Hugging Face's logo

bedus-creation
/
eng-limbu-t5-base-all-001

Text2Text Generation
Transformers
TensorFlow
t5
generated_from_keras_callback
Inference Endpoints
Model card Files Community
bedus-creation commited on
Commit
dfcc5e1
•
1 Parent(s): 6f913a8

Training in progress epoch 0

Browse files
Files changed (5) hide show
  1. README.md +6 -143
  2. config.json +1 -1
  3. tf_model.h5 +1 -1
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +4 -0
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: t5-base
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  # bedus-creation/eng-limbu-t5-base-all-001
15
 
16
- This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.8226
19
- - Validation Loss: 2.6325
20
- - Epoch: 137
21
 
22
  ## Model description
23
 
@@ -43,144 +43,7 @@ The following hyperparameters were used during training:
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
- | 7.2874 | 6.5633 | 0 |
47
- | 6.4232 | 6.1990 | 1 |
48
- | 6.1568 | 6.0153 | 2 |
49
- | 6.0061 | 5.8803 | 3 |
50
- | 5.9020 | 5.7640 | 4 |
51
- | 5.8048 | 5.6789 | 5 |
52
- | 5.6626 | 5.5948 | 6 |
53
- | 5.5848 | 5.5166 | 7 |
54
- | 5.5104 | 5.4389 | 8 |
55
- | 5.4123 | 5.3547 | 9 |
56
- | 5.3234 | 5.2776 | 10 |
57
- | 5.2340 | 5.2203 | 11 |
58
- | 5.1654 | 5.1697 | 12 |
59
- | 5.0841 | 5.1080 | 13 |
60
- | 4.9937 | 5.0664 | 14 |
61
- | 4.9113 | 5.0153 | 15 |
62
- | 4.8582 | 4.9646 | 16 |
63
- | 4.7942 | 4.9417 | 17 |
64
- | 4.7292 | 4.8847 | 18 |
65
- | 4.6360 | 4.8478 | 19 |
66
- | 4.5783 | 4.8167 | 20 |
67
- | 4.5391 | 4.7565 | 21 |
68
- | 4.4614 | 4.7051 | 22 |
69
- | 4.3773 | 4.6806 | 23 |
70
- | 4.3157 | 4.6535 | 24 |
71
- | 4.2730 | 4.6082 | 25 |
72
- | 4.2060 | 4.5799 | 26 |
73
- | 4.1279 | 4.5355 | 27 |
74
- | 4.0707 | 4.5202 | 28 |
75
- | 4.0216 | 4.4787 | 29 |
76
- | 3.9908 | 4.4401 | 30 |
77
- | 3.9034 | 4.4155 | 31 |
78
- | 3.8432 | 4.3823 | 32 |
79
- | 3.7864 | 4.3547 | 33 |
80
- | 3.7511 | 4.3313 | 34 |
81
- | 3.6824 | 4.3112 | 35 |
82
- | 3.6172 | 4.2764 | 36 |
83
- | 3.5942 | 4.2378 | 37 |
84
- | 3.5092 | 4.1943 | 38 |
85
- | 3.4827 | 4.1674 | 39 |
86
- | 3.4252 | 4.1349 | 40 |
87
- | 3.3630 | 4.1109 | 41 |
88
- | 3.3343 | 4.0672 | 42 |
89
- | 3.2801 | 4.0650 | 43 |
90
- | 3.2159 | 4.0524 | 44 |
91
- | 3.1785 | 4.0022 | 45 |
92
- | 3.1228 | 3.9873 | 46 |
93
- | 3.0704 | 3.9762 | 47 |
94
- | 3.0201 | 3.9244 | 48 |
95
- | 2.9825 | 3.9083 | 49 |
96
- | 2.9366 | 3.8723 | 50 |
97
- | 2.8811 | 3.8877 | 51 |
98
- | 2.8314 | 3.8137 | 52 |
99
- | 2.7829 | 3.7879 | 53 |
100
- | 2.7540 | 3.7691 | 54 |
101
- | 2.7024 | 3.7628 | 55 |
102
- | 2.6563 | 3.7334 | 56 |
103
- | 2.6096 | 3.7073 | 57 |
104
- | 2.5802 | 3.6936 | 58 |
105
- | 2.5430 | 3.6533 | 59 |
106
- | 2.5094 | 3.6374 | 60 |
107
- | 2.4740 | 3.6153 | 61 |
108
- | 2.4471 | 3.5830 | 62 |
109
- | 2.3820 | 3.5756 | 63 |
110
- | 2.3559 | 3.5195 | 64 |
111
- | 2.2974 | 3.5223 | 65 |
112
- | 2.2807 | 3.4774 | 66 |
113
- | 2.2312 | 3.4700 | 67 |
114
- | 2.2084 | 3.4522 | 68 |
115
- | 2.1697 | 3.4271 | 69 |
116
- | 2.1373 | 3.4175 | 70 |
117
- | 2.0972 | 3.3715 | 71 |
118
- | 2.0672 | 3.3515 | 72 |
119
- | 2.0228 | 3.3328 | 73 |
120
- | 1.9925 | 3.3276 | 74 |
121
- | 1.9623 | 3.2728 | 75 |
122
- | 1.9449 | 3.2553 | 76 |
123
- | 1.9007 | 3.2412 | 77 |
124
- | 1.8839 | 3.2152 | 78 |
125
- | 1.8487 | 3.1977 | 79 |
126
- | 1.8286 | 3.1870 | 80 |
127
- | 1.8008 | 3.1476 | 81 |
128
- | 1.7678 | 3.1412 | 82 |
129
- | 1.7306 | 3.1152 | 83 |
130
- | 1.7038 | 3.1064 | 84 |
131
- | 1.6817 | 3.0788 | 85 |
132
- | 1.6639 | 3.0666 | 86 |
133
- | 1.6280 | 3.0470 | 87 |
134
- | 1.5991 | 3.0384 | 88 |
135
- | 1.5706 | 3.0114 | 89 |
136
- | 1.5425 | 2.9920 | 90 |
137
- | 1.5268 | 2.9801 | 91 |
138
- | 1.5053 | 2.9711 | 92 |
139
- | 1.4853 | 2.9577 | 93 |
140
- | 1.4577 | 2.9318 | 94 |
141
- | 1.4283 | 2.9221 | 95 |
142
- | 1.4214 | 2.9050 | 96 |
143
- | 1.3879 | 2.8948 | 97 |
144
- | 1.3845 | 2.8711 | 98 |
145
- | 1.3533 | 2.8578 | 99 |
146
- | 1.3173 | 2.8623 | 100 |
147
- | 1.3351 | 2.8313 | 101 |
148
- | 1.2870 | 2.8154 | 102 |
149
- | 1.2675 | 2.8059 | 103 |
150
- | 1.2685 | 2.8006 | 104 |
151
- | 1.2394 | 2.7965 | 105 |
152
- | 1.2306 | 2.7801 | 106 |
153
- | 1.2128 | 2.7736 | 107 |
154
- | 1.1816 | 2.7579 | 108 |
155
- | 1.1840 | 2.7607 | 109 |
156
- | 1.1553 | 2.7330 | 110 |
157
- | 1.1401 | 2.7383 | 111 |
158
- | 1.1129 | 2.7264 | 112 |
159
- | 1.1071 | 2.7153 | 113 |
160
- | 1.1001 | 2.7166 | 114 |
161
- | 1.0730 | 2.7045 | 115 |
162
- | 1.0775 | 2.6979 | 116 |
163
- | 1.0503 | 2.6844 | 117 |
164
- | 1.0358 | 2.6796 | 118 |
165
- | 1.0197 | 2.6764 | 119 |
166
- | 1.0154 | 2.6817 | 120 |
167
- | 1.0029 | 2.6551 | 121 |
168
- | 0.9715 | 2.6581 | 122 |
169
- | 0.9633 | 2.6540 | 123 |
170
- | 0.9544 | 2.6502 | 124 |
171
- | 0.9475 | 2.6607 | 125 |
172
- | 0.9349 | 2.6438 | 126 |
173
- | 0.9166 | 2.6376 | 127 |
174
- | 0.9094 | 2.6522 | 128 |
175
- | 0.8969 | 2.6271 | 129 |
176
- | 0.9016 | 2.6322 | 130 |
177
- | 0.8777 | 2.6246 | 131 |
178
- | 0.8714 | 2.6267 | 132 |
179
- | 0.8560 | 2.6213 | 133 |
180
- | 0.8525 | 2.6302 | 134 |
181
- | 0.8437 | 2.6147 | 135 |
182
- | 0.8297 | 2.6206 | 136 |
183
- | 0.8226 | 2.6325 | 137 |
184
 
185
 
186
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: bedus-creation/eng-limbu-t5-base-all-001
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
 
13
 
14
  # bedus-creation/eng-limbu-t5-base-all-001
15
 
16
+ This model is a fine-tuned version of [bedus-creation/eng-limbu-t5-base-all-001](https://huggingface.co/bedus-creation/eng-limbu-t5-base-all-001) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 7.0062
19
+ - Validation Loss: 6.1115
20
+ - Epoch: 0
21
 
22
  ## Model description
23
 
 
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
+ | 7.0062 | 6.1115 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
 
48
 
49
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
 
1
  {
2
+ "_name_or_path": "bedus-creation/eng-limbu-t5-base-all-001",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a29600f81fc6902681902a3dc9be34b6cf781081cc2c3f4138720fbe18d11f0a
3
  size 1089544048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7282f3a27d16093cbcbc478f850aec7a9f61de4fa96b596a2ee0599dadce2285
3
  size 1089544048
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -104,8 +104,12 @@
104
  "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
  "extra_ids": 100,
 
107
  "model_max_length": 512,
108
  "pad_token": "<pad>",
 
109
  "tokenizer_class": "T5Tokenizer",
 
 
110
  "unk_token": "<unk>"
111
  }
 
104
  "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
  "extra_ids": 100,
107
+ "max_length": 128,
108
  "model_max_length": 512,
109
  "pad_token": "<pad>",
110
+ "stride": 0,
111
  "tokenizer_class": "T5Tokenizer",
112
+ "truncation_side": "right",
113
+ "truncation_strategy": "longest_first",
114
  "unk_token": "<unk>"
115
  }