JEdward7777
commited on
Commit
•
85639ed
1
Parent(s):
c4c17b5
End of training
Browse files- all_results.json +10 -10
- eval_results.json +5 -5
- train_results.json +6 -6
- trainer_state.json +308 -296
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_accuracy": 1.0,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 7.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
-
"total_flos": 3.
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second": 1.
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 40.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.04307302460074425,
|
5 |
+
"eval_runtime": 7.4924,
|
6 |
+
"eval_samples_per_second": 5.339,
|
7 |
+
"eval_steps_per_second": 0.267,
|
8 |
+
"total_flos": 3.579662466809856e+17,
|
9 |
+
"train_loss": 0.17003339926401775,
|
10 |
+
"train_runtime": 8221.5625,
|
11 |
+
"train_samples_per_second": 1.751,
|
12 |
+
"train_steps_per_second": 0.015
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_accuracy": 1.0,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 7.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 40.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.04307302460074425,
|
5 |
+
"eval_runtime": 7.4924,
|
6 |
+
"eval_samples_per_second": 5.339,
|
7 |
+
"eval_steps_per_second": 0.267
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos": 3.
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 1.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 40.0,
|
3 |
+
"total_flos": 3.579662466809856e+17,
|
4 |
+
"train_loss": 0.17003339926401775,
|
5 |
+
"train_runtime": 8221.5625,
|
6 |
+
"train_samples_per_second": 1.751,
|
7 |
+
"train_steps_per_second": 0.015
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,409 +1,421 @@
|
|
1 |
{
|
2 |
"best_metric": 1.0,
|
3 |
-
"best_model_checkpoint": "delivery_truck_classification\\checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch": 0
|
12 |
-
"eval_accuracy":
|
13 |
-
"eval_loss": 0.
|
14 |
-
"eval_runtime":
|
15 |
-
"eval_samples_per_second": 4.
|
16 |
-
"eval_steps_per_second": 0.
|
17 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
},
|
19 |
{
|
20 |
-
"epoch":
|
21 |
-
"eval_accuracy":
|
22 |
-
"eval_loss": 0.
|
23 |
-
"eval_runtime":
|
24 |
-
"eval_samples_per_second":
|
25 |
-
"eval_steps_per_second": 0.
|
26 |
-
"step":
|
27 |
},
|
28 |
{
|
29 |
-
"epoch":
|
30 |
-
"eval_accuracy":
|
31 |
-
"eval_loss": 0.
|
32 |
-
"eval_runtime":
|
33 |
-
"eval_samples_per_second":
|
34 |
-
"eval_steps_per_second": 0.
|
35 |
-
"step":
|
36 |
},
|
37 |
{
|
38 |
-
"epoch":
|
39 |
-
"eval_accuracy":
|
40 |
-
"eval_loss": 0.
|
41 |
-
"eval_runtime":
|
42 |
-
"eval_samples_per_second":
|
43 |
-
"eval_steps_per_second": 0.
|
44 |
-
"step":
|
45 |
},
|
46 |
{
|
47 |
-
"epoch":
|
48 |
"eval_accuracy": 1.0,
|
49 |
-
"eval_loss": 0.
|
50 |
-
"eval_runtime":
|
51 |
-
"eval_samples_per_second":
|
52 |
-
"eval_steps_per_second": 0.
|
53 |
-
"step":
|
54 |
},
|
55 |
{
|
56 |
-
"epoch":
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"
|
60 |
-
"eval_samples_per_second": 4.115,
|
61 |
-
"eval_steps_per_second": 0.222,
|
62 |
-
"step": 12
|
63 |
},
|
64 |
{
|
65 |
-
"epoch":
|
66 |
"eval_accuracy": 1.0,
|
67 |
-
"eval_loss": 0.
|
68 |
-
"eval_runtime": 8.
|
69 |
-
"eval_samples_per_second": 4.
|
70 |
-
"eval_steps_per_second": 0.
|
71 |
-
"step":
|
72 |
},
|
73 |
{
|
74 |
-
"epoch":
|
75 |
"eval_accuracy": 1.0,
|
76 |
-
"eval_loss": 0.
|
77 |
-
"eval_runtime":
|
78 |
-
"eval_samples_per_second":
|
79 |
-
"eval_steps_per_second": 0.
|
80 |
-
"step":
|
81 |
},
|
82 |
{
|
83 |
-
"epoch":
|
84 |
"eval_accuracy": 1.0,
|
85 |
-
"eval_loss": 0.
|
86 |
-
"eval_runtime":
|
87 |
-
"eval_samples_per_second":
|
88 |
-
"eval_steps_per_second": 0.
|
89 |
-
"step":
|
90 |
},
|
91 |
{
|
92 |
-
"epoch":
|
93 |
-
"
|
94 |
-
"
|
95 |
-
"
|
|
|
|
|
|
|
96 |
},
|
97 |
{
|
98 |
-
"epoch":
|
99 |
"eval_accuracy": 1.0,
|
100 |
-
"eval_loss": 0.
|
101 |
-
"eval_runtime": 8.
|
102 |
-
"eval_samples_per_second": 4.
|
103 |
-
"eval_steps_per_second": 0.
|
104 |
-
"step":
|
105 |
},
|
106 |
{
|
107 |
-
"epoch":
|
108 |
"eval_accuracy": 1.0,
|
109 |
-
"eval_loss": 0.
|
110 |
-
"eval_runtime": 8.
|
111 |
-
"eval_samples_per_second": 4.
|
112 |
-
"eval_steps_per_second": 0.
|
113 |
-
"step":
|
114 |
},
|
115 |
{
|
116 |
-
"epoch":
|
117 |
-
"eval_accuracy": 0
|
118 |
-
"eval_loss": 0.
|
119 |
-
"eval_runtime": 8.
|
120 |
-
"eval_samples_per_second": 4.
|
121 |
-
"eval_steps_per_second": 0.
|
122 |
-
"step":
|
123 |
},
|
124 |
{
|
125 |
-
"epoch":
|
126 |
-
"
|
127 |
-
"
|
128 |
-
"
|
129 |
-
"eval_samples_per_second": 4.154,
|
130 |
-
"eval_steps_per_second": 0.225,
|
131 |
-
"step": 26
|
132 |
},
|
133 |
{
|
134 |
-
"epoch":
|
135 |
-
"eval_accuracy":
|
136 |
-
"eval_loss": 0.
|
137 |
-
"eval_runtime":
|
138 |
-
"eval_samples_per_second": 4.
|
139 |
-
"eval_steps_per_second": 0.
|
140 |
-
"step":
|
141 |
},
|
142 |
{
|
143 |
-
"epoch":
|
144 |
-
"eval_accuracy":
|
145 |
-
"eval_loss": 0.
|
146 |
-
"eval_runtime":
|
147 |
-
"eval_samples_per_second":
|
148 |
-
"eval_steps_per_second": 0.
|
149 |
-
"step":
|
150 |
},
|
151 |
{
|
152 |
-
"epoch":
|
153 |
-
"eval_accuracy":
|
154 |
-
"eval_loss": 0.
|
155 |
-
"eval_runtime":
|
156 |
-
"eval_samples_per_second":
|
157 |
-
"eval_steps_per_second": 0.
|
158 |
-
"step":
|
159 |
},
|
160 |
{
|
161 |
-
"epoch":
|
162 |
"eval_accuracy": 1.0,
|
163 |
-
"eval_loss": 0.
|
164 |
-
"eval_runtime":
|
165 |
-
"eval_samples_per_second":
|
166 |
-
"eval_steps_per_second": 0.
|
167 |
-
"step":
|
168 |
},
|
169 |
{
|
170 |
-
"epoch":
|
171 |
-
"eval_accuracy": 0
|
172 |
-
"eval_loss": 0.
|
173 |
-
"eval_runtime":
|
174 |
-
"eval_samples_per_second":
|
175 |
-
"eval_steps_per_second": 0.
|
176 |
-
"step":
|
177 |
},
|
178 |
{
|
179 |
-
"epoch":
|
180 |
-
"eval_accuracy": 0
|
181 |
-
"eval_loss": 0.
|
182 |
-
"eval_runtime":
|
183 |
-
"eval_samples_per_second": 4.
|
184 |
-
"eval_steps_per_second": 0.
|
185 |
-
"step":
|
186 |
},
|
187 |
{
|
188 |
-
"epoch":
|
189 |
"learning_rate": 2.777777777777778e-05,
|
190 |
-
"loss": 0.
|
191 |
-
"step":
|
192 |
},
|
193 |
{
|
194 |
-
"epoch":
|
195 |
-
"eval_accuracy": 0
|
196 |
-
"eval_loss": 0.
|
197 |
-
"eval_runtime":
|
198 |
-
"eval_samples_per_second":
|
199 |
-
"eval_steps_per_second": 0.
|
200 |
-
"step":
|
201 |
},
|
202 |
{
|
203 |
-
"epoch":
|
204 |
"eval_accuracy": 1.0,
|
205 |
-
"eval_loss": 0.
|
206 |
-
"eval_runtime":
|
207 |
-
"eval_samples_per_second":
|
208 |
-
"eval_steps_per_second": 0.
|
209 |
-
"step":
|
210 |
},
|
211 |
{
|
212 |
-
"epoch":
|
213 |
"eval_accuracy": 1.0,
|
214 |
-
"eval_loss": 0.
|
215 |
-
"eval_runtime":
|
216 |
-
"eval_samples_per_second": 4.
|
217 |
-
"eval_steps_per_second": 0.
|
218 |
-
"step":
|
219 |
},
|
220 |
{
|
221 |
-
"epoch":
|
222 |
"eval_accuracy": 1.0,
|
223 |
-
"eval_loss": 0.
|
224 |
-
"eval_runtime":
|
225 |
-
"eval_samples_per_second": 4.
|
226 |
-
"eval_steps_per_second": 0.
|
227 |
-
"step":
|
228 |
},
|
229 |
{
|
230 |
-
"epoch":
|
231 |
"eval_accuracy": 1.0,
|
232 |
-
"eval_loss": 0.
|
233 |
-
"eval_runtime":
|
234 |
-
"eval_samples_per_second":
|
235 |
-
"eval_steps_per_second": 0.
|
236 |
-
"step":
|
237 |
},
|
238 |
{
|
239 |
-
"epoch":
|
240 |
-
"eval_accuracy": 0
|
241 |
-
"eval_loss": 0.
|
242 |
-
"eval_runtime":
|
243 |
-
"eval_samples_per_second":
|
244 |
-
"eval_steps_per_second": 0.
|
245 |
-
"step":
|
246 |
},
|
247 |
{
|
248 |
-
"epoch":
|
249 |
-
"eval_accuracy": 0
|
250 |
-
"eval_loss": 0.
|
251 |
-
"eval_runtime":
|
252 |
-
"eval_samples_per_second":
|
253 |
-
"eval_steps_per_second": 0.
|
254 |
-
"step":
|
255 |
},
|
256 |
{
|
257 |
-
"epoch": 26.
|
258 |
-
"
|
259 |
-
"
|
260 |
-
"
|
261 |
-
"eval_samples_per_second": 4.783,
|
262 |
-
"eval_steps_per_second": 0.259,
|
263 |
-
"step": 54
|
264 |
},
|
265 |
{
|
266 |
-
"epoch": 27.
|
267 |
-
"eval_accuracy": 0
|
268 |
-
"eval_loss": 0.
|
269 |
-
"eval_runtime": 8.
|
270 |
-
"eval_samples_per_second": 4.
|
271 |
-
"eval_steps_per_second": 0.
|
272 |
-
"step":
|
273 |
},
|
274 |
{
|
275 |
-
"epoch": 28.
|
276 |
-
"eval_accuracy": 0
|
277 |
-
"eval_loss": 0.
|
278 |
-
"eval_runtime":
|
279 |
-
"eval_samples_per_second": 5.
|
280 |
-
"eval_steps_per_second": 0.
|
281 |
-
"step":
|
282 |
},
|
283 |
{
|
284 |
-
"epoch": 29.
|
285 |
-
"
|
286 |
-
"
|
287 |
-
"
|
|
|
|
|
|
|
288 |
},
|
289 |
{
|
290 |
-
"epoch":
|
291 |
-
"eval_accuracy": 0
|
292 |
-
"eval_loss": 0.
|
293 |
-
"eval_runtime":
|
294 |
-
"eval_samples_per_second":
|
295 |
-
"eval_steps_per_second": 0.
|
296 |
-
"step":
|
297 |
},
|
298 |
{
|
299 |
-
"epoch":
|
300 |
-
"eval_accuracy": 0
|
301 |
-
"eval_loss": 0.
|
302 |
-
"eval_runtime":
|
303 |
-
"eval_samples_per_second":
|
304 |
-
"eval_steps_per_second": 0.
|
305 |
-
"step":
|
306 |
},
|
307 |
{
|
308 |
-
"epoch":
|
309 |
-
"eval_accuracy": 0
|
310 |
-
"eval_loss": 0.
|
311 |
-
"eval_runtime": 7.
|
312 |
-
"eval_samples_per_second":
|
313 |
-
"eval_steps_per_second": 0.
|
314 |
-
"step":
|
315 |
},
|
316 |
{
|
317 |
-
"epoch":
|
318 |
-
"eval_accuracy": 0
|
319 |
-
"eval_loss": 0.
|
320 |
-
"eval_runtime": 7.
|
321 |
-
"eval_samples_per_second":
|
322 |
-
"eval_steps_per_second": 0.
|
323 |
-
"step":
|
324 |
},
|
325 |
{
|
326 |
-
"epoch": 33.
|
327 |
-
"
|
328 |
-
"
|
329 |
-
"
|
330 |
-
"eval_samples_per_second": 4.767,
|
331 |
-
"eval_steps_per_second": 0.258,
|
332 |
-
"step": 68
|
333 |
},
|
334 |
{
|
335 |
-
"epoch": 34.
|
336 |
-
"eval_accuracy": 0
|
337 |
-
"eval_loss": 0.
|
338 |
-
"eval_runtime":
|
339 |
-
"eval_samples_per_second":
|
340 |
-
"eval_steps_per_second": 0.
|
341 |
-
"step":
|
342 |
},
|
343 |
{
|
344 |
-
"epoch": 35.
|
345 |
-
"eval_accuracy": 0
|
346 |
-
"eval_loss": 0.
|
347 |
-
"eval_runtime":
|
348 |
-
"eval_samples_per_second":
|
349 |
-
"eval_steps_per_second": 0.
|
350 |
-
"step":
|
351 |
},
|
352 |
{
|
353 |
-
"epoch": 36.
|
354 |
-
"eval_accuracy": 0
|
355 |
-
"eval_loss": 0.
|
356 |
-
"eval_runtime":
|
357 |
-
"eval_samples_per_second": 4.
|
358 |
-
"eval_steps_per_second": 0.
|
359 |
-
"step":
|
360 |
},
|
361 |
{
|
362 |
-
"epoch": 37.
|
363 |
-
"eval_accuracy": 0
|
364 |
-
"eval_loss": 0.
|
365 |
-
"eval_runtime":
|
366 |
-
"eval_samples_per_second":
|
367 |
-
"eval_steps_per_second": 0.
|
368 |
-
"step":
|
369 |
},
|
370 |
{
|
371 |
-
"epoch": 38.
|
372 |
-
"eval_accuracy": 0
|
373 |
-
"eval_loss": 0.
|
374 |
-
"eval_runtime": 7.
|
375 |
-
"eval_samples_per_second":
|
376 |
-
"eval_steps_per_second": 0.
|
377 |
-
"step":
|
378 |
},
|
379 |
{
|
380 |
-
"epoch": 39.
|
381 |
-
"
|
382 |
-
"
|
383 |
-
"
|
|
|
|
|
|
|
384 |
},
|
385 |
{
|
386 |
-
"epoch":
|
387 |
-
"
|
388 |
-
"
|
389 |
-
"
|
390 |
-
"eval_samples_per_second": 4.392,
|
391 |
-
"eval_steps_per_second": 0.237,
|
392 |
-
"step": 80
|
393 |
},
|
394 |
{
|
395 |
-
"epoch":
|
396 |
-
"
|
397 |
-
"
|
398 |
-
"
|
399 |
-
"
|
400 |
-
"
|
401 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
402 |
}
|
403 |
],
|
404 |
-
"max_steps":
|
405 |
"num_train_epochs": 40,
|
406 |
-
"total_flos": 3.
|
407 |
"trial_name": null,
|
408 |
"trial_params": null
|
409 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.0,
|
3 |
+
"best_model_checkpoint": "delivery_truck_classification\\checkpoint-18",
|
4 |
+
"epoch": 40.0,
|
5 |
+
"global_step": 120,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.95,
|
13 |
+
"eval_loss": 0.16261602938175201,
|
14 |
+
"eval_runtime": 8.6031,
|
15 |
+
"eval_samples_per_second": 4.649,
|
16 |
+
"eval_steps_per_second": 0.232,
|
17 |
+
"step": 3
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.95,
|
22 |
+
"eval_loss": 0.1592799872159958,
|
23 |
+
"eval_runtime": 8.1709,
|
24 |
+
"eval_samples_per_second": 4.895,
|
25 |
+
"eval_steps_per_second": 0.245,
|
26 |
+
"step": 6
|
27 |
},
|
28 |
{
|
29 |
+
"epoch": 3.0,
|
30 |
+
"eval_accuracy": 0.95,
|
31 |
+
"eval_loss": 0.13422292470932007,
|
32 |
+
"eval_runtime": 8.0249,
|
33 |
+
"eval_samples_per_second": 4.984,
|
34 |
+
"eval_steps_per_second": 0.249,
|
35 |
+
"step": 9
|
36 |
},
|
37 |
{
|
38 |
+
"epoch": 4.0,
|
39 |
+
"eval_accuracy": 0.975,
|
40 |
+
"eval_loss": 0.08705286681652069,
|
41 |
+
"eval_runtime": 8.0216,
|
42 |
+
"eval_samples_per_second": 4.987,
|
43 |
+
"eval_steps_per_second": 0.249,
|
44 |
+
"step": 12
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 5.0,
|
48 |
+
"eval_accuracy": 0.975,
|
49 |
+
"eval_loss": 0.06115349009633064,
|
50 |
+
"eval_runtime": 7.8977,
|
51 |
+
"eval_samples_per_second": 5.065,
|
52 |
+
"eval_steps_per_second": 0.253,
|
53 |
+
"step": 15
|
54 |
},
|
55 |
{
|
56 |
+
"epoch": 6.0,
|
57 |
"eval_accuracy": 1.0,
|
58 |
+
"eval_loss": 0.04307302460074425,
|
59 |
+
"eval_runtime": 8.1309,
|
60 |
+
"eval_samples_per_second": 4.92,
|
61 |
+
"eval_steps_per_second": 0.246,
|
62 |
+
"step": 18
|
63 |
},
|
64 |
{
|
65 |
+
"epoch": 6.67,
|
66 |
+
"learning_rate": 4.62962962962963e-05,
|
67 |
+
"loss": 0.2745,
|
68 |
+
"step": 20
|
|
|
|
|
|
|
69 |
},
|
70 |
{
|
71 |
+
"epoch": 7.0,
|
72 |
"eval_accuracy": 1.0,
|
73 |
+
"eval_loss": 0.03329644352197647,
|
74 |
+
"eval_runtime": 8.4823,
|
75 |
+
"eval_samples_per_second": 4.716,
|
76 |
+
"eval_steps_per_second": 0.236,
|
77 |
+
"step": 21
|
78 |
},
|
79 |
{
|
80 |
+
"epoch": 8.0,
|
81 |
"eval_accuracy": 1.0,
|
82 |
+
"eval_loss": 0.048651862889528275,
|
83 |
+
"eval_runtime": 7.9701,
|
84 |
+
"eval_samples_per_second": 5.019,
|
85 |
+
"eval_steps_per_second": 0.251,
|
86 |
+
"step": 24
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 9.0,
|
90 |
"eval_accuracy": 1.0,
|
91 |
+
"eval_loss": 0.045587461441755295,
|
92 |
+
"eval_runtime": 7.8557,
|
93 |
+
"eval_samples_per_second": 5.092,
|
94 |
+
"eval_steps_per_second": 0.255,
|
95 |
+
"step": 27
|
96 |
},
|
97 |
{
|
98 |
+
"epoch": 10.0,
|
99 |
+
"eval_accuracy": 1.0,
|
100 |
+
"eval_loss": 0.02726823464035988,
|
101 |
+
"eval_runtime": 8.1787,
|
102 |
+
"eval_samples_per_second": 4.891,
|
103 |
+
"eval_steps_per_second": 0.245,
|
104 |
+
"step": 30
|
105 |
},
|
106 |
{
|
107 |
+
"epoch": 11.0,
|
108 |
"eval_accuracy": 1.0,
|
109 |
+
"eval_loss": 0.017963390797376633,
|
110 |
+
"eval_runtime": 8.3083,
|
111 |
+
"eval_samples_per_second": 4.814,
|
112 |
+
"eval_steps_per_second": 0.241,
|
113 |
+
"step": 33
|
114 |
},
|
115 |
{
|
116 |
+
"epoch": 12.0,
|
117 |
"eval_accuracy": 1.0,
|
118 |
+
"eval_loss": 0.016819924116134644,
|
119 |
+
"eval_runtime": 8.1002,
|
120 |
+
"eval_samples_per_second": 4.938,
|
121 |
+
"eval_steps_per_second": 0.247,
|
122 |
+
"step": 36
|
123 |
},
|
124 |
{
|
125 |
+
"epoch": 13.0,
|
126 |
+
"eval_accuracy": 1.0,
|
127 |
+
"eval_loss": 0.031003978103399277,
|
128 |
+
"eval_runtime": 8.1225,
|
129 |
+
"eval_samples_per_second": 4.925,
|
130 |
+
"eval_steps_per_second": 0.246,
|
131 |
+
"step": 39
|
132 |
},
|
133 |
{
|
134 |
+
"epoch": 13.33,
|
135 |
+
"learning_rate": 3.7037037037037037e-05,
|
136 |
+
"loss": 0.1782,
|
137 |
+
"step": 40
|
|
|
|
|
|
|
138 |
},
|
139 |
{
|
140 |
+
"epoch": 14.0,
|
141 |
+
"eval_accuracy": 0.975,
|
142 |
+
"eval_loss": 0.043801963329315186,
|
143 |
+
"eval_runtime": 8.6445,
|
144 |
+
"eval_samples_per_second": 4.627,
|
145 |
+
"eval_steps_per_second": 0.231,
|
146 |
+
"step": 42
|
147 |
},
|
148 |
{
|
149 |
+
"epoch": 15.0,
|
150 |
+
"eval_accuracy": 0.975,
|
151 |
+
"eval_loss": 0.07503340393304825,
|
152 |
+
"eval_runtime": 7.8763,
|
153 |
+
"eval_samples_per_second": 5.079,
|
154 |
+
"eval_steps_per_second": 0.254,
|
155 |
+
"step": 45
|
156 |
},
|
157 |
{
|
158 |
+
"epoch": 16.0,
|
159 |
+
"eval_accuracy": 0.975,
|
160 |
+
"eval_loss": 0.03957166522741318,
|
161 |
+
"eval_runtime": 8.3356,
|
162 |
+
"eval_samples_per_second": 4.799,
|
163 |
+
"eval_steps_per_second": 0.24,
|
164 |
+
"step": 48
|
165 |
},
|
166 |
{
|
167 |
+
"epoch": 17.0,
|
168 |
"eval_accuracy": 1.0,
|
169 |
+
"eval_loss": 0.017652835696935654,
|
170 |
+
"eval_runtime": 7.9389,
|
171 |
+
"eval_samples_per_second": 5.038,
|
172 |
+
"eval_steps_per_second": 0.252,
|
173 |
+
"step": 51
|
174 |
},
|
175 |
{
|
176 |
+
"epoch": 18.0,
|
177 |
+
"eval_accuracy": 1.0,
|
178 |
+
"eval_loss": 0.02170238085091114,
|
179 |
+
"eval_runtime": 8.0236,
|
180 |
+
"eval_samples_per_second": 4.985,
|
181 |
+
"eval_steps_per_second": 0.249,
|
182 |
+
"step": 54
|
183 |
},
|
184 |
{
|
185 |
+
"epoch": 19.0,
|
186 |
+
"eval_accuracy": 1.0,
|
187 |
+
"eval_loss": 0.011599823832511902,
|
188 |
+
"eval_runtime": 8.0424,
|
189 |
+
"eval_samples_per_second": 4.974,
|
190 |
+
"eval_steps_per_second": 0.249,
|
191 |
+
"step": 57
|
192 |
},
|
193 |
{
|
194 |
+
"epoch": 20.0,
|
195 |
"learning_rate": 2.777777777777778e-05,
|
196 |
+
"loss": 0.1624,
|
197 |
+
"step": 60
|
198 |
},
|
199 |
{
|
200 |
+
"epoch": 20.0,
|
201 |
+
"eval_accuracy": 1.0,
|
202 |
+
"eval_loss": 0.008052630349993706,
|
203 |
+
"eval_runtime": 8.0111,
|
204 |
+
"eval_samples_per_second": 4.993,
|
205 |
+
"eval_steps_per_second": 0.25,
|
206 |
+
"step": 60
|
207 |
},
|
208 |
{
|
209 |
+
"epoch": 21.0,
|
210 |
"eval_accuracy": 1.0,
|
211 |
+
"eval_loss": 0.006596912629902363,
|
212 |
+
"eval_runtime": 8.4146,
|
213 |
+
"eval_samples_per_second": 4.754,
|
214 |
+
"eval_steps_per_second": 0.238,
|
215 |
+
"step": 63
|
216 |
},
|
217 |
{
|
218 |
+
"epoch": 22.0,
|
219 |
"eval_accuracy": 1.0,
|
220 |
+
"eval_loss": 0.008253499865531921,
|
221 |
+
"eval_runtime": 8.4625,
|
222 |
+
"eval_samples_per_second": 4.727,
|
223 |
+
"eval_steps_per_second": 0.236,
|
224 |
+
"step": 66
|
225 |
},
|
226 |
{
|
227 |
+
"epoch": 23.0,
|
228 |
"eval_accuracy": 1.0,
|
229 |
+
"eval_loss": 0.012594206258654594,
|
230 |
+
"eval_runtime": 8.1933,
|
231 |
+
"eval_samples_per_second": 4.882,
|
232 |
+
"eval_steps_per_second": 0.244,
|
233 |
+
"step": 69
|
234 |
},
|
235 |
{
|
236 |
+
"epoch": 24.0,
|
237 |
"eval_accuracy": 1.0,
|
238 |
+
"eval_loss": 0.015849163755774498,
|
239 |
+
"eval_runtime": 7.9982,
|
240 |
+
"eval_samples_per_second": 5.001,
|
241 |
+
"eval_steps_per_second": 0.25,
|
242 |
+
"step": 72
|
243 |
},
|
244 |
{
|
245 |
+
"epoch": 25.0,
|
246 |
+
"eval_accuracy": 1.0,
|
247 |
+
"eval_loss": 0.01883917860686779,
|
248 |
+
"eval_runtime": 7.9429,
|
249 |
+
"eval_samples_per_second": 5.036,
|
250 |
+
"eval_steps_per_second": 0.252,
|
251 |
+
"step": 75
|
252 |
},
|
253 |
{
|
254 |
+
"epoch": 26.0,
|
255 |
+
"eval_accuracy": 1.0,
|
256 |
+
"eval_loss": 0.014945434406399727,
|
257 |
+
"eval_runtime": 8.0615,
|
258 |
+
"eval_samples_per_second": 4.962,
|
259 |
+
"eval_steps_per_second": 0.248,
|
260 |
+
"step": 78
|
261 |
},
|
262 |
{
|
263 |
+
"epoch": 26.67,
|
264 |
+
"learning_rate": 1.8518518518518518e-05,
|
265 |
+
"loss": 0.1475,
|
266 |
+
"step": 80
|
|
|
|
|
|
|
267 |
},
|
268 |
{
|
269 |
+
"epoch": 27.0,
|
270 |
+
"eval_accuracy": 1.0,
|
271 |
+
"eval_loss": 0.010075708851218224,
|
272 |
+
"eval_runtime": 8.0344,
|
273 |
+
"eval_samples_per_second": 4.979,
|
274 |
+
"eval_steps_per_second": 0.249,
|
275 |
+
"step": 81
|
276 |
},
|
277 |
{
|
278 |
+
"epoch": 28.0,
|
279 |
+
"eval_accuracy": 1.0,
|
280 |
+
"eval_loss": 0.006395348347723484,
|
281 |
+
"eval_runtime": 7.9204,
|
282 |
+
"eval_samples_per_second": 5.05,
|
283 |
+
"eval_steps_per_second": 0.253,
|
284 |
+
"step": 84
|
285 |
},
|
286 |
{
|
287 |
+
"epoch": 29.0,
|
288 |
+
"eval_accuracy": 1.0,
|
289 |
+
"eval_loss": 0.004969631787389517,
|
290 |
+
"eval_runtime": 8.1818,
|
291 |
+
"eval_samples_per_second": 4.889,
|
292 |
+
"eval_steps_per_second": 0.244,
|
293 |
+
"step": 87
|
294 |
},
|
295 |
{
|
296 |
+
"epoch": 30.0,
|
297 |
+
"eval_accuracy": 1.0,
|
298 |
+
"eval_loss": 0.005222103092819452,
|
299 |
+
"eval_runtime": 7.9872,
|
300 |
+
"eval_samples_per_second": 5.008,
|
301 |
+
"eval_steps_per_second": 0.25,
|
302 |
+
"step": 90
|
303 |
},
|
304 |
{
|
305 |
+
"epoch": 31.0,
|
306 |
+
"eval_accuracy": 1.0,
|
307 |
+
"eval_loss": 0.006443561054766178,
|
308 |
+
"eval_runtime": 7.9514,
|
309 |
+
"eval_samples_per_second": 5.031,
|
310 |
+
"eval_steps_per_second": 0.252,
|
311 |
+
"step": 93
|
312 |
},
|
313 |
{
|
314 |
+
"epoch": 32.0,
|
315 |
+
"eval_accuracy": 1.0,
|
316 |
+
"eval_loss": 0.006998550146818161,
|
317 |
+
"eval_runtime": 7.9811,
|
318 |
+
"eval_samples_per_second": 5.012,
|
319 |
+
"eval_steps_per_second": 0.251,
|
320 |
+
"step": 96
|
321 |
},
|
322 |
{
|
323 |
+
"epoch": 33.0,
|
324 |
+
"eval_accuracy": 1.0,
|
325 |
+
"eval_loss": 0.006886245217174292,
|
326 |
+
"eval_runtime": 7.9804,
|
327 |
+
"eval_samples_per_second": 5.012,
|
328 |
+
"eval_steps_per_second": 0.251,
|
329 |
+
"step": 99
|
330 |
},
|
331 |
{
|
332 |
+
"epoch": 33.33,
|
333 |
+
"learning_rate": 9.259259259259259e-06,
|
334 |
+
"loss": 0.1345,
|
335 |
+
"step": 100
|
|
|
|
|
|
|
336 |
},
|
337 |
{
|
338 |
+
"epoch": 34.0,
|
339 |
+
"eval_accuracy": 1.0,
|
340 |
+
"eval_loss": 0.005939379800111055,
|
341 |
+
"eval_runtime": 7.962,
|
342 |
+
"eval_samples_per_second": 5.024,
|
343 |
+
"eval_steps_per_second": 0.251,
|
344 |
+
"step": 102
|
345 |
},
|
346 |
{
|
347 |
+
"epoch": 35.0,
|
348 |
+
"eval_accuracy": 1.0,
|
349 |
+
"eval_loss": 0.004927521105855703,
|
350 |
+
"eval_runtime": 7.9624,
|
351 |
+
"eval_samples_per_second": 5.024,
|
352 |
+
"eval_steps_per_second": 0.251,
|
353 |
+
"step": 105
|
354 |
},
|
355 |
{
|
356 |
+
"epoch": 36.0,
|
357 |
+
"eval_accuracy": 1.0,
|
358 |
+
"eval_loss": 0.004319839645177126,
|
359 |
+
"eval_runtime": 8.2724,
|
360 |
+
"eval_samples_per_second": 4.835,
|
361 |
+
"eval_steps_per_second": 0.242,
|
362 |
+
"step": 108
|
363 |
},
|
364 |
{
|
365 |
+
"epoch": 37.0,
|
366 |
+
"eval_accuracy": 1.0,
|
367 |
+
"eval_loss": 0.0039680288173258305,
|
368 |
+
"eval_runtime": 7.994,
|
369 |
+
"eval_samples_per_second": 5.004,
|
370 |
+
"eval_steps_per_second": 0.25,
|
371 |
+
"step": 111
|
372 |
},
|
373 |
{
|
374 |
+
"epoch": 38.0,
|
375 |
+
"eval_accuracy": 1.0,
|
376 |
+
"eval_loss": 0.003840196877717972,
|
377 |
+
"eval_runtime": 7.8877,
|
378 |
+
"eval_samples_per_second": 5.071,
|
379 |
+
"eval_steps_per_second": 0.254,
|
380 |
+
"step": 114
|
381 |
},
|
382 |
{
|
383 |
+
"epoch": 39.0,
|
384 |
+
"eval_accuracy": 1.0,
|
385 |
+
"eval_loss": 0.0038244160823524,
|
386 |
+
"eval_runtime": 8.0172,
|
387 |
+
"eval_samples_per_second": 4.989,
|
388 |
+
"eval_steps_per_second": 0.249,
|
389 |
+
"step": 117
|
390 |
},
|
391 |
{
|
392 |
+
"epoch": 40.0,
|
393 |
+
"learning_rate": 0.0,
|
394 |
+
"loss": 0.1232,
|
395 |
+
"step": 120
|
|
|
|
|
|
|
396 |
},
|
397 |
{
|
398 |
+
"epoch": 40.0,
|
399 |
+
"eval_accuracy": 1.0,
|
400 |
+
"eval_loss": 0.003828426357358694,
|
401 |
+
"eval_runtime": 7.9122,
|
402 |
+
"eval_samples_per_second": 5.055,
|
403 |
+
"eval_steps_per_second": 0.253,
|
404 |
+
"step": 120
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 40.0,
|
408 |
+
"step": 120,
|
409 |
+
"total_flos": 3.579662466809856e+17,
|
410 |
+
"train_loss": 0.17003339926401775,
|
411 |
+
"train_runtime": 8221.5625,
|
412 |
+
"train_samples_per_second": 1.751,
|
413 |
+
"train_steps_per_second": 0.015
|
414 |
}
|
415 |
],
|
416 |
+
"max_steps": 120,
|
417 |
"num_train_epochs": 40,
|
418 |
+
"total_flos": 3.579662466809856e+17,
|
419 |
"trial_name": null,
|
420 |
"trial_params": null
|
421 |
}
|