mekjr1 commited on
Commit
b6fa37c
1 Parent(s): c1ee75f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +105 -105
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-es](https://huggingface.co/Helsinki-NLP/opus-mt-en-es) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.4966
21
- - Bleu: 4.7931
22
- - Gen Len: 75.4033
23
 
24
  ## Model description
25
 
@@ -48,108 +48,108 @@ The following hyperparameters were used during training:
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
- |:-------------:|:-----:|:-----:|:---------------:|:------:|:--------:|
53
- | No log | 1.0 | 194 | 2.5190 | 0.4261 | 118.0446 |
54
- | No log | 2.0 | 388 | 2.1735 | 0.6863 | 94.2307 |
55
- | 2.6561 | 3.0 | 582 | 2.0123 | 0.8611 | 95.4628 |
56
- | 2.6561 | 4.0 | 776 | 1.9069 | 1.164 | 94.7917 |
57
- | 2.6561 | 5.0 | 970 | 1.8303 | 1.3784 | 91.8423 |
58
- | 1.8552 | 6.0 | 1164 | 1.7642 | 1.9842 | 85.5714 |
59
- | 1.8552 | 7.0 | 1358 | 1.7195 | 2.0005 | 89.3467 |
60
- | 1.6609 | 8.0 | 1552 | 1.6790 | 2.0224 | 85.5595 |
61
- | 1.6609 | 9.0 | 1746 | 1.6490 | 2.3548 | 86.1726 |
62
- | 1.6609 | 10.0 | 1940 | 1.6269 | 2.3567 | 86.1652 |
63
- | 1.5416 | 11.0 | 2134 | 1.5998 | 2.8122 | 84.0179 |
64
- | 1.5416 | 12.0 | 2328 | 1.5780 | 2.5282 | 83.4792 |
65
- | 1.449 | 13.0 | 2522 | 1.5585 | 2.6159 | 82.869 |
66
- | 1.449 | 14.0 | 2716 | 1.5372 | 2.8756 | 81.6518 |
67
- | 1.449 | 15.0 | 2910 | 1.5227 | 3.0051 | 80.8259 |
68
- | 1.3724 | 16.0 | 3104 | 1.5121 | 3.1957 | 79.6518 |
69
- | 1.3724 | 17.0 | 3298 | 1.5006 | 2.847 | 79.2798 |
70
- | 1.3724 | 18.0 | 3492 | 1.4927 | 3.2975 | 77.375 |
71
- | 1.3134 | 19.0 | 3686 | 1.4786 | 3.3924 | 76.744 |
72
- | 1.3134 | 20.0 | 3880 | 1.4698 | 3.5146 | 78.2173 |
73
- | 1.2583 | 21.0 | 4074 | 1.4638 | 3.2835 | 79.1548 |
74
- | 1.2583 | 22.0 | 4268 | 1.4532 | 3.2862 | 78.3363 |
75
- | 1.2583 | 23.0 | 4462 | 1.4521 | 3.5943 | 79.0923 |
76
- | 1.2111 | 24.0 | 4656 | 1.4458 | 3.856 | 77.4092 |
77
- | 1.2111 | 25.0 | 4850 | 1.4426 | 3.6296 | 77.9256 |
78
- | 1.1664 | 26.0 | 5044 | 1.4384 | 3.6092 | 76.442 |
79
- | 1.1664 | 27.0 | 5238 | 1.4342 | 3.7057 | 79.0357 |
80
- | 1.1664 | 28.0 | 5432 | 1.4290 | 3.5534 | 77.8452 |
81
- | 1.1259 | 29.0 | 5626 | 1.4323 | 3.8192 | 77.8304 |
82
- | 1.1259 | 30.0 | 5820 | 1.4258 | 4.0245 | 76.2872 |
83
- | 1.091 | 31.0 | 6014 | 1.4258 | 3.9815 | 75.0164 |
84
- | 1.091 | 32.0 | 6208 | 1.4252 | 3.8806 | 78.3289 |
85
- | 1.091 | 33.0 | 6402 | 1.4252 | 4.0585 | 76.9896 |
86
- | 1.0555 | 34.0 | 6596 | 1.4213 | 4.1074 | 75.9777 |
87
- | 1.0555 | 35.0 | 6790 | 1.4274 | 3.9179 | 79.1533 |
88
- | 1.0555 | 36.0 | 6984 | 1.4220 | 3.8599 | 76.4717 |
89
- | 1.0273 | 37.0 | 7178 | 1.4253 | 4.1578 | 77.6101 |
90
- | 1.0273 | 38.0 | 7372 | 1.4204 | 4.0983 | 78.497 |
91
- | 0.9949 | 39.0 | 7566 | 1.4280 | 4.2085 | 76.6057 |
92
- | 0.9949 | 40.0 | 7760 | 1.4207 | 4.0804 | 75.0729 |
93
- | 0.9949 | 41.0 | 7954 | 1.4234 | 4.1249 | 76.7411 |
94
- | 0.9687 | 42.0 | 8148 | 1.4243 | 4.2974 | 76.2188 |
95
- | 0.9687 | 43.0 | 8342 | 1.4298 | 4.417 | 76.4955 |
96
- | 0.9432 | 44.0 | 8536 | 1.4241 | 4.2923 | 77.0759 |
97
- | 0.9432 | 45.0 | 8730 | 1.4292 | 4.2664 | 77.5982 |
98
- | 0.9432 | 46.0 | 8924 | 1.4316 | 4.2662 | 75.2708 |
99
- | 0.9203 | 47.0 | 9118 | 1.4273 | 4.3311 | 74.3408 |
100
- | 0.9203 | 48.0 | 9312 | 1.4265 | 4.4701 | 76.0432 |
101
- | 0.8967 | 49.0 | 9506 | 1.4335 | 4.5713 | 76.7872 |
102
- | 0.8967 | 50.0 | 9700 | 1.4336 | 4.5226 | 76.9926 |
103
- | 0.8967 | 51.0 | 9894 | 1.4335 | 4.4275 | 77.7232 |
104
- | 0.8732 | 52.0 | 10088 | 1.4416 | 4.5138 | 77.2589 |
105
- | 0.8732 | 53.0 | 10282 | 1.4412 | 4.5469 | 76.0491 |
106
- | 0.8732 | 54.0 | 10476 | 1.4347 | 4.4204 | 74.4568 |
107
- | 0.8563 | 55.0 | 10670 | 1.4396 | 4.2991 | 77.0491 |
108
- | 0.8563 | 56.0 | 10864 | 1.4448 | 4.5678 | 76.7768 |
109
- | 0.8368 | 57.0 | 11058 | 1.4468 | 4.5362 | 76.1518 |
110
- | 0.8368 | 58.0 | 11252 | 1.4487 | 4.5456 | 76.0923 |
111
- | 0.8368 | 59.0 | 11446 | 1.4517 | 4.6951 | 76.692 |
112
- | 0.8187 | 60.0 | 11640 | 1.4501 | 4.6062 | 75.753 |
113
- | 0.8187 | 61.0 | 11834 | 1.4552 | 4.466 | 75.5193 |
114
- | 0.8031 | 62.0 | 12028 | 1.4547 | 4.6685 | 75.8155 |
115
- | 0.8031 | 63.0 | 12222 | 1.4593 | 4.6206 | 75.0625 |
116
- | 0.8031 | 64.0 | 12416 | 1.4570 | 4.7326 | 75.7783 |
117
- | 0.7885 | 65.0 | 12610 | 1.4586 | 4.6804 | 75.5774 |
118
- | 0.7885 | 66.0 | 12804 | 1.4661 | 4.483 | 76.503 |
119
- | 0.7885 | 67.0 | 12998 | 1.4630 | 4.8575 | 76.1146 |
120
- | 0.7749 | 68.0 | 13192 | 1.4654 | 4.8867 | 75.9524 |
121
- | 0.7749 | 69.0 | 13386 | 1.4713 | 4.8378 | 76.4152 |
122
- | 0.7607 | 70.0 | 13580 | 1.4659 | 4.7737 | 77.058 |
123
- | 0.7607 | 71.0 | 13774 | 1.4740 | 4.8789 | 76.3438 |
124
- | 0.7607 | 72.0 | 13968 | 1.4738 | 4.7456 | 75.9554 |
125
- | 0.7494 | 73.0 | 14162 | 1.4733 | 4.8289 | 75.811 |
126
- | 0.7494 | 74.0 | 14356 | 1.4729 | 4.7033 | 75.2247 |
127
- | 0.7369 | 75.0 | 14550 | 1.4749 | 4.7982 | 75.6815 |
128
- | 0.7369 | 76.0 | 14744 | 1.4767 | 4.8117 | 75.8839 |
129
- | 0.7369 | 77.0 | 14938 | 1.4781 | 4.5612 | 75.7188 |
130
- | 0.7283 | 78.0 | 15132 | 1.4779 | 4.7852 | 75.933 |
131
- | 0.7283 | 79.0 | 15326 | 1.4801 | 4.7405 | 76.0967 |
132
- | 0.7196 | 80.0 | 15520 | 1.4833 | 4.6466 | 76.7961 |
133
- | 0.7196 | 81.0 | 15714 | 1.4836 | 4.839 | 75.2604 |
134
- | 0.7196 | 82.0 | 15908 | 1.4853 | 4.7503 | 75.9881 |
135
- | 0.7102 | 83.0 | 16102 | 1.4907 | 4.9235 | 76.244 |
136
- | 0.7102 | 84.0 | 16296 | 1.4889 | 4.8346 | 75.3259 |
137
- | 0.7102 | 85.0 | 16490 | 1.4904 | 4.7364 | 75.9539 |
138
- | 0.7043 | 86.0 | 16684 | 1.4896 | 5.0884 | 75.0208 |
139
- | 0.7043 | 87.0 | 16878 | 1.4920 | 4.6834 | 75.2173 |
140
- | 0.6971 | 88.0 | 17072 | 1.4907 | 4.7318 | 75.7128 |
141
- | 0.6971 | 89.0 | 17266 | 1.4920 | 4.7857 | 75.8586 |
142
- | 0.6971 | 90.0 | 17460 | 1.4923 | 4.661 | 75.0193 |
143
- | 0.6933 | 91.0 | 17654 | 1.4935 | 4.8224 | 74.2054 |
144
- | 0.6933 | 92.0 | 17848 | 1.4942 | 4.8344 | 75.5461 |
145
- | 0.6873 | 93.0 | 18042 | 1.4953 | 4.9447 | 75.25 |
146
- | 0.6873 | 94.0 | 18236 | 1.4949 | 4.734 | 74.7113 |
147
- | 0.6873 | 95.0 | 18430 | 1.4946 | 4.7811 | 75.3973 |
148
- | 0.6853 | 96.0 | 18624 | 1.4965 | 4.7307 | 75.6414 |
149
- | 0.6853 | 97.0 | 18818 | 1.4957 | 4.8139 | 75.5878 |
150
- | 0.682 | 98.0 | 19012 | 1.4963 | 4.799 | 75.2857 |
151
- | 0.682 | 99.0 | 19206 | 1.4965 | 4.8997 | 75.2515 |
152
- | 0.682 | 100.0 | 19400 | 1.4966 | 4.7931 | 75.4033 |
153
 
154
 
155
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-es](https://huggingface.co/Helsinki-NLP/opus-mt-en-es) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.9576
21
+ - Bleu: 5.2917
22
+ - Gen Len: 76.1652
23
 
24
  ## Model description
25
 
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
53
+ | No log | 1.0 | 194 | 1.5013 | 4.5843 | 75.6652 |
54
+ | No log | 2.0 | 388 | 1.5089 | 4.6332 | 74.3943 |
55
+ | 0.6987 | 3.0 | 582 | 1.5167 | 4.6474 | 76.8423 |
56
+ | 0.6987 | 4.0 | 776 | 1.5170 | 4.8581 | 75.5565 |
57
+ | 0.6987 | 5.0 | 970 | 1.5234 | 4.7496 | 75.4673 |
58
+ | 0.6711 | 6.0 | 1164 | 1.5304 | 4.7982 | 74.4077 |
59
+ | 0.6711 | 7.0 | 1358 | 1.5285 | 4.8994 | 75.1533 |
60
+ | 0.6426 | 8.0 | 1552 | 1.5354 | 4.7699 | 74.7217 |
61
+ | 0.6426 | 9.0 | 1746 | 1.5481 | 5.0032 | 75.0938 |
62
+ | 0.6426 | 10.0 | 1940 | 1.5543 | 4.6445 | 75.4301 |
63
+ | 0.616 | 11.0 | 2134 | 1.5606 | 5.023 | 75.744 |
64
+ | 0.616 | 12.0 | 2328 | 1.5647 | 4.9297 | 75.2812 |
65
+ | 0.5893 | 13.0 | 2522 | 1.5650 | 5.082 | 76.2872 |
66
+ | 0.5893 | 14.0 | 2716 | 1.5794 | 4.9381 | 76.0521 |
67
+ | 0.5893 | 15.0 | 2910 | 1.5852 | 4.4323 | 74.2783 |
68
+ | 0.5614 | 16.0 | 3104 | 1.5895 | 4.8884 | 74.1042 |
69
+ | 0.5614 | 17.0 | 3298 | 1.5993 | 4.73 | 76.7842 |
70
+ | 0.5614 | 18.0 | 3492 | 1.6051 | 4.8878 | 74.1235 |
71
+ | 0.5382 | 19.0 | 3686 | 1.6114 | 4.7385 | 75.4196 |
72
+ | 0.5382 | 20.0 | 3880 | 1.6214 | 5.2447 | 75.7202 |
73
+ | 0.5134 | 21.0 | 4074 | 1.6299 | 5.2439 | 76.8512 |
74
+ | 0.5134 | 22.0 | 4268 | 1.6349 | 4.9998 | 74.7768 |
75
+ | 0.5134 | 23.0 | 4462 | 1.6441 | 5.1979 | 74.4405 |
76
+ | 0.4938 | 24.0 | 4656 | 1.6538 | 4.9686 | 74.8661 |
77
+ | 0.4938 | 25.0 | 4850 | 1.6586 | 5.2127 | 75.1042 |
78
+ | 0.4737 | 26.0 | 5044 | 1.6603 | 5.1942 | 75.1562 |
79
+ | 0.4737 | 27.0 | 5238 | 1.6760 | 5.218 | 75.4524 |
80
+ | 0.4737 | 28.0 | 5432 | 1.6764 | 4.9681 | 74.9092 |
81
+ | 0.4536 | 29.0 | 5626 | 1.6822 | 4.8603 | 75.442 |
82
+ | 0.4536 | 30.0 | 5820 | 1.6905 | 5.1553 | 75.9107 |
83
+ | 0.4358 | 31.0 | 6014 | 1.7020 | 4.9345 | 75.0193 |
84
+ | 0.4358 | 32.0 | 6208 | 1.7056 | 5.2455 | 75.3586 |
85
+ | 0.4358 | 33.0 | 6402 | 1.7083 | 5.083 | 76.5923 |
86
+ | 0.4184 | 34.0 | 6596 | 1.7148 | 5.0844 | 75.9792 |
87
+ | 0.4184 | 35.0 | 6790 | 1.7255 | 5.6166 | 76.0952 |
88
+ | 0.4184 | 36.0 | 6984 | 1.7198 | 5.1109 | 74.119 |
89
+ | 0.4041 | 37.0 | 7178 | 1.7409 | 5.1895 | 75.317 |
90
+ | 0.4041 | 38.0 | 7372 | 1.7467 | 5.1409 | 76.192 |
91
+ | 0.3871 | 39.0 | 7566 | 1.7457 | 5.2776 | 76.1384 |
92
+ | 0.3871 | 40.0 | 7760 | 1.7566 | 5.1878 | 76.5744 |
93
+ | 0.3871 | 41.0 | 7954 | 1.7648 | 5.1553 | 76.7202 |
94
+ | 0.3715 | 42.0 | 8148 | 1.7644 | 5.3827 | 75.1235 |
95
+ | 0.3715 | 43.0 | 8342 | 1.7789 | 4.9848 | 77.0938 |
96
+ | 0.3588 | 44.0 | 8536 | 1.7774 | 5.3408 | 76.4807 |
97
+ | 0.3588 | 45.0 | 8730 | 1.7877 | 5.2917 | 75.7098 |
98
+ | 0.3588 | 46.0 | 8924 | 1.7890 | 5.3424 | 76.5149 |
99
+ | 0.3461 | 47.0 | 9118 | 1.7962 | 5.2892 | 75.4048 |
100
+ | 0.3461 | 48.0 | 9312 | 1.8005 | 5.1806 | 76.1235 |
101
+ | 0.3361 | 49.0 | 9506 | 1.8067 | 5.1191 | 76.2098 |
102
+ | 0.3361 | 50.0 | 9700 | 1.8131 | 5.4998 | 75.3958 |
103
+ | 0.3361 | 51.0 | 9894 | 1.8203 | 5.1396 | 76.4926 |
104
+ | 0.323 | 52.0 | 10088 | 1.8254 | 5.3301 | 76.128 |
105
+ | 0.323 | 53.0 | 10282 | 1.8288 | 5.1309 | 75.4732 |
106
+ | 0.323 | 54.0 | 10476 | 1.8355 | 5.067 | 75.3929 |
107
+ | 0.3145 | 55.0 | 10670 | 1.8387 | 5.0625 | 75.4554 |
108
+ | 0.3145 | 56.0 | 10864 | 1.8485 | 5.0427 | 76.6399 |
109
+ | 0.3045 | 57.0 | 11058 | 1.8515 | 5.077 | 75.5685 |
110
+ | 0.3045 | 58.0 | 11252 | 1.8548 | 5.2864 | 75.5491 |
111
+ | 0.3045 | 59.0 | 11446 | 1.8647 | 5.1937 | 75.625 |
112
+ | 0.2954 | 60.0 | 11640 | 1.8638 | 5.2397 | 76.0089 |
113
+ | 0.2954 | 61.0 | 11834 | 1.8738 | 5.3512 | 75.9628 |
114
+ | 0.2867 | 62.0 | 12028 | 1.8767 | 5.3713 | 76.4241 |
115
+ | 0.2867 | 63.0 | 12222 | 1.8765 | 5.5181 | 76.7738 |
116
+ | 0.2867 | 64.0 | 12416 | 1.8841 | 5.0943 | 76.2932 |
117
+ | 0.2783 | 65.0 | 12610 | 1.8821 | 4.9868 | 75.7009 |
118
+ | 0.2783 | 66.0 | 12804 | 1.8915 | 5.4204 | 75.4688 |
119
+ | 0.2783 | 67.0 | 12998 | 1.8920 | 5.3434 | 75.5952 |
120
+ | 0.2738 | 68.0 | 13192 | 1.8941 | 5.2259 | 75.5476 |
121
+ | 0.2738 | 69.0 | 13386 | 1.8997 | 5.4174 | 77.5372 |
122
+ | 0.2661 | 70.0 | 13580 | 1.9044 | 5.2945 | 76.0312 |
123
+ | 0.2661 | 71.0 | 13774 | 1.9042 | 5.3489 | 75.7798 |
124
+ | 0.2661 | 72.0 | 13968 | 1.9087 | 5.1653 | 76.2366 |
125
+ | 0.2613 | 73.0 | 14162 | 1.9144 | 5.16 | 75.0402 |
126
+ | 0.2613 | 74.0 | 14356 | 1.9124 | 5.3944 | 74.8854 |
127
+ | 0.2548 | 75.0 | 14550 | 1.9194 | 4.9676 | 76.2827 |
128
+ | 0.2548 | 76.0 | 14744 | 1.9208 | 5.3381 | 75.6548 |
129
+ | 0.2548 | 77.0 | 14938 | 1.9228 | 5.3926 | 76.2024 |
130
+ | 0.2502 | 78.0 | 15132 | 1.9288 | 5.3713 | 76.0179 |
131
+ | 0.2502 | 79.0 | 15326 | 1.9292 | 5.3918 | 75.6786 |
132
+ | 0.2456 | 80.0 | 15520 | 1.9312 | 5.2898 | 76.0179 |
133
+ | 0.2456 | 81.0 | 15714 | 1.9323 | 5.1955 | 76.3051 |
134
+ | 0.2456 | 82.0 | 15908 | 1.9350 | 5.1054 | 76.0119 |
135
+ | 0.242 | 83.0 | 16102 | 1.9393 | 5.2818 | 75.0461 |
136
+ | 0.242 | 84.0 | 16296 | 1.9402 | 5.3891 | 76.0476 |
137
+ | 0.242 | 85.0 | 16490 | 1.9410 | 5.0327 | 76.4717 |
138
+ | 0.2385 | 86.0 | 16684 | 1.9445 | 5.2409 | 77.2262 |
139
+ | 0.2385 | 87.0 | 16878 | 1.9425 | 5.4225 | 75.7827 |
140
+ | 0.2341 | 88.0 | 17072 | 1.9485 | 5.2054 | 76.7262 |
141
+ | 0.2341 | 89.0 | 17266 | 1.9484 | 5.1336 | 75.5818 |
142
+ | 0.2341 | 90.0 | 17460 | 1.9518 | 5.1384 | 76.0476 |
143
+ | 0.2327 | 91.0 | 17654 | 1.9516 | 5.2578 | 75.8259 |
144
+ | 0.2327 | 92.0 | 17848 | 1.9534 | 5.4452 | 76.0655 |
145
+ | 0.2297 | 93.0 | 18042 | 1.9525 | 5.3555 | 76.5342 |
146
+ | 0.2297 | 94.0 | 18236 | 1.9533 | 5.3192 | 76.2619 |
147
+ | 0.2297 | 95.0 | 18430 | 1.9551 | 5.419 | 75.8988 |
148
+ | 0.2271 | 96.0 | 18624 | 1.9560 | 5.19 | 76.8036 |
149
+ | 0.2271 | 97.0 | 18818 | 1.9562 | 5.1571 | 76.186 |
150
+ | 0.226 | 98.0 | 19012 | 1.9570 | 5.1179 | 76.2812 |
151
+ | 0.226 | 99.0 | 19206 | 1.9575 | 5.2191 | 76.0699 |
152
+ | 0.226 | 100.0 | 19400 | 1.9576 | 5.2917 | 76.1652 |
153
 
154
 
155
  ### Framework versions