peft-layoutlmv3-funsd-qlora
This model is a fine-tuned version of microsoft/layoutlmv3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.0049
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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.6989 | 1.0 | 10 | 5.5577 |
| 5.4696 | 2.0 | 20 | 5.3128 |
| 5.2744 | 3.0 | 30 | 5.0956 |
| 5.0226 | 4.0 | 40 | 4.9065 |
| 4.8749 | 5.0 | 50 | 4.7439 |
| 4.6347 | 6.0 | 60 | 4.6037 |
| 4.5816 | 7.0 | 70 | 4.4855 |
| 4.3609 | 8.0 | 80 | 4.3854 |
| 4.3679 | 9.0 | 90 | 4.3048 |
| 4.3488 | 10.0 | 100 | 4.2402 |
| 4.3586 | 11.0 | 110 | 4.1888 |
| 4.0728 | 12.0 | 120 | 4.1497 |
| 4.1782 | 13.0 | 130 | 4.1221 |
| 4.2597 | 14.0 | 140 | 4.1052 |
| 4.0004 | 15.0 | 150 | 4.0995 |
| 4.0238 | 16.0 | 160 | 4.0679 |
| 4.143 | 17.0 | 170 | 4.0406 |
| 3.9794 | 18.0 | 180 | 4.0210 |
| 4.1413 | 19.0 | 190 | 4.0091 |
| 3.9497 | 20.0 | 200 | 4.0049 |
Framework versions
- PEFT 0.17.1
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.3.0
- Tokenizers 0.22.1
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Razgulyaistan/peft-layoutlmv3-funsd-qlora
Base model
microsoft/layoutlmv3-base