End of training
Browse files- README.md +3 -3
- all_results.json +9 -9
- eval_results.json +5 -5
- runs/Nov27_11-53-49_9e69cd33b119/events.out.tfevents.1701086484.9e69cd33b119.1373.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +96 -96
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 [100rab25/swin-tiny-patch4-window7-224-spa_saloon_classification](https://huggingface.co/100rab25/swin-tiny-patch4-window7-224-spa_saloon_classification) 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: 0.9930313588850174
|
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 [100rab25/swin-tiny-patch4-window7-224-spa_saloon_classification](https://huggingface.co/100rab25/swin-tiny-patch4-window7-224-spa_saloon_classification) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.0408
|
36 |
+
- Accuracy: 0.9930
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 9.88,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 4.
|
8 |
"total_flos": 6.325810471729889e+17,
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 9.88,
|
3 |
+
"eval_accuracy": 0.9930313588850174,
|
4 |
+
"eval_loss": 0.040804799646139145,
|
5 |
+
"eval_runtime": 2.2216,
|
6 |
+
"eval_samples_per_second": 129.185,
|
7 |
+
"eval_steps_per_second": 4.051,
|
8 |
"total_flos": 6.325810471729889e+17,
|
9 |
+
"train_loss": 0.15392300799489023,
|
10 |
+
"train_runtime": 432.1174,
|
11 |
+
"train_samples_per_second": 59.59,
|
12 |
+
"train_steps_per_second": 0.463
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 9.88,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 4.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 9.88,
|
3 |
+
"eval_accuracy": 0.9930313588850174,
|
4 |
+
"eval_loss": 0.040804799646139145,
|
5 |
+
"eval_runtime": 2.2216,
|
6 |
+
"eval_samples_per_second": 129.185,
|
7 |
+
"eval_steps_per_second": 4.051
|
8 |
}
|
runs/Nov27_11-53-49_9e69cd33b119/events.out.tfevents.1701086484.9e69cd33b119.1373.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33d321c905807548d7c09a008e2c31fbdebaafe2c1c6acec2b9bfe40a3e300a3
|
3 |
+
size 411
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 9.88,
|
3 |
"total_flos": 6.325810471729889e+17,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 9.88,
|
3 |
"total_flos": 6.325810471729889e+17,
|
4 |
+
"train_loss": 0.15392300799489023,
|
5 |
+
"train_runtime": 432.1174,
|
6 |
+
"train_samples_per_second": 59.59,
|
7 |
+
"train_steps_per_second": 0.463
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-spa_saloon_classification-spa-saloon/checkpoint-
|
4 |
"epoch": 9.876543209876543,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 200,
|
@@ -11,341 +11,341 @@
|
|
11 |
{
|
12 |
"epoch": 0.25,
|
13 |
"learning_rate": 1.25e-05,
|
14 |
-
"loss": 0.
|
15 |
"step": 5
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.49,
|
19 |
"learning_rate": 2.5e-05,
|
20 |
-
"loss": 0.
|
21 |
"step": 10
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.74,
|
25 |
"learning_rate": 3.7500000000000003e-05,
|
26 |
-
"loss": 0.
|
27 |
"step": 15
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.99,
|
31 |
"learning_rate": 5e-05,
|
32 |
-
"loss": 0.
|
33 |
"step": 20
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.99,
|
37 |
-
"eval_accuracy": 0.
|
38 |
-
"eval_loss": 0.
|
39 |
-
"eval_runtime":
|
40 |
-
"eval_samples_per_second":
|
41 |
-
"eval_steps_per_second": 4.
|
42 |
"step": 20
|
43 |
},
|
44 |
{
|
45 |
"epoch": 1.23,
|
46 |
"learning_rate": 4.8611111111111115e-05,
|
47 |
-
"loss": 0.
|
48 |
"step": 25
|
49 |
},
|
50 |
{
|
51 |
"epoch": 1.48,
|
52 |
"learning_rate": 4.722222222222222e-05,
|
53 |
-
"loss": 0.
|
54 |
"step": 30
|
55 |
},
|
56 |
{
|
57 |
"epoch": 1.73,
|
58 |
"learning_rate": 4.5833333333333334e-05,
|
59 |
-
"loss": 0.
|
60 |
"step": 35
|
61 |
},
|
62 |
{
|
63 |
"epoch": 1.98,
|
64 |
"learning_rate": 4.4444444444444447e-05,
|
65 |
-
"loss": 0.
|
66 |
"step": 40
|
67 |
},
|
68 |
{
|
69 |
"epoch": 1.98,
|
70 |
-
"eval_accuracy": 0.
|
71 |
-
"eval_loss": 0.
|
72 |
-
"eval_runtime": 1.
|
73 |
-
"eval_samples_per_second":
|
74 |
-
"eval_steps_per_second": 4.
|
75 |
"step": 40
|
76 |
},
|
77 |
{
|
78 |
"epoch": 2.22,
|
79 |
"learning_rate": 4.305555555555556e-05,
|
80 |
-
"loss": 0.
|
81 |
"step": 45
|
82 |
},
|
83 |
{
|
84 |
"epoch": 2.47,
|
85 |
"learning_rate": 4.166666666666667e-05,
|
86 |
-
"loss": 0.
|
87 |
"step": 50
|
88 |
},
|
89 |
{
|
90 |
"epoch": 2.72,
|
91 |
"learning_rate": 4.027777777777778e-05,
|
92 |
-
"loss": 0.
|
93 |
"step": 55
|
94 |
},
|
95 |
{
|
96 |
"epoch": 2.96,
|
97 |
"learning_rate": 3.888888888888889e-05,
|
98 |
-
"loss": 0.
|
99 |
"step": 60
|
100 |
},
|
101 |
{
|
102 |
"epoch": 2.96,
|
103 |
-
"eval_accuracy": 0.
|
104 |
-
"eval_loss": 0.
|
105 |
-
"eval_runtime":
|
106 |
-
"eval_samples_per_second":
|
107 |
-
"eval_steps_per_second": 4.
|
108 |
"step": 60
|
109 |
},
|
110 |
{
|
111 |
"epoch": 3.21,
|
112 |
"learning_rate": 3.7500000000000003e-05,
|
113 |
-
"loss": 0.
|
114 |
"step": 65
|
115 |
},
|
116 |
{
|
117 |
"epoch": 3.46,
|
118 |
"learning_rate": 3.611111111111111e-05,
|
119 |
-
"loss": 0.
|
120 |
"step": 70
|
121 |
},
|
122 |
{
|
123 |
"epoch": 3.7,
|
124 |
"learning_rate": 3.472222222222222e-05,
|
125 |
-
"loss": 0.
|
126 |
"step": 75
|
127 |
},
|
128 |
{
|
129 |
"epoch": 3.95,
|
130 |
"learning_rate": 3.3333333333333335e-05,
|
131 |
-
"loss": 0.
|
132 |
"step": 80
|
133 |
},
|
134 |
{
|
135 |
"epoch": 4.0,
|
136 |
-
"eval_accuracy": 0.
|
137 |
-
"eval_loss": 0.
|
138 |
-
"eval_runtime": 1.
|
139 |
-
"eval_samples_per_second":
|
140 |
-
"eval_steps_per_second": 4.
|
141 |
"step": 81
|
142 |
},
|
143 |
{
|
144 |
"epoch": 4.2,
|
145 |
"learning_rate": 3.194444444444444e-05,
|
146 |
-
"loss": 0.
|
147 |
"step": 85
|
148 |
},
|
149 |
{
|
150 |
"epoch": 4.44,
|
151 |
"learning_rate": 3.055555555555556e-05,
|
152 |
-
"loss": 0.
|
153 |
"step": 90
|
154 |
},
|
155 |
{
|
156 |
"epoch": 4.69,
|
157 |
"learning_rate": 2.916666666666667e-05,
|
158 |
-
"loss": 0.
|
159 |
"step": 95
|
160 |
},
|
161 |
{
|
162 |
"epoch": 4.94,
|
163 |
"learning_rate": 2.777777777777778e-05,
|
164 |
-
"loss": 0.
|
165 |
"step": 100
|
166 |
},
|
167 |
{
|
168 |
"epoch": 4.99,
|
169 |
-
"eval_accuracy": 0.
|
170 |
-
"eval_loss": 0.
|
171 |
-
"eval_runtime": 2.
|
172 |
-
"eval_samples_per_second":
|
173 |
-
"eval_steps_per_second": 3.
|
174 |
"step": 101
|
175 |
},
|
176 |
{
|
177 |
"epoch": 5.19,
|
178 |
"learning_rate": 2.6388888888888892e-05,
|
179 |
-
"loss": 0.
|
180 |
"step": 105
|
181 |
},
|
182 |
{
|
183 |
"epoch": 5.43,
|
184 |
"learning_rate": 2.5e-05,
|
185 |
-
"loss": 0.
|
186 |
"step": 110
|
187 |
},
|
188 |
{
|
189 |
"epoch": 5.68,
|
190 |
"learning_rate": 2.361111111111111e-05,
|
191 |
-
"loss": 0.
|
192 |
"step": 115
|
193 |
},
|
194 |
{
|
195 |
"epoch": 5.93,
|
196 |
"learning_rate": 2.2222222222222223e-05,
|
197 |
-
"loss": 0.
|
198 |
"step": 120
|
199 |
},
|
200 |
{
|
201 |
"epoch": 5.98,
|
202 |
-
"eval_accuracy": 0.
|
203 |
-
"eval_loss": 0.
|
204 |
-
"eval_runtime": 1.
|
205 |
-
"eval_samples_per_second":
|
206 |
-
"eval_steps_per_second": 4.
|
207 |
"step": 121
|
208 |
},
|
209 |
{
|
210 |
"epoch": 6.17,
|
211 |
"learning_rate": 2.0833333333333336e-05,
|
212 |
-
"loss": 0.
|
213 |
"step": 125
|
214 |
},
|
215 |
{
|
216 |
"epoch": 6.42,
|
217 |
"learning_rate": 1.9444444444444445e-05,
|
218 |
-
"loss": 0.
|
219 |
"step": 130
|
220 |
},
|
221 |
{
|
222 |
"epoch": 6.67,
|
223 |
"learning_rate": 1.8055555555555555e-05,
|
224 |
-
"loss": 0.
|
225 |
"step": 135
|
226 |
},
|
227 |
{
|
228 |
"epoch": 6.91,
|
229 |
"learning_rate": 1.6666666666666667e-05,
|
230 |
-
"loss": 0.
|
231 |
"step": 140
|
232 |
},
|
233 |
{
|
234 |
"epoch": 6.96,
|
235 |
-
"eval_accuracy": 0.
|
236 |
-
"eval_loss": 0.
|
237 |
-
"eval_runtime": 2.
|
238 |
-
"eval_samples_per_second":
|
239 |
-
"eval_steps_per_second":
|
240 |
"step": 141
|
241 |
},
|
242 |
{
|
243 |
"epoch": 7.16,
|
244 |
"learning_rate": 1.527777777777778e-05,
|
245 |
-
"loss": 0.
|
246 |
"step": 145
|
247 |
},
|
248 |
{
|
249 |
"epoch": 7.41,
|
250 |
"learning_rate": 1.388888888888889e-05,
|
251 |
-
"loss": 0.
|
252 |
"step": 150
|
253 |
},
|
254 |
{
|
255 |
"epoch": 7.65,
|
256 |
"learning_rate": 1.25e-05,
|
257 |
-
"loss": 0.
|
258 |
"step": 155
|
259 |
},
|
260 |
{
|
261 |
"epoch": 7.9,
|
262 |
"learning_rate": 1.1111111111111112e-05,
|
263 |
-
"loss": 0.
|
264 |
"step": 160
|
265 |
},
|
266 |
{
|
267 |
"epoch": 8.0,
|
268 |
-
"eval_accuracy": 0.
|
269 |
-
"eval_loss": 0.
|
270 |
-
"eval_runtime": 1.
|
271 |
-
"eval_samples_per_second":
|
272 |
-
"eval_steps_per_second": 4.
|
273 |
"step": 162
|
274 |
},
|
275 |
{
|
276 |
"epoch": 8.15,
|
277 |
"learning_rate": 9.722222222222223e-06,
|
278 |
-
"loss": 0.
|
279 |
"step": 165
|
280 |
},
|
281 |
{
|
282 |
"epoch": 8.4,
|
283 |
"learning_rate": 8.333333333333334e-06,
|
284 |
-
"loss": 0.
|
285 |
"step": 170
|
286 |
},
|
287 |
{
|
288 |
"epoch": 8.64,
|
289 |
"learning_rate": 6.944444444444445e-06,
|
290 |
-
"loss": 0.
|
291 |
"step": 175
|
292 |
},
|
293 |
{
|
294 |
"epoch": 8.89,
|
295 |
"learning_rate": 5.555555555555556e-06,
|
296 |
-
"loss": 0.
|
297 |
"step": 180
|
298 |
},
|
299 |
{
|
300 |
"epoch": 8.99,
|
301 |
-
"eval_accuracy": 0.
|
302 |
-
"eval_loss": 0.
|
303 |
-
"eval_runtime": 2.
|
304 |
-
"eval_samples_per_second":
|
305 |
-
"eval_steps_per_second":
|
306 |
"step": 182
|
307 |
},
|
308 |
{
|
309 |
"epoch": 9.14,
|
310 |
"learning_rate": 4.166666666666667e-06,
|
311 |
-
"loss": 0.
|
312 |
"step": 185
|
313 |
},
|
314 |
{
|
315 |
"epoch": 9.38,
|
316 |
"learning_rate": 2.777777777777778e-06,
|
317 |
-
"loss": 0.
|
318 |
"step": 190
|
319 |
},
|
320 |
{
|
321 |
"epoch": 9.63,
|
322 |
"learning_rate": 1.388888888888889e-06,
|
323 |
-
"loss": 0.
|
324 |
"step": 195
|
325 |
},
|
326 |
{
|
327 |
"epoch": 9.88,
|
328 |
"learning_rate": 0.0,
|
329 |
-
"loss": 0.
|
330 |
"step": 200
|
331 |
},
|
332 |
{
|
333 |
"epoch": 9.88,
|
334 |
-
"eval_accuracy": 0.
|
335 |
-
"eval_loss": 0.
|
336 |
-
"eval_runtime":
|
337 |
-
"eval_samples_per_second":
|
338 |
-
"eval_steps_per_second": 4.
|
339 |
"step": 200
|
340 |
},
|
341 |
{
|
342 |
"epoch": 9.88,
|
343 |
"step": 200,
|
344 |
"total_flos": 6.325810471729889e+17,
|
345 |
-
"train_loss": 0.
|
346 |
-
"train_runtime":
|
347 |
-
"train_samples_per_second":
|
348 |
-
"train_steps_per_second": 0.
|
349 |
}
|
350 |
],
|
351 |
"logging_steps": 5,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9930313588850174,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-spa_saloon_classification-spa-saloon/checkpoint-121",
|
4 |
"epoch": 9.876543209876543,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 200,
|
|
|
11 |
{
|
12 |
"epoch": 0.25,
|
13 |
"learning_rate": 1.25e-05,
|
14 |
+
"loss": 0.3756,
|
15 |
"step": 5
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.49,
|
19 |
"learning_rate": 2.5e-05,
|
20 |
+
"loss": 0.3312,
|
21 |
"step": 10
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.74,
|
25 |
"learning_rate": 3.7500000000000003e-05,
|
26 |
+
"loss": 0.3086,
|
27 |
"step": 15
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.99,
|
31 |
"learning_rate": 5e-05,
|
32 |
+
"loss": 0.2637,
|
33 |
"step": 20
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.99,
|
37 |
+
"eval_accuracy": 0.9442508710801394,
|
38 |
+
"eval_loss": 0.1274152249097824,
|
39 |
+
"eval_runtime": 2.2323,
|
40 |
+
"eval_samples_per_second": 128.565,
|
41 |
+
"eval_steps_per_second": 4.032,
|
42 |
"step": 20
|
43 |
},
|
44 |
{
|
45 |
"epoch": 1.23,
|
46 |
"learning_rate": 4.8611111111111115e-05,
|
47 |
+
"loss": 0.2486,
|
48 |
"step": 25
|
49 |
},
|
50 |
{
|
51 |
"epoch": 1.48,
|
52 |
"learning_rate": 4.722222222222222e-05,
|
53 |
+
"loss": 0.2594,
|
54 |
"step": 30
|
55 |
},
|
56 |
{
|
57 |
"epoch": 1.73,
|
58 |
"learning_rate": 4.5833333333333334e-05,
|
59 |
+
"loss": 0.2133,
|
60 |
"step": 35
|
61 |
},
|
62 |
{
|
63 |
"epoch": 1.98,
|
64 |
"learning_rate": 4.4444444444444447e-05,
|
65 |
+
"loss": 0.2582,
|
66 |
"step": 40
|
67 |
},
|
68 |
{
|
69 |
"epoch": 1.98,
|
70 |
+
"eval_accuracy": 0.975609756097561,
|
71 |
+
"eval_loss": 0.09369026869535446,
|
72 |
+
"eval_runtime": 1.916,
|
73 |
+
"eval_samples_per_second": 149.792,
|
74 |
+
"eval_steps_per_second": 4.697,
|
75 |
"step": 40
|
76 |
},
|
77 |
{
|
78 |
"epoch": 2.22,
|
79 |
"learning_rate": 4.305555555555556e-05,
|
80 |
+
"loss": 0.1924,
|
81 |
"step": 45
|
82 |
},
|
83 |
{
|
84 |
"epoch": 2.47,
|
85 |
"learning_rate": 4.166666666666667e-05,
|
86 |
+
"loss": 0.1749,
|
87 |
"step": 50
|
88 |
},
|
89 |
{
|
90 |
"epoch": 2.72,
|
91 |
"learning_rate": 4.027777777777778e-05,
|
92 |
+
"loss": 0.1551,
|
93 |
"step": 55
|
94 |
},
|
95 |
{
|
96 |
"epoch": 2.96,
|
97 |
"learning_rate": 3.888888888888889e-05,
|
98 |
+
"loss": 0.161,
|
99 |
"step": 60
|
100 |
},
|
101 |
{
|
102 |
"epoch": 2.96,
|
103 |
+
"eval_accuracy": 0.9581881533101045,
|
104 |
+
"eval_loss": 0.09241745620965958,
|
105 |
+
"eval_runtime": 2.1953,
|
106 |
+
"eval_samples_per_second": 130.734,
|
107 |
+
"eval_steps_per_second": 4.1,
|
108 |
"step": 60
|
109 |
},
|
110 |
{
|
111 |
"epoch": 3.21,
|
112 |
"learning_rate": 3.7500000000000003e-05,
|
113 |
+
"loss": 0.2067,
|
114 |
"step": 65
|
115 |
},
|
116 |
{
|
117 |
"epoch": 3.46,
|
118 |
"learning_rate": 3.611111111111111e-05,
|
119 |
+
"loss": 0.1642,
|
120 |
"step": 70
|
121 |
},
|
122 |
{
|
123 |
"epoch": 3.7,
|
124 |
"learning_rate": 3.472222222222222e-05,
|
125 |
+
"loss": 0.1413,
|
126 |
"step": 75
|
127 |
},
|
128 |
{
|
129 |
"epoch": 3.95,
|
130 |
"learning_rate": 3.3333333333333335e-05,
|
131 |
+
"loss": 0.1535,
|
132 |
"step": 80
|
133 |
},
|
134 |
{
|
135 |
"epoch": 4.0,
|
136 |
+
"eval_accuracy": 0.9860627177700348,
|
137 |
+
"eval_loss": 0.061225663870573044,
|
138 |
+
"eval_runtime": 1.959,
|
139 |
+
"eval_samples_per_second": 146.501,
|
140 |
+
"eval_steps_per_second": 4.594,
|
141 |
"step": 81
|
142 |
},
|
143 |
{
|
144 |
"epoch": 4.2,
|
145 |
"learning_rate": 3.194444444444444e-05,
|
146 |
+
"loss": 0.1393,
|
147 |
"step": 85
|
148 |
},
|
149 |
{
|
150 |
"epoch": 4.44,
|
151 |
"learning_rate": 3.055555555555556e-05,
|
152 |
+
"loss": 0.1377,
|
153 |
"step": 90
|
154 |
},
|
155 |
{
|
156 |
"epoch": 4.69,
|
157 |
"learning_rate": 2.916666666666667e-05,
|
158 |
+
"loss": 0.1266,
|
159 |
"step": 95
|
160 |
},
|
161 |
{
|
162 |
"epoch": 4.94,
|
163 |
"learning_rate": 2.777777777777778e-05,
|
164 |
+
"loss": 0.1347,
|
165 |
"step": 100
|
166 |
},
|
167 |
{
|
168 |
"epoch": 4.99,
|
169 |
+
"eval_accuracy": 0.9790940766550522,
|
170 |
+
"eval_loss": 0.05363203585147858,
|
171 |
+
"eval_runtime": 2.5164,
|
172 |
+
"eval_samples_per_second": 114.052,
|
173 |
+
"eval_steps_per_second": 3.577,
|
174 |
"step": 101
|
175 |
},
|
176 |
{
|
177 |
"epoch": 5.19,
|
178 |
"learning_rate": 2.6388888888888892e-05,
|
179 |
+
"loss": 0.1041,
|
180 |
"step": 105
|
181 |
},
|
182 |
{
|
183 |
"epoch": 5.43,
|
184 |
"learning_rate": 2.5e-05,
|
185 |
+
"loss": 0.0922,
|
186 |
"step": 110
|
187 |
},
|
188 |
{
|
189 |
"epoch": 5.68,
|
190 |
"learning_rate": 2.361111111111111e-05,
|
191 |
+
"loss": 0.1152,
|
192 |
"step": 115
|
193 |
},
|
194 |
{
|
195 |
"epoch": 5.93,
|
196 |
"learning_rate": 2.2222222222222223e-05,
|
197 |
+
"loss": 0.1155,
|
198 |
"step": 120
|
199 |
},
|
200 |
{
|
201 |
"epoch": 5.98,
|
202 |
+
"eval_accuracy": 0.9930313588850174,
|
203 |
+
"eval_loss": 0.040804799646139145,
|
204 |
+
"eval_runtime": 1.9704,
|
205 |
+
"eval_samples_per_second": 145.658,
|
206 |
+
"eval_steps_per_second": 4.568,
|
207 |
"step": 121
|
208 |
},
|
209 |
{
|
210 |
"epoch": 6.17,
|
211 |
"learning_rate": 2.0833333333333336e-05,
|
212 |
+
"loss": 0.1115,
|
213 |
"step": 125
|
214 |
},
|
215 |
{
|
216 |
"epoch": 6.42,
|
217 |
"learning_rate": 1.9444444444444445e-05,
|
218 |
+
"loss": 0.0837,
|
219 |
"step": 130
|
220 |
},
|
221 |
{
|
222 |
"epoch": 6.67,
|
223 |
"learning_rate": 1.8055555555555555e-05,
|
224 |
+
"loss": 0.1156,
|
225 |
"step": 135
|
226 |
},
|
227 |
{
|
228 |
"epoch": 6.91,
|
229 |
"learning_rate": 1.6666666666666667e-05,
|
230 |
+
"loss": 0.1306,
|
231 |
"step": 140
|
232 |
},
|
233 |
{
|
234 |
"epoch": 6.96,
|
235 |
+
"eval_accuracy": 0.9930313588850174,
|
236 |
+
"eval_loss": 0.04172113910317421,
|
237 |
+
"eval_runtime": 2.3226,
|
238 |
+
"eval_samples_per_second": 123.57,
|
239 |
+
"eval_steps_per_second": 3.875,
|
240 |
"step": 141
|
241 |
},
|
242 |
{
|
243 |
"epoch": 7.16,
|
244 |
"learning_rate": 1.527777777777778e-05,
|
245 |
+
"loss": 0.0813,
|
246 |
"step": 145
|
247 |
},
|
248 |
{
|
249 |
"epoch": 7.41,
|
250 |
"learning_rate": 1.388888888888889e-05,
|
251 |
+
"loss": 0.1014,
|
252 |
"step": 150
|
253 |
},
|
254 |
{
|
255 |
"epoch": 7.65,
|
256 |
"learning_rate": 1.25e-05,
|
257 |
+
"loss": 0.1172,
|
258 |
"step": 155
|
259 |
},
|
260 |
{
|
261 |
"epoch": 7.9,
|
262 |
"learning_rate": 1.1111111111111112e-05,
|
263 |
+
"loss": 0.1017,
|
264 |
"step": 160
|
265 |
},
|
266 |
{
|
267 |
"epoch": 8.0,
|
268 |
+
"eval_accuracy": 0.9895470383275261,
|
269 |
+
"eval_loss": 0.038007255643606186,
|
270 |
+
"eval_runtime": 1.9669,
|
271 |
+
"eval_samples_per_second": 145.914,
|
272 |
+
"eval_steps_per_second": 4.576,
|
273 |
"step": 162
|
274 |
},
|
275 |
{
|
276 |
"epoch": 8.15,
|
277 |
"learning_rate": 9.722222222222223e-06,
|
278 |
+
"loss": 0.0897,
|
279 |
"step": 165
|
280 |
},
|
281 |
{
|
282 |
"epoch": 8.4,
|
283 |
"learning_rate": 8.333333333333334e-06,
|
284 |
+
"loss": 0.0959,
|
285 |
"step": 170
|
286 |
},
|
287 |
{
|
288 |
"epoch": 8.64,
|
289 |
"learning_rate": 6.944444444444445e-06,
|
290 |
+
"loss": 0.0867,
|
291 |
"step": 175
|
292 |
},
|
293 |
{
|
294 |
"epoch": 8.89,
|
295 |
"learning_rate": 5.555555555555556e-06,
|
296 |
+
"loss": 0.0859,
|
297 |
"step": 180
|
298 |
},
|
299 |
{
|
300 |
"epoch": 8.99,
|
301 |
+
"eval_accuracy": 0.9895470383275261,
|
302 |
+
"eval_loss": 0.041699331253767014,
|
303 |
+
"eval_runtime": 2.3485,
|
304 |
+
"eval_samples_per_second": 122.208,
|
305 |
+
"eval_steps_per_second": 3.832,
|
306 |
"step": 182
|
307 |
},
|
308 |
{
|
309 |
"epoch": 9.14,
|
310 |
"learning_rate": 4.166666666666667e-06,
|
311 |
+
"loss": 0.0991,
|
312 |
"step": 185
|
313 |
},
|
314 |
{
|
315 |
"epoch": 9.38,
|
316 |
"learning_rate": 2.777777777777778e-06,
|
317 |
+
"loss": 0.091,
|
318 |
"step": 190
|
319 |
},
|
320 |
{
|
321 |
"epoch": 9.63,
|
322 |
"learning_rate": 1.388888888888889e-06,
|
323 |
+
"loss": 0.103,
|
324 |
"step": 195
|
325 |
},
|
326 |
{
|
327 |
"epoch": 9.88,
|
328 |
"learning_rate": 0.0,
|
329 |
+
"loss": 0.0897,
|
330 |
"step": 200
|
331 |
},
|
332 |
{
|
333 |
"epoch": 9.88,
|
334 |
+
"eval_accuracy": 0.9895470383275261,
|
335 |
+
"eval_loss": 0.03927117958664894,
|
336 |
+
"eval_runtime": 2.2228,
|
337 |
+
"eval_samples_per_second": 129.119,
|
338 |
+
"eval_steps_per_second": 4.049,
|
339 |
"step": 200
|
340 |
},
|
341 |
{
|
342 |
"epoch": 9.88,
|
343 |
"step": 200,
|
344 |
"total_flos": 6.325810471729889e+17,
|
345 |
+
"train_loss": 0.15392300799489023,
|
346 |
+
"train_runtime": 432.1174,
|
347 |
+
"train_samples_per_second": 59.59,
|
348 |
+
"train_steps_per_second": 0.463
|
349 |
}
|
350 |
],
|
351 |
"logging_steps": 5,
|