Instructions to use DanSarm/receipt-construction-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DanSarm/receipt-construction-model with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("DanSarm/receipt-construction-model") model = AutoModelForSeq2SeqLM.from_pretrained("DanSarm/receipt-construction-model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Fine-tuned Construction Receipt Model
Browse files- README.md +60 -63
- model.safetensors +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.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -47,68 +47,65 @@ The following hyperparameters were used during training:
|
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
-
| 1.
|
| 51 |
-
| 0.
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.0149 | 41.0 |
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.01 | 50.0 |
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.0055 | 60.0 | 2640 | 0.2629 |
|
| 110 |
-
| 0.0071 | 61.0 | 2684 | 0.2608 |
|
| 111 |
-
| 0.007 | 62.0 | 2728 | 0.2616 |
|
| 112 |
|
| 113 |
|
| 114 |
### 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: 0.2963
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 1.1652 | 1.0 | 56 | 0.4196 |
|
| 51 |
+
| 0.4227 | 2.0 | 112 | 0.2893 |
|
| 52 |
+
| 0.3059 | 3.0 | 168 | 0.2561 |
|
| 53 |
+
| 0.2414 | 4.0 | 224 | 0.2288 |
|
| 54 |
+
| 0.2046 | 5.0 | 280 | 0.2278 |
|
| 55 |
+
| 0.1767 | 6.0 | 336 | 0.2160 |
|
| 56 |
+
| 0.1565 | 7.0 | 392 | 0.2124 |
|
| 57 |
+
| 0.1384 | 8.0 | 448 | 0.2092 |
|
| 58 |
+
| 0.1288 | 9.0 | 504 | 0.2077 |
|
| 59 |
+
| 0.116 | 10.0 | 560 | 0.2103 |
|
| 60 |
+
| 0.1069 | 11.0 | 616 | 0.2136 |
|
| 61 |
+
| 0.0966 | 12.0 | 672 | 0.2215 |
|
| 62 |
+
| 0.086 | 13.0 | 728 | 0.2201 |
|
| 63 |
+
| 0.0822 | 14.0 | 784 | 0.2263 |
|
| 64 |
+
| 0.0764 | 15.0 | 840 | 0.2314 |
|
| 65 |
+
| 0.0697 | 16.0 | 896 | 0.2298 |
|
| 66 |
+
| 0.0677 | 17.0 | 952 | 0.2316 |
|
| 67 |
+
| 0.0623 | 18.0 | 1008 | 0.2306 |
|
| 68 |
+
| 0.0588 | 19.0 | 1064 | 0.2467 |
|
| 69 |
+
| 0.0555 | 20.0 | 1120 | 0.2432 |
|
| 70 |
+
| 0.0518 | 21.0 | 1176 | 0.2484 |
|
| 71 |
+
| 0.0488 | 22.0 | 1232 | 0.2570 |
|
| 72 |
+
| 0.0453 | 23.0 | 1288 | 0.2377 |
|
| 73 |
+
| 0.0452 | 24.0 | 1344 | 0.2531 |
|
| 74 |
+
| 0.0399 | 25.0 | 1400 | 0.2538 |
|
| 75 |
+
| 0.0347 | 26.0 | 1456 | 0.2529 |
|
| 76 |
+
| 0.032 | 27.0 | 1512 | 0.2583 |
|
| 77 |
+
| 0.0312 | 28.0 | 1568 | 0.2525 |
|
| 78 |
+
| 0.0282 | 29.0 | 1624 | 0.2631 |
|
| 79 |
+
| 0.0274 | 30.0 | 1680 | 0.2609 |
|
| 80 |
+
| 0.0266 | 31.0 | 1736 | 0.2574 |
|
| 81 |
+
| 0.0265 | 32.0 | 1792 | 0.2630 |
|
| 82 |
+
| 0.0221 | 33.0 | 1848 | 0.2611 |
|
| 83 |
+
| 0.0218 | 34.0 | 1904 | 0.2673 |
|
| 84 |
+
| 0.0194 | 35.0 | 1960 | 0.2693 |
|
| 85 |
+
| 0.0164 | 36.0 | 2016 | 0.2663 |
|
| 86 |
+
| 0.0183 | 37.0 | 2072 | 0.2655 |
|
| 87 |
+
| 0.0149 | 38.0 | 2128 | 0.2685 |
|
| 88 |
+
| 0.0156 | 39.0 | 2184 | 0.2604 |
|
| 89 |
+
| 0.0157 | 40.0 | 2240 | 0.2684 |
|
| 90 |
+
| 0.0149 | 41.0 | 2296 | 0.2697 |
|
| 91 |
+
| 0.0137 | 42.0 | 2352 | 0.2779 |
|
| 92 |
+
| 0.0116 | 43.0 | 2408 | 0.2738 |
|
| 93 |
+
| 0.0116 | 44.0 | 2464 | 0.2760 |
|
| 94 |
+
| 0.011 | 45.0 | 2520 | 0.2824 |
|
| 95 |
+
| 0.0109 | 46.0 | 2576 | 0.2894 |
|
| 96 |
+
| 0.0094 | 47.0 | 2632 | 0.2818 |
|
| 97 |
+
| 0.0098 | 48.0 | 2688 | 0.2885 |
|
| 98 |
+
| 0.0089 | 49.0 | 2744 | 0.2850 |
|
| 99 |
+
| 0.01 | 50.0 | 2800 | 0.2857 |
|
| 100 |
+
| 0.0096 | 51.0 | 2856 | 0.2855 |
|
| 101 |
+
| 0.0084 | 52.0 | 2912 | 0.2904 |
|
| 102 |
+
| 0.0088 | 53.0 | 2968 | 0.2871 |
|
| 103 |
+
| 0.0092 | 54.0 | 3024 | 0.2878 |
|
| 104 |
+
| 0.008 | 55.0 | 3080 | 0.2876 |
|
| 105 |
+
| 0.0072 | 56.0 | 3136 | 0.2904 |
|
| 106 |
+
| 0.0073 | 57.0 | 3192 | 0.2808 |
|
| 107 |
+
| 0.0065 | 58.0 | 3248 | 0.2978 |
|
| 108 |
+
| 0.0059 | 59.0 | 3304 | 0.2963 |
|
|
|
|
|
|
|
|
|
|
| 109 |
|
| 110 |
|
| 111 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 891644712
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa1956500acf39eabf287ed1513f650a75f4782e4c8b2201596172620e722caa
|
| 3 |
size 891644712
|