/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 0	score: 0.6006
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1	score: 0.8616
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 2	score: 0.8309
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 3	score: 0.7783
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 4	score: 0.7775
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 5	score: 0.6430
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 6	score: 0.7295
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 7	score: 0.9204
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 8	score: 0.8272
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 9	score: 0.6028
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 10	score: 0.6639
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 11	score: 0.2160
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 12	score: 0.8661
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 13	score: 0.9097
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 14	score: 0.6488
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 15	score: 0.7789
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 16	score: 0.8974
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 17	score: 0.9092
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 18	score: 0.8212
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 19	score: 0.8466
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 20	score: 0.9321
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 21	score: 0.8706
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 22	score: 0.6204
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 23	score: 0.7693
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 24	score: 0.9157
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 25	score: 0.9522
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 26	score: 0.8566
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 27	score: 0.7138
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 28	score: 0.7692
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 29	score: 0.9090
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 30	score: 0.6257
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 31	score: 0.7762
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 32	score: 0.8628
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 33	score: 0.7301
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 34	score: 0.7759
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 35	score: 0.8995
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 36	score: 0.7803
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 37	score: 0.8213
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 38	score: 0.6777
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 39	score: 0.9288
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 40	score: 0.6430
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 41	score: 0.8729
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 42	score: 0.7774
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 43	score: 0.8885
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 44	score: 0.7749
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 45	score: 0.8112
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 46	score: 0.2549
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 47	score: 0.7604
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 48	score: 0.8070
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 49	score: 0.8156
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 50	score: 0.7291
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 51	score: 0.8550
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 52	score: 0.9409
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 53	score: 0.8250
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 54	score: 0.7955
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 55	score: 0.8902
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 56	score: 0.8894
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 57	score: 0.2052
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 58	score: 0.8646
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 59	score: 0.9332
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 60	score: 0.8027
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 61	score: 0.7752
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 62	score: 0.8247
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 63	score: 0.8746
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 64	score: 0.7389
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 65	score: 0.7153
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 66	score: 0.7197
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 67	score: 0.5356
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 68	score: 0.9302
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 69	score: 0.9020
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 70	score: 0.3359
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 71	score: 0.8530
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 72	score: 0.7509
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 73	score: 0.8630
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 74	score: 0.7800
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 75	score: 0.8535
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 76	score: 0.7981
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 77	score: 0.8545
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 78	score: 0.9137
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 79	score: 0.8520
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 80	score: 0.8656
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 81	score: 0.9323
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 82	score: 0.6665
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 83	score: 0.1509
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 84	score: 0.5001
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 85	score: 0.8176
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 86	score: 0.6968
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 87	score: 0.7827
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 88	score: 0.8488
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 89	score: 0.7958
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 90	score: 0.6564
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 91	score: 0.8921
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 92	score: 0.8677
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 93	score: 0.7357
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 94	score: 0.8890
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 95	score: 0.8218
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 96	score: 0.6533
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 97	score: 0.7349
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 98	score: 0.7554
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 99	score: 0.8322
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 100	score: 0.6307
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 101	score: 0.6895
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 102	score: 0.6509
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 103	score: 0.7891
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 104	score: 0.8976
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 105	score: 0.9101
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 106	score: 0.9058
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 107	score: 0.8418
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 108	score: 0.5943
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 109	score: 0.7157
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 110	score: 0.8165
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 111	score: 0.9125
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 112	score: 0.6593
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 113	score: 0.7280
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 114	score: 0.7616
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 115	score: 0.7066
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 116	score: 0.9065
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 117	score: 0.9230
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 118	score: 0.8923
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 119	score: 0.6275
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 120	score: 0.7338
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 121	score: 0.8524
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 122	score: 0.9148
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 123	score: 0.9243
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 124	score: 0.6797
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 125	score: 0.8673
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 126	score: 0.8113
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 127	score: 0.7834
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 128	score: 0.8929
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 129	score: 0.6754
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 130	score: 0.8820
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 131	score: 0.6586
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 132	score: 0.7543
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 133	score: 0.8829
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 134	score: 0.9004
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 135	score: 0.7307
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 136	score: 0.6146
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 137	score: 0.6341
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 138	score: 0.8629
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 139	score: 0.7079
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 140	score: 0.7635
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 141	score: 0.8808
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 142	score: 0.9448
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 143	score: 0.8818
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 144	score: 0.8551
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 145	score: 0.9263
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 146	score: 0.7026
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 147	score: 0.8331
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 148	score: 0.6736
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 149	score: 0.6972
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 150	score: 0.8475
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 151	score: 0.8660
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 152	score: 0.7754
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 153	score: 0.7362
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 154	score: 0.7562
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 155	score: 0.8149
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 156	score: 0.7928
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 157	score: 0.8253
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 158	score: 0.8986
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 159	score: 0.8563
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 160	score: 0.8413
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 161	score: 0.8820
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 162	score: 0.5319
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 163	score: 0.7846
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 164	score: 0.7912
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 165	score: 0.6819
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 166	score: 0.7380
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 167	score: 0.7904
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 168	score: 0.7447
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 169	score: 0.7632
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 170	score: 0.8272
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 171	score: 0.7565
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 172	score: 0.7061
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 173	score: 0.8050
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 174	score: 0.8328
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 175	score: 0.9305
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 176	score: 0.7473
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 177	score: 0.7584
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 178	score: 0.8293
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 179	score: 0.6448
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 180	score: 0.8274
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 181	score: 0.8474
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 182	score: 0.9259
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 183	score: 0.8592
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 184	score: 0.8254
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 185	score: 0.7783
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 186	score: 0.9000
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 187	score: 0.8419
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 188	score: 0.6179
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 189	score: 0.6914
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 190	score: 0.5270
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 191	score: 0.8044
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 192	score: 0.7239
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 193	score: 0.7305
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 194	score: 0.8476
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 195	score: 0.8848
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 196	score: 0.8962
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 197	score: 0.7623
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 198	score: 0.7487
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 199	score: 0.8079
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 200	score: 0.8438
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 201	score: 0.5503
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 202	score: 0.5446
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 203	score: 0.7158
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 204	score: 0.3010
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 205	score: 0.7871
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 206	score: 0.8701
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 207	score: 0.7776
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 208	score: 0.8294
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 209	score: 0.9105
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 210	score: 0.3280
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 211	score: 0.6382
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 212	score: 0.9175
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 213	score: 0.9002
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 214	score: 0.8790
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 215	score: 0.8791
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 216	score: 0.6447
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 217	score: 0.7033
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 218	score: 0.7687
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 219	score: 0.7515
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 220	score: 0.9412
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 221	score: 0.7918
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 222	score: 0.8289
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 223	score: 0.5103
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 224	score: 0.7507
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 225	score: 0.9493
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 226	score: 0.8696
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 227	score: 0.5930
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 228	score: 0.6565
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 229	score: 0.8441
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 230	score: 0.9622
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 231	score: 0.7935
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 232	score: 0.7898
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 233	score: 0.8425
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 234	score: 0.6632
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 235	score: 0.7726
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 236	score: 0.8438
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 237	score: 0.5690
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 238	score: 0.8715
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 239	score: 0.5653
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 240	score: 0.3833
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 241	score: 0.7595
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 242	score: 0.6624
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 243	score: 0.7762
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 244	score: 0.6294
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 245	score: 0.9012
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 246	score: 0.6697
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 247	score: 0.5875
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 248	score: 0.5972
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 249	score: 0.7058
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 250	score: 0.8628
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 251	score: 0.9184
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 252	score: 0.8151
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 253	score: 0.8636
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 254	score: 0.9158
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 255	score: 0.2095
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 256	score: 0.3138
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 257	score: 0.8605
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 258	score: 0.7767
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 259	score: 0.5396
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 260	score: 0.8729
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 261	score: 0.5119
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 262	score: 0.2363
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 263	score: 0.7737
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 264	score: 0.8706
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 265	score: 0.8493
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 266	score: 0.8097
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 267	score: 0.7985
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 268	score: 0.9368
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 269	score: 0.8926
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 270	score: 0.8549
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 271	score: 0.5570
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 272	score: 0.8749
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 273	score: 0.7867
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 274	score: 0.8101
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 275	score: 0.6898
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 276	score: 0.5304
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 277	score: 0.8670
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 278	score: 0.7637
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 279	score: 0.8900
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 280	score: 0.9158
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 281	score: 0.8998
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 282	score: 0.9424
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 283	score: 0.5966
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 284	score: 0.8121
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 285	score: 0.8834
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 286	score: 0.5262
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 287	score: 0.7881
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 288	score: 0.8223
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 289	score: 0.8926
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 290	score: 0.8663
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 291	score: 0.7776
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 292	score: 0.8981
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 293	score: 0.8304
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 294	score: 0.6247
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 295	score: 0.3188
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 296	score: 0.7827
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 297	score: 0.9162
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 298	score: 0.5011
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 299	score: 0.8966
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 300	score: 0.9477
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 301	score: 0.8374
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 302	score: 0.3050
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 303	score: 0.8016
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 304	score: 0.7617
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 305	score: 0.7917
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 306	score: 0.9025
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 307	score: 0.8818
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 308	score: 0.9171
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 309	score: 0.6130
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 310	score: 0.9001
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 311	score: 0.5475
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 312	score: 0.5980
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 313	score: 0.6612
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 314	score: 0.8919
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 315	score: 0.9225
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 316	score: 0.6997
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 317	score: 0.6977
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 318	score: 0.8370
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 319	score: 0.7185
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 320	score: 0.8199
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 321	score: 0.7161
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 322	score: 0.6463
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 323	score: 0.8459
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 324	score: 0.8808
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 325	score: 0.7735
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 326	score: 0.5264
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 327	score: 0.8311
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 328	score: 0.9119
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 329	score: 0.8817
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 330	score: 0.8447
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 331	score: 0.9315
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 332	score: 0.7555
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 333	score: 0.6196
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 334	score: 0.9739
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 335	score: 0.7779
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 336	score: 0.6671
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 337	score: 0.5115
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 338	score: 0.8502
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 339	score: 0.9009
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 340	score: 0.8006
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 341	score: 0.6470
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 342	score: 0.4625
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 343	score: 0.7092
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 344	score: 0.6204
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 345	score: 0.5935
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 346	score: 0.8887
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 347	score: 0.8429
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 348	score: 0.7783
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 349	score: 0.5262
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 350	score: 0.7130
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 351	score: 0.6227
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 352	score: 0.8110
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 353	score: 0.8593
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 354	score: 0.4638
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 355	score: 0.7213
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 356	score: 0.6867
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 357	score: 0.7006
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 358	score: 0.6637
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 359	score: 0.6298
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 360	score: 0.5277
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 361	score: 0.7705
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 362	score: 0.7488
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 363	score: 0.4777
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 364	score: 0.9319
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 365	score: 0.7600
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 366	score: 0.7109
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 367	score: 0.7583
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 368	score: 0.6571
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 369	score: 0.5868
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 370	score: 0.6290
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 371	score: 0.6644
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 372	score: 0.7434
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 373	score: 0.7777
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 374	score: 0.6495
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 375	score: 0.6919
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 376	score: 0.9370
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 377	score: 0.7506
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 378	score: 0.5795
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 379	score: 0.9211
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 380	score: 0.9016
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 381	score: 0.7295
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 382	score: 0.6160
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 383	score: 0.7587
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 384	score: 0.7356
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 385	score: 0.3298
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 386	score: 0.6006
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 387	score: 0.8919
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 388	score: 0.4718
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 389	score: 0.8632
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 390	score: 0.7829
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 391	score: 0.7662
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 392	score: 0.8238
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 393	score: 0.9380
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 394	score: 0.8925
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 395	score: 0.6723
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 396	score: 0.5181
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 397	score: 0.9219
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 398	score: 0.7783
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 399	score: 0.7003
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 400	score: 0.9458
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 401	score: 0.6590
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 402	score: 0.8791
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 403	score: 0.8279
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 404	score: 0.6425
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 405	score: 0.9159
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 406	score: 0.8615
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 407	score: 0.8476
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 408	score: 0.9412
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 409	score: 0.8150
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 410	score: 0.9338
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 411	score: 0.8167
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 412	score: 0.7852
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 413	score: 0.8566
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 414	score: 0.8408
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 415	score: 0.8536
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 416	score: 0.7363
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 417	score: 0.7458
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 418	score: 0.9100
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 419	score: 0.5368
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 420	score: 0.8602
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 421	score: 0.9252
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 422	score: 0.2669
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 423	score: 0.8672
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 424	score: 0.7751
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 425	score: 0.9108
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 426	score: 0.8729
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 427	score: 0.8643
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 428	score: 0.7487
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 429	score: 0.7613
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 430	score: 0.8532
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 431	score: 0.6583
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 432	score: 0.6278
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 433	score: 0.6797
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 434	score: 0.7511
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 435	score: 0.7010
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 436	score: 0.6760
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 437	score: 0.8497
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 438	score: 0.8981
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 439	score: 0.8504
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 440	score: 0.7136
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 441	score: 0.8227
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 442	score: 0.8494
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 443	score: 0.6911
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 444	score: 0.8064
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 445	score: 0.8685
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 446	score: 0.7359
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 447	score: 0.8818
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 448	score: 0.9195
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 449	score: 0.8463
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 450	score: 0.8254
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 451	score: 0.9206
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 452	score: 0.9498
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 453	score: 0.8829
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 454	score: 0.7816
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 455	score: 0.7314
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 456	score: 0.4770
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 457	score: 0.8905
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 458	score: 0.8424
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 459	score: 0.6159
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 460	score: 0.8587
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 461	score: 0.5891
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 462	score: 0.7885
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 463	score: 0.9551
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 464	score: 0.9137
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 465	score: 0.8562
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 466	score: 0.8834
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 467	score: 0.6137
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 468	score: 0.6482
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 469	score: 0.6243
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 470	score: 0.6581
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 471	score: 0.6053
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 472	score: 0.7863
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 473	score: 0.6704
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 474	score: 0.7957
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 475	score: 0.8484
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 476	score: 0.7014
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 477	score: 0.5857
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 478	score: 0.8054
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 479	score: 0.9114
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 480	score: 0.7923
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 481	score: 0.7266
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 482	score: 0.6987
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 483	score: 0.7592
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 484	score: 0.8517
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 485	score: 0.8094
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 486	score: 0.7393
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 487	score: 0.7215
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 488	score: 0.8152
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 489	score: 0.8773
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 490	score: 0.7466
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 491	score: 0.9079
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 492	score: 0.8429
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 493	score: 0.7427
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 494	score: 0.6619
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 495	score: 0.5581
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 496	score: 0.6915
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 497	score: 0.6474
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 498	score: 0.5930
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 499	score: 0.6240
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 500	score: 0.8169
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 501	score: 0.8276
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 502	score: 0.8546
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 503	score: 0.7761
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 504	score: 0.7594
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 505	score: 0.7558
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 506	score: 0.6711
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 507	score: 0.7930
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 508	score: 0.7536
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 509	score: 0.8313
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 510	score: 0.6577
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 511	score: 0.7839
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 512	score: 0.7024
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 513	score: 0.8007
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 514	score: 0.9063
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 515	score: 0.8599
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 516	score: 0.5394
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 517	score: 0.8829
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 518	score: 0.7959
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 519	score: 0.8467
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 520	score: 0.8090
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 521	score: 0.6312
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 522	score: 0.7042
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 523	score: 0.4318
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 524	score: 0.9080
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 525	score: 0.8786
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 526	score: 0.8030
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 527	score: 0.4963
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 528	score: 0.5112
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 529	score: 0.5944
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 530	score: 0.6104
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 531	score: 0.8714
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 532	score: 0.5294
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 533	score: 0.8261
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 534	score: 0.7411
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 535	score: 0.4657
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 536	score: 0.5954
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 537	score: 0.8876
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 538	score: 0.6827
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 539	score: 0.6119
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 540	score: 0.8073
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 541	score: 0.7115
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 542	score: 0.6105
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 543	score: 0.8661
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 544	score: 0.8778
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 545	score: 0.9264
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 546	score: 0.7858
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 547	score: 0.8431
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 548	score: 0.7182
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 549	score: 0.9219
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 550	score: 0.8058
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 551	score: 0.9292
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 552	score: 0.9397
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 553	score: 0.8558
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 554	score: 0.7655
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 555	score: 0.7304
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 556	score: 0.2796
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 557	score: 0.7774
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 558	score: 0.5507
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 559	score: 0.6076
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 560	score: 0.6136
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 561	score: 0.5104
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 562	score: 0.7553
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 563	score: 0.5319
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 564	score: 0.7223
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 565	score: 0.8030
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 566	score: 0.8745
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 567	score: 0.8312
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 568	score: 0.6542
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 569	score: 0.5760
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 570	score: 0.8390
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 571	score: 0.9102
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 572	score: 0.6461
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 573	score: 0.6394
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 574	score: 0.8173
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 575	score: 0.7857
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 576	score: 0.5843
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 577	score: 0.8433
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 578	score: 0.7943
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 579	score: 0.6557
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 580	score: 0.5808
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 581	score: 0.6486
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 582	score: 0.8259
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 583	score: 0.7467
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 584	score: 0.6908
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 585	score: 0.8026
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 586	score: 0.7399
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 587	score: 0.8809
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 588	score: 0.5216
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 589	score: 0.9272
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 590	score: 0.9153
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 591	score: 0.9252
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 592	score: 0.6730
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 593	score: 0.9015
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 594	score: 0.8226
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 595	score: 0.6438
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 596	score: 0.7998
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 597	score: 0.8454
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 598	score: 0.6407
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 599	score: 0.7217
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 600	score: 0.7603
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 601	score: 0.8336
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 602	score: 0.8717
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 603	score: 0.8595
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 604	score: 0.8275
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 605	score: 0.8919
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 606	score: 0.7668
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 607	score: 0.7122
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 608	score: 0.8167
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 609	score: 0.6093
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 610	score: 0.7137
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 611	score: 0.8198
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 612	score: 0.8992
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 613	score: 0.8176
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 614	score: 0.6925
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 615	score: 0.6667
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 616	score: 0.8709
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 617	score: 0.8680
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 618	score: 0.7976
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 619	score: 0.8823
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 620	score: 0.7114
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 621	score: 0.4980
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 622	score: 0.7719
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 623	score: 0.8103
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 624	score: 0.9184
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 625	score: 0.8611
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 626	score: 0.8473
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 627	score: 0.9088
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 628	score: 0.9421
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 629	score: 0.8637
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 630	score: 0.8955
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 631	score: 0.8654
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 632	score: 0.9240
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 633	score: 0.9463
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 634	score: 0.9459
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 635	score: 0.8165
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 636	score: 0.7967
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 637	score: 0.7942
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 638	score: 0.5896
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 639	score: 0.7078
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 640	score: 0.8185
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 641	score: 0.8327
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 642	score: 0.5993
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 643	score: 0.7273
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 644	score: 0.5417
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 645	score: 0.6642
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 646	score: 0.5664
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 647	score: 0.8389
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 648	score: 0.7429
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 649	score: 0.5695
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 650	score: 0.8840
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 651	score: 0.6901
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 652	score: 0.7489
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 653	score: 0.8279
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 654	score: 0.7916
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 655	score: 0.8866
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 656	score: 0.9346
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 657	score: 0.8713
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 658	score: 0.7268
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 659	score: 0.8719
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 660	score: 0.7846
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 661	score: 0.9255
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 662	score: 0.9362
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 663	score: 0.8111
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 664	score: 0.9232
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 665	score: 0.7811
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 666	score: 0.8342
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 667	score: 0.7480
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 668	score: 0.7483
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 669	score: 0.6339
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 670	score: 0.7467
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 671	score: 0.8200
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 672	score: 0.8124
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 673	score: 0.9127
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 674	score: 0.9125
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 675	score: 0.7804
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 676	score: 0.8458
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 677	score: 0.9090
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 678	score: 0.8545
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 679	score: 0.9573
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 680	score: 0.7603
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 681	score: 0.7776
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 682	score: 0.8189
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 683	score: 0.6718
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 684	score: 0.7602
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 685	score: 0.6411
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 686	score: 0.8631
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 687	score: 0.8893
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 688	score: 0.8868
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 689	score: 0.8693
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 690	score: 0.8810
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 691	score: 0.7538
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 692	score: 0.8480
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 693	score: 0.6453
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 694	score: 0.8139
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 695	score: 0.5841
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 696	score: 0.6776
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 697	score: 0.9042
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 698	score: 0.6588
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 699	score: 0.3313
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 700	score: 0.8930
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 701	score: 0.8658
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 702	score: 0.6824
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 703	score: 0.6066
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 704	score: 0.8791
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 705	score: 0.6857
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 706	score: 0.7262
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 707	score: 0.8981
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 708	score: 0.9097
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 709	score: 0.8785
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 710	score: 0.9209
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 711	score: 0.8645
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 712	score: 0.8983
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 713	score: 0.7161
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 714	score: 0.8116
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 715	score: 0.7814
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 716	score: 0.8703
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 717	score: 0.6621
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 718	score: 0.7135
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 719	score: 0.5983
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 720	score: 0.6770
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 721	score: 0.9597
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 722	score: 0.3489
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 723	score: 0.8865
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 724	score: 0.8112
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 725	score: 0.8254
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 726	score: 0.8768
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 727	score: 0.9066
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 728	score: 0.7421
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 729	score: 0.8854
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 730	score: 0.7275
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 731	score: 0.7888
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 732	score: 0.8224
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 733	score: 0.8081
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 734	score: 0.5879
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 735	score: 0.8640
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 736	score: 0.6420
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 737	score: 0.7723
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 738	score: 0.8476
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 739	score: 0.7038
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 740	score: 0.6710
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 741	score: 0.6945
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 742	score: 0.8858
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 743	score: 0.9080
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 744	score: 0.7423
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 745	score: 0.8513
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 746	score: 0.8764
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 747	score: 0.9119
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 748	score: 0.8051
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 749	score: 0.9072
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 750	score: 0.8973
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 751	score: 0.8355
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 752	score: 0.8660
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 753	score: 0.8937
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 754	score: 0.1952
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 755	score: 0.6725
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 756	score: 0.7862
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 757	score: 0.7267
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 758	score: 0.8543
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 759	score: 0.7693
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 760	score: 0.8643
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 761	score: 0.8154
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 762	score: 0.9363
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 763	score: 0.6441
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 764	score: 0.7601
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 765	score: 0.7186
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 766	score: 0.8668
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 767	score: 0.5380
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 768	score: 0.9599
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 769	score: 0.2294
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 770	score: 0.8751
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 771	score: 0.8947
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 772	score: 0.7035
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 773	score: 0.8568
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 774	score: 0.8871
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 775	score: 0.6826
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 776	score: 0.6554
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 777	score: 0.8303
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 778	score: 0.7703
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 779	score: 0.6955
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 780	score: 0.7714
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 781	score: 0.6984
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 782	score: 0.2119
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 783	score: 0.8853
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 784	score: 0.7824
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 785	score: 0.5105
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 786	score: 0.7639
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 787	score: 0.7754
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 788	score: 0.7449
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 789	score: 0.8664
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 790	score: 0.9308
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 791	score: 0.8031
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 792	score: 0.8953
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 793	score: 0.8780
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 794	score: 0.7989
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 795	score: 0.9165
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 796	score: 0.9649
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 797	score: 0.6744
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 798	score: 0.8999
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 799	score: 0.7621
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 800	score: 0.8614
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 801	score: 0.7847
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 802	score: 0.9128
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 803	score: 0.7558
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 804	score: 0.7461
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 805	score: 0.7785
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 806	score: 0.8506
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 807	score: 0.8441
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 808	score: 0.7893
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 809	score: 0.6566
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 810	score: 0.7243
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 811	score: 0.7488
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 812	score: 0.8994
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 813	score: 0.8893
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 814	score: 0.8220
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 815	score: 0.7538
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 816	score: 0.8635
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 817	score: 0.5015
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 818	score: 0.6776
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 819	score: 0.8078
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 820	score: 0.9310
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 821	score: 0.7517
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 822	score: 0.8020
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 823	score: 0.4983
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 824	score: 0.5966
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 825	score: 0.5073
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 826	score: 0.6526
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 827	score: 0.8229
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 828	score: 0.7686
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 829	score: 0.5362
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 830	score: 0.8304
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 831	score: 0.7637
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 832	score: 0.7971
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 833	score: 0.2783
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 834	score: 0.7036
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 835	score: 0.7379
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 836	score: 0.7394
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 837	score: 0.7166
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 838	score: 0.7541
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 839	score: 0.8220
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 840	score: 0.8259
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 841	score: 0.5485
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 842	score: 0.6602
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 843	score: 0.8016
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 844	score: 0.6356
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 845	score: 0.7358
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 846	score: 0.6242
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 847	score: 0.6309
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 848	score: 0.6214
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 849	score: 0.8037
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 850	score: 0.8721
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 851	score: 0.8596
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 852	score: 0.6698
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 853	score: 0.8507
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 854	score: 0.7326
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 855	score: 0.8584
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 856	score: 0.5872
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 857	score: 0.2314
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 858	score: 0.6252
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 859	score: 0.8992
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 860	score: 0.6993
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 861	score: 0.6760
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 862	score: 0.8702
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 863	score: 0.6945
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 864	score: 0.6703
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 865	score: 0.8343
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 866	score: 0.8909
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 867	score: 0.8509
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 868	score: 0.7958
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 869	score: 0.8407
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 870	score: 0.8851
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 871	score: 0.8890
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 872	score: 0.8429
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 873	score: 0.9165
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 874	score: 0.9045
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 875	score: 0.7752
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 876	score: 0.5445
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 877	score: 0.8757
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 878	score: 0.9363
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 879	score: 0.8205
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 880	score: 0.6406
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 881	score: 0.8611
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 882	score: 0.9181
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 883	score: 0.8777
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 884	score: 0.8052
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 885	score: 0.5678
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 886	score: 0.7671
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 887	score: 0.5616
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 888	score: 0.6971
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 889	score: 0.7536
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 890	score: 0.5718
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 891	score: 0.7057
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 892	score: 0.7727
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 893	score: 0.7634
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 894	score: 0.6075
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 895	score: 0.7989
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 896	score: 0.7058
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 897	score: 0.7908
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 898	score: 0.8836
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 899	score: 0.7782
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 900	score: 0.7727
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 901	score: 0.6763
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 902	score: 0.8988
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 903	score: 0.8289
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 904	score: 0.8582
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 905	score: 0.9015
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 906	score: 0.9091
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 907	score: 0.8446
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 908	score: 0.7011
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 909	score: 0.8309
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 910	score: 0.7175
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 911	score: 0.8185
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 912	score: 0.8620
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 913	score: 0.6111
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 914	score: 0.7603
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 915	score: 0.8330
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 916	score: 0.7848
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 917	score: 0.8892
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 918	score: 0.5682
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 919	score: 0.8339
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 920	score: 0.8283
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 921	score: 0.9234
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 922	score: 0.8050
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 923	score: 0.9167
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 924	score: 0.7223
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 925	score: 0.8119
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 926	score: 0.8707
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 927	score: 0.8691
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 928	score: 0.7451
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 929	score: 0.6782
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 930	score: 0.9377
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 931	score: 0.8143
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 932	score: 0.6114
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 933	score: 0.7408
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 934	score: 0.7079
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 935	score: 0.6422
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 936	score: 0.7184
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 937	score: 0.9190
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 938	score: 0.7018
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 939	score: 0.8609
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 940	score: 0.8839
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 941	score: 0.9460
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 942	score: 0.7258
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 943	score: 0.6260
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 944	score: 0.7638
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 945	score: 0.9016
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 946	score: 0.7424
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 947	score: 0.8024
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 948	score: 0.8307
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 949	score: 0.7816
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 950	score: 0.8221
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 951	score: 0.8305
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 952	score: 0.6951
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 953	score: 0.7638
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 954	score: 0.4125
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 955	score: 0.9194
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 956	score: 0.9185
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 957	score: 0.7594
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 958	score: 0.6839
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 959	score: 0.6184
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 960	score: 0.6580
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 961	score: 0.4950
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 962	score: 0.7275
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 963	score: 0.7177
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 964	score: 0.8933
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 965	score: 0.8092
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 966	score: 0.8802
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 967	score: 0.5954
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 968	score: 0.2241
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 969	score: 0.5734
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 970	score: 0.7716
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 971	score: 0.6210
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 972	score: 0.7061
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 973	score: 0.7243
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 974	score: 0.8675
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 975	score: 0.9441
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 976	score: 0.7928
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 977	score: 0.8614
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 978	score: 0.9226
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 979	score: 0.9044
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 980	score: 0.9241
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 981	score: 0.7170
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 982	score: 0.8476
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 983	score: 0.7174
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 984	score: 0.8416
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 985	score: 0.8019
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 986	score: 0.7480
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 987	score: 0.7068
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 988	score: 0.7483
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 989	score: 0.6974
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 990	score: 0.8985
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 991	score: 0.7280
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 992	score: 0.8975
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 993	score: 0.8313
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 994	score: 0.6880
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 995	score: 0.6515
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 996	score: 0.8607
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 997	score: 0.9137
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 998	score: 0.8552
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 999	score: 0.7522
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1000	score: 0.9155
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1001	score: 0.3300
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1002	score: 0.7569
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1003	score: 0.5350
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1004	score: 0.7625
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1005	score: 0.8495
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1006	score: 0.8019
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1007	score: 0.8459
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1008	score: 0.9267
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1009	score: 0.6677
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1010	score: 0.6532
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	Segment 1011	score: 0.7985
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-el	score: 0.7651