Hugging Face's logo

DanSarm
/
receipt-operations-model

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
DanSarm commited on
Commit
e0f5db5
·
verified ·
1 Parent(s): b47dad6

Fine-tuned Construction Receipt Model

Browse files
Files changed (3) hide show
  1. README.md +88 -8
  2. model.safetensors +1 -1
  3. training_args.bin +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [DanSarm/receipt-core-model](https://huggingface.co/DanSarm/receipt-core-model) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 5.5149
20
 
21
  ## Model description
22
 
@@ -35,22 +35,102 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 5e-05
39
- - train_batch_size: 8
40
- - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - num_epochs: 3
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | No log | 1.0 | 2 | 7.6513 |
52
- | No log | 2.0 | 4 | 6.0836 |
53
- | No log | 3.0 | 6 | 5.5149 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [DanSarm/receipt-core-model](https://huggingface.co/DanSarm/receipt-core-model) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.1836
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
  - seed: 42
42
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 1000
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.8353 | 1.0 | 3 | 0.4787 |
52
+ | 0.5752 | 2.0 | 6 | 0.3820 |
53
+ | 0.44 | 3.0 | 9 | 0.3257 |
54
+ | 0.343 | 4.0 | 12 | 0.3046 |
55
+ | 0.2676 | 5.0 | 15 | 0.2868 |
56
+ | 0.2263 | 6.0 | 18 | 0.2429 |
57
+ | 0.2045 | 7.0 | 21 | 0.2125 |
58
+ | 0.1808 | 8.0 | 24 | 0.1952 |
59
+ | 0.1367 | 9.0 | 27 | 0.1801 |
60
+ | 0.1209 | 10.0 | 30 | 0.1740 |
61
+ | 0.1248 | 11.0 | 33 | 0.1752 |
62
+ | 0.097 | 12.0 | 36 | 0.1704 |
63
+ | 0.0811 | 13.0 | 39 | 0.1629 |
64
+ | 0.063 | 14.0 | 42 | 0.1592 |
65
+ | 0.0649 | 15.0 | 45 | 0.1565 |
66
+ | 0.0505 | 16.0 | 48 | 0.1559 |
67
+ | 0.0433 | 17.0 | 51 | 0.1588 |
68
+ | 0.0428 | 18.0 | 54 | 0.1630 |
69
+ | 0.0402 | 19.0 | 57 | 0.1624 |
70
+ | 0.0243 | 20.0 | 60 | 0.1595 |
71
+ | 0.0187 | 21.0 | 63 | 0.1589 |
72
+ | 0.0242 | 22.0 | 66 | 0.1659 |
73
+ | 0.0151 | 23.0 | 69 | 0.1704 |
74
+ | 0.022 | 24.0 | 72 | 0.1632 |
75
+ | 0.0141 | 25.0 | 75 | 0.1541 |
76
+ | 0.0148 | 26.0 | 78 | 0.1487 |
77
+ | 0.0165 | 27.0 | 81 | 0.1475 |
78
+ | 0.0116 | 28.0 | 84 | 0.1488 |
79
+ | 0.0072 | 29.0 | 87 | 0.1496 |
80
+ | 0.0107 | 30.0 | 90 | 0.1495 |
81
+ | 0.0078 | 31.0 | 93 | 0.1495 |
82
+ | 0.0076 | 32.0 | 96 | 0.1483 |
83
+ | 0.0093 | 33.0 | 99 | 0.1445 |
84
+ | 0.0047 | 34.0 | 102 | 0.1445 |
85
+ | 0.0074 | 35.0 | 105 | 0.1461 |
86
+ | 0.0073 | 36.0 | 108 | 0.1468 |
87
+ | 0.009 | 37.0 | 111 | 0.1482 |
88
+ | 0.0052 | 38.0 | 114 | 0.1516 |
89
+ | 0.0056 | 39.0 | 117 | 0.1539 |
90
+ | 0.0102 | 40.0 | 120 | 0.1570 |
91
+ | 0.007 | 41.0 | 123 | 0.1569 |
92
+ | 0.0063 | 42.0 | 126 | 0.1560 |
93
+ | 0.005 | 43.0 | 129 | 0.1568 |
94
+ | 0.0041 | 44.0 | 132 | 0.1583 |
95
+ | 0.0051 | 45.0 | 135 | 0.1603 |
96
+ | 0.0037 | 46.0 | 138 | 0.1613 |
97
+ | 0.0074 | 47.0 | 141 | 0.1615 |
98
+ | 0.0092 | 48.0 | 144 | 0.1595 |
99
+ | 0.0049 | 49.0 | 147 | 0.1569 |
100
+ | 0.0065 | 50.0 | 150 | 0.1545 |
101
+ | 0.0119 | 51.0 | 153 | 0.1520 |
102
+ | 0.0046 | 52.0 | 156 | 0.1504 |
103
+ | 0.0032 | 53.0 | 159 | 0.1500 |
104
+ | 0.0059 | 54.0 | 162 | 0.1503 |
105
+ | 0.0033 | 55.0 | 165 | 0.1492 |
106
+ | 0.0059 | 56.0 | 168 | 0.1453 |
107
+ | 0.0058 | 57.0 | 171 | 0.1474 |
108
+ | 0.0023 | 58.0 | 174 | 0.1503 |
109
+ | 0.0029 | 59.0 | 177 | 0.1545 |
110
+ | 0.0027 | 60.0 | 180 | 0.1593 |
111
+ | 0.0024 | 61.0 | 183 | 0.1630 |
112
+ | 0.004 | 62.0 | 186 | 0.1649 |
113
+ | 0.005 | 63.0 | 189 | 0.1657 |
114
+ | 0.0022 | 64.0 | 192 | 0.1658 |
115
+ | 0.0024 | 65.0 | 195 | 0.1652 |
116
+ | 0.0035 | 66.0 | 198 | 0.1659 |
117
+ | 0.0019 | 67.0 | 201 | 0.1674 |
118
+ | 0.0019 | 68.0 | 204 | 0.1690 |
119
+ | 0.0019 | 69.0 | 207 | 0.1706 |
120
+ | 0.0028 | 70.0 | 210 | 0.1716 |
121
+ | 0.0055 | 71.0 | 213 | 0.1728 |
122
+ | 0.0022 | 72.0 | 216 | 0.1734 |
123
+ | 0.0029 | 73.0 | 219 | 0.1742 |
124
+ | 0.0013 | 74.0 | 222 | 0.1749 |
125
+ | 0.0017 | 75.0 | 225 | 0.1750 |
126
+ | 0.0015 | 76.0 | 228 | 0.1756 |
127
+ | 0.0028 | 77.0 | 231 | 0.1780 |
128
+ | 0.0012 | 78.0 | 234 | 0.1807 |
129
+ | 0.0017 | 79.0 | 237 | 0.1827 |
130
+ | 0.0045 | 80.0 | 240 | 0.1837 |
131
+ | 0.0017 | 81.0 | 243 | 0.1840 |
132
+ | 0.0022 | 82.0 | 246 | 0.1841 |
133
+ | 0.0014 | 83.0 | 249 | 0.1836 |
134
 
135
 
136
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cd67950a31bd1d566516ed8a853137d022663df0d24cd6a37ac631cc021fafc
3
  size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12b792d04c7aa4254583efaf091df72b32fb25b0445996bea5b891eeb47ca28
3
  size 891644712
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fc44c112438c87b67652ae7a3a193cde9ddb53e263bf9e9f8791f87bb2c3d94
3
- size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2253c33e223c464dba0a7a9af2cef236304c1f38cd6915d3d894d937bc87941
3
+ size 5432