diff --git "a/test-en-lv.comet" "b/test-en-lv.comet"
new file mode 100644--- /dev/null
+++ "b/test-en-lv.comet"
@@ -0,0 +1,1013 @@
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 0	score: 0.7151
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1	score: 0.8267
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 2	score: 0.7404
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 3	score: 0.6832
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 4	score: 0.6555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 5	score: 0.5820
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 6	score: 0.7001
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 7	score: 0.8731
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 8	score: 0.8922
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 9	score: 0.8752
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 10	score: 0.6757
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 11	score: 0.6737
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 12	score: 0.8111
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 13	score: 0.3205
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 14	score: 0.8692
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 15	score: 0.7287
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 16	score: 0.7055
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 17	score: 0.7844
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 18	score: 0.8380
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 19	score: 0.8071
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 20	score: 0.9171
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 21	score: 0.7417
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 22	score: 0.8277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 23	score: 0.8838
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 24	score: 0.9264
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 25	score: 0.7805
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 26	score: 0.5913
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 27	score: 0.7191
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 28	score: 0.7568
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 29	score: 0.2198
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 30	score: 0.6487
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 31	score: 0.5670
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 32	score: 0.5148
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 33	score: 0.8883
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 34	score: 0.9469
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 35	score: 0.8957
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 36	score: 0.7034
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 37	score: 0.8733
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 38	score: 0.6866
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 39	score: 0.8438
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 40	score: 0.6408
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 41	score: 0.9623
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 42	score: 0.7946
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 43	score: 0.8244
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 44	score: 0.6558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 45	score: 0.8128
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 46	score: 0.8304
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 47	score: 0.8888
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 48	score: 0.5092
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 49	score: 0.8405
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 50	score: 0.9615
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 51	score: 0.4822
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 52	score: 0.6397
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 53	score: 0.7228
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 54	score: 0.8247
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 55	score: 0.7682
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 56	score: 0.7513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 57	score: 0.7647
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 58	score: 0.7343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 59	score: 0.9515
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 60	score: 0.8882
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 61	score: 0.9368
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 62	score: 0.9317
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 63	score: 0.7629
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 64	score: 0.7221
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 65	score: 0.5970
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 66	score: 0.6919
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 67	score: 0.5812
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 68	score: 0.9531
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 69	score: 0.8970
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 70	score: 0.5902
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 71	score: 0.5676
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 72	score: 0.7792
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 73	score: 0.7201
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 74	score: 0.6835
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 75	score: 0.7371
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 76	score: 0.8245
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 77	score: 0.9255
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 78	score: 0.9154
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 79	score: 0.8206
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 80	score: 0.6557
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 81	score: 0.8993
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 82	score: 0.6027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 83	score: 0.6324
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 84	score: 0.8074
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 85	score: 0.6261
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 86	score: 0.5660
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 87	score: 0.6082
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 88	score: 0.8558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 89	score: 0.3414
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 90	score: 0.6307
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 91	score: 0.7440
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 92	score: 0.7578
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 93	score: 0.9458
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 94	score: 0.5551
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 95	score: 0.9409
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 96	score: 0.4691
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 97	score: 0.8624
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 98	score: 0.7584
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 99	score: 0.9007
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 100	score: 0.9125
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 101	score: 0.7852
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 102	score: 0.6708
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 103	score: 0.7967
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 104	score: 0.8046
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 105	score: 0.7589
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 106	score: 0.7894
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 107	score: 0.6017
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 108	score: 0.3615
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 109	score: 0.7697
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 110	score: 0.6353
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 111	score: 0.8159
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 112	score: 0.7991
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 113	score: 0.4214
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 114	score: 0.6150
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 115	score: 0.7657
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 116	score: 0.5733
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 117	score: 0.9101
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 118	score: 0.1557
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 119	score: 0.6252
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 120	score: 0.6093
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 121	score: 0.6611
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 122	score: 0.8907
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 123	score: 0.6728
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 124	score: 0.7925
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 125	score: 0.8403
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 126	score: 0.9179
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 127	score: 0.6148
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 128	score: 0.5975
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 129	score: 0.8370
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 130	score: 0.5802
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 131	score: 0.6065
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 132	score: 0.7655
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 133	score: 0.7050
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 134	score: 0.7345
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 135	score: 0.5816
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 136	score: 0.6173
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 137	score: 0.8649
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 138	score: 0.8361
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 139	score: 0.6936
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 140	score: 0.6578
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 141	score: 0.7940
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 142	score: 0.9382
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 143	score: 0.2406
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 144	score: 0.7759
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 145	score: 0.8951
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 146	score: 0.9337
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 147	score: 0.7047
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 148	score: 0.6138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 149	score: 0.7289
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 150	score: 0.8665
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 151	score: 0.6772
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 152	score: 0.6431
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 153	score: 0.7203
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 154	score: 0.6451
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 155	score: 0.6938
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 156	score: 0.5955
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 157	score: 0.8496
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 158	score: 0.7975
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 159	score: 0.6963
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 160	score: 0.7840
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 161	score: 0.7006
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 162	score: 0.3686
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 163	score: 0.3297
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 164	score: 0.2291
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 165	score: 0.4996
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 166	score: 0.6063
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 167	score: 0.7131
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 168	score: 0.6606
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 169	score: 0.7853
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 170	score: 0.7323
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 171	score: 0.8898
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 172	score: 0.8345
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 173	score: 0.6814
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 174	score: 0.8268
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 175	score: 0.9094
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 176	score: 0.7663
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 177	score: 0.8388
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 178	score: 0.6051
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 179	score: 0.8031
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 180	score: 0.8577
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 181	score: 0.9145
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 182	score: 0.8221
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 183	score: 0.9501
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 184	score: 0.5454
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 185	score: 0.7373
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 186	score: 0.9274
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 187	score: 0.8360
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 188	score: 0.6417
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 189	score: 0.5429
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 190	score: 0.3809
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 191	score: 0.7967
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 192	score: 0.5102
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 193	score: 0.8080
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 194	score: 0.7698
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 195	score: 0.9308
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 196	score: 0.7725
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 197	score: 0.6967
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 198	score: 0.8957
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 199	score: 0.7718
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 200	score: 0.7396
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 201	score: 0.6260
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 202	score: 0.7465
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 203	score: 0.6188
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 204	score: 0.6081
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 205	score: 0.6503
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 206	score: 0.5893
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 207	score: 0.6277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 208	score: 0.6704
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 209	score: 0.8657
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 210	score: 0.8305
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 211	score: 0.8985
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 212	score: 0.8963
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 213	score: 0.9001
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 214	score: 0.9044
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 215	score: 0.8942
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 216	score: 0.9252
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 217	score: 0.6086
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 218	score: 0.6998
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 219	score: 0.7859
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 220	score: 0.9827
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 221	score: 0.9271
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 222	score: 0.8611
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 223	score: 0.8282
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 224	score: 0.9125
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 225	score: 0.9076
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 226	score: 0.6845
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 227	score: 0.6372
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 228	score: 0.7322
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 229	score: 0.6935
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 230	score: 0.9618
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 231	score: 0.7457
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 232	score: 0.7921
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 233	score: 0.8825
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 234	score: 0.6224
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 235	score: 0.8114
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 236	score: 0.7636
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 237	score: 0.5880
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 238	score: 0.8533
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 239	score: 0.8716
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 240	score: 0.2673
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 241	score: 0.5011
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 242	score: 0.7552
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 243	score: 0.5060
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 244	score: 0.6970
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 245	score: 0.4960
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 246	score: 0.5721
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 247	score: 0.5280
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 248	score: 0.5298
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 249	score: 0.8905
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 250	score: 0.7161
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 251	score: 0.9487
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 252	score: 0.5723
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 253	score: 0.3602
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 254	score: 0.9161
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 255	score: 0.8516
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 256	score: 0.7072
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 257	score: 0.9007
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 258	score: 0.8894
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 259	score: 0.6080
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 260	score: 0.9200
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 261	score: 0.7790
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 262	score: 0.5621
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 263	score: 0.7693
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 264	score: 0.8870
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 265	score: 0.5558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 266	score: 0.8514
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 267	score: 0.6497
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 268	score: 0.8886
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 269	score: 0.7545
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 270	score: 0.5936
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 271	score: 0.4906
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 272	score: 0.7366
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 273	score: 0.7249
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 274	score: 0.5628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 275	score: 0.6965
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 276	score: 0.7259
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 277	score: 0.6263
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 278	score: 0.6490
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 279	score: 0.6650
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 280	score: 0.8060
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 281	score: 0.6768
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 282	score: 0.9600
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 283	score: 0.1898
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 284	score: 0.8485
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 285	score: 0.9531
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 286	score: 0.8234
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 287	score: 0.6710
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 288	score: 0.8545
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 289	score: 0.8460
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 290	score: 0.6182
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 291	score: 0.8321
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 292	score: 0.7675
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 293	score: 0.6100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 294	score: 0.7384
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 295	score: 0.8663
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 296	score: 0.7928
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 297	score: 0.4935
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 298	score: 0.7014
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 299	score: 0.8191
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 300	score: 0.6903
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 301	score: 0.8098
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 302	score: 0.5675
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 303	score: 0.8608
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 304	score: 0.7760
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 305	score: 0.7688
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 306	score: 0.9189
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 307	score: 0.8896
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 308	score: 0.9401
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 309	score: 0.7536
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 310	score: 0.9422
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 311	score: 0.5787
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 312	score: 0.5698
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 313	score: 0.7760
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 314	score: 0.6366
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 315	score: 0.9283
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 316	score: 0.5761
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 317	score: 0.7575
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 318	score: 0.7703
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 319	score: 0.5216
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 320	score: 0.7615
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 321	score: 0.6897
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 322	score: 0.7234
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 323	score: 0.8516
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 324	score: 0.8887
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 325	score: 0.5799
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 326	score: 0.5883
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 327	score: 0.5721
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 328	score: 0.8816
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 329	score: 0.6834
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 330	score: 0.2474
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 331	score: 0.7672
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 332	score: 0.8269
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 333	score: 0.3985
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 334	score: 0.9496
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 335	score: 0.7379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 336	score: 0.2648
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 337	score: 0.4420
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 338	score: 0.8449
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 339	score: 0.8182
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 340	score: 0.5510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 341	score: 0.4778
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 342	score: 0.3559
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 343	score: 0.5350
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 344	score: 0.7705
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 345	score: 0.7067
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 346	score: 0.6981
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 347	score: 0.8185
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 348	score: 0.3551
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 349	score: 0.5218
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 350	score: 0.5555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 351	score: 0.8060
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 352	score: 0.7780
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 353	score: 0.5229
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 354	score: 0.7626
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 355	score: 0.6928
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 356	score: 0.8151
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 357	score: 0.8284
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 358	score: 0.8486
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 359	score: 0.4010
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 360	score: 0.4535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 361	score: 0.4849
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 362	score: 0.6305
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 363	score: 0.6417
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 364	score: 0.6266
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 365	score: 0.3330
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 366	score: 0.6433
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 367	score: 0.5230
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 368	score: 0.5121
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 369	score: 0.4370
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 370	score: 0.2997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 371	score: 0.4686
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 372	score: 0.7893
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 373	score: 0.8136
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 374	score: 0.7408
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 375	score: 0.6300
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 376	score: 0.8219
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 377	score: 0.9076
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 378	score: 0.6036
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 379	score: 0.5615
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 380	score: 0.7535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 381	score: 0.5535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 382	score: 0.4813
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 383	score: 0.5813
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 384	score: 0.8361
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 385	score: 0.5154
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 386	score: 0.4833
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 387	score: 0.6209
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 388	score: 0.6550
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 389	score: 0.8532
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 390	score: 0.4977
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 391	score: 0.5855
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 392	score: 0.7889
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 393	score: 0.5118
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 394	score: 0.7762
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 395	score: 0.8979
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 396	score: 0.4335
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 397	score: 0.8150
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 398	score: 0.5208
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 399	score: 0.9173
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 400	score: 0.9436
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 401	score: 0.5552
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 402	score: 0.7589
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 403	score: 0.6380
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 404	score: 0.5766
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 405	score: 0.6653
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 406	score: 0.8979
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 407	score: 0.6947
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 408	score: 0.8473
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 409	score: 0.9354
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 410	score: 0.7756
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 411	score: 0.7163
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 412	score: 0.6658
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 413	score: 0.9145
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 414	score: 0.7623
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 415	score: 0.7839
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 416	score: 0.6663
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 417	score: 0.4927
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 418	score: 0.9238
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 419	score: 0.9059
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 420	score: 0.9224
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 421	score: 0.9209
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 422	score: 0.8705
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 423	score: 0.7176
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 424	score: 0.7330
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 425	score: 0.9095
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 426	score: 0.8628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 427	score: 0.8478
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 428	score: 0.7592
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 429	score: 0.9096
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 430	score: 0.7265
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 431	score: 0.7007
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 432	score: 0.7981
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 433	score: 0.6663
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 434	score: 0.5160
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 435	score: 0.5913
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 436	score: 0.5815
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 437	score: 0.6687
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 438	score: 0.9526
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 439	score: 0.8040
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 440	score: 0.8105
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 441	score: 0.7779
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 442	score: 0.9429
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 443	score: 0.5892
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 444	score: 0.6481
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 445	score: 0.1426
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 446	score: 0.6001
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 447	score: 0.9297
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 448	score: 0.9221
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 449	score: 0.8420
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 450	score: 0.7623
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 451	score: 0.6078
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 452	score: 0.4210
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 453	score: 0.7163
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 454	score: 0.7995
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 455	score: 0.7695
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 456	score: 0.6102
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 457	score: 0.7531
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 458	score: 0.6439
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 459	score: 0.6417
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 460	score: 0.4468
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 461	score: 0.5588
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 462	score: 0.4328
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 463	score: 0.8328
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 464	score: 0.7576
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 465	score: 0.7801
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 466	score: 0.6337
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 467	score: 0.5395
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 468	score: 0.4890
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 469	score: 0.4910
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 470	score: 0.5005
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 471	score: 0.6052
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 472	score: 0.5044
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 473	score: 0.4614
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 474	score: 0.7002
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 475	score: 0.7726
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 476	score: 0.7078
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 477	score: 0.5536
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 478	score: 0.8117
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 479	score: 0.9336
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 480	score: 0.4279
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 481	score: 0.5418
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 482	score: 0.5781
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 483	score: 0.8904
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 484	score: 0.7581
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 485	score: 0.6204
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 486	score: 0.6566
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 487	score: 0.8351
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 488	score: 0.7735
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 489	score: 0.9156
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 490	score: 0.8305
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 491	score: 0.6523
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 492	score: 0.9061
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 493	score: 0.2510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 494	score: 0.7902
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 495	score: 0.7064
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 496	score: 0.6906
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 497	score: 0.7761
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 498	score: 0.5224
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 499	score: 0.8467
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 500	score: 0.8600
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 501	score: 0.9396
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 502	score: 0.6538
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 503	score: 0.4482
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 504	score: 0.6107
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 505	score: 0.6410
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 506	score: 0.5260
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 507	score: 0.7159
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 508	score: 0.6525
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 509	score: 0.8644
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 510	score: 0.5095
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 511	score: 0.6841
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 512	score: 0.4057
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 513	score: 0.6163
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 514	score: 0.7319
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 515	score: 0.7943
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 516	score: 0.5782
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 517	score: 0.8733
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 518	score: 0.8154
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 519	score: 0.9204
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 520	score: 0.8849
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 521	score: 0.7385
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 522	score: 0.5952
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 523	score: 0.7083
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 524	score: 0.9093
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 525	score: 0.6213
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 526	score: 0.5787
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 527	score: 0.5892
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 528	score: 0.4958
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 529	score: 0.6647
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 530	score: 0.6136
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 531	score: 0.5879
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 532	score: 0.4774
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 533	score: 0.4428
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 534	score: 0.5653
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 535	score: 0.3595
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 536	score: 0.4851
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 537	score: 0.3532
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 538	score: 0.5511
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 539	score: 0.5395
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 540	score: 0.8511
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 541	score: 0.8216
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 542	score: 0.6369
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 543	score: 0.7707
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 544	score: 0.5508
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 545	score: 0.4630
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 546	score: 0.8349
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 547	score: 0.7048
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 548	score: 0.6839
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 549	score: 0.8256
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 550	score: 0.8063
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 551	score: 0.2311
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 552	score: 0.7211
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 553	score: 0.5454
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 554	score: 0.5502
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 555	score: 0.4749
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 556	score: 0.4005
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 557	score: 0.5598
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 558	score: 0.4347
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 559	score: 0.4454
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 560	score: 0.4409
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 561	score: 0.4578
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 562	score: 0.5666
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 563	score: 0.5070
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 564	score: 0.4814
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 565	score: 0.6970
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 566	score: 0.7752
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 567	score: 0.8591
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 568	score: 0.4745
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 569	score: 0.7482
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 570	score: 0.8377
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 571	score: 0.7536
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 572	score: 0.6817
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 573	score: 0.8593
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 574	score: 0.6199
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 575	score: 0.6620
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 576	score: 0.3253
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 577	score: 0.8006
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 578	score: 0.7153
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 579	score: 0.6100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 580	score: 0.6064
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 581	score: 0.6100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 582	score: 0.5962
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 583	score: 0.5046
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 584	score: 0.4840
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 585	score: 0.7380
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 586	score: 0.8473
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 587	score: 0.9688
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 588	score: 0.4884
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 589	score: 0.9141
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 590	score: 0.8461
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 591	score: 0.8316
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 592	score: 0.6512
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 593	score: 0.8600
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 594	score: 0.9346
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 595	score: 0.7300
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 596	score: 0.3812
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 597	score: 0.6898
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 598	score: 0.5254
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 599	score: 0.8057
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 600	score: 0.7995
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 601	score: 0.8032
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 602	score: 0.7150
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 603	score: 0.7197
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 604	score: 0.6718
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 605	score: 0.6494
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 606	score: 0.7235
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 607	score: 0.5462
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 608	score: 0.5669
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 609	score: 0.6863
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 610	score: 0.8827
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 611	score: 0.6113
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 612	score: 0.8477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 613	score: 0.7575
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 614	score: 0.6663
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 615	score: 0.4600
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 616	score: 0.8623
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 617	score: 0.9585
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 618	score: 0.7173
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 619	score: 0.4984
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 620	score: 0.6699
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 621	score: 0.6336
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 622	score: 0.6719
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 623	score: 0.8303
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 624	score: 0.5157
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 625	score: 0.7385
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 626	score: 0.7306
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 627	score: 0.5321
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 628	score: 0.9115
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 629	score: 0.4891
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 630	score: 0.6335
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 631	score: 0.9667
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 632	score: 0.9528
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 633	score: 0.9567
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 634	score: 0.9621
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 635	score: 0.7066
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 636	score: 0.7830
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 637	score: 0.6094
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 638	score: 0.8283
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 639	score: 0.8199
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 640	score: 0.5821
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 641	score: 0.8596
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 642	score: 0.5193
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 643	score: 0.5385
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 644	score: 0.4564
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 645	score: 0.7239
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 646	score: 0.6982
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 647	score: 0.8756
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 648	score: 0.6631
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 649	score: 0.4794
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 650	score: 0.5266
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 651	score: 0.5811
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 652	score: 0.5099
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 653	score: 0.6758
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 654	score: 0.4929
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 655	score: 0.6756
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 656	score: 0.7961
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 657	score: 0.9230
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 658	score: 0.6326
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 659	score: 0.6486
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 660	score: 0.5024
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 661	score: 0.7380
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 662	score: 0.5250
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 663	score: 0.6149
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 664	score: 0.8989
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 665	score: 0.7032
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 666	score: 0.6446
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 667	score: 0.7216
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 668	score: 0.8227
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 669	score: 0.7308
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 670	score: 0.8191
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 671	score: 0.8056
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 672	score: 0.9010
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 673	score: 0.7136
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 674	score: 0.8704
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 675	score: 0.5382
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 676	score: 0.6307
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 677	score: 0.8352
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 678	score: 0.7415
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 679	score: 0.8081
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 680	score: 0.5904
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 681	score: 0.8313
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 682	score: 0.8578
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 683	score: 0.7474
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 684	score: 0.7012
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 685	score: 0.7073
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 686	score: 0.8548
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 687	score: 0.7868
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 688	score: 0.9277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 689	score: 0.5031
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 690	score: 0.4385
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 691	score: 0.7642
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 692	score: 0.9213
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 693	score: 0.8206
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 694	score: 0.6339
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 695	score: 0.7605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 696	score: 0.7935
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 697	score: 0.8827
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 698	score: 0.5340
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 699	score: 0.8407
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 700	score: 0.9270
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 701	score: 0.9337
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 702	score: 0.8413
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 703	score: 0.6071
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 704	score: 0.5792
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 705	score: 0.5666
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 706	score: 0.6609
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 707	score: 0.5974
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 708	score: 0.7996
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 709	score: 0.8971
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 710	score: 0.8966
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 711	score: 0.7876
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 712	score: 0.6605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 713	score: 0.8345
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 714	score: 0.6861
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 715	score: 0.6380
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 716	score: 0.9034
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 717	score: 0.8241
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 718	score: 0.6781
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 719	score: 0.6438
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 720	score: 0.6024
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 721	score: 0.8485
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 722	score: 0.8496
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 723	score: 0.9310
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 724	score: 0.9176
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 725	score: 0.2881
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 726	score: 0.5927
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 727	score: 0.8512
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 728	score: 0.6122
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 729	score: 0.5909
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 730	score: 0.8986
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 731	score: 0.8742
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 732	score: 0.7212
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 733	score: 0.8750
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 734	score: 0.7031
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 735	score: 0.9010
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 736	score: 0.6396
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 737	score: 0.3288
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 738	score: 0.8220
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 739	score: 0.5749
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 740	score: 0.5151
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 741	score: 0.7078
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 742	score: 0.6173
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 743	score: 0.8759
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 744	score: 0.8116
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 745	score: 0.7612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 746	score: 0.6938
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 747	score: 0.7078
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 748	score: 0.9697
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 749	score: 0.8186
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 750	score: 0.9562
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 751	score: 0.9581
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 752	score: 0.7100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 753	score: 0.9110
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 754	score: 0.9143
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 755	score: 0.6000
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 756	score: 0.8687
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 757	score: 0.8553
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 758	score: 0.7533
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 759	score: 0.6520
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 760	score: 0.9716
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 761	score: 0.8958
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 762	score: 0.8518
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 763	score: 0.5271
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 764	score: 0.7511
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 765	score: 0.5619
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 766	score: 0.6551
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 767	score: 0.3584
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 768	score: 0.9549
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 769	score: 0.8630
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 770	score: 0.5043
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 771	score: 0.8192
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 772	score: 0.7856
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 773	score: 0.6747
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 774	score: 0.5696
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 775	score: 0.6342
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 776	score: 0.7610
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 777	score: 0.9377
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 778	score: 0.8678
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 779	score: 0.6748
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 780	score: 0.5772
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 781	score: 0.5603
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 782	score: 0.7583
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 783	score: 0.2364
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 784	score: 0.7317
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 785	score: 0.5404
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 786	score: 0.7238
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 787	score: 0.8419
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 788	score: 0.4773
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 789	score: 0.7815
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 790	score: 0.9467
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 791	score: 0.8521
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 792	score: 0.7710
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 793	score: 0.5696
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 794	score: 0.6211
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 795	score: 0.8021
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 796	score: 0.6281
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 797	score: 0.5920
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 798	score: 0.8237
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 799	score: 0.5762
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 800	score: 0.7443
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 801	score: 0.7446
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 802	score: 0.6583
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 803	score: 0.5565
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 804	score: 0.4897
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 805	score: 0.2411
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 806	score: 0.9144
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 807	score: 0.5151
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 808	score: 0.6584
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 809	score: 0.4687
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 810	score: 0.6123
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 811	score: 0.6035
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 812	score: 0.9684
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 813	score: 0.8643
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 814	score: 0.5284
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 815	score: 0.6531
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 816	score: 0.8837
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 817	score: 0.4058
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 818	score: 0.5133
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 819	score: 0.4471
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 820	score: 0.7433
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 821	score: 0.7872
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 822	score: 0.5463
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 823	score: 0.6016
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 824	score: 0.5262
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 825	score: 0.8477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 826	score: 0.5066
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 827	score: 0.7089
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 828	score: 0.4916
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 829	score: 0.3217
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 830	score: 0.3840
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 831	score: 0.6317
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 832	score: 0.5022
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 833	score: 0.4803
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 834	score: 0.6346
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 835	score: 0.6465
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 836	score: 0.4100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 837	score: 0.5557
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 838	score: 0.8205
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 839	score: 0.2111
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 840	score: 0.6109
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 841	score: 0.6114
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 842	score: 0.2132
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 843	score: 0.5987
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 844	score: 0.5188
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 845	score: 0.4388
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 846	score: 0.3762
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 847	score: 0.7612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 848	score: 0.6283
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 849	score: 0.4549
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 850	score: 0.6491
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 851	score: 0.4888
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 852	score: 0.8969
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 853	score: 0.5245
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 854	score: 0.5842
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 855	score: 0.7344
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 856	score: 0.2156
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 857	score: 0.8379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 858	score: 0.9126
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 859	score: 0.1991
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 860	score: 0.7093
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 861	score: 0.8256
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 862	score: 0.7340
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 863	score: 0.6834
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 864	score: 0.3102
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 865	score: 0.6580
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 866	score: 0.7318
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 867	score: 0.7464
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 868	score: 0.8896
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 869	score: 0.6708
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 870	score: 0.6487
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 871	score: 0.7377
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 872	score: 0.8804
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 873	score: 0.7391
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 874	score: 0.7903
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 875	score: 0.5900
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 876	score: 0.7563
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 877	score: 0.8353
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 878	score: 0.9289
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 879	score: 0.6018
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 880	score: 0.6317
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 881	score: 0.6774
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 882	score: 0.7508
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 883	score: 0.5706
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 884	score: 0.5055
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 885	score: 0.3915
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 886	score: 0.8179
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 887	score: 0.6724
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 888	score: 0.5777
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 889	score: 0.6724
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 890	score: 0.6535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 891	score: 0.4908
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 892	score: 0.6550
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 893	score: 0.7383
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 894	score: 0.6446
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 895	score: 0.7538
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 896	score: 0.5535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 897	score: 0.9186
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 898	score: 0.9359
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 899	score: 0.6225
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 900	score: 0.5732
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 901	score: 0.7138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 902	score: 0.5537
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 903	score: 0.6089
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 904	score: 0.8138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 905	score: 0.6141
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 906	score: 0.8007
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 907	score: 0.5439
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 908	score: 0.8016
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 909	score: 0.8448
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 910	score: 0.6078
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 911	score: 0.8315
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 912	score: 0.7027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 913	score: 0.5942
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 914	score: 0.7281
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 915	score: 0.5838
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 916	score: 0.7367
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 917	score: 0.8502
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 918	score: 0.9468
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 919	score: 0.4788
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 920	score: 0.4191
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 921	score: 0.8214
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 922	score: 0.7240
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 923	score: 0.8027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 924	score: 0.6585
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 925	score: 0.7270
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 926	score: 0.9215
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 927	score: 0.7296
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 928	score: 0.7711
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 929	score: 0.8185
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 930	score: 0.7698
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 931	score: 0.6787
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 932	score: 0.8370
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 933	score: 0.8111
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 934	score: 0.5030
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 935	score: 0.7273
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 936	score: 0.6772
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 937	score: 0.9020
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 938	score: 0.7106
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 939	score: 0.8344
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 940	score: 0.9402
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 941	score: 0.9465
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 942	score: 0.6239
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 943	score: 0.6109
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 944	score: 0.6088
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 945	score: 0.7360
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 946	score: 0.5537
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 947	score: 0.4897
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 948	score: 0.6871
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 949	score: 0.4968
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 950	score: 0.6788
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 951	score: 0.6317
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 952	score: 0.5094
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 953	score: 0.6977
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 954	score: 0.6755
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 955	score: 0.9582
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 956	score: 0.8713
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 957	score: 0.8967
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 958	score: 0.9011
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 959	score: 0.8992
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 960	score: 0.5949
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 961	score: 0.5402
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 962	score: 0.7593
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 963	score: 0.6672
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 964	score: 0.8119
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 965	score: 0.5175
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 966	score: 0.3437
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 967	score: 0.4176
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 968	score: 0.2024
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 969	score: 0.4676
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 970	score: 0.4784
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 971	score: 0.4607
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 972	score: 0.4860
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 973	score: 0.9116
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 974	score: 0.8381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 975	score: 0.9342
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 976	score: 0.7976
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 977	score: 0.6388
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 978	score: 0.9093
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 979	score: 0.8325
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 980	score: 0.8040
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 981	score: 0.8147
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 982	score: 0.9130
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 983	score: 0.7539
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 984	score: 0.7223
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 985	score: 0.8544
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 986	score: 0.5891
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 987	score: 0.5298
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 988	score: 0.5488
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 989	score: 0.5268
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 990	score: 0.8088
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 991	score: 0.6686
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 992	score: 0.6600
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 993	score: 0.6202
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 994	score: 0.6737
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 995	score: 0.7367
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 996	score: 0.6392
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 997	score: 0.8534
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 998	score: 0.6776
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 999	score: 0.2733
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1000	score: 0.8454
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1001	score: 0.7633
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1002	score: 0.8433
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1003	score: 0.4812
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1004	score: 0.5440
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1005	score: 0.5522
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1006	score: 0.6970
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1007	score: 0.5664
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1008	score: 0.9117
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1009	score: 0.6705
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1010	score: 0.7328
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	Segment 1011	score: 0.8308
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-lv	score: 0.6981