.6882 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 361 score: 0.9091 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 362 score: 0.9617 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 363 score: 0.6277 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 364 score: 0.9040 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 365 score: 0.8629 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 366 score: 0.8069 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 367 score: 0.8831 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 368 score: 0.7525 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 369 score: 0.8668 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 370 score: 0.8029 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 371 score: 0.8310 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 372 score: 0.9019 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 373 score: 0.8642 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 374 score: 0.9215 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 375 score: 0.9219 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 376 score: 0.9178 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 377 score: 0.9384 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 378 score: 0.8083 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 379 score: 0.8773 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 380 score: 0.9457 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 381 score: 0.7675 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 382 score: 0.8171 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 383 score: 0.6547 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 384 score: 0.8975 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 385 score: 0.8042 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 386 score: 0.8061 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 387 score: 0.9063 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 388 score: 0.7578 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 389 score: 0.8844 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 390 score: 0.9096 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 391 score: 0.8774 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 392 score: 0.9442 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 393 score: 0.9568 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 394 score: 0.9434 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 395 score: 0.9740 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 396 score: 0.7344 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 397 score: 0.9400 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 398 score: 0.8611 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 399 score: 0.9667 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 400 score: 0.9656 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 401 score: 0.8968 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 402 score: 0.9258 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 403 score: 0.8300 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 404 score: 0.7294 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 405 score: 0.8858 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 406 score: 0.9152 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 407 score: 0.8707 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 408 score: 0.9377 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 409 score: 0.8915 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 410 score: 0.9081 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 411 score: 0.8510 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 412 score: 0.9051 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 413 score: 0.9435 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 414 score: 0.6606 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 415 score: 0.8838 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 416 score: 0.7847 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 417 score: 0.8343 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 418 score: 0.9513 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 419 score: 0.9410 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 420 score: 0.9573 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 421 score: 0.9653 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 422 score: 0.9206 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 423 score: 0.8202 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 424 score: 0.8535 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 425 score: 0.9484 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 426 score: 0.9428 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 427 score: 0.9260 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 428 score: 0.9334 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 429 score: 0.9584 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 430 score: 0.9288 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 431 score: 0.8918 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 432 score: 0.7489 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 433 score: 0.7935 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 434 score: 0.8808 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 435 score: 0.8007 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 436 score: 0.8622 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 437 score: 0.7553 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 438 score: 0.9493 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 439 score: 0.8866 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 440 score: 0.9353 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 441 score: 0.9077 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 442 score: 0.9656 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 443 score: 0.9121 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 444 score: 0.8593 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 445 score: 0.8146 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 446 score: 0.9438 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 447 score: 0.9376 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 448 score: 0.9373 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 449 score: 0.9045 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 450 score: 0.8984 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 451 score: 0.9168 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 452 score: 0.9644 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 453 score: 0.8965 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 454 score: 0.9344 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 455 score: 0.8598 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 456 score: 0.8265 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 457 score: 0.9396 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 458 score: 0.9125 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 459 score: 0.7704 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 460 score: 0.9380 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 461 score: 0.9113 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 462 score: 0.8033 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 463 score: 0.9501 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 464 score: 0.9231 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 465 score: 0.9402 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 466 score: 0.9049 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 467 score: 0.7412 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 468 score: 0.8313 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 469 score: 0.6748 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 470 score: 0.8509 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 471 score: 0.8630 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 472 score: 0.8503 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 473 score: 0.8934 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 474 score: 0.8859 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 475 score: 0.9213 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 476 score: 0.9155 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 477 score: 0.6663 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 478 score: 0.9020 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 479 score: 0.9161 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 480 score: 0.8568 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 481 score: 0.8914 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 482 score: 0.8931 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 483 score: 0.9101 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 484 score: 0.9109 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 485 score: 0.8909 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 486 score: 0.8102 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 487 score: 0.9061 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 488 score: 0.9437 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 489 score: 0.9580 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 490 score: 0.8983 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 491 score: 0.9386 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 492 score: 0.9675 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 493 score: 0.9442 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 494 score: 0.8926 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 495 score: 0.8649 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 496 score: 0.8939 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 497 score: 0.8677 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 498 score: 0.9287 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 499 score: 0.9325 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 500 score: 0.9688 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 501 score: 0.9229 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 502 score: 0.9365 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 503 score: 0.8852 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 504 score: 0.8764 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 505 score: 0.8883 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 506 score: 0.8854 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 507 score: 0.9131 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 508 score: 0.5535 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 509 score: 0.8023 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 510 score: 0.8473 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 511 score: 0.7543 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 512 score: 0.9024 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 513 score: 0.8083 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 514 score: 0.9362 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 515 score: 0.9417 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 516 score: 0.8788 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 517 score: 0.9542 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 518 score: 0.8929 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 519 score: 0.9498 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 520 score: 0.8543 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 521 score: 0.9320 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 522 score: 0.8756 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 523 score: 0.8862 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 524 score: 0.9626 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 525 score: 0.9275 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 526 score: 0.9215 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 527 score: 0.9152 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 528 score: 0.9092 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 529 score: 0.8997 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 530 score: 0.8406 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 531 score: 0.9029 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 532 score: 0.8653 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 533 score: 0.8739 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 534 score: 0.7233 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 535 score: 0.7264 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 536 score: 0.8776 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 537 score: 0.8779 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 538 score: 0.8881 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 539 score: 0.9165 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 540 score: 0.9142 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 541 score: 0.8844 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 542 score: 0.9195 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 543 score: 0.9151 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 544 score: 0.9419 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 545 score: 0.9538 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 546 score: 0.7835 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 547 score: 0.7320 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 548 score: 0.9043 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 549 score: 0.9661 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 550 score: 0.8408 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 551 score: 0.9224 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 552 score: 0.9484 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 553 score: 0.8889 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 554 score: 0.9040 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 555 score: 0.9039 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 556 score: 0.8661 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 557 score: 0.8329 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 558 score: 0.6970 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 559 score: 0.8312 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 560 score: 0.8473 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 561 score: 0.9417 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 562 score: 0.8123 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 563 score: 0.8644 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 564 score: 0.8462 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 565 score: 0.9176 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 566 score: 0.9377 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 567 score: 0.9278 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 568 score: 0.8573 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 569 score: 0.8097 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 570 score: 0.9490 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 571 score: 0.8950 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 572 score: 0.7737 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 573 score: 0.9355 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 574 score: 0.9366 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 575 score: 0.9000 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 576 score: 0.6403 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 577 score: 0.8888 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 578 score: 0.9383 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 579 score: 0.8319 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 580 score: 0.9433 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 581 score: 0.8294 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 582 score: 0.9450 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 583 score: 0.9189 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 584 score: 0.7007 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 585 score: 0.9194 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 586 score: 0.9319 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 587 score: 0.9383 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 588 score: 0.8911 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 589 score: 0.8415 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 590 score: 0.8711 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 591 score: 0.9666 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 592 score: 0.8348 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 593 score: 0.9190 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 594 score: 0.9575 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 595 score: 0.9481 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 596 score: 0.8933 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 597 score: 0.9271 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 598 score: 0.9027 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 599 score: 0.9141 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 600 score: 0.9231 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 601 score: 0.6558 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 602 score: 0.9033 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 603 score: 0.8711 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 604 score: 0.8997 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 605 score: 0.9372 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 606 score: 0.9448 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 607 score: 0.8834 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 608 score: 0.8433 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 609 score: 0.9125 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 610 score: 0.9004 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 611 score: 0.9087 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 612 score: 0.8399 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 613 score: 0.9026 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 614 score: 0.9361 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 615 score: 0.7952 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 616 score: 0.9156 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 617 score: 0.9358 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 618 score: 0.9159 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 619 score: 0.9071 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 620 score: 0.9575 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 621 score: 0.8813 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 622 score: 0.9426 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 623 score: 0.9168 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 624 score: 0.7734 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 625 score: 0.9420 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 626 score: 0.9063 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 627 score: 0.9583 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 628 score: 0.9447 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 629 score: 0.9017 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 630 score: 0.8288 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 631 score: 0.9620 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 632 score: 0.9514 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 633 score: 0.9644 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 634 score: 0.9681 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 635 score: 0.9492 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 636 score: 0.9310 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 637 score: 0.8761 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 638 score: 0.9213 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 639 score: 0.9638 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 640 score: 0.9193 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 641 score: 0.9259 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 642 score: 0.9201 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 643 score: 0.8511 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 644 score: 0.8617 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 645 score: 0.8525 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 646 score: 0.7103 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 647 score: 0.9139 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 648 score: 0.7095 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 649 score: 0.9129 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 650 score: 0.9601 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 651 score: 0.9099 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 652 score: 0.9174 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 653 score: 0.6749 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 654 score: 0.8964 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 655 score: 0.8898 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 656 score: 0.8678 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 657 score: 0.7278 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 658 score: 0.7725 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 659 score: 0.8608 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 660 score: 0.8272 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 661 score: 0.9375 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 662 score: 0.9551 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 663 score: 0.9083 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 664 score: 0.9458 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 665 score: 0.8322 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 666 score: 0.9069 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 667 score: 0.7965 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 668 score: 0.9138 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 669 score: 0.9468 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 670 score: 0.8956 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 671 score: 0.8675 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 672 score: 0.9208 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 673 score: 0.8864 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 674 score: 0.9421 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 675 score: 0.9322 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 676 score: 0.9199 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 677 score: 0.9304 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 678 score: 0.9083 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 679 score: 0.9399 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 680 score: 0.8266 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 681 score: 0.9353 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 682 score: 0.8522 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 683 score: 0.8759 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 684 score: 0.7784 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 685 score: 0.8632 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 686 score: 0.8650 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 687 score: 0.9049 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 688 score: 0.9461 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 689 score: 0.9053 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 690 score: 0.9229 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 691 score: 0.8676 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 692 score: 0.8979 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 693 score: 0.8935 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 694 score: 0.9220 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 695 score: 0.8474 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 696 score: 0.9116 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 697 score: 0.8844 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 698 score: 0.7612 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 699 score: 0.9626 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 700 score: 0.9234 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 701 score: 0.9080 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 702 score: 0.9601 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 703 score: 0.8709 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 704 score: 0.9359 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 705 score: 0.8868 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 706 score: 0.7549 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 707 score: 0.9173 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 708 score: 0.8322 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 709 score: 0.9274 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 710 score: 0.9284 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 711 score: 0.8540 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 712 score: 0.9677 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 713 score: 0.9349 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 714 score: 0.8858 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 715 score: 0.8857 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 716 score: 0.9272 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 717 score: 0.9409 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 718 score: 0.9409 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 719 score: 0.9299 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 720 score: 0.9563 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 721 score: 0.9053 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 722 score: 0.9343 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 723 score: 0.9428 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 724 score: 0.8977 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 725 score: 0.8968 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 726 score: 0.8536 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 727 score: 0.8933 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 728 score: 0.7366 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 729 score: 0.9034 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 730 score: 0.8132 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 731 score: 0.8899 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 732 score: 0.9052 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 733 score: 0.9566 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 734 score: 0.9084 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 735 score: 0.8957 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 736 score: 0.8949 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 737 score: 0.8924 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 738 score: 0.9140 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 739 score: 0.9218 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 740 score: 0.9062 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 741 score: 0.9151 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 742 score: 0.8024 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 743 score: 0.9337 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 744 score: 0.9256 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 745 score: 0.9412 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 746 score: 0.9474 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 747 score: 0.9422 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 748 score: 0.9782 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 749 score: 0.9431 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 750 score: 0.9590 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 751 score: 0.8868 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 752 score: 0.9157 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 753 score: 0.8845 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 754 score: 0.9442 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 755 score: 0.9227 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 756 score: 0.8579 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 757 score: 0.8715 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 758 score: 0.9406 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 759 score: 0.9540 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 760 score: 0.9593 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 761 score: 0.9102 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 762 score: 0.9689 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 763 score: 0.9279 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 764 score: 0.7985 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 765 score: 0.8651 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 766 score: 0.9040 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 767 score: 0.8333 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 768 score: 0.9727 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 769 score: 0.9475 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 770 score: 0.9307 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 771 score: 0.9493 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 772 score: 0.9501 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 773 score: 0.9369 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 774 score: 0.8676 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 775 score: 0.8576 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 776 score: 0.8816 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 777 score: 0.9396 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 778 score: 0.8915 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 779 score: 0.8079 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 780 score: 0.8968 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 781 score: 0.8096 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 782 score: 0.9176 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 783 score: 0.8286 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 784 score: 0.9227 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 785 score: 0.8146 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 786 score: 0.7508 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 787 score: 0.9525 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 788 score: 0.9071 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 789 score: 0.9181 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 790 score: 0.9241 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 791 score: 0.8945 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 792 score: 0.8973 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 793 score: 0.8178 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 794 score: 0.9007 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 795 score: 0.9112 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 796 score: 0.9551 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 797 score: 0.8388 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 798 score: 0.9406 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 799 score: 0.8623 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 800 score: 0.8194 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 801 score: 0.7911 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 802 score: 0.9106 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 803 score: 0.8308 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 804 score: 0.7391 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 805 score: 0.9424 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 806 score: 0.8941 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 807 score: 0.9420 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 808 score: 0.9244 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 809 score: 0.9002 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 810 score: 0.9089 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 811 score: 0.7868 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 812 score: 0.9549 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 813 score: 0.9530 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 814 score: 0.9287 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 815 score: 0.7934 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 816 score: 0.8368 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 817 score: 0.8065 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 818 score: 0.8787 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 819 score: 0.7299 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 820 score: 0.9414 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 821 score: 0.9084 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 822 score: 0.9277 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 823 score: 0.9223 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 824 score: 0.9054 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 825 score: 0.6831 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 826 score: 0.9270 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 827 score: 0.7834 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 828 score: 0.8574 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 829 score: 0.7197 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 830 score: 0.8846 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 831 score: 0.9166 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 832 score: 0.9157 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 833 score: 0.8401 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 834 score: 0.8576 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 835 score: 0.8590 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 836 score: 0.8739 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 837 score: 0.8292 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 838 score: 0.8557 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 839 score: 0.8844 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 840 score: 0.9305 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 841 score: 0.8245 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 842 score: 0.7771 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 843 score: 0.8575 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 844 score: 0.7477 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 845 score: 0.8054 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 846 score: 0.6365 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 847 score: 0.8779 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 848 score: 0.7721 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 849 score: 0.9121 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 850 score: 0.8488 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 851 score: 0.9610 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 852 score: 0.9459 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 853 score: 0.8714 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 854 score: 0.8571 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 855 score: 0.7703 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 856 score: 0.8184 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 857 score: 0.9218 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 858 score: 0.8650 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 859 score: 0.9082 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 860 score: 0.8734 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 861 score: 0.9265 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 862 score: 0.9424 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 863 score: 0.8883 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 864 score: 0.8734 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 865 score: 0.8779 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 866 score: 0.9164 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 867 score: 0.8563 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 868 score: 0.6417 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 869 score: 0.8519 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 870 score: 0.8911 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 871 score: 0.8609 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 872 score: 0.8991 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 873 score: 0.8787 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 874 score: 0.9270 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 875 score: 0.7277 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 876 score: 0.8039 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 877 score: 0.8979 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 878 score: 0.9592 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 879 score: 0.8391 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 880 score: 0.9055 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 881 score: 0.9435 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 882 score: 0.9344 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 883 score: 0.8857 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 884 score: 0.8507 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 885 score: 0.7867 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 886 score: 0.8936 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 887 score: 0.8193 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 888 score: 0.8606 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 889 score: 0.9087 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 890 score: 0.7657 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 891 score: 0.8790 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 892 score: 0.8398 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 893 score: 0.7686 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 894 score: 0.8952 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 895 score: 0.9363 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 896 score: 0.6815 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 897 score: 0.8348 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 898 score: 0.8969 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 899 score: 0.9140 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 900 score: 0.9131 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 901 score: 0.8937 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 902 score: 0.8816 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 903 score: 0.9374 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 904 score: 0.9502 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 905 score: 0.9022 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 906 score: 0.8804 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 907 score: 0.9178 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 908 score: 0.8924 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 909 score: 0.9527 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 910 score: 0.8923 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 911 score: 0.8312 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 912 score: 0.9330 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 913 score: 0.9026 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 914 score: 0.8694 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 915 score: 0.9166 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 916 score: 0.9371 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 917 score: 0.9278 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 918 score: 0.8600 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 919 score: 0.9083 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 920 score: 0.8921 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 921 score: 0.9084 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 922 score: 0.9292 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 923 score: 0.9288 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 924 score: 0.8960 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 925 score: 0.9037 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 926 score: 0.9603 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 927 score: 0.6620 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 928 score: 0.9169 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 929 score: 0.9053 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 930 score: 0.9078 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 931 score: 0.8192 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 932 score: 0.7325 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 933 score: 0.8496 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 934 score: 0.8469 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 935 score: 0.8873 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 936 score: 0.8595 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 937 score: 0.9768 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 938 score: 0.9390 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 939 score: 0.9293 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 940 score: 0.9613 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 941 score: 0.9791 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 942 score: 0.9415 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 943 score: 0.8671 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 944 score: 0.7274 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 945 score: 0.8995 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 946 score: 0.7062 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 947 score: 0.7705 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 948 score: 0.8886 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 949 score: 0.9413 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 950 score: 0.8604 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 951 score: 0.9367 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 952 score: 0.7963 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 953 score: 0.8907 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 954 score: 0.7172 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 955 score: 0.9615 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 956 score: 0.9337 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 957 score: 0.9316 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 958 score: 0.9300 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 959 score: 0.9265 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 960 score: 0.7806 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 961 score: 0.5667 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 962 score: 0.9313 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 963 score: 0.9514 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 964 score: 0.9533 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 965 score: 0.9018 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 966 score: 0.8759 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 967 score: 0.8919 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 968 score: 0.9272 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 969 score: 0.7990 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 970 score: 0.9095 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 971 score: 0.8097 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 972 score: 0.7681 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 973 score: 0.9356 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 974 score: 0.9182 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 975 score: 0.9373 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 976 score: 0.9188 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 977 score: 0.7415 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 978 score: 0.8967 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 979 score: 0.9090 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 980 score: 0.8616 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 981 score: 0.9226 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 982 score: 0.9179 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 983 score: 0.8754 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 984 score: 0.9350 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 985 score: 0.9240 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 986 score: 0.8325 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 987 score: 0.9284 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 988 score: 0.8521 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 989 score: 0.5516 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 990 score: 0.9131 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 991 score: 0.8613 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 992 score: 0.9149 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 993 score: 0.9119 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 994 score: 0.9460 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 995 score: 0.9256 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 996 score: 0.9601 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 997 score: 0.9544 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 998 score: 0.9479 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 999 score: 0.9163 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1000 score: 0.9049 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1001 score: 0.8858 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1002 score: 0.8947 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1003 score: 0.8278 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1004 score: 0.9266 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1005 score: 0.9237 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1006 score: 0.9350 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1007 score: 0.9200 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1008 score: 0.9278 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1009 score: 0.8984 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1010 score: 0.9057 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg Segment 1011 score: 0.8992 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-bg-max-tokens-512//test-en-bg score: 0.8821