Hugging Face's logo

thezeivier
/
Grietas_10k-Fine-tuning

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Inference Endpoints
Model card Files Community
2
thezeivier commited on
Commit
dcd1ec7
•
1 Parent(s): 40e155e

End of training

Browse files
Files changed (2) hide show
  1. README.md +142 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: thezeivier/Grietas_10k
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: Grietas_10k-Fine-tuning
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Grietas_10k-Fine-tuning
17
+
18
+ This model is a fine-tuned version of [thezeivier/Grietas_10k](https://huggingface.co/thezeivier/Grietas_10k) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.3864
21
+ - Accuracy: 0.8860
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 80
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 320
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 100
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | No log | 0.8 | 2 | 1.3737 | 0.3679 |
56
+ | No log | 2.0 | 5 | 1.0234 | 0.6218 |
57
+ | No log | 2.8 | 7 | 0.8146 | 0.7254 |
58
+ | 1.0488 | 4.0 | 10 | 0.6621 | 0.7772 |
59
+ | 1.0488 | 4.8 | 12 | 0.6295 | 0.8031 |
60
+ | 1.0488 | 6.0 | 15 | 0.5390 | 0.8083 |
61
+ | 1.0488 | 6.8 | 17 | 0.4902 | 0.8290 |
62
+ | 0.4981 | 8.0 | 20 | 0.4645 | 0.8290 |
63
+ | 0.4981 | 8.8 | 22 | 0.4484 | 0.8497 |
64
+ | 0.4981 | 10.0 | 25 | 0.4543 | 0.8446 |
65
+ | 0.4981 | 10.8 | 27 | 0.4325 | 0.8394 |
66
+ | 0.3669 | 12.0 | 30 | 0.4210 | 0.8497 |
67
+ | 0.3669 | 12.8 | 32 | 0.4303 | 0.8342 |
68
+ | 0.3669 | 14.0 | 35 | 0.4170 | 0.8497 |
69
+ | 0.3669 | 14.8 | 37 | 0.3861 | 0.8601 |
70
+ | 0.2811 | 16.0 | 40 | 0.3629 | 0.8705 |
71
+ | 0.2811 | 16.8 | 42 | 0.3982 | 0.8653 |
72
+ | 0.2811 | 18.0 | 45 | 0.4492 | 0.8290 |
73
+ | 0.2811 | 18.8 | 47 | 0.4216 | 0.8342 |
74
+ | 0.2026 | 20.0 | 50 | 0.4614 | 0.8394 |
75
+ | 0.2026 | 20.8 | 52 | 0.4325 | 0.8446 |
76
+ | 0.2026 | 22.0 | 55 | 0.4755 | 0.8342 |
77
+ | 0.2026 | 22.8 | 57 | 0.4175 | 0.8394 |
78
+ | 0.1709 | 24.0 | 60 | 0.4175 | 0.8497 |
79
+ | 0.1709 | 24.8 | 62 | 0.4105 | 0.8446 |
80
+ | 0.1709 | 26.0 | 65 | 0.4140 | 0.8601 |
81
+ | 0.1709 | 26.8 | 67 | 0.4641 | 0.8394 |
82
+ | 0.1293 | 28.0 | 70 | 0.4214 | 0.8394 |
83
+ | 0.1293 | 28.8 | 72 | 0.3802 | 0.8808 |
84
+ | 0.1293 | 30.0 | 75 | 0.4875 | 0.8290 |
85
+ | 0.1293 | 30.8 | 77 | 0.3972 | 0.8705 |
86
+ | 0.1167 | 32.0 | 80 | 0.4853 | 0.8394 |
87
+ | 0.1167 | 32.8 | 82 | 0.4082 | 0.8549 |
88
+ | 0.1167 | 34.0 | 85 | 0.3917 | 0.8601 |
89
+ | 0.1167 | 34.8 | 87 | 0.3573 | 0.8653 |
90
+ | 0.1034 | 36.0 | 90 | 0.4312 | 0.8497 |
91
+ | 0.1034 | 36.8 | 92 | 0.4035 | 0.8497 |
92
+ | 0.1034 | 38.0 | 95 | 0.4413 | 0.8238 |
93
+ | 0.1034 | 38.8 | 97 | 0.4728 | 0.8446 |
94
+ | 0.0782 | 40.0 | 100 | 0.3977 | 0.8808 |
95
+ | 0.0782 | 40.8 | 102 | 0.3449 | 0.8912 |
96
+ | 0.0782 | 42.0 | 105 | 0.4146 | 0.8808 |
97
+ | 0.0782 | 42.8 | 107 | 0.4380 | 0.8601 |
98
+ | 0.083 | 44.0 | 110 | 0.4579 | 0.8497 |
99
+ | 0.083 | 44.8 | 112 | 0.5234 | 0.8549 |
100
+ | 0.083 | 46.0 | 115 | 0.4053 | 0.8756 |
101
+ | 0.083 | 46.8 | 117 | 0.4724 | 0.8394 |
102
+ | 0.0741 | 48.0 | 120 | 0.4631 | 0.8549 |
103
+ | 0.0741 | 48.8 | 122 | 0.4351 | 0.8653 |
104
+ | 0.0741 | 50.0 | 125 | 0.4191 | 0.8756 |
105
+ | 0.0741 | 50.8 | 127 | 0.3772 | 0.8964 |
106
+ | 0.067 | 52.0 | 130 | 0.3960 | 0.8808 |
107
+ | 0.067 | 52.8 | 132 | 0.3749 | 0.8964 |
108
+ | 0.067 | 54.0 | 135 | 0.4395 | 0.8653 |
109
+ | 0.067 | 54.8 | 137 | 0.5284 | 0.8342 |
110
+ | 0.0632 | 56.0 | 140 | 0.3332 | 0.8808 |
111
+ | 0.0632 | 56.8 | 142 | 0.4342 | 0.8497 |
112
+ | 0.0632 | 58.0 | 145 | 0.3986 | 0.8756 |
113
+ | 0.0632 | 58.8 | 147 | 0.4771 | 0.8549 |
114
+ | 0.063 | 60.0 | 150 | 0.4505 | 0.8497 |
115
+ | 0.063 | 60.8 | 152 | 0.4023 | 0.8653 |
116
+ | 0.063 | 62.0 | 155 | 0.5208 | 0.8290 |
117
+ | 0.063 | 62.8 | 157 | 0.4915 | 0.8601 |
118
+ | 0.0571 | 64.0 | 160 | 0.4412 | 0.8756 |
119
+ | 0.0571 | 64.8 | 162 | 0.4554 | 0.8653 |
120
+ | 0.0571 | 66.0 | 165 | 0.4318 | 0.8653 |
121
+ | 0.0571 | 66.8 | 167 | 0.4317 | 0.8549 |
122
+ | 0.0608 | 68.0 | 170 | 0.4509 | 0.8653 |
123
+ | 0.0608 | 68.8 | 172 | 0.4176 | 0.8705 |
124
+ | 0.0608 | 70.0 | 175 | 0.5203 | 0.8394 |
125
+ | 0.0608 | 70.8 | 177 | 0.4375 | 0.8756 |
126
+ | 0.0478 | 72.0 | 180 | 0.4196 | 0.8601 |
127
+ | 0.0478 | 72.8 | 182 | 0.4744 | 0.8601 |
128
+ | 0.0478 | 74.0 | 185 | 0.4362 | 0.8808 |
129
+ | 0.0478 | 74.8 | 187 | 0.4804 | 0.8653 |
130
+ | 0.0519 | 76.0 | 190 | 0.4861 | 0.8446 |
131
+ | 0.0519 | 76.8 | 192 | 0.4605 | 0.8601 |
132
+ | 0.0519 | 78.0 | 195 | 0.4730 | 0.8394 |
133
+ | 0.0519 | 78.8 | 197 | 0.4650 | 0.8705 |
134
+ | 0.0553 | 80.0 | 200 | 0.3864 | 0.8860 |
135
+
136
+
137
+ ### Framework versions
138
+
139
+ - Transformers 4.33.1
140
+ - Pytorch 2.0.1+cu118
141
+ - Datasets 2.14.5
142
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7816bb09828c652e81462211e0bf8b66f870edbb9ab478f5f908f23a68e5b8ed
3
  size 343271789
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5799b634a6a7efe451a996aa28dca4d875a22eb5bd9addc96b44dd8975c139e
3
  size 343271789