diff --git "a/test-he-en.comet" "b/test-he-en.comet" new file mode 100644--- /dev/null +++ "b/test-he-en.comet" @@ -0,0 +1,1013 @@ +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 0 score: 0.5559 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1 score: 0.8444 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 2 score: 0.9071 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 3 score: 0.7760 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 4 score: 0.8588 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 5 score: 0.8163 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 6 score: 0.9611 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 7 score: 0.5742 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 8 score: 0.8940 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 9 score: 0.8094 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 10 score: 0.8160 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 11 score: 0.8342 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 12 score: 0.8854 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 13 score: 0.8178 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 14 score: 0.7209 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 15 score: 0.7030 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 16 score: 0.7583 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 17 score: 0.9296 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 18 score: 0.9026 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 19 score: 0.8796 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 20 score: 0.9444 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 21 score: 0.8801 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 22 score: 0.8534 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 23 score: 0.8532 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 24 score: 0.8235 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 25 score: 0.9226 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 26 score: 0.7990 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 27 score: 0.5827 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 28 score: 0.5513 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 29 score: 0.9396 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 30 score: 0.6871 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 31 score: 0.6875 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 32 score: 0.7999 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 33 score: 0.8722 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 34 score: 0.9004 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 35 score: 0.7399 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 36 score: 0.8498 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 37 score: 0.7892 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 38 score: 0.5170 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 39 score: 0.7370 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 40 score: 0.6970 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 41 score: 0.9292 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 42 score: 0.8532 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 43 score: 0.8973 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 44 score: 0.7246 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 45 score: 0.8394 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 46 score: 0.6376 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 47 score: 0.7294 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 48 score: 0.6585 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 49 score: 0.7215 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 50 score: 0.8675 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 51 score: 0.7783 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 52 score: 0.7055 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 53 score: 0.7824 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 54 score: 0.8862 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 55 score: 0.8685 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 56 score: 0.7735 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 57 score: 0.5854 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 58 score: 0.6332 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 59 score: 0.8536 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 60 score: 0.8214 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 61 score: 0.8372 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 62 score: 0.8246 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 63 score: 0.6129 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 64 score: 0.8217 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 65 score: 0.7398 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 66 score: 0.6292 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 67 score: 0.7203 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 68 score: 0.8931 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 69 score: 0.7049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 70 score: 0.6822 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 71 score: 0.8178 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 72 score: 0.5523 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 73 score: 0.7340 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 74 score: 0.8085 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 75 score: 0.7947 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 76 score: 0.8661 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 77 score: 0.8239 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 78 score: 0.9538 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 79 score: 0.8565 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 80 score: 0.8529 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 81 score: 0.9280 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 82 score: 0.8602 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 83 score: 0.7830 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 84 score: 0.7923 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 85 score: 0.7497 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 86 score: 0.6963 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 87 score: 0.8104 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 88 score: 0.8685 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 89 score: 0.6253 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 90 score: 0.7149 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 91 score: 0.4920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 92 score: 0.5236 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 93 score: 0.5019 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 94 score: 0.8614 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 95 score: 0.7454 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 96 score: 0.6510 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 97 score: 0.8261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 98 score: 0.7361 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 99 score: 0.6750 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 100 score: 0.6411 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 101 score: 0.7482 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 102 score: 0.8355 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 103 score: 0.9260 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 104 score: 0.8343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 105 score: 0.7279 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 106 score: 0.8487 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 107 score: 0.8885 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 108 score: 0.6508 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 109 score: 0.5365 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 110 score: 0.7823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 111 score: 0.9119 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 112 score: 0.9344 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 113 score: 0.8560 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 114 score: 0.7139 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 115 score: 0.7966 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 116 score: 0.7078 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 117 score: 0.7629 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 118 score: 0.6157 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 119 score: 0.7123 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 120 score: 0.7490 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 121 score: 0.7757 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 122 score: 0.9081 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 123 score: 0.9083 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 124 score: 0.8229 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 125 score: 0.8762 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 126 score: 0.8301 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 127 score: 0.8574 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 128 score: 0.8694 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 129 score: 0.6455 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 130 score: 0.8198 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 131 score: 0.6374 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 132 score: 0.8523 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 133 score: 0.6692 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 134 score: 0.8032 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 135 score: 0.8863 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 136 score: 0.8944 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 137 score: 0.7169 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 138 score: 0.5835 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 139 score: 0.8907 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 140 score: 0.7693 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 141 score: 0.8631 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 142 score: 0.8129 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 143 score: 0.8578 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 144 score: 0.8266 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 145 score: 0.8795 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 146 score: 0.9215 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 147 score: 0.9182 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 148 score: 0.5847 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 149 score: 0.8738 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 150 score: 0.8231 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 151 score: 0.8455 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 152 score: 0.7361 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 153 score: 0.7679 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 154 score: 0.7157 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 155 score: 0.8753 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 156 score: 0.8716 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 157 score: 0.6581 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 158 score: 0.7596 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 159 score: 0.6126 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 160 score: 0.6512 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 161 score: 0.7374 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 162 score: 0.8196 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 163 score: 0.8350 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 164 score: 0.8261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 165 score: 0.7550 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 166 score: 0.8000 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 167 score: 0.8573 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 168 score: 0.8104 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 169 score: 0.7165 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 170 score: 0.7882 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 171 score: 0.9007 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 172 score: 0.7027 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 173 score: 0.7903 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 174 score: 0.6021 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 175 score: 0.8457 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 176 score: 0.8560 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 177 score: 0.7609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 178 score: 0.6573 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 179 score: 0.7109 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 180 score: 0.8715 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 181 score: 0.9049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 182 score: 0.8507 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 183 score: 0.8583 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 184 score: 0.8615 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 185 score: 0.8995 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 186 score: 0.9172 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 187 score: 0.7134 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 188 score: 0.7561 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 189 score: 0.7559 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 190 score: 0.5487 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 191 score: 0.3664 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 192 score: 0.8255 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 193 score: 0.7797 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 194 score: 0.5921 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 195 score: 0.7415 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 196 score: 0.8784 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 197 score: 0.7962 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 198 score: 0.8077 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 199 score: 0.6508 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 200 score: 0.7099 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 201 score: 0.6059 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 202 score: 0.7153 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 203 score: 0.6867 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 204 score: 0.8533 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 205 score: 0.7145 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 206 score: 0.8498 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 207 score: 0.6777 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 208 score: 0.7246 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 209 score: 0.7670 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 210 score: 0.8345 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 211 score: 0.9126 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 212 score: 0.8013 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 213 score: 0.7290 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 214 score: 0.8651 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 215 score: 0.8669 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 216 score: 0.8688 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 217 score: 0.8188 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 218 score: 0.8596 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 219 score: 0.6315 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 220 score: 0.8189 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 221 score: 0.8495 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 222 score: 0.9099 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 223 score: 0.8207 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 224 score: 0.8921 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 225 score: 0.6549 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 226 score: 0.8977 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 227 score: 0.6071 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 228 score: 0.7343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 229 score: 0.7329 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 230 score: 0.9022 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 231 score: 0.7093 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 232 score: 0.8104 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 233 score: 0.5896 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 234 score: 0.6344 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 235 score: 0.7765 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 236 score: 0.8784 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 237 score: 0.8223 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 238 score: 0.8952 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 239 score: 0.8616 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 240 score: 0.7592 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 241 score: 0.8137 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 242 score: 0.7745 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 243 score: 0.6418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 244 score: 0.7201 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 245 score: 0.8400 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 246 score: 0.6838 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 247 score: 0.8117 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 248 score: 0.6901 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 249 score: 0.8428 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 250 score: 0.7257 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 251 score: 0.9108 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 252 score: 0.8433 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 253 score: 0.7710 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 254 score: 0.8415 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 255 score: 0.9431 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 256 score: 0.4677 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 257 score: 0.5987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 258 score: 0.6893 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 259 score: 0.5798 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 260 score: 0.7467 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 261 score: 0.8027 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 262 score: 0.5577 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 263 score: 0.5878 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 264 score: 0.9261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 265 score: 0.7820 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 266 score: 0.6016 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 267 score: 0.8154 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 268 score: 0.9235 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 269 score: 0.8888 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 270 score: 0.6284 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 271 score: 0.7211 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 272 score: 0.7520 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 273 score: 0.7686 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 274 score: 0.7136 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 275 score: 0.7859 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 276 score: 0.6482 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 277 score: 0.9118 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 278 score: 0.8146 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 279 score: 0.4617 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 280 score: 0.8797 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 281 score: 0.9130 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 282 score: 0.9225 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 283 score: 0.7506 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 284 score: 0.8087 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 285 score: 0.9193 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 286 score: 0.7997 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 287 score: 0.8994 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 288 score: 0.8315 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 289 score: 0.7780 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 290 score: 0.8212 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 291 score: 0.8306 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 292 score: 0.7898 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 293 score: 0.8734 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 294 score: 0.5449 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 295 score: 0.5305 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 296 score: 0.7316 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 297 score: 0.9044 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 298 score: 0.9323 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 299 score: 0.7619 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 300 score: 0.9075 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 301 score: 0.8418 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 302 score: 0.7317 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 303 score: 0.9144 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 304 score: 0.8325 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 305 score: 0.7285 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 306 score: 0.8553 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 307 score: 0.8311 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 308 score: 0.7669 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 309 score: 0.8737 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 310 score: 0.8848 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 311 score: 0.8238 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 312 score: 0.8589 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 313 score: 0.5864 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 314 score: 0.9048 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 315 score: 0.8912 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 316 score: 0.8366 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 317 score: 0.6963 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 318 score: 0.6473 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 319 score: 0.5870 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 320 score: 0.7727 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 321 score: 0.7679 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 322 score: 0.8835 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 323 score: 0.8800 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 324 score: 0.9105 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 325 score: 0.8458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 326 score: 0.8148 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 327 score: 0.7822 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 328 score: 0.9037 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 329 score: 0.5739 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 330 score: 0.8203 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 331 score: 0.8042 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 332 score: 0.7819 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 333 score: 0.7924 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 334 score: 0.5577 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 335 score: 0.8995 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 336 score: 0.8370 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 337 score: 0.7511 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 338 score: 0.8496 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 339 score: 0.8827 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 340 score: 0.8060 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 341 score: 0.8784 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 342 score: 0.5828 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 343 score: 0.7088 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 344 score: 0.8356 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 345 score: 0.7143 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 346 score: 0.8423 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 347 score: 0.6614 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 348 score: 0.7105 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 349 score: 0.5911 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 350 score: 0.5310 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 351 score: 0.7035 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 352 score: 0.8367 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 353 score: 0.8541 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 354 score: 0.7651 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 355 score: 0.8494 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 356 score: 0.5350 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 357 score: 0.8904 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 358 score: 0.8671 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 359 score: 0.6666 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 360 score: 0.6693 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 361 score: 0.7210 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 362 score: 0.7916 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 363 score: 0.5980 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 364 score: 0.5301 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 365 score: 0.6599 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 366 score: 0.7946 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 367 score: 0.7225 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 368 score: 0.7070 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 369 score: 0.7945 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 370 score: 0.7620 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 371 score: 0.7557 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 372 score: 0.8159 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 373 score: 0.8373 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 374 score: 0.6810 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 375 score: 0.8940 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 376 score: 0.8651 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 377 score: 0.9265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 378 score: 0.8426 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 379 score: 0.9179 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 380 score: 0.9228 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 381 score: 0.7688 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 382 score: 0.5044 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 383 score: 0.7871 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 384 score: 0.8510 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 385 score: 0.7498 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 386 score: 0.7699 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 387 score: 0.8646 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 388 score: 0.6378 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 389 score: 0.8265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 390 score: 0.8637 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 391 score: 0.8826 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 392 score: 0.7845 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 393 score: 0.7666 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 394 score: 0.6150 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 395 score: 0.7113 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 396 score: 0.8476 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 397 score: 0.8137 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 398 score: 0.6481 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 399 score: 0.7231 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 400 score: 0.9348 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 401 score: 0.6213 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 402 score: 0.6221 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 403 score: 0.7937 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 404 score: 0.5686 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 405 score: 0.6790 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 406 score: 0.8810 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 407 score: 0.7458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 408 score: 0.6961 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 409 score: 0.8952 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 410 score: 0.7205 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 411 score: 0.7380 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 412 score: 0.7141 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 413 score: 0.6497 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 414 score: 0.8667 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 415 score: 0.8510 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 416 score: 0.8442 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 417 score: 0.7822 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 418 score: 0.9003 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 419 score: 0.8853 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 420 score: 0.8541 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 421 score: 0.9032 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 422 score: 0.7796 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 423 score: 0.7513 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 424 score: 0.6770 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 425 score: 0.8876 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 426 score: 0.8394 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 427 score: 0.7895 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 428 score: 0.8990 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 429 score: 0.6146 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 430 score: 0.8746 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 431 score: 0.7320 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 432 score: 0.7264 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 433 score: 0.8049 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 434 score: 0.7122 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 435 score: 0.6246 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 436 score: 0.8187 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 437 score: 0.8774 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 438 score: 0.8901 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 439 score: 0.8405 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 440 score: 0.7197 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 441 score: 0.6030 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 442 score: 0.8374 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 443 score: 0.7897 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 444 score: 0.7535 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 445 score: 0.7739 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 446 score: 0.8679 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 447 score: 0.9020 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 448 score: 0.8672 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 449 score: 0.6784 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 450 score: 0.8580 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 451 score: 0.5787 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 452 score: 0.7930 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 453 score: 0.7577 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 454 score: 0.8309 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 455 score: 0.7758 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 456 score: 0.8245 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 457 score: 0.6930 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 458 score: 0.7108 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 459 score: 0.7898 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 460 score: 0.8838 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 461 score: 0.7704 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 462 score: 0.8458 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 463 score: 0.8770 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 464 score: 0.8633 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 465 score: 0.8098 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 466 score: 0.8815 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 467 score: 0.7548 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 468 score: 0.6296 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 469 score: 0.6429 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 470 score: 0.7031 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 471 score: 0.6981 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 472 score: 0.8380 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 473 score: 0.6556 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 474 score: 0.6931 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 475 score: 0.8193 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 476 score: 0.6565 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 477 score: 0.7416 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 478 score: 0.8638 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 479 score: 0.9112 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 480 score: 0.8841 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 481 score: 0.7859 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 482 score: 0.7990 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 483 score: 0.6265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 484 score: 0.7971 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 485 score: 0.7033 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 486 score: 0.6664 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 487 score: 0.7763 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 488 score: 0.8087 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 489 score: 0.7769 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 490 score: 0.6571 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 491 score: 0.8081 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 492 score: 0.9170 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 493 score: 0.8773 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 494 score: 0.6091 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 495 score: 0.8277 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 496 score: 0.7146 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 497 score: 0.7353 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 498 score: 0.9169 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 499 score: 0.8220 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 500 score: 0.8585 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 501 score: 0.7903 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 502 score: 0.7188 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 503 score: 0.8318 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 504 score: 0.7178 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 505 score: 0.6624 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 506 score: 0.6990 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 507 score: 0.7785 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 508 score: 0.7591 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 509 score: 0.8463 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 510 score: 0.5366 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 511 score: 0.7621 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 512 score: 0.8922 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 513 score: 0.8830 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 514 score: 0.7607 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 515 score: 0.8906 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 516 score: 0.6681 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 517 score: 0.7003 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 518 score: 0.7282 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 519 score: 0.8139 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 520 score: 0.7712 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 521 score: 0.7449 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 522 score: 0.7369 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 523 score: 0.8160 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 524 score: 0.8079 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 525 score: 0.8299 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 526 score: 0.6539 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 527 score: 0.5376 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 528 score: 0.7041 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 529 score: 0.7652 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 530 score: 0.6121 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 531 score: 0.8034 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 532 score: 0.6986 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 533 score: 0.7632 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 534 score: 0.8127 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 535 score: 0.7520 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 536 score: 0.6955 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 537 score: 0.4773 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 538 score: 0.5651 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 539 score: 0.7444 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 540 score: 0.8315 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 541 score: 0.6045 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 542 score: 0.7476 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 543 score: 0.7426 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 544 score: 0.8425 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 545 score: 0.8539 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 546 score: 0.7690 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 547 score: 0.8282 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 548 score: 0.7689 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 549 score: 0.9208 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 550 score: 0.7812 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 551 score: 0.8878 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 552 score: 0.5383 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 553 score: 0.8002 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 554 score: 0.8056 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 555 score: 0.8396 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 556 score: 0.6150 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 557 score: 0.8548 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 558 score: 0.7018 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 559 score: 0.7948 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 560 score: 0.4615 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 561 score: 0.8690 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 562 score: 0.7719 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 563 score: 0.4608 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 564 score: 0.7609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 565 score: 0.8088 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 566 score: 0.8937 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 567 score: 0.8389 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 568 score: 0.7272 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 569 score: 0.5596 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 570 score: 0.8228 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 571 score: 0.8110 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 572 score: 0.5937 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 573 score: 0.8556 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 574 score: 0.9301 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 575 score: 0.7593 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 576 score: 0.6718 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 577 score: 0.8785 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 578 score: 0.8316 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 579 score: 0.4985 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 580 score: 0.7346 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 581 score: 0.6129 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 582 score: 0.9064 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 583 score: 0.6447 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 584 score: 0.5975 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 585 score: 0.8083 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 586 score: 0.8319 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 587 score: 0.6794 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 588 score: 0.7021 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 589 score: 0.7726 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 590 score: 0.8952 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 591 score: 0.9124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 592 score: 0.6879 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 593 score: 0.7585 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 594 score: 0.9056 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 595 score: 0.9083 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 596 score: 0.6179 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 597 score: 0.8312 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 598 score: 0.4935 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 599 score: 0.8779 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 600 score: 0.8857 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 601 score: 0.7428 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 602 score: 0.6343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 603 score: 0.6271 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 604 score: 0.9017 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 605 score: 0.8867 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 606 score: 0.7119 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 607 score: 0.8062 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 608 score: 0.8176 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 609 score: 0.6705 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 610 score: 0.6967 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 611 score: 0.7894 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 612 score: 0.8898 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 613 score: 0.7796 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 614 score: 0.7283 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 615 score: 0.8386 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 616 score: 0.8593 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 617 score: 0.8596 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 618 score: 0.8707 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 619 score: 0.7175 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 620 score: 0.7772 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 621 score: 0.3900 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 622 score: 0.9152 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 623 score: 0.8653 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 624 score: 0.7270 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 625 score: 0.7979 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 626 score: 0.9022 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 627 score: 0.9143 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 628 score: 0.9261 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 629 score: 0.6987 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 630 score: 0.8683 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 631 score: 0.8279 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 632 score: 0.8765 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 633 score: 0.8776 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 634 score: 0.9517 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 635 score: 0.8314 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 636 score: 0.9090 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 637 score: 0.5856 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 638 score: 0.6609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 639 score: 0.7411 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 640 score: 0.8547 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 641 score: 0.8488 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 642 score: 0.8543 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 643 score: 0.6696 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 644 score: 0.6936 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 645 score: 0.6417 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 646 score: 0.5678 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 647 score: 0.8206 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 648 score: 0.6508 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 649 score: 0.5585 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 650 score: 0.5868 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 651 score: 0.7890 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 652 score: 0.4802 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 653 score: 0.6216 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 654 score: 0.6330 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 655 score: 0.8855 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 656 score: 0.8779 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 657 score: 0.8607 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 658 score: 0.7469 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 659 score: 0.7821 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 660 score: 0.8533 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 661 score: 0.9109 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 662 score: 0.8502 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 663 score: 0.8309 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 664 score: 0.8678 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 665 score: 0.7783 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 666 score: 0.8380 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 667 score: 0.8617 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 668 score: 0.7716 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 669 score: 0.9013 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 670 score: 0.8787 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 671 score: 0.8564 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 672 score: 0.8152 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 673 score: 0.8461 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 674 score: 0.8370 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 675 score: 0.7968 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 676 score: 0.8730 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 677 score: 0.8243 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 678 score: 0.8374 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 679 score: 0.9167 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 680 score: 0.8296 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 681 score: 0.9101 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 682 score: 0.8316 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 683 score: 0.8522 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 684 score: 0.7835 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 685 score: 0.7423 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 686 score: 0.8033 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 687 score: 0.7483 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 688 score: 0.8873 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 689 score: 0.8591 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 690 score: 0.8876 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 691 score: 0.8872 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 692 score: 0.8966 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 693 score: 0.6652 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 694 score: 0.6785 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 695 score: 0.8999 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 696 score: 0.7382 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 697 score: 0.7396 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 698 score: 0.5554 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 699 score: 0.9158 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 700 score: 0.4745 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 701 score: 0.7639 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 702 score: 0.8591 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 703 score: 0.8592 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 704 score: 0.4517 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 705 score: 0.8419 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 706 score: 0.7387 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 707 score: 0.6107 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 708 score: 0.9338 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 709 score: 0.8958 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 710 score: 0.9105 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 711 score: 0.7799 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 712 score: 0.8778 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 713 score: 0.6844 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 714 score: 0.8139 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 715 score: 0.7721 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 716 score: 0.8612 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 717 score: 0.8397 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 718 score: 0.7778 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 719 score: 0.7295 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 720 score: 0.5976 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 721 score: 0.6984 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 722 score: 0.8957 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 723 score: 0.8981 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 724 score: 0.9081 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 725 score: 0.7567 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 726 score: 0.8291 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 727 score: 0.6964 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 728 score: 0.5115 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 729 score: 0.7995 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 730 score: 0.8180 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 731 score: 0.8231 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 732 score: 0.8506 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 733 score: 0.7666 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 734 score: 0.5984 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 735 score: 0.8206 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 736 score: 0.8609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 737 score: 0.7192 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 738 score: 0.9142 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 739 score: 0.8725 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 740 score: 0.7530 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 741 score: 0.8729 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 742 score: 0.8520 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 743 score: 0.8991 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 744 score: 0.8360 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 745 score: 0.8843 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 746 score: 0.6947 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 747 score: 0.7046 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 748 score: 0.8881 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 749 score: 0.8767 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 750 score: 0.7715 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 751 score: 0.8680 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 752 score: 0.8928 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 753 score: 0.8241 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 754 score: 0.8876 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 755 score: 0.8122 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 756 score: 0.7702 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 757 score: 0.7292 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 758 score: 0.8364 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 759 score: 0.8641 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 760 score: 0.9198 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 761 score: 0.8834 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 762 score: 0.9090 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 763 score: 0.8679 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 764 score: 0.8738 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 765 score: 0.6427 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 766 score: 0.8969 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 767 score: 0.8169 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 768 score: 0.9213 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 769 score: 0.9342 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 770 score: 0.5658 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 771 score: 0.9234 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 772 score: 0.7430 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 773 score: 0.8588 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 774 score: 0.8819 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 775 score: 0.5710 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 776 score: 0.8264 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 777 score: 0.8685 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 778 score: 0.9064 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 779 score: 0.8662 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 780 score: 0.8539 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 781 score: 0.8265 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 782 score: 0.6416 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 783 score: 0.7135 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 784 score: 0.7515 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 785 score: 0.7519 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 786 score: 0.9217 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 787 score: 0.8160 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 788 score: 0.9010 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 789 score: 0.8372 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 790 score: 0.8991 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 791 score: 0.8149 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 792 score: 0.8770 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 793 score: 0.8650 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 794 score: 0.9014 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 795 score: 0.8597 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 796 score: 0.9595 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 797 score: 0.5810 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 798 score: 0.9119 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 799 score: 0.7574 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 800 score: 0.7082 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 801 score: 0.6694 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 802 score: 0.7638 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 803 score: 0.8505 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 804 score: 0.6392 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 805 score: 0.8929 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 806 score: 0.8977 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 807 score: 0.8824 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 808 score: 0.8196 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 809 score: 0.7806 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 810 score: 0.7479 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 811 score: 0.4584 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 812 score: 0.9107 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 813 score: 0.9234 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 814 score: 0.8787 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 815 score: 0.7387 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 816 score: 0.8440 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 817 score: 0.6293 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 818 score: 0.6765 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 819 score: 0.6066 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 820 score: 0.9076 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 821 score: 0.7125 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 822 score: 0.8370 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 823 score: 0.7848 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 824 score: 0.8354 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 825 score: 0.6920 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 826 score: 0.7540 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 827 score: 0.8662 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 828 score: 0.8160 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 829 score: 0.8288 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 830 score: 0.8582 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 831 score: 0.7985 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 832 score: 0.8114 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 833 score: 0.5213 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 834 score: 0.8368 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 835 score: 0.6415 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 836 score: 0.6421 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 837 score: 0.7439 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 838 score: 0.7485 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 839 score: 0.8191 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 840 score: 0.8396 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 841 score: 0.7865 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 842 score: 0.5504 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 843 score: 0.8826 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 844 score: 0.8348 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 845 score: 0.5275 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 846 score: 0.7766 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 847 score: 0.7311 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 848 score: 0.6824 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 849 score: 0.8647 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 850 score: 0.6228 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 851 score: 0.8621 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 852 score: 0.8514 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 853 score: 0.7356 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 854 score: 0.6981 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 855 score: 0.8178 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 856 score: 0.7377 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 857 score: 0.8496 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 858 score: 0.7345 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 859 score: 0.8794 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 860 score: 0.8054 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 861 score: 0.8165 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 862 score: 0.7651 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 863 score: 0.6947 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 864 score: 0.6376 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 865 score: 0.6122 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 866 score: 0.8421 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 867 score: 0.8343 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 868 score: 0.8388 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 869 score: 0.8698 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 870 score: 0.7652 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 871 score: 0.8971 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 872 score: 0.6136 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 873 score: 0.9005 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 874 score: 0.8417 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 875 score: 0.8229 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 876 score: 0.8387 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 877 score: 0.8494 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 878 score: 0.8823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 879 score: 0.6446 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 880 score: 0.8069 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 881 score: 0.9021 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 882 score: 0.8601 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 883 score: 0.8401 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 884 score: 0.5455 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 885 score: 0.7762 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 886 score: 0.8637 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 887 score: 0.7753 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 888 score: 0.5361 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 889 score: 0.7124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 890 score: 0.6663 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 891 score: 0.4990 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 892 score: 0.6845 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 893 score: 0.6531 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 894 score: 0.8152 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 895 score: 0.8356 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 896 score: 0.8475 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 897 score: 0.8035 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 898 score: 0.8957 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 899 score: 0.7616 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 900 score: 0.7307 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 901 score: 0.5821 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 902 score: 0.5788 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 903 score: 0.7710 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 904 score: 0.8411 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 905 score: 0.5765 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 906 score: 0.5827 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 907 score: 0.4725 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 908 score: 0.7383 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 909 score: 0.9437 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 910 score: 0.8628 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 911 score: 0.7699 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 912 score: 0.8718 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 913 score: 0.8719 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 914 score: 0.8823 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 915 score: 0.8376 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 916 score: 0.8817 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 917 score: 0.8162 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 918 score: 0.6528 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 919 score: 0.8039 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 920 score: 0.7169 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 921 score: 0.8172 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 922 score: 0.8609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 923 score: 0.8420 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 924 score: 0.6614 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 925 score: 0.7890 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 926 score: 0.9083 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 927 score: 0.7980 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 928 score: 0.8836 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 929 score: 0.8066 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 930 score: 0.8739 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 931 score: 0.4885 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 932 score: 0.5318 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 933 score: 0.8813 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 934 score: 0.8220 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 935 score: 0.6794 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 936 score: 0.8674 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 937 score: 0.9321 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 938 score: 0.7311 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 939 score: 0.8568 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 940 score: 0.7948 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 941 score: 0.9406 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 942 score: 0.8473 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 943 score: 0.7963 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 944 score: 0.7387 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 945 score: 0.6811 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 946 score: 0.7174 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 947 score: 0.5824 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 948 score: 0.6611 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 949 score: 0.7327 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 950 score: 0.5172 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 951 score: 0.6732 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 952 score: 0.8705 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 953 score: 0.7000 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 954 score: 0.7973 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 955 score: 0.8535 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 956 score: 0.7271 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 957 score: 0.8596 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 958 score: 0.8147 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 959 score: 0.5124 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 960 score: 0.7439 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 961 score: 0.5243 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 962 score: 0.5792 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 963 score: 0.8524 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 964 score: 0.9227 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 965 score: 0.7044 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 966 score: 0.8911 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 967 score: 0.6867 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 968 score: 0.7354 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 969 score: 0.7696 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 970 score: 0.8879 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 971 score: 0.8293 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 972 score: 0.7753 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 973 score: 0.7737 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 974 score: 0.7658 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 975 score: 0.9193 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 976 score: 0.7623 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 977 score: 0.7127 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 978 score: 0.4873 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 979 score: 0.6406 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 980 score: 0.7609 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 981 score: 0.8434 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 982 score: 0.7136 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 983 score: 0.7967 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 984 score: 0.9305 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 985 score: 0.6101 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 986 score: 0.9027 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 987 score: 0.6178 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 988 score: 0.6617 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 989 score: 0.5595 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 990 score: 0.8915 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 991 score: 0.8648 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 992 score: 0.9116 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 993 score: 0.7111 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 994 score: 0.7562 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 995 score: 0.8274 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 996 score: 0.9341 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 997 score: 0.9361 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 998 score: 0.8619 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 999 score: 0.8425 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1000 score: 0.8234 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1001 score: 0.7534 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1002 score: 0.7509 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1003 score: 0.6634 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1004 score: 0.8586 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1005 score: 0.7158 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1006 score: 0.7162 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1007 score: 0.8543 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1008 score: 0.9038 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1009 score: 0.8477 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1010 score: 0.7701 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en Segment 1011 score: 0.8235 +/beacon-scratch/tongzh24/ALMA-checkpoint/exp_16_languages/alma-13b-sft-16-languages-he-max-tokens-512//test-he-en score: 0.7771