diff --git "a/test-en-th.comet" "b/test-en-th.comet" new file mode 100644--- /dev/null +++ "b/test-en-th.comet" @@ -0,0 +1,1013 @@ +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 0 score: 0.8375 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1 score: 0.8621 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 2 score: 0.9024 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 3 score: 0.8519 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 4 score: 0.9161 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 5 score: 0.7090 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 6 score: 0.8261 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 7 score: 0.8574 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 8 score: 0.8494 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 9 score: 0.8301 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 10 score: 0.8860 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 11 score: 0.8436 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 12 score: 0.8519 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 13 score: 0.9258 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 14 score: 0.8022 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 15 score: 0.7439 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 16 score: 0.8984 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 17 score: 0.8611 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 18 score: 0.9442 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 19 score: 0.8921 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 20 score: 0.8657 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 21 score: 0.8923 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 22 score: 0.6356 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 23 score: 0.8709 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 24 score: 0.8698 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 25 score: 0.8558 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 26 score: 0.8437 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 27 score: 0.9123 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 28 score: 0.8249 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 29 score: 0.8929 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 30 score: 0.6698 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 31 score: 0.8487 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 32 score: 0.7969 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 33 score: 0.8691 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 34 score: 0.8677 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 35 score: 0.9480 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 36 score: 0.8860 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 37 score: 0.8722 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 38 score: 0.7674 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 39 score: 0.9278 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 40 score: 0.8452 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 41 score: 0.8497 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 42 score: 0.9040 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 43 score: 0.8254 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 44 score: 0.7721 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 45 score: 0.8983 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 46 score: 0.9098 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 47 score: 0.9237 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 48 score: 0.8096 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 49 score: 0.7596 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 50 score: 0.8720 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 51 score: 0.9061 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 52 score: 0.9003 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 53 score: 0.8742 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 54 score: 0.8854 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 55 score: 0.8877 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 56 score: 0.8204 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 57 score: 0.8279 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 58 score: 0.8484 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 59 score: 0.9486 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 60 score: 0.8601 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 61 score: 0.9398 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 62 score: 0.8812 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 63 score: 0.8722 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 64 score: 0.7950 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 65 score: 0.7575 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 66 score: 0.8146 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 67 score: 0.6793 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 68 score: 0.9449 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 69 score: 0.8562 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 70 score: 0.8116 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 71 score: 0.8256 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 72 score: 0.9081 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 73 score: 0.8811 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 74 score: 0.8287 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 75 score: 0.8091 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 76 score: 0.8914 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 77 score: 0.9165 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 78 score: 0.8816 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 79 score: 0.3846 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 80 score: 0.7658 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 81 score: 0.8985 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 82 score: 0.8214 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 83 score: 0.8436 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 84 score: 0.8392 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 85 score: 0.7789 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 86 score: 0.8465 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 87 score: 0.8949 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 88 score: 0.9174 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 89 score: 0.7721 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 90 score: 0.7272 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 91 score: 0.8581 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 92 score: 0.8002 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 93 score: 0.9148 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 94 score: 0.9322 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 95 score: 0.8558 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 96 score: 0.9057 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 97 score: 0.7950 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 98 score: 0.8604 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 99 score: 0.8252 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 100 score: 0.9205 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 101 score: 0.8582 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 102 score: 0.9296 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 103 score: 0.9501 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 104 score: 0.8711 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 105 score: 0.7318 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 106 score: 0.8492 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 107 score: 0.8444 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 108 score: 0.7779 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 109 score: 0.7849 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 110 score: 0.8290 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 111 score: 0.9339 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 112 score: 0.9575 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 113 score: 0.8944 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 114 score: 0.8976 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 115 score: 0.9338 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 116 score: 0.9444 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 117 score: 0.8744 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 118 score: 0.9180 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 119 score: 0.9050 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 120 score: 0.6797 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 121 score: 0.9043 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 122 score: 0.9401 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 123 score: 0.9376 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 124 score: 0.8739 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 125 score: 0.8764 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 126 score: 0.9593 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 127 score: 0.9060 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 128 score: 0.9092 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 129 score: 0.9338 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 130 score: 0.8944 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 131 score: 0.8793 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 132 score: 0.9256 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 133 score: 0.9256 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 134 score: 0.6329 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 135 score: 0.6031 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 136 score: 0.9163 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 137 score: 0.7779 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 138 score: 0.7812 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 139 score: 0.8657 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 140 score: 0.8868 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 141 score: 0.8706 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 142 score: 0.9319 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 143 score: 0.8769 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 144 score: 0.9136 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 145 score: 0.9178 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 146 score: 0.8744 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 147 score: 0.8816 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 148 score: 0.8760 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 149 score: 0.8572 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 150 score: 0.8877 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 151 score: 0.8663 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 152 score: 0.8587 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 153 score: 0.7676 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 154 score: 0.6023 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 155 score: 0.8754 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 156 score: 0.9050 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 157 score: 0.8067 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 158 score: 0.8599 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 159 score: 0.9238 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 160 score: 0.8670 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 161 score: 0.8427 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 162 score: 0.8319 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 163 score: 0.8946 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 164 score: 0.8189 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 165 score: 0.8690 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 166 score: 0.9282 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 167 score: 0.8723 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 168 score: 0.9188 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 169 score: 0.8604 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 170 score: 0.8286 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 171 score: 0.9747 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 172 score: 0.8829 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 173 score: 0.8785 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 174 score: 0.8337 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 175 score: 0.8521 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 176 score: 0.6645 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 177 score: 0.8575 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 178 score: 0.8352 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 179 score: 0.8855 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 180 score: 0.7672 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 181 score: 0.8951 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 182 score: 0.9169 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 183 score: 0.9105 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 184 score: 0.9045 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 185 score: 0.9399 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 186 score: 0.9110 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 187 score: 0.8387 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 188 score: 0.9029 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 189 score: 0.8705 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 190 score: 0.9315 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 191 score: 0.8040 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 192 score: 0.7067 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 193 score: 0.8271 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 194 score: 0.8304 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 195 score: 0.8327 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 196 score: 0.5787 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 197 score: 0.8163 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 198 score: 0.8977 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 199 score: 0.8664 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 200 score: 0.8639 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 201 score: 0.7930 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 202 score: 0.7695 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 203 score: 0.5377 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 204 score: 0.8976 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 205 score: 0.8663 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 206 score: 0.9480 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 207 score: 0.9333 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 208 score: 0.8663 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 209 score: 0.8313 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 210 score: 0.8883 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 211 score: 0.9232 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 212 score: 0.8724 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 213 score: 0.9212 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 214 score: 0.8630 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 215 score: 0.8127 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 216 score: 0.8934 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 217 score: 0.8938 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 218 score: 0.9352 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 219 score: 0.9286 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 220 score: 0.8719 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 221 score: 0.9328 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 222 score: 0.9170 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 223 score: 0.8902 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 224 score: 0.8987 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 225 score: 0.8551 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 226 score: 0.9250 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 227 score: 0.7218 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 228 score: 0.8363 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 229 score: 0.8521 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 230 score: 0.9005 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 231 score: 0.7409 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 232 score: 0.8949 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 233 score: 0.6723 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 234 score: 0.8478 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 235 score: 0.8472 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 236 score: 0.8439 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 237 score: 0.8357 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 238 score: 0.9025 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 239 score: 0.8283 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 240 score: 0.8243 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 241 score: 0.6723 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 242 score: 0.9587 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 243 score: 0.8651 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 244 score: 0.7999 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 245 score: 0.8017 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 246 score: 0.7981 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 247 score: 0.8586 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 248 score: 0.8200 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 249 score: 0.9101 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 250 score: 0.9261 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 251 score: 0.9234 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 252 score: 0.9361 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 253 score: 0.8654 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 254 score: 0.8948 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 255 score: 0.9405 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 256 score: 0.8638 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 257 score: 0.9035 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 258 score: 0.8798 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 259 score: 0.8133 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 260 score: 0.8959 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 261 score: 0.8597 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 262 score: 0.8815 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 263 score: 0.8453 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 264 score: 0.8919 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 265 score: 0.8873 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 266 score: 0.8916 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 267 score: 0.8361 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 268 score: 0.9183 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 269 score: 0.7683 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 270 score: 0.7978 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 271 score: 0.7585 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 272 score: 0.9267 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 273 score: 0.7014 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 274 score: 0.7711 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 275 score: 0.8232 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 276 score: 0.7893 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 277 score: 0.8452 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 278 score: 0.8727 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 279 score: 0.6701 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 280 score: 0.9321 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 281 score: 0.9417 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 282 score: 0.9370 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 283 score: 0.9047 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 284 score: 0.8301 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 285 score: 0.9265 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 286 score: 0.9110 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 287 score: 0.8552 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 288 score: 0.9213 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 289 score: 0.8935 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 290 score: 0.8975 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 291 score: 0.9295 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 292 score: 0.9347 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 293 score: 0.8855 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 294 score: 0.8591 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 295 score: 0.7887 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 296 score: 0.8359 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 297 score: 0.9181 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 298 score: 0.8682 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 299 score: 0.9219 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 300 score: 0.9177 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 301 score: 0.9140 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 302 score: 0.8694 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 303 score: 0.9361 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 304 score: 0.8726 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 305 score: 0.8627 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 306 score: 0.8754 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 307 score: 0.8802 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 308 score: 0.8598 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 309 score: 0.9054 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 310 score: 0.8165 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 311 score: 0.8324 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 312 score: 0.9008 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 313 score: 0.7662 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 314 score: 0.9336 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 315 score: 0.9593 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 316 score: 0.7355 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 317 score: 0.9094 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 318 score: 0.8744 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 319 score: 0.7189 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 320 score: 0.8160 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 321 score: 0.6743 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 322 score: 0.8697 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 323 score: 0.8926 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 324 score: 0.9357 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 325 score: 0.9159 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 326 score: 0.7293 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 327 score: 0.9134 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 328 score: 0.9090 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 329 score: 0.8812 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 330 score: 0.8872 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 331 score: 0.8952 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 332 score: 0.9106 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 333 score: 0.8931 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 334 score: 0.9164 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 335 score: 0.9164 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 336 score: 0.8933 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 337 score: 0.7913 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 338 score: 0.8236 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 339 score: 0.9389 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 340 score: 0.8401 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 341 score: 0.8671 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 342 score: 0.7341 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 343 score: 0.8034 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 344 score: 0.8870 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 345 score: 0.9299 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 346 score: 0.9316 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 347 score: 0.8891 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 348 score: 0.8826 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 349 score: 0.8579 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 350 score: 0.8066 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 351 score: 0.8193 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 352 score: 0.8844 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 353 score: 0.9517 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 354 score: 0.9120 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 355 score: 0.9036 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 356 score: 0.8942 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 357 score: 0.9150 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 358 score: 0.8126 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 359 score: 0.8353 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 360 score: 0.8304 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 361 score: 0.7991 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 362 score: 0.8838 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 363 score: 0.5042 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 364 score: 0.8644 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 365 score: 0.8630 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 366 score: 0.7035 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 367 score: 0.8421 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 368 score: 0.3936 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 369 score: 0.8604 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 370 score: 0.8359 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 371 score: 0.7603 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 372 score: 0.8512 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 373 score: 0.9151 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 374 score: 0.9214 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 375 score: 0.9287 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 376 score: 0.9206 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 377 score: 0.8971 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 378 score: 0.8661 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 379 score: 0.9100 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 380 score: 0.9168 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 381 score: 0.8023 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 382 score: 0.8255 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 383 score: 0.8333 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 384 score: 0.9014 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 385 score: 0.8700 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 386 score: 0.7939 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 387 score: 0.8883 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 388 score: 0.8552 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 389 score: 0.9321 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 390 score: 0.9101 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 391 score: 0.8300 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 392 score: 0.7266 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 393 score: 0.9081 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 394 score: 0.9065 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 395 score: 0.9001 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 396 score: 0.8309 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 397 score: 0.8847 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 398 score: 0.7253 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 399 score: 0.9154 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 400 score: 0.9496 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 401 score: 0.8322 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 402 score: 0.9143 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 403 score: 0.6857 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 404 score: 0.7755 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 405 score: 0.7678 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 406 score: 0.8115 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 407 score: 0.9099 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 408 score: 0.9258 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 409 score: 0.8865 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 410 score: 0.5723 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 411 score: 0.8013 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 412 score: 0.8317 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 413 score: 0.8899 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 414 score: 0.8914 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 415 score: 0.8704 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 416 score: 0.8312 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 417 score: 0.9183 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 418 score: 0.9144 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 419 score: 0.9204 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 420 score: 0.9486 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 421 score: 0.9557 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 422 score: 0.9285 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 423 score: 0.8606 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 424 score: 0.8895 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 425 score: 0.8794 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 426 score: 0.8781 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 427 score: 0.6181 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 428 score: 0.8194 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 429 score: 0.9146 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 430 score: 0.9217 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 431 score: 0.7705 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 432 score: 0.7792 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 433 score: 0.8757 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 434 score: 0.7114 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 435 score: 0.5475 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 436 score: 0.8837 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 437 score: 0.8537 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 438 score: 0.9423 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 439 score: 0.8685 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 440 score: 0.8817 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 441 score: 0.9297 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 442 score: 0.8626 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 443 score: 0.4592 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 444 score: 0.8192 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 445 score: 0.9020 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 446 score: 0.9055 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 447 score: 0.9465 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 448 score: 0.9358 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 449 score: 0.8314 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 450 score: 0.9089 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 451 score: 0.9213 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 452 score: 0.9341 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 453 score: 0.8640 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 454 score: 0.9214 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 455 score: 0.8724 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 456 score: 0.7709 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 457 score: 0.9608 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 458 score: 0.9007 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 459 score: 0.8521 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 460 score: 0.8981 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 461 score: 0.8490 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 462 score: 0.9020 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 463 score: 0.8860 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 464 score: 0.8988 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 465 score: 0.6690 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 466 score: 0.8869 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 467 score: 0.6988 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 468 score: 0.5675 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 469 score: 0.7470 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 470 score: 0.8939 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 471 score: 0.8135 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 472 score: 0.6945 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 473 score: 0.8301 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 474 score: 0.8563 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 475 score: 0.8927 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 476 score: 0.8492 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 477 score: 0.6969 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 478 score: 0.8754 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 479 score: 0.9370 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 480 score: 0.8644 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 481 score: 0.8105 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 482 score: 0.8297 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 483 score: 0.8387 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 484 score: 0.8996 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 485 score: 0.8898 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 486 score: 0.7857 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 487 score: 0.6648 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 488 score: 0.8847 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 489 score: 0.8904 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 490 score: 0.8462 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 491 score: 0.9059 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 492 score: 0.9745 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 493 score: 0.9572 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 494 score: 0.9070 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 495 score: 0.8062 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 496 score: 0.9253 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 497 score: 0.9194 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 498 score: 0.9344 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 499 score: 0.7577 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 500 score: 0.9435 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 501 score: 0.8600 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 502 score: 0.9170 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 503 score: 0.8195 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 504 score: 0.7279 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 505 score: 0.8680 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 506 score: 0.7793 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 507 score: 0.9269 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 508 score: 0.8533 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 509 score: 0.8997 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 510 score: 0.6787 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 511 score: 0.8747 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 512 score: 0.8016 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 513 score: 0.8708 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 514 score: 0.8913 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 515 score: 0.8889 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 516 score: 0.6633 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 517 score: 0.9182 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 518 score: 0.8986 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 519 score: 0.8690 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 520 score: 0.8185 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 521 score: 0.8128 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 522 score: 0.8904 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 523 score: 0.7781 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 524 score: 0.9136 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 525 score: 0.8883 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 526 score: 0.7592 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 527 score: 0.7988 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 528 score: 0.8554 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 529 score: 0.8648 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 530 score: 0.8849 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 531 score: 0.8993 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 532 score: 0.8009 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 533 score: 0.8488 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 534 score: 0.8653 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 535 score: 0.7674 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 536 score: 0.8413 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 537 score: 0.8454 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 538 score: 0.9089 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 539 score: 0.9012 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 540 score: 0.8714 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 541 score: 0.9065 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 542 score: 0.8054 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 543 score: 0.8488 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 544 score: 0.3577 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 545 score: 0.9462 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 546 score: 0.8820 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 547 score: 0.9047 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 548 score: 0.2419 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 549 score: 0.9612 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 550 score: 0.8938 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 551 score: 0.8906 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 552 score: 0.8883 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 553 score: 0.8857 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 554 score: 0.7662 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 555 score: 0.8502 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 556 score: 0.7918 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 557 score: 0.8106 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 558 score: 0.7971 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 559 score: 0.8228 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 560 score: 0.8209 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 561 score: 0.9032 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 562 score: 0.8515 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 563 score: 0.7152 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 564 score: 0.8471 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 565 score: 0.9296 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 566 score: 0.8747 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 567 score: 0.9251 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 568 score: 0.7540 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 569 score: 0.8112 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 570 score: 0.8176 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 571 score: 0.8714 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 572 score: 0.7746 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 573 score: 0.9032 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 574 score: 0.9301 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 575 score: 0.9203 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 576 score: 0.8150 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 577 score: 0.9135 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 578 score: 0.8833 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 579 score: 0.8889 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 580 score: 0.7775 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 581 score: 0.9252 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 582 score: 0.8600 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 583 score: 0.8897 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 584 score: 0.6976 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 585 score: 0.8474 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 586 score: 0.9047 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 587 score: 0.8705 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 588 score: 0.7568 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 589 score: 0.8144 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 590 score: 0.8102 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 591 score: 0.9238 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 592 score: 0.8378 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 593 score: 0.9109 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 594 score: 0.8531 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 595 score: 0.9267 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 596 score: 0.8019 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 597 score: 0.8595 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 598 score: 0.8316 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 599 score: 0.7938 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 600 score: 0.7979 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 601 score: 0.7967 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 602 score: 0.8927 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 603 score: 0.8923 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 604 score: 0.8737 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 605 score: 0.9371 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 606 score: 0.8308 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 607 score: 0.7753 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 608 score: 0.6867 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 609 score: 0.8524 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 610 score: 0.9202 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 611 score: 0.9107 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 612 score: 0.9160 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 613 score: 0.8792 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 614 score: 0.9309 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 615 score: 0.8968 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 616 score: 0.9396 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 617 score: 0.9681 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 618 score: 0.8997 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 619 score: 0.8298 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 620 score: 0.8317 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 621 score: 0.8507 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 622 score: 0.9211 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 623 score: 0.8993 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 624 score: 0.8864 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 625 score: 0.8693 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 626 score: 0.9383 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 627 score: 0.9222 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 628 score: 0.9238 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 629 score: 0.8751 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 630 score: 0.9077 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 631 score: 0.8804 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 632 score: 0.9444 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 633 score: 0.9370 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 634 score: 0.9487 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 635 score: 0.9239 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 636 score: 0.8781 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 637 score: 0.8904 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 638 score: 0.8530 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 639 score: 0.9049 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 640 score: 0.8110 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 641 score: 0.9471 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 642 score: 0.7587 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 643 score: 0.8047 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 644 score: 0.7035 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 645 score: 0.7761 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 646 score: 0.8652 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 647 score: 0.9170 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 648 score: 0.7352 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 649 score: 0.8057 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 650 score: 0.7665 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 651 score: 0.7754 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 652 score: 0.5871 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 653 score: 0.8483 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 654 score: 0.8506 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 655 score: 0.8859 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 656 score: 0.8897 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 657 score: 0.6823 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 658 score: 0.7637 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 659 score: 0.8398 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 660 score: 0.7284 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 661 score: 0.9242 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 662 score: 0.8992 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 663 score: 0.9121 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 664 score: 0.9349 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 665 score: 0.8564 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 666 score: 0.8240 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 667 score: 0.8967 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 668 score: 0.9126 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 669 score: 0.8545 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 670 score: 0.9303 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 671 score: 0.9044 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 672 score: 0.9268 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 673 score: 0.9086 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 674 score: 0.8997 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 675 score: 0.9081 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 676 score: 0.9267 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 677 score: 0.8691 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 678 score: 0.8948 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 679 score: 0.8911 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 680 score: 0.8815 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 681 score: 0.9486 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 682 score: 0.9173 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 683 score: 0.9160 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 684 score: 0.8960 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 685 score: 0.8886 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 686 score: 0.9001 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 687 score: 0.8717 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 688 score: 0.9005 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 689 score: 0.8755 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 690 score: 0.9289 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 691 score: 0.8496 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 692 score: 0.9105 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 693 score: 0.8214 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 694 score: 0.8703 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 695 score: 0.8702 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 696 score: 0.8264 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 697 score: 0.9303 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 698 score: 0.7970 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 699 score: 0.8981 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 700 score: 0.8785 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 701 score: 0.9118 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 702 score: 0.8680 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 703 score: 0.8910 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 704 score: 0.9359 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 705 score: 0.8651 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 706 score: 0.8840 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 707 score: 0.8898 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 708 score: 0.9382 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 709 score: 0.8988 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 710 score: 0.9106 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 711 score: 0.8104 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 712 score: 0.9462 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 713 score: 0.8962 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 714 score: 0.9028 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 715 score: 0.7387 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 716 score: 0.8677 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 717 score: 0.8178 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 718 score: 0.9444 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 719 score: 0.9155 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 720 score: 0.8084 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 721 score: 0.9161 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 722 score: 0.8643 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 723 score: 0.9100 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 724 score: 0.9214 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 725 score: 0.9069 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 726 score: 0.8113 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 727 score: 0.7955 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 728 score: 0.7879 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 729 score: 0.8629 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 730 score: 0.8086 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 731 score: 0.9387 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 732 score: 0.8468 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 733 score: 0.7363 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 734 score: 0.8439 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 735 score: 0.8247 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 736 score: 0.9028 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 737 score: 0.8816 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 738 score: 0.9313 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 739 score: 0.8587 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 740 score: 0.8343 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 741 score: 0.1727 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 742 score: 0.7728 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 743 score: 0.9274 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 744 score: 0.9175 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 745 score: 0.8544 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 746 score: 0.8835 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 747 score: 0.8680 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 748 score: 0.6630 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 749 score: 0.8940 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 750 score: 0.8934 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 751 score: 0.8881 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 752 score: 0.8392 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 753 score: 0.8789 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 754 score: 0.9297 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 755 score: 0.9055 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 756 score: 0.8437 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 757 score: 0.9056 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 758 score: 0.8767 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 759 score: 0.8432 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 760 score: 0.9103 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 761 score: 0.8633 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 762 score: 0.8970 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 763 score: 0.9263 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 764 score: 0.8917 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 765 score: 0.8403 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 766 score: 0.9064 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 767 score: 0.9029 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 768 score: 0.8951 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 769 score: 0.8946 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 770 score: 0.9171 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 771 score: 0.9013 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 772 score: 0.8334 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 773 score: 0.8759 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 774 score: 0.8620 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 775 score: 0.8485 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 776 score: 0.6705 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 777 score: 0.8805 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 778 score: 0.8438 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 779 score: 0.8584 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 780 score: 0.8772 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 781 score: 0.7424 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 782 score: 0.9216 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 783 score: 0.8475 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 784 score: 0.9309 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 785 score: 0.8440 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 786 score: 0.9284 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 787 score: 0.8769 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 788 score: 0.9523 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 789 score: 0.8840 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 790 score: 0.9256 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 791 score: 0.9002 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 792 score: 0.9064 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 793 score: 0.9136 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 794 score: 0.8794 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 795 score: 0.8963 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 796 score: 0.9676 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 797 score: 0.8801 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 798 score: 0.8954 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 799 score: 0.7356 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 800 score: 0.8603 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 801 score: 0.8671 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 802 score: 0.9007 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 803 score: 0.8816 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 804 score: 0.7503 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 805 score: 0.8999 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 806 score: 0.9183 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 807 score: 0.8386 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 808 score: 0.8701 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 809 score: 0.8837 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 810 score: 0.7177 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 811 score: 0.7491 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 812 score: 0.9158 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 813 score: 0.9604 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 814 score: 0.9180 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 815 score: 0.8653 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 816 score: 0.8779 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 817 score: 0.8834 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 818 score: 0.6547 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 819 score: 0.9052 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 820 score: 0.9121 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 821 score: 0.9020 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 822 score: 0.8872 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 823 score: 0.9431 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 824 score: 0.8431 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 825 score: 0.7944 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 826 score: 0.8770 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 827 score: 0.9198 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 828 score: 0.8523 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 829 score: 0.8781 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 830 score: 0.8725 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 831 score: 0.8364 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 832 score: 0.8915 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 833 score: 0.8672 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 834 score: 0.8964 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 835 score: 0.9104 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 836 score: 0.8738 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 837 score: 0.8881 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 838 score: 0.8441 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 839 score: 0.9076 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 840 score: 0.8826 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 841 score: 0.8888 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 842 score: 0.7929 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 843 score: 0.8866 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 844 score: 0.7931 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 845 score: 0.7512 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 846 score: 0.7285 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 847 score: 0.9040 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 848 score: 0.8637 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 849 score: 0.8476 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 850 score: 0.8868 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 851 score: 0.9139 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 852 score: 0.9300 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 853 score: 0.7340 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 854 score: 0.8036 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 855 score: 0.8102 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 856 score: 0.7749 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 857 score: 0.9204 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 858 score: 0.8178 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 859 score: 0.9299 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 860 score: 0.9114 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 861 score: 0.8968 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 862 score: 0.6803 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 863 score: 0.9052 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 864 score: 0.7831 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 865 score: 0.6620 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 866 score: 0.8887 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 867 score: 0.8968 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 868 score: 0.8853 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 869 score: 0.8754 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 870 score: 0.9670 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 871 score: 0.9292 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 872 score: 0.8943 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 873 score: 0.8877 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 874 score: 0.9279 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 875 score: 0.9222 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 876 score: 0.9298 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 877 score: 0.8709 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 878 score: 0.9393 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 879 score: 0.8239 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 880 score: 0.8965 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 881 score: 0.9186 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 882 score: 0.8761 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 883 score: 0.8755 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 884 score: 0.8557 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 885 score: 0.9194 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 886 score: 0.8617 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 887 score: 0.7926 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 888 score: 0.8435 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 889 score: 0.8492 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 890 score: 0.9103 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 891 score: 0.8273 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 892 score: 0.7551 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 893 score: 0.7553 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 894 score: 0.9277 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 895 score: 0.9241 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 896 score: 0.9259 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 897 score: 0.9378 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 898 score: 0.9324 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 899 score: 0.8804 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 900 score: 0.9301 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 901 score: 0.8979 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 902 score: 0.7794 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 903 score: 0.8135 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 904 score: 0.8118 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 905 score: 0.7791 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 906 score: 0.8608 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 907 score: 0.8439 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 908 score: 0.8376 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 909 score: 0.9446 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 910 score: 0.8507 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 911 score: 0.8792 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 912 score: 0.9689 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 913 score: 0.9414 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 914 score: 0.9099 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 915 score: 0.9296 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 916 score: 0.9293 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 917 score: 0.9008 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 918 score: 0.9537 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 919 score: 0.8861 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 920 score: 0.7409 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 921 score: 0.8545 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 922 score: 0.7926 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 923 score: 0.9334 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 924 score: 0.9360 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 925 score: 0.9074 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 926 score: 0.8986 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 927 score: 0.9359 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 928 score: 0.9241 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 929 score: 0.9033 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 930 score: 0.8984 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 931 score: 0.8819 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 932 score: 0.7865 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 933 score: 0.7726 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 934 score: 0.8036 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 935 score: 0.8805 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 936 score: 0.8827 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 937 score: 0.9623 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 938 score: 0.9075 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 939 score: 0.9260 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 940 score: 0.8814 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 941 score: 0.9376 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 942 score: 0.9373 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 943 score: 0.8970 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 944 score: 0.8693 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 945 score: 0.8424 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 946 score: 0.8217 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 947 score: 0.9374 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 948 score: 0.8695 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 949 score: 0.8993 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 950 score: 0.8561 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 951 score: 0.8960 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 952 score: 0.8619 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 953 score: 0.8133 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 954 score: 0.8356 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 955 score: 0.9064 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 956 score: 0.9362 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 957 score: 0.8021 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 958 score: 0.9017 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 959 score: 0.8360 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 960 score: 0.7894 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 961 score: 0.5718 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 962 score: 0.8629 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 963 score: 0.8704 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 964 score: 0.9465 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 965 score: 0.7884 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 966 score: 0.8632 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 967 score: 0.8417 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 968 score: 0.8225 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 969 score: 0.8219 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 970 score: 0.8948 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 971 score: 0.8570 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 972 score: 0.8850 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 973 score: 0.8955 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 974 score: 0.8889 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 975 score: 0.9476 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 976 score: 0.8851 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 977 score: 0.8607 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 978 score: 0.6681 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 979 score: 0.8130 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 980 score: 0.8423 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 981 score: 0.9089 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 982 score: 0.8213 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 983 score: 0.8499 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 984 score: 0.9280 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 985 score: 0.9601 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 986 score: 0.8479 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 987 score: 0.8853 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 988 score: 0.7784 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 989 score: 0.8480 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 990 score: 0.9051 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 991 score: 0.8575 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 992 score: 0.8603 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 993 score: 0.8151 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 994 score: 0.9096 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 995 score: 0.8037 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 996 score: 0.9042 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 997 score: 0.9441 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 998 score: 0.8405 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 999 score: 0.8056 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1000 score: 0.9093 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1001 score: 0.8803 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1002 score: 0.8624 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1003 score: 0.7442 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1004 score: 0.9428 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1005 score: 0.9266 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1006 score: 0.8253 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1007 score: 0.8858 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1008 score: 0.9318 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1009 score: 0.9354 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1010 score: 0.9410 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th Segment 1011 score: 0.8817 +/beacon-scratch/tongzh24/XALMA-checkpoint/exp_50_languages/seperate_training/xalma-13b-sft-50-languages-th-max-tokens-512/test-en-th score: 0.8584