|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: microsoft/Florence-2-base-ft |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Florence-2-FT-JP-TF |
|
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. --> |
|
|
|
# Florence-2-FT-JP-TF |
|
|
|
This model is a fine-tuned version of [microsoft/Florence-2-base-ft](https://huggingface.co/microsoft/Florence-2-base-ft) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.2269 |
|
|
|
## 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: 7e-06 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- 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: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.4289 | 1.0 | 45 | 2.8658 | |
|
| 1.7576 | 2.0 | 90 | 2.8422 | |
|
| 1.4401 | 3.0 | 135 | 2.9391 | |
|
| 1.2229 | 4.0 | 180 | 2.9810 | |
|
| 1.0519 | 5.0 | 225 | 2.9622 | |
|
| 0.9047 | 6.0 | 270 | 3.0516 | |
|
| 0.8089 | 7.0 | 315 | 3.0336 | |
|
| 0.7068 | 8.0 | 360 | 3.0954 | |
|
| 0.6517 | 9.0 | 405 | 3.1408 | |
|
| 0.5915 | 10.0 | 450 | 3.1432 | |
|
| 0.5247 | 11.0 | 495 | 3.2247 | |
|
| 0.5032 | 12.0 | 540 | 3.2057 | |
|
| 0.4687 | 13.0 | 585 | 3.2391 | |
|
| 0.4615 | 14.0 | 630 | 3.2328 | |
|
| 0.4484 | 15.0 | 675 | 3.2269 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.3.0 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.20.3 |
|
|
