Update README.md
Browse files
README.md
CHANGED
@@ -27,4 +27,517 @@ Since this is a base model the IKM dataset greatly affects the output. The IKM d
|
|
27 |
### Response:
|
28 |
|
29 |
```
|
30 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
### Response:
|
28 |
|
29 |
```
|
30 |
+
---
|
31 |
+
|
32 |
+
```
|
33 |
+
[3731/5850 3:38:52 < 2:04:22, 0.28 it/s, Epoch 6.37/10]
|
34 |
+
Step Training Loss
|
35 |
+
1 10.109800
|
36 |
+
2 9.924600
|
37 |
+
3 9.919700
|
38 |
+
4 9.919100
|
39 |
+
5 9.917400
|
40 |
+
6 9.895900
|
41 |
+
7 9.891700
|
42 |
+
8 9.893500
|
43 |
+
9 9.917200
|
44 |
+
10 9.918800
|
45 |
+
11 10.056100
|
46 |
+
12 9.916200
|
47 |
+
13 9.911200
|
48 |
+
14 9.884300
|
49 |
+
15 9.909800
|
50 |
+
16 9.883800
|
51 |
+
17 9.883800
|
52 |
+
18 9.878300
|
53 |
+
19 9.904400
|
54 |
+
20 9.976400
|
55 |
+
21 10.061600
|
56 |
+
22 10.063300
|
57 |
+
23 9.876200
|
58 |
+
24 9.890900
|
59 |
+
25 9.873100
|
60 |
+
26 9.893700
|
61 |
+
27 9.869400
|
62 |
+
28 9.867100
|
63 |
+
29 9.863400
|
64 |
+
30 9.910400
|
65 |
+
31 9.882300
|
66 |
+
32 9.884100
|
67 |
+
33 10.023100
|
68 |
+
34 9.883500
|
69 |
+
35 9.854800
|
70 |
+
36 9.847400
|
71 |
+
37 9.851400
|
72 |
+
38 9.879200
|
73 |
+
39 9.845300
|
74 |
+
40 9.845700
|
75 |
+
41 9.876800
|
76 |
+
42 9.844600
|
77 |
+
43 9.848000
|
78 |
+
44 9.851900
|
79 |
+
45 10.038100
|
80 |
+
46 9.865000
|
81 |
+
47 9.845400
|
82 |
+
48 9.838900
|
83 |
+
49 9.860100
|
84 |
+
50 9.842500
|
85 |
+
51 9.830200
|
86 |
+
52 10.144100
|
87 |
+
53 9.825600
|
88 |
+
54 9.832000
|
89 |
+
55 9.835000
|
90 |
+
56 9.850900
|
91 |
+
57 9.990500
|
92 |
+
58 10.020100
|
93 |
+
59 10.014500
|
94 |
+
60 9.849600
|
95 |
+
61 9.877500
|
96 |
+
62 9.819900
|
97 |
+
63 9.818800
|
98 |
+
64 9.987100
|
99 |
+
65 9.952300
|
100 |
+
66 9.861900
|
101 |
+
67 9.814100
|
102 |
+
68 9.840600
|
103 |
+
69 9.809600
|
104 |
+
70 9.809600
|
105 |
+
71 9.976200
|
106 |
+
72 9.810600
|
107 |
+
73 9.805900
|
108 |
+
74 9.829400
|
109 |
+
75 9.830300
|
110 |
+
76 9.831500
|
111 |
+
77 9.802800
|
112 |
+
78 9.798200
|
113 |
+
79 9.824900
|
114 |
+
80 9.795100
|
115 |
+
81 9.794400
|
116 |
+
82 9.801200
|
117 |
+
83 9.794000
|
118 |
+
84 9.820400
|
119 |
+
85 9.790100
|
120 |
+
86 9.840400
|
121 |
+
87 9.809500
|
122 |
+
88 9.860000
|
123 |
+
89 9.807000
|
124 |
+
90 9.948200
|
125 |
+
91 9.779500
|
126 |
+
92 9.781800
|
127 |
+
93 9.802700
|
128 |
+
94 9.827700
|
129 |
+
95 9.798000
|
130 |
+
96 9.825900
|
131 |
+
97 9.966000
|
132 |
+
98 9.773000
|
133 |
+
99 9.775400
|
134 |
+
100 9.764400
|
135 |
+
101 9.766000
|
136 |
+
102 9.817500
|
137 |
+
103 9.795200
|
138 |
+
104 9.757900
|
139 |
+
105 9.753000
|
140 |
+
106 9.758200
|
141 |
+
107 9.753000
|
142 |
+
108 9.751700
|
143 |
+
109 9.784200
|
144 |
+
110 9.749700
|
145 |
+
111 9.748200
|
146 |
+
112 9.746200
|
147 |
+
113 9.797200
|
148 |
+
114 9.747000
|
149 |
+
115 9.913200
|
150 |
+
116 9.739100
|
151 |
+
117 9.769800
|
152 |
+
118 9.764500
|
153 |
+
119 9.736900
|
154 |
+
120 9.760500
|
155 |
+
121 9.795500
|
156 |
+
122 9.935300
|
157 |
+
123 10.079200
|
158 |
+
124 9.727200
|
159 |
+
125 9.732400
|
160 |
+
126 9.755800
|
161 |
+
127 9.755500
|
162 |
+
128 9.758900
|
163 |
+
129 9.732800
|
164 |
+
130 9.749600
|
165 |
+
131 9.922100
|
166 |
+
132 9.719800
|
167 |
+
133 9.716600
|
168 |
+
134 9.721900
|
169 |
+
135 9.718100
|
170 |
+
136 9.746300
|
171 |
+
137 9.868900
|
172 |
+
138 9.740800
|
173 |
+
139 9.715600
|
174 |
+
140 9.711000
|
175 |
+
141 9.744000
|
176 |
+
142 9.705100
|
177 |
+
143 9.734300
|
178 |
+
144 9.881400
|
179 |
+
145 9.764000
|
180 |
+
146 9.699800
|
181 |
+
147 9.855700
|
182 |
+
148 9.705600
|
183 |
+
149 9.903000
|
184 |
+
150 9.697000
|
185 |
+
151 9.732500
|
186 |
+
152 9.695000
|
187 |
+
153 9.901200
|
188 |
+
154 9.865600
|
189 |
+
155 9.686900
|
190 |
+
156 9.890300
|
191 |
+
157 9.714300
|
192 |
+
158 9.683900
|
193 |
+
159 9.856900
|
194 |
+
160 10.032500
|
195 |
+
161 9.677200
|
196 |
+
162 9.683600
|
197 |
+
163 9.679800
|
198 |
+
164 9.670600
|
199 |
+
165 9.698900
|
200 |
+
166 9.763100
|
201 |
+
167 9.669600
|
202 |
+
168 9.713800
|
203 |
+
169 9.699100
|
204 |
+
170 9.869700
|
205 |
+
171 9.844000
|
206 |
+
172 9.697700
|
207 |
+
173 9.667200
|
208 |
+
174 9.692600
|
209 |
+
175 9.670400
|
210 |
+
176 9.664200
|
211 |
+
177 9.689400
|
212 |
+
178 9.667900
|
213 |
+
179 9.685200
|
214 |
+
180 9.664700
|
215 |
+
181 9.861600
|
216 |
+
182 9.653600
|
217 |
+
183 9.652500
|
218 |
+
184 9.652700
|
219 |
+
185 9.643500
|
220 |
+
186 9.675400
|
221 |
+
187 9.685200
|
222 |
+
188 9.648800
|
223 |
+
189 9.671700
|
224 |
+
190 9.656900
|
225 |
+
191 9.734500
|
226 |
+
192 9.637900
|
227 |
+
193 9.635800
|
228 |
+
194 9.681400
|
229 |
+
195 9.669400
|
230 |
+
196 9.635200
|
231 |
+
197 9.667900
|
232 |
+
198 9.662100
|
233 |
+
199 9.809700
|
234 |
+
200 9.627500
|
235 |
+
201 9.691600
|
236 |
+
202 9.657200
|
237 |
+
203 9.689900
|
238 |
+
204 9.633700
|
239 |
+
205 9.624900
|
240 |
+
206 9.621900
|
241 |
+
207 9.655200
|
242 |
+
208 9.620300
|
243 |
+
209 9.619600
|
244 |
+
210 9.616800
|
245 |
+
211 9.614600
|
246 |
+
212 9.646700
|
247 |
+
213 9.612400
|
248 |
+
214 9.676200
|
249 |
+
215 9.672100
|
250 |
+
216 9.788300
|
251 |
+
217 9.611000
|
252 |
+
218 9.613900
|
253 |
+
219 9.632700
|
254 |
+
220 9.785800
|
255 |
+
221 9.595400
|
256 |
+
222 9.599600
|
257 |
+
223 9.627600
|
258 |
+
224 9.631600
|
259 |
+
225 9.627400
|
260 |
+
226 9.637000
|
261 |
+
227 9.626000
|
262 |
+
228 9.600800
|
263 |
+
229 9.658900
|
264 |
+
230 9.584400
|
265 |
+
231 9.621600
|
266 |
+
232 9.583600
|
267 |
+
233 9.582800
|
268 |
+
234 9.613900
|
269 |
+
235 9.580700
|
270 |
+
236 9.580600
|
271 |
+
237 9.580800
|
272 |
+
238 9.581300
|
273 |
+
239 9.788600
|
274 |
+
240 9.574100
|
275 |
+
241 9.580500
|
276 |
+
242 9.783500
|
277 |
+
243 9.574300
|
278 |
+
244 9.785300
|
279 |
+
245 9.599800
|
280 |
+
246 9.565500
|
281 |
+
247 9.563900
|
282 |
+
248 9.592900
|
283 |
+
249 9.592700
|
284 |
+
250 9.592200
|
285 |
+
251 9.573000
|
286 |
+
252 9.769800
|
287 |
+
253 9.913400
|
288 |
+
254 9.553100
|
289 |
+
255 9.549500
|
290 |
+
256 9.616300
|
291 |
+
257 9.566200
|
292 |
+
258 9.766200
|
293 |
+
259 9.592900
|
294 |
+
260 9.547900
|
295 |
+
261 9.576800
|
296 |
+
262 9.543000
|
297 |
+
263 9.543600
|
298 |
+
264 9.978600
|
299 |
+
265 9.570100
|
300 |
+
266 9.570400
|
301 |
+
267 9.716600
|
302 |
+
268 9.529900
|
303 |
+
269 9.579200
|
304 |
+
270 9.545500
|
305 |
+
271 9.531600
|
306 |
+
272 9.555500
|
307 |
+
273 9.559900
|
308 |
+
274 9.524000
|
309 |
+
275 9.889300
|
310 |
+
276 9.553700
|
311 |
+
277 9.534400
|
312 |
+
278 9.566800
|
313 |
+
279 9.518700
|
314 |
+
280 9.510600
|
315 |
+
281 9.528800
|
316 |
+
282 9.545800
|
317 |
+
283 9.693700
|
318 |
+
284 9.507500
|
319 |
+
285 9.511300
|
320 |
+
286 9.500100
|
321 |
+
|
322 |
+
3509 6.093600
|
323 |
+
3510 6.874700
|
324 |
+
3511 6.239500
|
325 |
+
3512 6.262400
|
326 |
+
3513 6.262000
|
327 |
+
3514 6.093200
|
328 |
+
3515 6.095400
|
329 |
+
3516 6.429600
|
330 |
+
3517 6.090800
|
331 |
+
3518 6.548000
|
332 |
+
3519 6.237100
|
333 |
+
3520 6.237000
|
334 |
+
3521 6.088900
|
335 |
+
3522 6.279700
|
336 |
+
3523 7.310300
|
337 |
+
3524 6.695300
|
338 |
+
3525 6.243000
|
339 |
+
3526 6.087100
|
340 |
+
3527 6.697000
|
341 |
+
3528 6.412400
|
342 |
+
3529 6.087100
|
343 |
+
3530 6.087000
|
344 |
+
3531 6.227500
|
345 |
+
3532 6.085900
|
346 |
+
3533 6.376200
|
347 |
+
3534 6.231600
|
348 |
+
3535 6.080500
|
349 |
+
3536 6.079100
|
350 |
+
3537 6.082800
|
351 |
+
3538 6.535800
|
352 |
+
3539 6.082300
|
353 |
+
3540 6.081300
|
354 |
+
3541 6.080600
|
355 |
+
3542 6.437900
|
356 |
+
3543 6.071800
|
357 |
+
3544 6.072500
|
358 |
+
3545 6.078300
|
359 |
+
3546 6.076700
|
360 |
+
3547 6.226500
|
361 |
+
3548 6.081000
|
362 |
+
3549 6.071000
|
363 |
+
3550 6.066900
|
364 |
+
3551 6.370600
|
365 |
+
3552 6.077900
|
366 |
+
3553 6.854100
|
367 |
+
3554 6.077300
|
368 |
+
3555 6.265500
|
369 |
+
3556 6.065600
|
370 |
+
3557 6.389000
|
371 |
+
3558 6.072500
|
372 |
+
3559 6.522500
|
373 |
+
3560 6.072400
|
374 |
+
3561 6.216900
|
375 |
+
3562 6.213700
|
376 |
+
3563 6.067200
|
377 |
+
3564 6.696500
|
378 |
+
3565 6.237500
|
379 |
+
3566 6.935300
|
380 |
+
3567 6.213700
|
381 |
+
3568 6.236400
|
382 |
+
3569 6.061000
|
383 |
+
3570 7.399200
|
384 |
+
3571 6.249000
|
385 |
+
3572 6.235700
|
386 |
+
3573 6.059400
|
387 |
+
3574 6.238300
|
388 |
+
3575 6.058600
|
389 |
+
3576 6.064600
|
390 |
+
3577 6.063100
|
391 |
+
3578 6.220400
|
392 |
+
3579 6.071700
|
393 |
+
3580 6.249400
|
394 |
+
3581 6.708400
|
395 |
+
3582 6.060400
|
396 |
+
3583 6.062800
|
397 |
+
3584 6.358300
|
398 |
+
3585 6.057700
|
399 |
+
3586 6.053700
|
400 |
+
3587 6.251000
|
401 |
+
3588 6.513700
|
402 |
+
3589 6.208500
|
403 |
+
3590 7.053200
|
404 |
+
3591 6.048200
|
405 |
+
3592 6.230400
|
406 |
+
3593 6.201200
|
407 |
+
3594 7.549800
|
408 |
+
3595 6.058900
|
409 |
+
3596 6.207100
|
410 |
+
3597 6.206900
|
411 |
+
3598 6.042500
|
412 |
+
3599 6.189200
|
413 |
+
3600 6.354800
|
414 |
+
3601 6.219600
|
415 |
+
3602 6.238400
|
416 |
+
3603 6.206500
|
417 |
+
3604 7.172000
|
418 |
+
3605 6.040700
|
419 |
+
3606 6.215000
|
420 |
+
3607 6.216300
|
421 |
+
3608 6.045200
|
422 |
+
3609 7.134800
|
423 |
+
3610 6.230800
|
424 |
+
3611 6.037500
|
425 |
+
3612 6.499700
|
426 |
+
3613 6.791900
|
427 |
+
3614 6.034000
|
428 |
+
3615 6.957900
|
429 |
+
3616 6.180000
|
430 |
+
3617 6.041000
|
431 |
+
3618 6.642900
|
432 |
+
3619 6.651100
|
433 |
+
3620 6.225300
|
434 |
+
3621 6.034700
|
435 |
+
3622 6.510700
|
436 |
+
3623 6.227100
|
437 |
+
3624 6.208200
|
438 |
+
3625 6.336000
|
439 |
+
3626 6.027800
|
440 |
+
3627 6.489200
|
441 |
+
3628 6.591400
|
442 |
+
3629 6.030200
|
443 |
+
3630 6.796800
|
444 |
+
3631 6.027400
|
445 |
+
3632 6.374700
|
446 |
+
3633 6.032100
|
447 |
+
3634 6.025900
|
448 |
+
3635 6.369400
|
449 |
+
3636 6.634500
|
450 |
+
3637 6.481200
|
451 |
+
3638 6.220300
|
452 |
+
3639 6.217200
|
453 |
+
3640 6.025200
|
454 |
+
3641 6.016900
|
455 |
+
3642 6.491400
|
456 |
+
3643 6.025600
|
457 |
+
3644 6.483400
|
458 |
+
3645 6.478600
|
459 |
+
3646 6.387600
|
460 |
+
3647 6.168300
|
461 |
+
3648 6.654600
|
462 |
+
3649 6.809700
|
463 |
+
3650 6.193000
|
464 |
+
3651 6.194500
|
465 |
+
3652 6.349200
|
466 |
+
3653 6.172500
|
467 |
+
3654 6.174200
|
468 |
+
3655 6.014800
|
469 |
+
3656 6.626400
|
470 |
+
3657 6.011500
|
471 |
+
3658 6.162000
|
472 |
+
3659 6.504300
|
473 |
+
3660 7.084900
|
474 |
+
3661 6.622300
|
475 |
+
3662 6.470700
|
476 |
+
3663 6.011600
|
477 |
+
3664 6.188300
|
478 |
+
3665 6.198700
|
479 |
+
3666 6.009900
|
480 |
+
3667 6.644700
|
481 |
+
3668 6.185000
|
482 |
+
3669 6.008600
|
483 |
+
3670 6.005900
|
484 |
+
3671 6.009200
|
485 |
+
3672 6.614900
|
486 |
+
3673 6.198300
|
487 |
+
3674 6.933100
|
488 |
+
3675 6.171800
|
489 |
+
3676 6.147500
|
490 |
+
3677 6.464300
|
491 |
+
3678 6.009500
|
492 |
+
3679 6.371400
|
493 |
+
3680 6.162100
|
494 |
+
3681 5.998900
|
495 |
+
3682 6.645100
|
496 |
+
3683 6.192900
|
497 |
+
3684 6.813800
|
498 |
+
3685 6.331100
|
499 |
+
3686 6.832200
|
500 |
+
3687 6.480900
|
501 |
+
3688 5.993200
|
502 |
+
3689 6.156100
|
503 |
+
3690 6.172600
|
504 |
+
3691 6.185400
|
505 |
+
3692 5.999600
|
506 |
+
3693 6.151900
|
507 |
+
3694 6.187100
|
508 |
+
3695 6.459900
|
509 |
+
3696 5.993100
|
510 |
+
3697 5.989900
|
511 |
+
3698 6.348300
|
512 |
+
3699 5.992500
|
513 |
+
3700 5.995900
|
514 |
+
3701 5.994900
|
515 |
+
3702 5.984900
|
516 |
+
3703 6.161600
|
517 |
+
3704 6.170100
|
518 |
+
3705 6.507000
|
519 |
+
3706 5.989200
|
520 |
+
3707 6.138800
|
521 |
+
3708 6.890600
|
522 |
+
3709 5.984500
|
523 |
+
3710 6.157900
|
524 |
+
3711 5.991600
|
525 |
+
3712 5.992200
|
526 |
+
3713 6.135400
|
527 |
+
3714 6.133900
|
528 |
+
3715 6.164000
|
529 |
+
3716 5.988100
|
530 |
+
3717 6.351000
|
531 |
+
3718 5.981300
|
532 |
+
3719 5.981000
|
533 |
+
3720 7.087300
|
534 |
+
3721 6.135400
|
535 |
+
3722 6.280900
|
536 |
+
3723 5.982800
|
537 |
+
3724 5.983800
|
538 |
+
3725 6.350100
|
539 |
+
3726 6.618500
|
540 |
+
3727 6.600100
|
541 |
+
3728 6.440600
|
542 |
+
3729 5.973800
|
543 |
+
```
|