diff --git "a/test-en-lt.comet" "b/test-en-lt.comet"
new file mode 100644--- /dev/null
+++ "b/test-en-lt.comet"
@@ -0,0 +1,1013 @@
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 0	score: 0.7289
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1	score: 0.8983
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 2	score: 0.7877
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 3	score: 0.2811
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 4	score: 0.6764
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 5	score: 0.5849
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 6	score: 0.6660
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 7	score: 0.8345
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 8	score: 0.9740
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 9	score: 0.7954
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 10	score: 0.6448
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 11	score: 0.8365
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 12	score: 0.4784
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 13	score: 0.8293
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 14	score: 0.6613
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 15	score: 0.5771
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 16	score: 0.8107
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 17	score: 0.8935
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 18	score: 0.8535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 19	score: 0.8656
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 20	score: 0.9386
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 21	score: 0.7376
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 22	score: 0.7961
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 23	score: 0.8005
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 24	score: 0.7186
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 25	score: 0.9298
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 26	score: 0.6669
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 27	score: 0.7148
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 28	score: 0.6332
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 29	score: 0.6621
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 30	score: 0.4418
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 31	score: 0.4168
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 32	score: 0.4711
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 33	score: 0.9316
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 34	score: 0.8883
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 35	score: 0.7715
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 36	score: 0.6921
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 37	score: 0.6294
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 38	score: 0.6818
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 39	score: 0.9640
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 40	score: 0.6494
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 41	score: 0.9561
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 42	score: 0.8964
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 43	score: 0.6563
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 44	score: 0.5261
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 45	score: 0.8255
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 46	score: 0.2544
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 47	score: 0.8403
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 48	score: 0.6562
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 49	score: 0.5600
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 50	score: 0.9573
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 51	score: 0.5926
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 52	score: 0.9268
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 53	score: 0.7259
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 54	score: 0.8607
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 55	score: 0.6679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 56	score: 0.8891
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 57	score: 0.6377
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 58	score: 0.2943
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 59	score: 0.4831
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 60	score: 0.6382
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 61	score: 0.8691
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 62	score: 0.8542
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 63	score: 0.6561
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 64	score: 0.7567
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 65	score: 0.6252
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 66	score: 0.5868
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 67	score: 0.6716
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 68	score: 0.8381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 69	score: 0.9071
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 70	score: 0.8317
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 71	score: 0.6043
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 72	score: 0.7972
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 73	score: 0.7737
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 74	score: 0.7244
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 75	score: 0.5996
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 76	score: 0.2580
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 77	score: 0.6135
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 78	score: 0.6513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 79	score: 0.6414
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 80	score: 0.1307
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 81	score: 0.9361
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 82	score: 0.6763
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 83	score: 0.5065
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 84	score: 0.4807
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 85	score: 0.8856
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 86	score: 0.5434
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 87	score: 0.6620
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 88	score: 0.8029
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 89	score: 0.4711
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 90	score: 0.6003
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 91	score: 0.3694
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 92	score: 0.6891
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 93	score: 0.3873
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 94	score: 0.5114
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 95	score: 0.7014
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 96	score: 0.4762
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 97	score: 0.9090
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 98	score: 0.7541
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 99	score: 0.6892
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 100	score: 0.9290
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 101	score: 0.6666
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 102	score: 0.8332
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 103	score: 0.8568
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 104	score: 0.6803
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 105	score: 0.6141
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 106	score: 0.9188
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 107	score: 0.6220
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 108	score: 0.7589
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 109	score: 0.7611
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 110	score: 0.5676
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 111	score: 0.8125
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 112	score: 0.7894
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 113	score: 0.4036
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 114	score: 0.6192
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 115	score: 0.7930
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 116	score: 0.6582
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 117	score: 0.7789
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 118	score: 0.7106
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 119	score: 0.6567
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 120	score: 0.8637
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 121	score: 0.5775
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 122	score: 0.9784
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 123	score: 0.9278
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 124	score: 0.9350
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 125	score: 0.5411
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 126	score: 0.8376
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 127	score: 0.4809
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 128	score: 0.6390
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 129	score: 0.5001
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 130	score: 0.9484
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 131	score: 0.9157
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 132	score: 0.6702
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 133	score: 0.5559
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 134	score: 0.4829
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 135	score: 0.5100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 136	score: 0.8854
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 137	score: 0.5561
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 138	score: 0.7861
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 139	score: 0.5105
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 140	score: 0.8476
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 141	score: 0.8537
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 142	score: 0.7272
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 143	score: 0.4503
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 144	score: 0.9117
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 145	score: 0.9006
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 146	score: 0.9579
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 147	score: 0.7058
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 148	score: 0.8098
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 149	score: 0.4192
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 150	score: 0.2363
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 151	score: 0.7883
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 152	score: 0.5065
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 153	score: 0.3766
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 154	score: 0.5767
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 155	score: 0.8976
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 156	score: 0.5927
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 157	score: 0.8876
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 158	score: 0.7881
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 159	score: 0.5801
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 160	score: 0.8000
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 161	score: 0.6525
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 162	score: 0.4601
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 163	score: 0.7338
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 164	score: 0.9782
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 165	score: 0.3325
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 166	score: 0.7292
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 167	score: 0.7282
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 168	score: 0.4092
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 169	score: 0.7790
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 170	score: 0.7237
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 171	score: 0.9301
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 172	score: 0.7586
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 173	score: 0.8664
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 174	score: 0.7148
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 175	score: 0.5833
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 176	score: 0.8216
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 177	score: 0.7925
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 178	score: 0.9004
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 179	score: 0.7771
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 180	score: 0.8728
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 181	score: 0.7628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 182	score: 0.9056
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 183	score: 0.9422
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 184	score: 0.2233
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 185	score: 0.8422
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 186	score: 0.7867
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 187	score: 0.6352
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 188	score: 0.8564
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 189	score: 0.5373
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 190	score: 0.5482
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 191	score: 0.8960
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 192	score: 0.5586
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 193	score: 0.6845
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 194	score: 0.9117
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 195	score: 0.9488
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 196	score: 0.8131
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 197	score: 0.7217
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 198	score: 0.9147
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 199	score: 0.6783
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 200	score: 0.7861
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 201	score: 0.5934
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 202	score: 0.6460
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 203	score: 0.7644
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 204	score: 0.6396
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 205	score: 0.7378
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 206	score: 0.6979
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 207	score: 0.6290
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 208	score: 0.6897
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 209	score: 0.8947
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 210	score: 0.8140
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 211	score: 0.7207
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 212	score: 0.8889
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 213	score: 0.8336
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 214	score: 0.8846
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 215	score: 0.2153
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 216	score: 0.7629
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 217	score: 0.7332
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 218	score: 0.7164
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 219	score: 0.7086
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 220	score: 0.8238
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 221	score: 0.5617
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 222	score: 0.9205
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 223	score: 0.7425
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 224	score: 0.9433
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 225	score: 0.8905
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 226	score: 0.9138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 227	score: 0.8344
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 228	score: 0.8039
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 229	score: 0.5771
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 230	score: 0.9673
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 231	score: 0.5740
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 232	score: 0.6519
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 233	score: 0.5032
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 234	score: 0.5529
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 235	score: 0.9022
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 236	score: 0.8992
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 237	score: 0.6741
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 238	score: 0.6546
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 239	score: 0.7027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 240	score: 0.2669
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 241	score: 0.5941
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 242	score: 0.6585
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 243	score: 0.4904
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 244	score: 0.4244
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 245	score: 0.4266
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 246	score: 0.6678
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 247	score: 0.5517
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 248	score: 0.4630
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 249	score: 0.7152
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 250	score: 0.8519
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 251	score: 0.9562
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 252	score: 0.7261
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 253	score: 0.5838
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 254	score: 0.7846
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 255	score: 0.9182
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 256	score: 0.6415
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 257	score: 0.5496
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 258	score: 0.5510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 259	score: 0.5733
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 260	score: 0.9584
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 261	score: 0.8942
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 262	score: 0.5583
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 263	score: 0.7327
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 264	score: 0.5996
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 265	score: 0.6809
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 266	score: 0.7754
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 267	score: 0.6922
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 268	score: 0.9169
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 269	score: 0.9068
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 270	score: 0.4566
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 271	score: 0.4753
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 272	score: 0.8231
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 273	score: 0.7911
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 274	score: 0.6652
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 275	score: 0.6544
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 276	score: 0.7175
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 277	score: 0.8230
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 278	score: 0.8553
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 279	score: 0.9329
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 280	score: 0.6849
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 281	score: 0.7596
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 282	score: 0.9395
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 283	score: 0.7089
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 284	score: 0.6432
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 285	score: 0.7467
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 286	score: 0.7215
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 287	score: 0.6645
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 288	score: 0.8766
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 289	score: 0.8352
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 290	score: 0.5034
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 291	score: 0.6578
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 292	score: 0.5104
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 293	score: 0.5909
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 294	score: 0.5575
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 295	score: 0.5993
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 296	score: 0.7788
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 297	score: 0.6731
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 298	score: 0.5669
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 299	score: 0.8689
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 300	score: 0.8059
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 301	score: 0.7490
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 302	score: 0.5528
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 303	score: 0.7395
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 304	score: 0.8941
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 305	score: 0.6485
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 306	score: 0.9064
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 307	score: 0.8184
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 308	score: 0.9154
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 309	score: 0.6452
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 310	score: 0.8861
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 311	score: 0.5266
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 312	score: 0.5341
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 313	score: 0.5978
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 314	score: 0.7206
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 315	score: 0.9327
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 316	score: 0.6765
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 317	score: 0.7169
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 318	score: 0.7616
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 319	score: 0.6393
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 320	score: 0.7809
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 321	score: 0.5900
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 322	score: 0.6910
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 323	score: 0.7648
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 324	score: 0.8763
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 325	score: 0.5941
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 326	score: 0.7133
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 327	score: 0.6103
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 328	score: 0.8531
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 329	score: 0.7226
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 330	score: 0.9006
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 331	score: 0.7218
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 332	score: 0.7373
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 333	score: 0.5842
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 334	score: 0.9545
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 335	score: 0.6931
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 336	score: 0.8193
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 337	score: 0.5739
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 338	score: 0.7858
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 339	score: 0.8625
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 340	score: 0.6673
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 341	score: 0.5725
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 342	score: 0.4210
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 343	score: 0.6804
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 344	score: 0.8121
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 345	score: 0.5068
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 346	score: 0.7125
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 347	score: 0.7258
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 348	score: 0.3427
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 349	score: 0.2951
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 350	score: 0.6213
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 351	score: 0.7440
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 352	score: 0.7889
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 353	score: 0.9098
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 354	score: 0.4949
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 355	score: 0.6896
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 356	score: 0.6431
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 357	score: 0.7090
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 358	score: 0.7971
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 359	score: 0.5664
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 360	score: 0.4702
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 361	score: 0.5000
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 362	score: 0.7943
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 363	score: 0.4042
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 364	score: 0.4246
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 365	score: 0.5301
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 366	score: 0.4723
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 367	score: 0.8052
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 368	score: 0.4843
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 369	score: 0.5646
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 370	score: 0.5288
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 371	score: 0.5382
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 372	score: 0.5800
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 373	score: 0.7059
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 374	score: 0.6445
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 375	score: 0.8985
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 376	score: 0.7709
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 377	score: 0.8427
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 378	score: 0.2823
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 379	score: 0.5065
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 380	score: 0.8031
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 381	score: 0.6340
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 382	score: 0.4256
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 383	score: 0.5679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 384	score: 0.6737
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 385	score: 0.6022
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 386	score: 0.4817
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 387	score: 0.3815
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 388	score: 0.8581
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 389	score: 0.8707
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 390	score: 0.6546
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 391	score: 0.6679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 392	score: 0.8391
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 393	score: 0.5798
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 394	score: 0.8799
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 395	score: 0.7275
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 396	score: 0.4482
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 397	score: 0.8317
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 398	score: 0.5046
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 399	score: 0.9118
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 400	score: 0.8105
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 401	score: 0.6144
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 402	score: 0.6773
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 403	score: 0.7271
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 404	score: 0.5410
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 405	score: 0.5858
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 406	score: 0.5476
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 407	score: 0.8521
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 408	score: 0.8405
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 409	score: 0.6746
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 410	score: 0.7864
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 411	score: 0.5884
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 412	score: 0.4513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 413	score: 0.7066
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 414	score: 0.6771
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 415	score: 0.7292
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 416	score: 0.8475
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 417	score: 0.5610
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 418	score: 0.8681
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 419	score: 0.8709
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 420	score: 0.9352
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 421	score: 0.9534
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 422	score: 0.8920
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 423	score: 0.8245
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 424	score: 0.8477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 425	score: 0.9546
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 426	score: 0.7591
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 427	score: 0.8876
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 428	score: 0.7306
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 429	score: 0.7976
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 430	score: 0.6840
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 431	score: 0.6902
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 432	score: 0.5002
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 433	score: 0.6895
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 434	score: 0.5320
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 435	score: 0.6466
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 436	score: 0.5399
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 437	score: 0.5904
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 438	score: 0.8636
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 439	score: 0.1997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 440	score: 0.8746
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 441	score: 0.9153
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 442	score: 0.9234
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 443	score: 0.6538
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 444	score: 0.5732
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 445	score: 0.6659
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 446	score: 0.6549
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 447	score: 0.9359
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 448	score: 0.7011
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 449	score: 0.8422
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 450	score: 0.7233
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 451	score: 0.7586
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 452	score: 0.7697
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 453	score: 0.6589
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 454	score: 0.8918
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 455	score: 0.4663
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 456	score: 0.4778
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 457	score: 0.9227
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 458	score: 0.6822
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 459	score: 0.4731
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 460	score: 0.3523
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 461	score: 0.5155
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 462	score: 0.3887
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 463	score: 0.6591
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 464	score: 0.6672
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 465	score: 0.7591
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 466	score: 0.7602
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 467	score: 0.6075
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 468	score: 0.4449
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 469	score: 0.4681
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 470	score: 0.5913
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 471	score: 0.3010
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 472	score: 0.6265
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 473	score: 0.3449
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 474	score: 0.5057
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 475	score: 0.5613
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 476	score: 0.6649
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 477	score: 0.6450
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 478	score: 0.9343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 479	score: 0.8087
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 480	score: 0.5636
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 481	score: 0.6758
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 482	score: 0.5681
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 483	score: 0.5945
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 484	score: 0.6479
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 485	score: 0.7815
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 486	score: 0.7653
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 487	score: 0.6361
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 488	score: 0.8643
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 489	score: 0.5142
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 490	score: 0.6523
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 491	score: 0.9283
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 492	score: 0.6691
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 493	score: 0.7569
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 494	score: 0.7490
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 495	score: 0.4137
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 496	score: 0.6124
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 497	score: 0.4940
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 498	score: 0.6095
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 499	score: 0.5607
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 500	score: 0.7346
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 501	score: 0.8979
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 502	score: 0.7969
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 503	score: 0.5942
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 504	score: 0.6302
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 505	score: 0.5843
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 506	score: 0.6950
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 507	score: 0.3809
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 508	score: 0.8530
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 509	score: 0.7939
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 510	score: 0.4953
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 511	score: 0.6126
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 512	score: 0.5987
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 513	score: 0.5600
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 514	score: 0.8225
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 515	score: 0.7240
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 516	score: 0.6348
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 517	score: 0.6680
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 518	score: 0.6624
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 519	score: 0.8784
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 520	score: 0.8378
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 521	score: 0.7972
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 522	score: 0.9405
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 523	score: 0.6935
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 524	score: 0.5435
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 525	score: 0.6556
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 526	score: 0.6247
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 527	score: 0.3065
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 528	score: 0.5306
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 529	score: 0.8507
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 530	score: 0.5839
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 531	score: 0.5139
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 532	score: 0.5259
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 533	score: 0.5599
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 534	score: 0.4442
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 535	score: 0.4755
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 536	score: 0.4925
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 537	score: 0.4030
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 538	score: 0.6086
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 539	score: 0.5734
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 540	score: 0.7050
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 541	score: 0.8650
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 542	score: 0.6573
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 543	score: 0.7604
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 544	score: 0.5903
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 545	score: 0.5796
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 546	score: 0.7601
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 547	score: 0.6693
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 548	score: 0.4654
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 549	score: 0.7515
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 550	score: 0.5558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 551	score: 0.7333
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 552	score: 0.8719
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 553	score: 0.5331
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 554	score: 0.6261
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 555	score: 0.5102
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 556	score: 0.4637
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 557	score: 0.7162
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 558	score: 0.3937
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 559	score: 0.6467
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 560	score: 0.1810
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 561	score: 0.4652
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 562	score: 0.6156
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 563	score: 0.4367
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 564	score: 0.5120
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 565	score: 0.2913
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 566	score: 0.5766
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 567	score: 0.8534
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 568	score: 0.5512
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 569	score: 0.4287
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 570	score: 0.6902
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 571	score: 0.6346
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 572	score: 0.7504
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 573	score: 0.7844
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 574	score: 0.4652
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 575	score: 0.5982
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 576	score: 0.3934
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 577	score: 0.8075
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 578	score: 0.7993
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 579	score: 0.2947
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 580	score: 0.4702
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 581	score: 0.6849
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 582	score: 0.7264
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 583	score: 0.6166
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 584	score: 0.5678
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 585	score: 0.6290
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 586	score: 0.7765
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 587	score: 0.9229
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 588	score: 0.6097
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 589	score: 0.7414
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 590	score: 0.7891
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 591	score: 0.8233
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 592	score: 0.7493
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 593	score: 0.8675
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 594	score: 0.8306
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 595	score: 0.4330
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 596	score: 0.6077
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 597	score: 0.7141
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 598	score: 0.3871
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 599	score: 0.7608
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 600	score: 0.8300
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 601	score: 0.6456
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 602	score: 0.6956
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 603	score: 0.7264
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 604	score: 0.6296
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 605	score: 0.4443
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 606	score: 0.7632
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 607	score: 0.7250
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 608	score: 0.5966
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 609	score: 0.5933
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 610	score: 0.8884
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 611	score: 0.7144
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 612	score: 0.7796
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 613	score: 0.4879
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 614	score: 0.1857
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 615	score: 0.6189
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 616	score: 0.5101
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 617	score: 0.9407
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 618	score: 0.7557
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 619	score: 0.4640
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 620	score: 0.4915
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 621	score: 0.4185
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 622	score: 0.8942
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 623	score: 0.5741
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 624	score: 0.4381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 625	score: 0.7838
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 626	score: 0.6968
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 627	score: 0.9438
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 628	score: 0.7977
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 629	score: 0.7071
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 630	score: 0.7393
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 631	score: 0.8840
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 632	score: 0.9542
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 633	score: 0.9558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 634	score: 0.9433
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 635	score: 0.3869
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 636	score: 0.8940
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 637	score: 0.6591
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 638	score: 0.6153
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 639	score: 0.8111
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 640	score: 0.6805
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 641	score: 0.8441
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 642	score: 0.6353
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 643	score: 0.8523
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 644	score: 0.2405
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 645	score: 0.6667
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 646	score: 0.5883
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 647	score: 0.8094
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 648	score: 0.4989
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 649	score: 0.5268
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 650	score: 0.7818
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 651	score: 0.7070
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 652	score: 0.4106
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 653	score: 0.5897
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 654	score: 0.7420
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 655	score: 0.6413
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 656	score: 0.6447
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 657	score: 0.8120
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 658	score: 0.5686
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 659	score: 0.8098
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 660	score: 0.6183
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 661	score: 0.9347
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 662	score: 0.5897
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 663	score: 0.7980
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 664	score: 0.8319
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 665	score: 0.8393
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 666	score: 0.7088
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 667	score: 0.6895
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 668	score: 0.6904
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 669	score: 0.8741
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 670	score: 0.7520
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 671	score: 0.8816
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 672	score: 0.7644
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 673	score: 0.6892
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 674	score: 0.7771
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 675	score: 0.7554
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 676	score: 0.7155
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 677	score: 0.8339
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 678	score: 0.7025
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 679	score: 0.8281
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 680	score: 0.6614
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 681	score: 0.6230
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 682	score: 0.9067
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 683	score: 0.8616
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 684	score: 0.6374
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 685	score: 0.6228
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 686	score: 0.6469
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 687	score: 0.5006
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 688	score: 0.6581
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 689	score: 0.5148
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 690	score: 0.6053
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 691	score: 0.5446
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 692	score: 0.8289
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 693	score: 0.7285
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 694	score: 0.6613
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 695	score: 0.5837
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 696	score: 0.8319
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 697	score: 0.9537
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 698	score: 0.5385
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 699	score: 0.9280
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 700	score: 0.6247
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 701	score: 0.9112
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 702	score: 0.9480
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 703	score: 0.7303
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 704	score: 0.3900
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 705	score: 0.2533
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 706	score: 0.4858
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 707	score: 0.5329
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 708	score: 0.7988
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 709	score: 0.8529
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 710	score: 0.7984
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 711	score: 0.8644
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 712	score: 0.9213
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 713	score: 0.6817
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 714	score: 0.6238
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 715	score: 0.7227
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 716	score: 0.8113
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 717	score: 0.6973
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 718	score: 0.7043
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 719	score: 0.9041
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 720	score: 0.7892
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 721	score: 0.2147
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 722	score: 0.7418
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 723	score: 0.9356
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 724	score: 0.7961
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 725	score: 0.7031
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 726	score: 0.7967
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 727	score: 0.6406
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 728	score: 0.4331
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 729	score: 0.5293
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 730	score: 0.7516
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 731	score: 0.7946
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 732	score: 0.6868
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 733	score: 0.8383
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 734	score: 0.6634
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 735	score: 0.9390
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 736	score: 0.7938
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 737	score: 0.9027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 738	score: 0.6376
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 739	score: 0.8259
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 740	score: 0.8222
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 741	score: 0.7449
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 742	score: 0.8176
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 743	score: 0.8462
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 744	score: 0.7676
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 745	score: 0.6113
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 746	score: 0.5559
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 747	score: 0.8570
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 748	score: 0.9312
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 749	score: 0.9385
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 750	score: 0.9562
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 751	score: 0.8979
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 752	score: 0.7573
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 753	score: 0.6353
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 754	score: 0.8863
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 755	score: 0.7497
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 756	score: 0.6860
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 757	score: 0.7284
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 758	score: 0.7692
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 759	score: 0.4911
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 760	score: 0.9382
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 761	score: 0.7011
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 762	score: 0.8786
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 763	score: 0.6121
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 764	score: 0.5699
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 765	score: 0.4902
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 766	score: 0.6064
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 767	score: 0.4417
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 768	score: 0.9120
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 769	score: 0.8357
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 770	score: 0.7609
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 771	score: 0.5392
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 772	score: 0.7615
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 773	score: 0.6196
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 774	score: 0.2644
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 775	score: 0.2567
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 776	score: 0.7909
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 777	score: 0.6011
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 778	score: 0.7178
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 779	score: 0.7565
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 780	score: 0.5720
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 781	score: 0.5912
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 782	score: 0.6685
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 783	score: 0.4942
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 784	score: 0.5534
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 785	score: 0.5433
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 786	score: 0.7544
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 787	score: 0.8381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 788	score: 0.4564
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 789	score: 0.8323
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 790	score: 0.9077
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 791	score: 0.8808
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 792	score: 0.6413
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 793	score: 0.5067
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 794	score: 0.6334
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 795	score: 0.6936
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 796	score: 0.4679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 797	score: 0.2975
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 798	score: 0.6138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 799	score: 0.5209
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 800	score: 0.5065
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 801	score: 0.5201
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 802	score: 0.6541
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 803	score: 0.5888
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 804	score: 0.5658
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 805	score: 0.5718
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 806	score: 0.7509
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 807	score: 0.8448
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 808	score: 0.7484
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 809	score: 0.7320
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 810	score: 0.4340
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 811	score: 0.7641
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 812	score: 0.9513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 813	score: 0.6395
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 814	score: 0.5890
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 815	score: 0.7229
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 816	score: 0.8799
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 817	score: 0.5175
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 818	score: 0.3791
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 819	score: 0.5735
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 820	score: 0.8741
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 821	score: 0.5858
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 822	score: 0.5817
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 823	score: 0.5232
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 824	score: 0.6502
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 825	score: 0.5238
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 826	score: 0.5983
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 827	score: 0.5731
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 828	score: 0.4788
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 829	score: 0.4350
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 830	score: 0.5567
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 831	score: 0.5818
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 832	score: 0.5354
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 833	score: 0.1858
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 834	score: 0.5310
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 835	score: 0.7443
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 836	score: 0.4314
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 837	score: 0.7905
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 838	score: 0.8381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 839	score: 0.5922
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 840	score: 0.8887
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 841	score: 0.5719
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 842	score: 0.3244
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 843	score: 0.5686
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 844	score: 0.4940
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 845	score: 0.4135
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 846	score: 0.4709
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 847	score: 0.5388
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 848	score: 0.4316
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 849	score: 0.5357
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 850	score: 0.7061
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 851	score: 0.1862
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 852	score: 0.8272
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 853	score: 0.5184
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 854	score: 0.5538
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 855	score: 0.7561
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 856	score: 0.4176
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 857	score: 0.3281
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 858	score: 0.7547
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 859	score: 0.1961
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 860	score: 0.7115
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 861	score: 0.4927
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 862	score: 0.6335
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 863	score: 0.7319
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 864	score: 0.4488
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 865	score: 0.4589
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 866	score: 0.6009
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 867	score: 0.6679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 868	score: 0.8767
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 869	score: 0.8894
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 870	score: 0.6945
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 871	score: 0.8175
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 872	score: 0.6289
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 873	score: 0.6573
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 874	score: 0.5881
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 875	score: 0.6015
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 876	score: 0.4336
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 877	score: 0.8122
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 878	score: 0.8501
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 879	score: 0.5656
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 880	score: 0.6667
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 881	score: 0.8186
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 882	score: 0.5804
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 883	score: 0.8357
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 884	score: 0.2507
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 885	score: 0.7013
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 886	score: 0.7445
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 887	score: 0.5098
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 888	score: 0.2869
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 889	score: 0.5085
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 890	score: 0.5352
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 891	score: 0.5054
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 892	score: 0.4537
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 893	score: 0.4368
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 894	score: 0.5545
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 895	score: 0.5203
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 896	score: 0.8590
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 897	score: 0.4825
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 898	score: 0.9212
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 899	score: 0.4881
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 900	score: 0.6769
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 901	score: 0.7142
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 902	score: 0.4278
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 903	score: 0.5453
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 904	score: 0.8136
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 905	score: 0.5612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 906	score: 0.7342
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 907	score: 0.4435
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 908	score: 0.7323
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 909	score: 0.9232
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 910	score: 0.5825
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 911	score: 0.7484
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 912	score: 0.8577
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 913	score: 0.4023
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 914	score: 0.5864
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 915	score: 0.8597
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 916	score: 0.5826
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 917	score: 0.8164
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 918	score: 0.8343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 919	score: 0.7030
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 920	score: 0.7007
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 921	score: 0.7343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 922	score: 0.6370
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 923	score: 0.6781
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 924	score: 0.7915
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 925	score: 0.8236
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 926	score: 0.7335
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 927	score: 0.5526
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 928	score: 0.7058
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 929	score: 0.5576
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 930	score: 0.9192
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 931	score: 0.4930
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 932	score: 0.6782
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 933	score: 0.2278
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 934	score: 0.5071
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 935	score: 0.5887
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 936	score: 0.6720
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 937	score: 0.9603
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 938	score: 0.7025
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 939	score: 0.7327
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 940	score: 0.8788
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 941	score: 0.6859
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 942	score: 0.8919
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 943	score: 0.7572
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 944	score: 0.5646
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 945	score: 0.4709
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 946	score: 0.6868
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 947	score: 0.3709
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 948	score: 0.6019
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 949	score: 0.8616
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 950	score: 0.5496
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 951	score: 0.5925
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 952	score: 0.5168
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 953	score: 0.4865
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 954	score: 0.4141
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 955	score: 0.8555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 956	score: 0.8774
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 957	score: 0.9023
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 958	score: 0.7278
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 959	score: 0.7609
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 960	score: 0.4391
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 961	score: 0.7805
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 962	score: 0.4294
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 963	score: 0.4588
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 964	score: 0.7472
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 965	score: 0.5328
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 966	score: 0.4026
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 967	score: 0.3704
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 968	score: 0.3602
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 969	score: 0.4574
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 970	score: 0.5216
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 971	score: 0.5747
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 972	score: 0.6860
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 973	score: 0.4240
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 974	score: 0.7143
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 975	score: 0.7065
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 976	score: 0.5645
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 977	score: 0.6897
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 978	score: 0.9205
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 979	score: 0.7921
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 980	score: 0.9620
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 981	score: 0.8049
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 982	score: 0.5034
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 983	score: 0.6776
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 984	score: 0.8642
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 985	score: 0.8808
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 986	score: 0.4883
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 987	score: 0.4545
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 988	score: 0.5102
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 989	score: 0.5044
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 990	score: 0.5750
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 991	score: 0.5987
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 992	score: 0.6034
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 993	score: 0.6864
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 994	score: 0.7081
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 995	score: 0.6903
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 996	score: 0.8519
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 997	score: 0.6180
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 998	score: 0.7625
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 999	score: 0.4282
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1000	score: 0.7021
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1001	score: 0.7310
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1002	score: 0.6875
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1003	score: 0.1675
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1004	score: 0.5088
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1005	score: 0.7772
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1006	score: 0.5177
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1007	score: 0.7863
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1008	score: 0.9570
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1009	score: 0.6735
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1010	score: 0.7457
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	Segment 1011	score: 0.7277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lt	score: 0.6741