Hugging Face's logo

sayanmandal
/
t5-small_6_3-hi_en-to-en

Translation
Transformers
PyTorch
TensorBoard
t5
text2text-generation
generated_from_trainer
Eval Results
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
1
sayanmandal commited on
Commit
df13e9d
•
1 Parent(s): c220c25

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +175 -0
README.md ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - translation
4
+ - generated_from_trainer
5
+ datasets:
6
+ - cmu_hinglish_do_g
7
+ metrics:
8
+ - bleu
9
+ model-index:
10
+ - name: t5-small_6_3-hi_en-to-en
11
+ results:
12
+ - task:
13
+ name: Sequence-to-sequence Language Modeling
14
+ type: text2text-generation
15
+ dataset:
16
+ name: cmu_hinglish_do_g
17
+ type: cmu_hinglish_do_g
18
+ args: hi_en-en
19
+ metrics:
20
+ - name: Bleu
21
+ type: bleu
22
+ value: 18.0863
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # t5-small_6_3-hi_en-to-en
29
+
30
+ This model was trained from scratch on the cmu_hinglish_do_g dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 2.3662
33
+ - Bleu: 18.0863
34
+ - Gen Len: 15.2708
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 5e-05
54
+ - train_batch_size: 32
55
+ - eval_batch_size: 32
56
+ - seed: 42
57
+ - gradient_accumulation_steps: 2
58
+ - total_train_batch_size: 64
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 100
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
68
+ | No log | 1.0 | 126 | 3.0601 | 4.7146 | 11.9904 |
69
+ | No log | 2.0 | 252 | 2.8885 | 5.9584 | 12.3418 |
70
+ | No log | 3.0 | 378 | 2.7914 | 6.649 | 12.3758 |
71
+ | 3.4671 | 4.0 | 504 | 2.7347 | 7.3305 | 12.3854 |
72
+ | 3.4671 | 5.0 | 630 | 2.6832 | 8.3132 | 12.4268 |
73
+ | 3.4671 | 6.0 | 756 | 2.6485 | 8.339 | 12.3641 |
74
+ | 3.4671 | 7.0 | 882 | 2.6096 | 8.7269 | 12.414 |
75
+ | 3.0208 | 8.0 | 1008 | 2.5814 | 9.2163 | 12.2675 |
76
+ | 3.0208 | 9.0 | 1134 | 2.5542 | 9.448 | 12.3875 |
77
+ | 3.0208 | 10.0 | 1260 | 2.5339 | 9.9011 | 12.4321 |
78
+ | 3.0208 | 11.0 | 1386 | 2.5043 | 9.7529 | 12.5149 |
79
+ | 2.834 | 12.0 | 1512 | 2.4848 | 9.9606 | 12.4193 |
80
+ | 2.834 | 13.0 | 1638 | 2.4737 | 9.9368 | 12.3673 |
81
+ | 2.834 | 14.0 | 1764 | 2.4458 | 10.3182 | 12.4352 |
82
+ | 2.834 | 15.0 | 1890 | 2.4332 | 10.486 | 12.4671 |
83
+ | 2.7065 | 16.0 | 2016 | 2.4239 | 10.6921 | 12.414 |
84
+ | 2.7065 | 17.0 | 2142 | 2.4064 | 10.7426 | 12.4607 |
85
+ | 2.7065 | 18.0 | 2268 | 2.3941 | 11.0509 | 12.4087 |
86
+ | 2.7065 | 19.0 | 2394 | 2.3826 | 11.2407 | 12.3386 |
87
+ | 2.603 | 20.0 | 2520 | 2.3658 | 11.3711 | 12.3992 |
88
+ | 2.603 | 21.0 | 2646 | 2.3537 | 11.42 | 12.5032 |
89
+ | 2.603 | 22.0 | 2772 | 2.3475 | 12.0665 | 12.5074 |
90
+ | 2.603 | 23.0 | 2898 | 2.3398 | 12.0343 | 12.4342 |
91
+ | 2.5192 | 24.0 | 3024 | 2.3298 | 12.1011 | 12.5096 |
92
+ | 2.5192 | 25.0 | 3150 | 2.3216 | 12.2562 | 12.4809 |
93
+ | 2.5192 | 26.0 | 3276 | 2.3131 | 12.4585 | 12.4427 |
94
+ | 2.5192 | 27.0 | 3402 | 2.3052 | 12.7094 | 12.534 |
95
+ | 2.4445 | 28.0 | 3528 | 2.2984 | 12.7432 | 12.5053 |
96
+ | 2.4445 | 29.0 | 3654 | 2.2920 | 12.8409 | 12.4501 |
97
+ | 2.4445 | 30.0 | 3780 | 2.2869 | 12.6365 | 12.4936 |
98
+ | 2.4445 | 31.0 | 3906 | 2.2777 | 12.8523 | 12.5234 |
99
+ | 2.3844 | 32.0 | 4032 | 2.2788 | 12.9216 | 12.4204 |
100
+ | 2.3844 | 33.0 | 4158 | 2.2710 | 12.9568 | 12.5064 |
101
+ | 2.3844 | 34.0 | 4284 | 2.2643 | 12.9641 | 12.4299 |
102
+ | 2.3844 | 35.0 | 4410 | 2.2621 | 12.9787 | 12.448 |
103
+ | 2.3282 | 36.0 | 4536 | 2.2554 | 13.1264 | 12.4374 |
104
+ | 2.3282 | 37.0 | 4662 | 2.2481 | 13.1853 | 12.4416 |
105
+ | 2.3282 | 38.0 | 4788 | 2.2477 | 13.3259 | 12.4119 |
106
+ | 2.3282 | 39.0 | 4914 | 2.2448 | 13.2017 | 12.4278 |
107
+ | 2.2842 | 40.0 | 5040 | 2.2402 | 13.3772 | 12.4437 |
108
+ | 2.2842 | 41.0 | 5166 | 2.2373 | 13.2184 | 12.414 |
109
+ | 2.2842 | 42.0 | 5292 | 2.2357 | 13.5267 | 12.4342 |
110
+ | 2.2842 | 43.0 | 5418 | 2.2310 | 13.5754 | 12.4087 |
111
+ | 2.2388 | 44.0 | 5544 | 2.2244 | 13.653 | 12.4427 |
112
+ | 2.2388 | 45.0 | 5670 | 2.2243 | 13.6028 | 12.431 |
113
+ | 2.2388 | 46.0 | 5796 | 2.2216 | 13.7128 | 12.4151 |
114
+ | 2.2388 | 47.0 | 5922 | 2.2231 | 13.749 | 12.4172 |
115
+ | 2.2067 | 48.0 | 6048 | 2.2196 | 13.7256 | 12.4034 |
116
+ | 2.2067 | 49.0 | 6174 | 2.2125 | 13.8237 | 12.396 |
117
+ | 2.2067 | 50.0 | 6300 | 2.2131 | 13.6642 | 12.4416 |
118
+ | 2.2067 | 51.0 | 6426 | 2.2115 | 13.8876 | 12.4119 |
119
+ | 2.1688 | 52.0 | 6552 | 2.2091 | 14.0323 | 12.4639 |
120
+ | 2.1688 | 53.0 | 6678 | 2.2082 | 13.916 | 12.3843 |
121
+ | 2.1688 | 54.0 | 6804 | 2.2071 | 13.924 | 12.3758 |
122
+ | 2.1688 | 55.0 | 6930 | 2.2046 | 13.9563 | 12.4416 |
123
+ | 2.1401 | 56.0 | 7056 | 2.2020 | 14.0592 | 12.483 |
124
+ | 2.1401 | 57.0 | 7182 | 2.2047 | 13.8879 | 12.4076 |
125
+ | 2.1401 | 58.0 | 7308 | 2.2018 | 13.9267 | 12.3949 |
126
+ | 2.1401 | 59.0 | 7434 | 2.1964 | 14.0518 | 12.4363 |
127
+ | 2.1092 | 60.0 | 7560 | 2.1926 | 14.1518 | 12.4883 |
128
+ | 2.1092 | 61.0 | 7686 | 2.1972 | 14.132 | 12.4034 |
129
+ | 2.1092 | 62.0 | 7812 | 2.1939 | 14.2066 | 12.4151 |
130
+ | 2.1092 | 63.0 | 7938 | 2.1905 | 14.2923 | 12.4459 |
131
+ | 2.0932 | 64.0 | 8064 | 2.1932 | 14.2476 | 12.3418 |
132
+ | 2.0932 | 65.0 | 8190 | 2.1925 | 14.2057 | 12.3907 |
133
+ | 2.0932 | 66.0 | 8316 | 2.1906 | 14.2978 | 12.4055 |
134
+ | 2.0932 | 67.0 | 8442 | 2.1903 | 14.3276 | 12.4427 |
135
+ | 2.0706 | 68.0 | 8568 | 2.1918 | 14.4681 | 12.4034 |
136
+ | 2.0706 | 69.0 | 8694 | 2.1882 | 14.3751 | 12.4225 |
137
+ | 2.0706 | 70.0 | 8820 | 2.1870 | 14.5904 | 12.4204 |
138
+ | 2.0706 | 71.0 | 8946 | 2.1865 | 14.6409 | 12.4512 |
139
+ | 2.0517 | 72.0 | 9072 | 2.1831 | 14.6505 | 12.4352 |
140
+ | 2.0517 | 73.0 | 9198 | 2.1835 | 14.7485 | 12.4363 |
141
+ | 2.0517 | 74.0 | 9324 | 2.1824 | 14.7344 | 12.4586 |
142
+ | 2.0517 | 75.0 | 9450 | 2.1829 | 14.8097 | 12.4575 |
143
+ | 2.0388 | 76.0 | 9576 | 2.1822 | 14.6681 | 12.4108 |
144
+ | 2.0388 | 77.0 | 9702 | 2.1823 | 14.6421 | 12.4342 |
145
+ | 2.0388 | 78.0 | 9828 | 2.1816 | 14.7014 | 12.4459 |
146
+ | 2.0388 | 79.0 | 9954 | 2.1810 | 14.744 | 12.4565 |
147
+ | 2.0224 | 80.0 | 10080 | 2.1839 | 14.7889 | 12.4437 |
148
+ | 2.0224 | 81.0 | 10206 | 2.1793 | 14.802 | 12.4565 |
149
+ | 2.0224 | 82.0 | 10332 | 2.1776 | 14.7702 | 12.4214 |
150
+ | 2.0224 | 83.0 | 10458 | 2.1809 | 14.6772 | 12.4236 |
151
+ | 2.0115 | 84.0 | 10584 | 2.1786 | 14.709 | 12.4214 |
152
+ | 2.0115 | 85.0 | 10710 | 2.1805 | 14.7693 | 12.3981 |
153
+ | 2.0115 | 86.0 | 10836 | 2.1790 | 14.7628 | 12.4172 |
154
+ | 2.0115 | 87.0 | 10962 | 2.1785 | 14.7538 | 12.3992 |
155
+ | 2.0007 | 88.0 | 11088 | 2.1788 | 14.7493 | 12.3726 |
156
+ | 2.0007 | 89.0 | 11214 | 2.1788 | 14.8793 | 12.4045 |
157
+ | 2.0007 | 90.0 | 11340 | 2.1786 | 14.8318 | 12.3747 |
158
+ | 2.0007 | 91.0 | 11466 | 2.1769 | 14.8061 | 12.4013 |
159
+ | 1.9967 | 92.0 | 11592 | 2.1757 | 14.8108 | 12.3843 |
160
+ | 1.9967 | 93.0 | 11718 | 2.1747 | 14.8036 | 12.379 |
161
+ | 1.9967 | 94.0 | 11844 | 2.1764 | 14.7447 | 12.3737 |
162
+ | 1.9967 | 95.0 | 11970 | 2.1759 | 14.7759 | 12.3875 |
163
+ | 1.9924 | 96.0 | 12096 | 2.1760 | 14.7695 | 12.3875 |
164
+ | 1.9924 | 97.0 | 12222 | 2.1762 | 14.8022 | 12.3769 |
165
+ | 1.9924 | 98.0 | 12348 | 2.1763 | 14.7519 | 12.3822 |
166
+ | 1.9924 | 99.0 | 12474 | 2.1760 | 14.7756 | 12.3832 |
167
+ | 1.9903 | 100.0 | 12600 | 2.1761 | 14.7713 | 12.3822 |
168
+
169
+
170
+ ### Framework versions
171
+
172
+ - Transformers 4.20.0.dev0
173
+ - Pytorch 1.8.0
174
+ - Datasets 2.1.0
175
+ - Tokenizers 0.12.1