Hugging Face's logo

twieland
/
MIX1_ja-en_helsinki

Text2Text Generation
Transformers
PyTorch
marian
Generated from Trainer
Inference Endpoints
Model card Files Community
twieland commited on
Commit
574d086
•
1 Parent(s): ac5ba69

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +214 -0
README.md ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: MIX1_ja-en_helsinki
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # MIX1_ja-en_helsinki
14
+
15
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ja-en](https://huggingface.co/Helsinki-NLP/opus-mt-ja-en) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.7947
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.0003
37
+ - train_batch_size: 64
38
+ - eval_batch_size: 64
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 2
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:------:|:---------------:|
49
+ | 2.7495 | 0.01 | 2000 | 2.5989 |
50
+ | 2.5415 | 0.03 | 4000 | 2.4746 |
51
+ | 2.4409 | 0.04 | 6000 | 2.4731 |
52
+ | 2.3743 | 0.05 | 8000 | 2.4012 |
53
+ | 2.3254 | 0.06 | 10000 | 2.3904 |
54
+ | 2.2857 | 0.08 | 12000 | 2.3649 |
55
+ | 2.2448 | 0.09 | 14000 | 2.3188 |
56
+ | 2.2158 | 0.1 | 16000 | 2.2975 |
57
+ | 2.193 | 0.11 | 18000 | 2.2756 |
58
+ | 2.1669 | 0.13 | 20000 | 2.2852 |
59
+ | 2.144 | 0.14 | 22000 | 2.2689 |
60
+ | 2.1222 | 0.15 | 24000 | 2.2721 |
61
+ | 2.1045 | 0.16 | 26000 | 2.2489 |
62
+ | 2.0885 | 0.18 | 28000 | 2.2359 |
63
+ | 2.0732 | 0.19 | 30000 | 2.2771 |
64
+ | 2.0584 | 0.2 | 32000 | 2.2582 |
65
+ | 2.0471 | 0.21 | 34000 | 2.2093 |
66
+ | 2.0369 | 0.23 | 36000 | 2.1768 |
67
+ | 2.0241 | 0.24 | 38000 | 2.1884 |
68
+ | 2.0196 | 0.25 | 40000 | 2.2025 |
69
+ | 2.004 | 0.27 | 42000 | 2.1507 |
70
+ | 1.9936 | 0.28 | 44000 | 2.1668 |
71
+ | 1.9869 | 0.29 | 46000 | 2.1432 |
72
+ | 1.9735 | 0.3 | 48000 | 2.1662 |
73
+ | 1.9651 | 0.32 | 50000 | 2.1824 |
74
+ | 1.9551 | 0.33 | 52000 | 2.1608 |
75
+ | 1.9485 | 0.34 | 54000 | 2.1322 |
76
+ | 1.9421 | 0.35 | 56000 | 2.1476 |
77
+ | 1.9303 | 0.37 | 58000 | 2.0994 |
78
+ | 1.9236 | 0.38 | 60000 | 2.1182 |
79
+ | 1.9183 | 0.39 | 62000 | 2.1305 |
80
+ | 1.9108 | 0.4 | 64000 | 2.1469 |
81
+ | 1.9051 | 0.42 | 66000 | 2.1414 |
82
+ | 1.9018 | 0.43 | 68000 | 2.1089 |
83
+ | 1.8959 | 0.44 | 70000 | 2.0908 |
84
+ | 1.886 | 0.46 | 72000 | 2.0968 |
85
+ | 1.8802 | 0.47 | 74000 | 2.0503 |
86
+ | 1.8713 | 0.48 | 76000 | 2.0542 |
87
+ | 1.8648 | 0.49 | 78000 | 2.0990 |
88
+ | 1.8599 | 0.51 | 80000 | 2.1112 |
89
+ | 1.8563 | 0.52 | 82000 | 2.1007 |
90
+ | 1.8541 | 0.53 | 84000 | 2.0849 |
91
+ | 1.845 | 0.54 | 86000 | 2.0831 |
92
+ | 1.8448 | 0.56 | 88000 | 2.0560 |
93
+ | 1.8342 | 0.57 | 90000 | 2.0349 |
94
+ | 1.8344 | 0.58 | 92000 | 2.0301 |
95
+ | 1.8291 | 0.59 | 94000 | 2.0300 |
96
+ | 1.819 | 0.61 | 96000 | 2.0378 |
97
+ | 1.8154 | 0.62 | 98000 | 2.0197 |
98
+ | 1.82 | 0.63 | 100000 | 2.0463 |
99
+ | 1.8081 | 0.64 | 102000 | 2.0077 |
100
+ | 1.8046 | 0.66 | 104000 | 2.0101 |
101
+ | 1.7978 | 0.67 | 106000 | 2.0150 |
102
+ | 1.7934 | 0.68 | 108000 | 2.0215 |
103
+ | 1.7904 | 0.7 | 110000 | 2.0278 |
104
+ | 1.7871 | 0.71 | 112000 | 2.0588 |
105
+ | 1.779 | 0.72 | 114000 | 2.0062 |
106
+ | 1.7784 | 0.73 | 116000 | 2.0300 |
107
+ | 1.7749 | 0.75 | 118000 | 1.9664 |
108
+ | 1.7691 | 0.76 | 120000 | 2.0033 |
109
+ | 1.7622 | 0.77 | 122000 | 1.9983 |
110
+ | 1.7587 | 0.78 | 124000 | 2.0030 |
111
+ | 1.755 | 0.8 | 126000 | 1.9955 |
112
+ | 1.7531 | 0.81 | 128000 | 1.9764 |
113
+ | 1.7439 | 0.82 | 130000 | 1.9942 |
114
+ | 1.7406 | 0.83 | 132000 | 2.0221 |
115
+ | 1.7385 | 0.85 | 134000 | 1.9835 |
116
+ | 1.7332 | 0.86 | 136000 | 1.9967 |
117
+ | 1.7332 | 0.87 | 138000 | 2.0247 |
118
+ | 1.7309 | 0.88 | 140000 | 1.9817 |
119
+ | 1.7248 | 0.9 | 142000 | 2.0063 |
120
+ | 1.7209 | 0.91 | 144000 | 1.9583 |
121
+ | 1.7154 | 0.92 | 146000 | 1.9779 |
122
+ | 1.7153 | 0.94 | 148000 | 1.9478 |
123
+ | 1.7094 | 0.95 | 150000 | 1.9706 |
124
+ | 1.7061 | 0.96 | 152000 | 1.9605 |
125
+ | 1.7017 | 0.97 | 154000 | 1.9447 |
126
+ | 1.6965 | 0.99 | 156000 | 1.9419 |
127
+ | 1.6929 | 1.0 | 158000 | 1.9589 |
128
+ | 1.6628 | 1.01 | 160000 | 1.9383 |
129
+ | 1.6535 | 1.02 | 162000 | 1.9487 |
130
+ | 1.6495 | 1.04 | 164000 | 1.9400 |
131
+ | 1.6516 | 1.05 | 166000 | 1.9353 |
132
+ | 1.6513 | 1.06 | 168000 | 1.9253 |
133
+ | 1.6518 | 1.07 | 170000 | 1.9132 |
134
+ | 1.6491 | 1.09 | 172000 | 1.9076 |
135
+ | 1.6453 | 1.1 | 174000 | 1.9192 |
136
+ | 1.6426 | 1.11 | 176000 | 1.9191 |
137
+ | 1.6353 | 1.13 | 178000 | 1.9367 |
138
+ | 1.6352 | 1.14 | 180000 | 1.9218 |
139
+ | 1.6304 | 1.15 | 182000 | 1.9305 |
140
+ | 1.6299 | 1.16 | 184000 | 1.9072 |
141
+ | 1.6263 | 1.18 | 186000 | 1.9211 |
142
+ | 1.6284 | 1.19 | 188000 | 1.9037 |
143
+ | 1.6237 | 1.2 | 190000 | 1.8951 |
144
+ | 1.6231 | 1.21 | 192000 | 1.8998 |
145
+ | 1.6184 | 1.23 | 194000 | 1.8960 |
146
+ | 1.6153 | 1.24 | 196000 | 1.8776 |
147
+ | 1.6122 | 1.25 | 198000 | 1.8747 |
148
+ | 1.6109 | 1.26 | 200000 | 1.8951 |
149
+ | 1.6072 | 1.28 | 202000 | 1.8705 |
150
+ | 1.6094 | 1.29 | 204000 | 1.8903 |
151
+ | 1.6063 | 1.3 | 206000 | 1.8660 |
152
+ | 1.599 | 1.31 | 208000 | 1.8696 |
153
+ | 1.5931 | 1.33 | 210000 | 1.8598 |
154
+ | 1.5943 | 1.34 | 212000 | 1.8760 |
155
+ | 1.5906 | 1.35 | 214000 | 1.8833 |
156
+ | 1.5858 | 1.37 | 216000 | 1.8645 |
157
+ | 1.5873 | 1.38 | 218000 | 1.8620 |
158
+ | 1.5842 | 1.39 | 220000 | 1.8632 |
159
+ | 1.5808 | 1.4 | 222000 | 1.8782 |
160
+ | 1.5756 | 1.42 | 224000 | 1.8627 |
161
+ | 1.5728 | 1.43 | 226000 | 1.8649 |
162
+ | 1.5709 | 1.44 | 228000 | 1.8735 |
163
+ | 1.5704 | 1.45 | 230000 | 1.8630 |
164
+ | 1.5659 | 1.47 | 232000 | 1.8598 |
165
+ | 1.5637 | 1.48 | 234000 | 1.8519 |
166
+ | 1.5628 | 1.49 | 236000 | 1.8569 |
167
+ | 1.5559 | 1.5 | 238000 | 1.8401 |
168
+ | 1.5532 | 1.52 | 240000 | 1.8528 |
169
+ | 1.557 | 1.53 | 242000 | 1.8637 |
170
+ | 1.5499 | 1.54 | 244000 | 1.8701 |
171
+ | 1.5476 | 1.55 | 246000 | 1.8423 |
172
+ | 1.5502 | 1.57 | 248000 | 1.8320 |
173
+ | 1.5469 | 1.58 | 250000 | 1.8542 |
174
+ | 1.5382 | 1.59 | 252000 | 1.8526 |
175
+ | 1.5396 | 1.61 | 254000 | 1.8537 |
176
+ | 1.528 | 1.62 | 256000 | 1.8248 |
177
+ | 1.532 | 1.63 | 258000 | 1.8322 |
178
+ | 1.5269 | 1.64 | 260000 | 1.8381 |
179
+ | 1.5269 | 1.66 | 262000 | 1.8389 |
180
+ | 1.5269 | 1.67 | 264000 | 1.8445 |
181
+ | 1.525 | 1.68 | 266000 | 1.8232 |
182
+ | 1.5175 | 1.69 | 268000 | 1.8561 |
183
+ | 1.5172 | 1.71 | 270000 | 1.8342 |
184
+ | 1.5174 | 1.72 | 272000 | 1.8167 |
185
+ | 1.5114 | 1.73 | 274000 | 1.8281 |
186
+ | 1.5094 | 1.74 | 276000 | 1.8164 |
187
+ | 1.5083 | 1.76 | 278000 | 1.8317 |
188
+ | 1.5047 | 1.77 | 280000 | 1.8207 |
189
+ | 1.5045 | 1.78 | 282000 | 1.8155 |
190
+ | 1.497 | 1.8 | 284000 | 1.8275 |
191
+ | 1.4996 | 1.81 | 286000 | 1.8152 |
192
+ | 1.497 | 1.82 | 288000 | 1.8137 |
193
+ | 1.4967 | 1.83 | 290000 | 1.8109 |
194
+ | 1.4936 | 1.85 | 292000 | 1.8037 |
195
+ | 1.4867 | 1.86 | 294000 | 1.7955 |
196
+ | 1.4859 | 1.87 | 296000 | 1.8181 |
197
+ | 1.4869 | 1.88 | 298000 | 1.7999 |
198
+ | 1.4811 | 1.9 | 300000 | 1.8062 |
199
+ | 1.4831 | 1.91 | 302000 | 1.8042 |
200
+ | 1.4791 | 1.92 | 304000 | 1.8020 |
201
+ | 1.4797 | 1.93 | 306000 | 1.7972 |
202
+ | 1.483 | 1.95 | 308000 | 1.8044 |
203
+ | 1.4748 | 1.96 | 310000 | 1.8036 |
204
+ | 1.4772 | 1.97 | 312000 | 1.7958 |
205
+ | 1.4708 | 1.98 | 314000 | 1.7967 |
206
+ | 1.4743 | 2.0 | 316000 | 1.7947 |
207
+
208
+
209
+ ### Framework versions
210
+
211
+ - Transformers 4.19.2
212
+ - Pytorch 1.11.0+cu113
213
+ - Datasets 2.2.2
214
+ - Tokenizers 0.12.1