ansilmbabl
commited on
Commit
•
bc48e1f
1
Parent(s):
4e95b7a
Training in progress epoch 1
Browse files
.ipynb_checkpoints/README-checkpoint.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224-in21k
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: ansilmbabl/vit-base-patch16-224-in21k-Cards
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# ansilmbabl/vit-base-patch16-224-in21k-Cards
|
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 an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 1.3188
|
19 |
+
- Train Accuracy: 0.6043
|
20 |
+
- Train Top-3-accuracy: 0.8822
|
21 |
+
- Validation Loss: 0.8883
|
22 |
+
- Validation Accuracy: 0.7130
|
23 |
+
- Validation Top-3-accuracy: 0.9537
|
24 |
+
- Epoch: 0
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- optimizer: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 53200, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
|
44 |
+
- training_precision: mixed_float16
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
|
49 |
+
|:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
|
50 |
+
| 1.3188 | 0.6043 | 0.8822 | 0.8883 | 0.7130 | 0.9537 | 0 |
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- Transformers 4.41.2
|
56 |
+
- TensorFlow 2.14.0
|
57 |
+
- Datasets 2.19.1
|
58 |
+
- Tokenizers 0.19.1
|
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "Grade_08",
|
13 |
+
"1": "Grade_09",
|
14 |
+
"2": "Grade_02",
|
15 |
+
"3": "Grade_06",
|
16 |
+
"4": "Grade_04",
|
17 |
+
"5": "Grade_10",
|
18 |
+
"6": "Grade_05",
|
19 |
+
"7": "Grade_07",
|
20 |
+
"8": "Grade_03",
|
21 |
+
"9": "Grade_01"
|
22 |
+
},
|
23 |
+
"image_size": 224,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"Grade_01": "9",
|
28 |
+
"Grade_02": "2",
|
29 |
+
"Grade_03": "8",
|
30 |
+
"Grade_04": "4",
|
31 |
+
"Grade_05": "6",
|
32 |
+
"Grade_06": "3",
|
33 |
+
"Grade_07": "7",
|
34 |
+
"Grade_08": "0",
|
35 |
+
"Grade_09": "1",
|
36 |
+
"Grade_10": "5"
|
37 |
+
},
|
38 |
+
"layer_norm_eps": 1e-12,
|
39 |
+
"model_type": "vit",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"patch_size": 16,
|
44 |
+
"qkv_bias": true,
|
45 |
+
"transformers_version": "4.41.2"
|
46 |
+
}
|
README.md
CHANGED
@@ -15,13 +15,13 @@ probably proofread and complete it, then remove this comment. -->
|
|
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 an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
-
- Train Accuracy: 0.
|
20 |
-
- Train Top-3-accuracy: 0.
|
21 |
-
- Validation Loss: 0.
|
22 |
-
- Validation Accuracy: 0.
|
23 |
-
- Validation Top-3-accuracy: 0.
|
24 |
-
- Epoch:
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
|
|
48 |
| Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
|
49 |
|:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
|
50 |
| 1.3188 | 0.6043 | 0.8822 | 0.8883 | 0.7130 | 0.9537 | 0 |
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
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 an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.6864
|
19 |
+
- Train Accuracy: 0.7853
|
20 |
+
- Train Top-3-accuracy: 0.9705
|
21 |
+
- Validation Loss: 0.6807
|
22 |
+
- Validation Accuracy: 0.7647
|
23 |
+
- Validation Top-3-accuracy: 0.9650
|
24 |
+
- Epoch: 1
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
48 |
| Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
|
49 |
|:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
|
50 |
| 1.3188 | 0.6043 | 0.8822 | 0.8883 | 0.7130 | 0.9537 | 0 |
|
51 |
+
| 0.6864 | 0.7853 | 0.9705 | 0.6807 | 0.7647 | 0.9650 | 1 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
logs/train/events.out.tfevents.1717140134.e2e-60-58.11212.1.v2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cea82ffb16c5e6d065899285d1175aa6b332d9dfb0ef2b74ba31b074bc54100c
|
3 |
+
size 3388640
|
logs/validation/events.out.tfevents.1717140628.e2e-60-58.11212.2.v2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dc05908cdd64a602ebc38ea79006b6f052cde32a6fc5e97728f5564dea479d4
|
3 |
+
size 1064
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343510712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:119e0c028b2fc6faab292f5a5ac938f05d0a020e5e70c799eeee914173853b3e
|
3 |
size 343510712
|