Commit
•
c5a9ebb
1
Parent(s):
2be111c
Upload folder using huggingface_hub
Browse files- README.md +31 -0
- checkpoint-100/config.json +33 -0
- checkpoint-100/model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +418 -0
- checkpoint-100/training_args.bin +3 -0
- config.json +33 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Jul11_21-34-08_r-wendys-llc-autotrain-advanced-2t76ukwv-e008a-l1yrl/events.out.tfevents.1720733648.r-wendys-llc-autotrain-advanced-2t76ukwv-e008a-l1yrl.346.0 +2 -2
- runs/Jul11_21-34-08_r-wendys-llc-autotrain-advanced-2t76ukwv-e008a-l1yrl/events.out.tfevents.1720734720.r-wendys-llc-autotrain-advanced-2t76ukwv-e008a-l1yrl.346.1 +3 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- image-classification
|
6 |
+
base_model: google/vit-base-patch16-224
|
7 |
+
widget:
|
8 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
9 |
+
example_title: Tiger
|
10 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
|
11 |
+
example_title: Teapot
|
12 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
|
13 |
+
example_title: Palace
|
14 |
+
---
|
15 |
+
|
16 |
+
# Model Trained Using AutoTrain
|
17 |
+
|
18 |
+
- Problem type: Image Classification
|
19 |
+
|
20 |
+
## Validation Metrics
|
21 |
+
loss: 0.17235368490219116
|
22 |
+
|
23 |
+
f1: 0.94
|
24 |
+
|
25 |
+
precision: 0.94
|
26 |
+
|
27 |
+
recall: 0.94
|
28 |
+
|
29 |
+
auc: 0.9796
|
30 |
+
|
31 |
+
accuracy: 0.94
|
checkpoint-100/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"ViTForImageClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"encoder_stride": 16,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "negative",
|
14 |
+
"1": "positive"
|
15 |
+
},
|
16 |
+
"image_size": 224,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"negative": 0,
|
21 |
+
"positive": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"model_type": "vit",
|
25 |
+
"num_attention_heads": 12,
|
26 |
+
"num_channels": 3,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"patch_size": 16,
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"qkv_bias": true,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.42.2"
|
33 |
+
}
|
checkpoint-100/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfcbc3b1f90a6b8f1fd199d51e5b36d1d3f13ffa2fdbe505e4c97f8fd53b59cb
|
3 |
+
size 343223968
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e05d14e14e964f8656977b6833245df7185bf1f8861349504e4355b4fbc9e9e
|
3 |
+
size 686563258
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb265851bfe9ea76473c4ed187ad21806cefe6309d927f72d5a6466fbb18914a
|
3 |
+
size 13990
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7f13fa69fa5aededada161b8a9e4d59d1828d44ca7cd89db5434fe90d4bc5a9
|
3 |
+
size 1064
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,418 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.17235368490219116,
|
3 |
+
"best_model_checkpoint": "autotrain-dhurg-4zloz/checkpoint-100",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"grad_norm": 8.779764175415039,
|
14 |
+
"learning_rate": 6.666666666666667e-06,
|
15 |
+
"loss": 0.7021,
|
16 |
+
"step": 2
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.08,
|
20 |
+
"grad_norm": 11.571272850036621,
|
21 |
+
"learning_rate": 1.3333333333333333e-05,
|
22 |
+
"loss": 0.7476,
|
23 |
+
"step": 4
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.12,
|
27 |
+
"grad_norm": 7.2595109939575195,
|
28 |
+
"learning_rate": 2e-05,
|
29 |
+
"loss": 0.6407,
|
30 |
+
"step": 6
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.16,
|
34 |
+
"grad_norm": 22.257381439208984,
|
35 |
+
"learning_rate": 2.6666666666666667e-05,
|
36 |
+
"loss": 0.7677,
|
37 |
+
"step": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2,
|
41 |
+
"grad_norm": 9.527205467224121,
|
42 |
+
"learning_rate": 3.3333333333333335e-05,
|
43 |
+
"loss": 0.6452,
|
44 |
+
"step": 10
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24,
|
48 |
+
"grad_norm": 6.193709373474121,
|
49 |
+
"learning_rate": 4e-05,
|
50 |
+
"loss": 0.4157,
|
51 |
+
"step": 12
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.28,
|
55 |
+
"grad_norm": 8.290445327758789,
|
56 |
+
"learning_rate": 4.666666666666667e-05,
|
57 |
+
"loss": 0.6082,
|
58 |
+
"step": 14
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.32,
|
62 |
+
"grad_norm": 15.103638648986816,
|
63 |
+
"learning_rate": 4.962962962962963e-05,
|
64 |
+
"loss": 0.8635,
|
65 |
+
"step": 16
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.36,
|
69 |
+
"grad_norm": 9.055012702941895,
|
70 |
+
"learning_rate": 4.888888888888889e-05,
|
71 |
+
"loss": 0.4496,
|
72 |
+
"step": 18
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4,
|
76 |
+
"grad_norm": 7.674185276031494,
|
77 |
+
"learning_rate": 4.814814814814815e-05,
|
78 |
+
"loss": 0.4544,
|
79 |
+
"step": 20
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.44,
|
83 |
+
"grad_norm": 5.750149250030518,
|
84 |
+
"learning_rate": 4.740740740740741e-05,
|
85 |
+
"loss": 0.4023,
|
86 |
+
"step": 22
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.48,
|
90 |
+
"grad_norm": 9.68493938446045,
|
91 |
+
"learning_rate": 4.666666666666667e-05,
|
92 |
+
"loss": 0.4952,
|
93 |
+
"step": 24
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.52,
|
97 |
+
"grad_norm": 5.293528079986572,
|
98 |
+
"learning_rate": 4.592592592592593e-05,
|
99 |
+
"loss": 0.5546,
|
100 |
+
"step": 26
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.56,
|
104 |
+
"grad_norm": 7.6056647300720215,
|
105 |
+
"learning_rate": 4.518518518518519e-05,
|
106 |
+
"loss": 0.3908,
|
107 |
+
"step": 28
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6,
|
111 |
+
"grad_norm": 6.408599853515625,
|
112 |
+
"learning_rate": 4.4444444444444447e-05,
|
113 |
+
"loss": 0.2509,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.64,
|
118 |
+
"grad_norm": 6.033527374267578,
|
119 |
+
"learning_rate": 4.3703703703703705e-05,
|
120 |
+
"loss": 0.2029,
|
121 |
+
"step": 32
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.68,
|
125 |
+
"grad_norm": 11.087029457092285,
|
126 |
+
"learning_rate": 4.296296296296296e-05,
|
127 |
+
"loss": 0.5078,
|
128 |
+
"step": 34
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.72,
|
132 |
+
"grad_norm": 6.722639560699463,
|
133 |
+
"learning_rate": 4.222222222222222e-05,
|
134 |
+
"loss": 0.4449,
|
135 |
+
"step": 36
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.76,
|
139 |
+
"grad_norm": 5.349610805511475,
|
140 |
+
"learning_rate": 4.148148148148148e-05,
|
141 |
+
"loss": 0.3874,
|
142 |
+
"step": 38
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8,
|
146 |
+
"grad_norm": 7.29227352142334,
|
147 |
+
"learning_rate": 4.074074074074074e-05,
|
148 |
+
"loss": 0.5953,
|
149 |
+
"step": 40
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.84,
|
153 |
+
"grad_norm": 8.242330551147461,
|
154 |
+
"learning_rate": 4e-05,
|
155 |
+
"loss": 0.3056,
|
156 |
+
"step": 42
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.88,
|
160 |
+
"grad_norm": 3.6587088108062744,
|
161 |
+
"learning_rate": 3.925925925925926e-05,
|
162 |
+
"loss": 0.1099,
|
163 |
+
"step": 44
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.92,
|
167 |
+
"grad_norm": 3.0559661388397217,
|
168 |
+
"learning_rate": 3.851851851851852e-05,
|
169 |
+
"loss": 0.37,
|
170 |
+
"step": 46
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.96,
|
174 |
+
"grad_norm": 4.720924377441406,
|
175 |
+
"learning_rate": 3.777777777777778e-05,
|
176 |
+
"loss": 0.1703,
|
177 |
+
"step": 48
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.0,
|
181 |
+
"grad_norm": 3.9827725887298584,
|
182 |
+
"learning_rate": 3.7037037037037037e-05,
|
183 |
+
"loss": 0.3503,
|
184 |
+
"step": 50
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.0,
|
188 |
+
"eval_accuracy": 0.95,
|
189 |
+
"eval_auc": 0.964,
|
190 |
+
"eval_f1": 0.9494949494949495,
|
191 |
+
"eval_loss": 0.21780452132225037,
|
192 |
+
"eval_precision": 0.9591836734693877,
|
193 |
+
"eval_recall": 0.94,
|
194 |
+
"eval_runtime": 26.0018,
|
195 |
+
"eval_samples_per_second": 3.846,
|
196 |
+
"eval_steps_per_second": 0.269,
|
197 |
+
"step": 50
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.04,
|
201 |
+
"grad_norm": 2.406909465789795,
|
202 |
+
"learning_rate": 3.62962962962963e-05,
|
203 |
+
"loss": 0.1008,
|
204 |
+
"step": 52
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.08,
|
208 |
+
"grad_norm": 11.02933406829834,
|
209 |
+
"learning_rate": 3.555555555555556e-05,
|
210 |
+
"loss": 0.2756,
|
211 |
+
"step": 54
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 1.12,
|
215 |
+
"grad_norm": 8.120884895324707,
|
216 |
+
"learning_rate": 3.481481481481482e-05,
|
217 |
+
"loss": 0.2622,
|
218 |
+
"step": 56
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.16,
|
222 |
+
"grad_norm": 5.108714580535889,
|
223 |
+
"learning_rate": 3.4074074074074077e-05,
|
224 |
+
"loss": 0.1122,
|
225 |
+
"step": 58
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.2,
|
229 |
+
"grad_norm": 13.36482048034668,
|
230 |
+
"learning_rate": 3.3333333333333335e-05,
|
231 |
+
"loss": 0.2356,
|
232 |
+
"step": 60
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 1.24,
|
236 |
+
"grad_norm": 4.833813190460205,
|
237 |
+
"learning_rate": 3.25925925925926e-05,
|
238 |
+
"loss": 0.1811,
|
239 |
+
"step": 62
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.28,
|
243 |
+
"grad_norm": 4.81235933303833,
|
244 |
+
"learning_rate": 3.185185185185185e-05,
|
245 |
+
"loss": 0.1474,
|
246 |
+
"step": 64
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 1.32,
|
250 |
+
"grad_norm": 0.43874427676200867,
|
251 |
+
"learning_rate": 3.111111111111111e-05,
|
252 |
+
"loss": 0.2348,
|
253 |
+
"step": 66
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 1.3599999999999999,
|
257 |
+
"grad_norm": 1.1349278688430786,
|
258 |
+
"learning_rate": 3.037037037037037e-05,
|
259 |
+
"loss": 0.0234,
|
260 |
+
"step": 68
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.4,
|
264 |
+
"grad_norm": 2.6060400009155273,
|
265 |
+
"learning_rate": 2.962962962962963e-05,
|
266 |
+
"loss": 0.1018,
|
267 |
+
"step": 70
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.44,
|
271 |
+
"grad_norm": 6.894038200378418,
|
272 |
+
"learning_rate": 2.8888888888888888e-05,
|
273 |
+
"loss": 0.3433,
|
274 |
+
"step": 72
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 1.48,
|
278 |
+
"grad_norm": 0.4274143576622009,
|
279 |
+
"learning_rate": 2.814814814814815e-05,
|
280 |
+
"loss": 0.3128,
|
281 |
+
"step": 74
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.52,
|
285 |
+
"grad_norm": 4.964171886444092,
|
286 |
+
"learning_rate": 2.7407407407407408e-05,
|
287 |
+
"loss": 0.1867,
|
288 |
+
"step": 76
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 1.56,
|
292 |
+
"grad_norm": 3.660466194152832,
|
293 |
+
"learning_rate": 2.6666666666666667e-05,
|
294 |
+
"loss": 0.1936,
|
295 |
+
"step": 78
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 1.6,
|
299 |
+
"grad_norm": 9.657711029052734,
|
300 |
+
"learning_rate": 2.5925925925925925e-05,
|
301 |
+
"loss": 0.2673,
|
302 |
+
"step": 80
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.6400000000000001,
|
306 |
+
"grad_norm": 7.678964614868164,
|
307 |
+
"learning_rate": 2.5185185185185183e-05,
|
308 |
+
"loss": 0.2198,
|
309 |
+
"step": 82
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.6800000000000002,
|
313 |
+
"grad_norm": 2.8848860263824463,
|
314 |
+
"learning_rate": 2.4444444444444445e-05,
|
315 |
+
"loss": 0.2738,
|
316 |
+
"step": 84
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.72,
|
320 |
+
"grad_norm": 13.012591361999512,
|
321 |
+
"learning_rate": 2.3703703703703707e-05,
|
322 |
+
"loss": 0.2112,
|
323 |
+
"step": 86
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.76,
|
327 |
+
"grad_norm": 8.288191795349121,
|
328 |
+
"learning_rate": 2.2962962962962965e-05,
|
329 |
+
"loss": 0.1981,
|
330 |
+
"step": 88
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 1.8,
|
334 |
+
"grad_norm": 9.876968383789062,
|
335 |
+
"learning_rate": 2.2222222222222223e-05,
|
336 |
+
"loss": 0.3836,
|
337 |
+
"step": 90
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 1.8399999999999999,
|
341 |
+
"grad_norm": 0.2542683184146881,
|
342 |
+
"learning_rate": 2.148148148148148e-05,
|
343 |
+
"loss": 0.2617,
|
344 |
+
"step": 92
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.88,
|
348 |
+
"grad_norm": 1.3072165250778198,
|
349 |
+
"learning_rate": 2.074074074074074e-05,
|
350 |
+
"loss": 0.2146,
|
351 |
+
"step": 94
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 1.92,
|
355 |
+
"grad_norm": 5.043093681335449,
|
356 |
+
"learning_rate": 2e-05,
|
357 |
+
"loss": 0.0965,
|
358 |
+
"step": 96
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 1.96,
|
362 |
+
"grad_norm": 7.184999942779541,
|
363 |
+
"learning_rate": 1.925925925925926e-05,
|
364 |
+
"loss": 0.232,
|
365 |
+
"step": 98
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 2.0,
|
369 |
+
"grad_norm": 7.763317584991455,
|
370 |
+
"learning_rate": 1.8518518518518518e-05,
|
371 |
+
"loss": 0.3054,
|
372 |
+
"step": 100
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 2.0,
|
376 |
+
"eval_accuracy": 0.94,
|
377 |
+
"eval_auc": 0.9796,
|
378 |
+
"eval_f1": 0.94,
|
379 |
+
"eval_loss": 0.17235368490219116,
|
380 |
+
"eval_precision": 0.94,
|
381 |
+
"eval_recall": 0.94,
|
382 |
+
"eval_runtime": 24.1401,
|
383 |
+
"eval_samples_per_second": 4.142,
|
384 |
+
"eval_steps_per_second": 0.29,
|
385 |
+
"step": 100
|
386 |
+
}
|
387 |
+
],
|
388 |
+
"logging_steps": 2,
|
389 |
+
"max_steps": 150,
|
390 |
+
"num_input_tokens_seen": 0,
|
391 |
+
"num_train_epochs": 3,
|
392 |
+
"save_steps": 500,
|
393 |
+
"stateful_callbacks": {
|
394 |
+
"EarlyStoppingCallback": {
|
395 |
+
"args": {
|
396 |
+
"early_stopping_patience": 5,
|
397 |
+
"early_stopping_threshold": 0.01
|
398 |
+
},
|
399 |
+
"attributes": {
|
400 |
+
"early_stopping_patience_counter": 0
|
401 |
+
}
|
402 |
+
},
|
403 |
+
"TrainerControl": {
|
404 |
+
"args": {
|
405 |
+
"should_epoch_stop": false,
|
406 |
+
"should_evaluate": false,
|
407 |
+
"should_log": false,
|
408 |
+
"should_save": true,
|
409 |
+
"should_training_stop": false
|
410 |
+
},
|
411 |
+
"attributes": {}
|
412 |
+
}
|
413 |
+
},
|
414 |
+
"total_flos": 6.19935916916736e+16,
|
415 |
+
"train_batch_size": 8,
|
416 |
+
"trial_name": null,
|
417 |
+
"trial_params": null
|
418 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aac69707ce74ec40f025f7420488c7eff0af7ea496b999d721564f574e983363
|
3 |
+
size 5176
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"ViTForImageClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"encoder_stride": 16,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "negative",
|
14 |
+
"1": "positive"
|
15 |
+
},
|
16 |
+
"image_size": 224,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"negative": 0,
|
21 |
+
"positive": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"model_type": "vit",
|
25 |
+
"num_attention_heads": 12,
|
26 |
+
"num_channels": 3,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"patch_size": 16,
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"qkv_bias": true,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.42.2"
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfcbc3b1f90a6b8f1fd199d51e5b36d1d3f13ffa2fdbe505e4c97f8fd53b59cb
|
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": "ViTImageProcessor",
|
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/Jul11_21-34-08_r-wendys-llc-autotrain-advanced-2t76ukwv-e008a-l1yrl/events.out.tfevents.1720733648.r-wendys-llc-autotrain-advanced-2t76ukwv-e008a-l1yrl.346.0
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 sha256:21b66a0f96a961466d1956460475c7a6c8bd637cb6e61468574668370bdef6d2
|
3 |
+
size 22376
|
runs/Jul11_21-34-08_r-wendys-llc-autotrain-advanced-2t76ukwv-e008a-l1yrl/events.out.tfevents.1720734720.r-wendys-llc-autotrain-advanced-2t76ukwv-e008a-l1yrl.346.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:262cc8814107dc0371e492e9fcc04a085a8d9cd9e6f783b8befb7dcd22ed07bc
|
3 |
+
size 607
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aac69707ce74ec40f025f7420488c7eff0af7ea496b999d721564f574e983363
|
3 |
+
size 5176
|
training_params.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-dhurg-4zloz/autotrain-data",
|
3 |
+
"model": "google/vit-base-patch16-224",
|
4 |
+
"username": "wendys-llc",
|
5 |
+
"lr": 5e-05,
|
6 |
+
"epochs": 3,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"logging_steps": -1,
|
18 |
+
"project_name": "autotrain-dhurg-4zloz",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": "none",
|
21 |
+
"save_total_limit": 1,
|
22 |
+
"push_to_hub": true,
|
23 |
+
"eval_strategy": "epoch",
|
24 |
+
"image_column": "autotrain_image",
|
25 |
+
"target_column": "autotrain_label",
|
26 |
+
"log": "tensorboard",
|
27 |
+
"early_stopping_patience": 5,
|
28 |
+
"early_stopping_threshold": 0.01
|
29 |
+
}
|