Augusto777
commited on
Commit
•
5ae3f0a
1
Parent(s):
4e9b3ff
End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/May23_20-13-11_DESKTOP-SKBE9FB/events.out.tfevents.1716517472.DESKTOP-SKBE9FB.10384.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +234 -0
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
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.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.8333333333333334
|
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: 0.5903
|
36 |
+
- Accuracy: 0.8333
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.87,
|
3 |
+
"eval_accuracy": 0.8333333333333334,
|
4 |
+
"eval_loss": 0.5903454422950745,
|
5 |
+
"eval_runtime": 1.5404,
|
6 |
+
"eval_samples_per_second": 38.951,
|
7 |
+
"eval_steps_per_second": 1.298,
|
8 |
+
"train_loss": 0.5296587021727311,
|
9 |
+
"train_runtime": 382.3327,
|
10 |
+
"train_samples_per_second": 64.08,
|
11 |
+
"train_steps_per_second": 0.497
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.87,
|
3 |
+
"eval_accuracy": 0.8333333333333334,
|
4 |
+
"eval_loss": 0.5903454422950745,
|
5 |
+
"eval_runtime": 1.5404,
|
6 |
+
"eval_samples_per_second": 38.951,
|
7 |
+
"eval_steps_per_second": 1.298
|
8 |
+
}
|
runs/May23_20-13-11_DESKTOP-SKBE9FB/events.out.tfevents.1716517472.DESKTOP-SKBE9FB.10384.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2af4171d33973d32537194096b3d21498f75c66e7383e8cd3f74701e78cbfb05
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.87,
|
3 |
+
"train_loss": 0.5296587021727311,
|
4 |
+
"train_runtime": 382.3327,
|
5 |
+
"train_samples_per_second": 64.08,
|
6 |
+
"train_steps_per_second": 0.497
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8333333333333334,
|
3 |
+
"best_model_checkpoint": "vit-base-patch16-224-RU4-10\\checkpoint-115",
|
4 |
+
"epoch": 9.87012987012987,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 190,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.52,
|
13 |
+
"learning_rate": 5.5e-05,
|
14 |
+
"loss": 1.37,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.99,
|
19 |
+
"eval_accuracy": 0.6166666666666667,
|
20 |
+
"eval_loss": 1.1940264701843262,
|
21 |
+
"eval_runtime": 1.217,
|
22 |
+
"eval_samples_per_second": 49.302,
|
23 |
+
"eval_steps_per_second": 1.643,
|
24 |
+
"step": 19
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.04,
|
28 |
+
"learning_rate": 5.1944444444444446e-05,
|
29 |
+
"loss": 1.2407,
|
30 |
+
"step": 20
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.56,
|
34 |
+
"learning_rate": 4.888888888888889e-05,
|
35 |
+
"loss": 1.1393,
|
36 |
+
"step": 30
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 1.97,
|
40 |
+
"eval_accuracy": 0.7,
|
41 |
+
"eval_loss": 0.9230659604072571,
|
42 |
+
"eval_runtime": 1.0004,
|
43 |
+
"eval_samples_per_second": 59.978,
|
44 |
+
"eval_steps_per_second": 1.999,
|
45 |
+
"step": 38
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 2.08,
|
49 |
+
"learning_rate": 4.5833333333333334e-05,
|
50 |
+
"loss": 0.9532,
|
51 |
+
"step": 40
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 2.6,
|
55 |
+
"learning_rate": 4.277777777777778e-05,
|
56 |
+
"loss": 0.8115,
|
57 |
+
"step": 50
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 2.96,
|
61 |
+
"eval_accuracy": 0.7666666666666667,
|
62 |
+
"eval_loss": 0.7923756837844849,
|
63 |
+
"eval_runtime": 0.9942,
|
64 |
+
"eval_samples_per_second": 60.348,
|
65 |
+
"eval_steps_per_second": 2.012,
|
66 |
+
"step": 57
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 3.12,
|
70 |
+
"learning_rate": 3.972222222222222e-05,
|
71 |
+
"loss": 0.6693,
|
72 |
+
"step": 60
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 3.64,
|
76 |
+
"learning_rate": 3.6666666666666666e-05,
|
77 |
+
"loss": 0.5507,
|
78 |
+
"step": 70
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 4.0,
|
82 |
+
"eval_accuracy": 0.75,
|
83 |
+
"eval_loss": 0.6691194176673889,
|
84 |
+
"eval_runtime": 1.017,
|
85 |
+
"eval_samples_per_second": 59.0,
|
86 |
+
"eval_steps_per_second": 1.967,
|
87 |
+
"step": 77
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.16,
|
91 |
+
"learning_rate": 3.3611111111111116e-05,
|
92 |
+
"loss": 0.473,
|
93 |
+
"step": 80
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 4.68,
|
97 |
+
"learning_rate": 3.055555555555556e-05,
|
98 |
+
"loss": 0.4093,
|
99 |
+
"step": 90
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 4.99,
|
103 |
+
"eval_accuracy": 0.8166666666666667,
|
104 |
+
"eval_loss": 0.6462448239326477,
|
105 |
+
"eval_runtime": 0.9981,
|
106 |
+
"eval_samples_per_second": 60.113,
|
107 |
+
"eval_steps_per_second": 2.004,
|
108 |
+
"step": 96
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 5.19,
|
112 |
+
"learning_rate": 2.75e-05,
|
113 |
+
"loss": 0.4008,
|
114 |
+
"step": 100
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 5.71,
|
118 |
+
"learning_rate": 2.4444444444444445e-05,
|
119 |
+
"loss": 0.2869,
|
120 |
+
"step": 110
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 5.97,
|
124 |
+
"eval_accuracy": 0.8333333333333334,
|
125 |
+
"eval_loss": 0.5903454422950745,
|
126 |
+
"eval_runtime": 1.0618,
|
127 |
+
"eval_samples_per_second": 56.506,
|
128 |
+
"eval_steps_per_second": 1.884,
|
129 |
+
"step": 115
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 6.23,
|
133 |
+
"learning_rate": 2.138888888888889e-05,
|
134 |
+
"loss": 0.2562,
|
135 |
+
"step": 120
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 6.75,
|
139 |
+
"learning_rate": 1.8333333333333333e-05,
|
140 |
+
"loss": 0.2347,
|
141 |
+
"step": 130
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 6.96,
|
145 |
+
"eval_accuracy": 0.7333333333333333,
|
146 |
+
"eval_loss": 0.7096327543258667,
|
147 |
+
"eval_runtime": 1.0505,
|
148 |
+
"eval_samples_per_second": 57.116,
|
149 |
+
"eval_steps_per_second": 1.904,
|
150 |
+
"step": 134
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 7.27,
|
154 |
+
"learning_rate": 1.527777777777778e-05,
|
155 |
+
"loss": 0.266,
|
156 |
+
"step": 140
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 7.79,
|
160 |
+
"learning_rate": 1.2222222222222222e-05,
|
161 |
+
"loss": 0.2148,
|
162 |
+
"step": 150
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 8.0,
|
166 |
+
"eval_accuracy": 0.7833333333333333,
|
167 |
+
"eval_loss": 0.636201024055481,
|
168 |
+
"eval_runtime": 1.1226,
|
169 |
+
"eval_samples_per_second": 53.447,
|
170 |
+
"eval_steps_per_second": 1.782,
|
171 |
+
"step": 154
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 8.31,
|
175 |
+
"learning_rate": 9.166666666666666e-06,
|
176 |
+
"loss": 0.1998,
|
177 |
+
"step": 160
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 8.83,
|
181 |
+
"learning_rate": 6.111111111111111e-06,
|
182 |
+
"loss": 0.1868,
|
183 |
+
"step": 170
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 8.99,
|
187 |
+
"eval_accuracy": 0.8,
|
188 |
+
"eval_loss": 0.6496174335479736,
|
189 |
+
"eval_runtime": 0.9902,
|
190 |
+
"eval_samples_per_second": 60.595,
|
191 |
+
"eval_steps_per_second": 2.02,
|
192 |
+
"step": 173
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 9.35,
|
196 |
+
"learning_rate": 3.0555555555555556e-06,
|
197 |
+
"loss": 0.2031,
|
198 |
+
"step": 180
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 9.87,
|
202 |
+
"learning_rate": 0.0,
|
203 |
+
"loss": 0.1977,
|
204 |
+
"step": 190
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 9.87,
|
208 |
+
"eval_accuracy": 0.7666666666666667,
|
209 |
+
"eval_loss": 0.6367517113685608,
|
210 |
+
"eval_runtime": 1.0025,
|
211 |
+
"eval_samples_per_second": 59.849,
|
212 |
+
"eval_steps_per_second": 1.995,
|
213 |
+
"step": 190
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 9.87,
|
217 |
+
"step": 190,
|
218 |
+
"total_flos": 1.8748748039526973e+18,
|
219 |
+
"train_loss": 0.5296587021727311,
|
220 |
+
"train_runtime": 382.3327,
|
221 |
+
"train_samples_per_second": 64.08,
|
222 |
+
"train_steps_per_second": 0.497
|
223 |
+
}
|
224 |
+
],
|
225 |
+
"logging_steps": 10,
|
226 |
+
"max_steps": 190,
|
227 |
+
"num_input_tokens_seen": 0,
|
228 |
+
"num_train_epochs": 10,
|
229 |
+
"save_steps": 500,
|
230 |
+
"total_flos": 1.8748748039526973e+18,
|
231 |
+
"train_batch_size": 32,
|
232 |
+
"trial_name": null,
|
233 |
+
"trial_params": null
|
234 |
+
}
|