Hugging Face's logo

DanSarm
/
receipt-construction-model

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
1
DanSarm commited on
Commit
2c0f80a
·
verified ·
1 Parent(s): d2f3d85

Fine-tuned Construction Receipt Model

Browse files
Files changed (3) hide show
  1. README.md +71 -17
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
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: 0.7435
20
 
21
  ## Model description
22
 
@@ -35,31 +35,85 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0003
39
- - train_batch_size: 16
40
- - eval_batch_size: 16
41
  - seed: 42
42
- - gradient_accumulation_steps: 2
43
- - total_train_batch_size: 32
44
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
- - num_epochs: 20
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 4.0171 | 1.0 | 2 | 2.5465 |
54
- | 2.1463 | 2.0 | 4 | 1.9613 |
55
- | 1.6495 | 3.0 | 6 | 1.5790 |
56
- | 1.317 | 4.0 | 8 | 1.2996 |
57
- | 1.0697 | 5.0 | 10 | 1.0985 |
58
- | 0.9027 | 6.0 | 12 | 0.9597 |
59
- | 0.7894 | 7.0 | 14 | 0.8566 |
60
- | 0.7064 | 8.0 | 16 | 0.7940 |
61
- | 0.6629 | 9.0 | 18 | 0.7589 |
62
- | 0.629 | 10.0 | 20 | 0.7435 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
 
64
 
65
  ### 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: 0.5390
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
+ | 2.8325 | 1.0 | 10 | 1.3919 |
52
+ | 1.3984 | 2.0 | 20 | 0.9104 |
53
+ | 0.95 | 3.0 | 30 | 0.6835 |
54
+ | 0.7012 | 4.0 | 40 | 0.5888 |
55
+ | 0.5577 | 5.0 | 50 | 0.5169 |
56
+ | 0.4466 | 6.0 | 60 | 0.4848 |
57
+ | 0.3622 | 7.0 | 70 | 0.4670 |
58
+ | 0.3099 | 8.0 | 80 | 0.4516 |
59
+ | 0.2746 | 9.0 | 90 | 0.4427 |
60
+ | 0.2505 | 10.0 | 100 | 0.4373 |
61
+ | 0.2283 | 11.0 | 110 | 0.4302 |
62
+ | 0.1962 | 12.0 | 120 | 0.4325 |
63
+ | 0.1859 | 13.0 | 130 | 0.4373 |
64
+ | 0.1625 | 14.0 | 140 | 0.4457 |
65
+ | 0.1491 | 15.0 | 150 | 0.4275 |
66
+ | 0.1348 | 16.0 | 160 | 0.4265 |
67
+ | 0.1277 | 17.0 | 170 | 0.4267 |
68
+ | 0.112 | 18.0 | 180 | 0.4283 |
69
+ | 0.1081 | 19.0 | 190 | 0.4322 |
70
+ | 0.0908 | 20.0 | 200 | 0.4371 |
71
+ | 0.0827 | 21.0 | 210 | 0.4421 |
72
+ | 0.0882 | 22.0 | 220 | 0.4526 |
73
+ | 0.0764 | 23.0 | 230 | 0.4483 |
74
+ | 0.0705 | 24.0 | 240 | 0.4466 |
75
+ | 0.0701 | 25.0 | 250 | 0.4688 |
76
+ | 0.0597 | 26.0 | 260 | 0.4836 |
77
+ | 0.0536 | 27.0 | 270 | 0.4835 |
78
+ | 0.0488 | 28.0 | 280 | 0.4777 |
79
+ | 0.0552 | 29.0 | 290 | 0.4736 |
80
+ | 0.0507 | 30.0 | 300 | 0.4842 |
81
+ | 0.0464 | 31.0 | 310 | 0.4999 |
82
+ | 0.0412 | 32.0 | 320 | 0.4953 |
83
+ | 0.0421 | 33.0 | 330 | 0.4765 |
84
+ | 0.0326 | 34.0 | 340 | 0.4861 |
85
+ | 0.0378 | 35.0 | 350 | 0.4890 |
86
+ | 0.0318 | 36.0 | 360 | 0.5110 |
87
+ | 0.0356 | 37.0 | 370 | 0.5117 |
88
+ | 0.0345 | 38.0 | 380 | 0.4984 |
89
+ | 0.0313 | 39.0 | 390 | 0.5077 |
90
+ | 0.0283 | 40.0 | 400 | 0.5072 |
91
+ | 0.024 | 41.0 | 410 | 0.5087 |
92
+ | 0.024 | 42.0 | 420 | 0.5086 |
93
+ | 0.0185 | 43.0 | 430 | 0.5093 |
94
+ | 0.0216 | 44.0 | 440 | 0.5167 |
95
+ | 0.0192 | 45.0 | 450 | 0.5113 |
96
+ | 0.0223 | 46.0 | 460 | 0.4966 |
97
+ | 0.0192 | 47.0 | 470 | 0.4966 |
98
+ | 0.0143 | 48.0 | 480 | 0.5063 |
99
+ | 0.0197 | 49.0 | 490 | 0.4985 |
100
+ | 0.0143 | 50.0 | 500 | 0.4964 |
101
+ | 0.0168 | 51.0 | 510 | 0.5005 |
102
+ | 0.0181 | 52.0 | 520 | 0.5103 |
103
+ | 0.0183 | 53.0 | 530 | 0.5137 |
104
+ | 0.0164 | 54.0 | 540 | 0.5301 |
105
+ | 0.0142 | 55.0 | 550 | 0.5287 |
106
+ | 0.0161 | 56.0 | 560 | 0.5280 |
107
+ | 0.012 | 57.0 | 570 | 0.5203 |
108
+ | 0.0134 | 58.0 | 580 | 0.5198 |
109
+ | 0.0103 | 59.0 | 590 | 0.5242 |
110
+ | 0.0109 | 60.0 | 600 | 0.5235 |
111
+ | 0.0119 | 61.0 | 610 | 0.5179 |
112
+ | 0.0125 | 62.0 | 620 | 0.5245 |
113
+ | 0.0101 | 63.0 | 630 | 0.5353 |
114
+ | 0.012 | 64.0 | 640 | 0.5479 |
115
+ | 0.0106 | 65.0 | 650 | 0.5456 |
116
+ | 0.0097 | 66.0 | 660 | 0.5390 |
117
 
118
 
119
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd619dc300dd887b3caffd241d334862f7c2da82b80bda3a02660d6877fac7d5
3
  size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59506c55a03f42234fdc9f0f992c25226c2eed7286cbf835dd9b07a8b0e2b9e1
3
  size 891644712
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0d80b0af9f788d93aaf056a86ceafc9ba182f5cf4fdd2d3d18137a795c34e08
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b78e866639e360525130aceb768ecc0b4d5663acea3fae8b817631cb40018b73
3
  size 5432