Hugging Face's logo

mekjr1
/
opus-mt-en-es-finetuned-es-to-pbb-v2

Text2Text Generation
Transformers
PyTorch
TensorBoard
marian
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mekjr1 commited on
Commit
f1fc28a
•
1 Parent(s): 066a8d3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +160 -0
README.md ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Helsinki-NLP/opus-mt-en-es
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ model-index:
9
+ - name: opus-mt-en-es-finetuned-es-to-pbb-v2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # opus-mt-en-es-finetuned-es-to-pbb-v2
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: 1.4111
21
+ - Bleu: 5.0706
22
+ - Gen Len: 79.6843
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 100
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:--------:|
53
+ | No log | 1.0 | 199 | 2.3358 | 0.2033 | 107.6275 |
54
+ | No log | 2.0 | 398 | 1.9948 | 0.4105 | 93.4369 |
55
+ | 2.6836 | 3.0 | 597 | 1.8394 | 0.6885 | 96.226 |
56
+ | 2.6836 | 4.0 | 796 | 1.7505 | 0.9758 | 92.553 |
57
+ | 2.6836 | 5.0 | 995 | 1.6792 | 1.127 | 92.2639 |
58
+ | 1.8775 | 6.0 | 1194 | 1.6272 | 1.4205 | 91.798 |
59
+ | 1.8775 | 7.0 | 1393 | 1.5862 | 1.6797 | 90.0038 |
60
+ | 1.672 | 8.0 | 1592 | 1.5504 | 1.8211 | 89.0189 |
61
+ | 1.672 | 9.0 | 1791 | 1.5297 | 1.8881 | 88.6881 |
62
+ | 1.672 | 10.0 | 1990 | 1.4965 | 2.0444 | 87.7715 |
63
+ | 1.5519 | 11.0 | 2189 | 1.4794 | 2.006 | 87.971 |
64
+ | 1.5519 | 12.0 | 2388 | 1.4574 | 2.3905 | 87.8232 |
65
+ | 1.4555 | 13.0 | 2587 | 1.4427 | 2.6062 | 86.9836 |
66
+ | 1.4555 | 14.0 | 2786 | 1.4281 | 2.5166 | 85.5341 |
67
+ | 1.4555 | 15.0 | 2985 | 1.4140 | 2.6726 | 83.5884 |
68
+ | 1.3806 | 16.0 | 3184 | 1.4086 | 2.7819 | 84.1465 |
69
+ | 1.3806 | 17.0 | 3383 | 1.3958 | 2.575 | 85.2765 |
70
+ | 1.3123 | 18.0 | 3582 | 1.3854 | 2.7781 | 84.399 |
71
+ | 1.3123 | 19.0 | 3781 | 1.3822 | 2.7167 | 84.3889 |
72
+ | 1.3123 | 20.0 | 3980 | 1.3708 | 2.8562 | 82.5114 |
73
+ | 1.2618 | 21.0 | 4179 | 1.3651 | 3.0604 | 81.5694 |
74
+ | 1.2618 | 22.0 | 4378 | 1.3644 | 3.1175 | 80.5619 |
75
+ | 1.2128 | 23.0 | 4577 | 1.3611 | 3.2668 | 81.0215 |
76
+ | 1.2128 | 24.0 | 4776 | 1.3470 | 3.3155 | 82.1566 |
77
+ | 1.2128 | 25.0 | 4975 | 1.3447 | 3.184 | 82.7083 |
78
+ | 1.1657 | 26.0 | 5174 | 1.3436 | 3.3536 | 81.3182 |
79
+ | 1.1657 | 27.0 | 5373 | 1.3414 | 3.6943 | 81.1275 |
80
+ | 1.1247 | 28.0 | 5572 | 1.3369 | 3.423 | 80.6452 |
81
+ | 1.1247 | 29.0 | 5771 | 1.3367 | 3.5945 | 79.702 |
82
+ | 1.1247 | 30.0 | 5970 | 1.3335 | 3.6159 | 79.9609 |
83
+ | 1.0886 | 31.0 | 6169 | 1.3327 | 3.8038 | 81.0556 |
84
+ | 1.0886 | 32.0 | 6368 | 1.3359 | 3.6587 | 81.4571 |
85
+ | 1.0508 | 33.0 | 6567 | 1.3321 | 3.6724 | 81.3359 |
86
+ | 1.0508 | 34.0 | 6766 | 1.3299 | 4.0592 | 82.1376 |
87
+ | 1.0508 | 35.0 | 6965 | 1.3345 | 4.0112 | 81.0 |
88
+ | 1.0218 | 36.0 | 7164 | 1.3352 | 3.9508 | 81.0846 |
89
+ | 1.0218 | 37.0 | 7363 | 1.3326 | 3.9708 | 80.7399 |
90
+ | 0.9904 | 38.0 | 7562 | 1.3372 | 3.7645 | 78.673 |
91
+ | 0.9904 | 39.0 | 7761 | 1.3340 | 3.9126 | 80.8384 |
92
+ | 0.9904 | 40.0 | 7960 | 1.3310 | 4.0236 | 80.4432 |
93
+ | 0.9631 | 41.0 | 8159 | 1.3324 | 3.984 | 82.0808 |
94
+ | 0.9631 | 42.0 | 8358 | 1.3316 | 4.1408 | 79.4457 |
95
+ | 0.937 | 43.0 | 8557 | 1.3374 | 4.0462 | 81.7727 |
96
+ | 0.937 | 44.0 | 8756 | 1.3391 | 4.2246 | 81.1894 |
97
+ | 0.937 | 45.0 | 8955 | 1.3412 | 4.1861 | 78.7513 |
98
+ | 0.9109 | 46.0 | 9154 | 1.3388 | 4.2017 | 81.5253 |
99
+ | 0.9109 | 47.0 | 9353 | 1.3424 | 4.3345 | 80.3346 |
100
+ | 0.8888 | 48.0 | 9552 | 1.3390 | 3.9713 | 80.3687 |
101
+ | 0.8888 | 49.0 | 9751 | 1.3456 | 4.1395 | 79.1263 |
102
+ | 0.8888 | 50.0 | 9950 | 1.3411 | 4.1723 | 79.1641 |
103
+ | 0.8668 | 51.0 | 10149 | 1.3474 | 4.1349 | 80.0366 |
104
+ | 0.8668 | 52.0 | 10348 | 1.3482 | 4.15 | 80.2197 |
105
+ | 0.8471 | 53.0 | 10547 | 1.3495 | 4.4204 | 79.1869 |
106
+ | 0.8471 | 54.0 | 10746 | 1.3515 | 4.514 | 79.0707 |
107
+ | 0.8471 | 55.0 | 10945 | 1.3568 | 4.4396 | 77.7664 |
108
+ | 0.8275 | 56.0 | 11144 | 1.3589 | 4.4487 | 80.1616 |
109
+ | 0.8275 | 57.0 | 11343 | 1.3547 | 4.6807 | 80.2525 |
110
+ | 0.8098 | 58.0 | 11542 | 1.3645 | 4.6038 | 79.4306 |
111
+ | 0.8098 | 59.0 | 11741 | 1.3599 | 4.7848 | 80.4242 |
112
+ | 0.8098 | 60.0 | 11940 | 1.3587 | 4.7262 | 80.1629 |
113
+ | 0.7927 | 61.0 | 12139 | 1.3646 | 4.7493 | 79.4268 |
114
+ | 0.7927 | 62.0 | 12338 | 1.3677 | 4.627 | 80.0909 |
115
+ | 0.7791 | 63.0 | 12537 | 1.3685 | 4.662 | 80.5795 |
116
+ | 0.7791 | 64.0 | 12736 | 1.3721 | 4.7668 | 79.9962 |
117
+ | 0.7791 | 65.0 | 12935 | 1.3756 | 4.7693 | 79.5253 |
118
+ | 0.7613 | 66.0 | 13134 | 1.3746 | 4.7458 | 79.721 |
119
+ | 0.7613 | 67.0 | 13333 | 1.3752 | 4.803 | 80.6376 |
120
+ | 0.7497 | 68.0 | 13532 | 1.3742 | 4.8253 | 80.0846 |
121
+ | 0.7497 | 69.0 | 13731 | 1.3795 | 4.8703 | 79.4596 |
122
+ | 0.7497 | 70.0 | 13930 | 1.3803 | 4.9391 | 79.7891 |
123
+ | 0.7366 | 71.0 | 14129 | 1.3848 | 4.8426 | 79.0455 |
124
+ | 0.7366 | 72.0 | 14328 | 1.3831 | 4.7599 | 79.0303 |
125
+ | 0.7262 | 73.0 | 14527 | 1.3846 | 4.7025 | 80.0518 |
126
+ | 0.7262 | 74.0 | 14726 | 1.3889 | 4.7676 | 79.7727 |
127
+ | 0.7262 | 75.0 | 14925 | 1.3869 | 4.7789 | 79.2904 |
128
+ | 0.7138 | 76.0 | 15124 | 1.3897 | 4.6479 | 79.9621 |
129
+ | 0.7138 | 77.0 | 15323 | 1.3900 | 4.705 | 80.4457 |
130
+ | 0.7053 | 78.0 | 15522 | 1.3922 | 4.8455 | 79.3245 |
131
+ | 0.7053 | 79.0 | 15721 | 1.3998 | 4.9485 | 80.2273 |
132
+ | 0.7053 | 80.0 | 15920 | 1.3965 | 5.1349 | 79.5644 |
133
+ | 0.6958 | 81.0 | 16119 | 1.3983 | 5.1193 | 79.5732 |
134
+ | 0.6958 | 82.0 | 16318 | 1.3996 | 4.834 | 79.226 |
135
+ | 0.6894 | 83.0 | 16517 | 1.4017 | 4.9904 | 79.4217 |
136
+ | 0.6894 | 84.0 | 16716 | 1.4028 | 5.1735 | 80.3346 |
137
+ | 0.6894 | 85.0 | 16915 | 1.4028 | 5.1039 | 78.5947 |
138
+ | 0.6818 | 86.0 | 17114 | 1.4037 | 5.1245 | 79.1275 |
139
+ | 0.6818 | 87.0 | 17313 | 1.4053 | 4.9355 | 79.6465 |
140
+ | 0.6773 | 88.0 | 17512 | 1.4037 | 5.1365 | 79.6465 |
141
+ | 0.6773 | 89.0 | 17711 | 1.4051 | 5.0875 | 80.1023 |
142
+ | 0.6773 | 90.0 | 17910 | 1.4064 | 4.8926 | 79.5442 |
143
+ | 0.6715 | 91.0 | 18109 | 1.4085 | 5.0131 | 80.0038 |
144
+ | 0.6715 | 92.0 | 18308 | 1.4094 | 4.9254 | 79.7348 |
145
+ | 0.6675 | 93.0 | 18507 | 1.4080 | 4.9318 | 79.9028 |
146
+ | 0.6675 | 94.0 | 18706 | 1.4093 | 5.0165 | 79.5833 |
147
+ | 0.6675 | 95.0 | 18905 | 1.4110 | 4.9511 | 79.4545 |
148
+ | 0.6638 | 96.0 | 19104 | 1.4097 | 5.1593 | 79.8472 |
149
+ | 0.6638 | 97.0 | 19303 | 1.4100 | 4.9738 | 79.971 |
150
+ | 0.6604 | 98.0 | 19502 | 1.4116 | 4.9764 | 79.7626 |
151
+ | 0.6604 | 99.0 | 19701 | 1.4110 | 5.0511 | 79.7992 |
152
+ | 0.6604 | 100.0 | 19900 | 1.4111 | 5.0706 | 79.6843 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - Transformers 4.31.0
158
+ - Pytorch 2.0.1+cu118
159
+ - Datasets 2.14.4
160
+ - Tokenizers 0.13.3