Model save
Browse files- README.md +3 -17
- config.json +0 -1
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -2,10 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
-
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
-
metrics:
|
| 8 |
-
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: test-hasy-7
|
| 11 |
results: []
|
|
@@ -16,10 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# test-hasy-7
|
| 18 |
|
| 19 |
-
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
|
| 20 |
-
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 3.4984
|
| 22 |
-
- Accuracy: 0.4200
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -44,19 +38,11 @@ The following hyperparameters were used during training:
|
|
| 44 |
- seed: 1787
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
-
- num_epochs:
|
| 48 |
-
|
| 49 |
-
### Training results
|
| 50 |
-
|
| 51 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 53 |
-
| 4.2372 | 1.0 | 541 | 3.7457 | 0.3680 |
|
| 54 |
-
| 3.7808 | 2.0 | 1082 | 3.4984 | 0.4200 |
|
| 55 |
-
|
| 56 |
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.38.2
|
| 60 |
-
- Pytorch 2.1
|
| 61 |
- Datasets 2.18.0
|
| 62 |
- Tokenizers 0.15.2
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: test-hasy-7
|
| 8 |
results: []
|
|
|
|
| 13 |
|
| 14 |
# test-hasy-7
|
| 15 |
|
| 16 |
+
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 None dataset.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 38 |
- seed: 1787
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
### Framework versions
|
| 44 |
|
| 45 |
- Transformers 4.38.2
|
| 46 |
+
- Pytorch 2.2.1+cu121
|
| 47 |
- Datasets 2.18.0
|
| 48 |
- Tokenizers 0.15.2
|
config.json
CHANGED
|
@@ -269,7 +269,6 @@
|
|
| 269 |
"num_channels": 3,
|
| 270 |
"num_hidden_layers": 12,
|
| 271 |
"patch_size": 16,
|
| 272 |
-
"problem_type": "single_label_classification",
|
| 273 |
"qkv_bias": true,
|
| 274 |
"torch_dtype": "float32",
|
| 275 |
"transformers_version": "4.38.2"
|
|
|
|
| 269 |
"num_channels": 3,
|
| 270 |
"num_hidden_layers": 12,
|
| 271 |
"patch_size": 16,
|
|
|
|
| 272 |
"qkv_bias": true,
|
| 273 |
"torch_dtype": "float32",
|
| 274 |
"transformers_version": "4.38.2"
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343599256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33d8d8a7ba448b1e784bd2f47271c3732c79b9a5764a8139895e1318743223e8
|
| 3 |
size 343599256
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ac8610844ee6bc37f742a1f9fc9262e3e5885253e099ff43f5d97d967a29b73
|
| 3 |
size 4856
|