metadata
library_name: transformers
license: mit
base_model: microsoft/Florence-2-large-ft
tags:
- image-text-to-text
- generated_from_trainer
model-index:
- name: florence_final
results: []
florence_final
This model is a fine-tuned version of microsoft/Florence-2-large-ft on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4388
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7274 | 1.0 | 153 | 2.4825 |
| 2.0884 | 2.0 | 306 | 2.1203 |
| 1.8651 | 3.0 | 459 | 1.9587 |
| 1.7054 | 4.0 | 612 | 1.8127 |
| 1.5836 | 5.0 | 765 | 1.7042 |
| 1.4901 | 6.0 | 918 | 1.6121 |
| 1.4098 | 7.0 | 1071 | 1.5336 |
| 1.3635 | 8.0 | 1224 | 1.4825 |
| 1.3231 | 9.0 | 1377 | 1.4545 |
| 1.296 | 10.0 | 1530 | 1.4388 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0