Hugging Face's logo

phuong-tk-nguyen
/
vit-base-patch16-224-newly-trained

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
phuong-tk-nguyen commited on
Commit
7932d53
•
1 Parent(s): 75f5515

Model save

Browse files
Files changed (7) hide show
  1. README.md +10 -10
  2. all_results.json +13 -0
  3. eval_results.json +8 -0
  4. model.safetensors +1 -1
  5. train_results.json +8 -0
  6. trainer_state.json +133 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.961
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.2294
36
- - Accuracy: 0.961
37
 
38
  ## Model description
39
 
@@ -67,13 +67,13 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.1404 | 0.14 | 10 | 1.6121 | 0.629 |
71
- | 1.3709 | 0.28 | 20 | 0.8628 | 0.882 |
72
- | 0.8772 | 0.43 | 30 | 0.5010 | 0.933 |
73
- | 0.6335 | 0.57 | 40 | 0.3399 | 0.941 |
74
- | 0.5387 | 0.71 | 50 | 0.2673 | 0.957 |
75
- | 0.4319 | 0.85 | 60 | 0.2386 | 0.958 |
76
- | 0.4591 | 0.99 | 70 | 0.2294 | 0.961 |
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.964
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.1996
36
+ - Accuracy: 0.964
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 2.2183 | 0.14 | 10 | 1.6296 | 0.629 |
71
+ | 1.4213 | 0.28 | 20 | 0.8637 | 0.899 |
72
+ | 0.86 | 0.43 | 30 | 0.4598 | 0.949 |
73
+ | 0.614 | 0.57 | 40 | 0.2998 | 0.96 |
74
+ | 0.48 | 0.71 | 50 | 0.2337 | 0.967 |
75
+ | 0.4123 | 0.85 | 60 | 0.2091 | 0.964 |
76
+ | 0.4511 | 0.99 | 70 | 0.1996 | 0.964 |
77
 
78
 
79
  ### Framework versions
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.99,
3
+ "eval_accuracy": 0.961,
4
+ "eval_loss": 0.22941315174102783,
5
+ "eval_runtime": 11.2842,
6
+ "eval_samples_per_second": 88.619,
7
+ "eval_steps_per_second": 2.836,
8
+ "total_flos": 6.943780113009869e+17,
9
+ "train_loss": 0.9216747965131488,
10
+ "train_runtime": 351.6178,
11
+ "train_samples_per_second": 25.596,
12
+ "train_steps_per_second": 0.199
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.99,
3
+ "eval_accuracy": 0.961,
4
+ "eval_loss": 0.22941315174102783,
5
+ "eval_runtime": 11.2842,
6
+ "eval_samples_per_second": 88.619,
7
+ "eval_steps_per_second": 2.836
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c1d3344cb6f688bef2005b840122991e6eb416c3aed97011c88c32db46c6d00
3
  size 343248584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22041648b91886b95200463dccd51b15e6aa267845bb89f6e6a13ada4628b404
3
  size 343248584
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.99,
3
+ "total_flos": 6.943780113009869e+17,
4
+ "train_loss": 0.9216747965131488,
5
+ "train_runtime": 351.6178,
6
+ "train_samples_per_second": 25.596,
7
+ "train_steps_per_second": 0.199
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9929078014184397,
5
+ "eval_steps": 10,
6
+ "global_step": 70,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14,
13
+ "learning_rate": 4.761904761904762e-05,
14
+ "loss": 2.1404,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.14,
19
+ "eval_accuracy": 0.629,
20
+ "eval_loss": 1.6121153831481934,
21
+ "eval_runtime": 10.809,
22
+ "eval_samples_per_second": 92.515,
23
+ "eval_steps_per_second": 2.96,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.28,
28
+ "learning_rate": 3.968253968253968e-05,
29
+ "loss": 1.3709,
30
+ "step": 20
31
+ },
32
+ {
33
+ "epoch": 0.28,
34
+ "eval_accuracy": 0.882,
35
+ "eval_loss": 0.8628067374229431,
36
+ "eval_runtime": 10.9181,
37
+ "eval_samples_per_second": 91.591,
38
+ "eval_steps_per_second": 2.931,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.43,
43
+ "learning_rate": 3.1746031746031745e-05,
44
+ "loss": 0.8772,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.43,
49
+ "eval_accuracy": 0.933,
50
+ "eval_loss": 0.5010371208190918,
51
+ "eval_runtime": 11.2214,
52
+ "eval_samples_per_second": 89.116,
53
+ "eval_steps_per_second": 2.852,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.57,
58
+ "learning_rate": 2.380952380952381e-05,
59
+ "loss": 0.6335,
60
+ "step": 40
61
+ },
62
+ {
63
+ "epoch": 0.57,
64
+ "eval_accuracy": 0.941,
65
+ "eval_loss": 0.33985650539398193,
66
+ "eval_runtime": 11.3617,
67
+ "eval_samples_per_second": 88.015,
68
+ "eval_steps_per_second": 2.816,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.71,
73
+ "learning_rate": 1.5873015873015872e-05,
74
+ "loss": 0.5387,
75
+ "step": 50
76
+ },
77
+ {
78
+ "epoch": 0.71,
79
+ "eval_accuracy": 0.957,
80
+ "eval_loss": 0.2673340439796448,
81
+ "eval_runtime": 11.4297,
82
+ "eval_samples_per_second": 87.492,
83
+ "eval_steps_per_second": 2.8,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.85,
88
+ "learning_rate": 7.936507936507936e-06,
89
+ "loss": 0.4319,
90
+ "step": 60
91
+ },
92
+ {
93
+ "epoch": 0.85,
94
+ "eval_accuracy": 0.958,
95
+ "eval_loss": 0.23862411081790924,
96
+ "eval_runtime": 11.48,
97
+ "eval_samples_per_second": 87.108,
98
+ "eval_steps_per_second": 2.787,
99
+ "step": 60
100
+ },
101
+ {
102
+ "epoch": 0.99,
103
+ "learning_rate": 0.0,
104
+ "loss": 0.4591,
105
+ "step": 70
106
+ },
107
+ {
108
+ "epoch": 0.99,
109
+ "eval_accuracy": 0.961,
110
+ "eval_loss": 0.22941315174102783,
111
+ "eval_runtime": 11.5406,
112
+ "eval_samples_per_second": 86.651,
113
+ "eval_steps_per_second": 2.773,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.99,
118
+ "step": 70,
119
+ "total_flos": 6.943780113009869e+17,
120
+ "train_loss": 0.9216747965131488,
121
+ "train_runtime": 351.6178,
122
+ "train_samples_per_second": 25.596,
123
+ "train_steps_per_second": 0.199
124
+ }
125
+ ],
126
+ "logging_steps": 10,
127
+ "max_steps": 70,
128
+ "num_train_epochs": 1,
129
+ "save_steps": 500,
130
+ "total_flos": 6.943780113009869e+17,
131
+ "trial_name": null,
132
+ "trial_params": null
133
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c6f908a9393c1e422f41765454f24fe07b5c1592f2eb96db894ddcead448b9
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b2e6abbd726168d94aecfe9672bd98e5da66a8e179ba776e9d740153742407
3
  size 4600