howaboutyu
commited on
Commit
•
509fcf5
1
Parent(s):
324658e
End of training
Browse files- README.md +8 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/May22_14-34-34_DL-Station/events.out.tfevents.1716356265.DL-Station.2861848.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +266 -0
README.md
CHANGED
@@ -2,7 +2,11 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-base-patch16-224-in21k
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: vit-base-beans
|
8 |
results: []
|
@@ -13,7 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# vit-base-beans
|
15 |
|
16 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-base-patch16-224-in21k
|
4 |
tags:
|
5 |
+
- image-classification
|
6 |
+
- vision
|
7 |
- generated_from_trainer
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
model-index:
|
11 |
- name: vit-base-beans
|
12 |
results: []
|
|
|
17 |
|
18 |
# vit-base-beans
|
19 |
|
20 |
+
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 beans dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.1208
|
23 |
+
- Accuracy: 0.9774
|
24 |
|
25 |
## Model description
|
26 |
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.9774436090225563,
|
4 |
+
"eval_loss": 0.12084060162305832,
|
5 |
+
"eval_runtime": 1.7601,
|
6 |
+
"eval_samples_per_second": 75.563,
|
7 |
+
"eval_steps_per_second": 5.113,
|
8 |
+
"total_flos": 4.006371770595533e+17,
|
9 |
+
"train_loss": 0.29627929100623496,
|
10 |
+
"train_runtime": 105.6493,
|
11 |
+
"train_samples_per_second": 48.935,
|
12 |
+
"train_steps_per_second": 3.076
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.9774436090225563,
|
4 |
+
"eval_loss": 0.12084060162305832,
|
5 |
+
"eval_runtime": 1.7601,
|
6 |
+
"eval_samples_per_second": 75.563,
|
7 |
+
"eval_steps_per_second": 5.113
|
8 |
+
}
|
runs/May22_14-34-34_DL-Station/events.out.tfevents.1716356265.DL-Station.2861848.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fba878c917672a272d3c14776f47236cbdddf4b2abd4c96ec7fc4b10a6d46cd
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"total_flos": 4.006371770595533e+17,
|
4 |
+
"train_loss": 0.29627929100623496,
|
5 |
+
"train_runtime": 105.6493,
|
6 |
+
"train_samples_per_second": 48.935,
|
7 |
+
"train_steps_per_second": 3.076
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,266 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 325,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.15384615384615385,
|
13 |
+
"grad_norm": 1.6880494356155396,
|
14 |
+
"learning_rate": 1.9384615384615386e-05,
|
15 |
+
"loss": 1.0254,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3076923076923077,
|
20 |
+
"grad_norm": 1.6863218545913696,
|
21 |
+
"learning_rate": 1.876923076923077e-05,
|
22 |
+
"loss": 0.875,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.46153846153846156,
|
27 |
+
"grad_norm": 1.5608391761779785,
|
28 |
+
"learning_rate": 1.8153846153846155e-05,
|
29 |
+
"loss": 0.7825,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.6153846153846154,
|
34 |
+
"grad_norm": 1.4615881443023682,
|
35 |
+
"learning_rate": 1.753846153846154e-05,
|
36 |
+
"loss": 0.6326,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.7692307692307693,
|
41 |
+
"grad_norm": 2.1352627277374268,
|
42 |
+
"learning_rate": 1.6923076923076924e-05,
|
43 |
+
"loss": 0.5693,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.9230769230769231,
|
48 |
+
"grad_norm": 1.560471773147583,
|
49 |
+
"learning_rate": 1.630769230769231e-05,
|
50 |
+
"loss": 0.4709,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.0769230769230769,
|
55 |
+
"grad_norm": 1.3950369358062744,
|
56 |
+
"learning_rate": 1.5692307692307693e-05,
|
57 |
+
"loss": 0.4044,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.2307692307692308,
|
62 |
+
"grad_norm": 1.1524418592453003,
|
63 |
+
"learning_rate": 1.5076923076923078e-05,
|
64 |
+
"loss": 0.3491,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.3846153846153846,
|
69 |
+
"grad_norm": 1.3851335048675537,
|
70 |
+
"learning_rate": 1.4461538461538462e-05,
|
71 |
+
"loss": 0.3191,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.5384615384615383,
|
76 |
+
"grad_norm": 0.7817617654800415,
|
77 |
+
"learning_rate": 1.3846153846153847e-05,
|
78 |
+
"loss": 0.2975,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.6923076923076923,
|
83 |
+
"grad_norm": 2.4296486377716064,
|
84 |
+
"learning_rate": 1.3230769230769231e-05,
|
85 |
+
"loss": 0.2719,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.8461538461538463,
|
90 |
+
"grad_norm": 3.495382308959961,
|
91 |
+
"learning_rate": 1.2615384615384616e-05,
|
92 |
+
"loss": 0.2863,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.0,
|
97 |
+
"grad_norm": 0.9178031086921692,
|
98 |
+
"learning_rate": 1.2e-05,
|
99 |
+
"loss": 0.2066,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.1538461538461537,
|
104 |
+
"grad_norm": 1.042531967163086,
|
105 |
+
"learning_rate": 1.1384615384615385e-05,
|
106 |
+
"loss": 0.1934,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 2.3076923076923075,
|
111 |
+
"grad_norm": 2.2865443229675293,
|
112 |
+
"learning_rate": 1.076923076923077e-05,
|
113 |
+
"loss": 0.1905,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 2.4615384615384617,
|
118 |
+
"grad_norm": 2.3291144371032715,
|
119 |
+
"learning_rate": 1.0153846153846154e-05,
|
120 |
+
"loss": 0.2134,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 2.6153846153846154,
|
125 |
+
"grad_norm": 1.420284628868103,
|
126 |
+
"learning_rate": 9.53846153846154e-06,
|
127 |
+
"loss": 0.1895,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.769230769230769,
|
132 |
+
"grad_norm": 2.7554662227630615,
|
133 |
+
"learning_rate": 8.923076923076925e-06,
|
134 |
+
"loss": 0.1897,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 2.9230769230769234,
|
139 |
+
"grad_norm": 1.4687916040420532,
|
140 |
+
"learning_rate": 8.307692307692309e-06,
|
141 |
+
"loss": 0.1761,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 3.076923076923077,
|
146 |
+
"grad_norm": 3.535647392272949,
|
147 |
+
"learning_rate": 7.692307692307694e-06,
|
148 |
+
"loss": 0.1862,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 3.230769230769231,
|
153 |
+
"grad_norm": 3.035341739654541,
|
154 |
+
"learning_rate": 7.076923076923078e-06,
|
155 |
+
"loss": 0.1937,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 3.3846153846153846,
|
160 |
+
"grad_norm": 2.828181028366089,
|
161 |
+
"learning_rate": 6.461538461538463e-06,
|
162 |
+
"loss": 0.1407,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 3.5384615384615383,
|
167 |
+
"grad_norm": 2.125542163848877,
|
168 |
+
"learning_rate": 5.846153846153847e-06,
|
169 |
+
"loss": 0.1338,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 3.6923076923076925,
|
174 |
+
"grad_norm": 1.5795857906341553,
|
175 |
+
"learning_rate": 5.230769230769232e-06,
|
176 |
+
"loss": 0.131,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 3.8461538461538463,
|
181 |
+
"grad_norm": 0.5753270387649536,
|
182 |
+
"learning_rate": 4.615384615384616e-06,
|
183 |
+
"loss": 0.1493,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 4.0,
|
188 |
+
"grad_norm": 0.9189938306808472,
|
189 |
+
"learning_rate": 4.000000000000001e-06,
|
190 |
+
"loss": 0.1489,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 4.153846153846154,
|
195 |
+
"grad_norm": 0.939368724822998,
|
196 |
+
"learning_rate": 3.384615384615385e-06,
|
197 |
+
"loss": 0.1615,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 4.3076923076923075,
|
202 |
+
"grad_norm": 1.0938255786895752,
|
203 |
+
"learning_rate": 2.7692307692307697e-06,
|
204 |
+
"loss": 0.1433,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 4.461538461538462,
|
209 |
+
"grad_norm": 0.398496150970459,
|
210 |
+
"learning_rate": 2.153846153846154e-06,
|
211 |
+
"loss": 0.1485,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 4.615384615384615,
|
216 |
+
"grad_norm": 1.6919806003570557,
|
217 |
+
"learning_rate": 1.5384615384615387e-06,
|
218 |
+
"loss": 0.131,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 4.769230769230769,
|
223 |
+
"grad_norm": 0.9723582863807678,
|
224 |
+
"learning_rate": 9.230769230769232e-07,
|
225 |
+
"loss": 0.1288,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 4.923076923076923,
|
230 |
+
"grad_norm": 0.5153496265411377,
|
231 |
+
"learning_rate": 3.0769230769230774e-07,
|
232 |
+
"loss": 0.109,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 5.0,
|
237 |
+
"step": 325,
|
238 |
+
"total_flos": 4.006371770595533e+17,
|
239 |
+
"train_loss": 0.29627929100623496,
|
240 |
+
"train_runtime": 105.6493,
|
241 |
+
"train_samples_per_second": 48.935,
|
242 |
+
"train_steps_per_second": 3.076
|
243 |
+
}
|
244 |
+
],
|
245 |
+
"logging_steps": 10,
|
246 |
+
"max_steps": 325,
|
247 |
+
"num_input_tokens_seen": 0,
|
248 |
+
"num_train_epochs": 5,
|
249 |
+
"save_steps": 500,
|
250 |
+
"stateful_callbacks": {
|
251 |
+
"TrainerControl": {
|
252 |
+
"args": {
|
253 |
+
"should_epoch_stop": false,
|
254 |
+
"should_evaluate": false,
|
255 |
+
"should_log": false,
|
256 |
+
"should_save": false,
|
257 |
+
"should_training_stop": false
|
258 |
+
},
|
259 |
+
"attributes": {}
|
260 |
+
}
|
261 |
+
},
|
262 |
+
"total_flos": 4.006371770595533e+17,
|
263 |
+
"train_batch_size": 16,
|
264 |
+
"trial_name": null,
|
265 |
+
"trial_params": null
|
266 |
+
}
|