Natalia2314
commited on
Commit
•
f9cf1e6
1
Parent(s):
e5a8efb
cats_vs_dogs
Browse files- README.md +77 -0
- all_results.json +13 -0
- config.json +32 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Dec01_00-23-32_3e969321df64/events.out.tfevents.1701390262.3e969321df64.329.3 +3 -0
- runs/Dec01_00-23-32_3e969321df64/events.out.tfevents.1701398140.3e969321df64.329.4 +3 -0
- runs/Nov30_20-18-04_3e969321df64/events.out.tfevents.1701375911.3e969321df64.329.0 +3 -0
- runs/Nov30_21-13-42_3e969321df64/events.out.tfevents.1701378842.3e969321df64.329.1 +3 -0
- runs/Nov30_21-13-42_3e969321df64/events.out.tfevents.1701389962.3e969321df64.329.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +166 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224-in21k
|
4 |
+
tags:
|
5 |
+
- image-classification
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- cats_vs_dogs
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: vit-base-catsVSdogs-demo-v5
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Image Classification
|
16 |
+
type: image-classification
|
17 |
+
dataset:
|
18 |
+
name: cats_vs_dogs
|
19 |
+
type: cats_vs_dogs
|
20 |
+
config: default
|
21 |
+
split: train
|
22 |
+
args: default
|
23 |
+
metrics:
|
24 |
+
- name: Accuracy
|
25 |
+
type: accuracy
|
26 |
+
value: 0.98
|
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 |
+
# vit-base-catsVSdogs-demo-v5
|
33 |
+
|
34 |
+
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 cats_vs_dogs dataset.
|
35 |
+
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.0523
|
37 |
+
- Accuracy: 0.98
|
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: 0.0002
|
57 |
+
- train_batch_size: 16
|
58 |
+
- eval_batch_size: 8
|
59 |
+
- seed: 42
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- num_epochs: 4
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 0.0337 | 2.0 | 100 | 0.0523 | 0.98 |
|
69 |
+
| 0.0038 | 4.0 | 200 | 0.0591 | 0.985 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.35.2
|
75 |
+
- Pytorch 2.1.0+cu118
|
76 |
+
- Datasets 2.15.0
|
77 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.98,
|
4 |
+
"eval_loss": 0.05225329101085663,
|
5 |
+
"eval_runtime": 175.9654,
|
6 |
+
"eval_samples_per_second": 1.137,
|
7 |
+
"eval_steps_per_second": 0.142,
|
8 |
+
"total_flos": 2.479743667666944e+17,
|
9 |
+
"train_loss": 0.06029550410807133,
|
10 |
+
"train_runtime": 7671.8377,
|
11 |
+
"train_samples_per_second": 0.417,
|
12 |
+
"train_steps_per_second": 0.026
|
13 |
+
}
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "cat",
|
13 |
+
"1": "dog"
|
14 |
+
},
|
15 |
+
"image_size": 224,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"cat": "0",
|
20 |
+
"dog": "1"
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"model_type": "vit",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_channels": 3,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"patch_size": 16,
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"qkv_bias": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.35.2"
|
32 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.98,
|
4 |
+
"eval_loss": 0.05225329101085663,
|
5 |
+
"eval_runtime": 175.9654,
|
6 |
+
"eval_samples_per_second": 1.137,
|
7 |
+
"eval_steps_per_second": 0.142
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fdc26c6330a5962da28f0a8a0fbe978eb1b1522e09485599f832257fe48b6da
|
3 |
+
size 343223968
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTFeatureExtractor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
runs/Dec01_00-23-32_3e969321df64/events.out.tfevents.1701390262.3e969321df64.329.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f18e38e0467a82a193a9c2dd97d97fb8fc08d47f42a0e44890239b2ed6b00c85
|
3 |
+
size 8327
|
runs/Dec01_00-23-32_3e969321df64/events.out.tfevents.1701398140.3e969321df64.329.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dcc2d31a9e4ef0a5d4f26b35f681ec32669d72f5115fbc669c0483b656ad7b3
|
3 |
+
size 411
|
runs/Nov30_20-18-04_3e969321df64/events.out.tfevents.1701375911.3e969321df64.329.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:860d27fb56f61b3fcf5559c0b423e18a1ff0af63f2cec6ea922250ca73f875d1
|
3 |
+
size 5307
|
runs/Nov30_21-13-42_3e969321df64/events.out.tfevents.1701378842.3e969321df64.329.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7758e9e26de4e558b941bc5be5728f654c86134da04ecc06bf6a70c7e131b3d
|
3 |
+
size 13307
|
runs/Nov30_21-13-42_3e969321df64/events.out.tfevents.1701389962.3e969321df64.329.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0f78060d617d933b44d1698371a93c015ac2892e1acb961a53f9833a4624a9b
|
3 |
+
size 4323
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"total_flos": 2.479743667666944e+17,
|
4 |
+
"train_loss": 0.06029550410807133,
|
5 |
+
"train_runtime": 7671.8377,
|
6 |
+
"train_samples_per_second": 0.417,
|
7 |
+
"train_steps_per_second": 0.026
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,166 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.05225329101085663,
|
3 |
+
"best_model_checkpoint": "./vit-base-catsVSdogs-demo-v5/checkpoint-100",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.2,
|
13 |
+
"learning_rate": 0.00019,
|
14 |
+
"loss": 0.4108,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.4,
|
19 |
+
"learning_rate": 0.00018,
|
20 |
+
"loss": 0.1022,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.6,
|
25 |
+
"learning_rate": 0.00017,
|
26 |
+
"loss": 0.2383,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.8,
|
31 |
+
"learning_rate": 0.00016,
|
32 |
+
"loss": 0.1444,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.0,
|
37 |
+
"learning_rate": 0.00015000000000000001,
|
38 |
+
"loss": 0.0812,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.2,
|
43 |
+
"learning_rate": 0.00014,
|
44 |
+
"loss": 0.0268,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.4,
|
49 |
+
"learning_rate": 0.00013000000000000002,
|
50 |
+
"loss": 0.0375,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.6,
|
55 |
+
"learning_rate": 0.00012,
|
56 |
+
"loss": 0.0088,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.8,
|
61 |
+
"learning_rate": 0.00011000000000000002,
|
62 |
+
"loss": 0.0227,
|
63 |
+
"step": 90
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.0,
|
67 |
+
"learning_rate": 0.0001,
|
68 |
+
"loss": 0.0337,
|
69 |
+
"step": 100
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.0,
|
73 |
+
"eval_accuracy": 0.98,
|
74 |
+
"eval_loss": 0.05225329101085663,
|
75 |
+
"eval_runtime": 164.0992,
|
76 |
+
"eval_samples_per_second": 1.219,
|
77 |
+
"eval_steps_per_second": 0.152,
|
78 |
+
"step": 100
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 2.2,
|
82 |
+
"learning_rate": 9e-05,
|
83 |
+
"loss": 0.0065,
|
84 |
+
"step": 110
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 2.4,
|
88 |
+
"learning_rate": 8e-05,
|
89 |
+
"loss": 0.0055,
|
90 |
+
"step": 120
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.6,
|
94 |
+
"learning_rate": 7e-05,
|
95 |
+
"loss": 0.0179,
|
96 |
+
"step": 130
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 2.8,
|
100 |
+
"learning_rate": 6e-05,
|
101 |
+
"loss": 0.016,
|
102 |
+
"step": 140
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 3.0,
|
106 |
+
"learning_rate": 5e-05,
|
107 |
+
"loss": 0.0314,
|
108 |
+
"step": 150
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 3.2,
|
112 |
+
"learning_rate": 4e-05,
|
113 |
+
"loss": 0.0067,
|
114 |
+
"step": 160
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.4,
|
118 |
+
"learning_rate": 3e-05,
|
119 |
+
"loss": 0.004,
|
120 |
+
"step": 170
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 3.6,
|
124 |
+
"learning_rate": 2e-05,
|
125 |
+
"loss": 0.0041,
|
126 |
+
"step": 180
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 3.8,
|
130 |
+
"learning_rate": 1e-05,
|
131 |
+
"loss": 0.0039,
|
132 |
+
"step": 190
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 4.0,
|
136 |
+
"learning_rate": 0.0,
|
137 |
+
"loss": 0.0038,
|
138 |
+
"step": 200
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 4.0,
|
142 |
+
"eval_accuracy": 0.985,
|
143 |
+
"eval_loss": 0.059128113090991974,
|
144 |
+
"eval_runtime": 162.5287,
|
145 |
+
"eval_samples_per_second": 1.231,
|
146 |
+
"eval_steps_per_second": 0.154,
|
147 |
+
"step": 200
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 4.0,
|
151 |
+
"step": 200,
|
152 |
+
"total_flos": 2.479743667666944e+17,
|
153 |
+
"train_loss": 0.06029550410807133,
|
154 |
+
"train_runtime": 7671.8377,
|
155 |
+
"train_samples_per_second": 0.417,
|
156 |
+
"train_steps_per_second": 0.026
|
157 |
+
}
|
158 |
+
],
|
159 |
+
"logging_steps": 10,
|
160 |
+
"max_steps": 200,
|
161 |
+
"num_train_epochs": 4,
|
162 |
+
"save_steps": 100,
|
163 |
+
"total_flos": 2.479743667666944e+17,
|
164 |
+
"trial_name": null,
|
165 |
+
"trial_params": null
|
166 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0068cdc49051a47482a2c72986ff01979c70ff51c0addb896801168db347bb7d
|
3 |
+
size 4600
|