Commit
•
01e5ee1
1
Parent(s):
e551554
Model save
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# florence2_lora_vqa
|
| 16 |
|
| 17 |
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.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -39,11 +41,15 @@ The following hyperparameters were used during training:
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
-
- num_epochs:
|
| 43 |
- mixed_precision_training: Native AMP
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
|
|
|
| 15 |
# florence2_lora_vqa
|
| 16 |
|
| 17 |
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.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 4.4793
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 20
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 51 |
+
| 5.1294 | 7.0423 | 500 | 4.7076 |
|
| 52 |
+
| 4.8355 | 14.0845 | 1000 | 4.4793 |
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|