Hugging Face's logo

tiagoblima
/
t5_base-qg-ap-test

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
tiagoblima commited on
Commit
ab5985e
•
1 Parent(s): e455bdd

Model save

Browse files
Files changed (2) hide show
  1. README.md +106 -13
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,10 +1,8 @@
1
  ---
2
  license: mit
3
- base_model: unicamp-dl/ptt5-base-t5-vocab
4
  tags:
5
  - generated_from_trainer
6
- datasets:
7
- - tiagoblima/qg_squad_v1_pt
8
  model-index:
9
  - name: t5_base-qg-ap-test
10
  results: []
@@ -15,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # t5_base-qg-ap-test
17
 
18
- This model is a fine-tuned version of [unicamp-dl/ptt5-base-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-base-t5-vocab) on the tiagoblima/qg_squad_v1_pt dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.1012
21
 
22
  ## Model description
23
 
@@ -37,22 +35,117 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 0.0001
40
- - train_batch_size: 32
41
- - eval_batch_size: 4
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
44
  - lr_scheduler_type: linear
45
- - num_epochs: 5.0
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 1.0561 | 1.0 | 1616 | 1.1371 |
52
- | 0.9695 | 2.0 | 3232 | 1.1090 |
53
- | 0.9111 | 3.0 | 4848 | 1.1012 |
54
- | 0.8691 | 4.0 | 6464 | 1.1012 |
55
- | 0.8543 | 5.0 | 8080 | 1.1036 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: unicamp-dl/ptt5-base-portuguese-vocab
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: t5_base-qg-ap-test
8
  results: []
 
13
 
14
  # t5_base-qg-ap-test
15
 
16
+ This model is a fine-tuned version of [unicamp-dl/ptt5-base-portuguese-vocab](https://huggingface.co/unicamp-dl/ptt5-base-portuguese-vocab) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0163
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.0001
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 100.0
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 1 | 12.8054 |
50
+ | No log | 2.0 | 2 | 10.7880 |
51
+ | No log | 3.0 | 3 | 8.8731 |
52
+ | No log | 4.0 | 4 | 7.4068 |
53
+ | No log | 5.0 | 5 | 6.4581 |
54
+ | No log | 6.0 | 6 | 5.6475 |
55
+ | No log | 7.0 | 7 | 4.9596 |
56
+ | No log | 8.0 | 8 | 4.5058 |
57
+ | No log | 9.0 | 9 | 4.0768 |
58
+ | No log | 10.0 | 10 | 3.7047 |
59
+ | No log | 11.0 | 11 | 3.4143 |
60
+ | No log | 12.0 | 12 | 3.1360 |
61
+ | No log | 13.0 | 13 | 2.8866 |
62
+ | No log | 14.0 | 14 | 2.6325 |
63
+ | No log | 15.0 | 15 | 2.3889 |
64
+ | No log | 16.0 | 16 | 2.1914 |
65
+ | No log | 17.0 | 17 | 2.0424 |
66
+ | No log | 18.0 | 18 | 1.9111 |
67
+ | No log | 19.0 | 19 | 1.7763 |
68
+ | No log | 20.0 | 20 | 1.6505 |
69
+ | No log | 21.0 | 21 | 1.5257 |
70
+ | No log | 22.0 | 22 | 1.4126 |
71
+ | No log | 23.0 | 23 | 1.3109 |
72
+ | No log | 24.0 | 24 | 1.2189 |
73
+ | No log | 25.0 | 25 | 1.1338 |
74
+ | No log | 26.0 | 26 | 1.0486 |
75
+ | No log | 27.0 | 27 | 0.9640 |
76
+ | No log | 28.0 | 28 | 0.8828 |
77
+ | No log | 29.0 | 29 | 0.8060 |
78
+ | No log | 30.0 | 30 | 0.7329 |
79
+ | No log | 31.0 | 31 | 0.6639 |
80
+ | No log | 32.0 | 32 | 0.6010 |
81
+ | No log | 33.0 | 33 | 0.5439 |
82
+ | No log | 34.0 | 34 | 0.4925 |
83
+ | No log | 35.0 | 35 | 0.4471 |
84
+ | No log | 36.0 | 36 | 0.4066 |
85
+ | No log | 37.0 | 37 | 0.3690 |
86
+ | No log | 38.0 | 38 | 0.3341 |
87
+ | No log | 39.0 | 39 | 0.3023 |
88
+ | No log | 40.0 | 40 | 0.2746 |
89
+ | No log | 41.0 | 41 | 0.2470 |
90
+ | No log | 42.0 | 42 | 0.2205 |
91
+ | No log | 43.0 | 43 | 0.1968 |
92
+ | No log | 44.0 | 44 | 0.1771 |
93
+ | No log | 45.0 | 45 | 0.1593 |
94
+ | No log | 46.0 | 46 | 0.1424 |
95
+ | No log | 47.0 | 47 | 0.1288 |
96
+ | No log | 48.0 | 48 | 0.1170 |
97
+ | No log | 49.0 | 49 | 0.1070 |
98
+ | No log | 50.0 | 50 | 0.0996 |
99
+ | No log | 51.0 | 51 | 0.0939 |
100
+ | No log | 52.0 | 52 | 0.0888 |
101
+ | No log | 53.0 | 53 | 0.0845 |
102
+ | No log | 54.0 | 54 | 0.0818 |
103
+ | No log | 55.0 | 55 | 0.0790 |
104
+ | No log | 56.0 | 56 | 0.0763 |
105
+ | No log | 57.0 | 57 | 0.0732 |
106
+ | No log | 58.0 | 58 | 0.0697 |
107
+ | No log | 59.0 | 59 | 0.0666 |
108
+ | No log | 60.0 | 60 | 0.0642 |
109
+ | No log | 61.0 | 61 | 0.0611 |
110
+ | No log | 62.0 | 62 | 0.0583 |
111
+ | No log | 63.0 | 63 | 0.0560 |
112
+ | No log | 64.0 | 64 | 0.0532 |
113
+ | No log | 65.0 | 65 | 0.0512 |
114
+ | No log | 66.0 | 66 | 0.0487 |
115
+ | No log | 67.0 | 67 | 0.0464 |
116
+ | No log | 68.0 | 68 | 0.0431 |
117
+ | No log | 69.0 | 69 | 0.0399 |
118
+ | No log | 70.0 | 70 | 0.0381 |
119
+ | No log | 71.0 | 71 | 0.0364 |
120
+ | No log | 72.0 | 72 | 0.0348 |
121
+ | No log | 73.0 | 73 | 0.0333 |
122
+ | No log | 74.0 | 74 | 0.0316 |
123
+ | No log | 75.0 | 75 | 0.0299 |
124
+ | No log | 76.0 | 76 | 0.0285 |
125
+ | No log | 77.0 | 77 | 0.0274 |
126
+ | No log | 78.0 | 78 | 0.0264 |
127
+ | No log | 79.0 | 79 | 0.0253 |
128
+ | No log | 80.0 | 80 | 0.0242 |
129
+ | No log | 81.0 | 81 | 0.0236 |
130
+ | No log | 82.0 | 82 | 0.0231 |
131
+ | No log | 83.0 | 83 | 0.0229 |
132
+ | No log | 84.0 | 84 | 0.0226 |
133
+ | No log | 85.0 | 85 | 0.0223 |
134
+ | No log | 86.0 | 86 | 0.0218 |
135
+ | No log | 87.0 | 87 | 0.0212 |
136
+ | No log | 88.0 | 88 | 0.0205 |
137
+ | No log | 89.0 | 89 | 0.0198 |
138
+ | No log | 90.0 | 90 | 0.0192 |
139
+ | No log | 91.0 | 91 | 0.0186 |
140
+ | No log | 92.0 | 92 | 0.0181 |
141
+ | No log | 93.0 | 93 | 0.0177 |
142
+ | No log | 94.0 | 94 | 0.0173 |
143
+ | No log | 95.0 | 95 | 0.0170 |
144
+ | No log | 96.0 | 96 | 0.0168 |
145
+ | No log | 97.0 | 97 | 0.0166 |
146
+ | No log | 98.0 | 98 | 0.0165 |
147
+ | No log | 99.0 | 99 | 0.0164 |
148
+ | 1.4009 | 100.0 | 100 | 0.0163 |
149
 
150
 
151
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08ecf1636d4db21ae7426d593a9e53a49064e1ed62963bda0b8ba16f1bd2f023
3
  size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f757245857791afb85b1a23f04cbb12e94b3120026562125e00dd1227335ab56
3
  size 891644712