jlondonobo
commited on
Commit
•
5225fa2
1
Parent(s):
c9b640a
End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.35,
|
3 |
+
"eval_loss": 0.164794921875,
|
4 |
+
"eval_runtime": 4368.9954,
|
5 |
+
"eval_samples_per_second": 3.552,
|
6 |
+
"eval_steps_per_second": 0.222,
|
7 |
+
"eval_wer": 5.074450392391248,
|
8 |
+
"train_loss": 0.1855107421875,
|
9 |
+
"train_runtime": 20533.0269,
|
10 |
+
"train_samples_per_second": 2.338,
|
11 |
+
"train_steps_per_second": 0.073
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.35,
|
3 |
+
"eval_loss": 0.164794921875,
|
4 |
+
"eval_runtime": 4368.9954,
|
5 |
+
"eval_samples_per_second": 3.552,
|
6 |
+
"eval_steps_per_second": 0.222,
|
7 |
+
"eval_wer": 5.074450392391248
|
8 |
+
}
|
runs/Dec18_04-33-26_193-122-153-4/events.out.tfevents.1671363049.193-122-153-4.1752857.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62a08f6eef811d26cba951e7b3a55fde0ceaa59193f575f17b5d191ab1da0ae7
|
3 |
+
size 358
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.35,
|
3 |
+
"train_loss": 0.1855107421875,
|
4 |
+
"train_runtime": 20533.0269,
|
5 |
+
"train_samples_per_second": 2.338,
|
6 |
+
"train_steps_per_second": 0.073
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,403 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 5.074450392391248,
|
3 |
+
"best_model_checkpoint": "./checkpoint-1500",
|
4 |
+
"epoch": 1.3533333333333333,
|
5 |
+
"global_step": 1500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.02,
|
12 |
+
"learning_rate": 9.87983978638184e-07,
|
13 |
+
"loss": 0.676,
|
14 |
+
"step": 25
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.03,
|
18 |
+
"learning_rate": 9.712950600801067e-07,
|
19 |
+
"loss": 0.3062,
|
20 |
+
"step": 50
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.05,
|
24 |
+
"learning_rate": 9.546061415220292e-07,
|
25 |
+
"loss": 0.2604,
|
26 |
+
"step": 75
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.07,
|
30 |
+
"learning_rate": 9.379172229639519e-07,
|
31 |
+
"loss": 0.2175,
|
32 |
+
"step": 100
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.08,
|
36 |
+
"learning_rate": 9.212283044058745e-07,
|
37 |
+
"loss": 0.2147,
|
38 |
+
"step": 125
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.1,
|
42 |
+
"learning_rate": 9.04539385847797e-07,
|
43 |
+
"loss": 0.1825,
|
44 |
+
"step": 150
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.12,
|
48 |
+
"learning_rate": 8.885180240320427e-07,
|
49 |
+
"loss": 0.168,
|
50 |
+
"step": 175
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.13,
|
54 |
+
"learning_rate": 8.718291054739653e-07,
|
55 |
+
"loss": 0.1771,
|
56 |
+
"step": 200
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.15,
|
60 |
+
"learning_rate": 8.551401869158879e-07,
|
61 |
+
"loss": 0.1862,
|
62 |
+
"step": 225
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.17,
|
66 |
+
"learning_rate": 8.384512683578104e-07,
|
67 |
+
"loss": 0.1867,
|
68 |
+
"step": 250
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.18,
|
72 |
+
"learning_rate": 8.21762349799733e-07,
|
73 |
+
"loss": 0.1652,
|
74 |
+
"step": 275
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.2,
|
78 |
+
"learning_rate": 8.050734312416555e-07,
|
79 |
+
"loss": 0.1583,
|
80 |
+
"step": 300
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.22,
|
84 |
+
"learning_rate": 7.883845126835781e-07,
|
85 |
+
"loss": 0.1562,
|
86 |
+
"step": 325
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.23,
|
90 |
+
"learning_rate": 7.716955941255007e-07,
|
91 |
+
"loss": 0.1607,
|
92 |
+
"step": 350
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.25,
|
96 |
+
"learning_rate": 7.550066755674232e-07,
|
97 |
+
"loss": 0.1422,
|
98 |
+
"step": 375
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.27,
|
102 |
+
"learning_rate": 7.383177570093458e-07,
|
103 |
+
"loss": 0.1508,
|
104 |
+
"step": 400
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.28,
|
108 |
+
"learning_rate": 7.216288384512683e-07,
|
109 |
+
"loss": 0.1556,
|
110 |
+
"step": 425
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.3,
|
114 |
+
"learning_rate": 7.049399198931909e-07,
|
115 |
+
"loss": 0.1581,
|
116 |
+
"step": 450
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.32,
|
120 |
+
"learning_rate": 6.882510013351135e-07,
|
121 |
+
"loss": 0.1738,
|
122 |
+
"step": 475
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.33,
|
126 |
+
"learning_rate": 6.71562082777036e-07,
|
127 |
+
"loss": 0.151,
|
128 |
+
"step": 500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.35,
|
132 |
+
"learning_rate": 6.548731642189586e-07,
|
133 |
+
"loss": 0.1471,
|
134 |
+
"step": 525
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.37,
|
138 |
+
"learning_rate": 6.381842456608812e-07,
|
139 |
+
"loss": 0.1491,
|
140 |
+
"step": 550
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.38,
|
144 |
+
"learning_rate": 6.214953271028037e-07,
|
145 |
+
"loss": 0.1388,
|
146 |
+
"step": 575
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.4,
|
150 |
+
"learning_rate": 6.048064085447263e-07,
|
151 |
+
"loss": 0.1521,
|
152 |
+
"step": 600
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.42,
|
156 |
+
"learning_rate": 5.887850467289718e-07,
|
157 |
+
"loss": 0.1572,
|
158 |
+
"step": 625
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.43,
|
162 |
+
"learning_rate": 5.720961281708944e-07,
|
163 |
+
"loss": 0.1577,
|
164 |
+
"step": 650
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.45,
|
168 |
+
"learning_rate": 5.55407209612817e-07,
|
169 |
+
"loss": 0.1416,
|
170 |
+
"step": 675
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.47,
|
174 |
+
"learning_rate": 5.387182910547396e-07,
|
175 |
+
"loss": 0.1375,
|
176 |
+
"step": 700
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.48,
|
180 |
+
"learning_rate": 5.220293724966622e-07,
|
181 |
+
"loss": 0.1228,
|
182 |
+
"step": 725
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.5,
|
186 |
+
"learning_rate": 5.053404539385847e-07,
|
187 |
+
"loss": 0.1556,
|
188 |
+
"step": 750
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.5,
|
192 |
+
"eval_loss": 0.1683349609375,
|
193 |
+
"eval_runtime": 4390.4106,
|
194 |
+
"eval_samples_per_second": 3.535,
|
195 |
+
"eval_steps_per_second": 0.221,
|
196 |
+
"eval_wer": 5.095888987058885,
|
197 |
+
"step": 750
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 0.52,
|
201 |
+
"learning_rate": 4.886515353805072e-07,
|
202 |
+
"loss": 0.1318,
|
203 |
+
"step": 775
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.53,
|
207 |
+
"learning_rate": 4.719626168224299e-07,
|
208 |
+
"loss": 0.1586,
|
209 |
+
"step": 800
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.55,
|
213 |
+
"learning_rate": 4.5527369826435247e-07,
|
214 |
+
"loss": 0.1403,
|
215 |
+
"step": 825
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.57,
|
219 |
+
"learning_rate": 4.38584779706275e-07,
|
220 |
+
"loss": 0.144,
|
221 |
+
"step": 850
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.58,
|
225 |
+
"learning_rate": 4.225634178905207e-07,
|
226 |
+
"loss": 0.1417,
|
227 |
+
"step": 875
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.6,
|
231 |
+
"learning_rate": 4.058744993324432e-07,
|
232 |
+
"loss": 0.1544,
|
233 |
+
"step": 900
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.62,
|
237 |
+
"learning_rate": 3.891855807743658e-07,
|
238 |
+
"loss": 0.1483,
|
239 |
+
"step": 925
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.63,
|
243 |
+
"learning_rate": 3.724966622162884e-07,
|
244 |
+
"loss": 0.1469,
|
245 |
+
"step": 950
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 1.0,
|
249 |
+
"learning_rate": 3.558077436582109e-07,
|
250 |
+
"loss": 0.1782,
|
251 |
+
"step": 975
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.02,
|
255 |
+
"learning_rate": 3.391188251001335e-07,
|
256 |
+
"loss": 0.2161,
|
257 |
+
"step": 1000
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.04,
|
261 |
+
"learning_rate": 3.22429906542056e-07,
|
262 |
+
"loss": 0.1903,
|
263 |
+
"step": 1025
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.05,
|
267 |
+
"learning_rate": 3.057409879839786e-07,
|
268 |
+
"loss": 0.2003,
|
269 |
+
"step": 1050
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 1.07,
|
273 |
+
"learning_rate": 2.890520694259012e-07,
|
274 |
+
"loss": 0.2123,
|
275 |
+
"step": 1075
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.09,
|
279 |
+
"learning_rate": 2.723631508678237e-07,
|
280 |
+
"loss": 0.2347,
|
281 |
+
"step": 1100
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.1,
|
285 |
+
"learning_rate": 2.5567423230974635e-07,
|
286 |
+
"loss": 0.1982,
|
287 |
+
"step": 1125
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 1.12,
|
291 |
+
"learning_rate": 2.389853137516689e-07,
|
292 |
+
"loss": 0.1899,
|
293 |
+
"step": 1150
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.14,
|
297 |
+
"learning_rate": 2.2229639519359144e-07,
|
298 |
+
"loss": 0.1865,
|
299 |
+
"step": 1175
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.15,
|
303 |
+
"learning_rate": 2.05607476635514e-07,
|
304 |
+
"loss": 0.204,
|
305 |
+
"step": 1200
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 1.17,
|
309 |
+
"learning_rate": 1.8891855807743656e-07,
|
310 |
+
"loss": 0.2119,
|
311 |
+
"step": 1225
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 1.19,
|
315 |
+
"learning_rate": 1.7222963951935914e-07,
|
316 |
+
"loss": 0.2108,
|
317 |
+
"step": 1250
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.2,
|
321 |
+
"learning_rate": 1.555407209612817e-07,
|
322 |
+
"loss": 0.229,
|
323 |
+
"step": 1275
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.22,
|
327 |
+
"learning_rate": 1.3885180240320425e-07,
|
328 |
+
"loss": 0.2851,
|
329 |
+
"step": 1300
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 1.24,
|
333 |
+
"learning_rate": 1.221628838451268e-07,
|
334 |
+
"loss": 0.1927,
|
335 |
+
"step": 1325
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 1.25,
|
339 |
+
"learning_rate": 1.054739652870494e-07,
|
340 |
+
"loss": 0.1675,
|
341 |
+
"step": 1350
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 1.27,
|
345 |
+
"learning_rate": 8.878504672897195e-08,
|
346 |
+
"loss": 0.167,
|
347 |
+
"step": 1375
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 1.29,
|
351 |
+
"learning_rate": 7.209612817089452e-08,
|
352 |
+
"loss": 0.176,
|
353 |
+
"step": 1400
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.3,
|
357 |
+
"learning_rate": 5.5407209612817086e-08,
|
358 |
+
"loss": 0.1718,
|
359 |
+
"step": 1425
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.32,
|
363 |
+
"learning_rate": 3.871829105473965e-08,
|
364 |
+
"loss": 0.1831,
|
365 |
+
"step": 1450
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 1.34,
|
369 |
+
"learning_rate": 2.2029372496662217e-08,
|
370 |
+
"loss": 0.1793,
|
371 |
+
"step": 1475
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 1.35,
|
375 |
+
"learning_rate": 5.3404539385847795e-09,
|
376 |
+
"loss": 0.1732,
|
377 |
+
"step": 1500
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 1.35,
|
381 |
+
"eval_loss": 0.164794921875,
|
382 |
+
"eval_runtime": 4364.6715,
|
383 |
+
"eval_samples_per_second": 3.556,
|
384 |
+
"eval_steps_per_second": 0.222,
|
385 |
+
"eval_wer": 5.074450392391248,
|
386 |
+
"step": 1500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 1.35,
|
390 |
+
"step": 1500,
|
391 |
+
"total_flos": 1.0191220995495297e+20,
|
392 |
+
"train_loss": 0.1855107421875,
|
393 |
+
"train_runtime": 20533.0269,
|
394 |
+
"train_samples_per_second": 2.338,
|
395 |
+
"train_steps_per_second": 0.073
|
396 |
+
}
|
397 |
+
],
|
398 |
+
"max_steps": 1500,
|
399 |
+
"num_train_epochs": 9223372036854775807,
|
400 |
+
"total_flos": 1.0191220995495297e+20,
|
401 |
+
"trial_name": null,
|
402 |
+
"trial_params": null
|
403 |
+
}
|