/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 0 score: 0.6846 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1 score: 0.6990 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 2 score: 0.4834 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 3 score: 0.3480 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 4 score: 0.7518 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 5 score: 0.6342 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 6 score: 0.7533 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 7 score: 0.7533 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 8 score: 0.6407 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 9 score: 0.6411 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 10 score: 0.8171 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 11 score: 0.6685 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 12 score: 0.7146 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 13 score: 0.7135 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 14 score: 0.6050 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 15 score: 0.5740 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 16 score: 0.4465 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 17 score: 0.6771 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 18 score: 0.8205 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 19 score: 0.7355 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 20 score: 0.6917 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 21 score: 0.8252 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 22 score: 0.8073 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 23 score: 0.5253 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 24 score: 0.8481 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 25 score: 0.7540 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 26 score: 0.6815 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 27 score: 0.5383 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 28 score: 0.5908 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 29 score: 0.5966 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 30 score: 0.5230 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 31 score: 0.4528 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 32 score: 0.1917 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 33 score: 0.3041 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 34 score: 0.7720 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 35 score: 0.7413 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 36 score: 0.5587 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 37 score: 0.7144 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 38 score: 0.7585 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 39 score: 0.6268 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 40 score: 0.2641 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 41 score: 0.9427 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 42 score: 0.3554 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 43 score: 0.4589 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 44 score: 0.6086 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 45 score: 0.7878 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 46 score: 0.7775 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 47 score: 0.3133 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 48 score: 0.4466 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 49 score: 0.6022 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 50 score: 0.7704 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 51 score: 0.6629 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 52 score: 0.3353 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 53 score: 0.3649 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 54 score: 0.6372 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 55 score: 0.6734 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 56 score: 0.4285 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 57 score: 0.6135 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 58 score: 0.6022 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 59 score: 0.9195 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 60 score: 0.7827 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 61 score: 0.7674 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 62 score: 0.6485 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 63 score: 0.3242 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 64 score: 0.4985 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 65 score: 0.8181 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 66 score: 0.5509 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 67 score: 0.7160 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 68 score: 0.8305 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 69 score: 0.8191 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 70 score: 0.6191 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 71 score: 0.6307 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 72 score: 0.7752 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 73 score: 0.5850 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 74 score: 0.7545 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 75 score: 0.6819 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 76 score: 0.6599 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 77 score: 0.6205 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 78 score: 0.7370 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 79 score: 0.6410 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 80 score: 0.6892 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 81 score: 0.8481 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 82 score: 0.6905 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 83 score: 0.5213 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 84 score: 0.5677 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 85 score: 0.8137 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 86 score: 0.6203 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 87 score: 0.7120 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 88 score: 0.5540 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 89 score: 0.2910 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 90 score: 0.3056 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 91 score: 0.5717 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 92 score: 0.4881 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 93 score: 0.5971 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 94 score: 0.7749 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 95 score: 0.5691 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 96 score: 0.5104 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 97 score: 0.7486 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 98 score: 0.6355 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 99 score: 0.5891 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 100 score: 0.6534 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 101 score: 0.3687 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 102 score: 0.7773 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 103 score: 0.9028 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 104 score: 0.3994 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 105 score: 0.3593 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 106 score: 0.7760 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 107 score: 0.3304 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 108 score: 0.4660 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 109 score: 0.5211 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 110 score: 0.5328 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 111 score: 0.8211 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 112 score: 0.7266 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 113 score: 0.6821 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 114 score: 0.2352 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 115 score: 0.7460 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 116 score: 0.7328 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 117 score: 0.7229 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 118 score: 0.9475 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 119 score: 0.6762 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 120 score: 0.7645 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 121 score: 0.5644 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 122 score: 0.7046 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 123 score: 0.4403 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 124 score: 0.6535 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 125 score: 0.7219 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 126 score: 0.7607 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 127 score: 0.5936 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 128 score: 0.6687 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 129 score: 0.2162 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 130 score: 0.6993 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 131 score: 0.5201 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 132 score: 0.6381 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 133 score: 0.7911 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 134 score: 0.5061 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 135 score: 0.6037 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 136 score: 0.6495 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 137 score: 0.6198 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 138 score: 0.7352 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 139 score: 0.5144 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 140 score: 0.6531 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 141 score: 0.8280 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 142 score: 0.7677 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 143 score: 0.3640 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 144 score: 0.7677 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 145 score: 0.8332 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 146 score: 0.7113 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 147 score: 0.5979 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 148 score: 0.5557 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 149 score: 0.6080 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 150 score: 0.7231 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 151 score: 0.7353 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 152 score: 0.6061 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 153 score: 0.5640 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 154 score: 0.4176 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 155 score: 0.6263 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 156 score: 0.6142 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 157 score: 0.7475 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 158 score: 0.6173 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 159 score: 0.6097 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 160 score: 0.3912 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 161 score: 0.4637 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 162 score: 0.2696 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 163 score: 0.5688 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 164 score: 0.7030 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 165 score: 0.3924 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 166 score: 0.5822 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 167 score: 0.6171 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 168 score: 0.5648 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 169 score: 0.6822 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 170 score: 0.6508 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 171 score: 0.8356 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 172 score: 0.7630 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 173 score: 0.5996 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 174 score: 0.5973 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 175 score: 0.6075 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 176 score: 0.7800 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 177 score: 0.8140 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 178 score: 0.4520 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 179 score: 0.8395 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 180 score: 0.8069 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 181 score: 0.8453 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 182 score: 0.8366 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 183 score: 0.8483 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 184 score: 0.4160 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 185 score: 0.1897 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 186 score: 0.6537 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 187 score: 0.2037 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 188 score: 0.6522 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 189 score: 0.5451 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 190 score: 0.3993 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 191 score: 0.3371 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 192 score: 0.4131 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 193 score: 0.2606 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 194 score: 0.7657 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 195 score: 0.8542 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 196 score: 0.4221 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 197 score: 0.6771 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 198 score: 0.5300 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 199 score: 0.6056 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 200 score: 0.5319 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 201 score: 0.2908 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 202 score: 0.6716 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 203 score: 0.6595 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 204 score: 0.6974 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 205 score: 0.5987 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 206 score: 0.6538 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 207 score: 0.5206 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 208 score: 0.7149 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 209 score: 0.7116 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 210 score: 0.8746 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 211 score: 0.8254 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 212 score: 0.8292 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 213 score: 0.8904 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 214 score: 0.7505 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 215 score: 0.7230 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 216 score: 0.5148 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 217 score: 0.7211 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 218 score: 0.5225 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 219 score: 0.5886 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 220 score: 0.8425 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 221 score: 0.8902 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 222 score: 0.6951 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 223 score: 0.2032 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 224 score: 0.8415 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 225 score: 0.8699 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 226 score: 0.6410 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 227 score: 0.6125 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 228 score: 0.6683 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 229 score: 0.6498 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 230 score: 0.9145 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 231 score: 0.6818 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 232 score: 0.8184 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 233 score: 0.4343 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 234 score: 0.7543 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 235 score: 0.8422 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 236 score: 0.8395 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 237 score: 0.5639 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 238 score: 0.3487 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 239 score: 0.7238 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 240 score: 0.3521 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 241 score: 0.6487 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 242 score: 0.7677 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 243 score: 0.4823 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 244 score: 0.4692 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 245 score: 0.4604 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 246 score: 0.6314 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 247 score: 0.4486 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 248 score: 0.5241 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 249 score: 0.8297 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 250 score: 0.7986 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 251 score: 0.6111 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 252 score: 0.7760 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 253 score: 0.2300 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 254 score: 0.4946 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 255 score: 0.7119 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 256 score: 0.3862 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 257 score: 0.3618 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 258 score: 0.7406 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 259 score: 0.3266 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 260 score: 0.5995 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 261 score: 0.5980 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 262 score: 0.6219 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 263 score: 0.5644 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 264 score: 0.7820 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 265 score: 0.6044 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 266 score: 0.5373 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 267 score: 0.6332 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 268 score: 0.8497 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 269 score: 0.6821 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 270 score: 0.6545 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 271 score: 0.4454 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 272 score: 0.6979 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 273 score: 0.6006 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 274 score: 0.5983 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 275 score: 0.3493 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 276 score: 0.6695 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 277 score: 0.8931 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 278 score: 0.8452 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 279 score: 0.8961 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 280 score: 0.3587 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 281 score: 0.8261 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 282 score: 0.7232 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 283 score: 0.6310 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 284 score: 0.4787 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 285 score: 0.8504 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 286 score: 0.7160 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 287 score: 0.5883 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 288 score: 0.8348 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 289 score: 0.7037 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 290 score: 0.2346 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 291 score: 0.6858 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 292 score: 0.7806 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 293 score: 0.8599 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 294 score: 0.6951 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 295 score: 0.5994 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 296 score: 0.6158 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 297 score: 0.6810 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 298 score: 0.9244 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 299 score: 0.6036 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 300 score: 0.2563 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 301 score: 0.3601 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 302 score: 0.5464 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 303 score: 0.8784 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 304 score: 0.8037 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 305 score: 0.8141 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 306 score: 0.8017 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 307 score: 0.8666 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 308 score: 0.8413 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 309 score: 0.7521 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 310 score: 0.7740 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 311 score: 0.4950 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 312 score: 0.4910 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 313 score: 0.6357 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 314 score: 0.3781 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 315 score: 0.8184 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 316 score: 0.5594 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 317 score: 0.6945 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 318 score: 0.8020 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 319 score: 0.6100 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 320 score: 0.5608 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 321 score: 0.5593 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 322 score: 0.6813 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 323 score: 0.3098 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 324 score: 0.7356 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 325 score: 0.5594 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 326 score: 0.6307 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 327 score: 0.5612 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 328 score: 0.6624 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 329 score: 0.7794 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 330 score: 0.5915 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 331 score: 0.2681 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 332 score: 0.7233 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 333 score: 0.5792 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 334 score: 0.3675 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 335 score: 0.6728 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 336 score: 0.7186 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 337 score: 0.6435 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 338 score: 0.6963 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 339 score: 0.6694 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 340 score: 0.6438 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 341 score: 0.5213 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 342 score: 0.5646 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 343 score: 0.2166 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 344 score: 0.8096 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 345 score: 0.2552 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 346 score: 0.6690 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 347 score: 0.7248 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 348 score: 0.4530 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 349 score: 0.4846 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 350 score: 0.2996 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 351 score: 0.6686 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 352 score: 0.6731 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 353 score: 0.8812 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 354 score: 0.5142 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 355 score: 0.4900 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 356 score: 0.7286 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 357 score: 0.7077 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 358 score: 0.7717 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 359 score: 0.5827 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 360 score: 0.4343 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 361 score: 0.6338 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 362 score: 0.7126 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 363 score: 0.4999 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 364 score: 0.8187 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 365 score: 0.4333 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 366 score: 0.3502 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 367 score: 0.6168 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 368 score: 0.4230 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 369 score: 0.7094 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 370 score: 0.3430 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 371 score: 0.3966 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 372 score: 0.3560 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 373 score: 0.6430 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 374 score: 0.5621 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 375 score: 0.6120 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 376 score: 0.2338 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 377 score: 0.6331 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 378 score: 0.4543 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 379 score: 0.5889 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 380 score: 0.8601 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 381 score: 0.5854 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 382 score: 0.5833 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 383 score: 0.4808 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 384 score: 0.5421 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 385 score: 0.6951 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 386 score: 0.5777 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 387 score: 0.7846 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 388 score: 0.4783 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 389 score: 0.8338 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 390 score: 0.6784 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 391 score: 0.6354 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 392 score: 0.7628 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 393 score: 0.7427 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 394 score: 0.8051 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 395 score: 0.5092 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 396 score: 0.4840 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 397 score: 0.8214 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 398 score: 0.5997 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 399 score: 0.6960 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 400 score: 0.7381 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 401 score: 0.7155 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 402 score: 0.6874 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 403 score: 0.6517 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 404 score: 0.6334 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 405 score: 0.6942 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 406 score: 0.7003 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 407 score: 0.4970 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 408 score: 0.8622 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 409 score: 0.2867 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 410 score: 0.8122 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 411 score: 0.5881 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 412 score: 0.3268 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 413 score: 0.7025 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 414 score: 0.3071 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 415 score: 0.2711 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 416 score: 0.7902 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 417 score: 0.4426 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 418 score: 0.7660 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 419 score: 0.8783 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 420 score: 0.8132 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 421 score: 0.7030 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 422 score: 0.5370 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 423 score: 0.8152 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 424 score: 0.6684 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 425 score: 0.8450 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 426 score: 0.6546 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 427 score: 0.6373 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 428 score: 0.2982 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 429 score: 0.6088 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 430 score: 0.8272 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 431 score: 0.6941 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 432 score: 0.4488 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 433 score: 0.6963 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 434 score: 0.6275 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 435 score: 0.4539 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 436 score: 0.5744 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 437 score: 0.6261 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 438 score: 0.5789 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 439 score: 0.7126 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 440 score: 0.7923 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 441 score: 0.5897 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 442 score: 0.8100 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 443 score: 0.3847 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 444 score: 0.7296 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 445 score: 0.4443 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 446 score: 0.5551 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 447 score: 0.5320 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 448 score: 0.9129 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 449 score: 0.6225 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 450 score: 0.7192 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 451 score: 0.5277 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 452 score: 0.6251 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 453 score: 0.6270 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 454 score: 0.7859 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 455 score: 0.4801 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 456 score: 0.7332 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 457 score: 0.7441 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 458 score: 0.5638 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 459 score: 0.6264 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 460 score: 0.4391 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 461 score: 0.4319 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 462 score: 0.2821 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 463 score: 0.5226 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 464 score: 0.6482 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 465 score: 0.7609 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 466 score: 0.8269 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 467 score: 0.5707 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 468 score: 0.2651 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 469 score: 0.4002 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 470 score: 0.5528 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 471 score: 0.6325 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 472 score: 0.3417 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 473 score: 0.2655 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 474 score: 0.4842 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 475 score: 0.4989 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 476 score: 0.5096 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 477 score: 0.6426 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 478 score: 0.7089 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 479 score: 0.8471 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 480 score: 0.3778 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 481 score: 0.5453 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 482 score: 0.3745 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 483 score: 0.7655 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 484 score: 0.6138 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 485 score: 0.5401 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 486 score: 0.7790 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 487 score: 0.6136 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 488 score: 0.5845 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 489 score: 0.6825 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 490 score: 0.4692 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 491 score: 0.6158 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 492 score: 0.8513 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 493 score: 0.2145 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 494 score: 0.6441 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 495 score: 0.5777 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 496 score: 0.3023 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 497 score: 0.2567 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 498 score: 0.2735 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 499 score: 0.5324 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 500 score: 0.7489 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 501 score: 0.5348 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 502 score: 0.6333 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 503 score: 0.4234 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 504 score: 0.6617 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 505 score: 0.3413 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 506 score: 0.6325 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 507 score: 0.3315 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 508 score: 0.6493 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 509 score: 0.7953 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 510 score: 0.7011 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 511 score: 0.7176 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 512 score: 0.3634 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 513 score: 0.5992 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 514 score: 0.8074 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 515 score: 0.5830 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 516 score: 0.4504 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 517 score: 0.6522 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 518 score: 0.6586 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 519 score: 0.8304 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 520 score: 0.7779 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 521 score: 0.6568 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 522 score: 0.3114 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 523 score: 0.6603 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 524 score: 0.5439 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 525 score: 0.7403 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 526 score: 0.6168 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 527 score: 0.5123 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 528 score: 0.5212 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 529 score: 0.6275 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 530 score: 0.3253 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 531 score: 0.7288 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 532 score: 0.5057 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 533 score: 0.4952 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 534 score: 0.3206 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 535 score: 0.5639 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 536 score: 0.4164 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 537 score: 0.4209 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 538 score: 0.5783 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 539 score: 0.6550 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 540 score: 0.6629 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 541 score: 0.7081 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 542 score: 0.6812 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 543 score: 0.2786 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 544 score: 0.6667 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 545 score: 0.5616 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 546 score: 0.7378 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 547 score: 0.6198 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 548 score: 0.5512 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 549 score: 0.7854 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 550 score: 0.5301 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 551 score: 0.6931 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 552 score: 0.7458 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 553 score: 0.3822 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 554 score: 0.6814 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 555 score: 0.6037 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 556 score: 0.2414 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 557 score: 0.7001 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 558 score: 0.3486 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 559 score: 0.1951 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 560 score: 0.2554 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 561 score: 0.2328 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 562 score: 0.5869 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 563 score: 0.5076 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 564 score: 0.6439 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 565 score: 0.4370 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 566 score: 0.7119 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 567 score: 0.6261 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 568 score: 0.6161 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 569 score: 0.6755 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 570 score: 0.7469 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 571 score: 0.6743 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 572 score: 0.3016 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 573 score: 0.7111 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 574 score: 0.7175 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 575 score: 0.5813 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 576 score: 0.5048 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 577 score: 0.6735 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 578 score: 0.7562 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 579 score: 0.2340 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 580 score: 0.5830 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 581 score: 0.7150 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 582 score: 0.5482 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 583 score: 0.5158 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 584 score: 0.4079 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 585 score: 0.3633 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 586 score: 0.7653 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 587 score: 0.6174 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 588 score: 0.5318 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 589 score: 0.7680 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 590 score: 0.7252 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 591 score: 0.7178 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 592 score: 0.4002 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 593 score: 0.7446 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 594 score: 0.8494 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 595 score: 0.6780 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 596 score: 0.5306 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 597 score: 0.4826 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 598 score: 0.4259 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 599 score: 0.6824 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 600 score: 0.5801 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 601 score: 0.6967 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 602 score: 0.5700 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 603 score: 0.4764 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 604 score: 0.3713 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 605 score: 0.7362 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 606 score: 0.7350 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 607 score: 0.5658 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 608 score: 0.7826 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 609 score: 0.6578 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 610 score: 0.7053 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 611 score: 0.5564 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 612 score: 0.5948 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 613 score: 0.5669 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 614 score: 0.4612 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 615 score: 0.3587 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 616 score: 0.6771 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 617 score: 0.7980 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 618 score: 0.3638 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 619 score: 0.5593 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 620 score: 0.6394 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 621 score: 0.4324 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 622 score: 0.5518 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 623 score: 0.6053 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 624 score: 0.5648 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 625 score: 0.7680 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 626 score: 0.5842 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 627 score: 0.5829 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 628 score: 0.7256 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 629 score: 0.7117 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 630 score: 0.3107 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 631 score: 0.7445 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 632 score: 0.8664 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 633 score: 0.6658 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 634 score: 0.9423 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 635 score: 0.7163 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 636 score: 0.7992 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 637 score: 0.4228 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 638 score: 0.4412 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 639 score: 0.6673 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 640 score: 0.6124 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 641 score: 0.8196 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 642 score: 0.4190 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 643 score: 0.7420 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 644 score: 0.7328 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 645 score: 0.7578 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 646 score: 0.5809 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 647 score: 0.3278 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 648 score: 0.1490 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 649 score: 0.5535 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 650 score: 0.7300 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 651 score: 0.5938 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 652 score: 0.5340 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 653 score: 0.4773 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 654 score: 0.5513 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 655 score: 0.7020 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 656 score: 0.4824 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 657 score: 0.7235 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 658 score: 0.2415 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 659 score: 0.5671 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 660 score: 0.5895 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 661 score: 0.7821 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 662 score: 0.6635 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 663 score: 0.6001 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 664 score: 0.7165 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 665 score: 0.6911 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 666 score: 0.4461 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 667 score: 0.7357 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 668 score: 0.5157 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 669 score: 0.6207 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 670 score: 0.5763 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 671 score: 0.5878 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 672 score: 0.7154 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 673 score: 0.6114 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 674 score: 0.7612 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 675 score: 0.6239 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 676 score: 0.8606 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 677 score: 0.7525 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 678 score: 0.7011 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 679 score: 0.3089 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 680 score: 0.2233 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 681 score: 0.6801 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 682 score: 0.8137 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 683 score: 0.7121 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 684 score: 0.7051 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 685 score: 0.7079 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 686 score: 0.7950 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 687 score: 0.5939 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 688 score: 0.7192 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 689 score: 0.7019 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 690 score: 0.7663 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 691 score: 0.6760 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 692 score: 0.4356 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 693 score: 0.6321 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 694 score: 0.3757 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 695 score: 0.2390 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 696 score: 0.4431 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 697 score: 0.7446 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 698 score: 0.6297 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 699 score: 0.7859 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 700 score: 0.7275 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 701 score: 0.7715 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 702 score: 0.6928 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 703 score: 0.6017 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 704 score: 0.3300 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 705 score: 0.3584 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 706 score: 0.5834 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 707 score: 0.7228 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 708 score: 0.7745 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 709 score: 0.7960 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 710 score: 0.6322 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 711 score: 0.6254 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 712 score: 0.9028 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 713 score: 0.6573 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 714 score: 0.6225 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 715 score: 0.5788 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 716 score: 0.7886 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 717 score: 0.5606 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 718 score: 0.6596 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 719 score: 0.7623 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 720 score: 0.6361 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 721 score: 0.8346 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 722 score: 0.7211 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 723 score: 0.7497 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 724 score: 0.5016 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 725 score: 0.6572 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 726 score: 0.6899 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 727 score: 0.6769 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 728 score: 0.5656 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 729 score: 0.7146 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 730 score: 0.5169 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 731 score: 0.7231 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 732 score: 0.6938 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 733 score: 0.7038 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 734 score: 0.4831 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 735 score: 0.6628 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 736 score: 0.5031 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 737 score: 0.6270 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 738 score: 0.2923 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 739 score: 0.5833 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 740 score: 0.6712 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 741 score: 0.6729 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 742 score: 0.4954 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 743 score: 0.6949 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 744 score: 0.5878 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 745 score: 0.3825 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 746 score: 0.6699 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 747 score: 0.6207 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 748 score: 0.7309 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 749 score: 0.5632 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 750 score: 0.8768 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 751 score: 0.7964 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 752 score: 0.8095 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 753 score: 0.7237 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 754 score: 0.8182 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 755 score: 0.7763 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 756 score: 0.8226 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 757 score: 0.5098 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 758 score: 0.3688 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 759 score: 0.6554 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 760 score: 0.6778 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 761 score: 0.5383 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 762 score: 0.7611 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 763 score: 0.6024 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 764 score: 0.8417 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 765 score: 0.4539 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 766 score: 0.7349 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 767 score: 0.4396 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 768 score: 0.8285 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 769 score: 0.9144 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 770 score: 0.4884 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 771 score: 0.8409 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 772 score: 0.3046 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 773 score: 0.6929 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 774 score: 0.3953 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 775 score: 0.2894 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 776 score: 0.7058 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 777 score: 0.4798 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 778 score: 0.6977 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 779 score: 0.6919 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 780 score: 0.5973 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 781 score: 0.4329 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 782 score: 0.8049 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 783 score: 0.8171 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 784 score: 0.6854 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 785 score: 0.5302 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 786 score: 0.8205 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 787 score: 0.4847 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 788 score: 0.3999 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 789 score: 0.5948 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 790 score: 0.4930 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 791 score: 0.4350 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 792 score: 0.6194 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 793 score: 0.3008 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 794 score: 0.5086 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 795 score: 0.3693 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 796 score: 0.7589 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 797 score: 0.6073 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 798 score: 0.6989 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 799 score: 0.6068 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 800 score: 0.5301 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 801 score: 0.3050 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 802 score: 0.4591 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 803 score: 0.6137 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 804 score: 0.5319 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 805 score: 0.2943 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 806 score: 0.4563 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 807 score: 0.6677 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 808 score: 0.7355 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 809 score: 0.5770 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 810 score: 0.7385 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 811 score: 0.5909 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 812 score: 0.8004 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 813 score: 0.7810 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 814 score: 0.7233 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 815 score: 0.5681 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 816 score: 0.7243 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 817 score: 0.4708 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 818 score: 0.6236 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 819 score: 0.4776 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 820 score: 0.5186 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 821 score: 0.7061 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 822 score: 0.7025 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 823 score: 0.4865 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 824 score: 0.2829 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 825 score: 0.5515 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 826 score: 0.5209 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 827 score: 0.1741 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 828 score: 0.5394 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 829 score: 0.3821 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 830 score: 0.6776 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 831 score: 0.4671 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 832 score: 0.6552 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 833 score: 0.6255 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 834 score: 0.2227 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 835 score: 0.5295 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 836 score: 0.5384 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 837 score: 0.3101 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 838 score: 0.6716 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 839 score: 0.4309 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 840 score: 0.7179 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 841 score: 0.5936 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 842 score: 0.3908 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 843 score: 0.3945 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 844 score: 0.6554 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 845 score: 0.3603 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 846 score: 0.4519 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 847 score: 0.5717 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 848 score: 0.5919 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 849 score: 0.4853 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 850 score: 0.6293 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 851 score: 0.6479 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 852 score: 0.7811 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 853 score: 0.6140 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 854 score: 0.5733 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 855 score: 0.5266 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 856 score: 0.4382 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 857 score: 0.7075 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 858 score: 0.6751 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 859 score: 0.7201 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 860 score: 0.7250 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 861 score: 0.7900 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 862 score: 0.8220 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 863 score: 0.4341 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 864 score: 0.6047 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 865 score: 0.4577 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 866 score: 0.6498 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 867 score: 0.6223 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 868 score: 0.5918 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 869 score: 0.6036 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 870 score: 0.7933 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 871 score: 0.8457 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 872 score: 0.7941 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 873 score: 0.3214 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 874 score: 0.7353 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 875 score: 0.6360 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 876 score: 0.4850 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 877 score: 0.5113 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 878 score: 0.6737 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 879 score: 0.7147 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 880 score: 0.6634 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 881 score: 0.8057 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 882 score: 0.6883 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 883 score: 0.6810 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 884 score: 0.6644 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 885 score: 0.6049 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 886 score: 0.7581 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 887 score: 0.6612 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 888 score: 0.5032 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 889 score: 0.5349 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 890 score: 0.4375 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 891 score: 0.5327 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 892 score: 0.6003 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 893 score: 0.6118 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 894 score: 0.6748 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 895 score: 0.6076 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 896 score: 0.7243 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 897 score: 0.5177 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 898 score: 0.8745 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 899 score: 0.5657 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 900 score: 0.7097 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 901 score: 0.7180 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 902 score: 0.6867 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 903 score: 0.6363 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 904 score: 0.8082 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 905 score: 0.4637 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 906 score: 0.6836 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 907 score: 0.4946 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 908 score: 0.7753 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 909 score: 0.6200 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 910 score: 0.6478 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 911 score: 0.3220 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 912 score: 0.8130 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 913 score: 0.5459 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 914 score: 0.6536 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 915 score: 0.6286 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 916 score: 0.8944 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 917 score: 0.6066 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 918 score: 0.7371 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 919 score: 0.5981 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 920 score: 0.5079 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 921 score: 0.6678 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 922 score: 0.5313 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 923 score: 0.7768 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 924 score: 0.6420 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 925 score: 0.6943 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 926 score: 0.6815 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 927 score: 0.6296 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 928 score: 0.6144 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 929 score: 0.7785 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 930 score: 0.7854 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 931 score: 0.7207 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 932 score: 0.6496 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 933 score: 0.4261 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 934 score: 0.3362 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 935 score: 0.5302 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 936 score: 0.5421 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 937 score: 0.8945 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 938 score: 0.8656 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 939 score: 0.7930 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 940 score: 0.2895 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 941 score: 0.3976 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 942 score: 0.8335 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 943 score: 0.6368 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 944 score: 0.4320 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 945 score: 0.5239 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 946 score: 0.4359 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 947 score: 0.5987 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 948 score: 0.6386 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 949 score: 0.6672 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 950 score: 0.7399 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 951 score: 0.5061 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 952 score: 0.5847 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 953 score: 0.5808 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 954 score: 0.6739 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 955 score: 0.7481 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 956 score: 0.7995 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 957 score: 0.8174 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 958 score: 0.7512 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 959 score: 0.4913 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 960 score: 0.3823 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 961 score: 0.5143 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 962 score: 0.5111 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 963 score: 0.5120 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 964 score: 0.6278 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 965 score: 0.6405 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 966 score: 0.2678 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 967 score: 0.5000 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 968 score: 0.3919 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 969 score: 0.6728 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 970 score: 0.7020 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 971 score: 0.4520 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 972 score: 0.5432 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 973 score: 0.7604 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 974 score: 0.6504 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 975 score: 0.3369 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 976 score: 0.6663 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 977 score: 0.7238 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 978 score: 0.6473 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 979 score: 0.5961 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 980 score: 0.6682 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 981 score: 0.4698 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 982 score: 0.5168 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 983 score: 0.5666 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 984 score: 0.4213 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 985 score: 0.6937 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 986 score: 0.4885 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 987 score: 0.6063 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 988 score: 0.5375 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 989 score: 0.5030 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 990 score: 0.4030 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 991 score: 0.4946 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 992 score: 0.7855 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 993 score: 0.5094 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 994 score: 0.4198 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 995 score: 0.6312 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 996 score: 0.4755 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 997 score: 0.7195 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 998 score: 0.2985 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 999 score: 0.3100 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1000 score: 0.5124 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1001 score: 0.4973 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1002 score: 0.5088 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1003 score: 0.7141 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1004 score: 0.5249 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1005 score: 0.5489 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1006 score: 0.2630 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1007 score: 0.5209 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1008 score: 0.7899 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1009 score: 0.5847 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1010 score: 0.4685 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur Segment 1011 score: 0.3751 /beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages//alma-13b-sft-16-languages-ur-max-tokens-512/test-en-ur score: 0.6075