/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 0	score: 0.6917
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1	score: 0.9072
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 2	score: 0.8976
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 3	score: 0.7238
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 4	score: 0.7958
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 5	score: 0.6163
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 6	score: 0.8761
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 7	score: 0.7087
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 8	score: 0.8642
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 9	score: 0.6864
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 10	score: 0.6056
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 11	score: 0.7718
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 12	score: 0.8744
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 13	score: 0.8735
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 14	score: 0.5883
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 15	score: 0.6268
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 16	score: 0.6255
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 17	score: 0.9224
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 18	score: 0.7811
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 19	score: 0.7614
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 20	score: 0.7208
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 21	score: 0.7399
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 22	score: 0.4999
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 23	score: 0.8124
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 24	score: 0.8977
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 25	score: 0.7211
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 26	score: 0.8037
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 27	score: 0.7771
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 28	score: 0.6596
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 29	score: 0.7021
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 30	score: 0.2855
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 31	score: 0.5972
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 32	score: 0.6029
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 33	score: 0.9248
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 34	score: 0.9410
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 35	score: 0.8469
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 36	score: 0.8079
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 37	score: 0.7723
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 38	score: 0.7663
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 39	score: 0.8710
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 40	score: 0.6981
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 41	score: 0.9420
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 42	score: 0.7220
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 43	score: 0.9107
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 44	score: 0.7585
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 45	score: 0.7648
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 46	score: 0.7259
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 47	score: 0.8687
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 48	score: 0.5741
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 49	score: 0.6222
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 50	score: 0.9180
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 51	score: 0.9346
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 52	score: 0.7897
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 53	score: 0.5750
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 54	score: 0.9188
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 55	score: 0.7871
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 56	score: 0.7131
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 57	score: 0.6351
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 58	score: 0.7306
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 59	score: 0.4565
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 60	score: 0.6370
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 61	score: 0.6211
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 62	score: 0.5027
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 63	score: 0.6726
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 64	score: 0.7352
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 65	score: 0.6390
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 66	score: 0.7369
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 67	score: 0.6347
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 68	score: 0.8968
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 69	score: 0.6144
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 70	score: 0.6845
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 71	score: 0.7338
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 72	score: 0.7219
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 73	score: 0.6363
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 74	score: 0.7184
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 75	score: 0.8155
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 76	score: 0.9181
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 77	score: 0.8201
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 78	score: 0.7854
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 79	score: 0.9399
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 80	score: 0.7183
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 81	score: 0.8647
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 82	score: 0.5817
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 83	score: 0.6593
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 84	score: 0.6013
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 85	score: 0.8477
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 86	score: 0.6399
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 87	score: 0.7461
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 88	score: 0.9223
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 89	score: 0.6262
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 90	score: 0.7765
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 91	score: 0.6480
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 92	score: 0.7511
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 93	score: 0.7732
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 94	score: 0.8241
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 95	score: 0.9258
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 96	score: 0.9409
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 97	score: 0.7970
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 98	score: 0.4747
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 99	score: 0.8925
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 100	score: 0.9017
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 101	score: 0.8461
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 102	score: 0.7508
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 103	score: 0.7551
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 104	score: 0.8449
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 105	score: 0.7860
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 106	score: 0.9288
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 107	score: 0.7468
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 108	score: 0.6754
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 109	score: 0.8989
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 110	score: 0.8436
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 111	score: 0.8795
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 112	score: 0.9495
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 113	score: 0.8942
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 114	score: 0.6908
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 115	score: 0.8396
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 116	score: 0.8686
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 117	score: 0.7236
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 118	score: 0.9604
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 119	score: 0.8807
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 120	score: 0.6374
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 121	score: 0.9310
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 122	score: 0.9165
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 123	score: 0.8685
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 124	score: 0.7226
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 125	score: 0.7288
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 126	score: 0.8132
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 127	score: 0.6028
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 128	score: 0.8336
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 129	score: 0.5875
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 130	score: 0.7035
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 131	score: 0.7677
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 132	score: 0.8889
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 133	score: 0.8959
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 134	score: 0.8382
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 135	score: 0.5246
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 136	score: 0.9616
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 137	score: 0.7458
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 138	score: 0.5271
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 139	score: 0.4177
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 140	score: 0.6652
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 141	score: 0.9204
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 142	score: 0.7426
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 143	score: 0.6845
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 144	score: 0.9084
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 145	score: 0.7125
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 146	score: 0.9037
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 147	score: 0.8046
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 148	score: 0.8112
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 149	score: 0.8291
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 150	score: 0.7474
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 151	score: 0.8545
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 152	score: 0.6267
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 153	score: 0.6290
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 154	score: 0.6586
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 155	score: 0.8841
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 156	score: 0.7045
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 157	score: 0.7446
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 158	score: 0.8845
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 159	score: 0.7462
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 160	score: 0.5539
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 161	score: 0.7863
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 162	score: 0.6690
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 163	score: 0.8300
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 164	score: 0.8534
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 165	score: 0.6798
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 166	score: 0.7646
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 167	score: 0.7901
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 168	score: 0.7344
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 169	score: 0.7328
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 170	score: 0.6337
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 171	score: 0.8896
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 172	score: 0.5359
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 173	score: 0.9076
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 174	score: 0.8159
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 175	score: 0.6415
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 176	score: 0.7528
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 177	score: 0.8059
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 178	score: 0.6133
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 179	score: 0.8538
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 180	score: 0.9114
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 181	score: 0.8802
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 182	score: 0.7910
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 183	score: 0.9010
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 184	score: 0.7411
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 185	score: 0.8433
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 186	score: 0.8776
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 187	score: 0.6357
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 188	score: 0.8001
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 189	score: 0.8850
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 190	score: 0.6126
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 191	score: 0.8928
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 192	score: 0.7015
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 193	score: 0.8091
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 194	score: 0.9188
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 195	score: 0.5777
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 196	score: 0.7238
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 197	score: 0.6157
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 198	score: 0.8430
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 199	score: 0.6834
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 200	score: 0.8009
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 201	score: 0.6679
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 202	score: 0.5715
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 203	score: 0.6547
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 204	score: 0.2211
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 205	score: 0.6264
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 206	score: 0.8192
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 207	score: 0.2718
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 208	score: 0.2451
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 209	score: 0.8870
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 210	score: 0.9344
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 211	score: 0.9382
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 212	score: 0.7538
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 213	score: 0.7248
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 214	score: 0.6897
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 215	score: 0.5448
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 216	score: 0.9414
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 217	score: 0.8519
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 218	score: 0.8549
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 219	score: 0.8362
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 220	score: 0.9136
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 221	score: 0.8813
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 222	score: 0.9172
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 223	score: 0.8387
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 224	score: 0.9264
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 225	score: 0.9496
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 226	score: 0.8245
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 227	score: 0.6983
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 228	score: 0.6923
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 229	score: 0.7702
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 230	score: 0.9729
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 231	score: 0.9058
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 232	score: 0.6889
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 233	score: 0.8916
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 234	score: 0.7416
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 235	score: 0.7221
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 236	score: 0.8884
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 237	score: 0.7565
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 238	score: 0.9078
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 239	score: 0.8259
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 240	score: 0.5494
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 241	score: 0.5185
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 242	score: 0.8855
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 243	score: 0.5744
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 244	score: 0.5718
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 245	score: 0.8110
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 246	score: 0.6849
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 247	score: 0.5900
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 248	score: 0.6257
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 249	score: 0.9089
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 250	score: 0.8471
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 251	score: 0.6293
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 252	score: 0.8527
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 253	score: 0.4982
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 254	score: 0.5653
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 255	score: 0.8942
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 256	score: 0.8235
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 257	score: 0.4851
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 258	score: 0.7732
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 259	score: 0.5512
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 260	score: 0.9291
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 261	score: 0.7283
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 262	score: 0.8784
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 263	score: 0.6633
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 264	score: 0.7297
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 265	score: 0.7296
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 266	score: 0.8380
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 267	score: 0.8167
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 268	score: 0.9432
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 269	score: 0.7674
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 270	score: 0.7390
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 271	score: 0.5640
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 272	score: 0.7642
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 273	score: 0.7360
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 274	score: 0.6334
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 275	score: 0.1847
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 276	score: 0.5492
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 277	score: 0.9097
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 278	score: 0.7245
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 279	score: 0.9101
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 280	score: 0.8353
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 281	score: 0.5579
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 282	score: 0.8944
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 283	score: 0.5042
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 284	score: 0.4635
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 285	score: 0.9486
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 286	score: 0.9165
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 287	score: 0.5249
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 288	score: 0.9103
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 289	score: 0.2268
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 290	score: 0.8816
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 291	score: 0.7236
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 292	score: 0.8399
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 293	score: 0.7806
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 294	score: 0.4919
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 295	score: 0.6713
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 296	score: 0.6950
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 297	score: 0.8749
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 298	score: 0.6973
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 299	score: 0.7613
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 300	score: 0.8743
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 301	score: 0.7966
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 302	score: 0.8499
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 303	score: 0.9105
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 304	score: 0.7630
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 305	score: 0.8307
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 306	score: 0.9401
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 307	score: 0.8877
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 308	score: 0.9564
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 309	score: 0.7772
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 310	score: 0.5237
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 311	score: 0.5538
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 312	score: 0.9349
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 313	score: 0.6828
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 314	score: 0.9604
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 315	score: 0.9287
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 316	score: 0.7791
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 317	score: 0.7787
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 318	score: 0.7238
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 319	score: 0.5540
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 320	score: 0.7121
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 321	score: 0.7044
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 322	score: 0.6628
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 323	score: 0.8983
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 324	score: 0.9535
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 325	score: 0.8678
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 326	score: 0.5777
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 327	score: 0.5594
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 328	score: 0.8983
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 329	score: 0.6791
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 330	score: 0.6491
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 331	score: 0.8167
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 332	score: 0.7684
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 333	score: 0.5581
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 334	score: 0.9593
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 335	score: 0.7518
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 336	score: 0.7774
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 337	score: 0.6093
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 338	score: 0.5717
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 339	score: 0.9215
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 340	score: 0.6671
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 341	score: 0.4575
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 342	score: 0.4200
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 343	score: 0.7413
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 344	score: 0.7108
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 345	score: 0.5425
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 346	score: 0.7276
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 347	score: 0.9244
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 348	score: 0.5272
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 349	score: 0.5351
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 350	score: 0.8369
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 351	score: 0.5171
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 352	score: 0.8053
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 353	score: 0.7836
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 354	score: 0.6553
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 355	score: 0.6233
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 356	score: 0.5875
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 357	score: 0.8962
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 358	score: 0.7581
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 359	score: 0.5827
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 360	score: 0.6410
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 361	score: 0.7443
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 362	score: 0.6647
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 363	score: 0.4773
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 364	score: 0.7043
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 365	score: 0.7074
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 366	score: 0.5560
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 367	score: 0.8718
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 368	score: 0.6104
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 369	score: 0.6420
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 370	score: 0.5711
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 371	score: 0.4717
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 372	score: 0.7550
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 373	score: 0.7550
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 374	score: 0.7880
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 375	score: 0.6920
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 376	score: 0.6296
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 377	score: 0.9184
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 378	score: 0.4588
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 379	score: 0.7136
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 380	score: 0.5593
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 381	score: 0.8564
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 382	score: 0.5643
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 383	score: 0.4623
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 384	score: 0.7425
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 385	score: 0.7403
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 386	score: 0.6108
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 387	score: 0.7041
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 388	score: 0.4487
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 389	score: 0.8038
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 390	score: 0.5640
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 391	score: 0.7578
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 392	score: 0.8100
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 393	score: 0.6456
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 394	score: 0.8696
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 395	score: 0.8782
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 396	score: 0.7887
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 397	score: 0.8820
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 398	score: 0.6327
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 399	score: 0.9302
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 400	score: 0.9225
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 401	score: 0.7307
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 402	score: 0.8504
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 403	score: 0.5815
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 404	score: 0.4863
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 405	score: 0.8826
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 406	score: 0.8357
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 407	score: 0.7001
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 408	score: 0.9413
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 409	score: 0.8855
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 410	score: 0.7643
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 411	score: 0.3309
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 412	score: 0.7254
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 413	score: 0.8459
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 414	score: 0.6842
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 415	score: 0.6955
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 416	score: 0.8549
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 417	score: 0.7614
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 418	score: 0.9189
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 419	score: 0.8246
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 420	score: 0.6518
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 421	score: 0.9012
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 422	score: 0.6477
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 423	score: 0.7838
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 424	score: 0.6765
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 425	score: 0.8986
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 426	score: 0.8414
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 427	score: 0.8761
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 428	score: 0.9322
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 429	score: 0.9721
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 430	score: 0.8314
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 431	score: 0.8464
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 432	score: 0.6602
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 433	score: 0.6533
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 434	score: 0.7929
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 435	score: 0.5804
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 436	score: 0.5642
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 437	score: 0.7555
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 438	score: 0.9393
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 439	score: 0.8268
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 440	score: 0.7715
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 441	score: 0.7710
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 442	score: 0.8339
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 443	score: 0.8557
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 444	score: 0.7214
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 445	score: 0.6910
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 446	score: 0.7023
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 447	score: 0.6288
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 448	score: 0.9350
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 449	score: 0.6684
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 450	score: 0.7160
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 451	score: 0.7891
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 452	score: 0.6348
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 453	score: 0.7978
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 454	score: 0.7779
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 455	score: 0.9206
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 456	score: 0.6547
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 457	score: 0.6074
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 458	score: 0.6735
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 459	score: 0.5287
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 460	score: 0.7725
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 461	score: 0.6106
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 462	score: 0.5859
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 463	score: 0.6648
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 464	score: 0.7802
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 465	score: 0.8438
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 466	score: 0.7751
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 467	score: 0.4510
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 468	score: 0.4848
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 469	score: 0.5392
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 470	score: 0.5286
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 471	score: 0.6241
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 472	score: 0.6709
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 473	score: 0.5120
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 474	score: 0.6369
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 475	score: 0.8032
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 476	score: 0.7697
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 477	score: 0.7774
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 478	score: 0.9390
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 479	score: 0.8775
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 480	score: 0.4904
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 481	score: 0.5831
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 482	score: 0.8215
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 483	score: 0.5354
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 484	score: 0.7841
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 485	score: 0.6558
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 486	score: 0.9221
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 487	score: 0.6603
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 488	score: 0.9209
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 489	score: 0.6818
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 490	score: 0.6265
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 491	score: 0.9302
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 492	score: 0.9502
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 493	score: 0.6272
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 494	score: 0.7711
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 495	score: 0.5168
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 496	score: 0.9092
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 497	score: 0.6399
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 498	score: 0.7144
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 499	score: 0.5669
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 500	score: 0.9429
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 501	score: 0.8697
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 502	score: 0.8880
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 503	score: 0.5328
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 504	score: 0.6437
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 505	score: 0.5113
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 506	score: 0.5941
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 507	score: 0.5644
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 508	score: 0.5295
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 509	score: 0.8383
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 510	score: 0.5496
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 511	score: 0.2473
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 512	score: 0.4597
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 513	score: 0.5261
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 514	score: 0.5168
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 515	score: 0.9187
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 516	score: 0.6086
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 517	score: 0.9477
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 518	score: 0.7251
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 519	score: 0.9259
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 520	score: 0.8626
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 521	score: 0.8496
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 522	score: 0.5844
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 523	score: 0.7304
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 524	score: 0.9304
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 525	score: 0.6495
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 526	score: 0.7848
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 527	score: 0.6154
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 528	score: 0.7600
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 529	score: 0.6376
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 530	score: 0.5235
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 531	score: 0.6987
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 532	score: 0.5189
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 533	score: 0.6048
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 534	score: 0.5321
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 535	score: 0.4166
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 536	score: 0.6015
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 537	score: 0.5298
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 538	score: 0.6541
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 539	score: 0.6195
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 540	score: 0.7005
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 541	score: 0.7772
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 542	score: 0.7660
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 543	score: 0.8185
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 544	score: 0.7450
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 545	score: 0.9638
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 546	score: 0.7633
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 547	score: 0.8689
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 548	score: 0.6232
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 549	score: 0.8741
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 550	score: 0.6898
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 551	score: 0.7596
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 552	score: 0.9009
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 553	score: 0.8196
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 554	score: 0.6523
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 555	score: 0.5433
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 556	score: 0.5468
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 557	score: 0.5905
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 558	score: 0.6175
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 559	score: 0.2143
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 560	score: 0.7384
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 561	score: 0.7846
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 562	score: 0.9005
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 563	score: 0.4347
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 564	score: 0.8149
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 565	score: 0.7118
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 566	score: 0.6614
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 567	score: 0.7910
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 568	score: 0.6716
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 569	score: 0.7827
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 570	score: 0.8564
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 571	score: 0.8227
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 572	score: 0.7918
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 573	score: 0.9162
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 574	score: 0.9368
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 575	score: 0.5520
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 576	score: 0.7291
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 577	score: 0.8447
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 578	score: 0.9030
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 579	score: 0.5596
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 580	score: 0.6424
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 581	score: 0.6235
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 582	score: 0.7356
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 583	score: 0.6178
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 584	score: 0.3789
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 585	score: 0.8927
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 586	score: 0.8625
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 587	score: 0.9339
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 588	score: 0.6868
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 589	score: 0.7857
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 590	score: 0.7712
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 591	score: 0.7907
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 592	score: 0.2779
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 593	score: 0.9161
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 594	score: 0.8189
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 595	score: 0.5050
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 596	score: 0.5532
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 597	score: 0.7745
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 598	score: 0.5411
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 599	score: 0.8461
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 600	score: 0.8095
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 601	score: 0.7931
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 602	score: 0.6987
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 603	score: 0.5574
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 604	score: 0.7324
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 605	score: 0.8210
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 606	score: 0.8344
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 607	score: 0.5951
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 608	score: 0.6559
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 609	score: 0.6768
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 610	score: 0.8086
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 611	score: 0.9199
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 612	score: 0.8741
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 613	score: 0.8366
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 614	score: 0.9335
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 615	score: 0.5428
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 616	score: 0.5901
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 617	score: 0.8527
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 618	score: 0.6291
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 619	score: 0.5348
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 620	score: 0.5709
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 621	score: 0.4522
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 622	score: 0.8223
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 623	score: 0.7141
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 624	score: 0.6390
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 625	score: 0.9304
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 626	score: 0.9356
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 627	score: 0.9308
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 628	score: 0.9140
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 629	score: 0.9041
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 630	score: 0.8445
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 631	score: 0.9105
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 632	score: 0.9522
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 633	score: 0.8566
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 634	score: 0.9277
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 635	score: 0.8926
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 636	score: 0.8930
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 637	score: 0.6369
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 638	score: 0.7425
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 639	score: 0.8733
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 640	score: 0.6775
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 641	score: 0.9249
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 642	score: 0.7632
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 643	score: 0.3677
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 644	score: 0.4263
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 645	score: 0.6059
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 646	score: 0.8806
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 647	score: 0.8456
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 648	score: 0.7075
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 649	score: 0.5200
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 650	score: 0.8904
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 651	score: 0.7627
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 652	score: 0.4534
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 653	score: 0.1876
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 654	score: 0.8161
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 655	score: 0.7031
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 656	score: 0.8381
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 657	score: 0.8307
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 658	score: 0.6198
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 659	score: 0.5782
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 660	score: 0.6659
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 661	score: 0.8959
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 662	score: 0.9571
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 663	score: 0.8402
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 664	score: 0.8465
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 665	score: 0.8205
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 666	score: 0.8671
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 667	score: 0.8127
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 668	score: 0.9159
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 669	score: 0.6972
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 670	score: 0.7240
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 671	score: 0.9450
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 672	score: 0.9032
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 673	score: 0.8291
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 674	score: 0.8405
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 675	score: 0.8876
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 676	score: 0.9512
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 677	score: 0.9260
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 678	score: 0.6126
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 679	score: 0.8261
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 680	score: 0.5671
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 681	score: 0.9557
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 682	score: 0.9189
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 683	score: 0.7734
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 684	score: 0.8836
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 685	score: 0.8845
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 686	score: 0.7763
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 687	score: 0.7824
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 688	score: 0.9240
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 689	score: 0.5236
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 690	score: 0.8718
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 691	score: 0.7941
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 692	score: 0.9205
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 693	score: 0.6686
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 694	score: 0.7227
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 695	score: 0.5098
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 696	score: 0.7508
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 697	score: 0.6964
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 698	score: 0.5859
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 699	score: 0.8353
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 700	score: 0.7290
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 701	score: 0.6897
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 702	score: 0.8257
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 703	score: 0.7319
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 704	score: 0.4512
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 705	score: 0.8205
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 706	score: 0.5041
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 707	score: 0.5442
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 708	score: 0.8368
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 709	score: 0.9116
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 710	score: 0.7965
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 711	score: 0.6857
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 712	score: 0.9230
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 713	score: 0.8408
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 714	score: 0.7888
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 715	score: 0.5703
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 716	score: 0.8872
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 717	score: 0.7708
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 718	score: 0.8794
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 719	score: 0.5414
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 720	score: 0.6251
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 721	score: 0.8424
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 722	score: 0.6957
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 723	score: 0.8822
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 724	score: 0.8940
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 725	score: 0.8651
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 726	score: 0.8256
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 727	score: 0.7652
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 728	score: 0.5091
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 729	score: 0.7806
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 730	score: 0.5598
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 731	score: 0.8416
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 732	score: 0.8408
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 733	score: 0.9211
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 734	score: 0.5785
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 735	score: 0.7429
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 736	score: 0.9333
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 737	score: 0.7811
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 738	score: 0.8820
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 739	score: 0.6715
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 740	score: 0.9156
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 741	score: 0.7054
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 742	score: 0.7802
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 743	score: 0.8110
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 744	score: 0.8639
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 745	score: 0.6085
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 746	score: 0.6933
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 747	score: 0.8569
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 748	score: 0.9689
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 749	score: 0.8350
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 750	score: 0.7427
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 751	score: 0.9053
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 752	score: 0.6716
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 753	score: 0.7725
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 754	score: 0.9330
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 755	score: 0.7098
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 756	score: 0.8181
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 757	score: 0.6739
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 758	score: 0.9640
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 759	score: 0.5899
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 760	score: 0.9273
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 761	score: 0.6325
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 762	score: 0.7891
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 763	score: 0.5130
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 764	score: 0.7975
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 765	score: 0.8187
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 766	score: 0.7272
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 767	score: 0.6311
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 768	score: 0.9502
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 769	score: 0.9507
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 770	score: 0.6273
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 771	score: 0.5880
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 772	score: 0.8639
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 773	score: 0.9015
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 774	score: 0.8210
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 775	score: 0.7862
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 776	score: 0.8121
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 777	score: 0.7439
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 778	score: 0.7846
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 779	score: 0.6960
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 780	score: 0.6547
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 781	score: 0.7531
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 782	score: 0.7052
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 783	score: 0.5932
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 784	score: 0.6514
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 785	score: 0.5739
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 786	score: 0.6317
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 787	score: 0.8836
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 788	score: 0.5496
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 789	score: 0.8489
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 790	score: 0.7846
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 791	score: 0.8470
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 792	score: 0.8654
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 793	score: 0.5830
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 794	score: 0.8913
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 795	score: 0.7245
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 796	score: 0.9552
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 797	score: 0.6552
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 798	score: 0.6395
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 799	score: 0.5082
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 800	score: 0.6804
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 801	score: 0.6114
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 802	score: 0.7171
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 803	score: 0.5792
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 804	score: 0.5572
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 805	score: 0.7084
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 806	score: 0.7812
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 807	score: 0.9551
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 808	score: 0.7244
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 809	score: 0.6585
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 810	score: 0.8778
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 811	score: 0.8018
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 812	score: 0.9301
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 813	score: 0.8744
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 814	score: 0.4909
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 815	score: 0.6402
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 816	score: 0.7619
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 817	score: 0.4754
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 818	score: 0.5839
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 819	score: 0.6337
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 820	score: 0.8921
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 821	score: 0.7331
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 822	score: 0.7381
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 823	score: 0.5911
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 824	score: 0.6497
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 825	score: 0.6387
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 826	score: 0.7174
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 827	score: 0.6774
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 828	score: 0.7594
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 829	score: 0.3518
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 830	score: 0.7986
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 831	score: 0.7468
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 832	score: 0.7440
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 833	score: 0.6403
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 834	score: 0.6579
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 835	score: 0.7107
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 836	score: 0.5194
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 837	score: 0.6902
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 838	score: 0.7890
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 839	score: 0.7391
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 840	score: 0.5699
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 841	score: 0.5629
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 842	score: 0.4220
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 843	score: 0.6639
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 844	score: 0.5635
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 845	score: 0.6060
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 846	score: 0.4628
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 847	score: 0.6283
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 848	score: 0.4822
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 849	score: 0.6445
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 850	score: 0.6321
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 851	score: 0.8471
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 852	score: 0.8278
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 853	score: 0.3967
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 854	score: 0.8083
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 855	score: 0.6832
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 856	score: 0.5614
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 857	score: 0.8582
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 858	score: 0.8346
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 859	score: 0.8993
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 860	score: 0.6994
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 861	score: 0.5903
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 862	score: 0.7625
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 863	score: 0.8657
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 864	score: 0.7180
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 865	score: 0.4653
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 866	score: 0.7656
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 867	score: 0.5675
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 868	score: 0.7766
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 869	score: 0.6878
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 870	score: 0.8095
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 871	score: 0.6687
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 872	score: 0.8334
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 873	score: 0.7568
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 874	score: 0.5681
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 875	score: 0.6866
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 876	score: 0.8613
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 877	score: 0.8081
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 878	score: 0.8007
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 879	score: 0.7705
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 880	score: 0.8691
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 881	score: 0.8903
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 882	score: 0.8360
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 883	score: 0.7256
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 884	score: 0.6569
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 885	score: 0.9036
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 886	score: 0.8348
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 887	score: 0.5341
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 888	score: 0.5828
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 889	score: 0.6202
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 890	score: 0.7223
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 891	score: 0.6193
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 892	score: 0.4563
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 893	score: 0.1950
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 894	score: 0.6913
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 895	score: 0.6990
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 896	score: 0.5194
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 897	score: 0.4122
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 898	score: 0.8852
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 899	score: 0.7102
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 900	score: 0.8645
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 901	score: 0.5588
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 902	score: 0.5664
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 903	score: 0.5950
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 904	score: 0.8991
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 905	score: 0.8321
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 906	score: 0.9318
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 907	score: 0.6594
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 908	score: 0.8821
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 909	score: 0.8101
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 910	score: 0.7204
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 911	score: 0.5481
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 912	score: 0.8969
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 913	score: 0.7117
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 914	score: 0.3208
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 915	score: 0.7814
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 916	score: 0.6139
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 917	score: 0.6597
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 918	score: 0.6027
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 919	score: 0.6882
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 920	score: 0.6192
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 921	score: 0.8528
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 922	score: 0.5116
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 923	score: 0.8218
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 924	score: 0.6632
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 925	score: 0.6371
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 926	score: 0.5981
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 927	score: 0.4652
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 928	score: 0.5424
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 929	score: 0.7611
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 930	score: 0.6373
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 931	score: 0.6702
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 932	score: 0.5437
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 933	score: 0.8272
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 934	score: 0.6084
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 935	score: 0.5842
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 936	score: 0.5686
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 937	score: 0.9384
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 938	score: 0.6633
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 939	score: 0.8977
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 940	score: 0.7141
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 941	score: 0.7435
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 942	score: 0.9377
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 943	score: 0.7671
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 944	score: 0.6861
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 945	score: 0.7234
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 946	score: 0.7267
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 947	score: 0.4153
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 948	score: 0.8431
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 949	score: 0.9138
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 950	score: 0.8592
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 951	score: 0.7414
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 952	score: 0.6042
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 953	score: 0.5226
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 954	score: 0.4548
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 955	score: 0.9304
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 956	score: 0.9152
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 957	score: 0.8664
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 958	score: 0.7587
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 959	score: 0.9001
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 960	score: 0.6621
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 961	score: 0.4939
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 962	score: 0.6052
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 963	score: 0.7331
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 964	score: 0.8943
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 965	score: 0.6269
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 966	score: 0.4944
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 967	score: 0.4998
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 968	score: 0.3734
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 969	score: 0.5039
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 970	score: 0.4578
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 971	score: 0.5464
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 972	score: 0.5162
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 973	score: 0.8697
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 974	score: 0.7367
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 975	score: 0.6402
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 976	score: 0.5342
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 977	score: 0.6736
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 978	score: 0.8787
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 979	score: 0.6773
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 980	score: 0.8331
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 981	score: 0.6912
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 982	score: 0.9264
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 983	score: 0.6318
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 984	score: 0.7556
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 985	score: 0.9175
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 986	score: 0.6545
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 987	score: 0.7350
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 988	score: 0.5216
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 989	score: 0.4759
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 990	score: 0.8493
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 991	score: 0.6830
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 992	score: 0.8265
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 993	score: 0.8435
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 994	score: 0.5484
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 995	score: 0.5382
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 996	score: 0.4858
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 997	score: 0.9057
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 998	score: 0.7862
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 999	score: 0.6819
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1000	score: 0.9325
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1001	score: 0.2749
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1002	score: 0.8960
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1003	score: 0.6211
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1004	score: 0.7554
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1005	score: 0.8922
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1006	score: 0.7660
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1007	score: 0.4708
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1008	score: 0.9078
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1009	score: 0.6757
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1010	score: 0.5676
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	Segment 1011	score: 0.7207
/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-6-max-tokens-512//test-en-et	score: 0.7301