alinerodrigues
commited on
Commit
•
b0f3369
1
Parent(s):
a0e9b53
End of training
Browse files- all_results.json +16 -0
- eval_results.json +10 -0
- train_results.json +9 -0
- trainer_state.json +387 -0
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 32.0,
|
3 |
+
"eval_cer": 0.033413205537806176,
|
4 |
+
"eval_loss": 0.21965597569942474,
|
5 |
+
"eval_runtime": 5.3256,
|
6 |
+
"eval_samples": 86,
|
7 |
+
"eval_samples_per_second": 16.148,
|
8 |
+
"eval_steps_per_second": 2.065,
|
9 |
+
"eval_wer": 0.09813084112149532,
|
10 |
+
"total_flos": 1.751552315123992e+19,
|
11 |
+
"train_loss": 0.6797193247218465,
|
12 |
+
"train_runtime": 4402.1651,
|
13 |
+
"train_samples": 683,
|
14 |
+
"train_samples_per_second": 15.515,
|
15 |
+
"train_steps_per_second": 0.477
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 32.0,
|
3 |
+
"eval_cer": 0.033413205537806176,
|
4 |
+
"eval_loss": 0.21965597569942474,
|
5 |
+
"eval_runtime": 5.3256,
|
6 |
+
"eval_samples": 86,
|
7 |
+
"eval_samples_per_second": 16.148,
|
8 |
+
"eval_steps_per_second": 2.065,
|
9 |
+
"eval_wer": 0.09813084112149532
|
10 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 32.0,
|
3 |
+
"total_flos": 1.751552315123992e+19,
|
4 |
+
"train_loss": 0.6797193247218465,
|
5 |
+
"train_runtime": 4402.1651,
|
6 |
+
"train_samples": 683,
|
7 |
+
"train_samples_per_second": 15.515,
|
8 |
+
"train_steps_per_second": 0.477
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,387 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.21965597569942474,
|
3 |
+
"best_model_checkpoint": "wav2vec2-xlsr-1b-mecita-portuguese-all-text-protecao_aos_pandas-os_morcegos/checkpoint-258",
|
4 |
+
"epoch": 32.0,
|
5 |
+
"global_step": 688,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.05,
|
12 |
+
"learning_rate": 2.9985714285714284e-05,
|
13 |
+
"loss": 13.2168,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.98,
|
18 |
+
"eval_cer": 1.0,
|
19 |
+
"eval_loss": 2.912194013595581,
|
20 |
+
"eval_runtime": 5.4283,
|
21 |
+
"eval_samples_per_second": 15.843,
|
22 |
+
"eval_steps_per_second": 2.026,
|
23 |
+
"eval_wer": 1.0,
|
24 |
+
"step": 21
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"eval_cer": 1.0,
|
29 |
+
"eval_loss": 2.9751322269439697,
|
30 |
+
"eval_runtime": 5.3304,
|
31 |
+
"eval_samples_per_second": 16.134,
|
32 |
+
"eval_steps_per_second": 2.064,
|
33 |
+
"eval_wer": 1.0,
|
34 |
+
"step": 43
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.98,
|
38 |
+
"eval_cer": 1.0,
|
39 |
+
"eval_loss": 2.8292453289031982,
|
40 |
+
"eval_runtime": 5.3441,
|
41 |
+
"eval_samples_per_second": 16.092,
|
42 |
+
"eval_steps_per_second": 2.058,
|
43 |
+
"eval_wer": 1.0,
|
44 |
+
"step": 64
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 4.0,
|
48 |
+
"eval_cer": 0.999866879659212,
|
49 |
+
"eval_loss": 2.587308406829834,
|
50 |
+
"eval_runtime": 5.3309,
|
51 |
+
"eval_samples_per_second": 16.132,
|
52 |
+
"eval_steps_per_second": 2.063,
|
53 |
+
"eval_wer": 0.9992211838006231,
|
54 |
+
"step": 86
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 4.65,
|
58 |
+
"learning_rate": 2.86e-05,
|
59 |
+
"loss": 3.3173,
|
60 |
+
"step": 100
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 4.98,
|
64 |
+
"eval_cer": 0.23575612353567624,
|
65 |
+
"eval_loss": 1.0785298347473145,
|
66 |
+
"eval_runtime": 5.4048,
|
67 |
+
"eval_samples_per_second": 15.912,
|
68 |
+
"eval_steps_per_second": 2.035,
|
69 |
+
"eval_wer": 0.8940809968847352,
|
70 |
+
"step": 107
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 6.0,
|
74 |
+
"eval_cer": 0.06110223642172524,
|
75 |
+
"eval_loss": 0.3221881687641144,
|
76 |
+
"eval_runtime": 5.3075,
|
77 |
+
"eval_samples_per_second": 16.204,
|
78 |
+
"eval_steps_per_second": 2.073,
|
79 |
+
"eval_wer": 0.23052959501557632,
|
80 |
+
"step": 129
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 6.98,
|
84 |
+
"eval_cer": 0.0424653887113951,
|
85 |
+
"eval_loss": 0.2690502405166626,
|
86 |
+
"eval_runtime": 5.3502,
|
87 |
+
"eval_samples_per_second": 16.074,
|
88 |
+
"eval_steps_per_second": 2.056,
|
89 |
+
"eval_wer": 0.13629283489096572,
|
90 |
+
"step": 150
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 8.0,
|
94 |
+
"eval_cer": 0.03727369542066028,
|
95 |
+
"eval_loss": 0.23176124691963196,
|
96 |
+
"eval_runtime": 5.3567,
|
97 |
+
"eval_samples_per_second": 16.055,
|
98 |
+
"eval_steps_per_second": 2.053,
|
99 |
+
"eval_wer": 0.11682242990654206,
|
100 |
+
"step": 172
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 8.98,
|
104 |
+
"eval_cer": 0.03394568690095846,
|
105 |
+
"eval_loss": 0.22206291556358337,
|
106 |
+
"eval_runtime": 5.3897,
|
107 |
+
"eval_samples_per_second": 15.956,
|
108 |
+
"eval_steps_per_second": 2.041,
|
109 |
+
"eval_wer": 0.09657320872274143,
|
110 |
+
"step": 193
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 9.3,
|
114 |
+
"learning_rate": 2.717142857142857e-05,
|
115 |
+
"loss": 0.5524,
|
116 |
+
"step": 200
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 10.0,
|
120 |
+
"eval_cer": 0.03487752928647497,
|
121 |
+
"eval_loss": 0.22993727028369904,
|
122 |
+
"eval_runtime": 5.3145,
|
123 |
+
"eval_samples_per_second": 16.182,
|
124 |
+
"eval_steps_per_second": 2.07,
|
125 |
+
"eval_wer": 0.102803738317757,
|
126 |
+
"step": 215
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 10.98,
|
130 |
+
"eval_cer": 0.03221512247071352,
|
131 |
+
"eval_loss": 0.22247014939785004,
|
132 |
+
"eval_runtime": 5.3965,
|
133 |
+
"eval_samples_per_second": 15.936,
|
134 |
+
"eval_steps_per_second": 2.038,
|
135 |
+
"eval_wer": 0.0911214953271028,
|
136 |
+
"step": 236
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 12.0,
|
140 |
+
"eval_cer": 0.033413205537806176,
|
141 |
+
"eval_loss": 0.21965597569942474,
|
142 |
+
"eval_runtime": 5.3359,
|
143 |
+
"eval_samples_per_second": 16.117,
|
144 |
+
"eval_steps_per_second": 2.062,
|
145 |
+
"eval_wer": 0.09813084112149532,
|
146 |
+
"step": 258
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 12.98,
|
150 |
+
"eval_cer": 0.032348242811501594,
|
151 |
+
"eval_loss": 0.2268439382314682,
|
152 |
+
"eval_runtime": 5.3114,
|
153 |
+
"eval_samples_per_second": 16.192,
|
154 |
+
"eval_steps_per_second": 2.071,
|
155 |
+
"eval_wer": 0.09190031152647975,
|
156 |
+
"step": 279
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 13.95,
|
160 |
+
"learning_rate": 2.5742857142857144e-05,
|
161 |
+
"loss": 0.2169,
|
162 |
+
"step": 300
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 14.0,
|
166 |
+
"eval_cer": 0.03301384451544196,
|
167 |
+
"eval_loss": 0.2250145524740219,
|
168 |
+
"eval_runtime": 5.3082,
|
169 |
+
"eval_samples_per_second": 16.201,
|
170 |
+
"eval_steps_per_second": 2.072,
|
171 |
+
"eval_wer": 0.09657320872274143,
|
172 |
+
"step": 301
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 14.98,
|
176 |
+
"eval_cer": 0.03367944621938232,
|
177 |
+
"eval_loss": 0.23428502678871155,
|
178 |
+
"eval_runtime": 5.3401,
|
179 |
+
"eval_samples_per_second": 16.105,
|
180 |
+
"eval_steps_per_second": 2.06,
|
181 |
+
"eval_wer": 0.09501557632398754,
|
182 |
+
"step": 322
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 16.0,
|
186 |
+
"eval_cer": 0.03288072417465389,
|
187 |
+
"eval_loss": 0.23504719138145447,
|
188 |
+
"eval_runtime": 5.3189,
|
189 |
+
"eval_samples_per_second": 16.169,
|
190 |
+
"eval_steps_per_second": 2.068,
|
191 |
+
"eval_wer": 0.09423676012461059,
|
192 |
+
"step": 344
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 16.98,
|
196 |
+
"eval_cer": 0.03194888178913738,
|
197 |
+
"eval_loss": 0.22562479972839355,
|
198 |
+
"eval_runtime": 5.2996,
|
199 |
+
"eval_samples_per_second": 16.228,
|
200 |
+
"eval_steps_per_second": 2.076,
|
201 |
+
"eval_wer": 0.09190031152647975,
|
202 |
+
"step": 365
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 18.0,
|
206 |
+
"eval_cer": 0.03075079872204473,
|
207 |
+
"eval_loss": 0.23361057043075562,
|
208 |
+
"eval_runtime": 5.3339,
|
209 |
+
"eval_samples_per_second": 16.123,
|
210 |
+
"eval_steps_per_second": 2.062,
|
211 |
+
"eval_wer": 0.08021806853582554,
|
212 |
+
"step": 387
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 18.6,
|
216 |
+
"learning_rate": 2.4314285714285714e-05,
|
217 |
+
"loss": 0.1634,
|
218 |
+
"step": 400
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 18.98,
|
222 |
+
"eval_cer": 0.030617678381256657,
|
223 |
+
"eval_loss": 0.2233453392982483,
|
224 |
+
"eval_runtime": 5.3405,
|
225 |
+
"eval_samples_per_second": 16.103,
|
226 |
+
"eval_steps_per_second": 2.06,
|
227 |
+
"eval_wer": 0.08255451713395638,
|
228 |
+
"step": 408
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 20.0,
|
232 |
+
"eval_cer": 0.030617678381256657,
|
233 |
+
"eval_loss": 0.23442576825618744,
|
234 |
+
"eval_runtime": 5.3434,
|
235 |
+
"eval_samples_per_second": 16.095,
|
236 |
+
"eval_steps_per_second": 2.059,
|
237 |
+
"eval_wer": 0.08255451713395638,
|
238 |
+
"step": 430
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 20.98,
|
242 |
+
"eval_cer": 0.030085197018104366,
|
243 |
+
"eval_loss": 0.2269764393568039,
|
244 |
+
"eval_runtime": 5.3287,
|
245 |
+
"eval_samples_per_second": 16.139,
|
246 |
+
"eval_steps_per_second": 2.064,
|
247 |
+
"eval_wer": 0.08177570093457943,
|
248 |
+
"step": 451
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 22.0,
|
252 |
+
"eval_cer": 0.030484558040468585,
|
253 |
+
"eval_loss": 0.22603558003902435,
|
254 |
+
"eval_runtime": 5.3048,
|
255 |
+
"eval_samples_per_second": 16.212,
|
256 |
+
"eval_steps_per_second": 2.074,
|
257 |
+
"eval_wer": 0.08566978193146417,
|
258 |
+
"step": 473
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 22.98,
|
262 |
+
"eval_cer": 0.030484558040468585,
|
263 |
+
"eval_loss": 0.24596618115901947,
|
264 |
+
"eval_runtime": 5.2757,
|
265 |
+
"eval_samples_per_second": 16.301,
|
266 |
+
"eval_steps_per_second": 2.085,
|
267 |
+
"eval_wer": 0.08411214953271028,
|
268 |
+
"step": 494
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 23.26,
|
272 |
+
"learning_rate": 2.2885714285714288e-05,
|
273 |
+
"loss": 0.1322,
|
274 |
+
"step": 500
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 24.0,
|
278 |
+
"eval_cer": 0.02915335463258786,
|
279 |
+
"eval_loss": 0.23429615795612335,
|
280 |
+
"eval_runtime": 5.2974,
|
281 |
+
"eval_samples_per_second": 16.234,
|
282 |
+
"eval_steps_per_second": 2.076,
|
283 |
+
"eval_wer": 0.07476635514018691,
|
284 |
+
"step": 516
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 24.98,
|
288 |
+
"eval_cer": 0.02968583599574015,
|
289 |
+
"eval_loss": 0.24553684890270233,
|
290 |
+
"eval_runtime": 5.3041,
|
291 |
+
"eval_samples_per_second": 16.214,
|
292 |
+
"eval_steps_per_second": 2.074,
|
293 |
+
"eval_wer": 0.0794392523364486,
|
294 |
+
"step": 537
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 26.0,
|
298 |
+
"eval_cer": 0.029286474973375932,
|
299 |
+
"eval_loss": 0.24292151629924774,
|
300 |
+
"eval_runtime": 5.2915,
|
301 |
+
"eval_samples_per_second": 16.252,
|
302 |
+
"eval_steps_per_second": 2.079,
|
303 |
+
"eval_wer": 0.07866043613707165,
|
304 |
+
"step": 559
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 26.98,
|
308 |
+
"eval_cer": 0.03035143769968051,
|
309 |
+
"eval_loss": 0.23371268808841705,
|
310 |
+
"eval_runtime": 5.3835,
|
311 |
+
"eval_samples_per_second": 15.975,
|
312 |
+
"eval_steps_per_second": 2.043,
|
313 |
+
"eval_wer": 0.08099688473520249,
|
314 |
+
"step": 580
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 27.91,
|
318 |
+
"learning_rate": 2.1457142857142858e-05,
|
319 |
+
"loss": 0.1123,
|
320 |
+
"step": 600
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 28.0,
|
324 |
+
"eval_cer": 0.029552715654952075,
|
325 |
+
"eval_loss": 0.24279381334781647,
|
326 |
+
"eval_runtime": 5.2948,
|
327 |
+
"eval_samples_per_second": 16.242,
|
328 |
+
"eval_steps_per_second": 2.077,
|
329 |
+
"eval_wer": 0.0794392523364486,
|
330 |
+
"step": 602
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 28.98,
|
334 |
+
"eval_cer": 0.029419595314164004,
|
335 |
+
"eval_loss": 0.2420278638601303,
|
336 |
+
"eval_runtime": 5.3074,
|
337 |
+
"eval_samples_per_second": 16.204,
|
338 |
+
"eval_steps_per_second": 2.073,
|
339 |
+
"eval_wer": 0.07554517133956386,
|
340 |
+
"step": 623
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 30.0,
|
344 |
+
"eval_cer": 0.02915335463258786,
|
345 |
+
"eval_loss": 0.24469688534736633,
|
346 |
+
"eval_runtime": 5.3053,
|
347 |
+
"eval_samples_per_second": 16.21,
|
348 |
+
"eval_steps_per_second": 2.073,
|
349 |
+
"eval_wer": 0.07866043613707165,
|
350 |
+
"step": 645
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 30.98,
|
354 |
+
"eval_cer": 0.02875399361022364,
|
355 |
+
"eval_loss": 0.249618262052536,
|
356 |
+
"eval_runtime": 5.316,
|
357 |
+
"eval_samples_per_second": 16.178,
|
358 |
+
"eval_steps_per_second": 2.069,
|
359 |
+
"eval_wer": 0.0763239875389408,
|
360 |
+
"step": 666
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 32.0,
|
364 |
+
"eval_cer": 0.029020234291799788,
|
365 |
+
"eval_loss": 0.2536907494068146,
|
366 |
+
"eval_runtime": 5.3669,
|
367 |
+
"eval_samples_per_second": 16.024,
|
368 |
+
"eval_steps_per_second": 2.05,
|
369 |
+
"eval_wer": 0.07866043613707165,
|
370 |
+
"step": 688
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 32.0,
|
374 |
+
"step": 688,
|
375 |
+
"total_flos": 1.751552315123992e+19,
|
376 |
+
"train_loss": 0.6797193247218465,
|
377 |
+
"train_runtime": 4402.1651,
|
378 |
+
"train_samples_per_second": 15.515,
|
379 |
+
"train_steps_per_second": 0.477
|
380 |
+
}
|
381 |
+
],
|
382 |
+
"max_steps": 2100,
|
383 |
+
"num_train_epochs": 100,
|
384 |
+
"total_flos": 1.751552315123992e+19,
|
385 |
+
"trial_name": null,
|
386 |
+
"trial_params": null
|
387 |
+
}
|