diff --git "a/test-en-he.comet" "b/test-en-he.comet" new file mode 100644--- /dev/null +++ "b/test-en-he.comet" @@ -0,0 +1,1013 @@ +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 0 score: 0.5442 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1 score: 0.8318 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 2 score: 0.5004 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 3 score: 0.6822 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 4 score: 0.7490 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 5 score: 0.6591 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 6 score: 0.6355 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 7 score: 0.7295 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 8 score: 0.9062 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 9 score: 0.5636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 10 score: 0.3437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 11 score: 0.6622 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 12 score: 0.6031 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 13 score: 0.6956 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 14 score: 0.5039 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 15 score: 0.5367 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 16 score: 0.6680 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 17 score: 0.8290 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 18 score: 0.3424 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 19 score: 0.7989 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 20 score: 0.8464 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 21 score: 0.8977 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 22 score: 0.7125 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 23 score: 0.7320 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 24 score: 0.7282 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 25 score: 0.8168 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 26 score: 0.6937 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 27 score: 0.4861 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 28 score: 0.2127 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 29 score: 0.7498 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 30 score: 0.4815 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 31 score: 0.4082 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 32 score: 0.6362 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 33 score: 0.6403 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 34 score: 0.9149 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 35 score: 0.5624 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 36 score: 0.5124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 37 score: 0.5207 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 38 score: 0.6666 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 39 score: 0.5054 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 40 score: 0.6912 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 41 score: 0.6782 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 42 score: 0.6437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 43 score: 0.7471 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 44 score: 0.6915 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 45 score: 0.7571 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 46 score: 0.5228 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 47 score: 0.7199 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 48 score: 0.6123 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 49 score: 0.6420 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 50 score: 0.7334 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 51 score: 0.5875 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 52 score: 0.7939 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 53 score: 0.8459 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 54 score: 0.6657 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 55 score: 0.8466 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 56 score: 0.7024 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 57 score: 0.5288 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 58 score: 0.6409 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 59 score: 0.7156 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 60 score: 0.7824 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 61 score: 0.8583 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 62 score: 0.7292 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 63 score: 0.4519 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 64 score: 0.5870 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 65 score: 0.6870 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 66 score: 0.7081 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 67 score: 0.6335 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 68 score: 0.9340 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 69 score: 0.8326 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 70 score: 0.8618 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 71 score: 0.8671 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 72 score: 0.4763 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 73 score: 0.7137 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 74 score: 0.8528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 75 score: 0.7001 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 76 score: 0.4744 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 77 score: 0.5382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 78 score: 0.9057 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 79 score: 0.5524 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 80 score: 0.7172 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 81 score: 0.7128 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 82 score: 0.6437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 83 score: 0.2567 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 84 score: 0.4224 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 85 score: 0.5985 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 86 score: 0.6162 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 87 score: 0.8285 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 88 score: 0.6772 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 89 score: 0.5462 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 90 score: 0.6214 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 91 score: 0.4502 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 92 score: 0.6783 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 93 score: 0.6819 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 94 score: 0.6262 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 95 score: 0.8544 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 96 score: 0.4271 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 97 score: 0.6687 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 98 score: 0.7618 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 99 score: 0.5148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 100 score: 0.5767 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 101 score: 0.5975 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 102 score: 0.7273 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 103 score: 0.7626 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 104 score: 0.8191 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 105 score: 0.4540 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 106 score: 0.7695 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 107 score: 0.5107 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 108 score: 0.4952 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 109 score: 0.7628 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 110 score: 0.6551 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 111 score: 0.8130 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 112 score: 0.8332 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 113 score: 0.7858 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 114 score: 0.5192 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 115 score: 0.2381 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 116 score: 0.2390 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 117 score: 0.8339 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 118 score: 0.7620 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 119 score: 0.2573 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 120 score: 0.7791 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 121 score: 0.7058 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 122 score: 0.8793 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 123 score: 0.5379 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 124 score: 0.3115 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 125 score: 0.7649 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 126 score: 0.7988 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 127 score: 0.7313 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 128 score: 0.5396 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 129 score: 0.5786 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 130 score: 0.8506 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 131 score: 0.4773 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 132 score: 0.7636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 133 score: 0.6498 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 134 score: 0.5248 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 135 score: 0.5248 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 136 score: 0.4544 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 137 score: 0.4148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 138 score: 0.5767 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 139 score: 0.7819 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 140 score: 0.5146 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 141 score: 0.7680 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 142 score: 0.7318 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 143 score: 0.5654 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 144 score: 0.8214 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 145 score: 0.6919 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 146 score: 0.7605 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 147 score: 0.8371 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 148 score: 0.7797 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 149 score: 0.7855 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 150 score: 0.7943 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 151 score: 0.6292 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 152 score: 0.6242 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 153 score: 0.2535 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 154 score: 0.4458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 155 score: 0.6840 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 156 score: 0.4879 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 157 score: 0.5657 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 158 score: 0.6284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 159 score: 0.5508 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 160 score: 0.3945 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 161 score: 0.7226 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 162 score: 0.4674 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 163 score: 0.4339 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 164 score: 0.5563 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 165 score: 0.6713 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 166 score: 0.5768 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 167 score: 0.6295 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 168 score: 0.4589 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 169 score: 0.6411 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 170 score: 0.7965 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 171 score: 0.7387 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 172 score: 0.8127 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 173 score: 0.7974 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 174 score: 0.5291 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 175 score: 0.5541 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 176 score: 0.5629 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 177 score: 0.8067 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 178 score: 0.4366 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 179 score: 0.7868 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 180 score: 0.8346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 181 score: 0.8668 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 182 score: 0.8719 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 183 score: 0.8609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 184 score: 0.6182 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 185 score: 0.8528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 186 score: 0.7275 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 187 score: 0.6212 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 188 score: 0.6720 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 189 score: 0.6246 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 190 score: 0.4260 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 191 score: 0.5235 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 192 score: 0.6488 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 193 score: 0.6127 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 194 score: 0.7129 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 195 score: 0.7078 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 196 score: 0.8939 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 197 score: 0.4740 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 198 score: 0.5236 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 199 score: 0.8187 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 200 score: 0.7914 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 201 score: 0.7001 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 202 score: 0.5977 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 203 score: 0.7289 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 204 score: 0.4970 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 205 score: 0.6503 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 206 score: 0.7599 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 207 score: 0.6228 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 208 score: 0.6462 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 209 score: 0.6660 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 210 score: 0.8763 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 211 score: 0.4655 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 212 score: 0.8380 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 213 score: 0.7280 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 214 score: 0.6418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 215 score: 0.7084 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 216 score: 0.6520 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 217 score: 0.6621 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 218 score: 0.6625 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 219 score: 0.7704 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 220 score: 0.6680 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 221 score: 0.2575 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 222 score: 0.4731 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 223 score: 0.6053 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 224 score: 0.7885 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 225 score: 0.6929 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 226 score: 0.2777 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 227 score: 0.4275 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 228 score: 0.6236 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 229 score: 0.8673 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 230 score: 0.8342 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 231 score: 0.4006 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 232 score: 0.5848 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 233 score: 0.4939 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 234 score: 0.4960 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 235 score: 0.5603 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 236 score: 0.7090 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 237 score: 0.4563 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 238 score: 0.7961 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 239 score: 0.4233 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 240 score: 0.5072 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 241 score: 0.5098 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 242 score: 0.5727 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 243 score: 0.4758 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 244 score: 0.5330 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 245 score: 0.6973 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 246 score: 0.7011 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 247 score: 0.5524 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 248 score: 0.5687 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 249 score: 0.8934 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 250 score: 0.5733 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 251 score: 0.8291 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 252 score: 0.7074 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 253 score: 0.4643 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 254 score: 0.4445 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 255 score: 0.9032 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 256 score: 0.4778 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 257 score: 0.5221 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 258 score: 0.6695 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 259 score: 0.4821 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 260 score: 0.9128 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 261 score: 0.5600 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 262 score: 0.7068 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 263 score: 0.3413 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 264 score: 0.8782 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 265 score: 0.4819 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 266 score: 0.6882 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 267 score: 0.5839 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 268 score: 0.7805 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 269 score: 0.7261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 270 score: 0.6049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 271 score: 0.4220 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 272 score: 0.8095 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 273 score: 0.6702 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 274 score: 0.6334 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 275 score: 0.7347 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 276 score: 0.5430 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 277 score: 0.4005 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 278 score: 0.5242 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 279 score: 0.8352 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 280 score: 0.8136 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 281 score: 0.7504 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 282 score: 0.8460 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 283 score: 0.4490 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 284 score: 0.5815 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 285 score: 0.9163 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 286 score: 0.6758 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 287 score: 0.1971 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 288 score: 0.7035 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 289 score: 0.8142 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 290 score: 0.5870 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 291 score: 0.7821 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 292 score: 0.7339 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 293 score: 0.6558 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 294 score: 0.4737 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 295 score: 0.4660 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 296 score: 0.4810 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 297 score: 0.8115 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 298 score: 0.5779 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 299 score: 0.6836 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 300 score: 0.8581 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 301 score: 0.3748 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 302 score: 0.4440 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 303 score: 0.9108 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 304 score: 0.7020 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 305 score: 0.6780 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 306 score: 0.8781 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 307 score: 0.8612 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 308 score: 0.5185 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 309 score: 0.6604 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 310 score: 0.6647 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 311 score: 0.8112 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 312 score: 0.6298 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 313 score: 0.4774 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 314 score: 0.7915 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 315 score: 0.7935 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 316 score: 0.6403 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 317 score: 0.5064 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 318 score: 0.6762 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 319 score: 0.4600 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 320 score: 0.7395 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 321 score: 0.6766 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 322 score: 0.7831 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 323 score: 0.8814 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 324 score: 0.5606 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 325 score: 0.7610 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 326 score: 0.5082 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 327 score: 0.4716 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 328 score: 0.2848 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 329 score: 0.4458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 330 score: 0.6910 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 331 score: 0.4449 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 332 score: 0.6241 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 333 score: 0.5949 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 334 score: 0.9083 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 335 score: 0.6760 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 336 score: 0.5941 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 337 score: 0.4520 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 338 score: 0.5302 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 339 score: 0.8666 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 340 score: 0.5253 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 341 score: 0.4749 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 342 score: 0.3882 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 343 score: 0.4441 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 344 score: 0.8131 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 345 score: 0.5518 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 346 score: 0.6571 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 347 score: 0.8144 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 348 score: 0.4913 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 349 score: 0.3921 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 350 score: 0.5592 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 351 score: 0.5598 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 352 score: 0.5884 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 353 score: 0.7307 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 354 score: 0.4203 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 355 score: 0.5039 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 356 score: 0.6426 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 357 score: 0.8239 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 358 score: 0.4475 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 359 score: 0.3848 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 360 score: 0.5240 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 361 score: 0.5312 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 362 score: 0.6039 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 363 score: 0.4643 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 364 score: 0.7945 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 365 score: 0.5192 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 366 score: 0.4095 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 367 score: 0.6210 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 368 score: 0.7279 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 369 score: 0.5312 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 370 score: 0.5514 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 371 score: 0.4782 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 372 score: 0.8151 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 373 score: 0.5962 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 374 score: 0.6307 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 375 score: 0.7794 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 376 score: 0.5404 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 377 score: 0.6008 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 378 score: 0.4734 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 379 score: 0.9298 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 380 score: 0.5873 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 381 score: 0.6465 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 382 score: 0.4183 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 383 score: 0.5040 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 384 score: 0.6101 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 385 score: 0.2701 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 386 score: 0.5202 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 387 score: 0.7026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 388 score: 0.5525 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 389 score: 0.6777 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 390 score: 0.7083 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 391 score: 0.7154 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 392 score: 0.8237 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 393 score: 0.9015 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 394 score: 0.7059 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 395 score: 0.6081 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 396 score: 0.7118 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 397 score: 0.7441 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 398 score: 0.4988 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 399 score: 0.5148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 400 score: 0.7872 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 401 score: 0.7273 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 402 score: 0.8799 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 403 score: 0.6310 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 404 score: 0.5382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 405 score: 0.7434 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 406 score: 0.2037 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 407 score: 0.6646 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 408 score: 0.2289 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 409 score: 0.2392 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 410 score: 0.5573 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 411 score: 0.6884 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 412 score: 0.6026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 413 score: 0.4782 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 414 score: 0.6117 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 415 score: 0.6886 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 416 score: 0.5448 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 417 score: 0.6320 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 418 score: 0.8011 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 419 score: 0.5955 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 420 score: 0.4846 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 421 score: 0.7760 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 422 score: 0.2208 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 423 score: 0.3630 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 424 score: 0.6644 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 425 score: 0.7823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 426 score: 0.5597 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 427 score: 0.6406 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 428 score: 0.8446 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 429 score: 0.5518 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 430 score: 0.5980 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 431 score: 0.6309 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 432 score: 0.6103 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 433 score: 0.6054 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 434 score: 0.5072 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 435 score: 0.4517 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 436 score: 0.4968 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 437 score: 0.5124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 438 score: 0.8001 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 439 score: 0.6487 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 440 score: 0.5042 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 441 score: 0.7374 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 442 score: 0.6965 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 443 score: 0.4623 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 444 score: 0.7108 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 445 score: 0.6911 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 446 score: 0.4917 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 447 score: 0.9075 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 448 score: 0.9058 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 449 score: 0.8103 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 450 score: 0.6665 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 451 score: 0.6375 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 452 score: 0.4566 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 453 score: 0.6924 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 454 score: 0.7360 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 455 score: 0.6106 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 456 score: 0.7019 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 457 score: 0.6116 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 458 score: 0.5881 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 459 score: 0.6132 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 460 score: 0.5013 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 461 score: 0.5397 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 462 score: 0.7205 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 463 score: 0.5874 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 464 score: 0.6472 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 465 score: 0.8422 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 466 score: 0.7388 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 467 score: 0.6534 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 468 score: 0.4073 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 469 score: 0.5255 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 470 score: 0.5495 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 471 score: 0.6700 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 472 score: 0.4099 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 473 score: 0.4322 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 474 score: 0.5747 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 475 score: 0.7576 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 476 score: 0.5559 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 477 score: 0.4174 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 478 score: 0.7555 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 479 score: 0.7124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 480 score: 0.4187 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 481 score: 0.5137 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 482 score: 0.6705 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 483 score: 0.8398 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 484 score: 0.6267 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 485 score: 0.7039 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 486 score: 0.4849 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 487 score: 0.5379 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 488 score: 0.6383 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 489 score: 0.7163 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 490 score: 0.4478 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 491 score: 0.6256 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 492 score: 0.8203 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 493 score: 0.9046 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 494 score: 0.5730 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 495 score: 0.5681 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 496 score: 0.6554 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 497 score: 0.5759 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 498 score: 0.6538 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 499 score: 0.4179 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 500 score: 0.6536 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 501 score: 0.6591 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 502 score: 0.5558 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 503 score: 0.6459 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 504 score: 0.4388 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 505 score: 0.4811 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 506 score: 0.5705 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 507 score: 0.4273 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 508 score: 0.5288 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 509 score: 0.7332 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 510 score: 0.5707 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 511 score: 0.4908 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 512 score: 0.3843 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 513 score: 0.4101 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 514 score: 0.8206 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 515 score: 0.6948 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 516 score: 0.4563 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 517 score: 0.7197 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 518 score: 0.6916 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 519 score: 0.8676 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 520 score: 0.6948 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 521 score: 0.5566 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 522 score: 0.6300 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 523 score: 0.7189 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 524 score: 0.6269 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 525 score: 0.6374 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 526 score: 0.5086 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 527 score: 0.5098 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 528 score: 0.4148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 529 score: 0.6358 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 530 score: 0.4922 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 531 score: 0.5306 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 532 score: 0.5017 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 533 score: 0.2269 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 534 score: 0.2208 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 535 score: 0.6321 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 536 score: 0.4938 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 537 score: 0.4422 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 538 score: 0.2500 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 539 score: 0.6333 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 540 score: 0.6490 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 541 score: 0.8245 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 542 score: 0.7400 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 543 score: 0.7821 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 544 score: 0.6068 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 545 score: 0.6402 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 546 score: 0.6286 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 547 score: 0.6235 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 548 score: 0.6037 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 549 score: 0.8042 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 550 score: 0.5730 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 551 score: 0.8350 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 552 score: 0.6444 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 553 score: 0.5633 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 554 score: 0.6001 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 555 score: 0.5010 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 556 score: 0.4331 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 557 score: 0.8751 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 558 score: 0.4846 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 559 score: 0.5095 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 560 score: 0.5544 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 561 score: 0.5273 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 562 score: 0.6105 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 563 score: 0.5562 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 564 score: 0.7740 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 565 score: 0.6106 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 566 score: 0.7477 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 567 score: 0.5962 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 568 score: 0.6560 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 569 score: 0.7196 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 570 score: 0.8646 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 571 score: 0.7882 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 572 score: 0.4869 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 573 score: 0.8046 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 574 score: 0.3430 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 575 score: 0.4924 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 576 score: 0.5689 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 577 score: 0.6219 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 578 score: 0.7498 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 579 score: 0.5941 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 580 score: 0.4427 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 581 score: 0.2956 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 582 score: 0.7630 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 583 score: 0.4074 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 584 score: 0.6511 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 585 score: 0.7075 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 586 score: 0.5767 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 587 score: 0.5255 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 588 score: 0.5398 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 589 score: 0.6475 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 590 score: 0.5981 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 591 score: 0.8291 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 592 score: 0.4706 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 593 score: 0.8066 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 594 score: 0.6366 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 595 score: 0.6664 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 596 score: 0.5717 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 597 score: 0.4885 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 598 score: 0.6199 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 599 score: 0.6640 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 600 score: 0.7018 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 601 score: 0.5380 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 602 score: 0.5624 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 603 score: 0.4497 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 604 score: 0.7582 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 605 score: 0.2851 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 606 score: 0.8161 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 607 score: 0.4721 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 608 score: 0.5684 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 609 score: 0.5477 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 610 score: 0.6251 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 611 score: 0.7415 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 612 score: 0.5055 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 613 score: 0.7370 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 614 score: 0.4627 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 615 score: 0.1983 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 616 score: 0.5276 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 617 score: 0.8519 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 618 score: 0.5830 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 619 score: 0.6055 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 620 score: 0.5921 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 621 score: 0.5911 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 622 score: 0.8690 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 623 score: 0.8622 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 624 score: 0.3712 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 625 score: 0.7618 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 626 score: 0.4470 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 627 score: 0.7575 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 628 score: 0.8943 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 629 score: 0.6884 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 630 score: 0.5166 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 631 score: 0.7217 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 632 score: 0.8928 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 633 score: 0.8692 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 634 score: 0.5227 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 635 score: 0.6340 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 636 score: 0.7739 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 637 score: 0.6773 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 638 score: 0.5621 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 639 score: 0.7243 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 640 score: 0.6672 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 641 score: 0.3570 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 642 score: 0.1227 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 643 score: 0.7672 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 644 score: 0.4387 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 645 score: 0.5625 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 646 score: 0.5491 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 647 score: 0.4465 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 648 score: 0.4999 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 649 score: 0.4517 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 650 score: 0.7953 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 651 score: 0.8576 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 652 score: 0.6177 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 653 score: 0.4715 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 654 score: 0.4381 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 655 score: 0.4072 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 656 score: 0.7934 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 657 score: 0.5175 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 658 score: 0.5749 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 659 score: 0.6132 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 660 score: 0.5722 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 661 score: 0.8198 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 662 score: 0.8025 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 663 score: 0.4930 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 664 score: 0.4882 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 665 score: 0.7624 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 666 score: 0.8369 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 667 score: 0.5927 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 668 score: 0.3999 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 669 score: 0.4280 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 670 score: 0.6294 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 671 score: 0.8423 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 672 score: 0.8241 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 673 score: 0.6369 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 674 score: 0.6330 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 675 score: 0.5657 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 676 score: 0.8697 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 677 score: 0.7607 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 678 score: 0.4587 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 679 score: 0.4555 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 680 score: 0.5175 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 681 score: 0.8001 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 682 score: 0.7515 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 683 score: 0.8492 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 684 score: 0.6350 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 685 score: 0.6507 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 686 score: 0.5158 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 687 score: 0.6618 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 688 score: 0.6613 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 689 score: 0.6732 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 690 score: 0.5382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 691 score: 0.6542 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 692 score: 0.8371 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 693 score: 0.6685 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 694 score: 0.4737 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 695 score: 0.5401 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 696 score: 0.3899 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 697 score: 0.8855 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 698 score: 0.6152 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 699 score: 0.8920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 700 score: 0.7854 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 701 score: 0.6280 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 702 score: 0.8884 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 703 score: 0.6742 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 704 score: 0.5786 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 705 score: 0.4023 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 706 score: 0.4971 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 707 score: 0.7205 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 708 score: 0.7630 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 709 score: 0.7143 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 710 score: 0.8383 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 711 score: 0.5648 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 712 score: 0.9241 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 713 score: 0.7177 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 714 score: 0.8494 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 715 score: 0.5883 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 716 score: 0.8416 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 717 score: 0.5945 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 718 score: 0.6823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 719 score: 0.7404 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 720 score: 0.5896 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 721 score: 0.6542 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 722 score: 0.9093 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 723 score: 0.7570 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 724 score: 0.7735 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 725 score: 0.8365 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 726 score: 0.7032 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 727 score: 0.8368 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 728 score: 0.5365 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 729 score: 0.5731 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 730 score: 0.5458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 731 score: 0.7239 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 732 score: 0.6194 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 733 score: 0.7873 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 734 score: 0.4805 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 735 score: 0.7279 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 736 score: 0.4921 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 737 score: 0.7625 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 738 score: 0.6221 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 739 score: 0.8140 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 740 score: 0.7564 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 741 score: 0.8426 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 742 score: 0.6437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 743 score: 0.8174 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 744 score: 0.6910 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 745 score: 0.4618 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 746 score: 0.7251 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 747 score: 0.8060 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 748 score: 0.4970 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 749 score: 0.5471 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 750 score: 0.8012 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 751 score: 0.7049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 752 score: 0.7604 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 753 score: 0.7975 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 754 score: 0.8595 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 755 score: 0.7808 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 756 score: 0.5715 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 757 score: 0.4888 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 758 score: 0.5636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 759 score: 0.2537 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 760 score: 0.6762 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 761 score: 0.6698 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 762 score: 0.4600 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 763 score: 0.5920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 764 score: 0.5152 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 765 score: 0.5749 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 766 score: 0.7595 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 767 score: 0.4277 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 768 score: 0.8349 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 769 score: 0.9253 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 770 score: 0.7156 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 771 score: 0.8491 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 772 score: 0.8210 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 773 score: 0.6193 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 774 score: 0.8034 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 775 score: 0.5734 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 776 score: 0.6116 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 777 score: 0.6513 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 778 score: 0.5754 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 779 score: 0.6930 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 780 score: 0.5077 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 781 score: 0.5866 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 782 score: 0.3707 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 783 score: 0.6492 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 784 score: 0.5203 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 785 score: 0.5852 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 786 score: 0.6626 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 787 score: 0.5908 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 788 score: 0.4671 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 789 score: 0.5531 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 790 score: 0.5414 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 791 score: 0.7424 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 792 score: 0.5026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 793 score: 0.5861 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 794 score: 0.8567 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 795 score: 0.7091 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 796 score: 0.1865 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 797 score: 0.6746 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 798 score: 0.6033 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 799 score: 0.5434 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 800 score: 0.2222 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 801 score: 0.5456 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 802 score: 0.7026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 803 score: 0.5515 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 804 score: 0.4014 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 805 score: 0.4056 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 806 score: 0.5511 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 807 score: 0.4471 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 808 score: 0.5139 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 809 score: 0.6008 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 810 score: 0.4419 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 811 score: 0.4344 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 812 score: 0.2679 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 813 score: 0.7112 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 814 score: 0.6680 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 815 score: 0.6026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 816 score: 0.7340 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 817 score: 0.4272 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 818 score: 0.3397 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 819 score: 0.4724 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 820 score: 0.7746 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 821 score: 0.2507 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 822 score: 0.5243 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 823 score: 0.6024 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 824 score: 0.4968 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 825 score: 0.5705 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 826 score: 0.8587 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 827 score: 0.5672 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 828 score: 0.4311 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 829 score: 0.4437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 830 score: 0.6903 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 831 score: 0.6382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 832 score: 0.5945 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 833 score: 0.3564 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 834 score: 0.2540 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 835 score: 0.7368 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 836 score: 0.3823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 837 score: 0.5829 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 838 score: 0.7791 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 839 score: 0.7517 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 840 score: 0.6449 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 841 score: 0.4272 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 842 score: 0.4282 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 843 score: 0.4641 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 844 score: 0.5300 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 845 score: 0.5065 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 846 score: 0.4261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 847 score: 0.6575 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 848 score: 0.6292 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 849 score: 0.5324 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 850 score: 0.4732 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 851 score: 0.4930 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 852 score: 0.5112 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 853 score: 0.3719 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 854 score: 0.4847 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 855 score: 0.6596 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 856 score: 0.2175 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 857 score: 0.3461 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 858 score: 0.7721 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 859 score: 0.5245 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 860 score: 0.7733 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 861 score: 0.4791 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 862 score: 0.7040 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 863 score: 0.5608 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 864 score: 0.4986 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 865 score: 0.5390 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 866 score: 0.7197 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 867 score: 0.6254 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 868 score: 0.4694 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 869 score: 0.5063 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 870 score: 0.6884 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 871 score: 0.8014 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 872 score: 0.5513 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 873 score: 0.5469 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 874 score: 0.5888 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 875 score: 0.5585 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 876 score: 0.3677 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 877 score: 0.5329 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 878 score: 0.8461 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 879 score: 0.8338 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 880 score: 0.6692 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 881 score: 0.7552 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 882 score: 0.4276 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 883 score: 0.6864 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 884 score: 0.5529 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 885 score: 0.5855 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 886 score: 0.6920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 887 score: 0.5078 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 888 score: 0.5769 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 889 score: 0.5571 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 890 score: 0.6464 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 891 score: 0.5705 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 892 score: 0.5451 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 893 score: 0.5531 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 894 score: 0.2279 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 895 score: 0.8674 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 896 score: 0.5980 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 897 score: 0.4478 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 898 score: 0.7841 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 899 score: 0.7134 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 900 score: 0.8420 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 901 score: 0.6274 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 902 score: 0.4636 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 903 score: 0.5721 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 904 score: 0.8712 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 905 score: 0.6044 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 906 score: 0.7863 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 907 score: 0.5590 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 908 score: 0.7287 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 909 score: 0.8734 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 910 score: 0.4663 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 911 score: 0.6544 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 912 score: 0.8484 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 913 score: 0.5118 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 914 score: 0.6803 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 915 score: 0.7689 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 916 score: 0.8202 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 917 score: 0.6844 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 918 score: 0.4762 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 919 score: 0.5776 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 920 score: 0.5248 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 921 score: 0.7061 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 922 score: 0.7397 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 923 score: 0.7184 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 924 score: 0.7853 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 925 score: 0.8349 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 926 score: 0.8548 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 927 score: 0.5835 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 928 score: 0.6021 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 929 score: 0.5867 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 930 score: 0.8714 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 931 score: 0.6719 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 932 score: 0.5985 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 933 score: 0.5605 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 934 score: 0.6774 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 935 score: 0.3608 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 936 score: 0.5393 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 937 score: 0.8243 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 938 score: 0.9076 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 939 score: 0.8008 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 940 score: 0.6681 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 941 score: 0.9487 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 942 score: 0.9089 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 943 score: 0.7643 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 944 score: 0.6563 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 945 score: 0.6584 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 946 score: 0.6087 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 947 score: 0.5176 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 948 score: 0.6386 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 949 score: 0.6889 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 950 score: 0.6813 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 951 score: 0.8458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 952 score: 0.6971 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 953 score: 0.4677 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 954 score: 0.4554 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 955 score: 0.8750 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 956 score: 0.5008 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 957 score: 0.5420 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 958 score: 0.6202 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 959 score: 0.6647 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 960 score: 0.5250 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 961 score: 0.6225 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 962 score: 0.5242 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 963 score: 0.5743 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 964 score: 0.7600 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 965 score: 0.4155 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 966 score: 0.5726 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 967 score: 0.5192 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 968 score: 0.5757 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 969 score: 0.5155 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 970 score: 0.5262 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 971 score: 0.6211 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 972 score: 0.5713 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 973 score: 0.8854 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 974 score: 0.5177 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 975 score: 0.5117 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 976 score: 0.7606 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 977 score: 0.5364 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 978 score: 0.3808 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 979 score: 0.7507 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 980 score: 0.7689 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 981 score: 0.7633 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 982 score: 0.7252 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 983 score: 0.5507 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 984 score: 0.6646 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 985 score: 0.8802 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 986 score: 0.3681 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 987 score: 0.1400 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 988 score: 0.5040 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 989 score: 0.5740 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 990 score: 0.9125 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 991 score: 0.6049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 992 score: 0.6926 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 993 score: 0.6239 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 994 score: 0.5486 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 995 score: 0.6651 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 996 score: 0.5138 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 997 score: 0.2306 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 998 score: 0.6322 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 999 score: 0.4816 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1000 score: 0.6717 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1001 score: 0.5190 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1002 score: 0.4521 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1003 score: 0.4891 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1004 score: 0.4199 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1005 score: 0.5900 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1006 score: 0.6638 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1007 score: 0.5677 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1008 score: 0.7656 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1009 score: 0.5557 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1010 score: 0.8004 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he Segment 1011 score: 0.6449 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/seperate_training//alma-13b-sft-50-languages-he-max-tokens-512/test-en-he score: 0.6230