<!-- 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. -->
Albaran2.0
This model is a fine-tuned version of microsoft/layoutlmv3-base on the sroie dataset. It achieves the following results on the evaluation set:
- Loss: 0.0359
- Precision: 0.9283
- Recall: 0.9309
- F1: 0.9296
- Accuracy: 0.9909
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.72 | 100 | 0.2144 | 0.8984 | 0.8604 | 0.8790 | 0.9844 |
No log | 1.44 | 200 | 0.0730 | 0.9265 | 0.9069 | 0.9166 | 0.9893 |
No log | 2.16 | 300 | 0.0586 | 0.8984 | 0.8984 | 0.8984 | 0.9875 |
No log | 2.88 | 400 | 0.0413 | 0.9201 | 0.9252 | 0.9226 | 0.9907 |
0.2357 | 3.6 | 500 | 0.0435 | 0.9174 | 0.9238 | 0.9206 | 0.9900 |
0.2357 | 4.32 | 600 | 0.0373 | 0.9191 | 0.9295 | 0.9243 | 0.9907 |
0.2357 | 5.04 | 700 | 0.0406 | 0.9153 | 0.9295 | 0.9223 | 0.9902 |
0.2357 | 5.76 | 800 | 0.0353 | 0.9232 | 0.9323 | 0.9277 | 0.9909 |
0.2357 | 6.47 | 900 | 0.0354 | 0.9294 | 0.9281 | 0.9287 | 0.9914 |
0.0365 | 7.19 | 1000 | 0.0359 | 0.9283 | 0.9309 | 0.9296 | 0.9909 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2