|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: DanSarm/receipt-core-model |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: receipt-construction-model |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# receipt-construction-model |
|
|
|
|
|
This model is a fine-tuned version of [DanSarm/receipt-core-model](https://huggingface.co/DanSarm/receipt-core-model) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2963 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 0.0001 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 500 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 1.1652 | 1.0 | 56 | 0.4196 | |
|
|
| 0.4227 | 2.0 | 112 | 0.2893 | |
|
|
| 0.3059 | 3.0 | 168 | 0.2561 | |
|
|
| 0.2414 | 4.0 | 224 | 0.2288 | |
|
|
| 0.2046 | 5.0 | 280 | 0.2278 | |
|
|
| 0.1767 | 6.0 | 336 | 0.2160 | |
|
|
| 0.1565 | 7.0 | 392 | 0.2124 | |
|
|
| 0.1384 | 8.0 | 448 | 0.2092 | |
|
|
| 0.1288 | 9.0 | 504 | 0.2077 | |
|
|
| 0.116 | 10.0 | 560 | 0.2103 | |
|
|
| 0.1069 | 11.0 | 616 | 0.2136 | |
|
|
| 0.0966 | 12.0 | 672 | 0.2215 | |
|
|
| 0.086 | 13.0 | 728 | 0.2201 | |
|
|
| 0.0822 | 14.0 | 784 | 0.2263 | |
|
|
| 0.0764 | 15.0 | 840 | 0.2314 | |
|
|
| 0.0697 | 16.0 | 896 | 0.2298 | |
|
|
| 0.0677 | 17.0 | 952 | 0.2316 | |
|
|
| 0.0623 | 18.0 | 1008 | 0.2306 | |
|
|
| 0.0588 | 19.0 | 1064 | 0.2467 | |
|
|
| 0.0555 | 20.0 | 1120 | 0.2432 | |
|
|
| 0.0518 | 21.0 | 1176 | 0.2484 | |
|
|
| 0.0488 | 22.0 | 1232 | 0.2570 | |
|
|
| 0.0453 | 23.0 | 1288 | 0.2377 | |
|
|
| 0.0452 | 24.0 | 1344 | 0.2531 | |
|
|
| 0.0399 | 25.0 | 1400 | 0.2538 | |
|
|
| 0.0347 | 26.0 | 1456 | 0.2529 | |
|
|
| 0.032 | 27.0 | 1512 | 0.2583 | |
|
|
| 0.0312 | 28.0 | 1568 | 0.2525 | |
|
|
| 0.0282 | 29.0 | 1624 | 0.2631 | |
|
|
| 0.0274 | 30.0 | 1680 | 0.2609 | |
|
|
| 0.0266 | 31.0 | 1736 | 0.2574 | |
|
|
| 0.0265 | 32.0 | 1792 | 0.2630 | |
|
|
| 0.0221 | 33.0 | 1848 | 0.2611 | |
|
|
| 0.0218 | 34.0 | 1904 | 0.2673 | |
|
|
| 0.0194 | 35.0 | 1960 | 0.2693 | |
|
|
| 0.0164 | 36.0 | 2016 | 0.2663 | |
|
|
| 0.0183 | 37.0 | 2072 | 0.2655 | |
|
|
| 0.0149 | 38.0 | 2128 | 0.2685 | |
|
|
| 0.0156 | 39.0 | 2184 | 0.2604 | |
|
|
| 0.0157 | 40.0 | 2240 | 0.2684 | |
|
|
| 0.0149 | 41.0 | 2296 | 0.2697 | |
|
|
| 0.0137 | 42.0 | 2352 | 0.2779 | |
|
|
| 0.0116 | 43.0 | 2408 | 0.2738 | |
|
|
| 0.0116 | 44.0 | 2464 | 0.2760 | |
|
|
| 0.011 | 45.0 | 2520 | 0.2824 | |
|
|
| 0.0109 | 46.0 | 2576 | 0.2894 | |
|
|
| 0.0094 | 47.0 | 2632 | 0.2818 | |
|
|
| 0.0098 | 48.0 | 2688 | 0.2885 | |
|
|
| 0.0089 | 49.0 | 2744 | 0.2850 | |
|
|
| 0.01 | 50.0 | 2800 | 0.2857 | |
|
|
| 0.0096 | 51.0 | 2856 | 0.2855 | |
|
|
| 0.0084 | 52.0 | 2912 | 0.2904 | |
|
|
| 0.0088 | 53.0 | 2968 | 0.2871 | |
|
|
| 0.0092 | 54.0 | 3024 | 0.2878 | |
|
|
| 0.008 | 55.0 | 3080 | 0.2876 | |
|
|
| 0.0072 | 56.0 | 3136 | 0.2904 | |
|
|
| 0.0073 | 57.0 | 3192 | 0.2808 | |
|
|
| 0.0065 | 58.0 | 3248 | 0.2978 | |
|
|
| 0.0059 | 59.0 | 3304 | 0.2963 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.4.1 |
|
|
- Tokenizers 0.21.1 |
|
|
|
