diff --git "a/test-en-cs.comet" "b/test-en-cs.comet"
new file mode 100644--- /dev/null
+++ "b/test-en-cs.comet"
@@ -0,0 +1,1013 @@
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 0	score: 0.7785
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1	score: 0.9527
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 2	score: 0.9336
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 3	score: 0.8807
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 4	score: 0.9262
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 5	score: 0.7238
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 6	score: 0.8510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 7	score: 0.9286
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 8	score: 0.9029
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 9	score: 0.9679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 10	score: 0.9225
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 11	score: 0.8817
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 12	score: 0.8815
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 13	score: 0.9488
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 14	score: 0.8418
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 15	score: 0.6416
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 16	score: 0.9560
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 17	score: 0.9610
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 18	score: 0.9584
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 19	score: 0.9156
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 20	score: 0.9427
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 21	score: 0.9618
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 22	score: 0.8904
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 23	score: 0.9382
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 24	score: 0.9478
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 25	score: 0.9567
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 26	score: 0.9313
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 27	score: 0.9261
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 28	score: 0.9034
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 29	score: 0.9627
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 30	score: 0.8090
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 31	score: 0.9180
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 32	score: 0.8348
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 33	score: 0.9550
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 34	score: 0.9407
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 35	score: 0.9683
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 36	score: 0.9530
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 37	score: 0.8758
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 38	score: 0.9458
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 39	score: 0.9530
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 40	score: 0.8640
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 41	score: 0.9397
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 42	score: 0.9374
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 43	score: 0.9608
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 44	score: 0.9383
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 45	score: 0.9019
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 46	score: 0.9520
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 47	score: 0.8961
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 48	score: 0.7482
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 49	score: 0.9586
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 50	score: 0.9239
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 51	score: 0.9497
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 52	score: 0.9717
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 53	score: 0.9680
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 54	score: 0.9531
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 55	score: 0.9628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 56	score: 0.9412
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 57	score: 0.8431
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 58	score: 0.8991
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 59	score: 0.9744
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 60	score: 0.9493
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 61	score: 0.9602
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 62	score: 0.9175
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 63	score: 0.9278
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 64	score: 0.8899
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 65	score: 0.8053
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 66	score: 0.6652
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 67	score: 0.6086
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 68	score: 0.9659
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 69	score: 0.9381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 70	score: 0.8349
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 71	score: 0.8903
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 72	score: 0.8920
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 73	score: 0.9176
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 74	score: 0.9117
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 75	score: 0.8841
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 76	score: 0.9437
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 77	score: 0.9530
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 78	score: 0.9349
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 79	score: 0.9539
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 80	score: 0.9147
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 81	score: 0.9413
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 82	score: 0.8760
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 83	score: 0.8198
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 84	score: 0.9601
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 85	score: 0.9436
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 86	score: 0.8997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 87	score: 0.9335
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 88	score: 0.9605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 89	score: 0.9443
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 90	score: 0.8813
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 91	score: 0.9212
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 92	score: 0.8669
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 93	score: 0.9709
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 94	score: 0.9546
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 95	score: 0.9718
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 96	score: 0.8966
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 97	score: 0.9285
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 98	score: 0.8341
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 99	score: 0.9129
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 100	score: 0.9783
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 101	score: 0.9249
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 102	score: 0.9232
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 103	score: 0.9703
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 104	score: 0.9276
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 105	score: 0.8187
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 106	score: 0.9522
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 107	score: 0.9139
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 108	score: 0.8044
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 109	score: 0.7147
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 110	score: 0.9416
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 111	score: 0.9660
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 112	score: 0.9674
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 113	score: 0.9379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 114	score: 0.9320
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 115	score: 0.9587
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 116	score: 0.9477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 117	score: 0.9630
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 118	score: 0.9712
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 119	score: 0.9307
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 120	score: 0.9246
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 121	score: 0.9475
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 122	score: 0.9743
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 123	score: 0.9203
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 124	score: 0.9576
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 125	score: 0.9118
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 126	score: 0.9556
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 127	score: 0.9230
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 128	score: 0.9523
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 129	score: 0.9652
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 130	score: 0.9384
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 131	score: 0.9176
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 132	score: 0.9111
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 133	score: 0.9854
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 134	score: 0.8273
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 135	score: 0.9185
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 136	score: 0.9661
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 137	score: 0.9178
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 138	score: 0.9464
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 139	score: 0.9595
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 140	score: 0.9359
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 141	score: 0.9213
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 142	score: 0.9762
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 143	score: 0.9287
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 144	score: 0.9711
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 145	score: 0.9482
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 146	score: 0.9332
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 147	score: 0.8954
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 148	score: 0.9300
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 149	score: 0.9532
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 150	score: 0.9614
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 151	score: 0.9458
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 152	score: 0.7696
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 153	score: 0.7951
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 154	score: 0.8993
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 155	score: 0.9471
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 156	score: 0.8911
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 157	score: 0.7102
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 158	score: 0.9414
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 159	score: 0.9582
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 160	score: 0.9643
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 161	score: 0.8572
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 162	score: 0.9226
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 163	score: 0.9728
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 164	score: 0.9481
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 165	score: 0.8666
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 166	score: 0.9275
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 167	score: 0.8533
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 168	score: 0.8738
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 169	score: 0.9407
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 170	score: 0.8924
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 171	score: 0.9566
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 172	score: 0.9373
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 173	score: 0.9419
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 174	score: 0.9250
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 175	score: 0.8924
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 176	score: 0.9162
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 177	score: 0.9269
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 178	score: 0.9412
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 179	score: 0.9344
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 180	score: 0.9286
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 181	score: 0.9582
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 182	score: 0.9328
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 183	score: 0.9517
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 184	score: 0.7220
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 185	score: 0.9628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 186	score: 0.9853
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 187	score: 0.9346
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 188	score: 0.9174
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 189	score: 0.9206
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 190	score: 0.8894
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 191	score: 0.9455
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 192	score: 0.8732
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 193	score: 0.8627
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 194	score: 0.8276
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 195	score: 0.9781
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 196	score: 0.8938
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 197	score: 0.7863
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 198	score: 0.9153
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 199	score: 0.9059
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 200	score: 0.9014
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 201	score: 0.8563
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 202	score: 0.8363
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 203	score: 0.7972
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 204	score: 0.9417
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 205	score: 0.9517
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 206	score: 0.9474
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 207	score: 0.9343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 208	score: 0.9556
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 209	score: 0.9683
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 210	score: 0.9694
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 211	score: 0.9564
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 212	score: 0.9345
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 213	score: 0.8716
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 214	score: 0.9264
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 215	score: 0.9284
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 216	score: 0.9282
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 217	score: 0.9596
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 218	score: 0.9550
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 219	score: 0.9529
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 220	score: 0.9819
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 221	score: 0.9543
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 222	score: 0.9680
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 223	score: 0.8922
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 224	score: 0.9782
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 225	score: 0.9547
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 226	score: 0.9545
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 227	score: 0.7755
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 228	score: 0.9409
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 229	score: 0.9079
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 230	score: 0.9763
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 231	score: 0.7810
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 232	score: 0.8735
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 233	score: 0.8628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 234	score: 0.8657
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 235	score: 0.8252
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 236	score: 0.9381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 237	score: 0.8581
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 238	score: 0.9214
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 239	score: 0.9676
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 240	score: 0.8539
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 241	score: 0.9123
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 242	score: 0.9714
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 243	score: 0.8924
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 244	score: 0.9340
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 245	score: 0.9066
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 246	score: 0.8330
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 247	score: 0.8273
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 248	score: 0.7564
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 249	score: 0.9598
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 250	score: 0.9599
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 251	score: 0.9283
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 252	score: 0.9650
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 253	score: 0.9643
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 254	score: 0.9465
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 255	score: 0.9429
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 256	score: 0.9450
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 257	score: 0.9314
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 258	score: 0.9466
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 259	score: 0.9418
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 260	score: 0.9701
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 261	score: 0.9343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 262	score: 0.9518
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 263	score: 0.8824
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 264	score: 0.9579
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 265	score: 0.9374
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 266	score: 0.9013
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 267	score: 0.8793
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 268	score: 0.9191
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 269	score: 0.9338
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 270	score: 0.9305
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 271	score: 0.8541
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 272	score: 0.9371
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 273	score: 0.6095
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 274	score: 0.7080
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 275	score: 0.8605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 276	score: 0.8439
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 277	score: 0.9607
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 278	score: 0.9068
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 279	score: 0.9603
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 280	score: 0.9595
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 281	score: 0.9488
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 282	score: 0.9729
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 283	score: 0.9546
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 284	score: 0.9359
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 285	score: 0.9445
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 286	score: 0.9333
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 287	score: 0.9222
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 288	score: 0.9208
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 289	score: 0.9221
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 290	score: 0.8994
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 291	score: 0.9433
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 292	score: 0.9522
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 293	score: 0.9631
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 294	score: 0.8151
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 295	score: 0.8703
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 296	score: 0.9122
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 297	score: 0.9441
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 298	score: 0.9537
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 299	score: 0.9480
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 300	score: 0.9594
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 301	score: 0.9085
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 302	score: 0.8583
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 303	score: 0.9260
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 304	score: 0.9474
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 305	score: 0.8718
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 306	score: 0.9467
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 307	score: 0.9421
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 308	score: 0.9358
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 309	score: 0.9251
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 310	score: 0.9833
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 311	score: 0.9552
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 312	score: 0.9592
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 313	score: 0.8913
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 314	score: 0.9549
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 315	score: 0.9384
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 316	score: 0.9380
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 317	score: 0.9217
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 318	score: 0.9044
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 319	score: 0.7869
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 320	score: 0.7601
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 321	score: 0.9060
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 322	score: 0.8252
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 323	score: 0.9284
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 324	score: 0.9605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 325	score: 0.8198
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 326	score: 0.8686
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 327	score: 0.9228
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 328	score: 0.9302
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 329	score: 0.6393
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 330	score: 0.9568
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 331	score: 0.9052
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 332	score: 0.9544
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 333	score: 0.8866
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 334	score: 0.9454
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 335	score: 0.9519
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 336	score: 0.9151
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 337	score: 0.7566
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 338	score: 0.9538
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 339	score: 0.9436
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 340	score: 0.8305
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 341	score: 0.8391
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 342	score: 0.7230
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 343	score: 0.8629
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 344	score: 0.8728
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 345	score: 0.9237
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 346	score: 0.9611
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 347	score: 0.9532
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 348	score: 0.9600
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 349	score: 0.8839
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 350	score: 0.9273
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 351	score: 0.8937
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 352	score: 0.9385
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 353	score: 0.9679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 354	score: 0.9149
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 355	score: 0.9080
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 356	score: 0.9239
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 357	score: 0.9032
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 358	score: 0.9336
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 359	score: 0.8815
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 360	score: 0.8379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 361	score: 0.8637
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 362	score: 0.8202
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 363	score: 0.8217
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 364	score: 0.9246
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 365	score: 0.8795
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 366	score: 0.8691
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 367	score: 0.9426
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 368	score: 0.8427
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 369	score: 0.9448
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 370	score: 0.8499
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 371	score: 0.8498
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 372	score: 0.9156
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 373	score: 0.9445
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 374	score: 0.9837
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 375	score: 0.9739
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 376	score: 0.9513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 377	score: 0.9820
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 378	score: 0.9086
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 379	score: 0.9487
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 380	score: 0.9543
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 381	score: 0.9396
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 382	score: 0.7479
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 383	score: 0.8148
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 384	score: 0.9542
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 385	score: 0.8711
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 386	score: 0.8809
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 387	score: 0.9624
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 388	score: 0.9581
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 389	score: 0.9681
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 390	score: 0.9744
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 391	score: 0.9497
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 392	score: 0.9154
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 393	score: 0.9528
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 394	score: 0.9849
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 395	score: 0.9555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 396	score: 0.9213
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 397	score: 0.9707
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 398	score: 0.8385
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 399	score: 0.9428
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 400	score: 0.9655
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 401	score: 0.8966
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 402	score: 0.9605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 403	score: 0.8927
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 404	score: 0.7471
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 405	score: 0.9269
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 406	score: 0.9227
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 407	score: 0.9122
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 408	score: 0.9629
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 409	score: 0.9484
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 410	score: 0.9237
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 411	score: 0.8593
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 412	score: 0.8652
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 413	score: 0.9580
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 414	score: 0.8596
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 415	score: 0.9295
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 416	score: 0.9460
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 417	score: 0.9265
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 418	score: 0.9648
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 419	score: 0.9518
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 420	score: 0.9414
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 421	score: 0.9666
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 422	score: 0.9315
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 423	score: 0.8358
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 424	score: 0.9111
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 425	score: 0.9402
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 426	score: 0.9025
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 427	score: 0.8907
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 428	score: 0.9740
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 429	score: 0.9810
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 430	score: 0.9314
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 431	score: 0.8184
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 432	score: 0.8842
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 433	score: 0.8020
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 434	score: 0.9130
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 435	score: 0.9278
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 436	score: 0.9044
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 437	score: 0.9345
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 438	score: 0.9586
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 439	score: 0.9629
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 440	score: 0.9666
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 441	score: 0.9438
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 442	score: 0.9772
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 443	score: 0.9577
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 444	score: 0.9109
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 445	score: 0.8321
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 446	score: 0.9552
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 447	score: 0.9655
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 448	score: 0.9804
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 449	score: 0.9333
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 450	score: 0.9513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 451	score: 0.8955
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 452	score: 0.9548
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 453	score: 0.9527
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 454	score: 0.9602
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 455	score: 0.9514
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 456	score: 0.8122
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 457	score: 0.9593
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 458	score: 0.9274
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 459	score: 0.9454
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 460	score: 0.9528
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 461	score: 0.8966
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 462	score: 0.9237
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 463	score: 0.9741
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 464	score: 0.9438
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 465	score: 0.9009
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 466	score: 0.9463
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 467	score: 0.7343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 468	score: 0.7819
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 469	score: 0.7771
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 470	score: 0.6409
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 471	score: 0.8697
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 472	score: 0.8370
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 473	score: 0.7609
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 474	score: 0.8179
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 475	score: 0.9628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 476	score: 0.9284
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 477	score: 0.9646
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 478	score: 0.9400
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 479	score: 0.9620
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 480	score: 0.9282
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 481	score: 0.9061
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 482	score: 0.9109
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 483	score: 0.8811
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 484	score: 0.9438
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 485	score: 0.9436
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 486	score: 0.8471
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 487	score: 0.9021
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 488	score: 0.8676
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 489	score: 0.9533
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 490	score: 0.8997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 491	score: 0.9768
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 492	score: 0.9809
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 493	score: 0.9479
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 494	score: 0.9077
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 495	score: 0.9275
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 496	score: 0.9458
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 497	score: 0.9031
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 498	score: 0.8484
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 499	score: 0.9689
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 500	score: 0.9612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 501	score: 0.9605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 502	score: 0.9553
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 503	score: 0.9149
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 504	score: 0.8797
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 505	score: 0.9187
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 506	score: 0.8966
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 507	score: 0.8958
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 508	score: 0.7791
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 509	score: 0.9317
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 510	score: 0.6737
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 511	score: 0.8833
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 512	score: 0.9399
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 513	score: 0.8942
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 514	score: 0.9614
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 515	score: 0.9679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 516	score: 0.9380
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 517	score: 0.9653
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 518	score: 0.9035
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 519	score: 0.9547
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 520	score: 0.9296
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 521	score: 0.9603
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 522	score: 0.8881
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 523	score: 0.9316
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 524	score: 0.9659
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 525	score: 0.9102
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 526	score: 0.8750
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 527	score: 0.5815
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 528	score: 0.9047
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 529	score: 0.9062
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 530	score: 0.9209
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 531	score: 0.8457
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 532	score: 0.9329
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 533	score: 0.9433
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 534	score: 0.9097
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 535	score: 0.8336
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 536	score: 0.8421
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 537	score: 0.8770
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 538	score: 0.9569
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 539	score: 0.9642
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 540	score: 0.9275
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 541	score: 0.9218
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 542	score: 0.8936
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 543	score: 0.9367
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 544	score: 0.9575
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 545	score: 0.9764
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 546	score: 0.8875
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 547	score: 0.9016
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 548	score: 0.8666
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 549	score: 0.9521
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 550	score: 0.8714
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 551	score: 0.9553
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 552	score: 0.9408
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 553	score: 0.9601
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 554	score: 0.9328
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 555	score: 0.9448
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 556	score: 0.8014
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 557	score: 0.9191
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 558	score: 0.8754
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 559	score: 0.9144
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 560	score: 0.9485
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 561	score: 0.9256
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 562	score: 0.8846
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 563	score: 0.8890
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 564	score: 0.8743
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 565	score: 0.9519
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 566	score: 0.9471
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 567	score: 0.9589
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 568	score: 0.8875
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 569	score: 0.6921
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 570	score: 0.9193
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 571	score: 0.9402
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 572	score: 0.8101
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 573	score: 0.9561
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 574	score: 0.9560
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 575	score: 0.8071
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 576	score: 0.9175
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 577	score: 0.8808
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 578	score: 0.9563
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 579	score: 0.9517
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 580	score: 0.9251
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 581	score: 0.9136
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 582	score: 0.9354
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 583	score: 0.9168
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 584	score: 0.7342
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 585	score: 0.9546
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 586	score: 0.9639
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 587	score: 0.9286
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 588	score: 0.9417
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 589	score: 0.9449
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 590	score: 0.8999
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 591	score: 0.9474
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 592	score: 0.7342
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 593	score: 0.9638
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 594	score: 0.9763
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 595	score: 0.9574
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 596	score: 0.9616
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 597	score: 0.9527
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 598	score: 0.9027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 599	score: 0.9313
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 600	score: 0.9358
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 601	score: 0.8472
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 602	score: 0.8780
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 603	score: 0.9166
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 604	score: 0.9367
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 605	score: 0.9518
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 606	score: 0.9520
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 607	score: 0.8707
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 608	score: 0.8372
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 609	score: 0.9392
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 610	score: 0.9362
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 611	score: 0.9109
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 612	score: 0.9502
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 613	score: 0.9069
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 614	score: 0.9510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 615	score: 0.8937
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 616	score: 0.9353
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 617	score: 0.9618
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 618	score: 0.9476
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 619	score: 0.9356
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 620	score: 0.9558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 621	score: 0.8150
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 622	score: 0.9680
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 623	score: 0.9508
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 624	score: 0.8044
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 625	score: 0.9555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 626	score: 0.9672
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 627	score: 0.9729
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 628	score: 0.9525
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 629	score: 0.9480
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 630	score: 0.8299
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 631	score: 0.9351
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 632	score: 0.9229
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 633	score: 0.9727
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 634	score: 0.9706
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 635	score: 0.9681
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 636	score: 0.9527
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 637	score: 0.8975
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 638	score: 0.9669
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 639	score: 0.9424
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 640	score: 0.9619
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 641	score: 0.9800
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 642	score: 0.8929
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 643	score: 0.7850
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 644	score: 0.9102
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 645	score: 0.8325
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 646	score: 0.9188
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 647	score: 0.8876
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 648	score: 0.8841
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 649	score: 0.9453
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 650	score: 0.9194
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 651	score: 0.8152
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 652	score: 0.8635
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 653	score: 0.8933
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 654	score: 0.9263
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 655	score: 0.9519
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 656	score: 0.7347
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 657	score: 0.9462
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 658	score: 0.7322
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 659	score: 0.9431
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 660	score: 0.8308
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 661	score: 0.9708
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 662	score: 0.9621
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 663	score: 0.9546
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 664	score: 0.9578
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 665	score: 0.9313
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 666	score: 0.9097
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 667	score: 0.8290
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 668	score: 0.9705
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 669	score: 0.9747
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 670	score: 0.9481
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 671	score: 0.9568
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 672	score: 0.9477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 673	score: 0.8765
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 674	score: 0.9532
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 675	score: 0.9695
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 676	score: 0.9523
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 677	score: 0.9764
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 678	score: 0.9647
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 679	score: 0.9829
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 680	score: 0.9238
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 681	score: 0.9788
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 682	score: 0.8634
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 683	score: 0.9193
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 684	score: 0.9480
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 685	score: 0.9498
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 686	score: 0.8943
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 687	score: 0.8515
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 688	score: 0.8750
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 689	score: 0.9462
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 690	score: 0.9540
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 691	score: 0.9347
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 692	score: 0.9612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 693	score: 0.9045
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 694	score: 0.9199
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 695	score: 0.9696
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 696	score: 0.8936
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 697	score: 0.9871
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 698	score: 0.9129
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 699	score: 0.8247
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 700	score: 0.9240
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 701	score: 0.9567
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 702	score: 0.9680
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 703	score: 0.9154
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 704	score: 0.8873
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 705	score: 0.9078
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 706	score: 0.8498
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 707	score: 0.9639
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 708	score: 0.9388
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 709	score: 0.9522
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 710	score: 0.9855
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 711	score: 0.9387
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 712	score: 0.9550
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 713	score: 0.9539
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 714	score: 0.8792
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 715	score: 0.9043
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 716	score: 0.9002
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 717	score: 0.9606
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 718	score: 0.9526
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 719	score: 0.9190
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 720	score: 0.8844
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 721	score: 0.9615
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 722	score: 0.9116
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 723	score: 0.9438
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 724	score: 0.9665
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 725	score: 0.9404
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 726	score: 0.9356
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 727	score: 0.9128
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 728	score: 0.7798
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 729	score: 0.9261
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 730	score: 0.9008
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 731	score: 0.9541
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 732	score: 0.9502
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 733	score: 0.9483
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 734	score: 0.8927
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 735	score: 0.9351
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 736	score: 0.9287
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 737	score: 0.9118
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 738	score: 0.9477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 739	score: 0.9340
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 740	score: 0.9499
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 741	score: 0.8980
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 742	score: 0.9098
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 743	score: 0.9405
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 744	score: 0.9586
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 745	score: 0.9344
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 746	score: 0.9474
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 747	score: 0.9466
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 748	score: 0.9792
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 749	score: 0.9428
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 750	score: 0.9037
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 751	score: 0.8915
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 752	score: 0.9324
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 753	score: 0.8969
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 754	score: 0.9552
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 755	score: 0.9712
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 756	score: 0.8952
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 757	score: 0.9360
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 758	score: 0.9613
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 759	score: 0.9251
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 760	score: 0.9776
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 761	score: 0.9304
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 762	score: 0.9644
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 763	score: 0.9307
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 764	score: 0.9730
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 765	score: 0.9256
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 766	score: 0.9404
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 767	score: 0.9203
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 768	score: 0.9598
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 769	score: 0.9796
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 770	score: 0.9550
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 771	score: 0.9613
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 772	score: 0.9396
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 773	score: 0.9378
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 774	score: 0.9421
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 775	score: 0.9230
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 776	score: 0.8932
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 777	score: 0.9528
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 778	score: 0.9495
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 779	score: 0.6219
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 780	score: 0.9017
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 781	score: 0.8507
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 782	score: 0.9165
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 783	score: 0.8172
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 784	score: 0.9460
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 785	score: 0.6559
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 786	score: 0.9660
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 787	score: 0.9537
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 788	score: 0.9451
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 789	score: 0.9317
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 790	score: 0.9785
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 791	score: 0.9381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 792	score: 0.9422
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 793	score: 0.8138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 794	score: 0.8167
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 795	score: 0.9269
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 796	score: 0.9840
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 797	score: 0.8257
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 798	score: 0.9142
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 799	score: 0.7266
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 800	score: 0.9022
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 801	score: 0.9306
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 802	score: 0.9398
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 803	score: 0.9252
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 804	score: 0.8602
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 805	score: 0.9612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 806	score: 0.9552
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 807	score: 0.9601
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 808	score: 0.8887
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 809	score: 0.9538
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 810	score: 0.9367
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 811	score: 0.7996
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 812	score: 0.9508
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 813	score: 0.9538
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 814	score: 0.9414
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 815	score: 0.8095
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 816	score: 0.8978
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 817	score: 0.9289
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 818	score: 0.9191
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 819	score: 0.8713
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 820	score: 0.9621
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 821	score: 0.9699
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 822	score: 0.9376
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 823	score: 0.9618
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 824	score: 0.8982
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 825	score: 0.9577
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 826	score: 0.9493
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 827	score: 0.9584
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 828	score: 0.9279
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 829	score: 0.9413
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 830	score: 0.9427
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 831	score: 0.9336
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 832	score: 0.9299
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 833	score: 0.7396
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 834	score: 0.9427
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 835	score: 0.8892
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 836	score: 0.9207
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 837	score: 0.9331
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 838	score: 0.8824
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 839	score: 0.9046
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 840	score: 0.8190
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 841	score: 0.9208
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 842	score: 0.8568
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 843	score: 0.9132
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 844	score: 0.8368
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 845	score: 0.9165
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 846	score: 0.7932
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 847	score: 0.8425
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 848	score: 0.8683
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 849	score: 0.9206
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 850	score: 0.8088
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 851	score: 0.9561
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 852	score: 0.9488
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 853	score: 0.7213
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 854	score: 0.8300
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 855	score: 0.9879
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 856	score: 0.8366
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 857	score: 0.9540
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 858	score: 0.9691
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 859	score: 0.9525
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 860	score: 0.9566
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 861	score: 0.9567
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 862	score: 0.9432
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 863	score: 0.9453
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 864	score: 0.9344
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 865	score: 0.8956
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 866	score: 0.9254
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 867	score: 0.9538
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 868	score: 0.9195
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 869	score: 0.9095
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 870	score: 0.9669
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 871	score: 0.9479
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 872	score: 0.9577
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 873	score: 0.9415
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 874	score: 0.9378
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 875	score: 0.9187
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 876	score: 0.8994
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 877	score: 0.9351
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 878	score: 0.9545
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 879	score: 0.7577
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 880	score: 0.9188
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 881	score: 0.9534
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 882	score: 0.9692
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 883	score: 0.9583
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 884	score: 0.9356
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 885	score: 0.9474
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 886	score: 0.9329
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 887	score: 0.8631
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 888	score: 0.7002
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 889	score: 0.9215
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 890	score: 0.9517
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 891	score: 0.9518
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 892	score: 0.8295
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 893	score: 0.7605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 894	score: 0.9233
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 895	score: 0.9574
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 896	score: 0.9049
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 897	score: 0.8897
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 898	score: 0.9766
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 899	score: 0.9129
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 900	score: 0.8725
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 901	score: 0.9140
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 902	score: 0.8265
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 903	score: 0.9011
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 904	score: 0.9365
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 905	score: 0.9517
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 906	score: 0.9264
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 907	score: 0.8170
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 908	score: 0.9143
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 909	score: 0.9479
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 910	score: 0.9090
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 911	score: 0.8976
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 912	score: 0.9824
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 913	score: 0.9409
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 914	score: 0.9416
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 915	score: 0.9354
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 916	score: 0.9359
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 917	score: 0.9379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 918	score: 0.9746
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 919	score: 0.9567
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 920	score: 0.8886
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 921	score: 0.9314
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 922	score: 0.9304
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 923	score: 0.8683
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 924	score: 0.9432
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 925	score: 0.8517
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 926	score: 0.9253
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 927	score: 0.9339
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 928	score: 0.9298
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 929	score: 0.8740
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 930	score: 0.9590
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 931	score: 0.9017
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 932	score: 0.7823
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 933	score: 0.8912
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 934	score: 0.7931
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 935	score: 0.6314
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 936	score: 0.9379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 937	score: 0.9668
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 938	score: 0.9482
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 939	score: 0.9622
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 940	score: 0.9726
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 941	score: 0.9790
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 942	score: 0.9679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 943	score: 0.9304
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 944	score: 0.8629
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 945	score: 0.9108
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 946	score: 0.8943
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 947	score: 0.9510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 948	score: 0.8460
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 949	score: 0.9103
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 950	score: 0.8082
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 951	score: 0.9481
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 952	score: 0.8295
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 953	score: 0.9350
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 954	score: 0.8654
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 955	score: 0.9619
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 956	score: 0.9343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 957	score: 0.9725
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 958	score: 0.9191
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 959	score: 0.9841
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 960	score: 0.8948
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 961	score: 0.8113
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 962	score: 0.9687
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 963	score: 0.9449
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 964	score: 0.9799
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 965	score: 0.9322
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 966	score: 0.9388
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 967	score: 0.8570
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 968	score: 0.9235
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 969	score: 0.6067
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 970	score: 0.9440
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 971	score: 0.9095
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 972	score: 0.7436
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 973	score: 0.9649
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 974	score: 0.9351
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 975	score: 0.9736
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 976	score: 0.9155
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 977	score: 0.7741
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 978	score: 0.9803
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 979	score: 0.9226
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 980	score: 0.9211
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 981	score: 0.9156
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 982	score: 0.9579
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 983	score: 0.8617
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 984	score: 0.9190
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 985	score: 0.9439
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 986	score: 0.9587
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 987	score: 0.8972
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 988	score: 0.9281
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 989	score: 0.6142
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 990	score: 0.9629
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 991	score: 0.8570
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 992	score: 0.9611
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 993	score: 0.9316
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 994	score: 0.9382
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 995	score: 0.9229
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 996	score: 0.9591
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 997	score: 0.9712
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 998	score: 0.9698
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 999	score: 0.7302
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1000	score: 0.9214
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1001	score: 0.8795
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1002	score: 0.8866
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1003	score: 0.8279
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1004	score: 0.8828
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1005	score: 0.9597
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1006	score: 0.8870
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1007	score: 0.9284
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1008	score: 0.9612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1009	score: 0.9115
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1010	score: 0.9277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	Segment 1011	score: 0.9141
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-cs	score: 0.9128