Model save
Browse files
README.md
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/dinov2-base
|
| 4 |
tags:
|
|
@@ -22,7 +23,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -53,26 +54,35 @@ More information needed
|
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
- learning_rate: 5e-05
|
| 56 |
-
- train_batch_size:
|
| 57 |
-
- eval_batch_size:
|
| 58 |
- seed: 42
|
| 59 |
- gradient_accumulation_steps: 4
|
| 60 |
-
- total_train_batch_size:
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
- lr_scheduler_type: linear
|
| 63 |
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
-
- num_epochs:
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
-
| Training Loss | Epoch
|
| 69 |
-
|
| 70 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
|
| 72 |
|
| 73 |
### Framework versions
|
| 74 |
|
| 75 |
-
- Transformers 4.44.
|
| 76 |
-
- Pytorch 2.4.
|
| 77 |
- Datasets 2.21.0
|
| 78 |
- Tokenizers 0.19.1
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: transformers
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: facebook/dinov2-base
|
| 5 |
tags:
|
|
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
+
value: 0.9164021164021164
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.3027
|
| 37 |
+
- Accuracy: 0.9164
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 54 |
|
| 55 |
The following hyperparameters were used during training:
|
| 56 |
- learning_rate: 5e-05
|
| 57 |
+
- train_batch_size: 32
|
| 58 |
+
- eval_batch_size: 32
|
| 59 |
- seed: 42
|
| 60 |
- gradient_accumulation_steps: 4
|
| 61 |
+
- total_train_batch_size: 128
|
| 62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 63 |
- lr_scheduler_type: linear
|
| 64 |
- lr_scheduler_warmup_ratio: 0.1
|
| 65 |
+
- num_epochs: 10
|
| 66 |
|
| 67 |
### Training results
|
| 68 |
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 70 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 71 |
+
| 0.8554 | 0.9910 | 83 | 0.5252 | 0.8323 |
|
| 72 |
+
| 0.8162 | 1.9940 | 167 | 0.4597 | 0.8598 |
|
| 73 |
+
| 0.7303 | 2.9970 | 251 | 0.4403 | 0.8587 |
|
| 74 |
+
| 0.5644 | 4.0 | 335 | 0.3922 | 0.8746 |
|
| 75 |
+
| 0.5672 | 4.9910 | 418 | 0.3784 | 0.8857 |
|
| 76 |
+
| 0.454 | 5.9940 | 502 | 0.3856 | 0.8831 |
|
| 77 |
+
| 0.4379 | 6.9970 | 586 | 0.3510 | 0.8889 |
|
| 78 |
+
| 0.3356 | 8.0 | 670 | 0.3187 | 0.9063 |
|
| 79 |
+
| 0.2877 | 8.9910 | 753 | 0.3209 | 0.9116 |
|
| 80 |
+
| 0.2717 | 9.9104 | 830 | 0.3027 | 0.9164 |
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
| 84 |
|
| 85 |
+
- Transformers 4.44.2
|
| 86 |
+
- Pytorch 2.4.1+cu121
|
| 87 |
- Datasets 2.21.0
|
| 88 |
- Tokenizers 0.19.1
|