diff --git "a/test-en-fi.comet" "b/test-en-fi.comet"
new file mode 100644--- /dev/null
+++ "b/test-en-fi.comet"
@@ -0,0 +1,1013 @@
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 0	score: 0.8379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1	score: 0.9479
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 2	score: 0.9167
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 3	score: 0.8789
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 4	score: 0.9558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 5	score: 0.7290
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 6	score: 0.9492
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 7	score: 0.9164
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 8	score: 0.9228
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 9	score: 0.9166
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 10	score: 0.9151
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 11	score: 0.9105
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 12	score: 0.8389
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 13	score: 0.9195
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 14	score: 0.8573
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 15	score: 0.8305
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 16	score: 0.8816
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 17	score: 0.9622
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 18	score: 0.9441
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 19	score: 0.9318
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 20	score: 0.9644
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 21	score: 0.8837
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 22	score: 0.7913
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 23	score: 0.9349
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 24	score: 0.9419
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 25	score: 0.7053
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 26	score: 0.8580
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 27	score: 0.8887
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 28	score: 0.9369
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 29	score: 0.8008
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 30	score: 0.8521
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 31	score: 0.8904
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 32	score: 0.9064
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 33	score: 0.9596
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 34	score: 0.9561
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 35	score: 0.9432
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 36	score: 0.9258
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 37	score: 0.9385
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 38	score: 0.8609
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 39	score: 0.9320
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 40	score: 0.8264
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 41	score: 0.9620
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 42	score: 0.8997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 43	score: 0.9618
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 44	score: 0.9653
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 45	score: 0.9153
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 46	score: 0.9442
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 47	score: 0.8905
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 48	score: 0.9507
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 49	score: 0.9306
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 50	score: 0.9136
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 51	score: 0.9314
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 52	score: 0.9471
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 53	score: 0.9623
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 54	score: 0.9421
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 55	score: 0.9536
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 56	score: 0.9226
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 57	score: 0.9104
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 58	score: 0.9075
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 59	score: 0.9546
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 60	score: 0.9513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 61	score: 0.9480
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 62	score: 0.8098
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 63	score: 0.9420
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 64	score: 0.8481
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 65	score: 0.7264
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 66	score: 0.8102
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 67	score: 0.7649
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 68	score: 0.9685
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 69	score: 0.9067
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 70	score: 0.9153
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 71	score: 0.7867
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 72	score: 0.9218
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 73	score: 0.9159
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 74	score: 0.8527
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 75	score: 0.9180
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 76	score: 0.9352
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 77	score: 0.9331
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 78	score: 0.9571
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 79	score: 0.9345
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 80	score: 0.9530
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 81	score: 0.9598
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 82	score: 0.9202
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 83	score: 0.7326
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 84	score: 0.8856
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 85	score: 0.8518
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 86	score: 0.8851
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 87	score: 0.9337
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 88	score: 0.9544
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 89	score: 0.5976
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 90	score: 0.7563
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 91	score: 0.8173
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 92	score: 0.9266
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 93	score: 0.9521
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 94	score: 0.7119
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 95	score: 0.8040
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 96	score: 0.9622
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 97	score: 0.9244
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 98	score: 0.9727
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 99	score: 0.9338
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 100	score: 0.9212
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 101	score: 0.8835
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 102	score: 0.9331
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 103	score: 0.9773
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 104	score: 0.9374
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 105	score: 0.8659
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 106	score: 0.9414
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 107	score: 0.9239
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 108	score: 0.8449
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 109	score: 0.8610
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 110	score: 0.9163
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 111	score: 0.9693
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 112	score: 0.9574
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 113	score: 0.9323
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 114	score: 0.8700
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 115	score: 0.8756
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 116	score: 0.9225
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 117	score: 0.9343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 118	score: 0.9683
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 119	score: 0.9327
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 120	score: 0.8951
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 121	score: 0.9400
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 122	score: 0.9566
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 123	score: 0.9694
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 124	score: 0.9346
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 125	score: 0.8477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 126	score: 0.9233
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 127	score: 0.8951
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 128	score: 0.9261
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 129	score: 0.9557
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 130	score: 0.9598
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 131	score: 0.8863
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 132	score: 0.8617
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 133	score: 0.9767
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 134	score: 0.9283
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 135	score: 0.9146
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 136	score: 0.9647
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 137	score: 0.9116
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 138	score: 0.9313
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 139	score: 0.9448
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 140	score: 0.9308
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 141	score: 0.9308
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 142	score: 0.9530
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 143	score: 0.9341
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 144	score: 0.8681
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 145	score: 0.9470
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 146	score: 0.9434
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 147	score: 0.8752
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 148	score: 0.9646
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 149	score: 0.9218
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 150	score: 0.8536
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 151	score: 0.9353
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 152	score: 0.8937
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 153	score: 0.8732
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 154	score: 0.8542
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 155	score: 0.9298
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 156	score: 0.9099
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 157	score: 0.8277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 158	score: 0.9418
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 159	score: 0.8911
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 160	score: 0.9362
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 161	score: 0.9286
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 162	score: 0.9110
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 163	score: 0.9337
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 164	score: 0.8578
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 165	score: 0.8019
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 166	score: 0.9410
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 167	score: 0.8668
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 168	score: 0.7887
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 169	score: 0.9290
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 170	score: 0.9502
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 171	score: 0.9267
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 172	score: 0.8167
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 173	score: 0.8968
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 174	score: 0.9302
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 175	score: 0.9620
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 176	score: 0.8277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 177	score: 0.9069
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 178	score: 0.9126
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 179	score: 0.9429
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 180	score: 0.9653
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 181	score: 0.9298
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 182	score: 0.9550
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 183	score: 0.9610
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 184	score: 0.8711
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 185	score: 0.9605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 186	score: 0.9326
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 187	score: 0.9302
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 188	score: 0.9001
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 189	score: 0.9335
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 190	score: 0.8690
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 191	score: 0.9318
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 192	score: 0.8961
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 193	score: 0.8434
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 194	score: 0.8536
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 195	score: 0.9532
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 196	score: 0.8914
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 197	score: 0.8913
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 198	score: 0.9386
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 199	score: 0.9516
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 200	score: 0.8630
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 201	score: 0.7933
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 202	score: 0.6331
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 203	score: 0.7121
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 204	score: 0.9206
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 205	score: 0.9056
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 206	score: 0.9594
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 207	score: 0.9426
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 208	score: 0.9469
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 209	score: 0.7604
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 210	score: 0.9608
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 211	score: 0.9378
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 212	score: 0.9649
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 213	score: 0.9243
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 214	score: 0.9562
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 215	score: 0.9344
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 216	score: 0.9617
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 217	score: 0.9323
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 218	score: 0.8879
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 219	score: 0.9503
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 220	score: 0.9501
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 221	score: 0.9526
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 222	score: 0.9536
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 223	score: 0.9305
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 224	score: 0.9664
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 225	score: 0.9379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 226	score: 0.9561
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 227	score: 0.8261
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 228	score: 0.8349
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 229	score: 0.9066
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 230	score: 0.9578
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 231	score: 0.9245
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 232	score: 0.9119
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 233	score: 0.9166
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 234	score: 0.8861
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 235	score: 0.9329
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 236	score: 0.9319
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 237	score: 0.8507
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 238	score: 0.9306
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 239	score: 0.9448
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 240	score: 0.8920
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 241	score: 0.8822
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 242	score: 0.9296
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 243	score: 0.8541
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 244	score: 0.9001
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 245	score: 0.9339
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 246	score: 0.7406
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 247	score: 0.8710
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 248	score: 0.8024
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 249	score: 0.9756
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 250	score: 0.9431
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 251	score: 0.9494
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 252	score: 0.9303
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 253	score: 0.9516
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 254	score: 0.9580
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 255	score: 0.9338
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 256	score: 0.9161
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 257	score: 0.9263
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 258	score: 0.9068
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 259	score: 0.7711
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 260	score: 0.9628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 261	score: 0.9183
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 262	score: 0.9413
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 263	score: 0.9222
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 264	score: 0.9262
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 265	score: 0.8943
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 266	score: 0.9171
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 267	score: 0.9056
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 268	score: 0.9210
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 269	score: 0.9659
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 270	score: 0.6909
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 271	score: 0.8764
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 272	score: 0.8852
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 273	score: 0.7686
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 274	score: 0.7575
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 275	score: 0.8802
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 276	score: 0.8396
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 277	score: 0.9735
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 278	score: 0.8502
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 279	score: 0.9602
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 280	score: 0.9442
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 281	score: 0.9609
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 282	score: 0.9745
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 283	score: 0.9188
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 284	score: 0.9739
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 285	score: 0.9720
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 286	score: 0.9543
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 287	score: 0.9188
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 288	score: 0.9597
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 289	score: 0.9068
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 290	score: 0.9255
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 291	score: 0.9276
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 292	score: 0.9381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 293	score: 0.9540
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 294	score: 0.8278
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 295	score: 0.7782
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 296	score: 0.8612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 297	score: 0.9113
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 298	score: 0.6829
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 299	score: 0.9328
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 300	score: 0.9560
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 301	score: 0.9389
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 302	score: 0.9431
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 303	score: 0.9595
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 304	score: 0.8515
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 305	score: 0.9592
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 306	score: 0.9246
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 307	score: 0.9408
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 308	score: 0.9379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 309	score: 0.9526
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 310	score: 0.9354
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 311	score: 0.9346
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 312	score: 0.9184
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 313	score: 0.8021
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 314	score: 0.9736
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 315	score: 0.9600
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 316	score: 0.9134
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 317	score: 0.9492
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 318	score: 0.8383
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 319	score: 0.7196
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 320	score: 0.9005
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 321	score: 0.8479
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 322	score: 0.9374
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 323	score: 0.9385
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 324	score: 0.9477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 325	score: 0.9315
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 326	score: 0.8832
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 327	score: 0.8961
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 328	score: 0.8873
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 329	score: 0.9520
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 330	score: 0.7999
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 331	score: 0.9627
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 332	score: 0.9542
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 333	score: 0.9270
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 334	score: 0.9806
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 335	score: 0.9428
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 336	score: 0.9065
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 337	score: 0.8974
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 338	score: 0.9414
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 339	score: 0.9409
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 340	score: 0.8992
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 341	score: 0.9208
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 342	score: 0.9007
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 343	score: 0.9044
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 344	score: 0.8974
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 345	score: 0.8236
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 346	score: 0.8997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 347	score: 0.9408
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 348	score: 0.9047
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 349	score: 0.8777
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 350	score: 0.8774
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 351	score: 0.8637
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 352	score: 0.9453
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 353	score: 0.9555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 354	score: 0.9138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 355	score: 0.9496
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 356	score: 0.9549
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 357	score: 0.9374
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 358	score: 0.9653
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 359	score: 0.8324
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 360	score: 0.7780
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 361	score: 0.8455
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 362	score: 0.9393
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 363	score: 0.8917
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 364	score: 0.8882
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 365	score: 0.8932
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 366	score: 0.8807
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 367	score: 0.9260
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 368	score: 0.8333
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 369	score: 0.8225
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 370	score: 0.8459
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 371	score: 0.8526
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 372	score: 0.9300
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 373	score: 0.9426
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 374	score: 0.9588
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 375	score: 0.9433
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 376	score: 0.9674
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 377	score: 0.9524
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 378	score: 0.8485
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 379	score: 0.9360
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 380	score: 0.9559
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 381	score: 0.9299
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 382	score: 0.8063
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 383	score: 0.8680
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 384	score: 0.7562
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 385	score: 0.8561
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 386	score: 0.8591
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 387	score: 0.9532
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 388	score: 0.9497
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 389	score: 0.9845
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 390	score: 0.9559
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 391	score: 0.9179
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 392	score: 0.9370
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 393	score: 0.9465
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 394	score: 0.9501
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 395	score: 0.9659
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 396	score: 0.8326
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 397	score: 0.9786
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 398	score: 0.9378
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 399	score: 0.9684
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 400	score: 0.9757
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 401	score: 0.8505
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 402	score: 0.9289
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 403	score: 0.8880
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 404	score: 0.8326
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 405	score: 0.9499
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 406	score: 0.9558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 407	score: 0.9399
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 408	score: 0.9703
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 409	score: 0.9284
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 410	score: 0.9251
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 411	score: 0.9268
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 412	score: 0.8557
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 413	score: 0.9519
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 414	score: 0.9196
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 415	score: 0.9372
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 416	score: 0.9231
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 417	score: 0.9380
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 418	score: 0.9740
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 419	score: 0.9573
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 420	score: 0.9602
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 421	score: 0.9826
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 422	score: 0.8893
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 423	score: 0.7684
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 424	score: 0.9099
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 425	score: 0.9599
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 426	score: 0.9311
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 427	score: 0.9610
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 428	score: 0.9583
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 429	score: 0.9437
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 430	score: 0.9197
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 431	score: 0.7344
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 432	score: 0.8643
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 433	score: 0.8723
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 434	score: 0.8775
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 435	score: 0.9370
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 436	score: 0.8413
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 437	score: 0.8763
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 438	score: 0.9702
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 439	score: 0.9034
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 440	score: 0.9668
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 441	score: 0.9299
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 442	score: 0.8831
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 443	score: 0.9063
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 444	score: 0.8387
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 445	score: 0.9093
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 446	score: 0.7986
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 447	score: 0.9579
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 448	score: 0.9763
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 449	score: 0.8578
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 450	score: 0.9451
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 451	score: 0.9628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 452	score: 0.9314
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 453	score: 0.9368
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 454	score: 0.9376
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 455	score: 0.9083
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 456	score: 0.9112
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 457	score: 0.9388
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 458	score: 0.9153
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 459	score: 0.7233
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 460	score: 0.8039
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 461	score: 0.9381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 462	score: 0.9237
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 463	score: 0.7766
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 464	score: 0.9446
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 465	score: 0.8741
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 466	score: 0.9604
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 467	score: 0.7824
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 468	score: 0.6283
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 469	score: 0.8038
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 470	score: 0.8644
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 471	score: 0.9082
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 472	score: 0.8676
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 473	score: 0.9157
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 474	score: 0.8786
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 475	score: 0.9178
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 476	score: 0.9242
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 477	score: 0.8869
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 478	score: 0.9115
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 479	score: 0.9107
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 480	score: 0.8970
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 481	score: 0.9143
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 482	score: 0.9236
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 483	score: 0.8412
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 484	score: 0.9590
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 485	score: 0.8755
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 486	score: 0.8668
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 487	score: 0.8901
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 488	score: 0.9542
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 489	score: 0.8694
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 490	score: 0.9415
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 491	score: 0.9299
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 492	score: 0.9514
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 493	score: 0.9276
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 494	score: 0.7582
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 495	score: 0.9331
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 496	score: 0.9237
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 497	score: 0.8868
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 498	score: 0.7886
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 499	score: 0.9445
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 500	score: 0.9021
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 501	score: 0.9387
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 502	score: 0.9396
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 503	score: 0.8485
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 504	score: 0.8633
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 505	score: 0.7020
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 506	score: 0.9062
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 507	score: 0.7936
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 508	score: 0.7871
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 509	score: 0.8407
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 510	score: 0.8323
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 511	score: 0.8298
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 512	score: 0.9367
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 513	score: 0.8963
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 514	score: 0.9620
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 515	score: 0.9509
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 516	score: 0.9066
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 517	score: 0.9214
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 518	score: 0.9008
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 519	score: 0.9009
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 520	score: 0.9291
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 521	score: 0.9506
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 522	score: 0.9406
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 523	score: 0.9186
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 524	score: 0.9562
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 525	score: 0.9426
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 526	score: 0.8238
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 527	score: 0.7850
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 528	score: 0.7916
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 529	score: 0.8961
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 530	score: 0.8757
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 531	score: 0.8967
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 532	score: 0.9318
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 533	score: 0.8610
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 534	score: 0.8437
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 535	score: 0.8277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 536	score: 0.7549
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 537	score: 0.8991
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 538	score: 0.8148
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 539	score: 0.9505
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 540	score: 0.8499
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 541	score: 0.9453
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 542	score: 0.9150
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 543	score: 0.9213
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 544	score: 0.9535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 545	score: 0.9696
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 546	score: 0.9238
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 547	score: 0.9374
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 548	score: 0.9253
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 549	score: 0.9599
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 550	score: 0.9191
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 551	score: 0.9529
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 552	score: 0.9490
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 553	score: 0.9612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 554	score: 0.8903
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 555	score: 0.8293
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 556	score: 0.7504
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 557	score: 0.8767
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 558	score: 0.8690
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 559	score: 0.8627
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 560	score: 0.7870
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 561	score: 0.9314
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 562	score: 0.9288
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 563	score: 0.8771
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 564	score: 0.8810
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 565	score: 0.9599
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 566	score: 0.8849
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 567	score: 0.9513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 568	score: 0.9029
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 569	score: 0.9139
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 570	score: 0.9273
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 571	score: 0.9464
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 572	score: 0.9271
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 573	score: 0.9660
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 574	score: 0.9624
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 575	score: 0.7668
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 576	score: 0.8103
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 577	score: 0.9460
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 578	score: 0.9654
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 579	score: 0.7517
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 580	score: 0.7113
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 581	score: 0.9153
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 582	score: 0.9148
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 583	score: 0.5765
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 584	score: 0.5694
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 585	score: 0.8635
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 586	score: 0.9259
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 587	score: 0.9645
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 588	score: 0.9007
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 589	score: 0.8229
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 590	score: 0.9354
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 591	score: 0.9481
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 592	score: 0.8303
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 593	score: 0.9555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 594	score: 0.9549
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 595	score: 0.8428
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 596	score: 0.9158
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 597	score: 0.9115
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 598	score: 0.9196
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 599	score: 0.9374
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 600	score: 0.9490
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 601	score: 0.9045
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 602	score: 0.9217
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 603	score: 0.9118
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 604	score: 0.9520
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 605	score: 0.9569
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 606	score: 0.8216
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 607	score: 0.8216
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 608	score: 0.8505
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 609	score: 0.7627
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 610	score: 0.9700
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 611	score: 0.9679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 612	score: 0.9597
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 613	score: 0.9128
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 614	score: 0.8073
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 615	score: 0.9272
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 616	score: 0.9317
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 617	score: 0.6041
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 618	score: 0.9688
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 619	score: 0.8115
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 620	score: 0.9627
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 621	score: 0.7977
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 622	score: 0.9698
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 623	score: 0.9199
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 624	score: 0.9151
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 625	score: 0.9452
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 626	score: 0.9699
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 627	score: 0.9051
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 628	score: 0.9387
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 629	score: 0.9594
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 630	score: 0.9602
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 631	score: 0.9520
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 632	score: 0.9633
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 633	score: 0.9495
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 634	score: 0.9797
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 635	score: 0.9481
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 636	score: 0.9564
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 637	score: 0.8551
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 638	score: 0.8910
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 639	score: 0.9427
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 640	score: 0.9392
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 641	score: 0.9808
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 642	score: 0.2571
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 643	score: 0.9394
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 644	score: 0.7203
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 645	score: 0.8678
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 646	score: 0.8999
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 647	score: 0.9271
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 648	score: 0.8672
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 649	score: 0.8316
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 650	score: 0.9649
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 651	score: 0.6999
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 652	score: 0.8692
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 653	score: 0.8708
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 654	score: 0.8684
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 655	score: 0.9627
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 656	score: 0.9679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 657	score: 0.8076
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 658	score: 0.7978
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 659	score: 0.8950
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 660	score: 0.8745
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 661	score: 0.9503
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 662	score: 0.9624
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 663	score: 0.8259
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 664	score: 0.9281
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 665	score: 0.9045
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 666	score: 0.9057
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 667	score: 0.9082
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 668	score: 0.9544
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 669	score: 0.9768
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 670	score: 0.9258
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 671	score: 0.9464
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 672	score: 0.9572
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 673	score: 0.9361
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 674	score: 0.9553
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 675	score: 0.9395
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 676	score: 0.9674
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 677	score: 0.9559
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 678	score: 0.9454
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 679	score: 0.9470
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 680	score: 0.8901
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 681	score: 0.9436
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 682	score: 0.9032
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 683	score: 0.8421
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 684	score: 0.9042
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 685	score: 0.9390
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 686	score: 0.8887
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 687	score: 0.9389
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 688	score: 0.9269
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 689	score: 0.9200
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 690	score: 0.9693
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 691	score: 0.9122
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 692	score: 0.9652
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 693	score: 0.8987
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 694	score: 0.7492
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 695	score: 0.9589
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 696	score: 0.9561
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 697	score: 0.9831
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 698	score: 0.7849
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 699	score: 0.9468
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 700	score: 0.8251
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 701	score: 0.9346
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 702	score: 0.9604
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 703	score: 0.9136
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 704	score: 0.7555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 705	score: 0.9157
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 706	score: 0.7840
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 707	score: 0.9243
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 708	score: 0.9277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 709	score: 0.8994
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 710	score: 0.9490
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 711	score: 0.9439
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 712	score: 0.9609
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 713	score: 0.8851
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 714	score: 0.7853
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 715	score: 0.8013
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 716	score: 0.9372
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 717	score: 0.8841
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 718	score: 0.9798
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 719	score: 0.9571
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 720	score: 0.9456
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 721	score: 0.9564
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 722	score: 0.9400
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 723	score: 0.8997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 724	score: 0.9724
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 725	score: 0.9166
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 726	score: 0.9455
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 727	score: 0.9565
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 728	score: 0.7249
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 729	score: 0.8214
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 730	score: 0.6915
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 731	score: 0.8930
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 732	score: 0.9075
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 733	score: 0.9628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 734	score: 0.8985
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 735	score: 0.9526
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 736	score: 0.9375
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 737	score: 0.9338
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 738	score: 0.9460
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 739	score: 0.9051
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 740	score: 0.8947
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 741	score: 0.7632
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 742	score: 0.8762
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 743	score: 0.9437
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 744	score: 0.7634
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 745	score: 0.9552
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 746	score: 0.9524
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 747	score: 0.9138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 748	score: 0.9265
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 749	score: 0.9613
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 750	score: 0.9477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 751	score: 0.9555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 752	score: 0.9180
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 753	score: 0.9470
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 754	score: 0.9481
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 755	score: 0.9587
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 756	score: 0.8913
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 757	score: 0.9327
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 758	score: 0.9195
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 759	score: 0.9425
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 760	score: 0.9766
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 761	score: 0.9164
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 762	score: 0.9659
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 763	score: 0.8997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 764	score: 0.8930
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 765	score: 0.9319
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 766	score: 0.9518
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 767	score: 0.9322
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 768	score: 0.9631
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 769	score: 0.9866
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 770	score: 0.9168
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 771	score: 0.9570
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 772	score: 0.9474
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 773	score: 0.9364
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 774	score: 0.9100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 775	score: 0.9145
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 776	score: 0.8894
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 777	score: 0.8837
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 778	score: 0.7812
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 779	score: 0.9169
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 780	score: 0.8762
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 781	score: 0.8361
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 782	score: 0.9039
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 783	score: 0.7253
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 784	score: 0.9193
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 785	score: 0.8275
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 786	score: 0.8362
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 787	score: 0.9405
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 788	score: 0.9497
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 789	score: 0.9264
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 790	score: 0.9459
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 791	score: 0.9287
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 792	score: 0.9695
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 793	score: 0.9490
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 794	score: 0.9066
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 795	score: 0.9219
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 796	score: 0.9722
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 797	score: 0.9031
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 798	score: 0.9501
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 799	score: 0.7846
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 800	score: 0.8565
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 801	score: 0.9312
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 802	score: 0.9164
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 803	score: 0.8723
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 804	score: 0.6734
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 805	score: 0.9373
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 806	score: 0.8978
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 807	score: 0.9525
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 808	score: 0.9469
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 809	score: 0.8978
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 810	score: 0.8706
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 811	score: 0.8850
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 812	score: 0.9315
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 813	score: 0.9380
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 814	score: 0.9233
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 815	score: 0.8558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 816	score: 0.9210
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 817	score: 0.8908
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 818	score: 0.5948
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 819	score: 0.8412
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 820	score: 0.9667
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 821	score: 0.8510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 822	score: 0.8223
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 823	score: 0.9260
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 824	score: 0.9558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 825	score: 0.9288
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 826	score: 0.9285
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 827	score: 0.9274
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 828	score: 0.9382
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 829	score: 0.7597
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 830	score: 0.8425
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 831	score: 0.9021
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 832	score: 0.9199
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 833	score: 0.7666
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 834	score: 0.8581
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 835	score: 0.7729
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 836	score: 0.6611
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 837	score: 0.7158
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 838	score: 0.9210
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 839	score: 0.9148
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 840	score: 0.8942
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 841	score: 0.9121
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 842	score: 0.8650
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 843	score: 0.9345
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 844	score: 0.9168
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 845	score: 0.8945
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 846	score: 0.3038
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 847	score: 0.9115
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 848	score: 0.8747
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 849	score: 0.8796
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 850	score: 0.8891
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 851	score: 0.9510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 852	score: 0.9492
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 853	score: 0.7011
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 854	score: 0.8227
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 855	score: 0.9493
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 856	score: 0.8984
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 857	score: 0.9306
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 858	score: 0.9461
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 859	score: 0.9212
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 860	score: 0.9443
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 861	score: 0.8785
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 862	score: 0.8495
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 863	score: 0.9617
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 864	score: 0.9049
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 865	score: 0.9246
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 866	score: 0.9508
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 867	score: 0.7333
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 868	score: 0.8314
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 869	score: 0.9309
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 870	score: 0.9270
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 871	score: 0.9338
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 872	score: 0.9510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 873	score: 0.9681
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 874	score: 0.9589
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 875	score: 0.8751
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 876	score: 0.9347
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 877	score: 0.2908
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 878	score: 0.9535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 879	score: 0.7276
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 880	score: 0.9450
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 881	score: 0.9663
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 882	score: 0.9706
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 883	score: 0.8424
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 884	score: 0.8763
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 885	score: 0.9357
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 886	score: 0.9290
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 887	score: 0.9040
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 888	score: 0.8439
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 889	score: 0.8827
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 890	score: 0.8465
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 891	score: 0.9465
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 892	score: 0.6883
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 893	score: 0.8444
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 894	score: 0.9369
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 895	score: 0.9648
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 896	score: 0.9484
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 897	score: 0.8531
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 898	score: 0.9781
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 899	score: 0.9200
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 900	score: 0.8955
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 901	score: 0.9497
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 902	score: 0.8315
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 903	score: 0.9304
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 904	score: 0.9255
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 905	score: 0.9084
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 906	score: 0.9147
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 907	score: 0.9239
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 908	score: 0.9296
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 909	score: 0.9575
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 910	score: 0.8987
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 911	score: 0.8914
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 912	score: 0.9606
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 913	score: 0.9480
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 914	score: 0.9490
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 915	score: 0.9538
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 916	score: 0.9126
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 917	score: 0.9250
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 918	score: 0.7288
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 919	score: 0.9365
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 920	score: 0.9231
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 921	score: 0.9134
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 922	score: 0.9334
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 923	score: 0.9080
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 924	score: 0.9476
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 925	score: 0.9383
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 926	score: 0.9204
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 927	score: 0.7797
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 928	score: 0.9138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 929	score: 0.8672
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 930	score: 0.9404
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 931	score: 0.8090
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 932	score: 0.8860
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 933	score: 0.9084
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 934	score: 0.8622
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 935	score: 0.8718
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 936	score: 0.8241
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 937	score: 0.9704
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 938	score: 0.9781
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 939	score: 0.9426
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 940	score: 0.9612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 941	score: 0.9941
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 942	score: 0.9686
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 943	score: 0.9309
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 944	score: 0.9049
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 945	score: 0.8935
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 946	score: 0.6705
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 947	score: 0.8450
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 948	score: 0.9112
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 949	score: 0.9420
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 950	score: 0.7729
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 951	score: 0.5156
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 952	score: 0.8602
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 953	score: 0.9086
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 954	score: 0.7475
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 955	score: 0.9670
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 956	score: 0.9645
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 957	score: 0.9729
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 958	score: 0.9180
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 959	score: 0.9223
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 960	score: 0.9132
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 961	score: 0.7023
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 962	score: 0.9047
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 963	score: 0.8638
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 964	score: 0.9693
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 965	score: 0.9076
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 966	score: 0.9404
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 967	score: 0.7333
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 968	score: 0.9001
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 969	score: 0.8277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 970	score: 0.9265
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 971	score: 0.8100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 972	score: 0.8532
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 973	score: 0.8480
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 974	score: 0.9191
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 975	score: 0.9631
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 976	score: 0.9070
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 977	score: 0.8966
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 978	score: 0.9544
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 979	score: 0.9428
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 980	score: 0.8721
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 981	score: 0.8638
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 982	score: 0.8547
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 983	score: 0.9008
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 984	score: 0.9391
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 985	score: 0.9732
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 986	score: 0.9166
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 987	score: 0.8210
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 988	score: 0.7615
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 989	score: 0.7627
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 990	score: 0.9527
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 991	score: 0.7246
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 992	score: 0.9436
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 993	score: 0.9306
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 994	score: 0.7983
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 995	score: 0.8559
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 996	score: 0.9456
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 997	score: 0.9805
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 998	score: 0.6755
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 999	score: 0.8976
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1000	score: 0.9725
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1001	score: 0.9272
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1002	score: 0.6925
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1003	score: 0.8609
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1004	score: 0.8569
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1005	score: 0.9357
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1006	score: 0.9534
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1007	score: 0.9301
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1008	score: 0.9713
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1009	score: 0.8700
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1010	score: 0.8687
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	Segment 1011	score: 0.9124
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-fi	score: 0.8985