Hugging Face's logo

DanSarm
/
receipt-core-model

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
DanSarm commited on
Commit
056de2e
·
verified ·
1 Parent(s): 3f16082

Training complete!

Browse files
Files changed (6) hide show
  1. README.md +106 -107
  2. config.json +2 -2
  3. generation_config.json +1 -1
  4. model.safetensors +1 -1
  5. special_tokens_map.json +21 -3
  6. tokenizer_config.json +7 -0
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
- base_model: t5-base
5
  tags:
6
  - generated_from_trainer
7
  model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # receipt-core-model
16
 
17
- This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.7190
20
 
21
  ## Model description
22
 
@@ -47,113 +47,112 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 3.0009 | 1.0 | 29 | 1.1423 |
51
- | 0.3485 | 2.0 | 58 | 1.1296 |
52
- | 0.1717 | 3.0 | 87 | 1.1880 |
53
- | 0.1204 | 4.0 | 116 | 1.2580 |
54
- | 0.0912 | 5.0 | 145 | 1.2250 |
55
- | 0.0801 | 6.0 | 174 | 1.3189 |
56
- | 0.0677 | 7.0 | 203 | 1.2968 |
57
- | 0.058 | 8.0 | 232 | 1.3284 |
58
- | 0.0517 | 9.0 | 261 | 1.3641 |
59
- | 0.0441 | 10.0 | 290 | 1.3873 |
60
- | 0.0404 | 11.0 | 319 | 1.4239 |
61
- | 0.0353 | 12.0 | 348 | 1.4632 |
62
- | 0.0324 | 13.0 | 377 | 1.4464 |
63
- | 0.0282 | 14.0 | 406 | 1.4695 |
64
- | 0.0248 | 15.0 | 435 | 1.4713 |
65
- | 0.0234 | 16.0 | 464 | 1.4474 |
66
- | 0.0228 | 17.0 | 493 | 1.4191 |
67
- | 0.0198 | 18.0 | 522 | 1.4753 |
68
- | 0.0203 | 19.0 | 551 | 1.5000 |
69
- | 0.0159 | 20.0 | 580 | 1.5167 |
70
- | 0.0163 | 21.0 | 609 | 1.4873 |
71
- | 0.0177 | 22.0 | 638 | 1.5335 |
72
- | 0.0153 | 23.0 | 667 | 1.4642 |
73
- | 0.0127 | 24.0 | 696 | 1.4740 |
74
- | 0.0118 | 25.0 | 725 | 1.4890 |
75
- | 0.0097 | 26.0 | 754 | 1.5592 |
76
- | 0.0087 | 27.0 | 783 | 1.5312 |
77
- | 0.008 | 28.0 | 812 | 1.5255 |
78
- | 0.0083 | 29.0 | 841 | 1.5413 |
79
- | 0.0082 | 30.0 | 870 | 1.5408 |
80
- | 0.007 | 31.0 | 899 | 1.5491 |
81
- | 0.006 | 32.0 | 928 | 1.5660 |
82
- | 0.0062 | 33.0 | 957 | 1.5685 |
83
- | 0.0053 | 34.0 | 986 | 1.5968 |
84
- | 0.0044 | 35.0 | 1015 | 1.5778 |
85
- | 0.0046 | 36.0 | 1044 | 1.5743 |
86
- | 0.0041 | 37.0 | 1073 | 1.6028 |
87
- | 0.0049 | 38.0 | 1102 | 1.5782 |
88
- | 0.004 | 39.0 | 1131 | 1.5704 |
89
- | 0.004 | 40.0 | 1160 | 1.5804 |
90
- | 0.0034 | 41.0 | 1189 | 1.5837 |
91
- | 0.0037 | 42.0 | 1218 | 1.5838 |
92
- | 0.0037 | 43.0 | 1247 | 1.6018 |
93
- | 0.0024 | 44.0 | 1276 | 1.5922 |
94
- | 0.0025 | 45.0 | 1305 | 1.5824 |
95
- | 0.0036 | 46.0 | 1334 | 1.5884 |
96
- | 0.0042 | 47.0 | 1363 | 1.5972 |
97
- | 0.0025 | 48.0 | 1392 | 1.5946 |
98
- | 0.0023 | 49.0 | 1421 | 1.5923 |
99
- | 0.0038 | 50.0 | 1450 | 1.6010 |
100
- | 0.0027 | 51.0 | 1479 | 1.5831 |
101
- | 0.0053 | 52.0 | 1508 | 1.6958 |
102
- | 0.0034 | 53.0 | 1537 | 1.6677 |
103
- | 0.003 | 54.0 | 1566 | 1.6849 |
104
- | 0.0023 | 55.0 | 1595 | 1.6919 |
105
- | 0.0027 | 56.0 | 1624 | 1.6944 |
106
- | 0.0023 | 57.0 | 1653 | 1.6739 |
107
- | 0.0024 | 58.0 | 1682 | 1.6647 |
108
- | 0.0018 | 59.0 | 1711 | 1.6915 |
109
- | 0.0016 | 60.0 | 1740 | 1.6705 |
110
- | 0.0021 | 61.0 | 1769 | 1.6920 |
111
- | 0.002 | 62.0 | 1798 | 1.6965 |
112
- | 0.002 | 63.0 | 1827 | 1.6271 |
113
- | 0.0017 | 64.0 | 1856 | 1.6795 |
114
- | 0.0019 | 65.0 | 1885 | 1.6736 |
115
- | 0.0016 | 66.0 | 1914 | 1.7282 |
116
- | 0.0025 | 67.0 | 1943 | 1.7446 |
117
- | 0.0018 | 68.0 | 1972 | 1.7058 |
118
- | 0.0025 | 69.0 | 2001 | 1.6667 |
119
- | 0.0022 | 70.0 | 2030 | 1.6680 |
120
- | 0.0024 | 71.0 | 2059 | 1.6693 |
121
- | 0.0016 | 72.0 | 2088 | 1.6961 |
122
- | 0.0026 | 73.0 | 2117 | 1.6914 |
123
- | 0.0013 | 74.0 | 2146 | 1.6961 |
124
- | 0.0013 | 75.0 | 2175 | 1.6985 |
125
- | 0.0008 | 76.0 | 2204 | 1.7127 |
126
- | 0.001 | 77.0 | 2233 | 1.7117 |
127
- | 0.0016 | 78.0 | 2262 | 1.6930 |
128
- | 0.0022 | 79.0 | 2291 | 1.7050 |
129
- | 0.001 | 80.0 | 2320 | 1.7253 |
130
- | 0.001 | 81.0 | 2349 | 1.7169 |
131
- | 0.0016 | 82.0 | 2378 | 1.7116 |
132
- | 0.0012 | 83.0 | 2407 | 1.7689 |
133
- | 0.0008 | 84.0 | 2436 | 1.8345 |
134
- | 0.0012 | 85.0 | 2465 | 1.8240 |
135
- | 0.0007 | 86.0 | 2494 | 1.7860 |
136
- | 0.0008 | 87.0 | 2523 | 1.7905 |
137
- | 0.0007 | 88.0 | 2552 | 1.7736 |
138
- | 0.001 | 89.0 | 2581 | 1.7675 |
139
- | 0.0029 | 90.0 | 2610 | 1.8951 |
140
- | 0.0021 | 91.0 | 2639 | 1.7821 |
141
- | 0.0023 | 92.0 | 2668 | 1.8104 |
142
- | 0.0018 | 93.0 | 2697 | 1.7326 |
143
- | 0.0014 | 94.0 | 2726 | 1.7357 |
144
- | 0.0012 | 95.0 | 2755 | 1.7611 |
145
- | 0.001 | 96.0 | 2784 | 1.6929 |
146
- | 0.0014 | 97.0 | 2813 | 1.7353 |
147
- | 0.0011 | 98.0 | 2842 | 1.7296 |
148
- | 0.0013 | 99.0 | 2871 | 1.6806 |
149
- | 0.0019 | 100.0 | 2900 | 1.7465 |
150
- | 0.0012 | 101.0 | 2929 | 1.7528 |
151
- | 0.0015 | 102.0 | 2958 | 1.7190 |
152
 
153
 
154
  ### Framework versions
155
 
156
- - Transformers 4.48.1
157
  - Pytorch 2.6.0+cu124
158
- - Datasets 3.2.0
159
  - Tokenizers 0.21.0
 
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: DanSarm/receipt-core-model
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
14
 
15
  # receipt-core-model
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: 1.2194
20
 
21
  ## Model description
22
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 0.1872 | 1.0 | 36 | 0.8766 |
51
+ | 0.1235 | 2.0 | 72 | 0.9059 |
52
+ | 0.0904 | 3.0 | 108 | 0.9360 |
53
+ | 0.0762 | 4.0 | 144 | 0.8768 |
54
+ | 0.0652 | 5.0 | 180 | 0.9361 |
55
+ | 0.054 | 6.0 | 216 | 0.9305 |
56
+ | 0.047 | 7.0 | 252 | 0.9453 |
57
+ | 0.0427 | 8.0 | 288 | 1.0083 |
58
+ | 0.0375 | 9.0 | 324 | 1.0142 |
59
+ | 0.0317 | 10.0 | 360 | 1.0458 |
60
+ | 0.0303 | 11.0 | 396 | 1.0515 |
61
+ | 0.0283 | 12.0 | 432 | 1.0791 |
62
+ | 0.0259 | 13.0 | 468 | 1.0594 |
63
+ | 0.0236 | 14.0 | 504 | 1.1078 |
64
+ | 0.0213 | 15.0 | 540 | 1.0250 |
65
+ | 0.0194 | 16.0 | 576 | 1.0492 |
66
+ | 0.0158 | 17.0 | 612 | 1.0782 |
67
+ | 0.016 | 18.0 | 648 | 1.1181 |
68
+ | 0.0135 | 19.0 | 684 | 1.1222 |
69
+ | 0.0138 | 20.0 | 720 | 1.1314 |
70
+ | 0.013 | 21.0 | 756 | 1.1197 |
71
+ | 0.0106 | 22.0 | 792 | 1.1216 |
72
+ | 0.0106 | 23.0 | 828 | 1.1382 |
73
+ | 0.0105 | 24.0 | 864 | 1.1542 |
74
+ | 0.0084 | 25.0 | 900 | 1.1758 |
75
+ | 0.0078 | 26.0 | 936 | 1.1630 |
76
+ | 0.0071 | 27.0 | 972 | 1.1524 |
77
+ | 0.007 | 28.0 | 1008 | 1.1615 |
78
+ | 0.0049 | 29.0 | 1044 | 1.1673 |
79
+ | 0.0062 | 30.0 | 1080 | 1.1623 |
80
+ | 0.0057 | 31.0 | 1116 | 1.1709 |
81
+ | 0.0046 | 32.0 | 1152 | 1.1976 |
82
+ | 0.0043 | 33.0 | 1188 | 1.2217 |
83
+ | 0.0035 | 34.0 | 1224 | 1.1863 |
84
+ | 0.0051 | 35.0 | 1260 | 1.2208 |
85
+ | 0.006 | 36.0 | 1296 | 1.1681 |
86
+ | 0.0044 | 37.0 | 1332 | 1.1783 |
87
+ | 0.0053 | 38.0 | 1368 | 1.1821 |
88
+ | 0.0049 | 39.0 | 1404 | 1.1724 |
89
+ | 0.0042 | 40.0 | 1440 | 1.1936 |
90
+ | 0.0031 | 41.0 | 1476 | 1.2066 |
91
+ | 0.0031 | 42.0 | 1512 | 1.2156 |
92
+ | 0.0039 | 43.0 | 1548 | 1.2054 |
93
+ | 0.0026 | 44.0 | 1584 | 1.2000 |
94
+ | 0.0028 | 45.0 | 1620 | 1.2259 |
95
+ | 0.0021 | 46.0 | 1656 | 1.2244 |
96
+ | 0.0026 | 47.0 | 1692 | 1.2218 |
97
+ | 0.0037 | 48.0 | 1728 | 1.2165 |
98
+ | 0.003 | 49.0 | 1764 | 1.2012 |
99
+ | 0.0021 | 50.0 | 1800 | 1.1950 |
100
+ | 0.0026 | 51.0 | 1836 | 1.2444 |
101
+ | 0.0024 | 52.0 | 1872 | 1.2066 |
102
+ | 0.0023 | 53.0 | 1908 | 1.2075 |
103
+ | 0.002 | 54.0 | 1944 | 1.2476 |
104
+ | 0.0016 | 55.0 | 1980 | 1.2365 |
105
+ | 0.0016 | 56.0 | 2016 | 1.2422 |
106
+ | 0.0014 | 57.0 | 2052 | 1.2420 |
107
+ | 0.0013 | 58.0 | 2088 | 1.2246 |
108
+ | 0.002 | 59.0 | 2124 | 1.2482 |
109
+ | 0.0014 | 60.0 | 2160 | 1.2752 |
110
+ | 0.0014 | 61.0 | 2196 | 1.2494 |
111
+ | 0.0013 | 62.0 | 2232 | 1.2648 |
112
+ | 0.0018 | 63.0 | 2268 | 1.2743 |
113
+ | 0.0027 | 64.0 | 2304 | 1.2162 |
114
+ | 0.0019 | 65.0 | 2340 | 1.2315 |
115
+ | 0.0016 | 66.0 | 2376 | 1.2573 |
116
+ | 0.0012 | 67.0 | 2412 | 1.2511 |
117
+ | 0.0018 | 68.0 | 2448 | 1.2632 |
118
+ | 0.0022 | 69.0 | 2484 | 1.2582 |
119
+ | 0.0015 | 70.0 | 2520 | 1.2676 |
120
+ | 0.0011 | 71.0 | 2556 | 1.2798 |
121
+ | 0.002 | 72.0 | 2592 | 1.2352 |
122
+ | 0.0012 | 73.0 | 2628 | 1.2430 |
123
+ | 0.0012 | 74.0 | 2664 | 1.2731 |
124
+ | 0.001 | 75.0 | 2700 | 1.2773 |
125
+ | 0.0009 | 76.0 | 2736 | 1.2506 |
126
+ | 0.001 | 77.0 | 2772 | 1.2479 |
127
+ | 0.0008 | 78.0 | 2808 | 1.2521 |
128
+ | 0.0008 | 79.0 | 2844 | 1.2630 |
129
+ | 0.0005 | 80.0 | 2880 | 1.2725 |
130
+ | 0.0009 | 81.0 | 2916 | 1.2539 |
131
+ | 0.0005 | 82.0 | 2952 | 1.2643 |
132
+ | 0.0007 | 83.0 | 2988 | 1.2722 |
133
+ | 0.001 | 84.0 | 3024 | 1.2690 |
134
+ | 0.0007 | 85.0 | 3060 | 1.2914 |
135
+ | 0.0006 | 86.0 | 3096 | 1.2911 |
136
+ | 0.0007 | 87.0 | 3132 | 1.2977 |
137
+ | 0.0007 | 88.0 | 3168 | 1.3432 |
138
+ | 0.0008 | 89.0 | 3204 | 1.3392 |
139
+ | 0.001 | 90.0 | 3240 | 1.2964 |
140
+ | 0.0023 | 91.0 | 3276 | 1.2660 |
141
+ | 0.0019 | 92.0 | 3312 | 1.2739 |
142
+ | 0.0017 | 93.0 | 3348 | 1.2968 |
143
+ | 0.0017 | 94.0 | 3384 | 1.3048 |
144
+ | 0.0014 | 95.0 | 3420 | 1.3139 |
145
+ | 0.0017 | 96.0 | 3456 | 1.3031 |
146
+ | 0.0012 | 97.0 | 3492 | 1.2952 |
147
+ | 0.0014 | 98.0 | 3528 | 1.3281 |
148
+ | 0.0021 | 99.0 | 3564 | 1.3087 |
149
+ | 0.0024 | 100.0 | 3600 | 1.2122 |
150
+ | 0.0028 | 101.0 | 3636 | 1.2194 |
 
151
 
152
 
153
  ### Framework versions
154
 
155
+ - Transformers 4.49.0
156
  - Pytorch 2.6.0+cu124
157
+ - Datasets 3.3.1
158
  - Tokenizers 0.21.0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
@@ -55,7 +55,7 @@
55
  }
56
  },
57
  "torch_dtype": "float32",
58
- "transformers_version": "4.48.1",
59
  "use_cache": true,
60
  "vocab_size": 32128
61
  }
 
1
  {
2
+ "_name_or_path": "DanSarm/receipt-core-model",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
 
55
  }
56
  },
57
  "torch_dtype": "float32",
58
+ "transformers_version": "4.49.0",
59
  "use_cache": true,
60
  "vocab_size": 32128
61
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "decoder_start_token_id": 0,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.48.1"
7
  }
 
3
  "decoder_start_token_id": 0,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.49.0"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd7bcb6ad9e7d60b0c6489d293117c073d237a52131d2180942d892b539bea58
3
  size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9701fd74590ae0cb21086d946f5fb645fee1f3b13d53fe0019abc2af87aac5
3
  size 891644712
special_tokens_map.json CHANGED
@@ -101,7 +101,25 @@
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
- "eos_token": "</s>",
105
- "pad_token": "<pad>",
106
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  }
 
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
  }
tokenizer_config.json CHANGED
@@ -932,8 +932,15 @@
932
  "eos_token": "</s>",
933
  "extra_ids": 100,
934
  "extra_special_tokens": {},
 
935
  "model_max_length": 1000000000000000019884624838656,
 
936
  "pad_token": "<pad>",
 
 
 
937
  "tokenizer_class": "T5Tokenizer",
 
 
938
  "unk_token": "<unk>"
939
  }
 
932
  "eos_token": "</s>",
933
  "extra_ids": 100,
934
  "extra_special_tokens": {},
935
+ "max_length": 128,
936
  "model_max_length": 1000000000000000019884624838656,
937
+ "pad_to_multiple_of": null,
938
  "pad_token": "<pad>",
939
+ "pad_token_type_id": 0,
940
+ "padding_side": "right",
941
+ "stride": 0,
942
  "tokenizer_class": "T5Tokenizer",
943
+ "truncation_side": "right",
944
+ "truncation_strategy": "longest_first",
945
  "unk_token": "<unk>"
946
  }