diff --git "a/test-en-pl.comet" "b/test-en-pl.comet" new file mode 100644--- /dev/null +++ "b/test-en-pl.comet" @@ -0,0 +1,1013 @@ +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 0 score: 0.8490 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1 score: 0.9065 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 2 score: 0.9164 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 3 score: 0.8919 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 4 score: 0.8557 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 5 score: 0.8382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 6 score: 0.6104 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 7 score: 0.9210 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 8 score: 0.8263 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 9 score: 0.8069 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 10 score: 0.9087 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 11 score: 0.8690 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 12 score: 0.9012 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 13 score: 0.8509 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 14 score: 0.8583 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 15 score: 0.7813 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 16 score: 0.8762 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 17 score: 0.9538 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 18 score: 0.9185 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 19 score: 0.9081 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 20 score: 0.9661 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 21 score: 0.9156 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 22 score: 0.8734 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 23 score: 0.9093 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 24 score: 0.9515 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 25 score: 0.9273 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 26 score: 0.9284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 27 score: 0.8318 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 28 score: 0.7912 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 29 score: 0.9364 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 30 score: 0.8067 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 31 score: 0.8079 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 32 score: 0.8591 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 33 score: 0.8939 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 34 score: 0.9015 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 35 score: 0.9383 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 36 score: 0.9087 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 37 score: 0.8647 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 38 score: 0.8395 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 39 score: 0.8409 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 40 score: 0.7999 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 41 score: 0.9340 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 42 score: 0.9128 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 43 score: 0.8136 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 44 score: 0.8979 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 45 score: 0.9368 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 46 score: 0.9441 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 47 score: 0.9234 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 48 score: 0.8514 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 49 score: 0.9283 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 50 score: 0.9024 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 51 score: 0.9252 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 52 score: 0.9520 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 53 score: 0.9673 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 54 score: 0.9317 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 55 score: 0.9331 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 56 score: 0.9359 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 57 score: 0.7616 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 58 score: 0.8793 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 59 score: 0.9518 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 60 score: 0.9459 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 61 score: 0.9406 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 62 score: 0.8856 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 63 score: 0.9456 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 64 score: 0.9078 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 65 score: 0.7853 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 66 score: 0.7987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 67 score: 0.6862 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 68 score: 0.9548 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 69 score: 0.8310 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 70 score: 0.8820 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 71 score: 0.8164 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 72 score: 0.8600 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 73 score: 0.7241 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 74 score: 0.9240 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 75 score: 0.8781 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 76 score: 0.8035 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 77 score: 0.9153 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 78 score: 0.9322 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 79 score: 0.9562 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 80 score: 0.7661 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 81 score: 0.9214 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 82 score: 0.8838 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 83 score: 0.8151 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 84 score: 0.8311 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 85 score: 0.8460 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 86 score: 0.7830 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 87 score: 0.8280 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 88 score: 0.8987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 89 score: 0.9421 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 90 score: 0.8658 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 91 score: 0.8706 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 92 score: 0.8654 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 93 score: 0.9265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 94 score: 0.9078 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 95 score: 0.9562 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 96 score: 0.8762 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 97 score: 0.8636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 98 score: 0.9337 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 99 score: 0.8124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 100 score: 0.7670 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 101 score: 0.8817 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 102 score: 0.9360 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 103 score: 0.9564 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 104 score: 0.9467 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 105 score: 0.7707 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 106 score: 0.9412 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 107 score: 0.8867 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 108 score: 0.7200 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 109 score: 0.8576 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 110 score: 0.8616 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 111 score: 0.9662 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 112 score: 0.9694 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 113 score: 0.9459 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 114 score: 0.8728 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 115 score: 0.9257 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 116 score: 0.9289 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 117 score: 0.9309 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 118 score: 0.9778 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 119 score: 0.9347 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 120 score: 0.9050 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 121 score: 0.8962 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 122 score: 0.9330 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 123 score: 0.9740 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 124 score: 0.9505 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 125 score: 0.9309 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 126 score: 0.8641 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 127 score: 0.8832 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 128 score: 0.8665 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 129 score: 0.9513 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 130 score: 0.9161 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 131 score: 0.9329 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 132 score: 0.9329 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 133 score: 0.9736 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 134 score: 0.8239 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 135 score: 0.8949 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 136 score: 0.9396 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 137 score: 0.8901 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 138 score: 0.9077 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 139 score: 0.7502 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 140 score: 0.9009 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 141 score: 0.9397 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 142 score: 0.9654 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 143 score: 0.9000 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 144 score: 0.8851 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 145 score: 0.9457 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 146 score: 0.8666 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 147 score: 0.9312 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 148 score: 0.7709 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 149 score: 0.9185 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 150 score: 0.9285 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 151 score: 0.8663 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 152 score: 0.8847 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 153 score: 0.8084 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 154 score: 0.5202 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 155 score: 0.9148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 156 score: 0.9077 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 157 score: 0.8722 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 158 score: 0.9357 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 159 score: 0.8183 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 160 score: 0.8702 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 161 score: 0.8457 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 162 score: 0.8790 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 163 score: 0.9355 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 164 score: 0.9606 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 165 score: 0.7907 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 166 score: 0.9151 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 167 score: 0.6198 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 168 score: 0.8625 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 169 score: 0.8717 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 170 score: 0.8791 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 171 score: 0.8788 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 172 score: 0.8547 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 173 score: 0.8900 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 174 score: 0.9099 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 175 score: 0.9124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 176 score: 0.8733 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 177 score: 0.8882 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 178 score: 0.8416 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 179 score: 0.9297 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 180 score: 0.8869 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 181 score: 0.9288 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 182 score: 0.9129 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 183 score: 0.9407 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 184 score: 0.8564 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 185 score: 0.8945 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 186 score: 0.9429 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 187 score: 0.9076 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 188 score: 0.8601 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 189 score: 0.9112 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 190 score: 0.8441 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 191 score: 0.9368 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 192 score: 0.8346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 193 score: 0.8028 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 194 score: 0.8060 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 195 score: 0.9172 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 196 score: 0.9427 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 197 score: 0.8724 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 198 score: 0.9267 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 199 score: 0.7005 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 200 score: 0.8291 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 201 score: 0.8539 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 202 score: 0.8619 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 203 score: 0.7142 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 204 score: 0.8968 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 205 score: 0.9194 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 206 score: 0.8508 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 207 score: 0.9210 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 208 score: 0.9235 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 209 score: 0.8964 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 210 score: 0.9776 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 211 score: 0.9088 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 212 score: 0.9173 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 213 score: 0.9194 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 214 score: 0.9161 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 215 score: 0.9139 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 216 score: 0.8695 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 217 score: 0.9067 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 218 score: 0.9346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 219 score: 0.9112 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 220 score: 0.9541 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 221 score: 0.8880 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 222 score: 0.9264 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 223 score: 0.9128 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 224 score: 0.9057 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 225 score: 0.9609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 226 score: 0.9072 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 227 score: 0.7842 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 228 score: 0.9313 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 229 score: 0.8699 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 230 score: 0.9613 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 231 score: 0.8606 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 232 score: 0.8854 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 233 score: 0.8269 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 234 score: 0.8707 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 235 score: 0.9114 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 236 score: 0.9226 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 237 score: 0.8576 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 238 score: 0.9573 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 239 score: 0.8875 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 240 score: 0.8525 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 241 score: 0.8836 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 242 score: 0.9211 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 243 score: 0.8598 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 244 score: 0.8574 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 245 score: 0.8528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 246 score: 0.7513 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 247 score: 0.8063 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 248 score: 0.8308 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 249 score: 0.9495 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 250 score: 0.9084 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 251 score: 0.9514 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 252 score: 0.9201 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 253 score: 0.9314 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 254 score: 0.9125 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 255 score: 0.9158 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 256 score: 0.7480 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 257 score: 0.9438 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 258 score: 0.8972 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 259 score: 0.9019 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 260 score: 0.9515 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 261 score: 0.8988 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 262 score: 0.8321 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 263 score: 0.9264 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 264 score: 0.9302 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 265 score: 0.9244 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 266 score: 0.9077 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 267 score: 0.8233 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 268 score: 0.9179 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 269 score: 0.9402 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 270 score: 0.9479 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 271 score: 0.8564 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 272 score: 0.9058 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 273 score: 0.8228 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 274 score: 0.7762 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 275 score: 0.8369 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 276 score: 0.7953 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 277 score: 0.9748 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 278 score: 0.9356 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 279 score: 0.6506 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 280 score: 0.9526 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 281 score: 0.9409 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 282 score: 0.9288 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 283 score: 0.9373 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 284 score: 0.8937 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 285 score: 0.9585 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 286 score: 0.9325 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 287 score: 0.7246 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 288 score: 0.9420 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 289 score: 0.9092 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 290 score: 0.9009 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 291 score: 0.8696 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 292 score: 0.9325 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 293 score: 0.9501 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 294 score: 0.8468 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 295 score: 0.7987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 296 score: 0.9355 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 297 score: 0.9543 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 298 score: 0.9049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 299 score: 0.9140 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 300 score: 0.9464 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 301 score: 0.8426 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 302 score: 0.9033 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 303 score: 0.9638 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 304 score: 0.8630 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 305 score: 0.9102 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 306 score: 0.8580 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 307 score: 0.9326 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 308 score: 0.8818 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 309 score: 0.8211 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 310 score: 0.9270 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 311 score: 0.8885 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 312 score: 0.8748 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 313 score: 0.6865 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 314 score: 0.9616 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 315 score: 0.9585 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 316 score: 0.9176 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 317 score: 0.9110 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 318 score: 0.8629 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 319 score: 0.5150 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 320 score: 0.8456 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 321 score: 0.2396 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 322 score: 0.9181 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 323 score: 0.9163 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 324 score: 0.9100 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 325 score: 0.8263 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 326 score: 0.8704 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 327 score: 0.8929 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 328 score: 0.8922 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 329 score: 0.9131 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 330 score: 0.9437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 331 score: 0.9107 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 332 score: 0.9557 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 333 score: 0.9429 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 334 score: 0.9177 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 335 score: 0.9032 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 336 score: 0.8933 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 337 score: 0.7463 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 338 score: 0.9253 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 339 score: 0.9335 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 340 score: 0.8023 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 341 score: 0.8706 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 342 score: 0.7390 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 343 score: 0.8288 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 344 score: 0.8507 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 345 score: 0.9236 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 346 score: 0.8983 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 347 score: 0.9514 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 348 score: 0.8275 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 349 score: 0.8508 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 350 score: 0.8085 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 351 score: 0.9227 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 352 score: 0.9221 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 353 score: 0.9599 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 354 score: 0.8380 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 355 score: 0.8693 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 356 score: 0.9368 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 357 score: 0.7375 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 358 score: 0.6214 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 359 score: 0.8629 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 360 score: 0.7854 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 361 score: 0.7795 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 362 score: 0.9111 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 363 score: 0.8864 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 364 score: 0.9593 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 365 score: 0.8087 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 366 score: 0.8105 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 367 score: 0.8750 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 368 score: 0.8324 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 369 score: 0.8832 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 370 score: 0.8725 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 371 score: 0.8420 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 372 score: 0.8902 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 373 score: 0.8159 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 374 score: 0.9324 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 375 score: 0.8982 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 376 score: 0.9448 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 377 score: 0.9563 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 378 score: 0.9178 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 379 score: 0.8767 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 380 score: 0.9431 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 381 score: 0.8549 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 382 score: 0.6284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 383 score: 0.7593 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 384 score: 0.8172 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 385 score: 0.8281 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 386 score: 0.8979 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 387 score: 0.9333 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 388 score: 0.8180 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 389 score: 0.8926 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 390 score: 0.9172 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 391 score: 0.9443 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 392 score: 0.9328 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 393 score: 0.9186 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 394 score: 0.9459 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 395 score: 0.9284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 396 score: 0.8291 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 397 score: 0.9559 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 398 score: 0.8817 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 399 score: 0.8502 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 400 score: 0.9140 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 401 score: 0.7392 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 402 score: 0.9271 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 403 score: 0.8343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 404 score: 0.8034 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 405 score: 0.8423 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 406 score: 0.8920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 407 score: 0.8382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 408 score: 0.9415 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 409 score: 0.9241 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 410 score: 0.9313 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 411 score: 0.8914 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 412 score: 0.8399 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 413 score: 0.9636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 414 score: 0.9062 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 415 score: 0.9387 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 416 score: 0.8401 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 417 score: 0.8307 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 418 score: 0.9264 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 419 score: 0.9003 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 420 score: 0.9207 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 421 score: 0.9409 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 422 score: 0.9349 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 423 score: 0.9130 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 424 score: 0.9085 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 425 score: 0.9525 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 426 score: 0.9317 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 427 score: 0.9275 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 428 score: 0.8935 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 429 score: 0.9517 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 430 score: 0.8648 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 431 score: 0.7938 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 432 score: 0.8620 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 433 score: 0.8701 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 434 score: 0.9057 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 435 score: 0.7841 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 436 score: 0.8856 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 437 score: 0.9118 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 438 score: 0.9238 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 439 score: 0.8760 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 440 score: 0.9303 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 441 score: 0.8982 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 442 score: 0.9783 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 443 score: 0.9116 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 444 score: 0.8365 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 445 score: 0.6146 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 446 score: 0.9189 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 447 score: 0.9536 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 448 score: 0.9440 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 449 score: 0.8866 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 450 score: 0.9346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 451 score: 0.8841 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 452 score: 0.8932 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 453 score: 0.9201 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 454 score: 0.9209 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 455 score: 0.8802 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 456 score: 0.7885 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 457 score: 0.9591 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 458 score: 0.9331 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 459 score: 0.8960 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 460 score: 0.9164 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 461 score: 0.9068 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 462 score: 0.7691 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 463 score: 0.9626 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 464 score: 0.9361 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 465 score: 0.8978 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 466 score: 0.9165 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 467 score: 0.6691 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 468 score: 0.8162 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 469 score: 0.6643 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 470 score: 0.6927 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 471 score: 0.6912 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 472 score: 0.7839 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 473 score: 0.6198 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 474 score: 0.7184 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 475 score: 0.9385 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 476 score: 0.8929 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 477 score: 0.9317 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 478 score: 0.9008 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 479 score: 0.9295 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 480 score: 0.8397 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 481 score: 0.8640 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 482 score: 0.8924 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 483 score: 0.8697 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 484 score: 0.8890 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 485 score: 0.9218 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 486 score: 0.9097 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 487 score: 0.9175 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 488 score: 0.9075 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 489 score: 0.9509 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 490 score: 0.8966 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 491 score: 0.9407 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 492 score: 0.9702 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 493 score: 0.9135 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 494 score: 0.6280 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 495 score: 0.9254 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 496 score: 0.9234 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 497 score: 0.8370 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 498 score: 0.9060 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 499 score: 0.8894 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 500 score: 0.9339 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 501 score: 0.9394 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 502 score: 0.9188 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 503 score: 0.8677 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 504 score: 0.8054 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 505 score: 0.8147 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 506 score: 0.7873 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 507 score: 0.8621 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 508 score: 0.5878 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 509 score: 0.8820 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 510 score: 0.6400 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 511 score: 0.7776 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 512 score: 0.9504 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 513 score: 0.8839 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 514 score: 0.9064 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 515 score: 0.9538 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 516 score: 0.8641 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 517 score: 0.9304 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 518 score: 0.7697 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 519 score: 0.9496 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 520 score: 0.9304 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 521 score: 0.9383 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 522 score: 0.9314 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 523 score: 0.8266 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 524 score: 0.9505 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 525 score: 0.9073 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 526 score: 0.8486 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 527 score: 0.7142 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 528 score: 0.8423 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 529 score: 0.8371 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 530 score: 0.8882 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 531 score: 0.8254 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 532 score: 0.9046 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 533 score: 0.9157 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 534 score: 0.8493 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 535 score: 0.7556 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 536 score: 0.8299 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 537 score: 0.8815 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 538 score: 0.8983 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 539 score: 0.9407 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 540 score: 0.9251 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 541 score: 0.9364 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 542 score: 0.8785 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 543 score: 0.9131 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 544 score: 0.8645 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 545 score: 0.9493 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 546 score: 0.8369 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 547 score: 0.8823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 548 score: 0.8989 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 549 score: 0.9403 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 550 score: 0.9279 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 551 score: 0.9154 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 552 score: 0.8860 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 553 score: 0.9368 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 554 score: 0.9178 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 555 score: 0.8542 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 556 score: 0.8390 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 557 score: 0.8783 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 558 score: 0.8187 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 559 score: 0.6838 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 560 score: 0.8157 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 561 score: 0.9198 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 562 score: 0.8129 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 563 score: 0.7924 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 564 score: 0.8580 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 565 score: 0.9343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 566 score: 0.9127 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 567 score: 0.9443 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 568 score: 0.8067 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 569 score: 0.8912 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 570 score: 0.9399 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 571 score: 0.9023 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 572 score: 0.8487 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 573 score: 0.9520 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 574 score: 0.9609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 575 score: 0.8658 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 576 score: 0.9305 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 577 score: 0.9141 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 578 score: 0.9347 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 579 score: 0.9166 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 580 score: 0.8610 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 581 score: 0.8862 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 582 score: 0.8795 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 583 score: 0.8129 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 584 score: 0.7076 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 585 score: 0.9080 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 586 score: 0.9281 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 587 score: 0.9419 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 588 score: 0.8499 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 589 score: 0.9576 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 590 score: 0.9428 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 591 score: 0.9442 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 592 score: 0.7262 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 593 score: 0.8826 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 594 score: 0.9441 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 595 score: 0.9465 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 596 score: 0.9219 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 597 score: 0.9037 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 598 score: 0.7457 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 599 score: 0.9428 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 600 score: 0.8882 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 601 score: 0.8226 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 602 score: 0.8887 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 603 score: 0.9288 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 604 score: 0.9538 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 605 score: 0.9370 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 606 score: 0.9435 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 607 score: 0.7303 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 608 score: 0.8010 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 609 score: 0.9238 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 610 score: 0.9053 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 611 score: 0.9417 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 612 score: 0.8808 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 613 score: 0.8706 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 614 score: 0.9246 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 615 score: 0.8633 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 616 score: 0.9224 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 617 score: 0.9246 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 618 score: 0.9196 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 619 score: 0.8064 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 620 score: 0.9533 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 621 score: 0.7716 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 622 score: 0.9364 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 623 score: 0.8662 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 624 score: 0.9419 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 625 score: 0.9074 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 626 score: 0.9517 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 627 score: 0.9158 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 628 score: 0.8933 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 629 score: 0.7853 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 630 score: 0.9104 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 631 score: 0.9413 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 632 score: 0.8871 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 633 score: 0.8942 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 634 score: 0.9644 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 635 score: 0.9476 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 636 score: 0.8939 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 637 score: 0.8722 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 638 score: 0.7328 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 639 score: 0.9422 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 640 score: 0.8837 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 641 score: 0.9528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 642 score: 0.7904 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 643 score: 0.8488 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 644 score: 0.8324 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 645 score: 0.7673 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 646 score: 0.8047 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 647 score: 0.8514 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 648 score: 0.8623 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 649 score: 0.8542 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 650 score: 0.9283 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 651 score: 0.8689 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 652 score: 0.7706 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 653 score: 0.8353 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 654 score: 0.9195 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 655 score: 0.9312 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 656 score: 0.8942 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 657 score: 0.9330 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 658 score: 0.8235 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 659 score: 0.8685 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 660 score: 0.7595 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 661 score: 0.9189 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 662 score: 0.9314 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 663 score: 0.8616 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 664 score: 0.9361 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 665 score: 0.9024 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 666 score: 0.8542 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 667 score: 0.7550 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 668 score: 0.9024 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 669 score: 0.9124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 670 score: 0.9035 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 671 score: 0.9418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 672 score: 0.9569 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 673 score: 0.9281 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 674 score: 0.9121 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 675 score: 0.9210 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 676 score: 0.9197 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 677 score: 0.9261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 678 score: 0.9388 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 679 score: 0.9515 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 680 score: 0.8658 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 681 score: 0.9292 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 682 score: 0.9120 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 683 score: 0.9046 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 684 score: 0.9152 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 685 score: 0.8644 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 686 score: 0.9227 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 687 score: 0.9027 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 688 score: 0.8541 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 689 score: 0.8739 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 690 score: 0.9491 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 691 score: 0.8962 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 692 score: 0.9509 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 693 score: 0.8125 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 694 score: 0.9033 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 695 score: 0.9216 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 696 score: 0.9183 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 697 score: 0.9441 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 698 score: 0.8342 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 699 score: 0.9418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 700 score: 0.7462 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 701 score: 0.9430 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 702 score: 0.9055 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 703 score: 0.8914 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 704 score: 0.8701 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 705 score: 0.8933 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 706 score: 0.7207 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 707 score: 0.8892 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 708 score: 0.9232 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 709 score: 0.9348 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 710 score: 0.8888 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 711 score: 0.8737 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 712 score: 0.9025 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 713 score: 0.9321 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 714 score: 0.9174 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 715 score: 0.8751 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 716 score: 0.9320 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 717 score: 0.9091 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 718 score: 0.9459 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 719 score: 0.9034 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 720 score: 0.8650 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 721 score: 0.9669 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 722 score: 0.9265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 723 score: 0.9173 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 724 score: 0.9316 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 725 score: 0.9217 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 726 score: 0.8452 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 727 score: 0.9159 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 728 score: 0.8053 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 729 score: 0.8004 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 730 score: 0.8105 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 731 score: 0.9148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 732 score: 0.8715 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 733 score: 0.9353 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 734 score: 0.8584 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 735 score: 0.9043 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 736 score: 0.8606 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 737 score: 0.8774 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 738 score: 0.8411 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 739 score: 0.9475 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 740 score: 0.9317 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 741 score: 0.8668 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 742 score: 0.8956 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 743 score: 0.9059 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 744 score: 0.9139 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 745 score: 0.9021 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 746 score: 0.9189 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 747 score: 0.8646 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 748 score: 0.9637 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 749 score: 0.9499 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 750 score: 0.8948 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 751 score: 0.9157 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 752 score: 0.8797 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 753 score: 0.9090 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 754 score: 0.9476 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 755 score: 0.9569 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 756 score: 0.8896 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 757 score: 0.8772 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 758 score: 0.9179 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 759 score: 0.9429 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 760 score: 0.9283 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 761 score: 0.9177 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 762 score: 0.9435 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 763 score: 0.8880 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 764 score: 0.9277 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 765 score: 0.8991 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 766 score: 0.9063 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 767 score: 0.8711 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 768 score: 0.9239 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 769 score: 0.9246 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 770 score: 0.9366 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 771 score: 0.9554 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 772 score: 0.9175 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 773 score: 0.9137 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 774 score: 0.8490 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 775 score: 0.8812 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 776 score: 0.9105 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 777 score: 0.8975 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 778 score: 0.9251 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 779 score: 0.6257 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 780 score: 0.8180 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 781 score: 0.8402 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 782 score: 0.8991 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 783 score: 0.9116 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 784 score: 0.9165 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 785 score: 0.7564 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 786 score: 0.8698 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 787 score: 0.8959 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 788 score: 0.9328 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 789 score: 0.9327 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 790 score: 0.9417 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 791 score: 0.8911 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 792 score: 0.9313 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 793 score: 0.8515 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 794 score: 0.8774 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 795 score: 0.8722 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 796 score: 0.9538 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 797 score: 0.8921 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 798 score: 0.8709 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 799 score: 0.7481 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 800 score: 0.9308 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 801 score: 0.8927 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 802 score: 0.9187 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 803 score: 0.8201 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 804 score: 0.6896 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 805 score: 0.8733 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 806 score: 0.9258 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 807 score: 0.9430 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 808 score: 0.8963 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 809 score: 0.9012 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 810 score: 0.8171 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 811 score: 0.8176 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 812 score: 0.9242 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 813 score: 0.7693 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 814 score: 0.8676 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 815 score: 0.7903 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 816 score: 0.8473 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 817 score: 0.8337 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 818 score: 0.8269 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 819 score: 0.8603 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 820 score: 0.9414 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 821 score: 0.6811 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 822 score: 0.7816 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 823 score: 0.9059 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 824 score: 0.8836 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 825 score: 0.8548 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 826 score: 0.9176 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 827 score: 0.9101 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 828 score: 0.9310 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 829 score: 0.8747 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 830 score: 0.8658 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 831 score: 0.8406 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 832 score: 0.8931 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 833 score: 0.6333 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 834 score: 0.8760 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 835 score: 0.8219 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 836 score: 0.7293 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 837 score: 0.8803 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 838 score: 0.8748 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 839 score: 0.9313 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 840 score: 0.8817 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 841 score: 0.8782 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 842 score: 0.8083 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 843 score: 0.9162 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 844 score: 0.7185 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 845 score: 0.7987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 846 score: 0.6967 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 847 score: 0.9187 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 848 score: 0.8007 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 849 score: 0.5937 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 850 score: 0.8861 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 851 score: 0.9026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 852 score: 0.8747 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 853 score: 0.8542 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 854 score: 0.7273 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 855 score: 0.8412 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 856 score: 0.7702 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 857 score: 0.9436 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 858 score: 0.9407 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 859 score: 0.9710 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 860 score: 0.9214 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 861 score: 0.9128 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 862 score: 0.8775 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 863 score: 0.9416 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 864 score: 0.8063 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 865 score: 0.8639 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 866 score: 0.8968 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 867 score: 0.8804 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 868 score: 0.9026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 869 score: 0.9041 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 870 score: 0.8693 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 871 score: 0.9321 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 872 score: 0.9520 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 873 score: 0.9485 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 874 score: 0.9412 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 875 score: 0.9011 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 876 score: 0.8812 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 877 score: 0.9135 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 878 score: 0.9655 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 879 score: 0.8415 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 880 score: 0.8910 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 881 score: 0.9080 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 882 score: 0.9136 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 883 score: 0.9469 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 884 score: 0.6868 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 885 score: 0.8956 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 886 score: 0.8984 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 887 score: 0.8535 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 888 score: 0.7619 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 889 score: 0.8117 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 890 score: 0.7892 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 891 score: 0.8581 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 892 score: 0.6481 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 893 score: 0.8386 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 894 score: 0.9250 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 895 score: 0.9078 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 896 score: 0.9269 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 897 score: 0.9002 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 898 score: 0.9393 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 899 score: 0.9101 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 900 score: 0.8794 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 901 score: 0.8919 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 902 score: 0.9248 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 903 score: 0.8670 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 904 score: 0.9187 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 905 score: 0.9034 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 906 score: 0.8597 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 907 score: 0.8604 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 908 score: 0.9304 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 909 score: 0.9437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 910 score: 0.8734 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 911 score: 0.8845 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 912 score: 0.9144 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 913 score: 0.7365 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 914 score: 0.9437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 915 score: 0.8732 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 916 score: 0.9064 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 917 score: 0.9121 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 918 score: 0.9258 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 919 score: 0.9055 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 920 score: 0.8234 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 921 score: 0.6751 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 922 score: 0.9049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 923 score: 0.9148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 924 score: 0.9196 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 925 score: 0.6743 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 926 score: 0.9374 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 927 score: 0.6988 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 928 score: 0.9314 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 929 score: 0.9129 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 930 score: 0.9035 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 931 score: 0.9202 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 932 score: 0.8870 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 933 score: 0.9390 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 934 score: 0.8647 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 935 score: 0.8717 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 936 score: 0.9241 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 937 score: 0.9468 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 938 score: 0.9639 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 939 score: 0.9303 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 940 score: 0.9506 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 941 score: 0.9455 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 942 score: 0.9257 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 943 score: 0.9263 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 944 score: 0.8877 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 945 score: 0.8443 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 946 score: 0.9272 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 947 score: 0.9383 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 948 score: 0.8764 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 949 score: 0.9091 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 950 score: 0.8698 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 951 score: 0.8300 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 952 score: 0.8565 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 953 score: 0.9166 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 954 score: 0.5512 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 955 score: 0.9566 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 956 score: 0.9377 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 957 score: 0.9396 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 958 score: 0.9085 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 959 score: 0.8573 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 960 score: 0.7490 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 961 score: 0.8655 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 962 score: 0.9349 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 963 score: 0.9102 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 964 score: 0.9448 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 965 score: 0.8690 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 966 score: 0.9038 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 967 score: 0.7704 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 968 score: 0.8814 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 969 score: 0.7256 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 970 score: 0.8826 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 971 score: 0.7634 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 972 score: 0.6169 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 973 score: 0.7014 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 974 score: 0.8909 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 975 score: 0.9216 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 976 score: 0.8190 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 977 score: 0.6975 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 978 score: 0.9569 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 979 score: 0.9088 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 980 score: 0.8323 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 981 score: 0.8590 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 982 score: 0.9244 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 983 score: 0.8616 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 984 score: 0.9310 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 985 score: 0.7740 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 986 score: 0.9322 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 987 score: 0.8846 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 988 score: 0.8951 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 989 score: 0.6858 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 990 score: 0.9569 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 991 score: 0.7901 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 992 score: 0.9165 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 993 score: 0.8539 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 994 score: 0.9339 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 995 score: 0.9134 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 996 score: 0.9507 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 997 score: 0.9479 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 998 score: 0.8483 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 999 score: 0.8720 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1000 score: 0.9547 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1001 score: 0.8717 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1002 score: 0.7913 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1003 score: 0.8876 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1004 score: 0.8334 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1005 score: 0.9103 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1006 score: 0.8445 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1007 score: 0.9231 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1008 score: 0.9275 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1009 score: 0.8848 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1010 score: 0.9395 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl Segment 1011 score: 0.9155 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-pl-max-tokens-512/test-en-pl score: 0.8796