raffaelsiregar
commited on
Commit
•
ef86eab
1
Parent(s):
f4e046b
End of training
Browse files- .DS_Store +0 -0
- README.md +90 -0
- config.json +44 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
.DS_Store
ADDED
Binary file (10.2 kB). View file
|
|
README.md
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: google/vit-base-patch32-224-in21k
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- imagefolder
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: results
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Image Classification
|
16 |
+
type: image-classification
|
17 |
+
dataset:
|
18 |
+
name: imagefolder
|
19 |
+
type: imagefolder
|
20 |
+
config: default
|
21 |
+
split: train
|
22 |
+
args: default
|
23 |
+
metrics:
|
24 |
+
- name: Accuracy
|
25 |
+
type: accuracy
|
26 |
+
value: 0.45625
|
27 |
+
---
|
28 |
+
|
29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
30 |
+
should probably proofread and complete it, then remove this comment. -->
|
31 |
+
|
32 |
+
# results
|
33 |
+
|
34 |
+
This model is a fine-tuned version of [google/vit-base-patch32-224-in21k](https://huggingface.co/google/vit-base-patch32-224-in21k) on the imagefolder dataset.
|
35 |
+
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 1.4692
|
37 |
+
- Accuracy: 0.4562
|
38 |
+
|
39 |
+
## Model description
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Intended uses & limitations
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training and evaluation data
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training procedure
|
52 |
+
|
53 |
+
### Training hyperparameters
|
54 |
+
|
55 |
+
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 5e-05
|
57 |
+
- train_batch_size: 16
|
58 |
+
- eval_batch_size: 16
|
59 |
+
- seed: 42
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- num_epochs: 15
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 0.7426 | 1.0 | 40 | 1.4692 | 0.4562 |
|
69 |
+
| 0.4647 | 2.0 | 80 | 1.5033 | 0.4313 |
|
70 |
+
| 0.2527 | 3.0 | 120 | 1.5517 | 0.4813 |
|
71 |
+
| 0.1551 | 4.0 | 160 | 1.6071 | 0.4688 |
|
72 |
+
| 0.113 | 5.0 | 200 | 1.6474 | 0.475 |
|
73 |
+
| 0.0914 | 6.0 | 240 | 1.6752 | 0.45 |
|
74 |
+
| 0.0774 | 7.0 | 280 | 1.7003 | 0.45 |
|
75 |
+
| 0.0698 | 8.0 | 320 | 1.7336 | 0.4437 |
|
76 |
+
| 0.063 | 9.0 | 360 | 1.7595 | 0.45 |
|
77 |
+
| 0.0583 | 10.0 | 400 | 1.7778 | 0.4437 |
|
78 |
+
| 0.0551 | 11.0 | 440 | 1.7938 | 0.4375 |
|
79 |
+
| 0.0531 | 12.0 | 480 | 1.8082 | 0.4375 |
|
80 |
+
| 0.0509 | 13.0 | 520 | 1.8176 | 0.4437 |
|
81 |
+
| 0.0499 | 14.0 | 560 | 1.8230 | 0.4375 |
|
82 |
+
| 0.0494 | 15.0 | 600 | 1.8249 | 0.4375 |
|
83 |
+
|
84 |
+
|
85 |
+
### Framework versions
|
86 |
+
|
87 |
+
- Transformers 4.44.2
|
88 |
+
- Pytorch 2.4.1
|
89 |
+
- Datasets 2.21.0
|
90 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch32-224-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": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6",
|
19 |
+
"7": "LABEL_7"
|
20 |
+
},
|
21 |
+
"image_size": 224,
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"LABEL_0": 0,
|
26 |
+
"LABEL_1": 1,
|
27 |
+
"LABEL_2": 2,
|
28 |
+
"LABEL_3": 3,
|
29 |
+
"LABEL_4": 4,
|
30 |
+
"LABEL_5": 5,
|
31 |
+
"LABEL_6": 6,
|
32 |
+
"LABEL_7": 7
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-12,
|
35 |
+
"model_type": "vit",
|
36 |
+
"num_attention_heads": 12,
|
37 |
+
"num_channels": 3,
|
38 |
+
"num_hidden_layers": 12,
|
39 |
+
"patch_size": 32,
|
40 |
+
"problem_type": "single_label_classification",
|
41 |
+
"qkv_bias": true,
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.44.2"
|
44 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2177f6d98cbc8953ae47311f0d2b79bb08a9cd5f2584f0c412576677749c59d
|
3 |
+
size 349868752
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd73360147ebc99cf9b18797c73e3ca1b6a144dbe9fdefe8690a82c5b739003e
|
3 |
+
size 5112
|