|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: microsoft/Florence-2-large-ft |
|
tags: |
|
- image-text-to-text |
|
- generated_from_trainer |
|
model-index: |
|
- name: created_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. --> |
|
|
|
# created_model |
|
|
|
This model is a fine-tuned version of [microsoft/Florence-2-large-ft](https://huggingface.co/microsoft/Florence-2-large-ft) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7657 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- optimizer: Use OptimizerNames.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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.5758 | 1.0 | 22 | 1.7627 | |
|
| 1.1636 | 2.0 | 44 | 2.3089 | |
|
| 0.9265 | 3.0 | 66 | 1.7357 | |
|
| 0.7011 | 4.0 | 88 | 1.6376 | |
|
| 0.6003 | 5.0 | 110 | 1.5972 | |
|
| 0.4465 | 6.0 | 132 | 1.9380 | |
|
| 0.2891 | 7.0 | 154 | 2.3485 | |
|
| 0.2896 | 8.0 | 176 | 1.7245 | |
|
| 0.2192 | 9.0 | 198 | 1.7667 | |
|
| 0.1263 | 10.0 | 220 | 1.7657 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.0 |
|
- Pytorch 2.3.1+cu121 |
|
- Tokenizers 0.20.2 |
|
|
