End of training
Browse files- README.md +28 -9
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -5,9 +5,24 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: image_classification
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -17,13 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
-
|
| 21 |
-
-
|
| 22 |
-
- eval_runtime: 137.4967
|
| 23 |
-
- eval_samples_per_second: 1.164
|
| 24 |
-
- eval_steps_per_second: 0.073
|
| 25 |
-
- epoch: 0.05
|
| 26 |
-
- step: 2
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -42,7 +52,7 @@ More information needed
|
|
| 42 |
### Training hyperparameters
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
-
- learning_rate:
|
| 46 |
- train_batch_size: 16
|
| 47 |
- eval_batch_size: 16
|
| 48 |
- seed: 42
|
|
@@ -50,6 +60,15 @@ The following hyperparameters were used during training:
|
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- num_epochs: 3
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
- Transformers 4.33.2
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: image_classification
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: imagefolder
|
| 18 |
+
type: imagefolder
|
| 19 |
+
config: default
|
| 20 |
+
split: train
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.46875
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.5552
|
| 36 |
+
- Accuracy: 0.4688
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 52 |
### Training hyperparameters
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 9e-05
|
| 56 |
- train_batch_size: 16
|
| 57 |
- eval_batch_size: 16
|
| 58 |
- seed: 42
|
|
|
|
| 60 |
- lr_scheduler_type: linear
|
| 61 |
- num_epochs: 3
|
| 62 |
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 67 |
+
| No log | 1.0 | 40 | 1.7654 | 0.3125 |
|
| 68 |
+
| No log | 2.0 | 80 | 1.5370 | 0.4813 |
|
| 69 |
+
| No log | 3.0 | 120 | 1.4791 | 0.4813 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
### Framework versions
|
| 73 |
|
| 74 |
- Transformers 4.33.2
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343284397
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3686aad629043a77221365e7289ad825723cee2487a49604df74e29db9f9ac84
|
| 3 |
size 343284397
|